Experimental and Computational Materials Defects Investigation

Abstract

Production of railway axles (i.e., one of the basic material of the modern train) is an elaborate process unfree from faults and problems. Errors during the manufacturing or the plies' overlapping, in fact, can cause particular flaws in the resulting material, so compromising its same integrity. Within this framework, ultrasonic tests could be useful to characterize the presence of defect, depending on its dimensions. On the contrary, the requirement of a perfect state for used materials is unavoidable in order to assure both transport reliability and passenger safety. Therefore, a real-time approach able to recognize and classify the defect starting from the finite element simulated ultrasonic echoes could be very useful in industrial applications. The ill-posedness of the so defined process induces a regularization method. In this paper, a finite element and a heuristic approach are proposed. Particularly, the proposed method is based on the use of a Neural Network approach, the so called "learning by sample techniques", and on the use of Support Vector Machines in order to classify the kind of defect. Results assure good performances of the implemented approach, with very interesting applications.

Sub-Macroscopic Inclusion Classification in Bearing Steels Based on LFCN and Ultrasonic Testing

“…To comprehensively tackle this problem, various feature analysis techniques have been proposed. Buonsanti et al [30] utilized wavelet packet-principal component analysis (WP-PCA) for feature extraction of defect signals. Bernardi et al [31] applied principal component analysis (PCA) to characterize ultrasonic signals.…”

The detection and classification method of sub-macroscopic defects inside steel with an ultrasonic testing and CatBoost-based stacking model

“…Jian et al [29] first introduced lifting wavelet transform to extract defect signal features, and used the output as the input of the BPNN and RBF network for further classification. Buonsanti et al [30] utilized wavelet packet-principal component analysis (WP-PCA) for feature extraction of defect signals, and then verified the classification effectiveness of the support vector machine (SVM). Virupakshappa and Oruklu [31] combined fast Fourier transform with SVM to classify defect signals, and further proposed an advanced classification framework of discrete wavelet transform (DWT), SVM and artificial neural network (ANN) to optimize the experiment results [32].…”