SlideShare a Scribd company logo
1 of 69
Download to read offline
Big Data Pilot Demo Days
I-BiDaaS Application to the
Manufacturing Sector
Despina Kopanaki (FORTH) dkopanaki@ics.forth.gr
Diego Simoni (Trust-IT) d.simoni@trust-itservices.com
Dusan Jakovetic (UNSPMF) dusan.jakovetic@dmi.uns.ac.rs
Giuseppe Danilo Spennacchio (CRF) giuseppedanilo.spennacchio@crf.it
Leonardo Longhi (Sistematica) leonardo.longhi@grupposistematica.it
Webinar Speakers
2
Assistant Professor at the Department of
Mathematics and Informatics, Faculty of Sciences,
University of Novi Sad, Serbia
I-BiDaaS Scientific & Technical Manager.
Dr. Dušan Jakovetić
University of Novi Sad, Serbia
Flexible and Adaptive Systems Specialist at
Factory Innovation Department, CRF, Italy
Giuseppe Danilo
Spennacchio
CRF
Agenda
Big Data Pilot Demo Days. A joint effort by BigDataStack, I-BiDaaS,
Track & Know & Policy Cloud – Despina Kopanaki (FORTH)
I-BiDaaS overview – Dusan Jakovetic (UNSPMF)
CRF’s Pitches: Setting the requirements – Giuseppe Danilo
Spennacchio (CRF)
I-BiDaaS architecture: Scientific & Technical view; how it addresses
the requirements set by CRF – Dusan Jakovetic (UNSPMF)
Step by Step demonstration of I-BiDaaS solution and its application
to manufacturing sector – Giuseppe Danilo Spennacchio (CRF)
Introduction to the next webinar-Track & Know Insurance Sector:
Using mobility data to understand and mitigate risky driving
behaviour - Leonardo Longhi (Sistematica, Track & Know)
Questions & Answers
3
4
To which of our stakeholder types do you belong?
(Big Data Provider, Big Data Technology Provider, Manufacturing,
Research & Academia, Standardisation Body, other)
Are you working with Big Data?
(Yes, No)
Are you interested in Big Data Technologies to optimize your
customer experience?
(Yes, No, Maybe)
What is the main barrier or risk preventing you from
implementing Big Data analytical solutions in your
organization?
(Costs, Lack of expertise, Uncertain Value (ROI))
Questions
BDV PPP Summit 2020 went virtual
5
Why Big Data Pilot Demo Days?
The new data-driven industrial revolution highlights the need for big data
technologies to unlock the potential in various application domains.
BDV PPP projects I-BiDaaS, BigDataStack and Track & Know and Policy Cloud
deliver innovative technologies to address the emerging needs of data
operations and applications.
To fully exploit the sustainability of the developed technologies, the projects
onboarded pilots that exhibit their applicability in a wide variety of sectors.
In their third and final year, the projects are ready to demonstrate the
developed and implemented technologies to interested end-users from
industry as well as technology providers, for further adoption.
The recently started Policy Cloud project will highlight the adoption of
technologies developed by the more mature BDV PPP project BigDataStack,
showcasing its application for the policy making sector
6
BDV PPP Projects Join Forces
7
Industrial-Driven Big Data as a Self-Service Solution
Holistic stack for big data applications and
operations
Big Data for Mobility Tracking Knowledge
Extraction in Urban Areas
Cloud for Data-Driven Policy Management
BDV PPP projects joining forces to showcase application of innovative technologies in a
variety of domains, fostering futher adoption, contributing to Europe’s digital future.
Big Data Pilot Demo Days - A Series of Webinars
8
I-BiDaaS Application
to the Financial Sector
1
BigDataStack Connected
Consumer demo
Track & Know applied to
the fleet management
sector
2 3
456
7 8 9
A BigDataStack
Seafarer’s Tale on Real
Time Shipping
I-BiDaaS Application to
the Telecommunication
Sector
I-BiDaaS Application to the
manufacturing sector
Track & Know applied
to patient mobility in
the healthcare sector
Track & Know applied to
the automotive
insurance sector
Policy Cloud: Data
Driven Policies against
Radicalisation
Dusan Jakovetic
Ass. Professor, University of Novi Sad, Faculty of Sciences, Serbia;
I-BiDaaS Scientific & Technical Manager
I-BiDaaS Overview
I-BiDaaS Application to the Manufacturing
Sector
Thursday, July 9, 2020 - 14:00-15:00 CEST
Identity card
http://www.ibidaas.eu/ @Ibidaas https://www.linkedin.com/in/i-bidaas/
10
I-BiDaaS Consortium
1. FOUNDATION FOR RESEARCH AND TECHNOLOGY HELLAS (FORTH)
2. BARCELONA SUPERCOMPUTING CENTER - CENTRO NACIONAL DE
SUPERCOMPUTACION (BSC)
3. IBM ISRAEL - SCIENCE AND TECHNOLOGY LTD (IBM)
4. CENTRO RICERCHE FIAT SCPA (CRF)
5. SOFTWARE AG (SAG)
6. CAIXABANK, S.A (CAIXA)
7. THE UNIVERSITY OF MANCHESTER (UNIMAN)
8. ECOLE NATIONALE DES PONTS ET CHAUSSEES (ENPC)
9. ATOS SPAIN SA (ATOS)
10. AEGIS IT RESEARCH LTD (AEGIS)
11. INFORMATION TECHNOLOGY FOR MARKET LEADERSHIP (ITML)
12. University of Novi Sad Faculty of Sciences Serbia (UNSPMF)
13. TELEFONICA INVESTIGACION Y DESARROLLO SA (TID)
11
Motivation
12
EuropeanDataEconomy
Essential resource for growth,
competitiveness, innovation, job creation
and societal progress in general
Organizations leverage
data pools to drive value
The rise of the demand for platforms in the
market empowering end users to analyze
The convergence of internet of things
(IoT), cloud, and big data transforms our
economy and society
Self-service solutions are transformative
for organizations
Building a European Data Economy (Jan
2017)
Continue to struggle to turn opportunity
from big data into realized gains
Companies call upon expert analysts and
consultants to assist them
A completely new paradigm towards big
data analytics
The right knowledge, and insights decision-
makers need to make the right decisions.
Towards a common European data space
(Apr 2018)
Towards a thriving data-driven economy
(Jul 2014)
Digital Single Market
12
Our Vision
A complete and safe environment for
methodological big data experimentation
Tool and services to increase the
quality of data analytics
A Big Data as a Self-Service solution that helps
breaking industrial data silos and boosts EU's
data-driven economy
Tools and services for fast ingestion
and consolidation of both realistic
and fabricated data
Tools and services for the management
of heterogeneous infrastructures
including elasticity
Increases impact in research community
and contributes to industrial innovation
capacity
13
Project Statement
I-BiDaaS aims to empower users to easily utilize and interact
with big data technologies, by designing, building, and
demonstrating, a unified framework that:
significantly increases the speed of data analysis while coping
with the rate of data asset growth, and facilitates cross-
domain data-flow towards a thriving data-driven EU
economy.
I-BiDaaS will be tangibly validated by three real-world,
industry-lead experiments.
14
CAIXA
Enhance control of customers to online banking
Advanced analysis of bank transfer payment in
financial terminal
Analysis of relationships through IP address
CRF
Production process of aluminium casting
Maintenance and monitoring of production
assets
TID
Accurate location prediction with high traffic and
visibility
Optimization of placement of telecommunication
equipment
Quality of Service in Call Centers
Telecommunications
Industry
Banking/Finance Industry
Manufacturing Industry
Application / Experimentation
15
16
I-BiDaaS application domains
16
Giuseppe Danilo Spennacchio
Flexible and Adaptive Systems Specialist at Factory Innovation
Department, CRF, Italy
Setting the Pilot Requirements
I-BiDaaS Application to the Manufacturing
Sector
Thursday, July 09, 2020 - 14:00-15:00 CEST
18
CRF (Centro Ricerche Fiat)
one of the main private research centers in Italy
900 Employees
2,573 Patents
592 Inventions
1. to develop innovative power units, vehicle systems, materials, methods and processes to
improve the competitiveness of FCA products
founded in 1978
Orbassano
2. to represent FCA as part of European and national collaborative research, taking part in
pre-competitive research projects and promoting the development of a network of
contacts and partnerships on an international scale
3. to support FCA in enhancing the value of its intangible capital
The mission of CRF lies in three main goals:
19
Manufacturing
sector
Digitalisation
II000II00I00
III0000II00
I00II000
Networking
Automation
High value of
information
Data analysts &
technologists
Quality
improvement
Data
storage
Customer
satisfaction
Why do we need I-BiDaaS?
Industrial –Driven Big Data as a Self-Service Solution
q Lack of time to extract and analyse data due to fast rhythms of production
q Computerized production lines store large amounts of complex
structured/unstructured data
20
Why do we need I-BiDaaS?
q Data are strictly confidential
q Slowdown of data sharing due to security procedures
q Fast internal changes due to rescheduling production quantities and
component variations
q Data privacy: Anonymise data that can not be accessed or shared with external
qRequirements:
q Data cleaning: Identify incomplete, inaccurate and irrelevant parts of the data – dataset
generation
q Quality Improvement and PM: Exploit the I-BiDaaS platform to develop a methodology for quality and process
improvement and for Predictive Maintenance
q Data analysis and advanced visualisation tools: empower data providers decisions
qObjective:
Why do we need I-BiDaaS?
21
ACT PLAN
DOCHECK
§ Implement the plan:
§ Develop a
methodology
§ Update the standard
