Abstract
Maintenance planning in Industry 4.0 gains benefits from symbolic AI for knowledge representation learning from heterogeneous data. Traditionally simulation models are utilized that are not flexible to cope with dynamic changes and to react to ad-hoc events. This paper presents a novel competence-based maintenance planning (CBMP) methodology using a knowledge graph conjoined with linear programming and a genetic algorithm. Aligned with production planning goals, CMBP allows optimizing human resource planning through integrating competence factors in shift scheduling and task allocation. The use case study in semiconductor manufacturing has resulted in a reduced Mean Time To Repair of 18%.
Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
