对于复杂多变的生产调度问题，各种优化算法单独使用时均存在一定的局限性，

For complex and changeable production scheduling problems, various optimization algorithms have certain limitations when used alone. For example, genetic algorithms have poor local search capabilities and are prone to premature phenomena; ant colony algorithm evolutionary convergence is slow and easy to fall into local optimality Or stagnation occurs [14]. Compared with other optimization algorithms, the particle swarm optimization (PSO) algorithm has the advantages of simple structure, fast convergence, easy adjustment of parameters, and easy combination with other algorithms. The local search can be adjusted by introducing the simulated annealing strategy to effectively avoid the algorithm from getting stuck. Local optimization provides an effective means for improving the real-time and intelligence of multi-objective flexible job shop scheduling. Yuan [15] et al. combined simulated annealing, particle swarm optimization and genetic algorithm to solve the problem of maximizing cost-benefit, and verified the effectiveness of the method through examples; Mishra A [16] et al. particle swarm optimization based on simulated annealing To solve the comprehensive cost minimization problem consisting of processing inventory carrying cost and penalty cost in the scheduling process, for medium and large-scale problems, this method has more obvious advantages than traditional optimization algorithms.

For complex and changeable production scheduling problems, various optimization algorithms have certain limitations when used alone. For example, genetic algorithm has poor local search ability and is prone to premature phenomenon; The evolutionary convergence speed of ant colony algorithm is slow, easy to fall into local optimization or stagnation [14]. Compared with other optimization algorithms, particle swarm optimization (PSO) algorithm has the advantages of simple structure, fast convergence speed, easy parameter adjustment and easy combination with other algorithms. Simulated annealing strategy can be introduced to adjust the local search, effectively avoid the algorithm falling into local optimization, and provide an effective means to improve the real-time and intelligence of multi-objective flexible job shop scheduling. Yuan [15] et al. Solved the cost-benefit maximization problem by combining simulated annealing, particle swarm optimization and genetic algorithm, and verified the effectiveness of this method through an example; Mishra a [16] et al. Solved the comprehensive cost minimization problem composed of processing inventory carrying cost and penalty cost in the scheduling process based on simulated annealing particle swarm optimization. For medium and large-scale problems, this method has more obvious advantages than the traditional optimization algorithm.<br>

For complex and changeable production scheduling problems, all kinds of optimization algorithms have certain limitations when used alone. For example, genetic algorithms have poor local search ability and are prone to premature phenomenon. Ant colony algorithm is slow in evolutionary convergence, easy to fall into local optimum or appear stagnation phenomenon [14]. Compared with other optimization algorithms, Particle Swarm Optimization (PSO) algorithm has the advantages of simple structure, fast convergence, easy adjustment of parameters and easy combination with other algorithms, etc. It can adjust local search by introducing simulated annealing strategy, effectively avoiding the algorithm from falling into local optimum, and provides an effective means to improve the real-time and intelligence of multi-objective flexible job shop scheduling. Yuan[15] et al. solved the cost-benefit maximization problem by combining simulated annealing, particle swarm optimization and genetic algorithm, and verified the effectiveness of this method through an example. Mishra A [16] et al. solved the comprehensive cost minimization problem consisting of processing inventory bearing cost and penalty cost in the scheduling process based on simulated annealing particle swarm optimization. For medium and large-scale problems, this method has more obvious advantages than the traditional optimization algorithm.