© 2023, Inawisdom Ltd.
MAY 2023
USING ANALYTICS AND MACHINE LEARNING IN
ENGINEERING AND CONSTRUCTION
ABOUT INAWISDOM
“
Inawisdom was
founded with a
simple goal to give
our customers the
ability to exploit
every aspect of
their data using AI.”
- Robin Meehan,
co-founder & MD
Inawisdom is based in the UK (London & Ipswich) and Netherlands,
working with global organisations of all sizes across Europe and the
Middle East.
Inawisdom has a team of proven experts and is an Amazon Web
Services (AWS) Premier Services Partner, all-in AWS and leads the
way in full-stack Data, Engineering, Advanced Analytics and AI/ML.
Inawisdom was founded in 2016 to help companies drive ultimate
value from their own data assets and beyond.
Inawisdom is a leading specialist in Data, Advanced Analytics and AI
/ ML with proven, in-depth experience in building, deploying and
delivering innovative data solutions for our customers.
Who
Why
Where
How
We’ve been an AWS Partner since 2017
AN AWARD-WINNING AWS PARTNER
As an all-in AWS business, our development and delivery teams
live and breathe AWS services.
Our team holds over 180 AWS certifications and accreditations.
We maintain a close relationship with the AWS team, supporting
and staying up-to-date with all the latest developments.
Our team members hold individual certifications
and accreditations in the following areas:
► ML Partner of the Year 2020
► Differentiation Partner of the Year 2019
► Global Launch Partner – CCI
► Launch Partner – AWS UAE Region
► AWS Ambassadors X2
We hold 9 competencies and service designations, reflecting business-wide
expertise in key areas:
Our Qualifications
All of our consultants hold at least 1
AWS certification
Our AWS Ambassador has ranked
#1 in EMEA two years in a row
Inawisdom’s full-stack capability
OUR SERVICES
Business
Differentiation / Value
Data Driven
Business Decisions
Cloud Transformation
Adoption and Scale
Digital
Enablement
AI and Machine Learning
Data & Analytics
Data Foundations
Cloud Infrastructure
Landing Zone, Control Tower, migration
Proprietary platform that enables secure and rapid data capture and
analysis
RAMP – INAWISDOM’S CUTTING-EDGE TECHNOLOGY
Data Ingestion
Service Layer
Anomaly
Detection
Entity
Extraction
Natural
Language
Processing
Name
matching
Exploitation Layer
Prediction Classification
Enterprise
Security
Streaming Batch
Monitoring
High
Availability
Automated
Deployment
Operational
System
Management
Dashboard
Standard BI
Discovery
Dashboard
Human
Structured
e.g. SQL
Unstructured
e.g. documents
Devices
e.g. IoT
Public open
datasets
Public APIs
e.g. Twitter
REFERENCE ARCHITECTURE
USE CASES & CUSTOMER
SUCCESS STORIES
AI/ML USE CASES IN CONSTRUCTION AND
ENGINEERING
PPE
Detection
Simulation &
Metaverse
Budget Management
& Forecasting
Invoice
Processing
Risk
Management
Supply Chain
Management & ETA
Contract Summary
& Creation
Site
Management
Project
Scheduling
Fault
Detection
AR &
Digital Twin
Predictive
Maintenance
Intelligent
Document Search /
Knowledge Base
AI in Action: Using AI and ML for Predictive Maintenance
CASE STUDY
The Customer: The Sector:
The Result:
The Solution:
The Requirement: Predictive Maintenance service offering - to deliver
innovation and increased value to vehicle owners and operators
Construction Equipment
Manufacturing
Ø Build of an IoT-enabled Data Lake to ingest sensor data and alerts from
250,000 vehicles across the EMEA and American markets
Ø Utilised AWS Control Tower to ensure AWS account management, security
and automation for the customers, using Guardrails for governance
Ø Ingested data at three velocities (fast, med, slow) into the common store
Ø Transformed the data to an efficient, common format within a single logical
database, with querying and reporting capabilities
Ø Driving the evolution of new data-led solutions for vehicle owners, dealers,
manufacturers and operators
Ø Using Machine Learning for accurate predictive maintenance
Ø Expanded data to include vehicle and devices from the Asian market
Ø Created a roadmap to enable enhanced service offerings including:
§ Implementation of real-time analytics and alerting to customers
§ Manage other devices and manufacturing data sources
The Customer:
AI in Action: Health and Safety
The Sector: Construction
The Result:
The Solution:
The Requirement: Increase the profitability of projects by predicting likely
overspend
Ø Data Lake using AWS Data Warehouse tool Redshift for construction
projects, containing past project data that includes budget, hours and
health and safety incident data
Ø Our exploration of the data found the number of H&S incidents was a
strong indicator of poorly run sites, and poorly run sites historically
incurred higher overspend
Ø Machine Learning model was built in Amazon SageMaker (cloud-based
Machine Learning platform) to predict likely number of incidents
Multinational
infrastructure group
Ø Full Productionisation of the Data Lake including ingesting Field360 and
unstructured data from Project Portal
Ø Data Lakes are now judged to be essential and are used on joint ventures
Ø Project overruns lowered due to predicting likely number of incidents that
acted as proxy for how well projects are run
CASE STUDY
The Customer:
The Sector: Steel
Manufacturing industry
Ø The client launched the core service to their customers in April 2022.
