A study on using scanning acoustic microscopy and neural network techniques to evaluate the quality of resistance spot welding

Abstract

This paper shows that the quality of resistance spot welds can be evaluated using scanning acoustic microscopy (SAM). Two-layered coated spot-welded samples are investigated utilising a wide-field short-pulse scanning acoustic microscope with operation frequencies of 25, 50 and 100 MHz. Geometrical parameters, e.g. nugget area, maximum axis of nugget, and minimum axis of nugget, are acquired from C-scan images of weld nuggets using mathematical morphology techniques. These parameters serve as inputs for an artificial neural network (ANN) model to evaluate the quality of spot welds. The output of the model during the training process comprises the results of nugget peeling tests and expert opinions. The ANN can provide suggestions on weld quality with a higher than 95% correctness. A JAVA computer program is developed for image processing, ANN training, and ANN testing. With this model, the computer program can render the quality of spot welds that are close to those achieved using off-line destructive method.

Analysis of Using Acoustic Microscopy to Evaluate Defects in Spot Welding Joints

“…In subsequent years, scanning acoustic microscopy has become a common method for non-destructive testing, and the use of the presentation of Band C-scan allowed for the identification of such discontinuities as voids and foreign inclusions [7]. Automatic evaluation and identification of discontinuities is made possible by the use of neural network algorithms [18].…”

Non-Destructive Inspection by Infrared Thermography of Resistance Spot Welds Used in Automotive Industry

“…For example, the Scanmaster company attempted to use a modern UT technique of Phased Array to detect defected spot welds with additional results compared to the conventional UT, namely the nugget diameter and nugget total area [9]. Lee et al [4] patented a scanning acoustic microscopy using an artificial neural network (ANN) model to evaluate the quality of spot welds [10]. Such application would, however, involve a significant upfront investment cost that might diminish the industrial practicality.…”

“…The detection of non-systematic defects is mediated by non-destructive methods, including, visual (VT) and ultrasonic (UT) methods. Nevertheless, both methods can provide only a limited feedback on an incorrect set-up of the welding process [4].…”

RBF-Neural Network Applied to the Quality Classification of Tempered 100Cr6 Steel Cams by the Multi-Frequency Nondestructive Eddy Current Testing

“…Artificial Neural Networks (ANNs) are processing tools inspired by the human nervous system, which can implement expert systems using their input-output mapping capability [13]. Various authors have combined ANNs and NDT techniques in the literature: Wang et al employed a back propagation ANN to monitor the stress and the temperature of steel using the Barkhausen noise theory [14]; Sathiyasekar et al proposed a system based on an ANN and fuzzy logic to predict the quality of the insulation system of rotating machines [15]; Silva et al designed methods based on Multi-Layer Perceptron ANNs (MLP-ANNs) and Support Vector Machines to detect the sigma phase in duplex stainless steels analyzing induced magnetic field signals [16]; Lee et al employed a backpropagation ANN to evaluate the quality of resistance spot welding using scanning acoustic microscopy [17]; Junyan et al designed a MLP-ANN to detect subsurface defects in different materials using thermography [18]; Pérez-Benítez et al proposed a feature selection algorithm to optimize a probabilistic ANN that classifies magnetic material samples using magnetic Barkhausen noise information [19]; Cao et al employed a Radial Basis Function ANN (RBF-ANN) to evaluate wire ropes with eddy current inspection [20]; Xu et al proposed a Kohonen ANN to predict the coating failure process cycles on steel plates using electrochemical impedance spectroscopy data [21]; Nunes et al employed ultrasound signals to classify Ni-based alloy samples with a MLP-ANN [22]; and Wrzuszczak et al combined the eddy current information with ANNs to detect cracks on conducting layers and on ferrous tubes [12].…”