Decision-Making Optimization Model Construction Based on Intelligent Algorithms

Complex and multi-dimensional operational optimization problems have involved multiple fields and aim to achieve scientific decision-making for the optimal allocation of resources and maximum efficiency. Intelligent optimization algorithms provide potential solution strategies for this purpose. The implementation of operational optimization strategies is vital in the context of production decision-making, as they offer invaluable support in the pursuit of competitive advantages. This paper introduces a decision tree model as a means of addressing operational optimization problems in the production process. A decision tree model is introduced as a means of constructing a decision path, which can then be used to guide inspection or disassembly decisions, reduce costs, and improve efficiency. In the context of multi-stage production processes, a Markov decision process (MDP) model is employed for the purpose of optimizing decisions at each stage. The model results provide reference for the decision-making process and improve efficiency. When considering uncertainty, a Monte Carlo simulation is integrated with an MDP to assess the defect rate and optimize the inspection strategy. The findings indicate that the prioritized assembly and sales strategy is more effective and that inspection can be omitted when the defect rate is low. Furthermore, the developed intelligent decision-making framework has the potential to be extended to other optimization problem areas.