SlideShare a Scribd company logo
1 of 12
Download to read offline
AI Reliability
September 24th
, 2021
Goal And Objectives
2
▪ Сonfigure and demonstrate the capabilities to identify process and equipment anomalies to predict unplanned
shutdowns for two combined-cycle power plants. Analyze the following 6 subsystems: GT, ST, 2 Generators,
Boiler, Gas compressor
Goal
Objectives
Data sources P&ID
Visually detected
defects
Planned and
unplanned
shutdowns history
Sensors
▪ Creating and Replicating Models Between Similar Objects. Because of the strong differences in power generation
infrastructure objects, the ability to scale created models to objects of the same type has not been shown to be
effective.
▪ Data Integration. Services for handling downloaded engineering data from different types of sources, reducing the time
spent on cleanup, preparation, and other data management tasks.
▪ Implement and manage a large number of models in production. Use of multiple infrastructure components and
multi-model orchestration.
▪ Development of advanced user interfaces. Display both anomaly data and the potential economic impact of preventing
identified anomalies, operator actions, and output for key users on achieving planned targets.
▪ Target percentage of predicted complete unscheduled shutdowns in the test sample > 66%.
Anomaly Detection Models
• By default: 1 year train, 4 years test with retrain every 2 months
• Approach was adopted to every particular subsystem
• Test period complete unplanned shutdowns: 23 (out of 27)
• 14 ML models with rolling window approach - 336 ML models versions for dedicated periods required:
(6 subsystems + 1 power unit as a whole) * 2 power units * 4 test years * 6 models per year
Iteration 1
Test
Train Test
Iteration 2
Train Buffer zone between train/test
1Y 2M
1M Unplanned
shutdowns
Rolling window train/test approach was used
1Y 1M 2M
5
Several Models trained to recognize expected tags values
Expected by ML model value
Actual value
Subsystem power
Anomaly level detected
ML model recognizes how this tag behave according to the past and to other tags behavior
6
Using Expected Value We Can Identify Possible Anomalies
Expected by ML model value
Actual value
Subsystem power
Anomaly level detected
Vibration should go down according to
all the other tags behavior, but it goes
up. Anomaly level increases
7
336 Models tested about anomalous equipment behavior
generated
• Risk score (anomaly level) calculated on basis of all the subsystem tags anomaly levels - for every hour in test period
for every subsystem and for power unit as a whole
• If Risk score is higher than threshold – Alert was generated
Boiler PU-2 example:
Train period Test period
Alert generation threshold
Alerts before shutdowns –
shutdown predicted
Alerts not before shutdowns: could be
valuable (real anomaly) or wrong
No alert before shutdowns –
shutdown not predicted
Subsystem anomaly level
8
Production team reviewed alerts in detail
Application
detected anomaly:
High discharge
behind the air
house
Alert review example: PU-1 GT, shutdown 03.03.21, alert 23.01.2021 (36 days before shutdown), another alert 12.02.2021 (17 days before)
Investigation report conclusion: high discharge behind the air house: dP of the fine filters is high, the CSF is damaged
Drift
Application detected anomaly: dP of the fine filters is high at both points Application detected anomaly: dP CSF is low at both points (damaged?)
Expected by ML
model value
Tag actual value
Subsystem power
Anomaly level
• 2600 tags mapped to subsystems and key failure mode tags dedicated with alarm/ protection setpoints understanding
• >19 alerts reviewed:
• 77 iterations totally for 15 AI models
• >5 new diagnostic metrics developed
• >770 plots with anomalous tags behavior compared with investigation acts to check if alert relates to a shutdown
• 5 out of 19 alerts were not approved (2 of them after detailed internal discussions. Trial had preliminary recall 69.6% before)
• 5 expert rules developed jointly on basis of AI anomalies
• Production team demonstrated deep expertise and high readiness to interpret AI alerts and develop expert rules
Machine Learning model test results
9
Number of
shutdowns in test
period
Alerts before
shutdowns generated
(before review)
Statistical
Recall
Correctly detected
alerts
(approved by SME)
Reviewed Recall
(Anomaly relates to
a shutdown)
Average alerts
frequency
Alerts in a week:
Average lead
time, days
23 19 82,6% 14 60,9% 0,8 9,8
• Statistical recall 82.6% – alerts generated by the solution in advance of unplanned shutdowns
• Approved Recall 60.9% – alerts verified and confirmed by experts, proving that early anomaly detection can be
operationally used for unplanned shutdown prediction, i.e., anomalies detected are related to shutdowns and provide
potential reasons or early warning indications. All confirmed alerts either were generated earlier than staff detected a
defect (11 alerts), or provided new information about defect evolution (3 alerts)
• It is valuable to consider an accuracy rate of 82.6% when comparing with world practices, since there is usually no
investigation for the alert-shutdown relationship
• Of all 23 failure events, only 15 were technically predictable based on the supplied data, as agreed. The Reliability
solution picked 14 of these (or 93%)
* A methodology has been developed that will allow significantly reduce the number of faulse positives
during production implementation
Recall references science papers
1) ”Neural network-based data-driven modelling of anomaly detection in thermal power plant” from
Automatika Journal for Control, Measurement, Electronics, Computing and Communications
Published online: 07 Jul 2017 https://core.ac.uk/download/pdf/212472032.pdf
2) “Fault Detection in a Compined Cycle Power Based on Neural Networks …”
Master’s Thesis from Montan Universitat, Philipp Rohrweck, 2021
https://pure.unileoben.ac.at/portal/files/6491873/AC16191180.pdf
• Statistical recall 50%-60% is good result if you model subsystem as a whole. All the results with better accuracy were
delivered for detailed equipment or particular failure mode modelling
• It is worth using an accuracy rate of 82.6% when comparing with world practices, since there is usually no check for the
alert-shutdown relationship
Results overview
Operational staff efficiency increase
12
Number of alarms raised
per month per power unit
Few
times
per
day
<2
With app
Lead time, in days
3
10
With app
Reviewed Recall in %
(share of shutdowns correctly predicted)
35%
61%
With app
Performance can be further improved during the production deployment:
• More than 20 ML models shall be configured per power unit rather than 6 models per the trial project: equipment/ defect level
• Full set of PU tags should be analyzed. E.g., Steam turbine-2 generator currents are in protection metrics only. More sensor data can be ingested for the
project.
• It is valuable to add metrics for cumulative effect on equipment reliability estimation
• False Positives drastic decrease due to special treatment of G CV, subsystem power, alarm or expert set points usage
Baseline
(Alarm setpoints)
Baseline
Baseline

