SlideShare a Scribd company logo
1 of 34
Download to read offline
Predictive Analytics for IoT
Michael Adendorff
Architect, STSM IBM
IBM Predictive Maintenance and Quality
michael.adendorff@ca.ibm.com
Evidence , Clues > Failure Prediction
Predictive
Analytics
Valuable
Insight
Maintenance Insight
Maintenance Insight
Failure Risk: Under Maintained Equipment
Maintenance Insight
Wasted $$$$$: Over maintained equipment
Work Order
Urgent Inspection Required: High probability of failure
High risk of failure before next scheduled maintenance
Maintenance Schedule Update Request
Bring forward scheduled maintenance to Jul 5
Bring forward scheduled maintenance to Aug 7
Delay scheduled maintenance to Dec 15
Parts Requirements Forecast : Main Bearing
June: July: Aug:
10 3 22
9 20 12
7 21 14
12 15 17
Business Results : Predictive Maintenance
Downtime
Unplanned
Planned
Predictive
Analytics
Valuable
Insight
How does it work?
Simplistic Illustration
Historic Data
Failure
Records
Vibration
Levels
Correlation
FailureCount Vibration Level
More failures have been
witnessed when vibration
levels are high
Univariate Model
FailureCount
Vibration Level
Vibration
Level
P Failure Confidence
< 0.1 0.1 % 2%
0.-0.5 1% 3%
0.5 – 2 3% 5%
2 – 5 15% 10%
+5 98% 80%
p(fail)
Simple univariate models are generally not very accurate. This one
looks better than it is. High vibration strongly correlated with failure
as it is a lagging indicator. Need leading indicators to predict.
Multivariate model
p(fail)
More accurate than the univariate model, but raw input data never
reveals the whole story.
Correlates failures with
combinations between multiple
input variables
Historic Data
Advanced Data Prep + Ensemble Models
More accurate than the univariate model, but raw input data never
reveals the whole story.
Historic Data
p(fail)
E(fail date)
Advanced Data Prep + Ensemble Models
More accurate than the univariate model, but raw input data never
reveals the whole story.
Historic Data
Cumulative Cycles = f(speed,
operating hours)
p(fail)
E(fail date)
Advanced Data Prep + Ensemble Models
More accurate than the univariate model, but raw input data never
reveals the whole story.
Historic Data
Cumulative Fatigue Load =
f(Cycles, Speed)
p(fail)
E(fail date)
Advanced Data Prep + Ensemble Models
More accurate than the univariate model, but raw input data never
reveals the whole story.
Historic Data
Wear Damage Forecast
p(fail)
E(fail date)
Advanced Data Prep + Ensemble Models
p(fail)
More accurate than the univariate model, but raw input data never
reveals the whole story.
Historic Data
Wear Damage Forecast
E(fail date)
Wear Modeling
Advanced Data Prep + Ensemble Models
More accurate than the univariate model, but raw input data never
reveals the whole story.
Historic Data
Fatigue Damage Forecast
p(fail)
E(fail date)
Advanced Data Prep + Ensemble Models
p(fail)
More accurate than the univariate model, but raw input data never
reveals the whole story.
Historic Data
Wear Damage Forecast
E(fail date)
Fatigue Modeling
Advanced Data Prep + Ensemble Models
Building models like this requires brute force number crunching
as well as skills and knowledge. Payoff comes from more accurate
predictions – but – it doesn’t end here.
Historic Data
Time series forecast +
Combination Model
p(fail)
E(fail date)
Advanced Data Prep + Ensemble Models
Historic Data
Expected failure date is more
actionable than current
probability of failure
Building models like this requires brute force number crunching
as well as skills and knowledge. Payoff comes from more accurate
predictions – but – it doesn’t end here.
p(fail)
E(fail date)
Advanced Data Prep + Ensemble Models
Historic Data
Lorem ipsum dolor sit amet,
consectetur adipiscing elit. Ut
lacinia semper gravida. Morbi vel
orci in leo malesuada malesuada
in ac enim. Nam pulvinar nec
enim in venenatis. In nibh turpis,
sodales at fermentum in
Sensors don’t record every
causal factor. Text analytics is
used to fill in some of the blanks.
p(fail)
E(fail date)
Predictive
Analytics
Valuable
Insight
Building models is only half the fun. Next step – OPERATIONALIZE
Feed Data
APIs for:
• Describing target data structures
• Describing calculations and aggregations
• Running analytics
• Exposing analytic results
REST Historian DB
WebService
MQTT Other
Data flows into DB in realtime
Event
Master
Data
Profile
KPI
Predictive Analytics done in realtime
Event
Master
Data
Profile
KPI
p(fail)
E(fail date)
Predictive Analytics done in realtime
Event
Master
Data
Profile
KPI
p(fail)
E(fail date)
Predictive Outputs fed back as
new events
Deciding on Recommended Actions
Event
Profile Action
KPI
Taking Action
REST DB
WebService
FTP Other
Valuable
Insight
Build Models
1) Assemble historic data
2) Attempt to correlate historical data with a
known target
3) Improve results by putting more thought
about preparing inputs and algorithm
selection
Operationalize
1) Feed raw data
2) Describe calculation and aggregation
3) Perform analytics
4) Carry out decision logic
5) Feed results
6) Retrain models regularly
Questions?
Michael Adendorff
Architect, STSM IBM
IBM Predictive Maintenance and Quality
michael.adendorff@ca.ibm.com