operating procedures
§ Define the identified
use cases
§ Provide data
§ Carry out the plan in
the I-BiDaaS Platform
§ Analyse the
results
§ Verify that we
have improved
the plan
§ Identify 2 use cases
§ Define the steps we
need to take
§ Enter in the I-BiDaaS
project
§ Breaking data silos while complying Regulation
22
Why do we need I-BiDaaS?
§ Integrate data from different sources/ levels
§ External/ internal departments
§ Data and method management (complex, huge)
§ Technical and business demonstration of data sharing between company owning the
data, company performing the analysis (CRF) and consortium partners
§ As-a-Service
§ Empower expert/ non expert usage of
huge quantities of data
§ Include new competences in data
analysis/ update automatically
(SMEs, partners)
Break inter and intra-sectorial data-silos, and
support data sharing, exchange, and
interoperability
Support methodical big data experimentation
by putting in place a safe data processing
environment
§ Competitiveness & Innovation
23
Why do we need I-BiDaaS?
§ Enable WCM (World Class Manufacturing) strategies
§ Efficiency
§ Enable real time or near real time data transfer/ data analysis / internal procedures
update
§ Reduce manufacturing costs due to quality and maintenance
issues
§ Reduce environmental impact by reducing material and
energy consumption
Problem
Identification
Data
cleaning
Dataset
Fabrication
Big Data
Analytics
• Raw Data
Acquisition
• Data
Anonymisation
Business
Goals
definition
• Problem Solving
• Development of Process
Control System
• Implmentation of Process
improvements
Step 1
Step 2
Step 3
Step 4
Step 5
Step 6
Step 7
Assessment and Analytics
Start
Implementation
Dusan Jakovetic
Assistant Professor, University of Novi Sad, Serbia;
I-BiDaaS Scientific & Technical Manager
Big Data Architecture
I-BiDaaS Application
to the Manufacturing Sector
July 9, 2020
• Expert mode
Analyze your DataUsers
• Import your data
• Self-service mode
Data
• Fabricate Data
• Stream & Batch Analytics
• Expert: Upload your code
• Self-service: Select an
algorithm from the pool
Results
• Visualize the results
• Share models
Do it
yourself
In a flexible
manner
Break data silos Safe environment Interact with Big Data
technologies
Increase speed of
data analysis
Cope with the rate of
data asset growth
Intra- and inter-
domain data-
flow
Benefits of using I-BiDaaS
• Co-develop mode
The I-BiDaaS Solution: Front-end
• Co-develop: custom end-
to-end application
• Tokenize data
25
The I-BiDaaS Solution:
Architecture/back-end
Medium to long term business decisions
Data
Fabrication
Platform
(IBM)
Refined
specifications
for data
fabrication
GPU-accelerated Analytics
(FORTH)
Apama Complex Event
Processing (SAG)
Streaming Analytics
Batch Processing
Advanced ML (UNSPMF)
COMPsProgramming
Model(BSC)
Query Partitioning
Infrastructurelayer: Private cloud; Commodity cluster; GPUs
Pre-defined
Queries
SQL-like
interface
Domain
Language
Programming
API
User Interface
Resource managementand orchestration (ATOS)
Advanced
Visualis.
Advanced IT services for
Big Data processing tasks;
Open source pool of ML
algorithms
Data ingestion
Programming
Interface /
Sequential
Programming
(AEGIS+SAG)
(AEGIS)
COMPsRuntime
(BSC)
Distributed
large scale
layer
Application layer
UniversalMessaging(SAG)
TestData
Fabrication(IBM)
Meta-
data;
Data
descri-
ption
Hecuba tools
(BSC)
Short term decisions
real time alerts
Model structure improvements
Learnedpatterns correlations
26
WP2:
Data, user interface, visualization
Technologies:
• IBM TDF
• SAG UM
• AEGIS AVT
Medium to long term business decisions
Data
Fabrication
Platform
(IBM)
Refined
specifications
for data
fabrication
GPU-accelerated Analytics
(FORTH)
Apama Complex Event
Processing (SAG)
Streaming Analytics
Batch Processing
Advanced ML (UNSPMF)
COMPs Programming
Model (BSC)
Query Partitioning
Infrastructure layer: Private cloud; Commodity cluster; GPUs
Pre-defined
Queries
SQL-like
interface
Domain
Language
Programming
API
User Interface
Resource management and orchestration (ATOS)
Advanced
Visualis.
Advanced IT services for
Big Data processing tasks;
Open source pool of ML
algorithms
Programming
Interface /
Sequential
Programming
(AEGIS+SAG)
(AEGIS)
COMPs Runtime
(BSC)
Distributed
large scale
layer
Application layer
UniversalMessaging(SAG)
DataFabrication
Platform(IBM)
Meta-
data;
Data
descri-
ption
Hecuba tools
(BSC)
Short term decisions
real time alerts
Model structure improvements
Learned patterns correlations
http://ibidaas.eu/tools
27
Medium to long term business decisions
Data
Fabrication
Platform
(IBM)
Refined
specifications
for data
fabrication
GPU-accelerated Analytics
(FORTH)
Apama Complex Event
Processing (SAG)
Streaming Analytics
Batch Processing
Advanced ML (UNSPMF)
COMPs Programming
Model (BSC)
Query Partitioning
Infrastructure layer: Private cloud; Commodity cluster; GPUs
Pre-defined
Queries
SQL-like
interface
Domain
Language
Programming
API
User Interface
Resource management and orchestration (ATOS)
Advanced
Visualis.
Advanced IT services for
Big Data processing tasks;
Open source pool of ML
algorithms
Programming
Interface /
Sequential
Programming
(AEGIS+SAG)
(AEGIS)
COMPs Runtime
(BSC)
Distributed
large scale
layer
Application layer
UniversalMessaging(SAG)
DataFabrication
Platform(IBM)
Meta-
data;
Data
descri-
ption
Hecuba tools
(BSC)
Short term decisions
real time alerts
Model structure improvements
Learned patterns correlations
WP3:
Batch analytics
Technologies:
• BSC COMPSs
• BSC Hecuba
• BSC Qbeast
• Advanced ML (UNSPMF)
http://ibidaas.eu/tools
28
Medium to long term business decisions
Data
Fabrication
Platform
(IBM)
Refined
specifications
for data
fabrication
GPU-accelerated Analytics
(FORTH)
Apama Complex Event
Processing (SAG)
Streaming Analytics
Batch Processing
Advanced ML (UNSPMF)
COMPs Programming
Model (BSC)
Query Partitioning
Infrastructure layer: Private cloud; Commodity cluster; GPUs
Pre-defined
Queries
SQL-like
interface
Domain
Language
Programming
API
User Interface
Resource management and orchestration (ATOS)
Advanced
Visualis.
Advanced IT services for
Big Data processing tasks;
Open source pool of ML
algorithms
Programming
Interface /
Sequential
Programming
(AEGIS+SAG)
(AEGIS)
COMPs Runtime
(BSC)
Distributed
large scale
layer
Application layer
UniversalMessaging(SAG)
DataFabrication
Platform(IBM)
Meta-
data;
Data
descri-
ption
Hecuba tools
(BSC)
Short term decisions
real time alerts
Model structure improvements
Learned patterns correlations
WP4:
Streaming analytics
Technologies:
• SAG Apama CEP
• FORTH GPU-accel. analytics
http://ibidaas.eu/tools
29
Medium to long term business decisions
Data
Fabrication
Platform
(IBM)
Refined
specifications
for data
fabrication
GPU-accelerated Analytics
(FORTH)
Apama Complex Event
Processing (SAG)
Streaming Analytics
Batch Processing
Advanced ML (UNSPMF)
COMPs Programming
Model (BSC)
Query Partitioning
Infrastructure layer: Private cloud; Commodity cluster; GPUs
Pre-defined
Queries
SQL-like
interface
Domain
Language
Programming
API
User Interface
Resource management and orchestration (ATOS)
Advanced
Visualis.
Advanced IT services for
Big Data processing tasks;
Open source pool of ML
algorithms
Programming
Interface /
Sequential
Programming
(AEGIS+SAG)
(AEGIS)
COMPs Runtime
(BSC)
Distributed
large scale
layer
Application layer
UniversalMessaging(SAG)
DataFabrication
Platform(IBM)
Meta-
data;
Data
descri-
ption
Hecuba tools
(BSC)
Short term decisions
real time alerts
Model structure improvements
Learned patterns correlations
WP5:
Resource mgmt & integration
Technologies:
• ATOS Resource mgmt
• ITML integration services
http://ibidaas.eu/tools
30
Data fabrication capabilities
Solution flexibility
Easy to code programming paradigm
High code reusability
Key Features & Innovations
https://www.ibidaas.eu/deliverables
31
GPU-accelerated analytics; Synergy of CEP and GPU-
accelerated analytics for streaming data
Feedback from analytics to data fabrication
Feedback from analytics to problem modelling
Demonstrated on use cases across 3 different data providers
and 3 different industries
https://www.ibidaas.eu/deliverables
Key Features & Innovations (Cont’d)
32
• Production Process of Aluminium Die Casting
• During the casting process of the engine blocks, molten aluminium is
injected into the die cavity
• Can we classify the quality levels of the engine block correctly when they
are produced?
• Can we improve the production process, by increasing the number of high
quality engine blocks and decreasing the number of lower quality engine
blocks?
I-BiDaaS applied to CRF use cases
33
• Challenges
• High volume dataset
• Unbalanced dataset
• Single model for two source of data
• Thermal images
• Sensor (tabular) data (piston speed, intensification pressures etc.)
• I-BiDaaS approach
• Joint neural network model with CNN and FCNN (PyTorch)
• CNN with 201 layers (DenseNet201) for images – pretrained &
non-trained model
• Fully Connected NN with 7 layers for sensor data
• Random under-sampling to produce a balanced dataset
Production process of aluminium die casting
34
• Architecture of the joint
neural network
• Good accuracy for different classes:
• Orange line: model trained on
full dataset - 73.54% accuracy
• Pink line: model trained on
balanced dataset - 54.06%
accuracy (better model on
relevant classes)