More Related Content

Similar to AI Reliability Predicts Power Plant Shutdowns

Condition-based Maintenance with sensor arrays and telematics
Condition-based Maintenance with sensor arrays and telematicsCondition-based Maintenance with sensor arrays and telematics
Condition-based Maintenance with sensor arrays and telematicsGopalakrishna Palem
 
CONDITION-BASED MAINTENANCE USING SENSOR ARRAYS AND TELEMATICS
CONDITION-BASED MAINTENANCE USING SENSOR ARRAYS AND TELEMATICSCONDITION-BASED MAINTENANCE USING SENSOR ARRAYS AND TELEMATICS
CONDITION-BASED MAINTENANCE USING SENSOR ARRAYS AND TELEMATICSijmnct
 
Improving continuous process operation using data analytics delta v applicati...
Improving continuous process operation using data analytics delta v applicati...Improving continuous process operation using data analytics delta v applicati...
Improving continuous process operation using data analytics delta v applicati...Emerson Exchange
 
Synthesis and Refinement of Artificial HVAC Sensor Data Intended for Supervis...
Synthesis and Refinement of Artificial HVAC Sensor Data Intended for Supervis...Synthesis and Refinement of Artificial HVAC Sensor Data Intended for Supervis...
Synthesis and Refinement of Artificial HVAC Sensor Data Intended for Supervis...IES VE
 
Operational Efficiency Based on Innovative Automation, Industry Expertise, En...
Operational Efficiency Based on Innovative Automation, Industry Expertise, En...Operational Efficiency Based on Innovative Automation, Industry Expertise, En...
Operational Efficiency Based on Innovative Automation, Industry Expertise, En...Sergey Mishin
 
Innovation day 2013 2.5 joris vanderschrick (verhaert) - embedded system de...
Innovation day 2013   2.5 joris vanderschrick (verhaert) - embedded system de...Innovation day 2013   2.5 joris vanderschrick (verhaert) - embedded system de...
Innovation day 2013 2.5 joris vanderschrick (verhaert) - embedded system de...Verhaert Masters in Innovation
 
