SlideShare a Scribd company logo
PAM3: Machine Learning in the
Railway Industry
Dattaraj J Rao – Senior Architect – GE Transportation
(@DattarajR)
Scott Nelson – Product Manager – GE Transportation
2PREDIX TRANSFORM
Agenda
LocoVISION – Eyes for the Train1
Business problem and Value story
Computer Vision models
The PREDIX Advantage
DEMO
2
3
4
5
3PREDIX TRANSFORM
LocoVISION – Eyes for the Train
•  High-definition cameras on Locomotive
•  Monitor Track geometry, Assets
•  Computer Vision
4PREDIX TRANSFORM
Business problem and Value story
•  Track Inspection: Manual, Time consuming
•  Too late to find defects - Coverage
•  In-accurate PTC Asset database
Image Sources: ntsb.gov, Wikipedia.org
PTC = Positive Train Control
5PREDIX TRANSFORM
Picture
Here
Geometry-based approach
•  Extract geometry from images
•  Isolate features of interest
•  Define “rules” for anomalies
Computer Vision models
Machine Learning method
•  Image as pixel data array
•  Positive and Negative images
•  Self-learning from data
6PREDIX TRANSFORM
The PREDIX Advantage
•  Common Platform – Data Acquisition to Action
•  BLOB store for Video + metadata (GPS)
•  On-demand + Batch Analytics in Cloud
DATA ACQUISITION PREDIX 2.0 PRESENTATION
§  COMPUTER VISION MODELS
§  MACHINE LEARNING MODELS
BLOB STORE
ACTION
PREDIX MACHINE
7PREDIX TRANSFORM
DEMO
https://lviewer-dattaraj.run.aws-usw02-pr.ice.predix.io/
General Electric reserves the right to make changes in specifications and features, or discontinue the product or service described at any time, without notice or obligation. These materials do
not constitute a representation, warranty or documentation regarding the product or service featured. Illustrations are provided for informational purposes, and your configuration may differ. This
information does not constitute legal, financial, coding, or regulatory advice in connection with your use of the product or service. Please consult your professional advisors for any such advice.
GE, Predix and the GE Monogram are trademarks of General Electric Company. ©2016 General Electric Company – All rights reserved.

More Related Content

PDF
PAN1: Thermal Imaging Analysis ( Predix Transform 2016)
PDF
PEM2: Control Applications Portfolio from GE Power
PDF
IND3: Predix for Transportation (Predix Transform 2016)
PDF
D4: Predix Cool Features (Predix Transform 2016)
PDF
E4: Building Your First Predix App (Predix Transform 2016)
PDF
PAM1: Managing Assets at Scale
PDF
PCF1: Cloud Foundry Diego ( Predix Transform 2016)
PDF
E5: Predix Security with ACS & UAA (Predix Transform 2016)
PAN1: Thermal Imaging Analysis ( Predix Transform 2016)
PEM2: Control Applications Portfolio from GE Power
IND3: Predix for Transportation (Predix Transform 2016)
D4: Predix Cool Features (Predix Transform 2016)
E4: Building Your First Predix App (Predix Transform 2016)
PAM1: Managing Assets at Scale
PCF1: Cloud Foundry Diego ( Predix Transform 2016)
E5: Predix Security with ACS & UAA (Predix Transform 2016)

What's hot (20)

PDF
D02: Performance Engineering and Testing of Predix Apps (Predix Transform 2016)
PDF
D2: Predix Migration & IT Integration (Predix Transform 2016)
PDF
IIA1: Industrial Control Systems 101 (Predix Transform 2016)
PDF
E3: Edge and Cloud Connectivity (Predix Transform 2016)
PDF
Predix Builder Roadshow
PPTX
E1: Building the Digital Twin (Predix Transform 2016)
PDF
Cloud Foundry Summit 2015: Cloud Foundry and IoT Protocol Support
PDF
Efficient IT operations using monitoring systems and standardized tools - Ici...
PPTX
IoT Platform Meetup - GE
PDF
S1: Predix ISV Partner Program (Predix Transform 2016)
PDF
Jawsug hpc@jaws festa2016
PPTX
Predix Data Fabric & Digital Twin Framework- Platform for Continuous Learning...
PDF
Cheryl Wiebe - Advanced Analytics in the Industrial World
PPTX
BTech Projects in Scilab
PDF
Meetup talk Red Hat OpenShift service mesh
PDF
Experiments in Predix: Ramping up by Mixing Theory and Practice
PPTX
Health index and on line condition monitoring ELVIS event Marcus Stenstrand
PDF
„GitOps with Flux and Flagger“
PDF
Real-time analytics in IoT by Sam Vanhoutte (@Building The Future 2019)
PDF
[ Capella Day 2019 ] Capella integration with Teamcenter
D02: Performance Engineering and Testing of Predix Apps (Predix Transform 2016)
D2: Predix Migration & IT Integration (Predix Transform 2016)
IIA1: Industrial Control Systems 101 (Predix Transform 2016)
E3: Edge and Cloud Connectivity (Predix Transform 2016)
Predix Builder Roadshow
E1: Building the Digital Twin (Predix Transform 2016)
Cloud Foundry Summit 2015: Cloud Foundry and IoT Protocol Support
Efficient IT operations using monitoring systems and standardized tools - Ici...
IoT Platform Meetup - GE
S1: Predix ISV Partner Program (Predix Transform 2016)
Jawsug hpc@jaws festa2016
Predix Data Fabric & Digital Twin Framework- Platform for Continuous Learning...
Cheryl Wiebe - Advanced Analytics in the Industrial World
BTech Projects in Scilab
Meetup talk Red Hat OpenShift service mesh
Experiments in Predix: Ramping up by Mixing Theory and Practice
Health index and on line condition monitoring ELVIS event Marcus Stenstrand
„GitOps with Flux and Flagger“
Real-time analytics in IoT by Sam Vanhoutte (@Building The Future 2019)
[ Capella Day 2019 ] Capella integration with Teamcenter

