SlideShare a Scribd company logo

Amar Pradhan: 2013 Sandia National Laboratoies Wind Plant Reliability Workshop

•
•
Sandia National Laboratories: Energy & Climate: Renewables
Sandia National Laboratories: Energy & Climate: Renewables

This document summarizes Fluitec Wind, a machine learning company that uses diagnostic data from over 5,000 wind turbines to predict failures and reduce wind energy costs. It explains that Fluitec aggregates operational, genetic, and diagnostic data to create predictive models of turbine health. Through "fingerprinting" techniques on large oil analysis datasets, the company can identify turbines following specific failure modes with 95% accuracy. This allows early detection and prevention of downtime from components like gearboxes. The document provides a case study on improving alarm systems from individual to multi-attribute approaches and concludes by outlining Fluitec's data-driven process to generate analytical reports and work order tools for clients.

Related slideshows

Small Wind Turbine Market In India1
Small Wind Turbine Market In India1Small Wind Turbine Market In India1
Small Wind Turbine Market In India1
 
Wind Power Energy
Wind Power EnergyWind Power Energy
Wind Power Energy
 
Wind Vs Conventional Electricity Economics
Wind Vs Conventional Electricity EconomicsWind Vs Conventional Electricity Economics
Wind Vs Conventional Electricity Economics
 
1 of 28
Download to read offline
Use of Data to Reduce Wind Energy Costs Machine to Machine Learning for the Wind Industry
We are Fluitec Wind
We are a machine to machine learning company focused on improving performance © 2011 Fluitec International. All rights reserved. Fluitec Offices as Viewed from Space USA Belgium China Singapore
Awarded $3.3M through the New Jersey Clean Energy Manufacturing Fund to accelerate adoption of Technology to Reduce the Cost of Wind Energy. Matched by leading European Cleantech VCs.
An award winning company and a stellar team with unparalleled expertise. “Most Promising Innovation” “People’s Choice Award”
Fluitec Wind currently monitors >5,000 turbines: 8 GW Vestas V82, GE 1.5, & Acciona 1.5 turbines are best represented Fluitec Wind has the Largest Aggregated Database of Diagnostic & Operational Data in the World Acciona, 34% Vestas, 39% GE, 13% Suzlon, 4% Gamesa, 5% Mitsubishi, 2% Nordex, 3%
WTG Goal: Thrive in Variability
Wind turbines have high variability and are expensive to access. Therefore significant remote monitoring capabilities exist.
High Variability is also dealt with via specific key components. Most are rotating.
>60% of Unscheduled Downtime is on Nacelle Rotating Components. >40% of total downtime is unscheduled >80% of downtime on lubricated components is unscheduled Problem Component TOTAL Downtime Events Total Downtime (days) Unscheduled Downtime (days) Unscheduled Proportion Lubricated Component Downtime (days) Lubricated Component Unscheduled Downtime - - Yes No Gearbox 2300 802 1498 1,750 1,500 86% 1,750 1,500 Generator 1965 1651 314 834 595 71% 834 595 Yaw 603 272 331 253 216 85% 253 216 Hydraulic System 37 3 34 6 0 0% 6 0 Pitch Blade 956 564 392 547 389 71% - Rotor 306 288 18 80 71 89% - Other/Electrical 23988 3780 20208 5,264 1,039 20% - Grid 430 6 424 37 1 3% - Anemometer 12 7 5 2 2 100% - 30,598 7,374 23,224 8,773 3,811 43% 2,844 2,311 Unscheduled Events
What data is attractive and applicable?
M2M Analytics Work Orders Oil Analysis Data Operational Configuration Weather Data Existing Existing Existing Existing Existing SCADA Alerts & Sensors You have existing data with immediate predictive value. We can utilize this without any capital expense to identify and reduce risks.
Unique Extraction of Value from Data