Software Testing and Quality Assurance Assignment 2
Software Testing and Quality Assurance Assignment 2Software Testing and Quality Assurance Assignment 2
Software Testing and Quality Assurance Assignment 2Gurpreet singh
 
IoT Evolution Expo- Machine Learning and the Cloud
IoT Evolution Expo- Machine Learning and the CloudIoT Evolution Expo- Machine Learning and the Cloud
IoT Evolution Expo- Machine Learning and the CloudValue Amplify Consulting
 
IRJET- FPGA Implementation of an Improved Watchdog Timer for Safety Critical ...
IRJET- FPGA Implementation of an Improved Watchdog Timer for Safety Critical ...IRJET- FPGA Implementation of an Improved Watchdog Timer for Safety Critical ...
IRJET- FPGA Implementation of an Improved Watchdog Timer for Safety Critical ...IRJET Journal
 
Predicting Machine Learning Pipeline Runtimes in the Context of Automated Mac...
Predicting Machine Learning Pipeline Runtimes in the Context of Automated Mac...Predicting Machine Learning Pipeline Runtimes in the Context of Automated Mac...
Predicting Machine Learning Pipeline Runtimes in the Context of Automated Mac...IRJET Journal
 
DATI, AI E ROBOTICA @POLITO
DATI, AI E ROBOTICA @POLITODATI, AI E ROBOTICA @POLITO
DATI, AI E ROBOTICA @POLITOMarcoMellia
 
See the App Performance Future with Predictive Analytics Webcast
See the App Performance Future with Predictive Analytics WebcastSee the App Performance Future with Predictive Analytics Webcast
See the App Performance Future with Predictive Analytics WebcastCompuware
 
Parameter Estimation of Software Reliability Growth Models Using Simulated An...
Parameter Estimation of Software Reliability Growth Models Using Simulated An...Parameter Estimation of Software Reliability Growth Models Using Simulated An...
Parameter Estimation of Software Reliability Growth Models Using Simulated An...Editor IJCATR
 
Six sigma-measure-phase2505
Six sigma-measure-phase2505Six sigma-measure-phase2505
Six sigma-measure-phase2505densongco
 
FAULT DETECTION AND DIAGNOSIS OF INDUCTION MACHINE WITH ON-LINE PARAMETER PR...
FAULT DETECTION AND DIAGNOSIS OF INDUCTION MACHINE  WITH ON-LINE PARAMETER PR...FAULT DETECTION AND DIAGNOSIS OF INDUCTION MACHINE  WITH ON-LINE PARAMETER PR...
FAULT DETECTION AND DIAGNOSIS OF INDUCTION MACHINE WITH ON-LINE PARAMETER PR...Sheikh R Manihar Ahmed
 
Innovating Quality Control in the Semiconductor Manufacturing Industry.pptx
Innovating Quality Control in the Semiconductor Manufacturing Industry.pptxInnovating Quality Control in the Semiconductor Manufacturing Industry.pptx
Innovating Quality Control in the Semiconductor Manufacturing Industry.pptxyieldWerx Semiconductor
 
A robust algorithm based on a failure sensitive matrix for fault diagnosis of...
A robust algorithm based on a failure sensitive matrix for fault diagnosis of...A robust algorithm based on a failure sensitive matrix for fault diagnosis of...
A robust algorithm based on a failure sensitive matrix for fault diagnosis of...IJMER
 
Sensor Fault Detection in IoT System Using Machine Learning
Sensor Fault Detection in IoT System Using Machine LearningSensor Fault Detection in IoT System Using Machine Learning
Sensor Fault Detection in IoT System Using Machine LearningIRJET Journal
 
Implementing Vulnerability Management
Implementing Vulnerability Management Implementing Vulnerability Management
Implementing Vulnerability Management Argyle Executive Forum
 
IoT Device Intelligence & Real Time Anomaly Detection
IoT Device Intelligence & Real Time Anomaly DetectionIoT Device Intelligence & Real Time Anomaly Detection
IoT Device Intelligence & Real Time Anomaly DetectionBraja Krishna Das
 

Similar to AI Reliability Predicts Power Plant Shutdowns (20)

Condition-based Maintenance with sensor arrays and telematics
Condition-based Maintenance with sensor arrays and telematicsCondition-based Maintenance with sensor arrays and telematics
Condition-based Maintenance with sensor arrays and telematics
 
CONDITION-BASED MAINTENANCE USING SENSOR ARRAYS AND TELEMATICS
CONDITION-BASED MAINTENANCE USING SENSOR ARRAYS AND TELEMATICSCONDITION-BASED MAINTENANCE USING SENSOR ARRAYS AND TELEMATICS
CONDITION-BASED MAINTENANCE USING SENSOR ARRAYS AND TELEMATICS
 
Improving continuous process operation using data analytics delta v applicati...
Improving continuous process operation using data analytics delta v applicati...Improving continuous process operation using data analytics delta v applicati...
Improving continuous process operation using data analytics delta v applicati...
 
