Wind Turbine Operating State Evaluation via Dynamic Thresholding

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Existing methods for monitoring the operating state of wind turbines struggle to accurately and early detect abnormalities due to environmental factors and the need for wide margin thresholds, leading to potential false detections and delayed maintenance.

Innovation Solution

A method and device that evaluate the operating state by calculating an estimated value based on the operating condition using physical or machine learning models, comparing it with actual values, and verifying abnormality determinations through statistical processing and correlation analysis to reduce false positives and negatives.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Reliability

If a threshold with large margin is set to account for environmental variations and operating conditions, then false detections are reduced, but abnormality detection timing is delayed

Engineering Contradiction:
Improveaccuracy of abnormality detectionVSAvoidtime to detect abnormality
Core Design Contradiction:
ReliabilityVSLoss of time

Solution Approach 1:

The threshold is made dynamic by adjusting it according to operating conditions (wind speed, temperature, humidity) rather than using a fixed threshold. This allows the system to maintain high reliability across varying conditions while detecting abnormalities promptly when they occur.

Inventive Principle:
Principle #15Dynamics

Solution Approach 2:

The threshold parameters are changed based on environmental conditions and operating states. By modifying the threshold according to measured parameters like temperature and wind speed, the system achieves both early detection and reduced false positives.

Inventive Principle:
Principle #35Parameter changes

2Ease of operation

If a fixed threshold is used for monitoring, then the monitoring system is simple to operate, but it cannot accurately detect abnormalities under varying operating conditions

Engineering Contradiction:
Improvesimplicity of monitoring systemVSAvoidaccuracy of abnormality detection
Core Design Contradiction:
Ease of operationVSMeasurement precision

Solution Approach 1:

The monitoring system automatically adjusts its own threshold based on measured operating conditions without requiring manual intervention. This maintains ease of operation while improving detection accuracy through adaptive thresholding.

Inventive Principle:
Principle #25Self-service

Solution Approach 2:

The system uses feedback from environmental sensors and operating condition monitors to dynamically adjust the threshold. This closed-loop approach maintains simplicity while achieving accurate detection across varying conditions.

Inventive Principle:
Principle #23Feedback

3Ease of manufacture

If a uniform threshold is applied regardless of operating condition, then the monitoring criterion is consistent and easy to implement, but detection accuracy varies with environmental factors

Engineering Contradiction:
Improveease of implementing monitoring criterionVSAvoiddetection accuracy under different conditions
Core Design Contradiction:
Ease of manufactureVSReliability

Solution Approach 1:

The monitoring criterion changes parameters (threshold values) based on operating conditions while maintaining a consistent evaluation framework. This allows easy implementation through automated calculations while achieving reliable detection across diverse conditions.

Inventive Principle:
Principle #35Parameter changes

Data Source

PatentEP3696405B1Operating state evaluation method and operating state evaluation device
Publication Date: 2023.03.22 MITSUBISHI HEAVY IND LTD
  • EP3696405B1 patent drawingFigure 1
  • EP3696405B1 patent drawingFigure 2A~2B
  • EP3696405B1 patent drawingFigure 3

AI summary

An operating condition of a wind turbine facility or at least one wind turbine is acquired, and an estimated value of a measurable physical quantity corresponding to the operating condition is calculated. It is determined whether an abnormality is present in the wind turbine by comparing the estimated value and the actual value.