More Related Content

Viewers also liked

Big Data Analytics for the Industrial Internet of Things
Big Data Analytics for the Industrial Internet of ThingsBig Data Analytics for the Industrial Internet of Things
Big Data Analytics for the Industrial Internet of ThingsAnthony Chen
 
Internet of Things and Large-scale Data Analytics
Internet of Things and Large-scale Data Analytics Internet of Things and Large-scale Data Analytics
Internet of Things and Large-scale Data Analytics PayamBarnaghi
 
Internet of Things and Big Data: Vision and Concrete Use Cases
Internet of Things and Big Data: Vision and Concrete Use CasesInternet of Things and Big Data: Vision and Concrete Use Cases
Internet of Things and Big Data: Vision and Concrete Use CasesMongoDB
 
Internet of things, Big Data and Analytics 101
Internet of things, Big Data and Analytics 101Internet of things, Big Data and Analytics 101
Internet of things, Big Data and Analytics 101Mukul Krishna
 
101 Use Cases for IoT
101 Use Cases for IoT101 Use Cases for IoT
101 Use Cases for IoTCisco Canada
 
Internet-of-things- (IOT) - a-seminar - ppt - by- mohan-kumar-g
Internet-of-things- (IOT) - a-seminar - ppt - by- mohan-kumar-gInternet-of-things- (IOT) - a-seminar - ppt - by- mohan-kumar-g
Internet-of-things- (IOT) - a-seminar - ppt - by- mohan-kumar-gMohan Kumar G
 

Viewers also liked (7)

Big Data Analytics for the Industrial Internet of Things
Big Data Analytics for the Industrial Internet of ThingsBig Data Analytics for the Industrial Internet of Things
Big Data Analytics for the Industrial Internet of Things
 
Internet of Things and Large-scale Data Analytics
Internet of Things and Large-scale Data Analytics Internet of Things and Large-scale Data Analytics
Internet of Things and Large-scale Data Analytics
 
Data Analytics for IoT
Data Analytics for IoT Data Analytics for IoT
Data Analytics for IoT
 
Internet of Things and Big Data: Vision and Concrete Use Cases
Internet of Things and Big Data: Vision and Concrete Use CasesInternet of Things and Big Data: Vision and Concrete Use Cases
Internet of Things and Big Data: Vision and Concrete Use Cases
 
Internet of things, Big Data and Analytics 101
Internet of things, Big Data and Analytics 101Internet of things, Big Data and Analytics 101
Internet of things, Big Data and Analytics 101
 
101 Use Cases for IoT
101 Use Cases for IoT101 Use Cases for IoT
101 Use Cases for IoT
 
Internet-of-things- (IOT) - a-seminar - ppt - by- mohan-kumar-g
Internet-of-things- (IOT) - a-seminar - ppt - by- mohan-kumar-gInternet-of-things- (IOT) - a-seminar - ppt - by- mohan-kumar-g
Internet-of-things- (IOT) - a-seminar - ppt - by- mohan-kumar-g
 

Similar to IBM Predictive analytics IoT Presentation

Defect Analysis & Prevention, Data Mining & Visualization of Defect Matrix
Defect Analysis & Prevention, Data Mining & Visualization of Defect MatrixDefect Analysis & Prevention, Data Mining & Visualization of Defect Matrix
Defect Analysis & Prevention, Data Mining & Visualization of Defect MatrixAniruddha Sahasrabudhe
 
Simple is Not Necessarily Better: Why Software Productivity Factors Can Lead...
Simple is Not Necessarily Better:  Why Software Productivity Factors Can Lead...Simple is Not Necessarily Better:  Why Software Productivity Factors Can Lead...
Simple is Not Necessarily Better: Why Software Productivity Factors Can Lead...Michael Gallo
 
AiCore Brochure 27-Mar-2023-205529.pdf
AiCore Brochure 27-Mar-2023-205529.pdfAiCore Brochure 27-Mar-2023-205529.pdf
AiCore Brochure 27-Mar-2023-205529.pdfAjayRawat829497
 
MLOps - Build pipelines with Tensor Flow Extended & Kubeflow
MLOps - Build pipelines with Tensor Flow Extended & KubeflowMLOps - Build pipelines with Tensor Flow Extended & Kubeflow
MLOps - Build pipelines with Tensor Flow Extended & KubeflowJan Kirenz
 
Automatic Forecasting using Prophet, Databricks, Delta Lake and MLflow
Automatic Forecasting using Prophet, Databricks, Delta Lake and MLflowAutomatic Forecasting using Prophet, Databricks, Delta Lake and MLflow
Automatic Forecasting using Prophet, Databricks, Delta Lake and MLflowDatabricks
 
Automate your Machine Learning
Automate your Machine LearningAutomate your Machine Learning
Automate your Machine LearningAjit Ananthram
 