Ø Further phases are underway to provide valuable insights into devices statistics
Ø Reduced product defects by using Machine Learning used detect when
Fabricators etc are operating outside of normal conditions.
The Solution:
The Requirement: Leverage Internet of Things (IoT) functionality to receive data
from machine owners, making the data available to their new Mobile Apps and
Web interface. Foundation for analytics to enable better insights into the product
performance, enhance service and customer experience.
Ø Set up a secure service for connecting devices, ingesting machine status using
IoT Greengrass on the Edge and processing the data
Ø Developed a Data Lake House platform, with transformations and a rich API so
that customers can remotely view machine data and receive notifications of any
issues with individual machines.
Ø The platform is largely based on “Serverless” technologies. This was an agile
delivery, working closely with the customer product owner and front-end team.
The project took 4 months and is designed to quickly scale up to hundreds of
customers and thousands of machines
The Result:
Machine Operator
AI in Action: Connected Machines using AWS IOT
CASE STUDY
The Customer:
AI in Action: Personal Protective Equipment
The Result:
The Solution:
The Requirement: The ability to detect that the correct PPE is being
warn on a site to reduce risk of H&S incident
Ø Uses a ADLINK Neon-1040 Camera and VISI-AI device at the site that
runs a custom computer vision model
Ø The custom computer vision model is trained in AWS SageMaker to
provide the GPU compute power needed and then converted to
OpenVINO to run on device
Ø Built on TensorFlow and required the labeling of images to train the
model to detect the PPE using AWS Grown Truth
Ø The successful detection of:
§ Safety helmet
§ Hi-Vis jacket
§ Person
The Sector: Construction
Multinational
infrastructure group
CASE STUDY
BEST PERFORMING MODEL
Cross Industry Use Cases
CASE STUDY
AI in Action: Driving Innovation to Optimise Yields in Farming
The Customer: The Sector:
The Solution:
The Result:
The Requirement: Image Processing and Deep Learning – helping to
transform Production Forecasting in Cashew Farming
Ø Created a commercially-ready platform for further customer adoption
Ø Delivered AI models that accurately forecast crop production to enable
better definition of yield and onward value
Ø Vastly reduced the manual processes of image matching that prevented
working at scale
Ø E2E solution automation which enable high scalability for the solution
Ø Built and productionised innovative AI models, embedding ML and deep
learning into image recognition to identify cashew plant signature
Ø Created a productionised, scalable infrastructure to AWS best practice,
allowing for further AI models and leveraging the power of AWS cloud
Ø Delivered a cloud-based tool, using Amazon SageMaker, to speed up the
annotation of the cashew plant images and validate image analysis
AgriTech
Improvement in the ETA accuracies i.e. ETA reliability has the potential to:
BENEFIT IDENTIFICATION
Increase Brand
Value and
Reputation
Reduce inbound
customer service
calls
Provide crucial insights
for operational
improvements
Reduce cash-in-
transit risk
Increase efficiency
for staff on the
ground
Higher
Value
ETAs can improve
• Using Machine Learning to
identify patterns in historical
and route completion data
• Breaking the problem
statement into dwell / transit
component for each leg
• Applying ML to each
component
• Using SME knowledge to
guide ML models and achieve
higher performances
POC success:
ETA improvement
22% → 32%
* 1-leg journeys only
30% of all deliveries
Tangible Value
ETA accuracy increase by:
10 percentage points
Potential:
1%-5% Increase in sales revenue
per quarter
Reliable ETAs can increase customers’
perception of the Brand and reputation
An increase in the Brand value can
significantly increase sales
According to a conversative draft
benefits model:
* Automotive Industry
Current ETAs
For 1-leg journeys
2nd
Quarter 2021
Inawisdom ETAs predictions
For 1-leg journeys
2nd
Quarter 2021
