SlideShare a Scribd company logo
Data Driven Industrial Digitalization
through Reverse Engineering of Systems
Lokukaluge Prasad Perera
September 12th, 2019
1st Workshop on Digitalization and Blockchain – Managerial and Organizational Implications
University of South-Eastern Norway, Campus Vestfold.
Outline
• Industrial Digitalization.
• Data Analytics.
• From Newton's Law to Deep Neural Networks
: Autoencoders.
• Shipping Industrial Example.
• Conclusions.
Industrial Digitalization in Shipping
" Poor data quality costs…
the US economy around US$ 3.1 trillions per year"*
"1 in 3 Business Leaders don't trust…
the information they use to make decisions "*
"27% of the respondents in a survey…
were unsure of how much of their data sets are inaccurate"*
*IBM, The four V's of Big Data, URL:http://www.ibmbigdatahub.com/infographic/four-vs-big-data, 2017.
Why Data Analytics ..?
• Conventional Models
– Various Conventional Models in the shipping industry for various applications.
– Some challenges in handling Big Data : erroneous data conditions, system-model
uncertainty, estimation algorithm failures, data visualization challenges and high
computational power.
• Machine Learning & Statistical Analysis
– Machine Learning (ML) & Statistical Analysis will play an important role in
analyzing such data sets.
– Statistical Analysis will guide ML Algorithms.
– Towards Data Driven Models: Digital Models.
– It is Geometrical…
• Domain Knowledge
– Ship Dynamics & Hydrodynamics.
– Automation & Navigation Systems.
Data Analytics Types
– Digital model consists of data driven relationships.
– Descriptive analytics identifies various data anomalies.
– Diagnostic analytics recovers/removes such data anomalies.
– Predictive analytics forecasts vessel and ship system behavior.
– Visual analytics visualizes the same information.
– The information creates Advanced Knowledge and that will lead to Industrial Intelligence.
– Both advanced knowledge and industrial intelligence support Decision Analytics.
– Decision analytics may consist of appropriate Key Performance Indicators (i.e. KPIs)
Newton's Laws of Motion
– "A body at rest will remain at rest, and a body
in motion will remain in motion unless it is
acted upon by an external force."
– "The force acting on an object is equal to the
mass of that object times its acceleration.“
F = ma
where F is force, m is mass, and a is acceleration.
– "For every action, there is an equal and
opposite reaction."
Source: https://www.livescience.com
Newton's Laws of Motion
F = ma
F is force,
m is mass
a is acceleration.
Sensor Measurements
F = ma
F is force,
m is mass
a is acceleration.
Singular Values and Vectors
F = ma => Z1 and Z2 => sensor noise
F is force,
m is mass
a is acceleration.
Z1,2 are singular vectors
Data Projection
F = ma => Z1
F is force,
m is mass
a is acceleration.
Z1,2 are singular vectors
Least Squares Fitting
Reinvention of Newton's Laws of Motion
F = ma
F is force,
m is mass
a is acceleration.
Z1,2 are singular vectors
Reverse Engineering of Systems
F = ma
F is force,
m is mass
a is acceleration
Z1,2 are singular vectors
Deep Neural Networks: Autoencoders
F = ma
F is force,
m is mass
a is acceleration
F
a
Z 1,2
R
Advanced System Models
F = ma + Fm
where
F is force,
Fm is mean force,
m is mass,
a is acceleration
Digital Models in High Dimensions
Singular Values & Vectors
– The structure of each data cluster is denoted by several vectors: singular vectors
(i.e. associated with the respective singular values)
– Singular values and vectors represent the building blocks of electrical and
mechanical systems
– System behavior, i.e. system information, can be accommodated into the same.
Digital Models
– Three-dimensional vector space with the right-hand coordinate system.
– Three data clusters, i.e. system states, with the respective mean vectors.
– Each data cluster consists of local operational information of the respective
system.
– The structure of each data cluster is denoted by several vectors: singular vectors
(i.e. associated with the respective singular values).
– Each singular vector consists of local operational information of the respective
systems.
– Each cluster is a linear model, i.e. Piecewise linearization: the best approximation
of a nonlinear function as a piecewise linear function.
– The system can jump from one state to another state in a high dimensional data
space.
– Some data clusters may relate to data anomalies or system abnormal events.
Model Complexity
– From Components to System of Systems
– Various Model Levels
– High dimensional Digital Models
– From Big Data to Low Level Models
Ship Performance & Navigation Data Set
Parameter Mini. Max.
1. Avg. draft (m) 0 15
2. STW (Knots)- Speed through water 3 20
3. Engine power (kW) 1000 8000
4. Shaft speed (rpm) 20 120
5. Engine fuel cons. (Tons/day) 1 40
6. SOG (Knots) – Speed over ground 0 20
7. Trim (m) -2 6
8. Rel. wind speed (m/s) 0 25
9. Rel. wind direction (deg) 2 360
10. Aux. engine fuel cons. (Tons/day) 0 8
Ship Engine Data
in Histograms
– The vessel is a bulk carrier with ship
length: 225 (m) and beam: 32.29 (m)
– Three parameters: engine speed,
power and fuel consumption
– Engine data are clustered around
three Gaussian type distributions
– Three engine modes of this vessel
– Ship performance and navigation
data sets are often clustered in a
high dimensional space
– Those clusters relate to vessel
navigation and ship system
operational conditions
Ship Engine Data
– Two parameters: engine speed and
power.
– Combined kernel density estimation
(multivariate KDE) with the
respective univariate KDEs.
– Engine data are clustered around
three Gaussian type distributions.
– Three engine modes of this vessel.
– Ship performance and navigation
data sets are often clustered in a
high dimensional space.
– That introduce the discreteness (i.e.
digital-ness) into the proposed
models.
Digital Models
– Each cluster is a linear model, i.e. Piecewise linearization: the best
approximation of a nonlinear function as a piecewise linear function.
– The vessel & ship system can jump from one state to another state in a high
dimensional data space.
– Some data clusters may relate to data anomalies or system abnormal events.
– Digital models interact with the descriptive and diagnostic analytics to improve the data quality
– Data anomaly filter 1: missing data points and preliminary data anomalies (i.e. Min-Max values)
detected
– Data anomaly filter 2: Additional data anomalies (i.e. the outliers of digital models) detected
– Data anomalies send to separate groups where the data anomalies against known and unknown
sensor and DAQ faults and system abnormalities compared
– Data sets from anomaly group 1 and 2 transfer through the data recovery filter and digital models
– A considerable amount of data anomalies can be recovered by this step
Data Anomaly Detection and Recovery
Procedure
Data Anomalies in Newton's Laws of Motion
F = ma
F is force,
m is mass
a is acceleration.
Z1,2 are singular vectors
Data Anomaly Detection and
Recovery Procedure: Filter 2
– Digital models interact with the descriptive and diagnostic analytics to improve the data quality
– Data anomaly filter 1: missing data points and preliminary data anomalies (i.e. Min-Max values)
detected
– Data anomaly filter 2: Additional data anomalies (i.e. the outliers of digital models) detected
– Data anomalies send to separate groups where the data anomalies against known and unknown
sensor and DAQ faults and system abnormalities compared
– Data sets from anomaly group 1 and 2 transfer through the data recovery filter and digital models
– A considerable amount of data anomalies can be recovered by this step
Data Anomaly Detection and
Recovery Procedure: Filter 2
– Digital models interact with the descriptive and diagnostic analytics to improve the data quality
– Data anomaly filter 1: missing data points and preliminary data anomalies (i.e. Min-Max values)
detected
– Data anomaly filter 2: Additional data anomalies (i.e. the outliers of digital models) detected
– Data anomalies send to separate groups where the data anomalies against known and unknown
sensor and DAQ faults and system abnormalities compared
– Data sets from anomaly group 1 and 2 transfer through the data recovery filter and digital models
– A considerable amount of data anomalies can be recovered by this step
Data Anomaly Detection and
Recovery Procedure: Data Recovery
– Digital models interact with the descriptive and diagnostic analytics to improve the data quality
– Data anomaly filter 1: missing data points and preliminary data anomalies (i.e. Min-Max values)
detected
– Data anomaly filter 2: Additional data anomalies (i.e. the outliers of digital models) detected
– Data anomalies send to separate groups where the data anomalies against known and unknown
sensor and DAQ faults and system abnormalities compared
– Data sets from anomaly group 1 and 2 transfer through the data recovery filter and digital
models
– A considerable amount of data anomalies can be recovered by this step
Data Anomaly Detection &
Recovery Procedure: Filter 2
Data Visualization of Newton's Laws of Motion
Visual Analytics
– Digital models should be visualized to extract relevant parameter
relationships.
– Covariance values of the data sets are represented by singular vectors.
– Each vector will present correlation information among the respective
parameters.
Visual Analytics
– Digital models should be visualized to extract relevant parameter
relationships in a High Dimensional Space.
– Covariance values of the data sets are represented by singular vectors.
– Each vector will present correlation information among the respective
parameters.
Visual Analytics
– Digital models should be visualized to extract relevant parameter relationships
in a High Dimensional Space.
– Covariance values of the data sets are represented by singular vectors.
– Each vector will present correlation information among the respective
parameters.
– The top singular vector is presented in the outer circle.
– The bottom singular vector is presented in the inner circle.
Visual Analytics
Visual Analytics
Predictive Analytics
– The outputs of the predictive analytics are predicted vessel and ship
system behavior.
– The information creates advanced knowledge and facilitates towards
industrial intelligence
Deep Learning
Source: https://www.edureka.co/blog/what-is-deep-learning
Data Handling Framework
Conclusions
– Novel mathematical framework to support industrial digitization of shipping
is presented: i.e. from Industrial IoT to Predictive Analytics.
– Data analytics can…
• self-learn (i.e. the data structure can learn itself)
• self-clean (i.e. data anomalies can be detected, isolated and recovered by considering the
outliers of the data structure),
• self-compress and expend (i.e. the respective parameters in the data sets can be reduced
and expanded by considering the same data structure)
• self-visualize (i.e. the respective data structures can be used for both vessel and ship
system performance observations)
– That introduces Intelligent Analytics to any industry and also provides
important solutions to the big data challenges under the Industrial
Digitalization.
Any Questions?