DevOps and Machine Learning (Geekwire Cloud Tech Summit)
DevOps and Machine Learning (Geekwire Cloud Tech Summit)DevOps and Machine Learning (Geekwire Cloud Tech Summit)
DevOps and Machine Learning (Geekwire Cloud Tech Summit)Jasjeet Thind
 
Measure() or die()
Measure() or die() Measure() or die()
Measure() or die() LivePerson
 
VerticaPy_original - Anritsu.pdf
VerticaPy_original - Anritsu.pdfVerticaPy_original - Anritsu.pdf
VerticaPy_original - Anritsu.pdfAmzath3
 
Evolution of a big data project
Evolution of a big data projectEvolution of a big data project
Evolution of a big data projectMichael Peacock
 
R meetup talk scaling data science with dgit
R meetup talk   scaling data science with dgitR meetup talk   scaling data science with dgit
R meetup talk scaling data science with dgitVenkata Pingali
 
ThoughtWorks Continuous Delivery
ThoughtWorks Continuous DeliveryThoughtWorks Continuous Delivery
ThoughtWorks Continuous DeliveryKyle Hodgson
 
Cansat 2008: University of Michigan Maizesat Final Presentation
Cansat 2008: University of Michigan Maizesat Final PresentationCansat 2008: University of Michigan Maizesat Final Presentation
Cansat 2008: University of Michigan Maizesat Final PresentationAmerican Astronautical Society
 
Data science for infrastructure dev week 2022
Data science for infrastructure   dev week 2022Data science for infrastructure   dev week 2022
Data science for infrastructure dev week 2022ZainAsgar1
 
V like Velocity, Predicting in Real-Time with Azure ML
V like Velocity, Predicting in Real-Time with Azure MLV like Velocity, Predicting in Real-Time with Azure ML
V like Velocity, Predicting in Real-Time with Azure MLBarbara Fusinska
 
Learning from Computer Simulation to Tackle Real-World Problems
Learning from Computer Simulation to Tackle Real-World ProblemsLearning from Computer Simulation to Tackle Real-World Problems
Learning from Computer Simulation to Tackle Real-World ProblemsNAVER Engineering
 

Similar to IBM Predictive analytics IoT Presentation (20)

Defect Analysis & Prevention, Data Mining & Visualization of Defect Matrix
Defect Analysis & Prevention, Data Mining & Visualization of Defect MatrixDefect Analysis & Prevention, Data Mining & Visualization of Defect Matrix
Defect Analysis & Prevention, Data Mining & Visualization of Defect Matrix
 
Simple is Not Necessarily Better: Why Software Productivity Factors Can Lead...
Simple is Not Necessarily Better:  Why Software Productivity Factors Can Lead...Simple is Not Necessarily Better:  Why Software Productivity Factors Can Lead...
Simple is Not Necessarily Better: Why Software Productivity Factors Can Lead...
 
AiCore Brochure 27-Mar-2023-205529.pdf
AiCore Brochure 27-Mar-2023-205529.pdfAiCore Brochure 27-Mar-2023-205529.pdf
AiCore Brochure 27-Mar-2023-205529.pdf
 
MLOps - Build pipelines with Tensor Flow Extended & Kubeflow
MLOps - Build pipelines with Tensor Flow Extended & KubeflowMLOps - Build pipelines with Tensor Flow Extended & Kubeflow
MLOps - Build pipelines with Tensor Flow Extended & Kubeflow
 
Automatic Forecasting using Prophet, Databricks, Delta Lake and MLflow
Automatic Forecasting using Prophet, Databricks, Delta Lake and MLflowAutomatic Forecasting using Prophet, Databricks, Delta Lake and MLflow
Automatic Forecasting using Prophet, Databricks, Delta Lake and MLflow
 
Automate your Machine Learning
Automate your Machine LearningAutomate your Machine Learning
Automate your Machine Learning
 
1030 iordanescu
1030 iordanescu1030 iordanescu
1030 iordanescu
 
DevOps and Machine Learning (Geekwire Cloud Tech Summit)
DevOps and Machine Learning (Geekwire Cloud Tech Summit)DevOps and Machine Learning (Geekwire Cloud Tech Summit)
DevOps and Machine Learning (Geekwire Cloud Tech Summit)
 
Measure() or die()
Measure() or die()Measure() or die()
Measure() or die()
 
Measure() or die()
Measure() or die() Measure() or die()
Measure() or die()
 
VerticaPy_original - Anritsu.pdf
VerticaPy_original - Anritsu.pdfVerticaPy_original - Anritsu.pdf
VerticaPy_original - Anritsu.pdf
 
Evolution of a big data project
Evolution of a big data projectEvolution of a big data project
Evolution of a big data project
 
data science
data sciencedata science
data science
 
R meetup talk scaling data science with dgit
R meetup talk   scaling data science with dgitR meetup talk   scaling data science with dgit
R meetup talk scaling data science with dgit
 
ThoughtWorks Continuous Delivery
ThoughtWorks Continuous DeliveryThoughtWorks Continuous Delivery
ThoughtWorks Continuous Delivery
 
