Multistage Inventory Hybrid Intelligent Optimization Under Grey Fuzzy Uncertainty

The customer demand and replenishment lead-time can be considered as grey fuzzy variables combining grey and fuzzy twofold uncertain factors. The multistage inventory model under periodical review policy was presented based on the chance measure of grey fuzzy variable. The inventory would be replenished to certain level when the inventory level drops to the re-order point. The optimal re-order point and the inventory replenishment level of every stage can be obtained by minimizing the multistage inventory cost. The grey fuzzy simulation technology can generate input-output data for the uncertain functions. The neural network trained from the input-output data can approximate the uncertain functions. The particle swarm optimization (PSO) algorithm was improved with the differential evolution algorithm. The improved PSO algorithm was combined with neural network to optimize the inventory model. A numerical example was given to illustrate the feasibility of the model and algorithm