Production process of aluminium die casting
35
Production process of aluminium die casting
36
• Maintenance and monitoring of production assets
• Different sensors are installed on the production line
• Can we prevent faults before they happen?
• Can we see the trend of a sensor’s behavior across different days?
• Can we see the similarity between sensors ?
I-BiDaaS applied to CRF use cases
37
• Challenges
• High volume dataset (over 100 sensors, 26 months of
measurements)
• How to model the similar behavior?
• Unlabeled data
• I-BiDaas approach
• Pandas library for data preprocessing
• Time series per sensor with number of outliers per day
• Visualization
• Further analysis
• Rescaled time series pairwise distance
• Obtain the most similar sensors
Maintenance and monitoring of production assets
38
• Time series of
outliers for a sensor
• Time series of
measurements for a sensor
Maintenance and monitoring of production assets
39
• Histogram of similarity between sensors
Maintenance and monitoring of production assets
40
Maintenance and monitoring of production assets
41
Giuseppe Danilo Spennacchio
Flexible and Adaptive Systems Specialist at Factory Innovation
Department, CRF, Italy
Manufacturing Pilot: step by step
I-BiDaaS Application to the Manufacturing
Sector
Thursday, July 09, 2020 - 14:00-15:00 CEST
§ Anonymisation: result of elaboration is gathered in new anonymised files
with all information useful for analytics
§ Security: original data provided by plants are retrieved in the CRF server
§ Quality analysis: data and defects manually detected are elaborated
Current situation
43
§ Data analyses are executed in Factory Innovation Department (CRF)
data,
operator
and quality
information
periodically
reports
internal
analyses
all
information
processed
§ Data Analytics in CRF
§ Results: periodically discussion with manufacturers
§ Analytics lifecycle:
Data
anonymisation
Data
gathering
Data
Storage
Production
Site 1
CRF
I-BiDaaS solution
computerized
production
machine
component
Production Site 2
Areas
provided
with sensors
SCADA
MES
vehicle
Internal
analysis
Analytic & Visualisation tools
q Data fabrication
q Data cleaning
q Data analyses
q Data visualisation
Results
VM
CRF
Data
flow
VM
Results
Data flow
Data
flowImprovement of
the production
process
Data flow
I-BiDaaS Platform
44
CFR Data Roadmap
2018 2019 2020
Q1 Q2 Q3 Q4 Q1 Q2 Q3 Q4 Q1 Q2 Q3 Q4
M3
Preliminary
Definition of
Use Case
M6
Use Case
Consolidation
and definition of
dataset
M9
Definition of
dataset
characteristics,
format and first
structured
dataset
M12
Definition of
Rules for the
IBM’s Data
Fabrication
Tool
M15
Validation of
synthesized
data
M18
Hackathon
event in
Melfi
M21
CRF
Demo
M24
Provided a
new type of
data
(Thermal
data) for the
1°use case
M27
Progress on
analytics
M30
Progress on
visualisation
M33
Experimental
implementation
M36
45
IN
Molten
Aluminium
OUT
Cylinder
blocksDie
TC1 TC2
Die Parameters Data (.csv)PC
PC
Thermal images(.img)
Quality
Control
Quality Data (.csv)
PC
Complex process:
an enormous amount of
heterogeneous data such as
piston speed in the first and
second phase,
intensification pressures;
Temperatures, etc
Production Process of Aluminium Die Casting
46
Business Goal
Quality Process Improvement:
§ avoid decrease of quality level
§ prevent repairs and reworks
§ reduce scrap and waste
Use Case Goals
§ Develop high level algorithms
§ Identify and select critical
parameters
§ Provide a mode to quickly visualize
analyses results
Die Parameters
Data & Quality
Data
q collected and merged data -
Process Parameters
q anonymised data
q collected and converted
data in Thermal images &
Thermal values
Improvement of
the production
process
Plant CRF
I-BiDaaS Platform
q Analytic tools
q Advanced
Visualisation
tools
CRF
q Data fabrication
q Data cleaning
q Data analyses
q Data visualisation
Thermal Data
Data flow
Data flowResults
Virtual
Machine
Data flow
Virtual
Machine
Results
47
Production Process of Aluminium Die Casting – data flow
I-BiDaaS platform to easy utilise I-BiDaaS solutions developed by data
analysts and technologists.
48
Production Process of Aluminium Die Casting - demo
After login, we selects co-develop mode, in which the data source and analysis
algorithm are predefined.
49
Production Process of Aluminium Die Casting - demo
50
The Aluminium Die Casting use case is a complex industrial process with many
heterogeneous parameters. The co-develop mode allows to us to check data processing
in real time.
Production Process of Aluminium Die Casting - demo
A dynamic diagram will show the incoming streaming data in real-time, as well
as aggregations of them that are constantly updated, after pressing the top-left
button ‘Run Experiment’.
51
Production Process of Aluminium Die Casting - demo
52
We can visualise the trend of parameters and quickly check if there is
something of anomalous compared to the set values of parameters
Production Process of Aluminium Die Casting - demo
53
If we see something of anomalous, we can press on the button ‘Pause/Start’
and quickly visualise data trends
Production Process of Aluminium Die Casting - demo
we can visualise the parameter values for each classification level (0,1,2) press
on the corresponding button
54
Production Process of Aluminium Die Casting - demo
55
we can visualise the data table, that shows a colour- coded presentation of the
results according to a given dimension of data (classification level)
We can choose how many
items per page to visualise
Production Process of Aluminium Die Casting - demo
We can visualise in real time and quickly the sequence of engine block with their
level of classification
56
Production Process of Aluminium Die Casting - demo
Maintenance and Monitoring of production assets
57
Business Goal
Predictive Maintenance:
§ predict faults before they happen
§ predict unnecessary actions
(preventive or planned maintenance)
§ avoid micro or macro stoppages
§ predict retooling and refurbishing
Use Case Goals
§ collect, structure and analyse
sensor data with high level
algorithms
§ obtain thresholds for anomalous
measurements
§ create a structured foundational
database to be easily utilised to
check outlier detections for a
continuous and periodic control of
the service conditions (PM)
58
Maintenance and Monitoring of production assets
q The monitoring of vibrations is important to check the status of a machine
q The analysis of the trend of vibrations over time allows to predict the onset of
deterioration and to intervene in time before the failure
q Accelerometers are used for measuring vibration and shock on machines and basically
anything that moves
The continuous and periodic control of the service conditions of a machine is
known as Predictive Maintenance
Sensors:
q detect the change in the environment and
transfers these information to other systems
q convert a physical phenomenon into a
measurable analog value (or sometimes a digital
signal) which is human-readable and suitable for
a display or transmission for reading or further
processing
SCADA DATA
MES DATA
q Collected and anonymised
data
Methodology for
Predictive
Maintenance
Plant CRF
I-BiDaaS Platform
q Analytic tools
q Visualisation
tools
CRF
q Data fabrication
q Data cleaning
q Data analyses
q Data visualisation
Data flow
Data flowResults
Virtual
Machine
Data flow
Maintenance and Monitoring of the production assets –
data flow
Virtual
Machine
Results
59
Maintenance and Monitoring of production assets - demo
60
61
Maintenance and Monitoring of production assets - demo
Maintenance and Monitoring of production assets - demo
62
Maintenance and Monitoring of production assets. The co-develop mode
allows us to monitor the outlier time series for each sensor any day
Maintenance and Monitoring of production assets - demo
63
Structured foundational database to be easily utilised to check outliers for a
continuous and periodic control of the service conditions (Predictive Maintenance)
Maintenance and Monitoring of production assets - demo
64
Sensors - Categories
65
Accelerometer [mg] / Id sensor
Maintenance and Monitoring of production assets - demo
65
66
Anomalies number per day
Maintenance and Monitoring of production assets - demo
66
67
• Data has been transformed into separate time series - one
per sensor
• anomalous measurements
Maintenance and Monitoring of production assets - demo
67
Benefits KPIs
68
CRF benefits from I-BiDaaS
To improve the efficiency of manufacturing plants, by
getting the best performance from the machinery to
reduce production losses and achieve greater
competitiveness of the company
Increase of 1 - 1.5 % in current Overall
Equipment Effectiveness (OEE) and
decrease of 50 % in maintenance costs
To enhance production times, to reduce costs and,
consequently, to obtain results that satisfy manufacturers’
requests in terms of product quality, machine performance
and timing
To reduce time to produce decisions
To break data silos and achieve accuracy of new models
with respect to internal CRF models in use
Increase of 3-7 % of quality control level
related to good products and decrease of 1-
4% and 0-2 % of two quality control levels
related to defective products
From one month to real time
Increase of 6 % for the first use case and
20% for the second one
Questions?
Thank you!
Your feedback is valuable for us!
https://bit.ly/2O8YV8D

