TY - JOUR

T1 - Evaluation of machine learning techniques for structural health monitoring using ultrasonic guided waves under varying temperature conditions

AU - Abbassi, Abderrahim

AU - Römgens, Niklas

AU - Tritschel, Franz Ferdinand

AU - Penner, Nikolai

AU - Rolfes, Raimund

N1 - Funding Information: The authors would like to thank the Federal Ministry for Economic Affairs and Climate Action of the Federal Republic of Germany (BMWi) for funding, the project “SONYA - Increasing the reliability of segmented rotor blades through hybrid condition monitoring” (FKZ 03EE3026B), and the project partners as well as the team of the project Open Guided Waves for providing a free and open access to the data set.

PY - 2023/3

Y1 - 2023/3

N2 - The implementation of machine learning methods for structural health monitoring applications has proven to be very powerful, especially in detecting damage and compensating for environmental and operational conditions. The use of guided waves in this area has also shown to be a powerful tool due to their sensitivity to structural changes in the propagation medium. In this work, two strategies for detecting damage and distinguishing their positions and for dealing with temperature variations without an additional classical temperature compensation technique are investigated. For this purpose, four unsupervised dimensionality reduction learning methods were used and compared: Principal Component Analysis, Kernel Principal Component Analysis, t-distributed stochastic neighbour embedding and Autoencoder. The first strategy (score plot) consists of using the latent dimensions directly to distinguish the data points of different states of the structure, and the second (DI plot) proposes a method to use Q- and T2-statistics, which have been proposed in previous work for PCA, computed using the compressed representation of the monitoring data. To this end, monitoring data from intact and damaged states of a 500x500x2 mm plate of carbon-fibre–reinforced polymer recorded by 12 piezoelectric transducers at different temperatures are examined. As a reversible damage model, a 10 mm thick aluminium disc is placed at four different locations on the plate. The results primarily show the success of the methods used with DI plot in detecting damage regardless of varying temperature. The autoencoder in the first strategy also demonstrates promising performance in detecting and distinguishing the position of the damage, even in the presence of varying temperature conditions.

AB - The implementation of machine learning methods for structural health monitoring applications has proven to be very powerful, especially in detecting damage and compensating for environmental and operational conditions. The use of guided waves in this area has also shown to be a powerful tool due to their sensitivity to structural changes in the propagation medium. In this work, two strategies for detecting damage and distinguishing their positions and for dealing with temperature variations without an additional classical temperature compensation technique are investigated. For this purpose, four unsupervised dimensionality reduction learning methods were used and compared: Principal Component Analysis, Kernel Principal Component Analysis, t-distributed stochastic neighbour embedding and Autoencoder. The first strategy (score plot) consists of using the latent dimensions directly to distinguish the data points of different states of the structure, and the second (DI plot) proposes a method to use Q- and T2-statistics, which have been proposed in previous work for PCA, computed using the compressed representation of the monitoring data. To this end, monitoring data from intact and damaged states of a 500x500x2 mm plate of carbon-fibre–reinforced polymer recorded by 12 piezoelectric transducers at different temperatures are examined. As a reversible damage model, a 10 mm thick aluminium disc is placed at four different locations on the plate. The results primarily show the success of the methods used with DI plot in detecting damage regardless of varying temperature. The autoencoder in the first strategy also demonstrates promising performance in detecting and distinguishing the position of the damage, even in the presence of varying temperature conditions.

KW - autoencoder

KW - damage detection

KW - damage identification

KW - kernel principal component analysis

KW - machine learning

KW - principal component analysis

KW - structural health monitoring

KW - t-distributed stochastic neighbour embedding

KW - ultrasonic guided waves

KW - varying temperature conditions

UR - http://www.scopus.com/inward/record.url?scp=85132125394&partnerID=8YFLogxK

U2 - 10.1177/14759217221107566

DO - 10.1177/14759217221107566

M3 - Article

VL - 22

SP - 1308

EP - 1325

JO - Structural health monitoring

JF - Structural health monitoring

SN - 1475-9217

IS - 2

ER -