Synthesis and Refinement of Artificial HVAC Sensor Data Intended for Supervis...
Synthesis and Refinement of Artificial HVAC Sensor Data Intended for Supervis...Synthesis and Refinement of Artificial HVAC Sensor Data Intended for Supervis...
Synthesis and Refinement of Artificial HVAC Sensor Data Intended for Supervis...
 
Operational Efficiency Based on Innovative Automation, Industry Expertise, En...
Operational Efficiency Based on Innovative Automation, Industry Expertise, En...Operational Efficiency Based on Innovative Automation, Industry Expertise, En...
Operational Efficiency Based on Innovative Automation, Industry Expertise, En...
 
Innovation day 2013 2.5 joris vanderschrick (verhaert) - embedded system de...
Innovation day 2013   2.5 joris vanderschrick (verhaert) - embedded system de...Innovation day 2013   2.5 joris vanderschrick (verhaert) - embedded system de...
Innovation day 2013 2.5 joris vanderschrick (verhaert) - embedded system de...
 
Software Testing and Quality Assurance Assignment 2
Software Testing and Quality Assurance Assignment 2Software Testing and Quality Assurance Assignment 2
Software Testing and Quality Assurance Assignment 2
 
IoT Evolution Expo- Machine Learning and the Cloud
IoT Evolution Expo- Machine Learning and the CloudIoT Evolution Expo- Machine Learning and the Cloud
IoT Evolution Expo- Machine Learning and the Cloud
 
IRJET- FPGA Implementation of an Improved Watchdog Timer for Safety Critical ...
IRJET- FPGA Implementation of an Improved Watchdog Timer for Safety Critical ...IRJET- FPGA Implementation of an Improved Watchdog Timer for Safety Critical ...
IRJET- FPGA Implementation of an Improved Watchdog Timer for Safety Critical ...
 
Predicting Machine Learning Pipeline Runtimes in the Context of Automated Mac...
Predicting Machine Learning Pipeline Runtimes in the Context of Automated Mac...Predicting Machine Learning Pipeline Runtimes in the Context of Automated Mac...
Predicting Machine Learning Pipeline Runtimes in the Context of Automated Mac...
 
DATI, AI E ROBOTICA @POLITO
DATI, AI E ROBOTICA @POLITODATI, AI E ROBOTICA @POLITO
DATI, AI E ROBOTICA @POLITO
 
See the App Performance Future with Predictive Analytics Webcast
See the App Performance Future with Predictive Analytics WebcastSee the App Performance Future with Predictive Analytics Webcast
See the App Performance Future with Predictive Analytics Webcast
 
Parameter Estimation of Software Reliability Growth Models Using Simulated An...
Parameter Estimation of Software Reliability Growth Models Using Simulated An...Parameter Estimation of Software Reliability Growth Models Using Simulated An...
Parameter Estimation of Software Reliability Growth Models Using Simulated An...
 
Six sigma-measure-phase2505
Six sigma-measure-phase2505Six sigma-measure-phase2505
Six sigma-measure-phase2505
 
FAULT DETECTION AND DIAGNOSIS OF INDUCTION MACHINE WITH ON-LINE PARAMETER PR...
FAULT DETECTION AND DIAGNOSIS OF INDUCTION MACHINE  WITH ON-LINE PARAMETER PR...FAULT DETECTION AND DIAGNOSIS OF INDUCTION MACHINE  WITH ON-LINE PARAMETER PR...
FAULT DETECTION AND DIAGNOSIS OF INDUCTION MACHINE WITH ON-LINE PARAMETER PR...
 
