Multi-level predictive maintenance of smart manufacturing systems driven by digital twin: A matheuristics approach

Digital twin technology is gradually being applied to smart manufacturing systems and is providing valuable information for predictive maintenance of swarms of machines, but also raises the need for more accurate and real-time decision making. However, there is still a shortage of research in this area. This paper proposes a general multi-level predictive maintenance decision-making framework driven by digital twin, considering component dependencies, the variable time scale of decisions, and comprehensive maintenance resources, in which an optimal maintenance schedule can be obtained in real time and then fed back to the physical space, so as to realize closed-loop control. A maintenance decision-making optimization model is then formulated based on integer linear programming to minimize total maintenance costs while meeting required production capacity. Further, a novel matheuristics algorithm (i.e., the interoperation of metaheuristics and mathematical programming techniques) is introduced for various maintenance decision scenarios. Finally, a case study of an offshore oil and gas production system consisting of eight subsea Christmas trees is examined, and the effects of changes in production capacity, failure thresholds, and maintenance resources on the multi-level optimization of decision-making solutions are discussed.

Automated summary

Digital twin technology is applied to smart manufacturing systems to provide valuable information for predictive maintenance, but there is a lack of research in this area. This paper proposes a predictive maintenance decision-making framework driven by digital twin, considering component dependencies and comprehensive maintenance resources. An optimal maintenance schedule can be obtained in real time, and an integer linear programming model is formulated to minimize maintenance costs while meeting production capacity. A matheuristics algorithm is introduced for various maintenance decision scenarios, and a case study is conducted on an offshore oil and gas production system.