Production Decision Optimization Based on Monte Carlo Simulation and Genetic Algorithm

Abstract

This study proposes an optimization method based on Monte Carlo simulation and genetic algorithm to explore the production decision-making scheme for assembly products. The study aims to provide efficient production decision support for enterprises by constructing a sequential decision model, an evaluation class model and a multi-stage decision model. In this paper, the sequential decision model and likelihood ratio method are first applied to design a scheme to minimize the number of sampling inspections, and the Monte Carlo simulation algorithm is used to simulate the quality of assemblies and finished products under different inspection schemes, which leads to the corresponding decision scheme. Then, the multi-objective decision-making model is solved using genetic algorithm to maximize the average profit as the goal to explore the economic benefits of different decision-making schemes. The research in this paper provides a reliable theoretical basis and practical guidance for sampling inspection, inspection scheme design and optimization decision-making in production decision-makingt.