Intelligent Energy Consumption Optimization in Flexible Job Shop Scheduling Considering Reliability-Centered Maintenance (RCM)

Abstract

Maintenance is a significant cost factor in supply chains and production systems. Intelligent maintenance systems are gaining global interest with the rise of IT-based technologies. This study focuses on a new reliability-centered maintenance (RCM) method, where an intelligent system decides on repair or replacement based on system reliability in the practical flexible job shop scheduling problem (FJSP). The research introduces a balance by integrating industrial units' green production and energy consumption with traditional objectives like production costs and system reliability in a multi-objective framework. Another key aspect is the consideration of less developed regions as a social factor in the energy calculation model, resembling the Ministry of Energy's computational models. The reliability model is tailored for a complex system with multiple machines having time-dependent lifespans and repair probabilities, where operation times, maintenance times, and post-repair reliability levels are all stochastic. Metaheuristic algorithms combined with simulation-based optimization are used to solve the model. Statistical and non-statistical methods are used to depict the performance of the algorithms. The study shows that these algorithms effectively solve complex multi-objective stochastic problems and can be considered as a decision support system (DSS) for software developers working on real-world applications.

Keywords

• maintenance system prediction
• rcm
• stochastic
• simulation-based optimization
• flexible jobshop
• metaheuristic algorithm