More Related Content

What's hot

Enterprise Architecture for MBSE and Virtual Manufacturing digital continuity...
Enterprise Architecture for MBSE and Virtual Manufacturing digital continuity...Enterprise Architecture for MBSE and Virtual Manufacturing digital continuity...
Enterprise Architecture for MBSE and Virtual Manufacturing digital continuity...
Dr Nicolas Figay
 
00_Atos_for_Media_16_9_V4[1]
00_Atos_for_Media_16_9_V4[1]00_Atos_for_Media_16_9_V4[1]
00_Atos_for_Media_16_9_V4[1]
Ray ffrench
 

What's hot (20)

Lange - Industrial Data Space – Digital Sovereignty over Data
Lange - Industrial Data Space – Digital Sovereignty over DataLange - Industrial Data Space – Digital Sovereignty over Data
Lange - Industrial Data Space – Digital Sovereignty over Data
 
Bhadale IT project list 2020
Bhadale IT project list 2020Bhadale IT project list 2020
Bhadale IT project list 2020
 
Industry 4.0 - Internet of Manufacturing
Industry 4.0 - Internet of ManufacturingIndustry 4.0 - Internet of Manufacturing
Industry 4.0 - Internet of Manufacturing
 
3D visualisation needs for CAD and PDM
3D visualisation needs for CAD and PDM3D visualisation needs for CAD and PDM
3D visualisation needs for CAD and PDM
 
Fraunhofer – SINTEF: towards an initiative on Data Sovereignty in Europe
Fraunhofer – SINTEF: towards an initiative on Data Sovereignty in EuropeFraunhofer – SINTEF: towards an initiative on Data Sovereignty in Europe
Fraunhofer – SINTEF: towards an initiative on Data Sovereignty in Europe
 
Industry 4.0 : Relevance to your industry
Industry 4.0 : Relevance to your industryIndustry 4.0 : Relevance to your industry
Industry 4.0 : Relevance to your industry
 
FIWARE Global Summit - MD4PROD
FIWARE Global Summit - MD4PRODFIWARE Global Summit - MD4PROD
FIWARE Global Summit - MD4PROD
 
Conférence Internet des objets IoT M2M - CCI Bordeaux - 02 04 2015 - presenta...
Conférence Internet des objets IoT M2M - CCI Bordeaux - 02 04 2015 - presenta...Conférence Internet des objets IoT M2M - CCI Bordeaux - 02 04 2015 - presenta...
Conférence Internet des objets IoT M2M - CCI Bordeaux - 02 04 2015 - presenta...
 
RDA ICT Technical Specifications
RDA ICT Technical SpecificationsRDA ICT Technical Specifications
RDA ICT Technical Specifications
 
MARKET PLACE_Catalogue_ICT
MARKET PLACE_Catalogue_ICTMARKET PLACE_Catalogue_ICT
MARKET PLACE_Catalogue_ICT
 
PTC Fast Facts
PTC Fast Facts PTC Fast Facts
PTC Fast Facts
 
Borqs Technologies Presentation 2021
Borqs Technologies Presentation 2021Borqs Technologies Presentation 2021
Borqs Technologies Presentation 2021
 
WM press release VIP Tower - 122017
WM press release VIP Tower - 122017WM press release VIP Tower - 122017
WM press release VIP Tower - 122017
 
Enterprise Architecture for MBSE and Virtual Manufacturing digital continuity...
Enterprise Architecture for MBSE and Virtual Manufacturing digital continuity...Enterprise Architecture for MBSE and Virtual Manufacturing digital continuity...
Enterprise Architecture for MBSE and Virtual Manufacturing digital continuity...
 
Industrial Data Space - Why we need a European Initiative on Data Sovereignty
Industrial Data Space - Why we need a European Initiative on Data SovereigntyIndustrial Data Space - Why we need a European Initiative on Data Sovereignty
Industrial Data Space - Why we need a European Initiative on Data Sovereignty
 
DХ Roadmap
DХ RoadmapDХ Roadmap
DХ Roadmap
 
Dirk Slama Keynote on the Internet of Things
Dirk Slama Keynote on the Internet of ThingsDirk Slama Keynote on the Internet of Things
Dirk Slama Keynote on the Internet of Things
 
A Multi-agent Approach for Processing Industrial Enterprise Data
A Multi-agent Approach for Processing Industrial Enterprise DataA Multi-agent Approach for Processing Industrial Enterprise Data
A Multi-agent Approach for Processing Industrial Enterprise Data
 
TEKK Tour Closing Session
TEKK Tour Closing SessionTEKK Tour Closing Session
TEKK Tour Closing Session
 
00_Atos_for_Media_16_9_V4[1]
00_Atos_for_Media_16_9_V4[1]00_Atos_for_Media_16_9_V4[1]
00_Atos_for_Media_16_9_V4[1]
 

Similar to BigDataPilotDemoDays - I BiDaaS Application to the Manufacturing Sector Webinar

Similar to BigDataPilotDemoDays - I BiDaaS Application to the Manufacturing Sector Webinar (20)

BigDataPilotDemoDays - I-BiDaaS Application to the Financial Sector Webinar
BigDataPilotDemoDays - I-BiDaaS Application to the Financial Sector WebinarBigDataPilotDemoDays - I-BiDaaS Application to the Financial Sector Webinar
BigDataPilotDemoDays - I-BiDaaS Application to the Financial Sector Webinar
 
Big Data Pilot Days
Big Data Pilot DaysBig Data Pilot Days
Big Data Pilot Days
 
Policy Cloud Data Driven - Policies against Radicalisation
Policy Cloud Data Driven - Policies against RadicalisationPolicy Cloud Data Driven - Policies against Radicalisation
Policy Cloud Data Driven - Policies against Radicalisation
 
Policy Cloud Data Driven Policies against Radicalisation
Policy Cloud Data Driven Policies against RadicalisationPolicy Cloud Data Driven Policies against Radicalisation
Policy Cloud Data Driven Policies against Radicalisation
 
IBM Think Milano
IBM Think MilanoIBM Think Milano
IBM Think Milano
 
Microservices: The Future-Proof Framework for IoT
Microservices: The Future-Proof Framework for IoTMicroservices: The Future-Proof Framework for IoT
Microservices: The Future-Proof Framework for IoT
 
Big Data Pilot Demo Days A Big DataStack Seafer's tale of Real-time Shipping
Big Data Pilot Demo Days A Big DataStack Seafer's tale of Real-time ShippingBig Data Pilot Demo Days A Big DataStack Seafer's tale of Real-time Shipping
Big Data Pilot Demo Days A Big DataStack Seafer's tale of Real-time Shipping
 
Internet of things
Internet of thingsInternet of things
Internet of things
 
Data sharing between private companies and research facilities
Data sharing between private companies and research facilitiesData sharing between private companies and research facilities
Data sharing between private companies and research facilities
 
2019 04-30 MIDIH for CONFAPI
2019 04-30 MIDIH for CONFAPI 2019 04-30 MIDIH for CONFAPI
2019 04-30 MIDIH for CONFAPI
 
Convertigo Low Code / No Code Platform
Convertigo Low Code / No Code PlatformConvertigo Low Code / No Code Platform
Convertigo Low Code / No Code Platform
 
CONFERENCIA: El impacto de la Tecnología en la optimización de la cadena de s...
CONFERENCIA: El impacto de la Tecnología en la optimización de la cadena de s...CONFERENCIA: El impacto de la Tecnología en la optimización de la cadena de s...
CONFERENCIA: El impacto de la Tecnología en la optimización de la cadena de s...
 
DataAquitaine February 2022
DataAquitaine February 2022DataAquitaine February 2022
DataAquitaine February 2022
 
Cloud Expo 2015: DICE: Developing Data-Intensive Cloud Applications with Iter...
Cloud Expo 2015: DICE: Developing Data-Intensive Cloud Applications with Iter...Cloud Expo 2015: DICE: Developing Data-Intensive Cloud Applications with Iter...
Cloud Expo 2015: DICE: Developing Data-Intensive Cloud Applications with Iter...
 
Mastercourse Hortibusiness
Mastercourse HortibusinessMastercourse Hortibusiness
Mastercourse Hortibusiness
 
DAY2_4.1_Jesper Vauvert_Digitalisation in EE_EN.pdf
DAY2_4.1_Jesper Vauvert_Digitalisation in EE_EN.pdfDAY2_4.1_Jesper Vauvert_Digitalisation in EE_EN.pdf
DAY2_4.1_Jesper Vauvert_Digitalisation in EE_EN.pdf
 
Idsa, smau, milano, 2019 10-24
Idsa, smau, milano, 2019 10-24Idsa, smau, milano, 2019 10-24
Idsa, smau, milano, 2019 10-24
 
Big data presentation, explanations and use cases in industrial sector
Big data presentation, explanations and use cases in industrial sectorBig data presentation, explanations and use cases in industrial sector
Big data presentation, explanations and use cases in industrial sector
 
NIIT and Denodo: Business Continuity Planning in the times of the Covid-19 Pa...
NIIT and Denodo: Business Continuity Planning in the times of the Covid-19 Pa...NIIT and Denodo: Business Continuity Planning in the times of the Covid-19 Pa...
NIIT and Denodo: Business Continuity Planning in the times of the Covid-19 Pa...
 
Real World IoT Architecture Use Cases
Real World IoT Architecture Use CasesReal World IoT Architecture Use Cases
Real World IoT Architecture Use Cases
 

More from Big Data Value Association

More from Big Data Value Association (20)

Data Privacy, Security in personal data sharing
Data Privacy, Security in personal data sharingData Privacy, Security in personal data sharing
Data Privacy, Security in personal data sharing
 
Key Modules for a trsuted and privacy preserving personal data marketplace
Key Modules for a trsuted and privacy preserving personal data marketplaceKey Modules for a trsuted and privacy preserving personal data marketplace
Key Modules for a trsuted and privacy preserving personal data marketplace
 
GDPR and Data Ethics considerations in personal data sharing
GDPR and Data Ethics considerations in personal data sharingGDPR and Data Ethics considerations in personal data sharing
GDPR and Data Ethics considerations in personal data sharing
 
Intro - Three pillars for building a Smart Data Ecosystem: Trust, Security an...
Intro - Three pillars for building a Smart Data Ecosystem: Trust, Security an...Intro - Three pillars for building a Smart Data Ecosystem: Trust, Security an...
Intro - Three pillars for building a Smart Data Ecosystem: Trust, Security an...
 
