An artificial neural network methodology for damage detection: Demonstration on an operating wind turbine blade

Artur Movsessian, David Garcia Cava, Dmitri Tcherniak

Research output: Contribution to journalArticlepeer-review

Abstract

This study presents a novel artificial neural network (ANN) based methodology within avibration-based structural health monitoring framework for robust damage detection.The ANN-based methodology establishes the nonlinear relationships between selecteddamage sensitive features (DSF) influenced by environmental and operational variabilities(EOVs) and their corresponding novelty indices computed by the Mahalanobis distance(MD). The ANN regression model is trained and validated based on a reference state (i.e.,a healthy structure). The trained model is used to predict the corresponding MD of newobservations. The prediction error between the calculated and predicted MD is used as anew novelty index for damage detection. Firstly, an artificial 2D feature set is generatedto illustrate how the limitations of solely using the MD-based novelty index can beovercome by the proposed ANN-based methodology. Secondly, the methodology is imple-mented in data obtained from an in-operation wind turbine with different artificiallyinduced damage scenarios in one of its blades. Finally, the performance of the proposedmethodology is evaluated by the metrics of accuracy, F1-score and Matthews correlationcoefficient. The results demonstrate the advantages of the proposed methodology byimproving damage detectability in all the different damage scenarios despite the influenceof EOVs in both the simulated and real data
Original languageEnglish
Article number107766
JournalMechanical System and Signal Processing
Volume159
Early online date19 Mar 2021
DOIs
Publication statusE-pub ahead of print - 19 Mar 2021

Keywords

  • Artificial Neural Networks
  • Damage detection
  • Novelty index
  • Mahalanobis distance
  • Environmental and operational variabilities

Fingerprint Dive into the research topics of 'An artificial neural network methodology for damage detection: Demonstration on an operating wind turbine blade'. Together they form a unique fingerprint.

Cite this