Digitalized evaluation of welder performance in GTAW using hand motion sensor

Abstract

The purpose of this study is to use the data from the Myo hand motion sensor to evaluate the welder performance in Gas Tungsten Arc Welding (GTAW) process. The weld quality produces in this welding process critically depends on how well a welder can maintain the torch evenly to create a good weld bead. It found a direct correlation between hand motion and weld bead appearance. In this research, the Euclidean Norm was used to combine the three axes of accelerometer and gyroscope. The three-axis signals of the accelerometer and the gyroscope were combined respectively, and a relationship was found. It differentiated the normal and abnormal cup-walking pattern of hand motion that is commonly used in a welding process. Moreover, the Continuous Wavelet Transform (CWT) was applied for evaluating the stability of cup-walking motion. The result showed that the expert welder performs cup-walking performance more consistently than the intermediate and beginner welder. By using the quantitative method, the data of accelerometer, gyroscope, and voltage have been transferred to create a scoring system with the multivariable. The results show that it could differentiate between beginner, intermediate, and expert welder.