(searched for: doi:10.22362/ijcert/2016/v3/i9/48869)
Published: 5 October 2022
Journal: IEEE Access
IEEE Access, Volume 10, pp 113619-113630; https://doi.org/10.1109/access.2022.3212410
In automobile manufacturing, the quality assessment of resistance spot welding (RSW) plays a decisive role in the quality and safety of products. Recently, it has become very popular to use machine learning to evaluate the quality of welding nuggets. However, there are two obstacles: data imbalance caused by limited defective samples, and data shortage due to expensive time and labor costs. This paper proposes a novel method. On one hand, the self-paced ensemble (SPE) algorithm for binary classification is improved to handle imbalanced multi-class classification of quality levels. On the other hand, an instance-based ensemble transfer learning approach is proposed to predict the tensile-shear strength of RSW for precise control of the weld quality. In detail, a quality level identification model is formulated with the process and material parameters as the input at first. Secondly, an explainable algorithm SHapley Additive exPlanations (SHAP) was introduced to anatomize the impacts of welding parameters on the welding quality predictions. Finally, a hybrid dataset including actual historic production data and 454 spot-welding cases is constructed, and then the eXtreme Gradient Boosting (XGBoost) is introduced as the base learner of TrAdaBoost.R2 to train the prediction model. Compared with conventional methods, the SPE provides the greatest macro geometric-mean score of 0.923, and the proposed regression model yields superior accuracy R 2 of 0.952, which shows the potential of assisting welding process design.
Computers in Industry, Volume 124; https://doi.org/10.1016/j.compind.2020.103345
The publisher has not yet granted permission to display this abstract.
Published: 14 December 2018
Iop Conference Series: Earth and Environmental Science, Volume 195; https://doi.org/10.1088/1755-1315/195/1/012071
Welding quality of a product is very important. Resistance Spot Welding (RSW) is a process widely used in the industrial, mostly in the automotive industry. RSW is used to joint two or more materials in order to form the structure of the car. Resistance spot welding requires parameters that play as an important role in the welding process. There are three important parameters in the welding process, namely welding current (kA), welding time (cycle), and electrode force (kN). All three parameters should be optimized in order to produce high quality spot weld joints and less welding defects. In relation to Green Manufacturing, less defects means less waste and less consumption of materials. In the present study, we utilized RSM (Response Surface Method) to optimize the parameters by using statistical and mathematical techniques to analyze the problem. Optimal result parameters on welding current 8.7 kA, welding time 19,25 cycle, and electrode force 1,6 kN with diameter nugget 6,969 mm.