Lamb wave based damage detection in metallic plates using multi-headed 1-dimensional convolutional neural network

Abstract

Lamb wave based damage diagnosis holds potential for real-time structural health monitoring; however, analysing the Lamb wave response possess challenge due to its complex physics. Data-driven machine learning (ML) algorithms are often more effective in identifying the damage-related features from these complex responses. However, in analysing such complex responses the ML algorithms requires extensive data pre-processing and are often not suitable for real-time damage detection. This paper presents a deep learning multi-headed 1-dimensional convolutional neural network (1D-CNN) architecture capable to operate directly on raw discrete time-domain Lamb wave signals recorded from a thin metallic plate. The multi-headed configuration consisting of two parallel 1D-CNN layers is capable to learn higher order damage-related features and enhances robustness of overall classification performance. To train the adopted 1D-CNN algorithm a diverse database is also constructed consisting 216 numerically and 24 experimentally generated responses of a thin 1.6 mm Al-5052 plate structure. The diversification of training database is achieved by varying parameters like scanning length, scanning frequency and adding different levels of white noises to the captured responses. Later, the trained 1D-CNN architecture is tested against two separated unseen test-databases. The first test database consist of experimentally generated 12 samples with notch-like damage and 12 samples of pristine condition. The proposed 1D-CNN classifier generalizes well on the unseen samples and decisively predicts the outcome for 23 out of 24 samples of first test database. The second test database consists of 108 unseen FE simulated samples capturing additional damage scenarios. In the second test phase, the model has correctly predicted the condition of all the 108 samples.

Wave based damage detection in solid structures using spatially asymmetric encoder–decoder network

“…The model achieves a high accuracy for single and multiple damage, and is robust to noise. Rai and Mitra proposed a multi-headed 1D-CNN architecture for damage detection based on raw discrete time-domain Lamb wave signals recorded from a thin metallic plate 23 . Both simulated data and experimentally generated data are used to train and evaluate the model.…”

Fatigue Crack Evaluation with the Guided Wave–Convolutional Neural Network Ensemble and Differential Wavelet Spectrogram

“…For example, Xu et al [ 28 ] organized GW damage indexes from different excitation–sensing paths as a one-dimensional vector, which was input into a convolutional neural network (CNN) for classifying fatigue crack levels in a lug structure. Rai et al [ 29 ] and Mariani et al [ 30 ] directly adopted the one-dimensional GW signal as the CNN input to localize and evaluate the notched damage in the plate structure. Lim et al [ 31 ] repeated the same GW signal as a matrix, in which the CNN is used for monitoring the stress in a strip structure.…”

A Damage Detection Method Using Neural Network Optimized by Multiple Particle Collision Algorithm

“…The most important task of the SHM strategy is the damage identification procedure that can be classified into four levels: detection, location, quantification, and prediction [9]. SHM systems perform structural inspection in real time using embedded sensors [10]. A usual sensor and actuator option is piezoelectric (PZT) transducers [11][12][13][14][15].…”

“…Deep learning is a subbranch of machine learning, and it has the capability to deal with a large dataset [20,33]. Recent studies have proposed the 1-dimensional convolutional neural network (1D-CNN) for structural damage detection and localization [8,10,13,20]. The main advantage of 1D-CNN is automatic feature extraction performed through its initial convolutional layers [10,13,34].…”

“…Recent studies have proposed the 1-dimensional convolutional neural network (1D-CNN) for structural damage detection and localization [8,10,13,20]. The main advantage of 1D-CNN is automatic feature extraction performed through its initial convolutional layers [10,13,34]. However, CNN has a high computational cost, and its architecture design is a difficult task [35].…”