Compatibility and challenges in machine learning approach for structural crack assessment

Abstract

Structural health monitoring and assessment (SHMA) is exceptionally essential for preserving and sustaining any mechanical structure’s service life. A successful assessment should provide reliable and resolute information to maintain the continuous performance of the structure. This information can effectively determine crack progression and its overall impact on the structural operation. However, the available sensing techniques and methods for performing SHMA generate raw measurements that require significant data processing before making any valuable predictions. Machine learning (ML) algorithms (supervised and unsupervised learning) have been extensively used for such data processing. These algorithms extract damage-sensitive features from the raw data to identify structural conditions and performance. As per the available published literature, the extraction of these features has been quite random and used by academic researchers without a suitability justification. In this paper, a comprehensive literature review is performed to emphasise the influence of damage-sensitive features on ML algorithms. The selection and suitability of these features are critically reviewed while processing raw data obtained from different materials (metals, composites and polymers). It has been found that an accurate crack prediction is only possible if the selection of damage-sensitive features and ML algorithms is performed based on available raw data and structure material type. This paper also highlights the current challenges and limitations during the mentioned sections.

Acoustic emission signal filtering based on artificial intelligence

“…The target/outputs for the dataset are either unknown or known in unsupervised and supervised algorithms, respectively. Density estimation is typically an unsupervised problem, whereas classification and regression are supervised approaches [13]. Logistic regression, Decision tree, Support vector machine (SVM), and K-nearest neighbour (KNN) methods are used in this study for this purpose.…”

Suitability Analysis of Machine Learning Algorithms for Crack Growth Prediction Based on Dynamic Response Data

“…Some scholars such as [ 24 ] have examined the performance of different SVM kernels, and their results confirmed that Gaussian RBF and polynomial were the best choices for damage detection using acoustic signals. On the other hand, [ 25 ] observed that Gaussian RBF and hyperbolic tangent were the best for genome-wide prediction. Less popular kernels might achieve better findings compared to the more common kernels.…”

“…Deep learning techniques can often achieve a high accuracy but may require a larger amount of data and more computational resources. At this point, advanced learning strategies (e.g., Bayesian optimization) and feature extraction approaches (e.g., PCA) can be applied to reduce the time needed for training and testing machine learning algorithms [ 16 , 25 , 26 , 47 ]. The use of two- or three-layer deep neural networks (DNNs) for fatigue crack growth rate prediction could potentially be effective, depending on the complexity of the problem and the amount of data available.…”

Study of cyclic crack‐tip opening displacement of microstructurally small fatigue crack using digital image correlation

“…With increasing computational capabilities, sophisticated multiscale modeling frameworks 18 and data‐driven machine learning approaches 19 have been used to study the complex phenomena behind the propagation of small cracks. Still, the data‐driven approaches face several challenges due to the limited availability of high‐quality experimental data 20 . Consequently, microstructurally small fatigue crack growth and crack interactions with the microstructure is still an open topic due to the complex three‐dimensional nature of the problem and the experimental challenges of observing the phenomena at such a small scale 21 …”

“…Still, the data-driven approaches face several challenges due to the limited availability of high-quality experimental data. 20 Consequently, microstructurally small fatigue crack growth and crack interactions with the microstructure is still an open topic due to the complex threedimensional nature of the problem and the experimental challenges of observing the phenomena at such a small scale. 21 The behavior of microstructurally small cracks is often investigated with a focus on the crack driving force.…”