Wind Turbine Condition Monitoring via Vibration Spectrum Analysis

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Conventional methods for monitoring machine systems, such as wind turbines, face limitations in reliability, sensitivity, and informative value due to noisy vibration spectra, making it difficult to detect structural changes and maintenance needs in a timely manner.

Innovation Solution

A method and device that analyze time series of natural vibration spectra to determine deformation and noise parameters, allowing for reliable and sensitive evaluation of machine state by comparing measured spectra to reference spectra, using deformation and noise parameters to distinguish between structural changes and noise-induced fluctuations.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Measurement precision

If conventional methods are used to analyze vibration spectra, then the monitoring device complexity is reduced, but the measurement precision and reliability deteriorate due to noisy spectra

Engineering Contradiction:
Improvemeasurement precisionVSAvoiddevice complexity
Core Design Contradiction:
Measurement precisionVSDevice complexity

Solution Approach 1:

The vibration spectrum analysis is segmented into multiple frequency ranges, with each range processed independently through dedicated filtering and deformation detection algorithms. This segmentation allows targeted processing of specific frequency bands (e.g., tower bending, nacelle vibrations) to improve measurement precision without requiring the entire system to be overly complex.

Inventive Principle:
Principle #1Segmentation

Solution Approach 2:

Reference vibration spectra are pre-calculated and stored for comparison against measured spectra. The deformation detection algorithm uses these pre-prepared references to quickly identify changes in structural conditions, avoiding the need for complex real-time reference generation and improving measurement precision through efficient comparison.

Inventive Principle:
Principle #10Preliminary action

2Reliability

If conventional vibration analysis methods are used, then the ease of operation is maintained, but the reliability of damage detection deteriorates

Engineering Contradiction:
ImprovereliabilityVSAvoidease of operation
Core Design Contradiction:
ReliabilityVSEase of operation

Solution Approach 1:

The system continuously monitors vibration spectra and compares them against reference data, providing feedback on structural changes. The deformation parameter calculation incorporates feedback from multiple measurement cycles and environmental data, improving reliability through iterative refinement while maintaining ease of operation through automated decision-making.

Inventive Principle:
Principle #23Feedback

Solution Approach 2:

Environmental parameters (wind speed, temperature, humidity) serve as intermediaries that are incorporated into the deformation detection algorithm. These intermediaries help distinguish between vibrations caused by environmental factors and those indicating structural damage, improving reliability without requiring direct observation of all possible failure modes.

Inventive Principle:
Principle #24Intermediary (Mediator)

3Reliability

If short-term vibration measurements are used, then the ease of operation is maintained, but the ability to detect long-term changes deteriorates

Engineering Contradiction:
ImprovereliabilityVSAvoidtime
Core Design Contradiction:
ReliabilityVSLoss of time

Solution Approach 1:

The monitoring system operates continuously, accumulating vibration data over extended periods to detect long-term structural changes. The deformation parameter calculation integrates information from multiple time intervals, allowing the system to maintain reliability for long-term detection while the automated processing eliminates time loss associated with manual analysis.

Inventive Principle:
Principle #20Continuity of useful action

Solution Approach 2:

Reference spectra are pre-established from new or repaired structures, and the deformation detection algorithm is pre-configured with appropriate thresholds and comparison criteria. This preliminary preparation enables rapid and accurate detection of long-term changes without requiring time-consuming analysis procedures during actual monitoring.

Inventive Principle:
Principle #10Preliminary action

4Loss of information

If simple vibration spectra analysis is used, then the device complexity is reduced, but the informative value of the monitoring deteriorates

Engineering Contradiction:
Improveinformative valueVSAvoiddevice complexity
Core Design Contradiction:
Loss of informationVSDevice complexity

Solution Approach 1:

The vibration spectrum is segmented into multiple frequency ranges, with each range analyzed separately to extract specific structural information. This segmentation increases informative value by providing detailed breakdowns of different structural components (tower, nacelle, rotor) while the automated processing keeps device complexity manageable.

Inventive Principle:
Principle #1Segmentation

Solution Approach 2:

The analysis transitions from single-parameter vibration amplitude measurement to multi-dimensional assessment incorporating deformation parameters, noise parameters, and environmental factors. This dimensional expansion enriches the informative value by providing comprehensive structural health assessment while the systematic approach prevents uncontrolled complexity increase.

Inventive Principle:
Principle #17Another dimension (Dimensionality change)

Data Source

PatentEP4442997A1Method and device for monitoring the condition of a machine of a machine assembly, in particular of a wind turbine
Publication Date: 2024.10.09 BACHMANN GMBH
  • EP4442997A1 patent drawingFigure 1
  • EP4442997A1 patent drawingFigure 2
  • EP4442997A1 patent drawingFigure 3A~3C

AI summary

A method for monitoring the machine condition of a machine system, in particular a wind turbine, comprises the steps of providing a time series of measured natural frequency spectra of the machine system, acquiring a deformation parameter in at least one monitoring time interval, wherein the deformation parameter is characteristic of a deviation of the measured natural frequency spectra from a reference natural frequency spectrum of at least one reference machine system, acquiring a noise parameter for the at least one monitoring time interval, wherein the noise parameter is characteristic of noise in the measured natural frequency spectra, and determining the machine condition from the deformation parameter and the noise parameter. A monitoring device for monitoring the machine condition of a machine system, in particular a wind turbine, is also described.