amar pradhan: 2013 sandia national laboratoies wind plant reliability workshop

28
Use of Data to Reduce Wind Energy Costs Machine to Machine Learning for the Wind Industry

Upload: sandia-national-laboratories-energy-climate-renewables

Post on 18-Nov-2014

546 views

Category:

Business


1 download

DESCRIPTION

Use of Data to Reduce Wind Energy Costs

TRANSCRIPT

Page 1: Amar Pradhan: 2013 Sandia National Laboratoies Wind Plant Reliability Workshop

Use of Data to Reduce Wind Energy Costs

Machine to Machine Learning for the Wind Industry

Page 2: Amar Pradhan: 2013 Sandia National Laboratoies Wind Plant Reliability Workshop

We are Fluitec Wind

Page 3: Amar Pradhan: 2013 Sandia National Laboratoies Wind Plant Reliability Workshop

We are a machine to machine learning company focused on improving performance

© 2011 Fluitec International. All rights reserved.

Fluitec Offices as Viewed from Space

USABelgium

China

Singapore

Page 4: Amar Pradhan: 2013 Sandia National Laboratoies Wind Plant Reliability Workshop

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.

Page 5: Amar Pradhan: 2013 Sandia National Laboratoies Wind Plant Reliability Workshop

An award winning company and a stellar team with unparalleled expertise.

“Most Promising Innovation”

“People’s Choice Award”

Page 6: Amar Pradhan: 2013 Sandia National Laboratoies Wind Plant Reliability Workshop

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%

Page 7: Amar Pradhan: 2013 Sandia National Laboratoies Wind Plant Reliability Workshop

WTG Goal: Thrive in Variability

Page 8: Amar Pradhan: 2013 Sandia National Laboratoies Wind Plant Reliability Workshop

Wind turbines have high variability and are expensive to access.Therefore significant remote monitoring capabilities exist.

Page 9: Amar Pradhan: 2013 Sandia National Laboratoies Wind Plant Reliability Workshop

High Variability is also dealt with via specific key components. Most are rotating.

Page 10: Amar Pradhan: 2013 Sandia National Laboratoies Wind Plant Reliability Workshop

>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 NoGearbox 2300 802 1498 1,750 1,500 86% 1,750 1,500

Generator 1965 1651 314 834 595 71% 834 595Yaw 603 272 331 253 216 85% 253 216

Hydraulic System 37 3 34 6 0 0% 6 0Pitch 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

Page 11: Amar Pradhan: 2013 Sandia National Laboratoies Wind Plant Reliability Workshop

What data is attractive and applicable?

Page 12: Amar Pradhan: 2013 Sandia National Laboratoies Wind Plant Reliability Workshop

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.

Page 13: Amar Pradhan: 2013 Sandia National Laboratoies Wind Plant Reliability Workshop

Unique Extraction of Value from Data

Page 14: Amar Pradhan: 2013 Sandia National Laboratoies Wind Plant Reliability Workshop

Genetic: Equipment

PermutationLocation

>20 Input Attributes

Operational:SCADA

O&M LogsInsurance 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

ProductionWeather

Oil AnalysisVibration

>500 Input Attributes

Page 15: Amar Pradhan: 2013 Sandia National Laboratoies Wind Plant Reliability Workshop

Oil Analysis is the deepest and widest diagnostic data set and perfect for such analyses if unlocked.

We utilize “fingerprinting” technology on this bigdata. Further minimizing the effect of outliers or poor data. Similar to how doctors use blood analysis, and the police use criminal data.

Page 16: Amar Pradhan: 2013 Sandia National Laboratoies Wind Plant Reliability Workshop

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 avgfarm age of 5 years

Page 17: Amar Pradhan: 2013 Sandia National Laboratoies Wind Plant Reliability Workshop

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

Page 18: Amar Pradhan: 2013 Sandia National Laboratoies Wind Plant Reliability Workshop

N

Three Algorithmic Steps to Creating a Predictive Map

1. SimilarityDefine the similarity between each point in time to every other point in time

2. ClusterCluster the points in time based on their similarity

3. SeverityAsses the severity of each cluster

Page 19: Amar Pradhan: 2013 Sandia National Laboratoies Wind Plant Reliability Workshop

Short Case Study: Multi-Attribute Alarms

Page 20: Amar Pradhan: 2013 Sandia National Laboratoies Wind Plant Reliability Workshop

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

Page 21: Amar Pradhan: 2013 Sandia National Laboratoies Wind Plant Reliability Workshop

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

Page 22: Amar Pradhan: 2013 Sandia National Laboratoies Wind Plant Reliability Workshop

Include:1. Genetic Attributes2. Multiple Attributes to define an Alarm Band3. Rate of Change AttributesIdeally use all of the above

Three ways to make Better Alarm Levels

Page 23: Amar Pradhan: 2013 Sandia National Laboratoies Wind Plant Reliability Workshop

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

Page 24: Amar Pradhan: 2013 Sandia National Laboratoies Wind Plant Reliability Workshop

Tune Multi-Attribute Alarms to Failures

Clustering by Gearbox, one can see a profile or “fingerprint” that precedes failure

Page 25: Amar Pradhan: 2013 Sandia National Laboratoies Wind Plant Reliability Workshop

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

Page 26: Amar Pradhan: 2013 Sandia National Laboratoies Wind Plant Reliability Workshop

What does Fluitec Wind Do?

Page 27: Amar Pradhan: 2013 Sandia National Laboratoies Wind Plant Reliability Workshop

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)

Page 28: Amar Pradhan: 2013 Sandia National Laboratoies Wind Plant Reliability Workshop

M2M Analytics

Slashing O&M Costs in the Wind Industry

Amar PradhanCTO

www.FluitecWind.com