Genetic: Equipment Permutation Location >20 Input Attributes Operational: SCADA O&M Logs Insurance Claims >1000 Outputs We aggregate your data to enhance signal to noise detection. Allowing for noisy, small datasets to be utilized. We can corroborate the reliability of any data point and use. We also report this quality so you can improve in the future. Diagnostic: Sensors Production Weather Oil Analysis Vibration >500 Input Attributes
Oil Analysis is the deepest and widest diagnostic data set and perfect for such analyses if unlocked. We utilize “fingerprinting” technology on this big data. Further minimizing the effect of outliers or poor data. Similar to how doctors use blood analysis, and the police use criminal data.
We aggregate global data to have a map of good and poor states of various turbine permutations. Fleets of various ages and models become predictable. Current database size is 8 GW, with an avg farm age of 5 years
Allows an accurate method to identify turbines that are following a specific failure mode or pattern. Has a proven 95% accuracy in gearbox failure prediction. Finally, we match “fingerprints” to poor states, not simply identifying “abnormal” turbines. This drastically increases the predictive value of data. Police catch criminals by matching to known offenders. NN
N Three Algorithmic Steps to Creating a Predictive Map 1. Similarity Define the similarity between each point in time to every other point in time 2. Cluster Cluster the points in time based on their similarity 3. Severity Asses the severity of each cluster
Short Case Study: Multi-Attribute Alarms
In the following we will focus on the limitations of individual attribute alarms, and discuss how we develop multi-attribute alarms. The discussion is centered on gearbox oil analysis, as it provides a large number of attributes to consider, and the individual attribute approach is particularly flawed. However, the fundamentals of our recommendations should be exercised on all turbine level data: temperatures, speeds, direction, etc. Disclaimer
Copper Iron Silicon 50 100% 100 99% 60 99% 30 99% 50 96% 45 96% 1 25% 1 16% 30 85% Visc40 Oil Age PQ Index 384 99% 1691 90% 15 91% 320 61% 715 50% 8 50% 256 20% 178 10% 1 21% Individual Attribute Alarms Are Not Working & Are Not Predictive Within an analysis of 25,000 samples: ~99% of the time, the individual values received are below the critical limits. Average Visc40 and Iron prior to gearbox failure is 318 and 11, respectively. Individual attribute alarms are inherently less predictive. Percent of Oil Sample Data Below Adjacent Value
Include: 1. Genetic Attributes 2. Multiple Attributes to define an Alarm Band 3. Rate of Change Attributes Ideally use all of the above Three ways to make Better Alarm Levels
Use Genetic Attributes to define Bands Simply looking at attributes in the context of the equipment permutation gives a clear picture of what are normal levels. Especially Ingression and Wear elements
Tune Multi-Attribute Alarms to Failures Clustering by Gearbox, one can see a profile or “fingerprint” that precedes failure
1. In the vast majority of instances just prior to failure, oil attributes were within the “acceptable range” provided by OEMs. 2. The pronounced difference in the profile prior to failure, versus in general can be seen via multi- attribute bands. 3. Rate of Change thresholds are more effective in highly variable environments. Case Study Summary
What does Fluitec Wind Do?
Raw Unstructured Data: equipment model/year, SCADA alerts, production data, oil analysis Usable Data 6-10 weeks How to Get Started: Send Us Raw Data & We Provide Deliverables 1-3 Data Cleaned & Structured: Returned in any format Analytical Reports Expert Risk Assessment Provided as Report Web portal: visualization, analysis, and dynamic work order toolkit Provide Raw Data: best results are if sample set has 2,000 turbine-years of data, high failure rates, and/or use of popular equipment permutation (Vestas V82, GE 1.5, AW1500)
M2M Analytics Slashing O&M Costs in the Wind Industry Amar Pradhan CTO www.FluitecWind.com