Three pillars for building a Smart Data Ecosystem: Trust, Security and Privacy
Three pillars for building a Smart Data Ecosystem: Trust, Security and PrivacyThree pillars for building a Smart Data Ecosystem: Trust, Security and Privacy
Three pillars for building a Smart Data Ecosystem: Trust, Security and Privacy
 
Market into context - Three pillars for building a Smart Data Ecosystem: Trus...
Market into context - Three pillars for building a Smart Data Ecosystem: Trus...Market into context - Three pillars for building a Smart Data Ecosystem: Trus...
Market into context - Three pillars for building a Smart Data Ecosystem: Trus...
 
BDV Skills Accreditation - Future of digital skills in Europe reskilling and ...
BDV Skills Accreditation - Future of digital skills in Europe reskilling and ...BDV Skills Accreditation - Future of digital skills in Europe reskilling and ...
BDV Skills Accreditation - Future of digital skills in Europe reskilling and ...
 
BDV Skills Accreditation - Big Data skilling in Emilia-Romagna
BDV Skills Accreditation - Big Data skilling in Emilia-Romagna BDV Skills Accreditation - Big Data skilling in Emilia-Romagna
BDV Skills Accreditation - Big Data skilling in Emilia-Romagna
 
BDV Skills Accreditation - EIT labels for professionals
BDV Skills Accreditation - EIT labels for professionalsBDV Skills Accreditation - EIT labels for professionals
BDV Skills Accreditation - EIT labels for professionals
 
BDV Skills Accreditation - Recognizing Data Science Skills with BDV Data Scie...
BDV Skills Accreditation - Recognizing Data Science Skills with BDV Data Scie...BDV Skills Accreditation - Recognizing Data Science Skills with BDV Data Scie...
BDV Skills Accreditation - Recognizing Data Science Skills with BDV Data Scie...
 
BDV Skills Accreditation - Objectives of the workshop
BDV Skills Accreditation - Objectives of the workshopBDV Skills Accreditation - Objectives of the workshop
BDV Skills Accreditation - Objectives of the workshop
 
BDV Skills Accreditation - Welcome introduction to the workshop
BDV Skills Accreditation - Welcome introduction to the workshopBDV Skills Accreditation - Welcome introduction to the workshop
BDV Skills Accreditation - Welcome introduction to the workshop
 
BDV Skills Accreditation - Definition and ensuring of digital roles and compe...
BDV Skills Accreditation - Definition and ensuring of digital roles and compe...BDV Skills Accreditation - Definition and ensuring of digital roles and compe...
BDV Skills Accreditation - Definition and ensuring of digital roles and compe...
 
Virtual BenchLearning - Data Bench Framework
Virtual BenchLearning - Data Bench FrameworkVirtual BenchLearning - Data Bench Framework
Virtual BenchLearning - Data Bench Framework
 
Virtual BenchLearning - DeepHealth - Needs & Requirements for Benchmarking
Virtual BenchLearning - DeepHealth - Needs & Requirements for BenchmarkingVirtual BenchLearning - DeepHealth - Needs & Requirements for Benchmarking
Virtual BenchLearning - DeepHealth - Needs & Requirements for Benchmarking
 
Virtual BenchLearning - I-BiDaaS - Industrial-Driven Big Data as a Self-Servi...
Virtual BenchLearning - I-BiDaaS - Industrial-Driven Big Data as a Self-Servi...Virtual BenchLearning - I-BiDaaS - Industrial-Driven Big Data as a Self-Servi...
Virtual BenchLearning - I-BiDaaS - Industrial-Driven Big Data as a Self-Servi...
 
Policy Cloud Data Driven Policies against Radicalisation - Technical Overview
Policy Cloud Data Driven Policies against Radicalisation - Technical OverviewPolicy Cloud Data Driven Policies against Radicalisation - Technical Overview
Policy Cloud Data Driven Policies against Radicalisation - Technical Overview
 
Policy Cloud Data Driven Policies against Radicalisation - Participatory poli...
Policy Cloud Data Driven Policies against Radicalisation - Participatory poli...Policy Cloud Data Driven Policies against Radicalisation - Participatory poli...
Policy Cloud Data Driven Policies against Radicalisation - Participatory poli...
 
BDVA i Spaces - What they are, how to become one, value and collaborations
BDVA i Spaces - What they are, how to become one, value and collaborationsBDVA i Spaces - What they are, how to become one, value and collaborations
BDVA i Spaces - What they are, how to become one, value and collaborations
 
BDVA i Spaces - ITA Aragón
BDVA i Spaces - ITA AragónBDVA i Spaces - ITA Aragón
BDVA i Spaces - ITA Aragón
 

Recently uploaded

一比一原版阿德莱德大学毕业证成绩单如何办理
一比一原版阿德莱德大学毕业证成绩单如何办理一比一原版阿德莱德大学毕业证成绩单如何办理
一比一原版阿德莱德大学毕业证成绩单如何办理
pyhepag
 
一比一原版纽卡斯尔大学毕业证成绩单如何办理
一比一原版纽卡斯尔大学毕业证成绩单如何办理一比一原版纽卡斯尔大学毕业证成绩单如何办理
一比一原版纽卡斯尔大学毕业证成绩单如何办理
cyebo
 
Exploratory Data Analysis - Dilip S.pptx
Exploratory Data Analysis - Dilip S.pptxExploratory Data Analysis - Dilip S.pptx
Exploratory Data Analysis - Dilip S.pptx
DilipVasan
 
Fuzzy Sets decision making under information of uncertainty
Fuzzy Sets decision making under information of uncertaintyFuzzy Sets decision making under information of uncertainty
Fuzzy Sets decision making under information of uncertainty
RafigAliyev2
 
一比一原版(Monash毕业证书)莫纳什大学毕业证成绩单如何办理
一比一原版(Monash毕业证书)莫纳什大学毕业证成绩单如何办理一比一原版(Monash毕业证书)莫纳什大学毕业证成绩单如何办理
一比一原版(Monash毕业证书)莫纳什大学毕业证成绩单如何办理
pyhepag
 
一比一原版麦考瑞大学毕业证成绩单如何办理
一比一原版麦考瑞大学毕业证成绩单如何办理一比一原版麦考瑞大学毕业证成绩单如何办理
一比一原版麦考瑞大学毕业证成绩单如何办理
cyebo
 
一比一原版西悉尼大学毕业证成绩单如何办理
一比一原版西悉尼大学毕业证成绩单如何办理一比一原版西悉尼大学毕业证成绩单如何办理
一比一原版西悉尼大学毕业证成绩单如何办理
pyhepag
 
一比一原版加利福尼亚大学尔湾分校毕业证成绩单如何办理
一比一原版加利福尼亚大学尔湾分校毕业证成绩单如何办理一比一原版加利福尼亚大学尔湾分校毕业证成绩单如何办理
一比一原版加利福尼亚大学尔湾分校毕业证成绩单如何办理
pyhepag
 
Abortion pills in Dammam Saudi Arabia// +966572737505 // buy cytotec
Abortion pills in Dammam Saudi Arabia// +966572737505 // buy cytotecAbortion pills in Dammam Saudi Arabia// +966572737505 // buy cytotec
Abortion pills in Dammam Saudi Arabia// +966572737505 // buy cytotec
Abortion pills in Riyadh +966572737505 get cytotec
 

Recently uploaded (20)

一比一原版阿德莱德大学毕业证成绩单如何办理
一比一原版阿德莱德大学毕业证成绩单如何办理一比一原版阿德莱德大学毕业证成绩单如何办理
一比一原版阿德莱德大学毕业证成绩单如何办理
 
Machine Learning for Accident Severity Prediction
Machine Learning for Accident Severity PredictionMachine Learning for Accident Severity Prediction
Machine Learning for Accident Severity Prediction
 
How can I successfully sell my pi coins in Philippines?
How can I successfully sell my pi coins in Philippines?How can I successfully sell my pi coins in Philippines?
How can I successfully sell my pi coins in Philippines?
 
一比一原版纽卡斯尔大学毕业证成绩单如何办理
一比一原版纽卡斯尔大学毕业证成绩单如何办理一比一原版纽卡斯尔大学毕业证成绩单如何办理
一比一原版纽卡斯尔大学毕业证成绩单如何办理
 
Easy and simple project file on mp online
Easy and simple project file on mp onlineEasy and simple project file on mp online
Easy and simple project file on mp online
 
Exploratory Data Analysis - Dilip S.pptx
Exploratory Data Analysis - Dilip S.pptxExploratory Data Analysis - Dilip S.pptx
Exploratory Data Analysis - Dilip S.pptx
 
Atlantic Grupa Case Study (Mintec Data AI)
Atlantic Grupa Case Study (Mintec Data AI)Atlantic Grupa Case Study (Mintec Data AI)
Atlantic Grupa Case Study (Mintec Data AI)
 
MALL CUSTOMER SEGMENTATION USING K-MEANS CLUSTERING.pptx
MALL CUSTOMER SEGMENTATION USING K-MEANS CLUSTERING.pptxMALL CUSTOMER SEGMENTATION USING K-MEANS CLUSTERING.pptx
MALL CUSTOMER SEGMENTATION USING K-MEANS CLUSTERING.pptx
 
Fuzzy Sets decision making under information of uncertainty
Fuzzy Sets decision making under information of uncertaintyFuzzy Sets decision making under information of uncertainty
Fuzzy Sets decision making under information of uncertainty
 
Slip-and-fall Injuries: Top Workers' Comp Claims
Slip-and-fall Injuries: Top Workers' Comp ClaimsSlip-and-fall Injuries: Top Workers' Comp Claims
Slip-and-fall Injuries: Top Workers' Comp Claims
 
一比一原版(Monash毕业证书)莫纳什大学毕业证成绩单如何办理
一比一原版(Monash毕业证书)莫纳什大学毕业证成绩单如何办理一比一原版(Monash毕业证书)莫纳什大学毕业证成绩单如何办理
一比一原版(Monash毕业证书)莫纳什大学毕业证成绩单如何办理
 