Cansat 2008: University of Michigan Maizesat Final Presentation
Cansat 2008: University of Michigan Maizesat Final PresentationCansat 2008: University of Michigan Maizesat Final Presentation
Cansat 2008: University of Michigan Maizesat Final Presentation
 
Data science for infrastructure dev week 2022
Data science for infrastructure   dev week 2022Data science for infrastructure   dev week 2022
Data science for infrastructure dev week 2022
 
V like Velocity, Predicting in Real-Time with Azure ML
V like Velocity, Predicting in Real-Time with Azure MLV like Velocity, Predicting in Real-Time with Azure ML
V like Velocity, Predicting in Real-Time with Azure ML
 
Learning from Computer Simulation to Tackle Real-World Problems
Learning from Computer Simulation to Tackle Real-World ProblemsLearning from Computer Simulation to Tackle Real-World Problems
Learning from Computer Simulation to Tackle Real-World Problems
 
1120 rao mathew
1120 rao mathew1120 rao mathew
1120 rao mathew
 

More from Ian Skerrett

Connecting the smart factory to the cloud with MQTT and Sparkplug
Connecting the smart factory to the cloud with MQTT and SparkplugConnecting the smart factory to the cloud with MQTT and Sparkplug
Connecting the smart factory to the cloud with MQTT and SparkplugIan Skerrett
 
IoT Meetup HiveMQ and MQTT
IoT Meetup HiveMQ and MQTTIoT Meetup HiveMQ and MQTT
IoT Meetup HiveMQ and MQTTIan Skerrett
 
The State of Edge Computing for IoT
The State of Edge Computing for IoTThe State of Edge Computing for IoT
The State of Edge Computing for IoTIan Skerrett
 
Internet of manufacturing and Open Source
Internet of manufacturing and Open SourceInternet of manufacturing and Open Source
Internet of manufacturing and Open SourceIan Skerrett
 
Open Source Software for Industry 4.0
Open Source Software for Industry 4.0Open Source Software for Industry 4.0
Open Source Software for Industry 4.0Ian Skerrett
 
Eclipse IoT Overview
Eclipse IoT OverviewEclipse IoT Overview
Eclipse IoT OverviewIan Skerrett
 
Eclipse IoT for Industry 4.0
Eclipse IoT for Industry 4.0Eclipse IoT for Industry 4.0
Eclipse IoT for Industry 4.0Ian Skerrett
 
Eclipse IOT [IoT World Santa Clara]
Eclipse IOT  [IoT World Santa Clara]Eclipse IOT  [IoT World Santa Clara]
Eclipse IOT [IoT World Santa Clara]Ian Skerrett
 
IoT Developer Survey 2017
IoT Developer Survey 2017IoT Developer Survey 2017
IoT Developer Survey 2017Ian Skerrett
 
3 Software Stacks for IoT Solutions
3 Software Stacks for IoT Solutions3 Software Stacks for IoT Solutions
3 Software Stacks for IoT SolutionsIan Skerrett
 
IoT Developer Survey 2016
IoT Developer Survey 2016IoT Developer Survey 2016
IoT Developer Survey 2016Ian Skerrett
 
Creating the open source building blocks for IoT
Creating the open source building blocks for IoT Creating the open source building blocks for IoT
Creating the open source building blocks for IoT Ian Skerrett
 
Eclipse IoT: Open source technology for IoT developers
Eclipse IoT: Open source technology for IoT developersEclipse IoT: Open source technology for IoT developers
Eclipse IoT: Open source technology for IoT developersIan Skerrett
 
Defining an Open IoT Stack - Presented at IoT World 2015
Defining an Open IoT Stack - Presented at IoT World 2015Defining an Open IoT Stack - Presented at IoT World 2015
Defining an Open IoT Stack - Presented at IoT World 2015Ian Skerrett
 
IoT Developer Survey 2015
IoT Developer Survey 2015IoT Developer Survey 2015
IoT Developer Survey 2015Ian Skerrett
 
Using open source for IoT
Using open source for IoTUsing open source for IoT
Using open source for IoTIan Skerrett
 
Leveraging the Open IoT Ecosystem to Accelerate Innovation [BizofIoT]
Leveraging the Open IoT Ecosystem to Accelerate Innovation [BizofIoT]Leveraging the Open IoT Ecosystem to Accelerate Innovation [BizofIoT]
Leveraging the Open IoT Ecosystem to Accelerate Innovation [BizofIoT]Ian Skerrett
 
ABC of IoT Consortiums
ABC of IoT ConsortiumsABC of IoT Consortiums
ABC of IoT ConsortiumsIan Skerrett
 
Eclipse community survey 2014 v2
Eclipse community survey 2014 v2Eclipse community survey 2014 v2
Eclipse community survey 2014 v2Ian Skerrett
 
Leveraging the Open IoT Ecosystem to Accelerate Product Strategy
Leveraging the Open IoT Ecosystem to Accelerate Product StrategyLeveraging the Open IoT Ecosystem to Accelerate Product Strategy
Leveraging the Open IoT Ecosystem to Accelerate Product StrategyIan Skerrett
 

More from Ian Skerrett (20)