More Related Content

Similar to Data Driven Industrial Digitalization through Reverse Engineering of Systems

Industrial IoT to Predictive Analytics: A Reverse Engineering Approach from S...
Industrial IoT to Predictive Analytics: A Reverse Engineering Approach from S...Industrial IoT to Predictive Analytics: A Reverse Engineering Approach from S...
Industrial IoT to Predictive Analytics: A Reverse Engineering Approach from S...
Lokukaluge Prasad Perera
 
Role of Big Data Analytics in Power System Application Ravi v angadi asst. pr...
Role of Big Data Analytics in Power System Application Ravi v angadi asst. pr...Role of Big Data Analytics in Power System Application Ravi v angadi asst. pr...
Role of Big Data Analytics in Power System Application Ravi v angadi asst. pr...
PresidencyUniversity
 
Ghhh
GhhhGhhh
Ghhh
agammya
 
Model-Simulation-and-Measurement-Based Systems Engineering of Power System Sy...
Model-Simulation-and-Measurement-Based Systems Engineering of Power System Sy...Model-Simulation-and-Measurement-Based Systems Engineering of Power System Sy...
Model-Simulation-and-Measurement-Based Systems Engineering of Power System Sy...
Luigi Vanfretti
 
Big Data and IOT
Big Data and IOTBig Data and IOT
Big Data and IOT
Shubhangi Sheel
 
Term Paper Presentation
Term Paper PresentationTerm Paper Presentation
Term Paper Presentation
Shubham Singh
 
bigdatalittledataspe-pd2aoct2012denesuk-140321031823-phpapp02
bigdatalittledataspe-pd2aoct2012denesuk-140321031823-phpapp02bigdatalittledataspe-pd2aoct2012denesuk-140321031823-phpapp02
bigdatalittledataspe-pd2aoct2012denesuk-140321031823-phpapp02
denesuk
 