AI in Action: ETA Prediction in Automotive
More reliable ETAs are made possible
by:
CASE STUDY
The Customer:
AI in Action: From Document-led to a Data-driven marketplace
The Sector: Insurance
The Solution:
The Result:
The Requirement Revolutionise the approach for under-writing risk in
Specialty Insurance – leveraging AI/ML automated document processing
Leading Global Specialty
Insurer (Lloyds London syndicate)
Ø Deployed a cutting-edge AWS data platform, empowered by AI/ML, as part
of a highly strategic implementation
Ø Established an automated, scalable underwriting process to improve
underwriters’ day to day operations and drive business growth
Ø Created intelligent AI solution to extract key data points (pricing/policies)
from broker documents held in multiple types (pdf, email, xls)
Ø Enabling faster velocity and quality for risk writing, encompassing various
components and personas, to drive profitable business
Ø Exploiting new innovations to improve accuracy in rating, forecasting, pricing
and binding risk
Ø Reducing operational costs
Ø Creating a next-generation of market solutions to enable the business to be
‘future fit’
Ø Leading the digital revolution within the underwriting and risk process
CASE STUDY
AI in Action: Predictive Aftersales to drive success
CASE STUDY
The Customer: The Sector: Automotive
Ø Predictions for parts wear, service due dates, along with customer mileage
predictions (including a method for compensating for COVID-19) allows
marketing to deliver the right message at the right time
Ø Aftersales retention and loyalty increases significantly
Ø Increases sales revenues impacting the bottom line
Ø Improved customer experience
The Solution:
The Requirement: Predictive Aftersales – A large automotive brand wanted
to be able to utilise historic data to proactively target customers with relevant
and timely aftersales marketing
Ø Deployed RAMP accelerator to rapidly create a secure analytics platform
on AWS
Ø Ingested historic data on vehicle usage, service history, parts & labour
Ø Trained and productionised ML Models for mileage and brakes
Ø Applied customer behavioural models to create a sales conversion
prediction tool
The Result:
Columba House,
Adastral Park, Martlesham Heath
Ipswich, Suffolk, IP5 3RE
www.inawisdom.com
phil@inawisdom.com

Inawisdom Overview - construction.pdf

  • 1.
    © 2023, InawisdomLtd. MAY 2023 USING ANALYTICS AND MACHINE LEARNING IN ENGINEERING AND CONSTRUCTION
  • 2.
    ABOUT INAWISDOM “ Inawisdom was foundedwith a simple goal to give our customers the ability to exploit every aspect of their data using AI.” - Robin Meehan, co-founder & MD Inawisdom is based in the UK (London & Ipswich) and Netherlands, working with global organisations of all sizes across Europe and the Middle East. Inawisdom has a team of proven experts and is an Amazon Web Services (AWS) Premier Services Partner, all-in AWS and leads the way in full-stack Data, Engineering, Advanced Analytics and AI/ML. Inawisdom was founded in 2016 to help companies drive ultimate value from their own data assets and beyond. Inawisdom is a leading specialist in Data, Advanced Analytics and AI / ML with proven, in-depth experience in building, deploying and delivering innovative data solutions for our customers. Who Why Where How
  • 3.
    We’ve been anAWS Partner since 2017 AN AWARD-WINNING AWS PARTNER As an all-in AWS business, our development and delivery teams live and breathe AWS services. Our team holds over 180 AWS certifications and accreditations. We maintain a close relationship with the AWS team, supporting and staying up-to-date with all the latest developments. Our team members hold individual certifications and accreditations in the following areas: ► ML Partner of the Year 2020 ► Differentiation Partner of the Year 2019 ► Global Launch Partner – CCI ► Launch Partner – AWS UAE Region ► AWS Ambassadors X2 We hold 9 competencies and service designations, reflecting business-wide expertise in key areas: Our Qualifications All of our consultants hold at least 1 AWS certification Our AWS Ambassador has ranked #1 in EMEA two years in a row
  • 4.