Connecting the smart factory to the cloud with MQTT and Sparkplug
Connecting the smart factory to the cloud with MQTT and SparkplugConnecting the smart factory to the cloud with MQTT and Sparkplug
Connecting the smart factory to the cloud with MQTT and Sparkplug
 
IoT Meetup HiveMQ and MQTT
IoT Meetup HiveMQ and MQTTIoT Meetup HiveMQ and MQTT
IoT Meetup HiveMQ and MQTT
 
The State of Edge Computing for IoT
The State of Edge Computing for IoTThe State of Edge Computing for IoT
The State of Edge Computing for IoT
 
Internet of manufacturing and Open Source
Internet of manufacturing and Open SourceInternet of manufacturing and Open Source
Internet of manufacturing and Open Source
 
Open Source Software for Industry 4.0
Open Source Software for Industry 4.0Open Source Software for Industry 4.0
Open Source Software for Industry 4.0
 
Eclipse IoT Overview
Eclipse IoT OverviewEclipse IoT Overview
Eclipse IoT Overview
 
Eclipse IoT for Industry 4.0
Eclipse IoT for Industry 4.0Eclipse IoT for Industry 4.0
Eclipse IoT for Industry 4.0
 
Eclipse IOT [IoT World Santa Clara]
Eclipse IOT  [IoT World Santa Clara]Eclipse IOT  [IoT World Santa Clara]
Eclipse IOT [IoT World Santa Clara]
 
IoT Developer Survey 2017
IoT Developer Survey 2017IoT Developer Survey 2017
IoT Developer Survey 2017
 
3 Software Stacks for IoT Solutions
3 Software Stacks for IoT Solutions3 Software Stacks for IoT Solutions
3 Software Stacks for IoT Solutions
 
IoT Developer Survey 2016
IoT Developer Survey 2016IoT Developer Survey 2016
IoT Developer Survey 2016
 
Creating the open source building blocks for IoT
Creating the open source building blocks for IoT Creating the open source building blocks for IoT
Creating the open source building blocks for IoT
 
Eclipse IoT: Open source technology for IoT developers
Eclipse IoT: Open source technology for IoT developersEclipse IoT: Open source technology for IoT developers
Eclipse IoT: Open source technology for IoT developers
 
Defining an Open IoT Stack - Presented at IoT World 2015
Defining an Open IoT Stack - Presented at IoT World 2015Defining an Open IoT Stack - Presented at IoT World 2015
Defining an Open IoT Stack - Presented at IoT World 2015
 
IoT Developer Survey 2015
IoT Developer Survey 2015IoT Developer Survey 2015
IoT Developer Survey 2015
 
Using open source for IoT
Using open source for IoTUsing open source for IoT
Using open source for IoT
 
Leveraging the Open IoT Ecosystem to Accelerate Innovation [BizofIoT]
Leveraging the Open IoT Ecosystem to Accelerate Innovation [BizofIoT]Leveraging the Open IoT Ecosystem to Accelerate Innovation [BizofIoT]
Leveraging the Open IoT Ecosystem to Accelerate Innovation [BizofIoT]
 
ABC of IoT Consortiums
ABC of IoT ConsortiumsABC of IoT Consortiums
ABC of IoT Consortiums
 
Eclipse community survey 2014 v2
Eclipse community survey 2014 v2Eclipse community survey 2014 v2
Eclipse community survey 2014 v2
 
Leveraging the Open IoT Ecosystem to Accelerate Product Strategy
Leveraging the Open IoT Ecosystem to Accelerate Product StrategyLeveraging the Open IoT Ecosystem to Accelerate Product Strategy
Leveraging the Open IoT Ecosystem to Accelerate Product Strategy
 

Recently uploaded

How to submit a standout Adobe Champion Application
How to submit a standout Adobe Champion ApplicationHow to submit a standout Adobe Champion Application
How to submit a standout Adobe Champion ApplicationBradBedford3
 
Software Project Health Check: Best Practices and Techniques for Your Product...
Software Project Health Check: Best Practices and Techniques for Your Product...Software Project Health Check: Best Practices and Techniques for Your Product...
Software Project Health Check: Best Practices and Techniques for Your Product...Velvetech LLC
 
GOING AOT WITH GRAALVM – DEVOXX GREECE.pdf
GOING AOT WITH GRAALVM – DEVOXX GREECE.pdfGOING AOT WITH GRAALVM – DEVOXX GREECE.pdf
GOING AOT WITH GRAALVM – DEVOXX GREECE.pdfAlina Yurenko
 
PREDICTING RIVER WATER QUALITY ppt presentation
PREDICTING  RIVER  WATER QUALITY  ppt presentationPREDICTING  RIVER  WATER QUALITY  ppt presentation
PREDICTING RIVER WATER QUALITY ppt presentationvaddepallysandeep122
 
React Server Component in Next.js by Hanief Utama
React Server Component in Next.js by Hanief UtamaReact Server Component in Next.js by Hanief Utama
React Server Component in Next.js by Hanief UtamaHanief Utama
 
