Analysis of Gas Metal Arc Welding Process Using Improved Complete Ensemble Empirical Mode Decomposition with Adaptive Noise

Abstract

The gas metal arc welding (GMAW) process, prevalent in construction and fabrication sectors, traditionally relies on postproduction evaluations, which are both costly and time-consuming. This study proposes a more efficient, real-time monitoring approach utilizing high-speed data acquisition and analysis systems to record and scrutinize voltage and current fluctuations during welding. Various decomposition techniques, including EMD (empirical mode decomposition), EEMD (ensemble empirical mode decomposition with noise), CEEMDAN (complete ensemble empirical mode decomposition with adaptive noise), and ICEEMDAN (improved complete ensemble empirical mode decomposition with adaptive noise), were analyzed to assess arc variations and thereby evaluate GMAW process quality. The research identified an optimal technique for analyzing non-stationary welding signals, further applied to real-time signals using decomposition and time–frequency representation (TFR) techniques. Findings indicate that key GMAW parameters, such as metal transfer mode and penetration depth, correlate significantly with the intrinsic mode functions (IMFs) and TFRs of decomposed signals. The study suggests that the introduced techniques can effectively analyze the influence of different shielding gases and arc currents on the GMAW process, presenting a promising method for real-time GMAW process monitoring.