Structural damage detection in wind turbine blades based on time series representations of dynamic responses

2015 ◽  
Author(s):  
Simon Hoell ◽  
Piotr Omenzetter
Keyword(s):  
Time Series ◽  
Damage Detection ◽  
Wind Turbine ◽  
Structural Damage ◽  
Turbine Blades ◽  
Dynamic Responses ◽  
Structural Damage Detection ◽  
Wind Turbine Blades ◽  
Series Representations

Radar-based structural health monitoring of wind turbine blades: The case of damage detection

2017 ◽  
Vol 17 (4) ◽  
pp. 815-822 ◽  
Author(s):  
Jochen Moll ◽  
Philip Arnold ◽  
Moritz Mälzer ◽  
Viktor Krozer ◽  
Dimitry Pozdniakov ◽  
...  
Keyword(s):  
Structural Health Monitoring ◽  
Damage Detection ◽  
Wind Turbine ◽  
Health Monitoring ◽  
Turbine Blades ◽  
Heterogeneous Material ◽  
Material System ◽  
Wind Turbine Blades ◽  
Millimetre Wave ◽  
Structural Health

Structural health monitoring of wind turbine blades is challenging due to its large dimensions, as well as the complex and heterogeneous material system. In this article, we will introduce a radically new structural health monitoring approach that uses permanently installed radar sensors in the microwave and millimetre-wave frequency range for remote and in-service inspection of wind turbine blades. The radar sensor is placed at the tower of the wind turbine and irradiates the electromagnetic waves in the direction of the rotating blades. Experimental results for damage detection of complex structures will be presented in a laboratory environment for the case of a 10-mm-thick glass-fibre-reinforced plastic plate, as well as a real blade-tip sample.

Experimental Verification of the Statistical Time-Series Methods for Diagnosing Wind Turbine Blades Damage

2018 ◽  
Vol 19 (01) ◽  
pp. 1940008 ◽  
Author(s):  
Hesheng Tang ◽  
Suqi Ling ◽  
Chunfeng Wan ◽  
Songtao Xue
Keyword(s):  
Time Series ◽  
Wind Turbine ◽  
Experimental Verification ◽  
Turbine Blades ◽  
Ar Model ◽  
Wind Turbine Blades ◽  
Statistical Decision ◽  
Vibration Data ◽  
The Status ◽  
Statistical Time

This paper presents an experimental verification of the statistical time-series methods, which utilize adapted frequency response ratio (FRR), autoregressive (AR) model parameter and AR model residual as performance characteristics, for diagnosing the damage of wind turbine blades. Specifically, the statistical decision-making techniques are used to identify the status patterns from turbine vibration data. For experiments, a small-size, laboratory-used operating wind turbine structure is used. The performance of each method in diagnosing damages simulated by saw cut in three critical positions in the blade are assessed and compared. The experimental results show that these methods yielded a promising damage diagnosis capability in the condition monitoring of wind turbine.

Wind Turbine Blade Damage Detection Using Various Machine Learning Algorithms

2016 ◽  
Author(s):  
Taylor Regan ◽  
Rukiye Canturk ◽  
Elizabeth Slavkovsky ◽  
Christopher Niezrecki ◽  
Murat Inalpolat
Keyword(s):  
Machine Learning ◽  
Damage Detection ◽  
Wind Turbine ◽  
Health Monitoring ◽  
Turbine Blades ◽  
Machine Learning Algorithms ◽  
Support Vector ◽  
Test Rig ◽  
Wind Turbine Blades ◽  
Baseline Characteristics

Wind turbine blades undergo high operational loads, experience variable environmental conditions, and are susceptible to failures due to defects, fatigue, and weather induced damage. These large-scale composite structures are essentially enclosed acoustic cavities and currently have limited, if any, structural health monitoring in practice. A novel acoustics-based structural sensing and health monitoring technique is developed, requiring efficient algorithms for operational damage detection of cavity structures. This paper describes a systematic approach used in the identification of a competent machine learning algorithm as well as a set of statistical features for acoustics-based damage detection of enclosed cavities, such as wind turbine blades. Logistic regression (LR) and support vector machine (SVM) methods are identified and used with optimal feature selection for decision making using binary classification. A laboratory-scale wind turbine with hollow composite blades was built for damage detection studies. This test rig allows for testing of stationary or rotating blades (each fit with an internally located speaker and microphone), of which time and frequency domain information can be collected to establish baseline characteristics. The test rig can then be used to observe any deviations from the baseline characteristics. An external microphone attached to the tower will also be utilized to monitor blade damage while blades are internally ensonified by wireless speakers. An initial test campaign with healthy and damaged blade specimens is carried out to arrive at certain conclusions on the detectability and feature extraction capabilities required for damage detection.

scholarly journals Interpretable machine learning in damage detection using Shapley Additive Explanations