Buds n Tech IT Solutions: Top-Notch Web Services in Noida
Buds n Tech IT Solutions: Top-Notch Web Services in NoidaBuds n Tech IT Solutions: Top-Notch Web Services in Noida
Buds n Tech IT Solutions: Top-Notch Web Services in Noidabntitsolutionsrishis
 
What are the key points to focus on before starting to learn ETL Development....
What are the key points to focus on before starting to learn ETL Development....What are the key points to focus on before starting to learn ETL Development....
What are the key points to focus on before starting to learn ETL Development....kzayra69
 
Best Web Development Agency- Idiosys USA.pdf
Best Web Development Agency- Idiosys USA.pdfBest Web Development Agency- Idiosys USA.pdf
Best Web Development Agency- Idiosys USA.pdfIdiosysTechnologies1
 
Taming Distributed Systems: Key Insights from Wix's Large-Scale Experience - ...
Taming Distributed Systems: Key Insights from Wix's Large-Scale Experience - ...Taming Distributed Systems: Key Insights from Wix's Large-Scale Experience - ...
Taming Distributed Systems: Key Insights from Wix's Large-Scale Experience - ...Natan Silnitsky
 
Catch the Wave: SAP Event-Driven and Data Streaming for the Intelligence Ente...
Catch the Wave: SAP Event-Driven and Data Streaming for the Intelligence Ente...Catch the Wave: SAP Event-Driven and Data Streaming for the Intelligence Ente...
Catch the Wave: SAP Event-Driven and Data Streaming for the Intelligence Ente...confluent
 
Cyber security and its impact on E commerce
Cyber security and its impact on E commerceCyber security and its impact on E commerce
Cyber security and its impact on E commercemanigoyal112
 
Folding Cheat Sheet #4 - fourth in a series
Folding Cheat Sheet #4 - fourth in a seriesFolding Cheat Sheet #4 - fourth in a series
Folding Cheat Sheet #4 - fourth in a seriesPhilip Schwarz
 
BATTLEFIELD ORM: TIPS, TACTICS AND STRATEGIES FOR CONQUERING YOUR DATABASE
BATTLEFIELD ORM: TIPS, TACTICS AND STRATEGIES FOR CONQUERING YOUR DATABASEBATTLEFIELD ORM: TIPS, TACTICS AND STRATEGIES FOR CONQUERING YOUR DATABASE
BATTLEFIELD ORM: TIPS, TACTICS AND STRATEGIES FOR CONQUERING YOUR DATABASEOrtus Solutions, Corp
 
Ahmed Motair CV April 2024 (Senior SW Developer)
Ahmed Motair CV April 2024 (Senior SW Developer)Ahmed Motair CV April 2024 (Senior SW Developer)
Ahmed Motair CV April 2024 (Senior SW Developer)Ahmed Mater
 
A healthy diet for your Java application Devoxx France.pdf
A healthy diet for your Java application Devoxx France.pdfA healthy diet for your Java application Devoxx France.pdf
A healthy diet for your Java application Devoxx France.pdfMarharyta Nedzelska
 
What is Fashion PLM and Why Do You Need It
What is Fashion PLM and Why Do You Need ItWhat is Fashion PLM and Why Do You Need It
What is Fashion PLM and Why Do You Need ItWave PLM
 
Maximizing Efficiency and Profitability with OnePlan’s Professional Service A...
Maximizing Efficiency and Profitability with OnePlan’s Professional Service A...Maximizing Efficiency and Profitability with OnePlan’s Professional Service A...
Maximizing Efficiency and Profitability with OnePlan’s Professional Service A...OnePlan Solutions
 
Global Identity Enrolment and Verification Pro Solution - Cizo Technology Ser...
Global Identity Enrolment and Verification Pro Solution - Cizo Technology Ser...Global Identity Enrolment and Verification Pro Solution - Cizo Technology Ser...
Global Identity Enrolment and Verification Pro Solution - Cizo Technology Ser...Cizo Technology Services
 
Balasore Best It Company|| Top 10 IT Company || Balasore Software company Odisha
Balasore Best It Company|| Top 10 IT Company || Balasore Software company OdishaBalasore Best It Company|| Top 10 IT Company || Balasore Software company Odisha
Balasore Best It Company|| Top 10 IT Company || Balasore Software company Odishasmiwainfosol
 
Building a General PDE Solving Framework with Symbolic-Numeric Scientific Mac...
Building a General PDE Solving Framework with Symbolic-Numeric Scientific Mac...Building a General PDE Solving Framework with Symbolic-Numeric Scientific Mac...
Building a General PDE Solving Framework with Symbolic-Numeric Scientific Mac...stazi3110
 

Recently uploaded (20)

How to submit a standout Adobe Champion Application
How to submit a standout Adobe Champion ApplicationHow to submit a standout Adobe Champion Application
How to submit a standout Adobe Champion Application
 
Software Project Health Check: Best Practices and Techniques for Your Product...
Software Project Health Check: Best Practices and Techniques for Your Product...Software Project Health Check: Best Practices and Techniques for Your Product...
Software Project Health Check: Best Practices and Techniques for Your Product...
 