Innovating Quality Control in the Semiconductor Manufacturing Industry.pptx
Innovating Quality Control in the Semiconductor Manufacturing Industry.pptxInnovating Quality Control in the Semiconductor Manufacturing Industry.pptx
Innovating Quality Control in the Semiconductor Manufacturing Industry.pptx
 
A robust algorithm based on a failure sensitive matrix for fault diagnosis of...
A robust algorithm based on a failure sensitive matrix for fault diagnosis of...A robust algorithm based on a failure sensitive matrix for fault diagnosis of...
A robust algorithm based on a failure sensitive matrix for fault diagnosis of...
 
Sensor Fault Detection in IoT System Using Machine Learning
Sensor Fault Detection in IoT System Using Machine LearningSensor Fault Detection in IoT System Using Machine Learning
Sensor Fault Detection in IoT System Using Machine Learning
 
Implementing Vulnerability Management
Implementing Vulnerability Management Implementing Vulnerability Management
Implementing Vulnerability Management
 
IoT Device Intelligence & Real Time Anomaly Detection
IoT Device Intelligence & Real Time Anomaly DetectionIoT Device Intelligence & Real Time Anomaly Detection
IoT Device Intelligence & Real Time Anomaly Detection
 

Recently uploaded

Asset Management Software - Infographic
Asset Management Software - InfographicAsset Management Software - Infographic
Asset Management Software - InfographicHr365.us smith
 
Intelligent Home Wi-Fi Solutions | ThinkPalm
Intelligent Home Wi-Fi Solutions | ThinkPalmIntelligent Home Wi-Fi Solutions | ThinkPalm
Intelligent Home Wi-Fi Solutions | ThinkPalmSujith Sukumaran
 
EY_Graph Database Powered Sustainability
EY_Graph Database Powered SustainabilityEY_Graph Database Powered Sustainability
EY_Graph Database Powered SustainabilityNeo4j
 
Project Based Learning (A.I).pptx detail explanation
Project Based Learning (A.I).pptx detail explanationProject Based Learning (A.I).pptx detail explanation
Project Based Learning (A.I).pptx detail explanationkaushalgiri8080
 
Steps To Getting Up And Running Quickly With MyTimeClock Employee Scheduling ...
Steps To Getting Up And Running Quickly With MyTimeClock Employee Scheduling ...Steps To Getting Up And Running Quickly With MyTimeClock Employee Scheduling ...
Steps To Getting Up And Running Quickly With MyTimeClock Employee Scheduling ...MyIntelliSource, Inc.
 
办理学位证(UQ文凭证书)昆士兰大学毕业证成绩单原版一模一样
办理学位证(UQ文凭证书)昆士兰大学毕业证成绩单原版一模一样办理学位证(UQ文凭证书)昆士兰大学毕业证成绩单原版一模一样
办理学位证(UQ文凭证书)昆士兰大学毕业证成绩单原版一模一样umasea
 
Implementing Zero Trust strategy with Azure
Implementing Zero Trust strategy with AzureImplementing Zero Trust strategy with Azure
Implementing Zero Trust strategy with AzureDinusha Kumarasiri
 
Der Spagat zwischen BIAS und FAIRNESS (2024)
Der Spagat zwischen BIAS und FAIRNESS (2024)Der Spagat zwischen BIAS und FAIRNESS (2024)
Der Spagat zwischen BIAS und FAIRNESS (2024)OPEN KNOWLEDGE GmbH
 
Short Story: Unveiling the Reasoning Abilities of Large Language Models by Ke...
Short Story: Unveiling the Reasoning Abilities of Large Language Models by Ke...Short Story: Unveiling the Reasoning Abilities of Large Language Models by Ke...
Short Story: Unveiling the Reasoning Abilities of Large Language Models by Ke...kellynguyen01
 
Engage Usergroup 2024 - The Good The Bad_The Ugly
Engage Usergroup 2024 - The Good The Bad_The UglyEngage Usergroup 2024 - The Good The Bad_The Ugly
Engage Usergroup 2024 - The Good The Bad_The UglyFrank van der Linden
 
Call Girls in Naraina Delhi 💯Call Us 🔝8264348440🔝
Call Girls in Naraina Delhi 💯Call Us 🔝8264348440🔝Call Girls in Naraina Delhi 💯Call Us 🔝8264348440🔝
Call Girls in Naraina Delhi 💯Call Us 🔝8264348440🔝soniya singh
 