2021 ◽  
Author(s):  
Artur Movsessian ◽  
David Garcia Cava ◽  
Dmitri Tcherniak
Keyword(s):  
Machine Learning ◽  
Damage Detection ◽  
Wind Turbine ◽  
Prediction Models ◽  
Turbine Blades ◽  
Wind Turbine Blades ◽  
Lumped Mass ◽  
Damage Indices ◽  
Wide Range ◽  
The Difference

In recent years, Machine Learning (ML) techniques have gained popularity in Structural Health Monitoring (SHM). These have been particularly used for damage detection in a wide range of engineering applications such as wind turbine blades. The outcomes of previous research studies in this area have demonstrated the capabilities of ML for robust damage detection. However, the primary challenge facing ML in SHM is the lack of interpretability of the prediction models hindering the broader implementation of these techniques. For this purpose, this study integrates the novel Shapley Additive exPlanations (SHAP) method into a ML-based damage detection process as a tool for introducing interpretability and, thus, build evidence for reliable decision-making in SHM applications. The SHAP method is based on coalitional game theory and adds global and local interpretability to ML-based models by computing the marginal contribution of each feature. The contribution is used to understand the nature of damage indices (DIs). The applicability of the SHAP method is first demonstrated on a simple lumped mass-spring-damper system with simulated temperature variabilities. Later, the SHAP method has been evaluated on data from an in-operation V27 wind turbine with artificially introduced damage in one of its blades. The results show the relationship between the environmental and operational variabilities (EOVs) and their direct influence on the damage indices. This ultimately helps to understand the difference between false positives caused by EOVs and true positives resulting from damage in the structure.

Structural damage detection using transmissibility together with hierarchical clustering analysis and similarity measure

2016 ◽  
Vol 16 (6) ◽  
pp. 711-731 ◽  
Author(s):  
Yun-Lai Zhou ◽  
Nuno M.M. Maia ◽  
Rui P.C. Sampaio ◽  
Magd Abdel Wahab
Keyword(s):  
Damage Detection ◽  
Hierarchical Clustering ◽  
Similarity Measure ◽  
Clustering Analysis ◽  
Structural Damage ◽  
Real Life ◽  
Dynamic Responses ◽  
Hierarchical Clustering Analysis ◽  
Structural Damage Detection ◽  
Structural Dynamic

Maintenance and repairing in actual engineering for long-term used structures, such as pipelines and bridges, make structural damage detection indispensable, as an unanticipated damage may give rise to a disaster, leading to huge economic loss. A new approach for detecting structural damage using transmissibility together with hierarchical clustering and similarity analysis is proposed in this study. Transmissibility is derived from the structural dynamic responses characterizing the structural state. First, for damage detection analysis, hierarchical clustering analysis is adopted to discriminate the damaged scenarios from an unsupervised perspective, taking transmissibility as feature for discriminating damaged patterns from undamaged ones. This is unlike directly predicting the structural damage from the indicators manifestation, as sometimes this can be vague due to the small difference between damaged scenarios and the intact baseline. For comparison reasons, cosine similarity measure and distance measure are also adopted to draw out sensitive indicators, and correspondingly, these indicators will manifest in recognizing damaged patterns from the intact baseline. Finally, for verification purposes, simulated results on a 10-floor structure and experimental tests on a free-free beam are undertaken to check the suitability of the raised approach. The results of both studies are indicative of a good performance in detecting damage that might suggest potential application in actual engineering real life.

scholarly journals Interpretable Machine Learning in Damage Detection Using Shapley Additive Explanations

2021 ◽  
Author(s):  
Artur Movsessian ◽  
David Garcia Cava ◽  
Dmitri Tcherniak
Keyword(s):  
Machine Learning ◽  
Damage Detection ◽  
Wind Turbine ◽  
Prediction Models ◽  
Turbine Blades ◽  
Wind Turbine Blades ◽  
Lumped Mass ◽  
Damage Indices ◽  
Wide Range ◽  
The Difference

Abstract In recent years, Machine Learning (ML) techniques have gained popularity in Structural Health Monitoring (SHM). These have been particularly used for damage detection in a wide range of engineering applications such as wind turbine blades. The outcomes of previous research studies in this area have demonstrated the capabilities of ML for robust damage detection. However, the primary challenge facing ML in SHM is the lack of interpretability of the prediction models hindering the broader implementation of these techniques. For this purpose, this study integrates the novel Shapley Additive exPlanations (SHAP) method into a ML-based damage detection process as a tool for introducing interpretability and, thus, build evidence for reliable decision-making in SHM applications. The SHAP method is based on coalitional game theory and adds global and local interpretability to ML-based models by computing the marginal contribution of each feature. The contribution is used to understand the nature of damage indices (DIs). The applicability of the SHAP method is first demonstrated on a simple lumped mass-spring-damper system with simulated temperature variabilities. Later, the SHAP method has been evaluated on data from an in-operation V27 wind turbine with artificially introduced damage in one of its blades. The results show the relationship between the environmental and operational variabilities (EOVs) and their direct influence on the damage indices. This ultimately helps to understand the difference between false positives caused by EOVs and true positives resulting from damage in the structure.

Sign in / Sign up

Export Citation Format

Share Document