Wind Turbine Fault Root Cause Analysis Using Machine Learning
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Wind turbine systems face challenges in efficiently identifying the root cause of faults due to the large quantity of error codes and textual log entries, making it difficult and time-consuming for professionals to diagnose issues.
Innovation Solution
A Root Cause Analysis (RCA) system that uses a machine learning model to classify and locate candidate root causes by analyzing operational data, including logs, telemetry data, and configuration data, to provide accurate and time-efficient fault identification.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If professionals manually scrutinize error codes and log entries to identify root causes, then diagnostic accuracy can be maintained, but the time required for troubleshooting increases significantly
Solution Approach 1:
The patent introduces an intermediary system (RCA system with machine learning model) that mediates between the raw operational data/logs and the final root cause identification. This intermediary automatically processes and analyzes the data, reducing the time burden on professionals while maintaining diagnostic accuracy through sophisticated pattern recognition algorithms.
Solution Approach 2:
The patent replaces the manual mechanical process of scrutinizing logs with an automated computational system. The machine learning model substitutes human analysts in the initial data processing and pattern recognition tasks, dramatically reducing troubleshooting time while preserving diagnostic quality through algorithmic analysis.
2Loss of information
If the wind turbine system implements comprehensive event and alarm systems to record all faults, then diagnostic information completeness improves, but the complexity of analyzing the data increases
Solution Approach 1:
The patent extracts the essential diagnostic information from the comprehensive log data using machine learning patterns. Instead of requiring analysts to process all raw data, the system extracts and highlights only the relevant features and patterns that indicate root causes, reducing analysis complexity while maintaining information completeness.
Solution Approach 2:
The patent transforms the raw operational data into meaningful diagnostic parameters through the machine learning model. By changing the representation of data from raw logs to structured patterns and features, the system makes the data more manageable and easier to analyze while preserving all critical diagnostic information.
3Productivity
If the RCA system uses a machine learning model to automatically classify root causes, then troubleshooting speed increases, but the system complexity increases
Solution Approach 1:
The patent applies preliminary action by pre-training the machine learning model with extensive operational data before deployment. This preliminary training phase enables the system to quickly classify root causes during actual troubleshooting without requiring complex real-time computations, thus increasing troubleshooting speed while managing system complexity through offline preparation.
Data Source
AI summary
Disclosed is a method, performed by a root cause analysis system. The method comprises obtaining operational data associated with operation of a wind turbine system in response to a fault of the wind turbine system. The method comprises determining, based on the operational data, a set of candidate root causes associated with the fault, by applying a machine learning model to the operational data. The machine learning model is configured to classify and/or locate one or more candidate root causes. The method comprises providing, based on the set of candidate root causes, output data indicative of at least one root cause of the fault of the wind turbine system.