Viewers also liked (9)

PDF
PEM1: Device Authentication in IIOT ( Predix Transform 2016)
PPTX
My Top Five DevOps Learnings
PDF
D6: Cloud Directions ( Predix Transform 2016)
PPTX
GE Predix - The IIoT Platform
PDF
IIA8: Smartsignal Goes Microservices (Predix Transform 2016)
PDF
IIA4: Open Source and the Enterprise ( Predix Transform 2016)
PPSX
GE IOT Predix Time Series & Data Ingestion Service using Apache Apex (Hadoop)
PPTX
PPTX
Digital twins - Technology that is Changing Industry
PEM1: Device Authentication in IIOT ( Predix Transform 2016)
My Top Five DevOps Learnings
D6: Cloud Directions ( Predix Transform 2016)
GE Predix - The IIoT Platform
IIA8: Smartsignal Goes Microservices (Predix Transform 2016)
IIA4: Open Source and the Enterprise ( Predix Transform 2016)
GE IOT Predix Time Series & Data Ingestion Service using Apache Apex (Hadoop)
Digital twins - Technology that is Changing Industry

Similar to PAM3: Machine Learning in the Railway Industry ( Predix Transform 2016) (20)

PDF
LocoVISION Video Analytics - Indian Railways Tech conference
PDF
Pursuing the digital railroad
PDF
Predictive analytics in mobility
PDF
Digital Transformation in Rail, Science Fiction or Reality?
PDF
Digital Twin For The Railway Network
PPTX
Predix Analytics
PDF
AWS Summit Singapore 2019 | The Smart Way to Build an AI & ML Strategy for Yo...
PPTX
Ge’s journey to becoming a digital industrial company
PPTX
Shiva Amiri, Chief Product Officer, RTDS Inc. at MLconf SEA - 5/01/15
PDF
AI meets Big Data
PDF
Traditional Machine Learning and Deep Learning on OpenPOWER/POWER systems
PPTX
Pushing Machine Learning Down the Security Stack to Make It More Effective fo...
PPTX
7 Predictive Analytics, Spark , Streaming use cases
PDF
Enterprise deep learning lessons bodkin o reilly ai sf 2017
PDF
Asset information and data management smart rail
PDF
Data Analytics for IoT
PPTX
Machine Learning with Apache Spark
PDF
Sumyag profile deck
PDF
Predictive Maintenance - Predict the Unpredictable
PDF
IW13 Keynote, Bill Ruh, GE Software—The Emerging Industrial Internet
LocoVISION Video Analytics - Indian Railways Tech conference
Pursuing the digital railroad
Predictive analytics in mobility
Digital Transformation in Rail, Science Fiction or Reality?
Digital Twin For The Railway Network
Predix Analytics
AWS Summit Singapore 2019 | The Smart Way to Build an AI & ML Strategy for Yo...
Ge’s journey to becoming a digital industrial company
Shiva Amiri, Chief Product Officer, RTDS Inc. at MLconf SEA - 5/01/15
AI meets Big Data
Traditional Machine Learning and Deep Learning on OpenPOWER/POWER systems
Pushing Machine Learning Down the Security Stack to Make It More Effective fo...
7 Predictive Analytics, Spark , Streaming use cases
Enterprise deep learning lessons bodkin o reilly ai sf 2017
Asset information and data management smart rail
Data Analytics for IoT
Machine Learning with Apache Spark
Sumyag profile deck
Predictive Maintenance - Predict the Unpredictable
IW13 Keynote, Bill Ruh, GE Software—The Emerging Industrial Internet

Recently uploaded (20)

