Wind Turbine Root Cause Classification From Fault Logs

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Wind turbine systems face challenges in efficiently identifying the root cause of faults due to the vast amount of error codes and textual log entries, making it time-consuming for professionals to discern the true cause even with domain knowledge.

Innovation Solution

A Root Cause Analysis (RCA) system utilizing a machine learning model to classify and locate candidate root causes by analyzing operational data, including logs, telemetry data, and configuration data, thereby narrowing down possible causes and providing indicative output for technicians.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Measurement precision

If professionals manually scrutinize error codes and log entries to identify root causes, then domain knowledge can be applied to diagnose faults, but the process becomes extremely time-consuming and difficult due to the large quantity of data

Engineering Contradiction:
Improveroot cause identification accuracyVSAvoidtroubleshooting time
Core Design Contradiction:
Measurement precisionVSLoss of time

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 human technician. The system automatically processes and analyzes the large volume of error codes and log entries, presenting filtered and prioritized root cause candidates to technicians, thereby reducing both the time and cognitive load required for diagnosis while maintaining high accuracy

Inventive Principle:
Principle #24Intermediary (Mediator)

Solution Approach 2:

The patent replaces the manual mechanical process of scrutinizing logs with an automated machine learning-based analysis system. The ML model automatically patterns recognition and root cause identification from operational data, substituting the manual inspection process with automated intelligent analysis that operates faster and more consistently

Inventive Principle:
Principle #28Mechanics substitution (Replace mechanical system)

2Loss of information

If the wind turbine system records comprehensive operational data including all error codes and log entries, then complete information is available for diagnosis, but the complexity of data processing increases significantly

Engineering Contradiction:
Improvefault information completenessVSAvoiddata processing complexity
Core Design Contradiction:
Loss of informationVSDevice complexity

Solution Approach 1:

The patent extracts only the most relevant and diagnostic information from the comprehensive operational data using the machine learning model. The system identifies and extracts key patterns, error codes, and log entries that are most indicative of root causes, separating signal from noise in the large volume of recorded data to reduce processing complexity while maintaining diagnostic completeness

Inventive Principle:
Principle #2Taking out (Extraction)

Solution Approach 2:

The patent transforms the raw operational data into processed features and metrics that are more suitable for root cause analysis. The machine learning model changes the parameters of the data from raw log entries to structured, analyzable features that reveal patterns and relationships, making the data processing more manageable and efficient

Inventive Principle:
Principle #35Parameter changes

Data Source

PatentEP4390593A1Root cause analysis of a wind turbine system
Publication Date: 2024.06.26 VESTAS WIND SYSTEMS AS
  • EP4390593A1 patent drawingFigure 1
  • EP4390593A1 patent drawingFigure 2
  • EP4390593A1 patent drawingFigure 3

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.