Multivariate data-driven modelling and pattern recognition for damage detection and identification for acoustic emission and acousto-ultrasonics

Torres-Arredondo, Miguel Angel; Burgos, Diego Alexander Tibaduiza; McGugan, Malcolm; Toftegaard, Helmuth Langmaack; Borum, Kaj Kvisgaard; Mujica, Luis Eduardo; Rodellar, José; Fritzen, Claus‐Peter

doi:10.1088/0964-1726/22/10/105023

Cited by 23 publications

(13 citation statements)

References 41 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…This network is built with several piezoelectric transducers which are attached to the structure under test in a permanent way and distributed over its surface as in Figures 9 and 13. Because these transducers can work as actuators or as sensors, each actuation phase is defined by a PZT working as an actuator and using the rest of PZTs as sensors, this procedure is repeated for each PZT in the sensor network [42]. This means that an excitation signal is applied to a piezoelectric sensor and propagated signals through the structure are collected by the rest of sensors, organized and preprocessed.…”

Section: Damage Classification Methodologymentioning

confidence: 99%

A Damage Classification Approach for Structural Health Monitoring Using Machine Learning

et al. 2018

View full text Add to dashboard Cite

Inspection strategies with guided wave-based approaches give to structural health monitoring (SHM) applications several advantages, among them, the possibility of the use of real data from the structure which enables continuous monitoring and online damage identification. These kinds of inspection strategies are based on the fact that these waves can propagate over relatively long distances and are able to interact sensitively with and uniquely with different types of defects. The principal goal for SHM is oriented to the development of efficient methodologies to process these data and provide results associated with the different levels of the damage identification process. As a contribution, this work presents a damage detection and classification methodology which includes the use of data collected from a structure under different structural states by means of a piezoelectric sensor network taking advantage of the use of guided waves, hierarchical nonlinear principal component analysis (h-NLPCA), and machine learning. The methodology is evaluated and tested in two structures: (i) a carbon fibre reinforced polymer (CFRP) sandwich structure with some damages on the multilayered composite sandwich structure and (ii) a CFRP composite plate. Damages in the structures were intentionally produced to simulate different damage mechanisms, that is, delamination and cracking of the skin.

show abstract

Section: Damage Classification Methodologymentioning

confidence: 99%

A Damage Classification Approach for Structural Health Monitoring Using Machine Learning

et al. 2018

View full text Add to dashboard Cite

show abstract

“…The family of Daubechies wavelet basis function “db8” was carefully chosen for this study because it proved to be adequate to encode and approximate the ultrasonic waveforms. This selection is accomplished by means of performing different trial and error tests by evaluating different mother wavelets and levels of decomposition so that the signal could be properly reconstructed from the calculated wavelet coefficients . The chosen wavelet is an orthogonal wavelet with the advantage of avoiding phase shifts and allowing exact reconstruction of the signal what makes this wavelet appropriate for analysing transient signals …”

Section: Proposed Methodologymentioning

confidence: 99%

An acousto-ultrasonics approach for probabilistic modelling and inference based on Gaussian processes

Torres-Arredondo

Burgos

2018

Struct Control Health Monit

View full text Add to dashboard Cite

Summary In recent years, there has been an increasing interest in employing and analysing complex ultrasonic waves for the purpose of designing health monitoring systems for guaranteeing the safe structural operation by means of early damage prognosis strategies and reducing the costs of maintenance and downtimes. For this reason, monitoring systems are essential and require highly efficient techniques providing a probabilistic interpretation of their diagnostics. On that account, a Bayesian framework within the context of Gaussian processes is adopted in the present work for the purpose of probabilistic data‐driven modelling and damage detection. A network of permanently installed piezoelectric sensors in a pitch‐catch configuration is used for collecting the propagated ultrasonic waves together with the discrete wavelet transform for feature extraction purposes and matrix unfolding procedures such as the ones used in the monitoring of batch processes for sensor data fusion. The effectiveness of the proposed methodology is experimentally evaluated in three different composite structures. Receiver operating characteristics are used as a statistical measure to assess the damage detection capabilities of the presented method.

show abstract

“…Figure 6 includes a representation of the steps that are needed between the data acquisition and the machine training. These steps include a data normalization as in Section 2.1.2 [ 42 , 43 ] and principal component analysis (PCA). In this case, we consider the projection onto the first two principal components (scores) as the input to train the machine.…”

Section: Damage Classification Methodologymentioning

confidence: 99%

Distributed Piezoelectric Sensor System for Damage Identification in Structures Subjected to Temperature Changes

Vitola

Pozo

Burgos

et al. 2017

Sensors

View full text Add to dashboard Cite

Structural health monitoring (SHM) is a very important area in a wide spectrum of fields and engineering applications. With an SHM system, it is possible to reduce the number of non-necessary inspection tasks, the associated risk and the maintenance cost in a wide range of structures during their lifetime. One of the problems in the detection and classification of damage are the constant changes in the operational and environmental conditions. Small changes of these conditions can be considered by the SHM system as damage even though the structure is healthy. Several applications for monitoring of structures have been developed and reported in the literature, and some of them include temperature compensation techniques. In real applications, however, digital processing technologies have proven their value by: (i) offering a very interesting way to acquire information from the structures under test; (ii) applying methodologies to provide a robust analysis; and (iii) performing a damage identification with a practical useful accuracy. This work shows the implementation of an SHM system based on the use of piezoelectric (PZT) sensors for inspecting a structure subjected to temperature changes. The methodology includes the use of multivariate analysis, sensor data fusion and machine learning approaches. The methodology is tested and evaluated with aluminum and composite structures that are subjected to temperature variations. Results show that damage can be detected and classified in all of the cases in spite of the temperature changes.

show abstract

Multivariate data-driven modelling and pattern recognition for damage detection and identification for acoustic emission and acousto-ultrasonics

Cited by 23 publications

References 41 publications

A Damage Classification Approach for Structural Health Monitoring Using Machine Learning

A Damage Classification Approach for Structural Health Monitoring Using Machine Learning

An acousto-ultrasonics approach for probabilistic modelling and inference based on Gaussian processes

Distributed Piezoelectric Sensor System for Damage Identification in Structures Subjected to Temperature Changes

Contact Info

Product

Resources

About