Big data, little data, whatever
Big data, little data, whateverBig data, little data, whatever
Big data, little data, whatever
denesuk
 
Survey on classification algorithms for data mining (comparison and evaluation)
Survey on classification algorithms for data mining (comparison and evaluation)Survey on classification algorithms for data mining (comparison and evaluation)
Survey on classification algorithms for data mining (comparison and evaluation)
Alexander Decker
 
Analyst’s Nightmare or Laundering Massive Spreadsheets
Analyst’s Nightmare or Laundering Massive SpreadsheetsAnalyst’s Nightmare or Laundering Massive Spreadsheets
Analyst’s Nightmare or Laundering Massive Spreadsheets
PyData
 
K-MEANS AND D-STREAM ALGORITHM IN HEALTHCARE
K-MEANS AND D-STREAM ALGORITHM IN HEALTHCAREK-MEANS AND D-STREAM ALGORITHM IN HEALTHCARE
K-MEANS AND D-STREAM ALGORITHM IN HEALTHCARE
International Journal of Technical Research & Application
 
Wanted!: Open M&S Standards and Technologies for the Smart Grid - Introducing...
Wanted!: Open M&S Standards and Technologies for the Smart Grid - Introducing...Wanted!: Open M&S Standards and Technologies for the Smart Grid - Introducing...
Wanted!: Open M&S Standards and Technologies for the Smart Grid - Introducing...
Luigi Vanfretti
 
Certain Investigation on Dynamic Clustering in Dynamic Datamining
Certain Investigation on Dynamic Clustering in Dynamic DataminingCertain Investigation on Dynamic Clustering in Dynamic Datamining
Certain Investigation on Dynamic Clustering in Dynamic Datamining
ijdmtaiir
 
Hybrid Model using Unsupervised Filtering Based on Ant Colony Optimization an...
Hybrid Model using Unsupervised Filtering Based on Ant Colony Optimization an...Hybrid Model using Unsupervised Filtering Based on Ant Colony Optimization an...
Hybrid Model using Unsupervised Filtering Based on Ant Colony Optimization an...
IRJET Journal
 
Concept Drift Identification using Classifier Ensemble Approach
Concept Drift Identification using Classifier Ensemble Approach  Concept Drift Identification using Classifier Ensemble Approach
Concept Drift Identification using Classifier Ensemble Approach
IJECEIAES
 
Abnormal Traffic Detection Based on Attention and Big Step Convolution.docx
Abnormal Traffic Detection Based on Attention and Big Step Convolution.docxAbnormal Traffic Detection Based on Attention and Big Step Convolution.docx
Abnormal Traffic Detection Based on Attention and Big Step Convolution.docx
Shakas Technologies
 
Abnormal Traffic Detection Based on Attention and Big Step Convolution.docx
Abnormal Traffic Detection Based on Attention and Big Step Convolution.docxAbnormal Traffic Detection Based on Attention and Big Step Convolution.docx
Abnormal Traffic Detection Based on Attention and Big Step Convolution.docx
Shakas Technologies
 
Clustering for Stream and Parallelism (DATA ANALYTICS)
Clustering for Stream and Parallelism (DATA ANALYTICS)Clustering for Stream and Parallelism (DATA ANALYTICS)
Clustering for Stream and Parallelism (DATA ANALYTICS)
DheerajPachauri
 
Crowd Density Estimation Using Base Line Filtering
Crowd Density Estimation Using Base Line FilteringCrowd Density Estimation Using Base Line Filtering
Crowd Density Estimation Using Base Line Filtering
paperpublications3
 
IRJET- Fault Detection and Prediction of Failure using Vibration Analysis
IRJET-	 Fault Detection and Prediction of Failure using Vibration AnalysisIRJET-	 Fault Detection and Prediction of Failure using Vibration Analysis
IRJET- Fault Detection and Prediction of Failure using Vibration Analysis
IRJET Journal
 

Similar to Data Driven Industrial Digitalization through Reverse Engineering of Systems (20)

Industrial IoT to Predictive Analytics: A Reverse Engineering Approach from S...
Industrial IoT to Predictive Analytics: A Reverse Engineering Approach from S...Industrial IoT to Predictive Analytics: A Reverse Engineering Approach from S...
Industrial IoT to Predictive Analytics: A Reverse Engineering Approach from S...
 
Role of Big Data Analytics in Power System Application Ravi v angadi asst. pr...
Role of Big Data Analytics in Power System Application Ravi v angadi asst. pr...Role of Big Data Analytics in Power System Application Ravi v angadi asst. pr...
Role of Big Data Analytics in Power System Application Ravi v angadi asst. pr...
 
Ghhh
GhhhGhhh
Ghhh
 
Model-Simulation-and-Measurement-Based Systems Engineering of Power System Sy...
Model-Simulation-and-Measurement-Based Systems Engineering of Power System Sy...Model-Simulation-and-Measurement-Based Systems Engineering of Power System Sy...
Model-Simulation-and-Measurement-Based Systems Engineering of Power System Sy...
 
