Wind Turbine Anomaly Detection for Underperformance Root Cause Analysis
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conventional methods for identifying turbine underperformance in wind turbines are manual and uncertain, making it difficult to automatically connect energy underproduction to operational anomalies and hindering root cause identification.
Innovation Solution
An automated system and method that applies operating characteristic models to detect turbine underperformance and operational anomalies, using data filtering, preprocessing, and baseline models to identify root causes, enabling automatic adjustment of control parameters and maintenance recommendations.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If manual analysis of turbine performance data is used, then results can be obtained, but large uncertainty is introduced and root cause identification becomes difficult
Solution Approach 1:
The patent replaces manual mechanical analysis with an automated computer-based system that uses machine learning models and algorithms to analyze turbine performance data, eliminating human error and subjectivity while preserving all relevant information for root cause identification
Solution Approach 2:
The patent introduces an intermediary automated analysis system that acts as a bridge between raw turbine data and actionable insights, using trained machine learning models to automatically connect energy underproduction with operational anomalies and identify root causes
2Reliability
If automated detection systems are implemented, then root cause identification is improved, but system complexity increases
Solution Approach 1:
The patent creates a universal automated detection system that performs multiple functions including data collection, preprocessing, anomaly detection, and root cause identification through integrated machine learning models, reducing the need for separate specialized systems
Solution Approach 2:
The patent implements preliminary action by pre-training machine learning models with historical turbine data before deployment, so that when the system operates, the complex analysis is already prepared and can quickly identify root causes without requiring complex real-time computation
Data Source
Figure 1
Figure 2
Figure 3
AI summary
A method of correcting turbine underperformance includes calculating a power production curve using monitored data, detecting changes between the monitored data and a baseline power production curve, generating operability curves for paired operational variables from the monitored data, detecting changes between the operability curves and corresponding baseline operability curves, comparing the changes to a respective predetermined metric, and if the change exceeds the metric, providing feedback to a turbine control system identifying at least one of the paired operational variables for each paired variable in excess of the metric. A system and a non-transitory computer-readable medium are also disclosed.