PDF
Dropbox Q2 2025 Financial Results & Investor Presentation
PDF
Review of recent advances in non-invasive hemoglobin estimation
PDF
KodekX | Application Modernization Development
PDF
How UI/UX Design Impacts User Retention in Mobile Apps.pdf
PDF
Profit Center Accounting in SAP S/4HANA, S4F28 Col11
PPTX
Programs and apps: productivity, graphics, security and other tools
PDF
cuic standard and advanced reporting.pdf
PDF
Architecting across the Boundaries of two Complex Domains - Healthcare & Tech...
PPT
Teaching material agriculture food technology
PDF
Peak of Data & AI Encore- AI for Metadata and Smarter Workflows
PPTX
20250228 LYD VKU AI Blended-Learning.pptx
PPTX
Big Data Technologies - Introduction.pptx
PDF
Chapter 3 Spatial Domain Image Processing.pdf
PPTX
Spectroscopy.pptx food analysis technology
PPTX
Detection-First SIEM: Rule Types, Dashboards, and Threat-Informed Strategy
PDF
Approach and Philosophy of On baking technology
PPTX
ACSFv1EN-58255 AWS Academy Cloud Security Foundations.pptx
PDF
Building Integrated photovoltaic BIPV_UPV.pdf
PDF
Spectral efficient network and resource selection model in 5G networks
PPTX
VMware vSphere Foundation How to Sell Presentation-Ver1.4-2-14-2024.pptx
Dropbox Q2 2025 Financial Results & Investor Presentation
Review of recent advances in non-invasive hemoglobin estimation
KodekX | Application Modernization Development
How UI/UX Design Impacts User Retention in Mobile Apps.pdf
Profit Center Accounting in SAP S/4HANA, S4F28 Col11
Programs and apps: productivity, graphics, security and other tools
cuic standard and advanced reporting.pdf
Architecting across the Boundaries of two Complex Domains - Healthcare & Tech...
Teaching material agriculture food technology
Peak of Data & AI Encore- AI for Metadata and Smarter Workflows
20250228 LYD VKU AI Blended-Learning.pptx
Big Data Technologies - Introduction.pptx
Chapter 3 Spatial Domain Image Processing.pdf
Spectroscopy.pptx food analysis technology
Detection-First SIEM: Rule Types, Dashboards, and Threat-Informed Strategy
Approach and Philosophy of On baking technology
ACSFv1EN-58255 AWS Academy Cloud Security Foundations.pptx
Building Integrated photovoltaic BIPV_UPV.pdf
Spectral efficient network and resource selection model in 5G networks
VMware vSphere Foundation How to Sell Presentation-Ver1.4-2-14-2024.pptx

PAM3: Machine Learning in the Railway Industry ( Predix Transform 2016)

  • 1. PAM3: Machine Learning in the Railway Industry Dattaraj J Rao – Senior Architect – GE Transportation (@DattarajR) Scott Nelson – Product Manager – GE Transportation
  • 2. 2PREDIX TRANSFORM Agenda LocoVISION – Eyes for the Train1 Business problem and Value story Computer Vision models The PREDIX Advantage DEMO 2 3 4 5
  • 3. 3PREDIX TRANSFORM LocoVISION – Eyes for the Train •  High-definition cameras on Locomotive •  Monitor Track geometry, Assets •  Computer Vision
  • 4. 4PREDIX TRANSFORM Business problem and Value story •  Track Inspection: Manual, Time consuming •  Too late to find defects - Coverage •  In-accurate PTC Asset database Image Sources: ntsb.gov, Wikipedia.org PTC = Positive Train Control
  • 5. 5PREDIX TRANSFORM Picture Here Geometry-based approach •  Extract geometry from images •  Isolate features of interest •  Define “rules” for anomalies Computer Vision models Machine Learning method •  Image as pixel data array •  Positive and Negative images •  Self-learning from data
  • 6. 6PREDIX TRANSFORM The PREDIX Advantage •  Common Platform – Data Acquisition to Action •  BLOB store for Video + metadata (GPS) •  On-demand + Batch Analytics in Cloud DATA ACQUISITION PREDIX 2.0 PRESENTATION §  COMPUTER VISION MODELS §  MACHINE LEARNING MODELS BLOB STORE ACTION PREDIX MACHINE
  • 8. General Electric reserves the right to make changes in specifications and features, or discontinue the product or service described at any time, without notice or obligation. These materials do not constitute a representation, warranty or documentation regarding the product or service featured. Illustrations are provided for informational purposes, and your configuration may differ. This information does not constitute legal, financial, coding, or regulatory advice in connection with your use of the product or service. Please consult your professional advisors for any such advice. GE, Predix and the GE Monogram are trademarks of General Electric Company. ©2016 General Electric Company – All rights reserved.