Big Data and IOT
Big Data and IOTBig Data and IOT
Big Data and IOT
 
Term Paper Presentation
Term Paper PresentationTerm Paper Presentation
Term Paper Presentation
 
bigdatalittledataspe-pd2aoct2012denesuk-140321031823-phpapp02
bigdatalittledataspe-pd2aoct2012denesuk-140321031823-phpapp02bigdatalittledataspe-pd2aoct2012denesuk-140321031823-phpapp02
bigdatalittledataspe-pd2aoct2012denesuk-140321031823-phpapp02
 
Big data, little data, whatever
Big data, little data, whateverBig data, little data, whatever
Big data, little data, whatever
 
Survey on classification algorithms for data mining (comparison and evaluation)
Survey on classification algorithms for data mining (comparison and evaluation)Survey on classification algorithms for data mining (comparison and evaluation)
Survey on classification algorithms for data mining (comparison and evaluation)
 
Analyst’s Nightmare or Laundering Massive Spreadsheets
Analyst’s Nightmare or Laundering Massive SpreadsheetsAnalyst’s Nightmare or Laundering Massive Spreadsheets
Analyst’s Nightmare or Laundering Massive Spreadsheets
 
K-MEANS AND D-STREAM ALGORITHM IN HEALTHCARE
K-MEANS AND D-STREAM ALGORITHM IN HEALTHCAREK-MEANS AND D-STREAM ALGORITHM IN HEALTHCARE
K-MEANS AND D-STREAM ALGORITHM IN HEALTHCARE
 
Wanted!: Open M&S Standards and Technologies for the Smart Grid - Introducing...
Wanted!: Open M&S Standards and Technologies for the Smart Grid - Introducing...Wanted!: Open M&S Standards and Technologies for the Smart Grid - Introducing...
Wanted!: Open M&S Standards and Technologies for the Smart Grid - Introducing...
 
Certain Investigation on Dynamic Clustering in Dynamic Datamining
Certain Investigation on Dynamic Clustering in Dynamic DataminingCertain Investigation on Dynamic Clustering in Dynamic Datamining
Certain Investigation on Dynamic Clustering in Dynamic Datamining
 
Hybrid Model using Unsupervised Filtering Based on Ant Colony Optimization an...
Hybrid Model using Unsupervised Filtering Based on Ant Colony Optimization an...Hybrid Model using Unsupervised Filtering Based on Ant Colony Optimization an...
Hybrid Model using Unsupervised Filtering Based on Ant Colony Optimization an...
 
Concept Drift Identification using Classifier Ensemble Approach
Concept Drift Identification using Classifier Ensemble Approach  Concept Drift Identification using Classifier Ensemble Approach
Concept Drift Identification using Classifier Ensemble Approach
 
Abnormal Traffic Detection Based on Attention and Big Step Convolution.docx
Abnormal Traffic Detection Based on Attention and Big Step Convolution.docxAbnormal Traffic Detection Based on Attention and Big Step Convolution.docx
Abnormal Traffic Detection Based on Attention and Big Step Convolution.docx
 
Abnormal Traffic Detection Based on Attention and Big Step Convolution.docx
Abnormal Traffic Detection Based on Attention and Big Step Convolution.docxAbnormal Traffic Detection Based on Attention and Big Step Convolution.docx
Abnormal Traffic Detection Based on Attention and Big Step Convolution.docx
 
Clustering for Stream and Parallelism (DATA ANALYTICS)
Clustering for Stream and Parallelism (DATA ANALYTICS)Clustering for Stream and Parallelism (DATA ANALYTICS)
Clustering for Stream and Parallelism (DATA ANALYTICS)
 
Crowd Density Estimation Using Base Line Filtering
Crowd Density Estimation Using Base Line FilteringCrowd Density Estimation Using Base Line Filtering
Crowd Density Estimation Using Base Line Filtering
 
IRJET- Fault Detection and Prediction of Failure using Vibration Analysis
IRJET-	 Fault Detection and Prediction of Failure using Vibration AnalysisIRJET-	 Fault Detection and Prediction of Failure using Vibration Analysis
IRJET- Fault Detection and Prediction of Failure using Vibration Analysis
 

More from Lokukaluge Prasad Perera

Wärtsilä’s SeaTech project to change the face of shipping emissions
Wärtsilä’s SeaTech project to change the face of shipping emissionsWärtsilä’s SeaTech project to change the face of shipping emissions
Wärtsilä’s SeaTech project to change the face of shipping emissions
Lokukaluge Prasad Perera
 
UiT Autonomous Ship Program, including recent research activities
UiT Autonomous Ship Program, including recent research activitiesUiT Autonomous Ship Program, including recent research activities
UiT Autonomous Ship Program, including recent research activities
Lokukaluge Prasad Perera
 
Digital Helmsman of Autonomous Ships
Digital Helmsman of Autonomous ShipsDigital Helmsman of Autonomous Ships
Digital Helmsman of Autonomous Ships
Lokukaluge Prasad Perera
 
UiT Autonomous Ship Program
UiT Autonomous Ship Program UiT Autonomous Ship Program
UiT Autonomous Ship Program
Lokukaluge Prasad Perera
 
UiT Autonomous Ship Program
UiT Autonomous Ship Program UiT Autonomous Ship Program
UiT Autonomous Ship Program
Lokukaluge Prasad Perera
 
AUTONOMOUS SHIP NAVIGATION UNDER DEEP LEARNING AND THE CHALLENGES IN COLREGS
AUTONOMOUS SHIP NAVIGATION UNDER DEEP LEARNING AND THE CHALLENGES IN COLREGSAUTONOMOUS SHIP NAVIGATION UNDER DEEP LEARNING AND THE CHALLENGES IN COLREGS
AUTONOMOUS SHIP NAVIGATION UNDER DEEP LEARNING AND THE CHALLENGES IN COLREGS
Lokukaluge Prasad Perera
 
Digitalization of Sea going Vessels under High Dimensional Data Driven Models...
Digitalization of Sea going Vessels under High Dimensional Data Driven Models...Digitalization of Sea going Vessels under High Dimensional Data Driven Models...
Digitalization of Sea going Vessels under High Dimensional Data Driven Models...
Lokukaluge Prasad Perera
 
Intelligent Decision Making Framework for Ship Collision Avoidance based on C...
Intelligent Decision Making Framework for Ship Collision Avoidance based on C...Intelligent Decision Making Framework for Ship Collision Avoidance based on C...
Intelligent Decision Making Framework for Ship Collision Avoidance based on C...
Lokukaluge Prasad Perera
 
Handling Big Data in Ship Performance & Navigation Monitoring.
Handling Big Data in Ship Performance & Navigation Monitoring.Handling Big Data in Ship Performance & Navigation Monitoring.
Handling Big Data in Ship Performance & Navigation Monitoring.
Lokukaluge Prasad Perera
 