The Evolution of Karaoke From Analog to App.pdf
The Evolution of Karaoke From Analog to App.pdfThe Evolution of Karaoke From Analog to App.pdf
The Evolution of Karaoke From Analog to App.pdfPower Karaoke
 
buds n tech IT solutions
buds n  tech IT                solutionsbuds n  tech IT                solutions
buds n tech IT solutionsmonugehlot87
 
What is Binary Language? Computer Number Systems
What is Binary Language?  Computer Number SystemsWhat is Binary Language?  Computer Number Systems
What is Binary Language? Computer Number SystemsJheuzeDellosa
 
Automate your Kamailio Test Calls - Kamailio World 2024
Automate your Kamailio Test Calls - Kamailio World 2024Automate your Kamailio Test Calls - Kamailio World 2024
Automate your Kamailio Test Calls - Kamailio World 2024Andreas Granig
 
cybersecurity notes for mca students for learning
cybersecurity notes for mca students for learningcybersecurity notes for mca students for learning
cybersecurity notes for mca students for learningVitsRangannavar
 
What are the features of Vehicle Tracking System?
What are the features of Vehicle Tracking System?What are the features of Vehicle Tracking System?
What are the features of Vehicle Tracking System?Watsoo Telematics
 
why an Opensea Clone Script might be your perfect match.pdf
why an Opensea Clone Script might be your perfect match.pdfwhy an Opensea Clone Script might be your perfect match.pdf
why an Opensea Clone Script might be your perfect match.pdfjoe51371421
 
Salesforce Certified Field Service Consultant
Salesforce Certified Field Service ConsultantSalesforce Certified Field Service Consultant
Salesforce Certified Field Service ConsultantAxelRicardoTrocheRiq
 

Recently uploaded (20)

Asset Management Software - Infographic
Asset Management Software - InfographicAsset Management Software - Infographic
Asset Management Software - Infographic
 
Intelligent Home Wi-Fi Solutions | ThinkPalm
Intelligent Home Wi-Fi Solutions | ThinkPalmIntelligent Home Wi-Fi Solutions | ThinkPalm
Intelligent Home Wi-Fi Solutions | ThinkPalm
 
EY_Graph Database Powered Sustainability
EY_Graph Database Powered SustainabilityEY_Graph Database Powered Sustainability
EY_Graph Database Powered Sustainability
 
Project Based Learning (A.I).pptx detail explanation
Project Based Learning (A.I).pptx detail explanationProject Based Learning (A.I).pptx detail explanation
Project Based Learning (A.I).pptx detail explanation
 
Call Girls In Mukherjee Nagar 📱 9999965857 🤩 Delhi 🫦 HOT AND SEXY VVIP 🍎 SE...
Call Girls In Mukherjee Nagar 📱  9999965857  🤩 Delhi 🫦 HOT AND SEXY VVIP 🍎 SE...Call Girls In Mukherjee Nagar 📱  9999965857  🤩 Delhi 🫦 HOT AND SEXY VVIP 🍎 SE...
Call Girls In Mukherjee Nagar 📱 9999965857 🤩 Delhi 🫦 HOT AND SEXY VVIP 🍎 SE...
 
Steps To Getting Up And Running Quickly With MyTimeClock Employee Scheduling ...
Steps To Getting Up And Running Quickly With MyTimeClock Employee Scheduling ...Steps To Getting Up And Running Quickly With MyTimeClock Employee Scheduling ...
Steps To Getting Up And Running Quickly With MyTimeClock Employee Scheduling ...
 
办理学位证(UQ文凭证书)昆士兰大学毕业证成绩单原版一模一样
办理学位证(UQ文凭证书)昆士兰大学毕业证成绩单原版一模一样办理学位证(UQ文凭证书)昆士兰大学毕业证成绩单原版一模一样
办理学位证(UQ文凭证书)昆士兰大学毕业证成绩单原版一模一样
 
Implementing Zero Trust strategy with Azure
Implementing Zero Trust strategy with AzureImplementing Zero Trust strategy with Azure
Implementing Zero Trust strategy with Azure
 
Der Spagat zwischen BIAS und FAIRNESS (2024)
Der Spagat zwischen BIAS und FAIRNESS (2024)Der Spagat zwischen BIAS und FAIRNESS (2024)
Der Spagat zwischen BIAS und FAIRNESS (2024)
 
Short Story: Unveiling the Reasoning Abilities of Large Language Models by Ke...
Short Story: Unveiling the Reasoning Abilities of Large Language Models by Ke...Short Story: Unveiling the Reasoning Abilities of Large Language Models by Ke...
Short Story: Unveiling the Reasoning Abilities of Large Language Models by Ke...
 
