Deep Learning CNN-LSTM Approach for Identifying Welder’s Hand Motion Gestures Using Wearable Sensors

Abstract A welder plays a crucial role in the construction of a new ship. Monitoring the performance of welders involved in the construction of a ship is particularly important for controlling dimensions. he competency and consistency of welders play a vital role, with specific hand movement patterns contributing to welding quality. This study aims to identify individual welders’ hand movement patterns using Deep Learning with CNN-LSTM configurations. Data was collected through IMU motion sensors attached to welders’ wrists, capturing acceleration, angular speed, magnetic force, and electric current changes. The data was classified using CNN-LSTM, which showed higher accuracy than SVM methods. Experimental results indicated an overall classification accuracy of 99.73% for identifying individual welders and 97.07% for determining welding positions.