Full Scale Data Handling in Shipping: A Big Data Solution
Full Scale Data Handling in Shipping: A Big Data SolutionFull Scale Data Handling in Shipping: A Big Data Solution
Full Scale Data Handling in Shipping: A Big Data Solution
Lokukaluge Prasad Perera
 

More from Lokukaluge Prasad Perera (10)

Wärtsilä’s SeaTech project to change the face of shipping emissions
Wärtsilä’s SeaTech project to change the face of shipping emissionsWärtsilä’s SeaTech project to change the face of shipping emissions
Wärtsilä’s SeaTech project to change the face of shipping emissions
 
UiT Autonomous Ship Program, including recent research activities
UiT Autonomous Ship Program, including recent research activitiesUiT Autonomous Ship Program, including recent research activities
UiT Autonomous Ship Program, including recent research activities
 
Digital Helmsman of Autonomous Ships
Digital Helmsman of Autonomous ShipsDigital Helmsman of Autonomous Ships
Digital Helmsman of Autonomous Ships
 
UiT Autonomous Ship Program
UiT Autonomous Ship Program UiT Autonomous Ship Program
UiT Autonomous Ship Program
 
UiT Autonomous Ship Program
UiT Autonomous Ship Program UiT Autonomous Ship Program
UiT Autonomous Ship Program
 
AUTONOMOUS SHIP NAVIGATION UNDER DEEP LEARNING AND THE CHALLENGES IN COLREGS
AUTONOMOUS SHIP NAVIGATION UNDER DEEP LEARNING AND THE CHALLENGES IN COLREGSAUTONOMOUS SHIP NAVIGATION UNDER DEEP LEARNING AND THE CHALLENGES IN COLREGS
AUTONOMOUS SHIP NAVIGATION UNDER DEEP LEARNING AND THE CHALLENGES IN COLREGS
 
Digitalization of Sea going Vessels under High Dimensional Data Driven Models...
Digitalization of Sea going Vessels under High Dimensional Data Driven Models...Digitalization of Sea going Vessels under High Dimensional Data Driven Models...
Digitalization of Sea going Vessels under High Dimensional Data Driven Models...
 
Intelligent Decision Making Framework for Ship Collision Avoidance based on C...
Intelligent Decision Making Framework for Ship Collision Avoidance based on C...Intelligent Decision Making Framework for Ship Collision Avoidance based on C...
Intelligent Decision Making Framework for Ship Collision Avoidance based on C...
 
Handling Big Data in Ship Performance & Navigation Monitoring.
Handling Big Data in Ship Performance & Navigation Monitoring.Handling Big Data in Ship Performance & Navigation Monitoring.
Handling Big Data in Ship Performance & Navigation Monitoring.
 
Full Scale Data Handling in Shipping: A Big Data Solution
Full Scale Data Handling in Shipping: A Big Data SolutionFull Scale Data Handling in Shipping: A Big Data Solution
Full Scale Data Handling in Shipping: A Big Data Solution
 

Recently uploaded

basic-wireline-operations-course-mahmoud-f-radwan.pdf
basic-wireline-operations-course-mahmoud-f-radwan.pdfbasic-wireline-operations-course-mahmoud-f-radwan.pdf
basic-wireline-operations-course-mahmoud-f-radwan.pdf
NidhalKahouli2
 
ISPM 15 Heat Treated Wood Stamps and why your shipping must have one
ISPM 15 Heat Treated Wood Stamps and why your shipping must have oneISPM 15 Heat Treated Wood Stamps and why your shipping must have one
ISPM 15 Heat Treated Wood Stamps and why your shipping must have one
Las Vegas Warehouse
 
哪里办理(csu毕业证书)查尔斯特大学毕业证硕士学历原版一模一样
哪里办理(csu毕业证书)查尔斯特大学毕业证硕士学历原版一模一样哪里办理(csu毕业证书)查尔斯特大学毕业证硕士学历原版一模一样
哪里办理(csu毕业证书)查尔斯特大学毕业证硕士学历原版一模一样
insn4465
 
spirit beverages ppt without graphics.pptx
spirit beverages ppt without graphics.pptxspirit beverages ppt without graphics.pptx
spirit beverages ppt without graphics.pptx
Madan Karki
 
Textile Chemical Processing and Dyeing.pdf
Textile Chemical Processing and Dyeing.pdfTextile Chemical Processing and Dyeing.pdf
Textile Chemical Processing and Dyeing.pdf
NazakatAliKhoso2
 
Literature Review Basics and Understanding Reference Management.pptx
Literature Review Basics and Understanding Reference Management.pptxLiterature Review Basics and Understanding Reference Management.pptx
Literature Review Basics and Understanding Reference Management.pptx
Dr Ramhari Poudyal
 
CSM Cloud Service Management Presentarion
CSM Cloud Service Management PresentarionCSM Cloud Service Management Presentarion
CSM Cloud Service Management Presentarion
rpskprasana
 
Understanding Inductive Bias in Machine Learning
Understanding Inductive Bias in Machine LearningUnderstanding Inductive Bias in Machine Learning
Understanding Inductive Bias in Machine Learning
SUTEJAS
 
Recycled Concrete Aggregate in Construction Part III
Recycled Concrete Aggregate in Construction Part IIIRecycled Concrete Aggregate in Construction Part III
Recycled Concrete Aggregate in Construction Part III
Aditya Rajan Patra
 
Eric Nizeyimana's document 2006 from gicumbi to ttc nyamata handball play
Eric Nizeyimana's document 2006 from gicumbi to ttc nyamata handball playEric Nizeyimana's document 2006 from gicumbi to ttc nyamata handball play
Eric Nizeyimana's document 2006 from gicumbi to ttc nyamata handball play
enizeyimana36
 
Iron and Steel Technology Roadmap - Towards more sustainable steelmaking.pdf
Iron and Steel Technology Roadmap - Towards more sustainable steelmaking.pdfIron and Steel Technology Roadmap - Towards more sustainable steelmaking.pdf
Iron and Steel Technology Roadmap - Towards more sustainable steelmaking.pdf
RadiNasr
 