一比一原版麦考瑞大学毕业证成绩单如何办理
一比一原版麦考瑞大学毕业证成绩单如何办理一比一原版麦考瑞大学毕业证成绩单如何办理
一比一原版麦考瑞大学毕业证成绩单如何办理
 
how can i exchange pi coins for others currency like Bitcoin
how can i exchange pi coins for others currency like Bitcoinhow can i exchange pi coins for others currency like Bitcoin
how can i exchange pi coins for others currency like Bitcoin
 
一比一原版西悉尼大学毕业证成绩单如何办理
一比一原版西悉尼大学毕业证成绩单如何办理一比一原版西悉尼大学毕业证成绩单如何办理
一比一原版西悉尼大学毕业证成绩单如何办理
 
Artificial_General_Intelligence__storm_gen_article.pdf
Artificial_General_Intelligence__storm_gen_article.pdfArtificial_General_Intelligence__storm_gen_article.pdf
Artificial_General_Intelligence__storm_gen_article.pdf
 
Pre-ProductionImproveddsfjgndflghtgg.pptx
Pre-ProductionImproveddsfjgndflghtgg.pptxPre-ProductionImproveddsfjgndflghtgg.pptx
Pre-ProductionImproveddsfjgndflghtgg.pptx
 
一比一原版加利福尼亚大学尔湾分校毕业证成绩单如何办理
一比一原版加利福尼亚大学尔湾分校毕业证成绩单如何办理一比一原版加利福尼亚大学尔湾分校毕业证成绩单如何办理
一比一原版加利福尼亚大学尔湾分校毕业证成绩单如何办理
 
How I opened a fake bank account and didn't go to prison
How I opened a fake bank account and didn't go to prisonHow I opened a fake bank account and didn't go to prison
How I opened a fake bank account and didn't go to prison
 
Abortion pills in Dammam Saudi Arabia// +966572737505 // buy cytotec
Abortion pills in Dammam Saudi Arabia// +966572737505 // buy cytotecAbortion pills in Dammam Saudi Arabia// +966572737505 // buy cytotec
Abortion pills in Dammam Saudi Arabia// +966572737505 // buy cytotec
 
AI Imagen for data-storytelling Infographics.pdf
AI Imagen for data-storytelling Infographics.pdfAI Imagen for data-storytelling Infographics.pdf
AI Imagen for data-storytelling Infographics.pdf
 

