Online evaluation of resistance spot welding quality and defect classification

Abstract

Resistance Spot Welding (RSW) is widely used in industrial product manufacturing, and weld quality is critical to ensuring the safety and reliability of mechanical structures. In order to improve the product quality, online monitoring of weld quality has become a priority. Therefore, a method based on online evaluation of mild steel RSW quality and automatic defect classification is proposed. First of all, the optimal welding parameters for DC01 mild steel RSW are determined, and the welding parameters are slightly adjusted, resulting in expulsion and incomplete fusion. By acquiring welding data in real time, a new dynamic resistance signal filtering method is used to extract features in the time domain from dynamic resistance signals, and then analyze the performance of the extracted features in the classifier. A new method that can accurately classify the quality of welding spots is established to improve the classification accuracy of normal and expulsion welding spots. The classification performance test results of the new method show that the online quality evaluation results are extremely consistent with the actual situation. This research can reliably evaluate the quality of DC01 the spots online and automatically classify the welding defects of RSW.

Quality Assurance in Resistance Spot Welding: State of Practice, State of the Art, and Prospects

“…On the other hand, for [56,61], as the monitoring setup includes pressure sensors, the feasibility may be limited to stationary applications, but this depends on the design of the welding machine. The majority of the available studies for expulsion's online assessment [81][82][83][84] based their success on the classification of features extracted from the dynamic signals of the current, voltage, and pressure. Finally, another aspect that makes online expulsion assurance a real thing is the available studies concerning cases that involve different materials and welding infrastructure.…”

Resistance spot welding defect detection based on vectorized dynamic resistance signal and LightGBM classifier

“…Research has found that certain signals released in the welding process are strongly correlated with the formation and development of nugget, such as electrode displacement signal, electrode pressure signal, acoustic emission signal, and dynamic resistance signal [16][17][18][19][20]. Zhang et al [21] divided the welding process into three stages, explained the relationship between dynamic resistance and welding quality, and held that welding quality is related to the extreme value of dynamic resistance.…”