| Summary: | In the manufacturing industry, robots are constantly operated at high speed, which degrades their performance by the degradation of internal components, eventually reaching failure. To address this issue, a framework for system-level fault diagnosis is proposed, which consists of extracting useful features from the motor control signal acquired during the operation, diagnosing the current health of each component using the features, and estimating the associated degradation in the robot system’s performance. Finally, a maintenance strategy is determined by evaluating how well the system performance is restored by the replacement of each component. The framework is demonstrated using the example of a wafer transfer robot in the semiconductor industry, in which the robot is operated under faults with various severities for two critical components: the harmonic drive and the timing belt. Features are extracted for the motor signal using wavelet packet decomposition, followed by feature selection by considering the trendability and separability of the fault severity. An artificial neural network model and Gaussian process regression are employed for the diagnosis of the components’ health and the system’s performance, respectively.
|
|---|