In flexible production environments, challenges such as fluctuating customer demands and machine performance degradation significantly complicate production scheduling. This study introduces a neuro-evolution of augmenting topologies (NEAT) algorithm aimed at optimizing the scheduling efficiency in flexible job shops by minimizing both maximum completion and average lag times, taking into account variables like sporadic job arrivals, variable machining durations, tool wear, preventive maintenance, and equipment failures. The NEAT algorithm harnesses the features of dynamic flexible job shop scheduling problems (DFJSPs) to devise heuristic rules for job selection and machine allocation, synthesizing these rules into coherent scheduling strategies. Employing the entropy weight method, a fitness function for multiobjective optimization is formulated, facilitating the enhancement of the neural network’s structural and nodal parameters through genetic algorithms. Comparative analysis with four conventional scheduling rules indicates that the NEAT approach consistently surpasses traditional methods, especially in managing complex disturbances. For example, in a scenario involving 50 jobs and 20 machines, NEAT dramatically reduced the average completion time to 142.14 s, markedly outperforming the 644.36 s achieved by the minimum operation completion rate/shortest processing time (MOCR/SPT) approach. These findings underscore the superiority of NEAT in dynamic scheduling contexts.

Aiming at the impact of machine failure on scheduling schemes in actual production, this paper proposes a multi-fidelity optimization approach considering the preventive maintenance of the machine (MOAPMM). The genetic algorithm (GA) is used as a low-fidelity model to generate a number of feasible solutions; the feasible solutions are sorted, grouped, and selected as high-quality solutions according to the EOCBA method; the high-fidelity model considering machine preventive maintenance (PM) is constructed by using the FlexSim^@ software; and the high-quality solutions are simulated to obtain the optimal scheduling scheme. Experimental results show that our proposed method outperforms approaches that do not consider machine PM in terms of completion time for the flexible job shop scheduling problem with machine failure.