    Inawisdom’s full-stack capability OURSERVICES Business Differentiation / Value Data Driven Business Decisions Cloud Transformation Adoption and Scale Digital Enablement AI and Machine Learning Data & Analytics Data Foundations Cloud Infrastructure Landing Zone, Control Tower, migration
  • 5.
    Proprietary platform thatenables secure and rapid data capture and analysis RAMP – INAWISDOM’S CUTTING-EDGE TECHNOLOGY Data Ingestion Service Layer Anomaly Detection Entity Extraction Natural Language Processing Name matching Exploitation Layer Prediction Classification Enterprise Security Streaming Batch Monitoring High Availability Automated Deployment Operational System Management Dashboard Standard BI Discovery Dashboard Human Structured e.g. SQL Unstructured e.g. documents Devices e.g. IoT Public open datasets Public APIs e.g. Twitter
  • 6.
  • 7.
    USE CASES &CUSTOMER SUCCESS STORIES
  • 8.
    AI/ML USE CASESIN CONSTRUCTION AND ENGINEERING PPE Detection Simulation & Metaverse Budget Management & Forecasting Invoice Processing Risk Management Supply Chain Management & ETA Contract Summary & Creation Site Management Project Scheduling Fault Detection AR & Digital Twin Predictive Maintenance Intelligent Document Search / Knowledge Base
  • 9.
    AI in Action:Using AI and ML for Predictive Maintenance CASE STUDY The Customer: The Sector: The Result: The Solution: The Requirement: Predictive Maintenance service offering - to deliver innovation and increased value to vehicle owners and operators Construction Equipment Manufacturing Ø Build of an IoT-enabled Data Lake to ingest sensor data and alerts from 250,000 vehicles across the EMEA and American markets Ø Utilised AWS Control Tower to ensure AWS account management, security and automation for the customers, using Guardrails for governance Ø Ingested data at three velocities (fast, med, slow) into the common store Ø Transformed the data to an efficient, common format within a single logical database, with querying and reporting capabilities Ø Driving the evolution of new data-led solutions for vehicle owners, dealers, manufacturers and operators Ø Using Machine Learning for accurate predictive maintenance Ø Expanded data to include vehicle and devices from the Asian market Ø Created a roadmap to enable enhanced service offerings including: § Implementation of real-time analytics and alerting to customers § Manage other devices and manufacturing data sources
  • 10.
    The Customer: AI inAction: Health and Safety The Sector: Construction The Result: The Solution: The Requirement: Increase the profitability of projects by predicting likely overspend Ø Data Lake using AWS Data Warehouse tool Redshift for construction projects, containing past project data that includes budget, hours and health and safety incident data Ø Our exploration of the data found the number of H&S incidents was a strong indicator of poorly run sites, and poorly run sites historically incurred higher overspend Ø Machine Learning model was built in Amazon SageMaker (cloud-based Machine Learning platform) to predict likely number of incidents Multinational infrastructure group Ø Full Productionisation of the Data Lake including ingesting Field360 and unstructured data from Project Portal Ø Data Lakes are now judged to be essential and are used on joint ventures Ø Project overruns lowered due to predicting likely number of incidents that acted as proxy for how well projects are run CASE STUDY
  • 11.
    The Customer: The Sector:Steel Manufacturing industry Ø The client launched the core service to their customers in April 2022. Ø Further phases are underway to provide valuable insights into devices statistics Ø Reduced product defects by using Machine Learning used detect when Fabricators etc are operating outside of normal conditions. The Solution: The Requirement: Leverage Internet of Things (IoT) functionality to receive data from machine owners, making the data available to their new Mobile Apps and Web interface. Foundation for analytics to enable better insights into the product performance, enhance service and customer experience. Ø Set up a secure service for connecting devices, ingesting machine status using IoT Greengrass on the Edge and processing the data Ø Developed a Data Lake House platform, with transformations and a rich API so that customers can remotely view machine data and receive notifications of any issues with individual machines. Ø The platform is largely based on “Serverless” technologies. This was an agile delivery, working closely with the customer product owner and front-end team. The project took 4 months and is designed to quickly scale up to hundreds of customers and thousands of machines The Result: Machine Operator AI in Action: Connected Machines using AWS IOT CASE STUDY
  • 12.