GOING AOT WITH GRAALVM – DEVOXX GREECE.pdf
GOING AOT WITH GRAALVM – DEVOXX GREECE.pdfGOING AOT WITH GRAALVM – DEVOXX GREECE.pdf
GOING AOT WITH GRAALVM – DEVOXX GREECE.pdf
 
PREDICTING RIVER WATER QUALITY ppt presentation
PREDICTING  RIVER  WATER QUALITY  ppt presentationPREDICTING  RIVER  WATER QUALITY  ppt presentation
PREDICTING RIVER WATER QUALITY ppt presentation
 
React Server Component in Next.js by Hanief Utama
React Server Component in Next.js by Hanief UtamaReact Server Component in Next.js by Hanief Utama
React Server Component in Next.js by Hanief Utama
 
Buds n Tech IT Solutions: Top-Notch Web Services in Noida
Buds n Tech IT Solutions: Top-Notch Web Services in NoidaBuds n Tech IT Solutions: Top-Notch Web Services in Noida
Buds n Tech IT Solutions: Top-Notch Web Services in Noida
 
What are the key points to focus on before starting to learn ETL Development....
What are the key points to focus on before starting to learn ETL Development....What are the key points to focus on before starting to learn ETL Development....
What are the key points to focus on before starting to learn ETL Development....
 
Best Web Development Agency- Idiosys USA.pdf
Best Web Development Agency- Idiosys USA.pdfBest Web Development Agency- Idiosys USA.pdf
Best Web Development Agency- Idiosys USA.pdf
 
Taming Distributed Systems: Key Insights from Wix's Large-Scale Experience - ...
Taming Distributed Systems: Key Insights from Wix's Large-Scale Experience - ...Taming Distributed Systems: Key Insights from Wix's Large-Scale Experience - ...
Taming Distributed Systems: Key Insights from Wix's Large-Scale Experience - ...
 
Catch the Wave: SAP Event-Driven and Data Streaming for the Intelligence Ente...
Catch the Wave: SAP Event-Driven and Data Streaming for the Intelligence Ente...Catch the Wave: SAP Event-Driven and Data Streaming for the Intelligence Ente...
Catch the Wave: SAP Event-Driven and Data Streaming for the Intelligence Ente...
 
Cyber security and its impact on E commerce
Cyber security and its impact on E commerceCyber security and its impact on E commerce
Cyber security and its impact on E commerce
 
Folding Cheat Sheet #4 - fourth in a series
Folding Cheat Sheet #4 - fourth in a seriesFolding Cheat Sheet #4 - fourth in a series
Folding Cheat Sheet #4 - fourth in a series
 
BATTLEFIELD ORM: TIPS, TACTICS AND STRATEGIES FOR CONQUERING YOUR DATABASE
BATTLEFIELD ORM: TIPS, TACTICS AND STRATEGIES FOR CONQUERING YOUR DATABASEBATTLEFIELD ORM: TIPS, TACTICS AND STRATEGIES FOR CONQUERING YOUR DATABASE
BATTLEFIELD ORM: TIPS, TACTICS AND STRATEGIES FOR CONQUERING YOUR DATABASE
 
Ahmed Motair CV April 2024 (Senior SW Developer)
Ahmed Motair CV April 2024 (Senior SW Developer)Ahmed Motair CV April 2024 (Senior SW Developer)
Ahmed Motair CV April 2024 (Senior SW Developer)
 
A healthy diet for your Java application Devoxx France.pdf
A healthy diet for your Java application Devoxx France.pdfA healthy diet for your Java application Devoxx France.pdf
A healthy diet for your Java application Devoxx France.pdf
 
What is Fashion PLM and Why Do You Need It
What is Fashion PLM and Why Do You Need ItWhat is Fashion PLM and Why Do You Need It
What is Fashion PLM and Why Do You Need It
 
Maximizing Efficiency and Profitability with OnePlan’s Professional Service A...
Maximizing Efficiency and Profitability with OnePlan’s Professional Service A...Maximizing Efficiency and Profitability with OnePlan’s Professional Service A...
Maximizing Efficiency and Profitability with OnePlan’s Professional Service A...
 
Global Identity Enrolment and Verification Pro Solution - Cizo Technology Ser...
Global Identity Enrolment and Verification Pro Solution - Cizo Technology Ser...Global Identity Enrolment and Verification Pro Solution - Cizo Technology Ser...
Global Identity Enrolment and Verification Pro Solution - Cizo Technology Ser...
 
Balasore Best It Company|| Top 10 IT Company || Balasore Software company Odisha
Balasore Best It Company|| Top 10 IT Company || Balasore Software company OdishaBalasore Best It Company|| Top 10 IT Company || Balasore Software company Odisha
Balasore Best It Company|| Top 10 IT Company || Balasore Software company Odisha
 
Building a General PDE Solving Framework with Symbolic-Numeric Scientific Mac...
Building a General PDE Solving Framework with Symbolic-Numeric Scientific Mac...Building a General PDE Solving Framework with Symbolic-Numeric Scientific Mac...
Building a General PDE Solving Framework with Symbolic-Numeric Scientific Mac...
 

