Abstract
Manufacturing companies are improving shop floor tasks, especially related to assembly, thanks to the installation of collaborative robots, shortly cobots. Despite their reliability, they experience intrinsic difficulties in extending the CBM (condition-based maintenance) solutions from traditional machinery. The inherent challenges are due to the cobot flexibility, on-the-job training from operator, and internal control for trajectory optimization in cobot operations. Therefore, this research work tackles the issue of developing CBM by leveraging on the human-machine collaborative setting, proposing a human-in-the-loop (HIL)-based framework. The framework is demonstrated via a laboratory-scale application through induced functional failures. The demonstration shows that, via entropy-controlled prompting, the operator can provide feedback about CBM algorithms’ prediction accuracy. Based on the current outcomes, a roadmap for further improving the HIL-based solution for cobot maintenance is proposed, with the end purpose of promoting complete monitoring of all the equipment on the companies’ shop floor fostering the smart manufacturing paradigm.