Robot manipulator drive fault diagnostics using data-driven and analytical modelling

Belt-driven mechatronic systems are popular for a range of applications. A modified robotic manipulator was adapted to allow different belt-drive faults to be incorporated into the mechanism, with additional sensors to characterize the compromised kinematics. Different data-driven models were used studied to detect anomalies in motor power consumption and end-effector motion; and a physics-based, lumped-parameter dynamic model was used to identify different faults. Comparative assessment metrics were sdused to compare the performance of different fault models from sets of laboratory test data.