Multi-Stage Product Control Decision-Making Based on Monte Carlo and Bayesian Methods

Product production control decision-making refers to the decision-making on the organization of the production process that is closely related to product production. Enterprises face a key challenge in optimizing spare parts, semi-finished products, and finished products in complex production situations involving multiple processes and components. Detecting problems while minimizing production and logistics losses is crucial. To address this, we adopt a multi-stage decision-making approach using dynamic programming optimization. Specifically, we apply sequential sampling, Monte Carlo, and Bayesian methods to infer and optimize various segments. Our decision-making method covers issues such as whether to inspect spare parts, inspect finished products, or dismantle unqualified finished products. Experimental data show that the model can simulate different combinations of inspection strategies, providing optimal decisions for multi-stage control of product quality.