    The Customer: AI inAction: Personal Protective Equipment The Result: The Solution: The Requirement: The ability to detect that the correct PPE is being warn on a site to reduce risk of H&S incident Ø Uses a ADLINK Neon-1040 Camera and VISI-AI device at the site that runs a custom computer vision model Ø The custom computer vision model is trained in AWS SageMaker to provide the GPU compute power needed and then converted to OpenVINO to run on device Ø Built on TensorFlow and required the labeling of images to train the model to detect the PPE using AWS Grown Truth Ø The successful detection of: § Safety helmet § Hi-Vis jacket § Person The Sector: Construction Multinational infrastructure group CASE STUDY
  • 13.
  • 14.
  • 15.
    CASE STUDY AI inAction: Driving Innovation to Optimise Yields in Farming The Customer: The Sector: The Solution: The Result: The Requirement: Image Processing and Deep Learning – helping to transform Production Forecasting in Cashew Farming Ø Created a commercially-ready platform for further customer adoption Ø Delivered AI models that accurately forecast crop production to enable better definition of yield and onward value Ø Vastly reduced the manual processes of image matching that prevented working at scale Ø E2E solution automation which enable high scalability for the solution Ø Built and productionised innovative AI models, embedding ML and deep learning into image recognition to identify cashew plant signature Ø Created a productionised, scalable infrastructure to AWS best practice, allowing for further AI models and leveraging the power of AWS cloud Ø Delivered a cloud-based tool, using Amazon SageMaker, to speed up the annotation of the cashew plant images and validate image analysis AgriTech
  • 17.
    Improvement in theETA accuracies i.e. ETA reliability has the potential to: BENEFIT IDENTIFICATION Increase Brand Value and Reputation Reduce inbound customer service calls Provide crucial insights for operational improvements Reduce cash-in- transit risk Increase efficiency for staff on the ground Higher Value ETAs can improve • Using Machine Learning to identify patterns in historical and route completion data • Breaking the problem statement into dwell / transit component for each leg • Applying ML to each component • Using SME knowledge to guide ML models and achieve higher performances POC success: ETA improvement 22% → 32% * 1-leg journeys only 30% of all deliveries Tangible Value ETA accuracy increase by: 10 percentage points Potential: 1%-5% Increase in sales revenue per quarter Reliable ETAs can increase customers’ perception of the Brand and reputation An increase in the Brand value can significantly increase sales According to a conversative draft benefits model: * Automotive Industry Current ETAs For 1-leg journeys 2nd Quarter 2021 Inawisdom ETAs predictions For 1-leg journeys 2nd Quarter 2021 AI in Action: ETA Prediction in Automotive More reliable ETAs are made possible by: CASE STUDY
  • 18.
    The Customer: AI inAction: From Document-led to a Data-driven marketplace The Sector: Insurance The Solution: The Result: The Requirement Revolutionise the approach for under-writing risk in Specialty Insurance – leveraging AI/ML automated document processing Leading Global Specialty Insurer (Lloyds London syndicate) Ø Deployed a cutting-edge AWS data platform, empowered by AI/ML, as part of a highly strategic implementation Ø Established an automated, scalable underwriting process to improve underwriters’ day to day operations and drive business growth Ø Created intelligent AI solution to extract key data points (pricing/policies) from broker documents held in multiple types (pdf, email, xls) Ø Enabling faster velocity and quality for risk writing, encompassing various components and personas, to drive profitable business Ø Exploiting new innovations to improve accuracy in rating, forecasting, pricing and binding risk Ø Reducing operational costs Ø Creating a next-generation of market solutions to enable the business to be ‘future fit’ Ø Leading the digital revolution within the underwriting and risk process CASE STUDY
  • 19.
    AI in Action:Predictive Aftersales to drive success CASE STUDY The Customer: The Sector: Automotive Ø Predictions for parts wear, service due dates, along with customer mileage predictions (including a method for compensating for COVID-19) allows marketing to deliver the right message at the right time Ø Aftersales retention and loyalty increases significantly Ø Increases sales revenues impacting the bottom line Ø Improved customer experience The Solution: The Requirement: Predictive Aftersales – A large automotive brand wanted to be able to utilise historic data to proactively target customers with relevant and timely aftersales marketing Ø Deployed RAMP accelerator to rapidly create a secure analytics platform on AWS Ø Ingested historic data on vehicle usage, service history, parts & labour Ø Trained and productionised ML Models for mileage and brakes Ø Applied customer behavioural models to create a sales conversion prediction tool The Result:
  • 20.
    Columba House, Adastral Park,Martlesham Heath Ipswich, Suffolk, IP5 3RE www.inawisdom.com phil@inawisdom.com