IBM Predictive analytics IoT Presentation

  • 1. Predictive Analytics for IoT Michael Adendorff Architect, STSM IBM IBM Predictive Maintenance and Quality michael.adendorff@ca.ibm.com
  • 2.
  • 3. Evidence , Clues > Failure Prediction
  • 6. Maintenance Insight Failure Risk: Under Maintained Equipment
  • 7. Maintenance Insight Wasted $$$$$: Over maintained equipment
  • 8. Work Order Urgent Inspection Required: High probability of failure High risk of failure before next scheduled maintenance
  • 9. Maintenance Schedule Update Request Bring forward scheduled maintenance to Jul 5 Bring forward scheduled maintenance to Aug 7 Delay scheduled maintenance to Dec 15
  • 10. Parts Requirements Forecast : Main Bearing June: July: Aug: 10 3 22 9 20 12 7 21 14 12 15 17
  • 11. Business Results : Predictive Maintenance Downtime Unplanned Planned
  • 13. Simplistic Illustration Historic Data Failure Records Vibration Levels Correlation FailureCount Vibration Level More failures have been witnessed when vibration levels are high
  • 14. Univariate Model FailureCount Vibration Level Vibration Level P Failure Confidence < 0.1 0.1 % 2% 0.-0.5 1% 3% 0.5 – 2 3% 5% 2 – 5 15% 10% +5 98% 80% p(fail) Simple univariate models are generally not very accurate. This one looks better than it is. High vibration strongly correlated with failure as it is a lagging indicator. Need leading indicators to predict.
  • 15. Multivariate model p(fail) More accurate than the univariate model, but raw input data never reveals the whole story. Correlates failures with combinations between multiple input variables Historic Data
  • 16. Advanced Data Prep + Ensemble Models More accurate than the univariate model, but raw input data never reveals the whole story. Historic Data p(fail) E(fail date)
  • 17. Advanced Data Prep + Ensemble Models More accurate than the univariate model, but raw input data never reveals the whole story. Historic Data Cumulative Cycles = f(speed, operating hours) p(fail) E(fail date)
  • 18. Advanced Data Prep + Ensemble Models More accurate than the univariate model, but raw input data never reveals the whole story. Historic Data Cumulative Fatigue Load = f(Cycles, Speed) p(fail) E(fail date)
  • 19. Advanced Data Prep + Ensemble Models More accurate than the univariate model, but raw input data never reveals the whole story. Historic Data Wear Damage Forecast p(fail) E(fail date)
  • 20. Advanced Data Prep + Ensemble Models p(fail) More accurate than the univariate model, but raw input data never reveals the whole story. Historic Data Wear Damage Forecast E(fail date) Wear Modeling
  • 21. Advanced Data Prep + Ensemble Models More accurate than the univariate model, but raw input data never reveals the whole story. Historic Data Fatigue Damage Forecast p(fail) E(fail date)
  • 22. Advanced Data Prep + Ensemble Models p(fail) More accurate than the univariate model, but raw input data never reveals the whole story. Historic Data Wear Damage Forecast E(fail date) Fatigue Modeling
  • 23. Advanced Data Prep + Ensemble Models Building models like this requires brute force number crunching as well as skills and knowledge. Payoff comes from more accurate predictions – but – it doesn’t end here. Historic Data Time series forecast + Combination Model p(fail) E(fail date)
  • 24. Advanced Data Prep + Ensemble Models Historic Data Expected failure date is more actionable than current probability of failure Building models like this requires brute force number crunching as well as skills and knowledge. Payoff comes from more accurate predictions – but – it doesn’t end here. p(fail) E(fail date)
  • 25. Advanced Data Prep + Ensemble Models Historic Data Lorem ipsum dolor sit amet, consectetur adipiscing elit. Ut lacinia semper gravida. Morbi vel orci in leo malesuada malesuada in ac enim. Nam pulvinar nec enim in venenatis. In nibh turpis, sodales at fermentum in Sensors don’t record every causal factor. Text analytics is used to fill in some of the blanks. p(fail) E(fail date)
  • 26. Predictive Analytics Valuable Insight Building models is only half the fun. Next step – OPERATIONALIZE
  • 27. Feed Data APIs for: • Describing target data structures • Describing calculations and aggregations • Running analytics • Exposing analytic results REST Historian DB WebService MQTT Other
  • 28. Data flows into DB in realtime Event Master Data Profile KPI
  • 29. Predictive Analytics done in realtime Event Master Data Profile KPI p(fail) E(fail date)
  • 30. Predictive Analytics done in realtime Event Master Data Profile KPI p(fail) E(fail date) Predictive Outputs fed back as new events
  • 31. Deciding on Recommended Actions Event Profile Action KPI
  • 33. Valuable Insight Build Models 1) Assemble historic data 2) Attempt to correlate historical data with a known target 3) Improve results by putting more thought about preparing inputs and algorithm selection Operationalize 1) Feed raw data 2) Describe calculation and aggregation 3) Perform analytics 4) Carry out decision logic 5) Feed results 6) Retrain models regularly
  • 34. Questions? Michael Adendorff Architect, STSM IBM IBM Predictive Maintenance and Quality michael.adendorff@ca.ibm.com