Research on production decision optimization based on Monte Carlo algorithm

Abstract

In the context of optimizing enterprise production processes, this paper focuses on the design of sampling inspection schemes and decision-making models that enhance cost control, production efficiency, and product quality. A sequential sampling method is employed to minimize the number of inspections while maintaining high confidence in rejecting defective batches. Monte Carlo simulation is utilized to generate random datasets of varying defect rates, which are used to compare the performance of sequential sampling against traditional single sampling methods. The results demonstrate that sequential sampling significantly reduces the number of inspections required, providing a more efficient approach. In addition, this study develops a multi-objective 0-1 programming model to analyze and optimize production decisions at various stages, aiming to maximize economic profit while considering secondary objectives such as process optimization. The model is implemented using Python to calculate total costs, revenues, and profits for 16 different decision scenarios. Furthermore, the model is applied to decision-making in the assembly of components, semi-finished products, and final products, taking into account defect rates and associated costs. By integrating these methods, the study provides a comprehensive approach to improving production decision-making processes. The proposed models can be widely applied to various industries, including manufacturing, supply chain management, and quality control, enabling enterprises to make data-driven, economically optimized decisions that enhance overall production performance.