Research on Production Decision-Making Based on Simulated Annealing Algorithm and Monte Carlo Model

This paper investigates production decision-making based on simulated annealing algorithm and cost-benefit model, using simulated annealing algorithm, Monte Carlo model, cost-benefit model, and sensitivity analysis and robustness analysis, aiming to reduce the production cost and improve the decision-making efficiency of enterprises by optimizing the production and inspection processes. This study focuses on the acquisition of minimum inspection sample size, optimization of inspection cost, cost-benefit decision analysis, step-by-step optimization of total cost and analysis of optimal decision path. Firstly, based on the assumption that the defective rate of spare parts obeys binomial distribution, a Monte Carlo model is constructed to optimize the sampling and testing scheme. Second, a cost-benefit model is constructed to evaluate the total cost of different decision combinations by considering various related costs and combining with decision tree analysis. Then, the simulated annealing algorithm is used to explore the global optimal solution to deal with the complex and large number of decision combinations. Finally, the impact of variable fluctuations on the model is investigated through sensitivity and robustness analyses. The series of studies in this paper can help to reduce the total cost of the enterprise, and improve the competitiveness and profit margin in the market.