BigDataPilotDemoDays - I BiDaaS Application to the Manufacturing Sector Webinar

  • 1. Big Data Pilot Demo Days I-BiDaaS Application to the Manufacturing Sector Despina Kopanaki (FORTH) dkopanaki@ics.forth.gr Diego Simoni (Trust-IT) d.simoni@trust-itservices.com Dusan Jakovetic (UNSPMF) dusan.jakovetic@dmi.uns.ac.rs Giuseppe Danilo Spennacchio (CRF) giuseppedanilo.spennacchio@crf.it Leonardo Longhi (Sistematica) leonardo.longhi@grupposistematica.it
  • 2. Webinar Speakers 2 Assistant Professor at the Department of Mathematics and Informatics, Faculty of Sciences, University of Novi Sad, Serbia I-BiDaaS Scientific & Technical Manager. Dr. Dušan Jakovetić University of Novi Sad, Serbia Flexible and Adaptive Systems Specialist at Factory Innovation Department, CRF, Italy Giuseppe Danilo Spennacchio CRF
  • 3. Agenda Big Data Pilot Demo Days. A joint effort by BigDataStack, I-BiDaaS, Track & Know & Policy Cloud – Despina Kopanaki (FORTH) I-BiDaaS overview – Dusan Jakovetic (UNSPMF) CRF’s Pitches: Setting the requirements – Giuseppe Danilo Spennacchio (CRF) I-BiDaaS architecture: Scientific & Technical view; how it addresses the requirements set by CRF – Dusan Jakovetic (UNSPMF) Step by Step demonstration of I-BiDaaS solution and its application to manufacturing sector – Giuseppe Danilo Spennacchio (CRF) Introduction to the next webinar-Track & Know Insurance Sector: Using mobility data to understand and mitigate risky driving behaviour - Leonardo Longhi (Sistematica, Track & Know) Questions & Answers 3
  • 4. 4 To which of our stakeholder types do you belong? (Big Data Provider, Big Data Technology Provider, Manufacturing, Research & Academia, Standardisation Body, other) Are you working with Big Data? (Yes, No) Are you interested in Big Data Technologies to optimize your customer experience? (Yes, No, Maybe) What is the main barrier or risk preventing you from implementing Big Data analytical solutions in your organization? (Costs, Lack of expertise, Uncertain Value (ROI)) Questions
  • 5. BDV PPP Summit 2020 went virtual 5
  • 6. Why Big Data Pilot Demo Days? The new data-driven industrial revolution highlights the need for big data technologies to unlock the potential in various application domains. BDV PPP projects I-BiDaaS, BigDataStack and Track & Know and Policy Cloud deliver innovative technologies to address the emerging needs of data operations and applications. To fully exploit the sustainability of the developed technologies, the projects onboarded pilots that exhibit their applicability in a wide variety of sectors. In their third and final year, the projects are ready to demonstrate the developed and implemented technologies to interested end-users from industry as well as technology providers, for further adoption. The recently started Policy Cloud project will highlight the adoption of technologies developed by the more mature BDV PPP project BigDataStack, showcasing its application for the policy making sector 6
  • 7. BDV PPP Projects Join Forces 7 Industrial-Driven Big Data as a Self-Service Solution Holistic stack for big data applications and operations Big Data for Mobility Tracking Knowledge Extraction in Urban Areas Cloud for Data-Driven Policy Management BDV PPP projects joining forces to showcase application of innovative technologies in a variety of domains, fostering futher adoption, contributing to Europe’s digital future.
  • 8. Big Data Pilot Demo Days - A Series of Webinars 8 I-BiDaaS Application to the Financial Sector 1 BigDataStack Connected Consumer demo Track & Know applied to the fleet management sector 2 3 456 7 8 9 A BigDataStack Seafarer’s Tale on Real Time Shipping I-BiDaaS Application to the Telecommunication Sector I-BiDaaS Application to the manufacturing sector Track & Know applied to patient mobility in the healthcare sector Track & Know applied to the automotive insurance sector Policy Cloud: Data Driven Policies against Radicalisation
  • 9. Dusan Jakovetic Ass. Professor, University of Novi Sad, Faculty of Sciences, Serbia; I-BiDaaS Scientific & Technical Manager I-BiDaaS Overview I-BiDaaS Application to the Manufacturing Sector Thursday, July 9, 2020 - 14:00-15:00 CEST
  • 10. Identity card http://www.ibidaas.eu/ @Ibidaas https://www.linkedin.com/in/i-bidaas/ 10
  • 11. I-BiDaaS Consortium 1. FOUNDATION FOR RESEARCH AND TECHNOLOGY HELLAS (FORTH) 2. BARCELONA SUPERCOMPUTING CENTER - CENTRO NACIONAL DE SUPERCOMPUTACION (BSC) 3. IBM ISRAEL - SCIENCE AND TECHNOLOGY LTD (IBM) 4. CENTRO RICERCHE FIAT SCPA (CRF) 5. SOFTWARE AG (SAG) 6. CAIXABANK, S.A (CAIXA) 7. THE UNIVERSITY OF MANCHESTER (UNIMAN) 8. ECOLE NATIONALE DES PONTS ET CHAUSSEES (ENPC) 9. ATOS SPAIN SA (ATOS) 10. AEGIS IT RESEARCH LTD (AEGIS) 11. INFORMATION TECHNOLOGY FOR MARKET LEADERSHIP (ITML) 12. University of Novi Sad Faculty of Sciences Serbia (UNSPMF) 13. TELEFONICA INVESTIGACION Y DESARROLLO SA (TID) 11
  • 12. Motivation 12 EuropeanDataEconomy Essential resource for growth, competitiveness, innovation, job creation and societal progress in general Organizations leverage data pools to drive value The rise of the demand for platforms in the market empowering end users to analyze The convergence of internet of things (IoT), cloud, and big data transforms our economy and society Self-service solutions are transformative for organizations Building a European Data Economy (Jan 2017) Continue to struggle to turn opportunity from big data into realized gains Companies call upon expert analysts and consultants to assist them A completely new paradigm towards big data analytics The right knowledge, and insights decision- makers need to make the right decisions. Towards a common European data space (Apr 2018) Towards a thriving data-driven economy (Jul 2014) Digital Single Market 12
  • 13. Our Vision A complete and safe environment for methodological big data experimentation Tool and services to increase the quality of data analytics A Big Data as a Self-Service solution that helps breaking industrial data silos and boosts EU's data-driven economy Tools and services for fast ingestion and consolidation of both realistic and fabricated data Tools and services for the management of heterogeneous infrastructures including elasticity Increases impact in research community and contributes to industrial innovation capacity 13
  • 14. Project Statement I-BiDaaS aims to empower users to easily utilize and interact with big data technologies, by designing, building, and demonstrating, a unified framework that: significantly increases the speed of data analysis while coping with the rate of data asset growth, and facilitates cross- domain data-flow towards a thriving data-driven EU economy. I-BiDaaS will be tangibly validated by three real-world, industry-lead experiments. 14
  • 15. CAIXA Enhance control of customers to online banking Advanced analysis of bank transfer payment in financial terminal Analysis of relationships through IP address CRF Production process of aluminium casting Maintenance and monitoring of production assets TID Accurate location prediction with high traffic and visibility Optimization of placement of telecommunication equipment Quality of Service in Call Centers Telecommunications Industry Banking/Finance Industry Manufacturing Industry Application / Experimentation 15
  • 17. Giuseppe Danilo Spennacchio Flexible and Adaptive Systems Specialist at Factory Innovation Department, CRF, Italy Setting the Pilot Requirements I-BiDaaS Application to the Manufacturing Sector Thursday, July 09, 2020 - 14:00-15:00 CEST
  • 18. 18 CRF (Centro Ricerche Fiat) one of the main private research centers in Italy 900 Employees 2,573 Patents 592 Inventions 1. to develop innovative power units, vehicle systems, materials, methods and processes to improve the competitiveness of FCA products founded in 1978 Orbassano 2. to represent FCA as part of European and national collaborative research, taking part in pre-competitive research projects and promoting the development of a network of contacts and partnerships on an international scale 3. to support FCA in enhancing the value of its intangible capital The mission of CRF lies in three main goals:
  • 19. 19 Manufacturing sector Digitalisation II000II00I00 III0000II00 I00II000 Networking Automation High value of information Data analysts & technologists Quality improvement Data storage Customer satisfaction Why do we need I-BiDaaS? Industrial –Driven Big Data as a Self-Service Solution
  • 20. q Lack of time to extract and analyse data due to fast rhythms of production q Computerized production lines store large amounts of complex structured/unstructured data 20 Why do we need I-BiDaaS? q Data are strictly confidential q Slowdown of data sharing due to security procedures q Fast internal changes due to rescheduling production quantities and component variations q Data privacy: Anonymise data that can not be accessed or shared with external qRequirements: q Data cleaning: Identify incomplete, inaccurate and irrelevant parts of the data – dataset generation q Quality Improvement and PM: Exploit the I-BiDaaS platform to develop a methodology for quality and process improvement and for Predictive Maintenance q Data analysis and advanced visualisation tools: empower data providers decisions qObjective:
  • 21. Why do we need I-BiDaaS? 21 ACT PLAN DOCHECK § Implement the plan: § Develop a methodology § Update the standard operating procedures § Define the identified use cases § Provide data § Carry out the plan in the I-BiDaaS Platform § Analyse the results § Verify that we have improved the plan § Identify 2 use cases § Define the steps we need to take § Enter in the I-BiDaaS project
  • 22. § Breaking data silos while complying Regulation 22 Why do we need I-BiDaaS? § Integrate data from different sources/ levels § External/ internal departments § Data and method management (complex, huge) § Technical and business demonstration of data sharing between company owning the data, company performing the analysis (CRF) and consortium partners § As-a-Service § Empower expert/ non expert usage of huge quantities of data § Include new competences in data analysis/ update automatically (SMEs, partners) Break inter and intra-sectorial data-silos, and support data sharing, exchange, and interoperability Support methodical big data experimentation by putting in place a safe data processing environment
  • 23. § Competitiveness & Innovation 23 Why do we need I-BiDaaS? § Enable WCM (World Class Manufacturing) strategies § Efficiency § Enable real time or near real time data transfer/ data analysis / internal procedures update § Reduce manufacturing costs due to quality and maintenance issues § Reduce environmental impact by reducing material and energy consumption Problem Identification Data cleaning Dataset Fabrication Big Data Analytics • Raw Data Acquisition • Data Anonymisation Business Goals definition • Problem Solving • Development of Process Control System • Implmentation of Process improvements Step 1 Step 2 Step 3 Step 4 Step 5 Step 6 Step 7 Assessment and Analytics Start Implementation
  • 24. Dusan Jakovetic Assistant Professor, University of Novi Sad, Serbia; I-BiDaaS Scientific & Technical Manager Big Data Architecture I-BiDaaS Application to the Manufacturing Sector July 9, 2020
  • 25. • Expert mode Analyze your DataUsers • Import your data • Self-service mode Data • Fabricate Data • Stream & Batch Analytics • Expert: Upload your code • Self-service: Select an algorithm from the pool Results • Visualize the results • Share models Do it yourself In a flexible manner Break data silos Safe environment Interact with Big Data technologies Increase speed of data analysis Cope with the rate of data asset growth Intra- and inter- domain data- flow Benefits of using I-BiDaaS • Co-develop mode The I-BiDaaS Solution: Front-end • Co-develop: custom end- to-end application • Tokenize data 25
  • 26. The I-BiDaaS Solution: Architecture/back-end Medium to long term business decisions Data Fabrication Platform (IBM) Refined specifications for data fabrication GPU-accelerated Analytics (FORTH) Apama Complex Event Processing (SAG) Streaming Analytics Batch Processing Advanced ML (UNSPMF) COMPsProgramming Model(BSC) Query Partitioning Infrastructurelayer: Private cloud; Commodity cluster; GPUs Pre-defined Queries SQL-like interface Domain Language Programming API User Interface Resource managementand orchestration (ATOS) Advanced Visualis. Advanced IT services for Big Data processing tasks; Open source pool of ML algorithms Data ingestion Programming Interface / Sequential Programming (AEGIS+SAG) (AEGIS) COMPsRuntime (BSC) Distributed large scale layer Application layer UniversalMessaging(SAG) TestData Fabrication(IBM) Meta- data; Data descri- ption Hecuba tools (BSC) Short term decisions real time alerts Model structure improvements Learnedpatterns correlations 26
  • 27. WP2: Data, user interface, visualization Technologies: • IBM TDF • SAG UM • AEGIS AVT Medium to long term business decisions Data Fabrication Platform (IBM) Refined specifications for data fabrication GPU-accelerated Analytics (FORTH) Apama Complex Event Processing (SAG) Streaming Analytics Batch Processing Advanced ML (UNSPMF) COMPs Programming Model (BSC) Query Partitioning Infrastructure layer: Private cloud; Commodity cluster; GPUs Pre-defined Queries SQL-like interface Domain Language Programming API User Interface Resource management and orchestration (ATOS) Advanced Visualis. Advanced IT services for Big Data processing tasks; Open source pool of ML algorithms Programming Interface / Sequential Programming (AEGIS+SAG) (AEGIS) COMPs Runtime (BSC) Distributed large scale layer Application layer UniversalMessaging(SAG) DataFabrication Platform(IBM) Meta- data; Data descri- ption Hecuba tools (BSC) Short term decisions real time alerts Model structure improvements Learned patterns correlations http://ibidaas.eu/tools 27
