Online monitoring of weld cross-sectional shape using optical emission spectroscopy and neural network during laser dissimilar welding

Laser dissimilar welding (LDW) has received substantial interest in manufacturing due to its advantages in enhancing product performance. However, offline quality monitoring remains prevalent in LDW manufacturing, resulting in high costs and extended production times. In this study, a novel deep neural network (DNN) model was developed to predict the cross-sectional shape of the weld in online, allowing for an intuitive assessment of the welding state during aluminum/copper (Al/Cu) LDW. The weld shape prediction (WSP) training model utilized three parallel DNNs. In each DNN, the mean squared error of the output was determined via forward propagation, and the weights and biases between DNN layers were adjusted through backpropagation of the error. The resilient backpropagation algorithm was selected as the optimization method for training. Optical signals collected by optical emission spectroscopy were used as DNN input. Principal component analysis (PCA), major emission line (MEL), and line intensity ratio (LIR) methods were used to preprocess input data. Representative weld cross-sectional images, obtained via singular value decomposition, served as DNN output for model training. For PCA and MEL, the WSP model using input data with Cu information (89.5% for PCA and 88.3% for MEL) showed higher average prediction accuracy (PA) compared to the case using input data without Cu information (81.2% for PCA and 82.6% for MEL) because Cu emission lines better reflected LDW-associated physical phenomena. The highest average PA (89.8%) was achieved using input data preprocessed by the LIR method. These results demonstrate the applicability of the proposed WSP to online LDW process monitoring with high accuracy and robustness.