Nondestructive test (NDT) technology is required in the gas metal arc (GMA) welding process to secure weld robustness and to monitor the welding quality in real-time. In this study, a laser vision sensor (LVS) is designed and fabricated, and an image processing algorithm is developed and implemented to extract precise laser lines on tested welds. A camera calibration method based on a gyro sensor is used to cope with the complex motion of the welding robot. Data are obtained based on GMA welding experiments at various welding conditions for the estimation of quality prediction models. Deep neural network (DNN) models are developed based on external bead shapes and welding conditions to predict the internal bead shapes and the tensile strengths of welded joints.

An efficient nondestructive testing method of resistance spot weld quality is essential in evaluating the weld quality of all welded joints in the automotive components of a car body production line. This study proposes a quality prediction algorithm for resistance spot welding that can predict the geometrical and physical properties of a spot-welded joint and evaluate weld quality based on quality acceptance criteria. To this end, four statistical models that predict the main geometrical and physical properties of a spot-welded joint, including tensile shear strength, indentation depth, expulsion occurrence, and failure mode, were estimated based on material information, dynamic resistance, and electrode displacement signals. The significance of the estimated models was then verified through an analysis of variance. The prediction accuracies of the models were 94.3%, 93.4%, 97.5%, and 85.0% for the tensile shear strength, indentation depth, expulsion occurrence, and failure modes, respectively. A weld quality evaluation methodology that can predict the properties of a spot-welded joint and evaluate the overall quality requirements based on authorized welding standards was proposed using the four statistical models.

In this study, the effect of weld bead shape on the fatigue strength of lap fillet joints using the gas metal arc welding (GMAW) process was investigated. The base material used in the experiment was 590 MPa grade galvanealed steel sheet with 2.3 mm and 2.6 mm thickness. In order to make the four types of weld beads with different shapes by factors such as length, angle, and area, the welding process, wire feeding speed, and joint shape were changed. The stress-number of cycles to failure (S–N) curve and fatigue strength were obtained from the fatigue test for four types of weld bead, and the cause of the fatigue strength difference was clarified through the analysis of the geometrical factors, such as length, angle, and area of the weld bead. In addition, the relationship between weld bead shape and fatigue strength was discussed.

The quality of the resistance spot weld is predicted qualitatively using information from the weld’s external apparent image. The predicting tool used for weld qualities was a convolution neural network (CNN) algorithm with excellent performance in pattern recognition. A heat trace image of the weld surface was used as information on the external apparent image of welds. The materials used in the experiment were advanced high strength steel (AHSS) with 980 MPa strength, and uncoated cold-rolled (CR) steel sheets and galvannealed (GA) steel sheets were used. The quantitatively predicted weld quality information contained tensile shear strength, nugget diameter, fracture mode of welds, and expulsion occurrence. The predicted performance of the verification step of the model determined through the learning process was as follows; the predicted error rate for tensile shear strength and nugget diameter were 2.2% and 2.6%, respectively. And the predicted accuracy on fracture mode and expulsion occurrence was 100%.

For the automation of a laser beam welding (LBW) process, the weld quality must be monitored without destructive testing, and the quality must be assessed. A deep neural network (DNN)-based quality assessment method in spectrometry-based LBW is presented in this study. A spectrometer with a response range of 225–975 nm is designed and fabricated to measure and analyze the light reflected from the welding area in the LBW process. The weld quality is classified through welding experiments, and the spectral data are thus analyzed using the spectrometer, according to the welding conditions and weld quality classes. The measured data are converted to RGB (red, green, blue) values to obtain standardized and simplified spectral data. The weld quality prediction model is designed based on DNN, and the DNN model is trained using the experimental data. It is seen that the developed model has a weld-quality prediction accuracy of approximately 90%.

Weld defects such as blowholes and surface pores occur due to zinc vaporization during the gas metal arc welding of lap fillet joints of Zn-coated steel. In this study, the effect of porosity on fatigue behavior was investigated. A Zn-coated steel sheet with the strength of 590 MPa and a thickness of 2.3 mm was used as the base material. Three kinds of specimens with weld pore defects, such as blowholes and surface pores, were prepared and the tensile shear strength, hardness and fatigue behavior were investigated. The pore defects in the welds reduced the tensile shear strength. In the fatigue test, at higher load stresses between 122 and 366 MPa, pore defects reduced the fatigue life of the weld. However, the pore defects in the welds did not significantly affect the fatigue life of the welds at stresses below 92 MPa.