Engage Usergroup 2024 - The Good The Bad_The Ugly
Engage Usergroup 2024 - The Good The Bad_The UglyEngage Usergroup 2024 - The Good The Bad_The Ugly
Engage Usergroup 2024 - The Good The Bad_The Ugly
 
Call Girls in Naraina Delhi 💯Call Us 🔝8264348440🔝
Call Girls in Naraina Delhi 💯Call Us 🔝8264348440🔝Call Girls in Naraina Delhi 💯Call Us 🔝8264348440🔝
Call Girls in Naraina Delhi 💯Call Us 🔝8264348440🔝
 
The Evolution of Karaoke From Analog to App.pdf
The Evolution of Karaoke From Analog to App.pdfThe Evolution of Karaoke From Analog to App.pdf
The Evolution of Karaoke From Analog to App.pdf
 
buds n tech IT solutions
buds n  tech IT                solutionsbuds n  tech IT                solutions
buds n tech IT solutions
 
What is Binary Language? Computer Number Systems
What is Binary Language?  Computer Number SystemsWhat is Binary Language?  Computer Number Systems
What is Binary Language? Computer Number Systems
 
Automate your Kamailio Test Calls - Kamailio World 2024
Automate your Kamailio Test Calls - Kamailio World 2024Automate your Kamailio Test Calls - Kamailio World 2024
Automate your Kamailio Test Calls - Kamailio World 2024
 
cybersecurity notes for mca students for learning
cybersecurity notes for mca students for learningcybersecurity notes for mca students for learning
cybersecurity notes for mca students for learning
 
What are the features of Vehicle Tracking System?
What are the features of Vehicle Tracking System?What are the features of Vehicle Tracking System?
What are the features of Vehicle Tracking System?
 
why an Opensea Clone Script might be your perfect match.pdf
why an Opensea Clone Script might be your perfect match.pdfwhy an Opensea Clone Script might be your perfect match.pdf
why an Opensea Clone Script might be your perfect match.pdf
 
Salesforce Certified Field Service Consultant
Salesforce Certified Field Service ConsultantSalesforce Certified Field Service Consultant
Salesforce Certified Field Service Consultant
 

