Abstract

Purpose - The purpose of this study is to develop a robotic training system for the hand movements during manual welding. The system provides real-time notice-feedback with sound or light alarms, whenever the welding hand vibrates beyond the nominal level observed with professional welders. Design/methodology/approach - The large variations of hand movements are detected by monitoring the deviation of the tool position from a smooth curve estimated in real time by a Kalman filter. An alarm is generated in the form of a flashing light or beep sound whenever the deviations exceed a predetermined threshold. The performance of hand movements is measured in terms of the variations of the position data. Twelve novice and five professional welders took part in the experiments and answered a questionnaire that assessed the usability and work load of the system. Findings - Compared to the sound alarms, the light alarms resulted in a larger and statistically significant decrease in the variation of hand movements of the novice welders and brought the level of variation close to that of the professional welders. The alarms did not result in a significant decrease in the variation of hand movements of the professional welders. The responses to the questionnaire indicated that both professional and novice welders found the system useful and they did not experience any significant work load. Social implications - The system developed in this study can ease the training of novice welders, by speeding up the learning and reducing the need for human tutors. Originality/value - This study is first to provide real-time notice-feedback for training while manual welding, based on a comparison of the performances of novice and professional welders.

Details

Actions