Supply chain management is a sharp weapon for enterprises to bring huge profits which attracts the attention of decision-makers.However,it is very difficult for enterprise decision-makers to choose the suppliers that meet their own interests quickly and correctly when the number of suppliers rapidly increasing.The complex features of the supply chain network structure determine that the application intelligent optimization algorithm has a strong feasibility and reality for the management and decision of the supply chain network.Based on the analysis of the supply chain network topology,intelligent optimization algorithms and clustering method,some improved algorithms are proposed to solve different problems.The main contents are as follows:(1)Aiming at the problem that the density peak clustering algorithm is too dependent on truncation distance parameters,and the uncertainty and lack of objectivity of clustering results of data points among clusters caused by the over impact of results between data points,the density peak clustering algorithm based on artificial bee colony is proposed.(2)In view of the complex structure of the supply chain network,the large amount of data and the slow solving speed,an improved algorithm based on complex network theory and Bias classification can reduce the complexity of the supply chain network structure and speed up the speed of algorithm optimization greatly.(3)For the problem that the solution space is limited and the optimization speed is slow,artificial bee colony algorithm based on simulated annealing and gradient descent is proposed.The method of random walk of reconnaissance wasps was changed,and the search set of the algorithm was expanded.The reference of the naive Bayes probability speeds up the algorithm.In this paper,we break the limitations of artificial bee colony algorithms in different ways and use them into solving the problem of supply chain decision-making.The results show that the proposed method can effectively screen suppliers,and seek more effective supply chain optimization solutions for enterprise decision-makers. |