A human modelling and monitoring approach to support the execution of manufacturing operations


Human workers have a vital role in manufacturing given their adaptability to varying environmental conditions, their capability of judgment and understanding of the context. Nevertheless, the increasing complexity and variety of manufacturing operations ask for the exploitation of digital technologies to support human workers and/or facilitate their interaction with automation equipment. The proposed approach uses artificial intelligence for image processing to identify the actions of the workers and exploits the knowledge related to the processes through hidden-Markov models to identify possible errors, deviations from the planned execution or dangerous situations. An application case is provided for assembly operations to assess the viability of the proposed approach in realistic conditions. © 2019

CIRP Annals