More Related Content

Amar Pradhan: 2013 Sandia National Laboratoies Wind Plant Reliability Workshop

  • 1. Use of Data to Reduce Wind Energy Costs Machine to Machine Learning for the Wind Industry
  • 3. We are a machine to machine learning company focused on improving performance © 2011 Fluitec International. All rights reserved. Fluitec Offices as Viewed from Space USA Belgium China Singapore
  • 4. Awarded $3.3M through the New Jersey Clean Energy Manufacturing Fund to accelerate adoption of Technology to Reduce the Cost of Wind Energy. Matched by leading European Cleantech VCs.
  • 5. An award winning company and a stellar team with unparalleled expertise. “Most Promising Innovation” “People’s Choice Award”
  • 6. Fluitec Wind currently monitors >5,000 turbines: 8 GW Vestas V82, GE 1.5, & Acciona 1.5 turbines are best represented Fluitec Wind has the Largest Aggregated Database of Diagnostic & Operational Data in the World Acciona, 34% Vestas, 39% GE, 13% Suzlon, 4% Gamesa, 5% Mitsubishi, 2% Nordex, 3%
  • 7. WTG Goal: Thrive in Variability
  • 8. Wind turbines have high variability and are expensive to access. Therefore significant remote monitoring capabilities exist.
  • 9. High Variability is also dealt with via specific key components. Most are rotating.
  • 10. >60% of Unscheduled Downtime is on Nacelle Rotating Components. >40% of total downtime is unscheduled >80% of downtime on lubricated components is unscheduled Problem Component TOTAL Downtime Events Total Downtime (days) Unscheduled Downtime (days) Unscheduled Proportion Lubricated Component Downtime (days) Lubricated Component Unscheduled Downtime - - Yes No Gearbox 2300 802 1498 1,750 1,500 86% 1,750 1,500 Generator 1965 1651 314 834 595 71% 834 595 Yaw 603 272 331 253 216 85% 253 216 Hydraulic System 37 3 34 6 0 0% 6 0 Pitch Blade 956 564 392 547 389 71% - Rotor 306 288 18 80 71 89% - Other/Electrical 23988 3780 20208 5,264 1,039 20% - Grid 430 6 424 37 1 3% - Anemometer 12 7 5 2 2 100% - 30,598 7,374 23,224 8,773 3,811 43% 2,844 2,311 Unscheduled Events
  • 11. What data is attractive and applicable?
  • 12. M2M Analytics Work Orders Oil Analysis Data Operational Configuration Weather Data Existing Existing Existing Existing Existing SCADA Alerts & Sensors You have existing data with immediate predictive value. We can utilize this without any capital expense to identify and reduce risks.
  • 13. Unique Extraction of Value from Data
  • 14. Genetic: Equipment Permutation Location >20 Input Attributes Operational: SCADA O&M Logs Insurance Claims >1000 Outputs We aggregate your data to enhance signal to noise detection. Allowing for noisy, small datasets to be utilized. We can corroborate the reliability of any data point and use. We also report this quality so you can improve in the future. Diagnostic: Sensors Production Weather Oil Analysis Vibration >500 Input Attributes
  • 15. Oil Analysis is the deepest and widest diagnostic data set and perfect for such analyses if unlocked. We utilize “fingerprinting” technology on this big data. Further minimizing the effect of outliers or poor data. Similar to how doctors use blood analysis, and the police use criminal data.
  • 16. We aggregate global data to have a map of good and poor states of various turbine permutations. Fleets of various ages and models become predictable. Current database size is 8 GW, with an avg farm age of 5 years
  • 17. Allows an accurate method to identify turbines that are following a specific failure mode or pattern. Has a proven 95% accuracy in gearbox failure prediction. Finally, we match “fingerprints” to poor states, not simply identifying “abnormal” turbines. This drastically increases the predictive value of data. Police catch criminals by matching to known offenders. NN
  • 18. N Three Algorithmic Steps to Creating a Predictive Map 1. Similarity Define the similarity between each point in time to every other point in time 2. Cluster Cluster the points in time based on their similarity 3. Severity Asses the severity of each cluster
  • 19. Short Case Study: Multi-Attribute Alarms
  • 20. In the following we will focus on the limitations of individual attribute alarms, and discuss how we develop multi-attribute alarms. The discussion is centered on gearbox oil analysis, as it provides a large number of attributes to consider, and the individual attribute approach is particularly flawed. However, the fundamentals of our recommendations should be exercised on all turbine level data: temperatures, speeds, direction, etc. Disclaimer
  • 21. Copper Iron Silicon 50 100% 100 99% 60 99% 30 99% 50 96% 45 96% 1 25% 1 16% 30 85% Visc40 Oil Age PQ Index 384 99% 1691 90% 15 91% 320 61% 715 50% 8 50% 256 20% 178 10% 1 21% Individual Attribute Alarms Are Not Working & Are Not Predictive Within an analysis of 25,000 samples: ~99% of the time, the individual values received are below the critical limits. Average Visc40 and Iron prior to gearbox failure is 318 and 11, respectively. Individual attribute alarms are inherently less predictive. Percent of Oil Sample Data Below Adjacent Value
  • 22. Include: 1. Genetic Attributes 2. Multiple Attributes to define an Alarm Band 3. Rate of Change Attributes Ideally use all of the above Three ways to make Better Alarm Levels
  • 23. Use Genetic Attributes to define Bands Simply looking at attributes in the context of the equipment permutation gives a clear picture of what are normal levels. Especially Ingression and Wear elements
  • 24. Tune Multi-Attribute Alarms to Failures Clustering by Gearbox, one can see a profile or “fingerprint” that precedes failure
  • 25. 1. In the vast majority of instances just prior to failure, oil attributes were within the “acceptable range” provided by OEMs. 2. The pronounced difference in the profile prior to failure, versus in general can be seen via multi- attribute bands. 3. Rate of Change thresholds are more effective in highly variable environments. Case Study Summary
  • 26. What does Fluitec Wind Do?
  • 27. Raw Unstructured Data: equipment model/year, SCADA alerts, production data, oil analysis Usable Data 6-10 weeks How to Get Started: Send Us Raw Data & We Provide Deliverables 1-3 Data Cleaned & Structured: Returned in any format Analytical Reports Expert Risk Assessment Provided as Report Web portal: visualization, analysis, and dynamic work order toolkit Provide Raw Data: best results are if sample set has 2,000 turbine-years of data, high failure rates, and/or use of popular equipment permutation (Vestas V82, GE 1.5, AW1500)
  • 28. M2M Analytics Slashing O&M Costs in the Wind Industry Amar Pradhan CTO www.FluitecWind.com