An Evaluation Model of Supply Chain Performances Using 5DBSC and LMBP Neural Network Algorithm
An Evaluation Model of Supply Chain Performances Using 5DBSC and LMBP Neural Network Algorithm作者机构：School of Biological and Agricultural Engineering Jilin University Changchun 130022 P. R. China Logistics Department College of Quartermaster Technology Jilin University Changchun 130062 P. R. China Key Laboratory of Bionic Engineering (Ministry of Education China) Jilin University Changchun 130022 P. R. China School of Computing and Technology the University of Gloucestershire Cheltenham GL50 2RH UK
出 版 物：《Journal of Bionic Engineering》 (仿生工程学报（英文版）)
年 卷 期：2013年第10卷第3期
页 面：383-395页
核心收录：
学科分类：12[管理学] 1201[管理学-管理科学与工程(可授管理学、工学学位)] 081104[工学-模式识别与智能系统] 08[工学] 0835[工学-软件工程] 0811[工学-控制科学与工程] 0812[工学-计算机科学与技术（可授工学、理学学位）]
主 题：supply chain performance evaluation 5DBSC bionics LMBP neural network
摘 要：A high efficient Supply Chain （SC） would bring great benefits to an enterprise such as integrated resources, reduced logistics costs, improved logistics efficiency and high quality of overall level of services. So it is important to research various methods, performance indicator systems and technology for evaluating, monitoring, predicting and optimizing the performance of a SC. In this paper, the existing performance indicator systems and methods are discussed and evaluated. Various nature-inspired algorithms are reviewed and their applications for SC Performance Evaluation （PE） are discussed. Then, a model is proposed and developed using 5 Dimensional Balanced Scorecard （5DBSC） and LMBP （Levenberg-Marquardt Back Propagation） neural network for SC PE. A program is written using Matlab tool box to implement the model based on the practical values of the 14 indicators of 5DBSC of a given previous period. This model can be used to evaluate, predict and optimize the performance of a SC. The analysis results of a case study of a company show that the proposed model is valid, reliable and effective. The convergence speed is faster than that in the previous work.
维普期刊数据库