Optimizing Gradle Builds - Gradle DPE Tour Berlin 2024
Optimizing Gradle Builds - Gradle DPE Tour Berlin 2024Optimizing Gradle Builds - Gradle DPE Tour Berlin 2024
Optimizing Gradle Builds - Gradle DPE Tour Berlin 2024
Sinan KOZAK
 
CHINA’S GEO-ECONOMIC OUTREACH IN CENTRAL ASIAN COUNTRIES AND FUTURE PROSPECT
CHINA’S GEO-ECONOMIC OUTREACH IN CENTRAL ASIAN COUNTRIES AND FUTURE PROSPECTCHINA’S GEO-ECONOMIC OUTREACH IN CENTRAL ASIAN COUNTRIES AND FUTURE PROSPECT
CHINA’S GEO-ECONOMIC OUTREACH IN CENTRAL ASIAN COUNTRIES AND FUTURE PROSPECT
jpsjournal1
 
Electric vehicle and photovoltaic advanced roles in enhancing the financial p...
Electric vehicle and photovoltaic advanced roles in enhancing the financial p...Electric vehicle and photovoltaic advanced roles in enhancing the financial p...
Electric vehicle and photovoltaic advanced roles in enhancing the financial p...
IJECEIAES
 
Engineering Drawings Lecture Detail Drawings 2014.pdf
Engineering Drawings Lecture Detail Drawings 2014.pdfEngineering Drawings Lecture Detail Drawings 2014.pdf
Engineering Drawings Lecture Detail Drawings 2014.pdf
abbyasa1014
 
A review on techniques and modelling methodologies used for checking electrom...
A review on techniques and modelling methodologies used for checking electrom...A review on techniques and modelling methodologies used for checking electrom...
A review on techniques and modelling methodologies used for checking electrom...
nooriasukmaningtyas
 
Engine Lubrication performance System.pdf
Engine Lubrication performance System.pdfEngine Lubrication performance System.pdf
Engine Lubrication performance System.pdf
mamamaam477
 
ACEP Magazine edition 4th launched on 05.06.2024
ACEP Magazine edition 4th launched on 05.06.2024ACEP Magazine edition 4th launched on 05.06.2024
ACEP Magazine edition 4th launched on 05.06.2024
Rahul
 
Recycled Concrete Aggregate in Construction Part II
Recycled Concrete Aggregate in Construction Part IIRecycled Concrete Aggregate in Construction Part II
Recycled Concrete Aggregate in Construction Part II
Aditya Rajan Patra
 
Question paper of renewable energy sources
Question paper of renewable energy sourcesQuestion paper of renewable energy sources
Question paper of renewable energy sources
mahammadsalmanmech
 

Recently uploaded (20)

basic-wireline-operations-course-mahmoud-f-radwan.pdf
basic-wireline-operations-course-mahmoud-f-radwan.pdfbasic-wireline-operations-course-mahmoud-f-radwan.pdf
basic-wireline-operations-course-mahmoud-f-radwan.pdf
 
ISPM 15 Heat Treated Wood Stamps and why your shipping must have one
ISPM 15 Heat Treated Wood Stamps and why your shipping must have oneISPM 15 Heat Treated Wood Stamps and why your shipping must have one
ISPM 15 Heat Treated Wood Stamps and why your shipping must have one
 
哪里办理(csu毕业证书)查尔斯特大学毕业证硕士学历原版一模一样
哪里办理(csu毕业证书)查尔斯特大学毕业证硕士学历原版一模一样哪里办理(csu毕业证书)查尔斯特大学毕业证硕士学历原版一模一样
哪里办理(csu毕业证书)查尔斯特大学毕业证硕士学历原版一模一样
 
spirit beverages ppt without graphics.pptx
spirit beverages ppt without graphics.pptxspirit beverages ppt without graphics.pptx
spirit beverages ppt without graphics.pptx
 
Textile Chemical Processing and Dyeing.pdf
Textile Chemical Processing and Dyeing.pdfTextile Chemical Processing and Dyeing.pdf
Textile Chemical Processing and Dyeing.pdf
 
Literature Review Basics and Understanding Reference Management.pptx
Literature Review Basics and Understanding Reference Management.pptxLiterature Review Basics and Understanding Reference Management.pptx
Literature Review Basics and Understanding Reference Management.pptx
 
CSM Cloud Service Management Presentarion
CSM Cloud Service Management PresentarionCSM Cloud Service Management Presentarion
CSM Cloud Service Management Presentarion
 
Understanding Inductive Bias in Machine Learning
Understanding Inductive Bias in Machine LearningUnderstanding Inductive Bias in Machine Learning
Understanding Inductive Bias in Machine Learning
 
Recycled Concrete Aggregate in Construction Part III
Recycled Concrete Aggregate in Construction Part IIIRecycled Concrete Aggregate in Construction Part III
Recycled Concrete Aggregate in Construction Part III
 
Eric Nizeyimana's document 2006 from gicumbi to ttc nyamata handball play
Eric Nizeyimana's document 2006 from gicumbi to ttc nyamata handball playEric Nizeyimana's document 2006 from gicumbi to ttc nyamata handball play
Eric Nizeyimana's document 2006 from gicumbi to ttc nyamata handball play
 
Iron and Steel Technology Roadmap - Towards more sustainable steelmaking.pdf
Iron and Steel Technology Roadmap - Towards more sustainable steelmaking.pdfIron and Steel Technology Roadmap - Towards more sustainable steelmaking.pdf
Iron and Steel Technology Roadmap - Towards more sustainable steelmaking.pdf
 
Optimizing Gradle Builds - Gradle DPE Tour Berlin 2024
Optimizing Gradle Builds - Gradle DPE Tour Berlin 2024Optimizing Gradle Builds - Gradle DPE Tour Berlin 2024
Optimizing Gradle Builds - Gradle DPE Tour Berlin 2024
 
CHINA’S GEO-ECONOMIC OUTREACH IN CENTRAL ASIAN COUNTRIES AND FUTURE PROSPECT
CHINA’S GEO-ECONOMIC OUTREACH IN CENTRAL ASIAN COUNTRIES AND FUTURE PROSPECTCHINA’S GEO-ECONOMIC OUTREACH IN CENTRAL ASIAN COUNTRIES AND FUTURE PROSPECT
CHINA’S GEO-ECONOMIC OUTREACH IN CENTRAL ASIAN COUNTRIES AND FUTURE PROSPECT
 
Electric vehicle and photovoltaic advanced roles in enhancing the financial p...
Electric vehicle and photovoltaic advanced roles in enhancing the financial p...Electric vehicle and photovoltaic advanced roles in enhancing the financial p...
Electric vehicle and photovoltaic advanced roles in enhancing the financial p...
 
