Research on Production Optimization Based on Simulated Annealing Algorithm and Bayesian Sampling Optimization Model

Simulated annealing algorithm is an optimization algorithm in the field of machine learning that is good at processing high-dimensional complex data and seeking global optimal solutions. In this research, the simulated annealing algorithm is combined with mixed integer linear programming and applied to the production decision optimization scenario. Firstly, the normal distribution and hypothesis testing method and the Bayesian sampling optimization model are used to formulate the corresponding sample sampling scheme. This method provides the most comprehensive possible picture of the yield of a complete batch of parts, semi-finished products, or products with the minimum number of samples and the smallest batch size. Secondly, this paper takes the profit maximization of the enterprise as the objective function to model the production inspection and compensation process of the enterprise and uses the simulated annealing algorithm to solve the corresponding optimal production decision scheme. In general, this research not only expands the application scope of simulated annealing algorithm, but also provides a feasible optimization method and reference for similar multi-objective production decision-making problems.