AI Reliability Predicts Power Plant Shutdowns

  • 2. Goal And Objectives 2 ▪ Сonfigure and demonstrate the capabilities to identify process and equipment anomalies to predict unplanned shutdowns for two combined-cycle power plants. Analyze the following 6 subsystems: GT, ST, 2 Generators, Boiler, Gas compressor Goal Objectives Data sources P&ID Visually detected defects Planned and unplanned shutdowns history Sensors ▪ Creating and Replicating Models Between Similar Objects. Because of the strong differences in power generation infrastructure objects, the ability to scale created models to objects of the same type has not been shown to be effective. ▪ Data Integration. Services for handling downloaded engineering data from different types of sources, reducing the time spent on cleanup, preparation, and other data management tasks. ▪ Implement and manage a large number of models in production. Use of multiple infrastructure components and multi-model orchestration. ▪ Development of advanced user interfaces. Display both anomaly data and the potential economic impact of preventing identified anomalies, operator actions, and output for key users on achieving planned targets. ▪ Target percentage of predicted complete unscheduled shutdowns in the test sample > 66%.
  • 4. • By default: 1 year train, 4 years test with retrain every 2 months • Approach was adopted to every particular subsystem • Test period complete unplanned shutdowns: 23 (out of 27) • 14 ML models with rolling window approach - 336 ML models versions for dedicated periods required: (6 subsystems + 1 power unit as a whole) * 2 power units * 4 test years * 6 models per year Iteration 1 Test Train Test Iteration 2 Train Buffer zone between train/test 1Y 2M 1M Unplanned shutdowns Rolling window train/test approach was used 1Y 1M 2M
  • 5. 5 Several Models trained to recognize expected tags values Expected by ML model value Actual value Subsystem power Anomaly level detected ML model recognizes how this tag behave according to the past and to other tags behavior
  • 6. 6 Using Expected Value We Can Identify Possible Anomalies Expected by ML model value Actual value Subsystem power Anomaly level detected Vibration should go down according to all the other tags behavior, but it goes up. Anomaly level increases
  • 7. 7 336 Models tested about anomalous equipment behavior generated • Risk score (anomaly level) calculated on basis of all the subsystem tags anomaly levels - for every hour in test period for every subsystem and for power unit as a whole • If Risk score is higher than threshold – Alert was generated Boiler PU-2 example: Train period Test period Alert generation threshold Alerts before shutdowns – shutdown predicted Alerts not before shutdowns: could be valuable (real anomaly) or wrong No alert before shutdowns – shutdown not predicted Subsystem anomaly level
  • 8. 8 Production team reviewed alerts in detail Application detected anomaly: High discharge behind the air house Alert review example: PU-1 GT, shutdown 03.03.21, alert 23.01.2021 (36 days before shutdown), another alert 12.02.2021 (17 days before) Investigation report conclusion: high discharge behind the air house: dP of the fine filters is high, the CSF is damaged Drift Application detected anomaly: dP of the fine filters is high at both points Application detected anomaly: dP CSF is low at both points (damaged?) Expected by ML model value Tag actual value Subsystem power Anomaly level • 2600 tags mapped to subsystems and key failure mode tags dedicated with alarm/ protection setpoints understanding • >19 alerts reviewed: • 77 iterations totally for 15 AI models • >5 new diagnostic metrics developed • >770 plots with anomalous tags behavior compared with investigation acts to check if alert relates to a shutdown • 5 out of 19 alerts were not approved (2 of them after detailed internal discussions. Trial had preliminary recall 69.6% before) • 5 expert rules developed jointly on basis of AI anomalies • Production team demonstrated deep expertise and high readiness to interpret AI alerts and develop expert rules
  • 9. Machine Learning model test results 9 Number of shutdowns in test period Alerts before shutdowns generated (before review) Statistical Recall Correctly detected alerts (approved by SME) Reviewed Recall (Anomaly relates to a shutdown) Average alerts frequency Alerts in a week: Average lead time, days 23 19 82,6% 14 60,9% 0,8 9,8 • Statistical recall 82.6% – alerts generated by the solution in advance of unplanned shutdowns • Approved Recall 60.9% – alerts verified and confirmed by experts, proving that early anomaly detection can be operationally used for unplanned shutdown prediction, i.e., anomalies detected are related to shutdowns and provide potential reasons or early warning indications. All confirmed alerts either were generated earlier than staff detected a defect (11 alerts), or provided new information about defect evolution (3 alerts) • It is valuable to consider an accuracy rate of 82.6% when comparing with world practices, since there is usually no investigation for the alert-shutdown relationship • Of all 23 failure events, only 15 were technically predictable based on the supplied data, as agreed. The Reliability solution picked 14 of these (or 93%) * A methodology has been developed that will allow significantly reduce the number of faulse positives during production implementation
  • 10. Recall references science papers 1) ”Neural network-based data-driven modelling of anomaly detection in thermal power plant” from Automatika Journal for Control, Measurement, Electronics, Computing and Communications Published online: 07 Jul 2017 https://core.ac.uk/download/pdf/212472032.pdf 2) “Fault Detection in a Compined Cycle Power Based on Neural Networks …” Master’s Thesis from Montan Universitat, Philipp Rohrweck, 2021 https://pure.unileoben.ac.at/portal/files/6491873/AC16191180.pdf • Statistical recall 50%-60% is good result if you model subsystem as a whole. All the results with better accuracy were delivered for detailed equipment or particular failure mode modelling • It is worth using an accuracy rate of 82.6% when comparing with world practices, since there is usually no check for the alert-shutdown relationship
  • 12. Operational staff efficiency increase 12 Number of alarms raised per month per power unit Few times per day <2 With app Lead time, in days 3 10 With app Reviewed Recall in % (share of shutdowns correctly predicted) 35% 61% With app Performance can be further improved during the production deployment: • More than 20 ML models shall be configured per power unit rather than 6 models per the trial project: equipment/ defect level • Full set of PU tags should be analyzed. E.g., Steam turbine-2 generator currents are in protection metrics only. More sensor data can be ingested for the project. • It is valuable to add metrics for cumulative effect on equipment reliability estimation • False Positives drastic decrease due to special treatment of G CV, subsystem power, alarm or expert set points usage Baseline (Alarm setpoints) Baseline Baseline