Evaluation of Supply Chain Logistics Capability Based on ANN

Supply chain management is receiving increasing importance among academics and practitioners. A key objective of supply chain management is to ensure smooth and efficient operations at the production side of the chain. Logistic capability is the most important content of supply chain management, so firms are utilizing it to effectively manage their supply chain through a variety of activities. Decision-makers need to assess and compare alternative logistic solutions accounting not just for their direct costs and benefits but, most importantly, for their impact on production performance. For instance, the management of transportation logistics, involves difficult trade-offs among capacity utilization, transportation costs, and production variability often leading to the identification of multiple logistic solutions. The objective of the work described in this paper is to introduce a technique for logistics capability evaluation. Firstly an index system is constructed, which includes three aspects interpreted by thirteen indices. Secondly, a BP artificial neural network (ANN) is illustrated for the evaluation process. The network has three layers: the input layer has 13 neurons; the second layer, hidden layer, has 26 neurons; and only 1 neuron in the output layer. Then based on a survey of 80 beverage companies in China and the network constructed, an evaluation process is carried out, and the results are compared to the outcomes of fuzzy comprehensive evaluation process. Primary research proves that the two methods match very well.