Engineering Drawings Lecture Detail Drawings 2014.pdf
Engineering Drawings Lecture Detail Drawings 2014.pdfEngineering Drawings Lecture Detail Drawings 2014.pdf
Engineering Drawings Lecture Detail Drawings 2014.pdf
 
A review on techniques and modelling methodologies used for checking electrom...
A review on techniques and modelling methodologies used for checking electrom...A review on techniques and modelling methodologies used for checking electrom...
A review on techniques and modelling methodologies used for checking electrom...
 
Engine Lubrication performance System.pdf
Engine Lubrication performance System.pdfEngine Lubrication performance System.pdf
Engine Lubrication performance System.pdf
 
ACEP Magazine edition 4th launched on 05.06.2024
ACEP Magazine edition 4th launched on 05.06.2024ACEP Magazine edition 4th launched on 05.06.2024
ACEP Magazine edition 4th launched on 05.06.2024
 
Recycled Concrete Aggregate in Construction Part II
Recycled Concrete Aggregate in Construction Part IIRecycled Concrete Aggregate in Construction Part II
Recycled Concrete Aggregate in Construction Part II
 
Question paper of renewable energy sources
Question paper of renewable energy sourcesQuestion paper of renewable energy sources
Question paper of renewable energy sources
 

Data Driven Industrial Digitalization through Reverse Engineering of Systems

  • 1. Data Driven Industrial Digitalization through Reverse Engineering of Systems Lokukaluge Prasad Perera September 12th, 2019 1st Workshop on Digitalization and Blockchain – Managerial and Organizational Implications University of South-Eastern Norway, Campus Vestfold.
  • 2. Outline • Industrial Digitalization. • Data Analytics. • From Newton's Law to Deep Neural Networks : Autoencoders. • Shipping Industrial Example. • Conclusions.
  • 3. Industrial Digitalization in Shipping " Poor data quality costs… the US economy around US$ 3.1 trillions per year"* "1 in 3 Business Leaders don't trust… the information they use to make decisions "* "27% of the respondents in a survey… were unsure of how much of their data sets are inaccurate"* *IBM, The four V's of Big Data, URL:http://www.ibmbigdatahub.com/infographic/four-vs-big-data, 2017.
  • 4. Why Data Analytics ..? • Conventional Models – Various Conventional Models in the shipping industry for various applications. – Some challenges in handling Big Data : erroneous data conditions, system-model uncertainty, estimation algorithm failures, data visualization challenges and high computational power. • Machine Learning & Statistical Analysis – Machine Learning (ML) & Statistical Analysis will play an important role in analyzing such data sets. – Statistical Analysis will guide ML Algorithms. – Towards Data Driven Models: Digital Models. – It is Geometrical… • Domain Knowledge – Ship Dynamics & Hydrodynamics. – Automation & Navigation Systems.
  • 5. Data Analytics Types – Digital model consists of data driven relationships. – Descriptive analytics identifies various data anomalies. – Diagnostic analytics recovers/removes such data anomalies. – Predictive analytics forecasts vessel and ship system behavior. – Visual analytics visualizes the same information. – The information creates Advanced Knowledge and that will lead to Industrial Intelligence. – Both advanced knowledge and industrial intelligence support Decision Analytics. – Decision analytics may consist of appropriate Key Performance Indicators (i.e. KPIs)
  • 6. Newton's Laws of Motion – "A body at rest will remain at rest, and a body in motion will remain in motion unless it is acted upon by an external force." – "The force acting on an object is equal to the mass of that object times its acceleration.“ F = ma where F is force, m is mass, and a is acceleration. – "For every action, there is an equal and opposite reaction." Source: https://www.livescience.com
  • 7. Newton's Laws of Motion F = ma F is force, m is mass a is acceleration.
  • 8. Sensor Measurements F = ma F is force, m is mass a is acceleration.
  • 9. Singular Values and Vectors F = ma => Z1 and Z2 => sensor noise F is force, m is mass a is acceleration. Z1,2 are singular vectors
  • 10. Data Projection F = ma => Z1 F is force, m is mass a is acceleration. Z1,2 are singular vectors Least Squares Fitting
  • 11. Reinvention of Newton's Laws of Motion F = ma F is force, m is mass a is acceleration. Z1,2 are singular vectors
  • 12. Reverse Engineering of Systems F = ma F is force, m is mass a is acceleration Z1,2 are singular vectors
  • 13. Deep Neural Networks: Autoencoders F = ma F is force, m is mass a is acceleration F a Z 1,2 R
  • 14. Advanced System Models F = ma + Fm where F is force, Fm is mean force, m is mass, a is acceleration
  • 15. Digital Models in High Dimensions
  • 16. Singular Values & Vectors – The structure of each data cluster is denoted by several vectors: singular vectors (i.e. associated with the respective singular values) – Singular values and vectors represent the building blocks of electrical and mechanical systems – System behavior, i.e. system information, can be accommodated into the same.
  • 17. Digital Models – Three-dimensional vector space with the right-hand coordinate system. – Three data clusters, i.e. system states, with the respective mean vectors. – Each data cluster consists of local operational information of the respective system. – The structure of each data cluster is denoted by several vectors: singular vectors (i.e. associated with the respective singular values). – Each singular vector consists of local operational information of the respective systems. – Each cluster is a linear model, i.e. Piecewise linearization: the best approximation of a nonlinear function as a piecewise linear function. – The system can jump from one state to another state in a high dimensional data space. – Some data clusters may relate to data anomalies or system abnormal events.
  • 18. Model Complexity – From Components to System of Systems – Various Model Levels – High dimensional Digital Models – From Big Data to Low Level Models
  • 19. Ship Performance & Navigation Data Set Parameter Mini. Max. 1. Avg. draft (m) 0 15 2. STW (Knots)- Speed through water 3 20 3. Engine power (kW) 1000 8000 4. Shaft speed (rpm) 20 120 5. Engine fuel cons. (Tons/day) 1 40 6. SOG (Knots) – Speed over ground 0 20 7. Trim (m) -2 6 8. Rel. wind speed (m/s) 0 25 9. Rel. wind direction (deg) 2 360 10. Aux. engine fuel cons. (Tons/day) 0 8
