Analyses of Online Monitoring Signals for a GMAW Process Before and After Improvement

Abstract

The ability to detect the onset of welding instability is a very powerful tool in welding process monitoring and control. Toward this goal, this study investigates a gas metal arc welding (GMAW) process by analyzing online monitoring signals. Two separate data sets are obtained from the process, which correspond to (a) a stable process after improvement and (b) a relatively unstable process which tends to exhibit spatter and poor weld bead geometry. Voltage, current, wire-feeding speed and line speed signals for both data sets are analysed and features are extracted from the raw signals using different signal processing techniques. Specifically, phase diagrams, signal distributions, Fast Fourier transform (FFT) and Wavelet Transform methodologies are implemented. The process parameters differ for the data corresponding to the stable and unstable processes rendering the two data sets incomparable. As such, an overlapping region of parameters is selected and this data is used to develop a multi-layer neural network model. The model uses the features extracted to distinguish between the two data sets under the similar input conditions. The trained model is then used to classify data as being from a stable process or an unstable process. Finally, an ant colony optimization algorithm is used to select the optimal subset of features for the classification model. For this task, fuzzy k-nearest neighbor algorithm is used as the classifier instead due to the computational simplicity. The results indicate that more than one single feature is able to yield 100% classification accuracy alone. A way to rank those features is discussed. Moreover, the effect of window size is also investigated.