  • 28. Medium to long term business decisions Data Fabrication Platform (IBM) Refined specifications for data fabrication GPU-accelerated Analytics (FORTH) Apama Complex Event Processing (SAG) Streaming Analytics Batch Processing Advanced ML (UNSPMF) COMPs Programming Model (BSC) Query Partitioning Infrastructure layer: Private cloud; Commodity cluster; GPUs Pre-defined Queries SQL-like interface Domain Language Programming API User Interface Resource management and orchestration (ATOS) Advanced Visualis. Advanced IT services for Big Data processing tasks; Open source pool of ML algorithms Programming Interface / Sequential Programming (AEGIS+SAG) (AEGIS) COMPs Runtime (BSC) Distributed large scale layer Application layer UniversalMessaging(SAG) DataFabrication Platform(IBM) Meta- data; Data descri- ption Hecuba tools (BSC) Short term decisions real time alerts Model structure improvements Learned patterns correlations WP3: Batch analytics Technologies: • BSC COMPSs • BSC Hecuba • BSC Qbeast • Advanced ML (UNSPMF) http://ibidaas.eu/tools 28
  • 29. Medium to long term business decisions Data Fabrication Platform (IBM) Refined specifications for data fabrication GPU-accelerated Analytics (FORTH) Apama Complex Event Processing (SAG) Streaming Analytics Batch Processing Advanced ML (UNSPMF) COMPs Programming Model (BSC) Query Partitioning Infrastructure layer: Private cloud; Commodity cluster; GPUs Pre-defined Queries SQL-like interface Domain Language Programming API User Interface Resource management and orchestration (ATOS) Advanced Visualis. Advanced IT services for Big Data processing tasks; Open source pool of ML algorithms Programming Interface / Sequential Programming (AEGIS+SAG) (AEGIS) COMPs Runtime (BSC) Distributed large scale layer Application layer UniversalMessaging(SAG) DataFabrication Platform(IBM) Meta- data; Data descri- ption Hecuba tools (BSC) Short term decisions real time alerts Model structure improvements Learned patterns correlations WP4: Streaming analytics Technologies: • SAG Apama CEP • FORTH GPU-accel. analytics http://ibidaas.eu/tools 29
  • 30. Medium to long term business decisions Data Fabrication Platform (IBM) Refined specifications for data fabrication GPU-accelerated Analytics (FORTH) Apama Complex Event Processing (SAG) Streaming Analytics Batch Processing Advanced ML (UNSPMF) COMPs Programming Model (BSC) Query Partitioning Infrastructure layer: Private cloud; Commodity cluster; GPUs Pre-defined Queries SQL-like interface Domain Language Programming API User Interface Resource management and orchestration (ATOS) Advanced Visualis. Advanced IT services for Big Data processing tasks; Open source pool of ML algorithms Programming Interface / Sequential Programming (AEGIS+SAG) (AEGIS) COMPs Runtime (BSC) Distributed large scale layer Application layer UniversalMessaging(SAG) DataFabrication Platform(IBM) Meta- data; Data descri- ption Hecuba tools (BSC) Short term decisions real time alerts Model structure improvements Learned patterns correlations WP5: Resource mgmt & integration Technologies: • ATOS Resource mgmt • ITML integration services http://ibidaas.eu/tools 30
  • 31. Data fabrication capabilities Solution flexibility Easy to code programming paradigm High code reusability Key Features & Innovations https://www.ibidaas.eu/deliverables 31
  • 32. GPU-accelerated analytics; Synergy of CEP and GPU- accelerated analytics for streaming data Feedback from analytics to data fabrication Feedback from analytics to problem modelling Demonstrated on use cases across 3 different data providers and 3 different industries https://www.ibidaas.eu/deliverables Key Features & Innovations (Cont’d) 32
  • 33. • Production Process of Aluminium Die Casting • During the casting process of the engine blocks, molten aluminium is injected into the die cavity • Can we classify the quality levels of the engine block correctly when they are produced? • Can we improve the production process, by increasing the number of high quality engine blocks and decreasing the number of lower quality engine blocks? I-BiDaaS applied to CRF use cases 33
  • 34. • Challenges • High volume dataset • Unbalanced dataset • Single model for two source of data • Thermal images • Sensor (tabular) data (piston speed, intensification pressures etc.) • I-BiDaaS approach • Joint neural network model with CNN and FCNN (PyTorch) • CNN with 201 layers (DenseNet201) for images – pretrained & non-trained model • Fully Connected NN with 7 layers for sensor data • Random under-sampling to produce a balanced dataset Production process of aluminium die casting 34
  • 35. • Architecture of the joint neural network • Good accuracy for different classes: • Orange line: model trained on full dataset - 73.54% accuracy • Pink line: model trained on balanced dataset - 54.06% accuracy (better model on relevant classes) Production process of aluminium die casting 35
  • 36. Production process of aluminium die casting 36
  • 37. • Maintenance and monitoring of production assets • Different sensors are installed on the production line • Can we prevent faults before they happen? • Can we see the trend of a sensor’s behavior across different days? • Can we see the similarity between sensors ? I-BiDaaS applied to CRF use cases 37
  • 38. • Challenges • High volume dataset (over 100 sensors, 26 months of measurements) • How to model the similar behavior? • Unlabeled data • I-BiDaas approach • Pandas library for data preprocessing • Time series per sensor with number of outliers per day • Visualization • Further analysis • Rescaled time series pairwise distance • Obtain the most similar sensors Maintenance and monitoring of production assets 38
  • 39. • Time series of outliers for a sensor • Time series of measurements for a sensor Maintenance and monitoring of production assets 39
  • 40. • Histogram of similarity between sensors Maintenance and monitoring of production assets 40
  • 41. Maintenance and monitoring of production assets 41
  • 42. Giuseppe Danilo Spennacchio Flexible and Adaptive Systems Specialist at Factory Innovation Department, CRF, Italy Manufacturing Pilot: step by step I-BiDaaS Application to the Manufacturing Sector Thursday, July 09, 2020 - 14:00-15:00 CEST
  • 43. § Anonymisation: result of elaboration is gathered in new anonymised files with all information useful for analytics § Security: original data provided by plants are retrieved in the CRF server § Quality analysis: data and defects manually detected are elaborated Current situation 43 § Data analyses are executed in Factory Innovation Department (CRF) data, operator and quality information periodically reports internal analyses all information processed § Data Analytics in CRF § Results: periodically discussion with manufacturers § Analytics lifecycle:
  • 44. Data anonymisation Data gathering Data Storage Production Site 1 CRF I-BiDaaS solution computerized production machine component Production Site 2 Areas provided with sensors SCADA MES vehicle Internal analysis Analytic & Visualisation tools q Data fabrication q Data cleaning q Data analyses q Data visualisation Results VM CRF Data flow VM Results Data flow Data flowImprovement of the production process Data flow I-BiDaaS Platform 44
  • 45. CFR Data Roadmap 2018 2019 2020 Q1 Q2 Q3 Q4 Q1 Q2 Q3 Q4 Q1 Q2 Q3 Q4 M3 Preliminary Definition of Use Case M6 Use Case Consolidation and definition of dataset M9 Definition of dataset characteristics, format and first structured dataset M12 Definition of Rules for the IBM’s Data Fabrication Tool M15 Validation of synthesized data M18 Hackathon event in Melfi M21 CRF Demo M24 Provided a new type of data (Thermal data) for the 1°use case M27 Progress on analytics M30 Progress on visualisation M33 Experimental implementation M36 45
  • 46. IN Molten Aluminium OUT Cylinder blocksDie TC1 TC2 Die Parameters Data (.csv)PC PC Thermal images(.img) Quality Control Quality Data (.csv) PC Complex process: an enormous amount of heterogeneous data such as piston speed in the first and second phase, intensification pressures; Temperatures, etc Production Process of Aluminium Die Casting 46 Business Goal Quality Process Improvement: § avoid decrease of quality level § prevent repairs and reworks § reduce scrap and waste Use Case Goals § Develop high level algorithms § Identify and select critical parameters § Provide a mode to quickly visualize analyses results
  • 47. Die Parameters Data & Quality Data q collected and merged data - Process Parameters q anonymised data q collected and converted data in Thermal images & Thermal values Improvement of the production process Plant CRF I-BiDaaS Platform q Analytic tools q Advanced Visualisation tools CRF q Data fabrication q Data cleaning q Data analyses q Data visualisation Thermal Data Data flow Data flowResults Virtual Machine Data flow Virtual Machine Results 47 Production Process of Aluminium Die Casting – data flow
  • 48. I-BiDaaS platform to easy utilise I-BiDaaS solutions developed by data analysts and technologists. 48 Production Process of Aluminium Die Casting - demo
  • 49. After login, we selects co-develop mode, in which the data source and analysis algorithm are predefined. 49 Production Process of Aluminium Die Casting - demo
  • 50. 50 The Aluminium Die Casting use case is a complex industrial process with many heterogeneous parameters. The co-develop mode allows to us to check data processing in real time. Production Process of Aluminium Die Casting - demo
  • 51. A dynamic diagram will show the incoming streaming data in real-time, as well as aggregations of them that are constantly updated, after pressing the top-left button ‘Run Experiment’. 51 Production Process of Aluminium Die Casting - demo
  • 52. 52 We can visualise the trend of parameters and quickly check if there is something of anomalous compared to the set values of parameters Production Process of Aluminium Die Casting - demo
  • 53. 53 If we see something of anomalous, we can press on the button ‘Pause/Start’ and quickly visualise data trends Production Process of Aluminium Die Casting - demo
  • 54. we can visualise the parameter values for each classification level (0,1,2) press on the corresponding button 54 Production Process of Aluminium Die Casting - demo
  • 55. 55 we can visualise the data table, that shows a colour- coded presentation of the results according to a given dimension of data (classification level) We can choose how many items per page to visualise Production Process of Aluminium Die Casting - demo
  • 56. We can visualise in real time and quickly the sequence of engine block with their level of classification 56 Production Process of Aluminium Die Casting - demo
  • 57. Maintenance and Monitoring of production assets 57 Business Goal Predictive Maintenance: § predict faults before they happen § predict unnecessary actions (preventive or planned maintenance) § avoid micro or macro stoppages § predict retooling and refurbishing Use Case Goals § collect, structure and analyse sensor data with high level algorithms § obtain thresholds for anomalous measurements § create a structured foundational database to be easily utilised to check outlier detections for a continuous and periodic control of the service conditions (PM)
  • 58. 58 Maintenance and Monitoring of production assets q The monitoring of vibrations is important to check the status of a machine q The analysis of the trend of vibrations over time allows to predict the onset of deterioration and to intervene in time before the failure q Accelerometers are used for measuring vibration and shock on machines and basically anything that moves The continuous and periodic control of the service conditions of a machine is known as Predictive Maintenance Sensors: q detect the change in the environment and transfers these information to other systems q convert a physical phenomenon into a measurable analog value (or sometimes a digital signal) which is human-readable and suitable for a display or transmission for reading or further processing
  • 59. SCADA DATA MES DATA q Collected and anonymised data Methodology for Predictive Maintenance Plant CRF I-BiDaaS Platform q Analytic tools q Visualisation tools CRF q Data fabrication q Data cleaning q Data analyses q Data visualisation Data flow Data flowResults Virtual Machine Data flow Maintenance and Monitoring of the production assets – data flow Virtual Machine Results 59
  • 60. Maintenance and Monitoring of production assets - demo 60
  • 61. 61 Maintenance and Monitoring of production assets - demo
  • 62. Maintenance and Monitoring of production assets - demo 62 Maintenance and Monitoring of production assets. The co-develop mode allows us to monitor the outlier time series for each sensor any day
  • 63. Maintenance and Monitoring of production assets - demo 63 Structured foundational database to be easily utilised to check outliers for a continuous and periodic control of the service conditions (Predictive Maintenance)
  • 64. Maintenance and Monitoring of production assets - demo 64 Sensors - Categories
  • 65. 65 Accelerometer [mg] / Id sensor Maintenance and Monitoring of production assets - demo 65
  • 66. 66 Anomalies number per day Maintenance and Monitoring of production assets - demo 66
  • 67. 67 • Data has been transformed into separate time series - one per sensor • anomalous measurements Maintenance and Monitoring of production assets - demo 67
  • 68. Benefits KPIs 68 CRF benefits from I-BiDaaS To improve the efficiency of manufacturing plants, by getting the best performance from the machinery to reduce production losses and achieve greater competitiveness of the company Increase of 1 - 1.5 % in current Overall Equipment Effectiveness (OEE) and decrease of 50 % in maintenance costs To enhance production times, to reduce costs and, consequently, to obtain results that satisfy manufacturers’ requests in terms of product quality, machine performance and timing To reduce time to produce decisions To break data silos and achieve accuracy of new models with respect to internal CRF models in use Increase of 3-7 % of quality control level related to good products and decrease of 1- 4% and 0-2 % of two quality control levels related to defective products From one month to real time Increase of 6 % for the first use case and 20% for the second one
  • 69. Questions? Thank you! Your feedback is valuable for us! https://bit.ly/2O8YV8D