  • 20. Ship Engine Data in Histograms – The vessel is a bulk carrier with ship length: 225 (m) and beam: 32.29 (m) – Three parameters: engine speed, power and fuel consumption – Engine data are clustered around three Gaussian type distributions – Three engine modes of this vessel – Ship performance and navigation data sets are often clustered in a high dimensional space – Those clusters relate to vessel navigation and ship system operational conditions
  • 21. Ship Engine Data – Two parameters: engine speed and power. – Combined kernel density estimation (multivariate KDE) with the respective univariate KDEs. – Engine data are clustered around three Gaussian type distributions. – Three engine modes of this vessel. – Ship performance and navigation data sets are often clustered in a high dimensional space. – That introduce the discreteness (i.e. digital-ness) into the proposed models.
  • 22. Digital Models – Each cluster is a linear model, i.e. Piecewise linearization: the best approximation of a nonlinear function as a piecewise linear function. – The vessel & ship system can jump from one state to another state in a high dimensional data space. – Some data clusters may relate to data anomalies or system abnormal events.
  • 23. – Digital models interact with the descriptive and diagnostic analytics to improve the data quality – Data anomaly filter 1: missing data points and preliminary data anomalies (i.e. Min-Max values) detected – Data anomaly filter 2: Additional data anomalies (i.e. the outliers of digital models) detected – Data anomalies send to separate groups where the data anomalies against known and unknown sensor and DAQ faults and system abnormalities compared – Data sets from anomaly group 1 and 2 transfer through the data recovery filter and digital models – A considerable amount of data anomalies can be recovered by this step Data Anomaly Detection and Recovery Procedure
  • 24. Data Anomalies in Newton's Laws of Motion F = ma F is force, m is mass a is acceleration. Z1,2 are singular vectors
  • 25. Data Anomaly Detection and Recovery Procedure: Filter 2 – Digital models interact with the descriptive and diagnostic analytics to improve the data quality – Data anomaly filter 1: missing data points and preliminary data anomalies (i.e. Min-Max values) detected – Data anomaly filter 2: Additional data anomalies (i.e. the outliers of digital models) detected – Data anomalies send to separate groups where the data anomalies against known and unknown sensor and DAQ faults and system abnormalities compared – Data sets from anomaly group 1 and 2 transfer through the data recovery filter and digital models – A considerable amount of data anomalies can be recovered by this step
  • 26. Data Anomaly Detection and Recovery Procedure: Filter 2 – Digital models interact with the descriptive and diagnostic analytics to improve the data quality – Data anomaly filter 1: missing data points and preliminary data anomalies (i.e. Min-Max values) detected – Data anomaly filter 2: Additional data anomalies (i.e. the outliers of digital models) detected – Data anomalies send to separate groups where the data anomalies against known and unknown sensor and DAQ faults and system abnormalities compared – Data sets from anomaly group 1 and 2 transfer through the data recovery filter and digital models – A considerable amount of data anomalies can be recovered by this step
  • 27. Data Anomaly Detection and Recovery Procedure: Data Recovery – Digital models interact with the descriptive and diagnostic analytics to improve the data quality – Data anomaly filter 1: missing data points and preliminary data anomalies (i.e. Min-Max values) detected – Data anomaly filter 2: Additional data anomalies (i.e. the outliers of digital models) detected – Data anomalies send to separate groups where the data anomalies against known and unknown sensor and DAQ faults and system abnormalities compared – Data sets from anomaly group 1 and 2 transfer through the data recovery filter and digital models – A considerable amount of data anomalies can be recovered by this step
  • 28. Data Anomaly Detection & Recovery Procedure: Filter 2
  • 29. Data Visualization of Newton's Laws of Motion
  • 30. Visual Analytics – Digital models should be visualized to extract relevant parameter relationships. – Covariance values of the data sets are represented by singular vectors. – Each vector will present correlation information among the respective parameters.
  • 31. Visual Analytics – Digital models should be visualized to extract relevant parameter relationships in a High Dimensional Space. – Covariance values of the data sets are represented by singular vectors. – Each vector will present correlation information among the respective parameters.
  • 32. Visual Analytics – Digital models should be visualized to extract relevant parameter relationships in a High Dimensional Space. – Covariance values of the data sets are represented by singular vectors. – Each vector will present correlation information among the respective parameters. – The top singular vector is presented in the outer circle. – The bottom singular vector is presented in the inner circle.
  • 35. Predictive Analytics – The outputs of the predictive analytics are predicted vessel and ship system behavior. – The information creates advanced knowledge and facilitates towards industrial intelligence
  • 38. Conclusions – Novel mathematical framework to support industrial digitization of shipping is presented: i.e. from Industrial IoT to Predictive Analytics. – Data analytics can… • self-learn (i.e. the data structure can learn itself) • self-clean (i.e. data anomalies can be detected, isolated and recovered by considering the outliers of the data structure), • self-compress and expend (i.e. the respective parameters in the data sets can be reduced and expanded by considering the same data structure) • self-visualize (i.e. the respective data structures can be used for both vessel and ship system performance observations) – That introduces Intelligent Analytics to any industry and also provides important solutions to the big data challenges under the Industrial Digitalization.