Journal of Systems Engineering and Electronics ›› 2011, Vol. 33 ›› Issue (7): 1575-1579.doi: 10.3969/j.issn.1001-506X.2011.07.27

• 系统工程 • 上一篇    下一篇

基于模糊神经网络的复杂产品研发决策评估

吴延勋1,2, 秦现生1, 张海峰1,3   

  1. 1. 西北工业大学机电工程学院, 陕西 西安 710072; 
    2. 北京仿真中心, 北京 100854;
    3. 北京航天情报与信息研究所, 北京 100854
  • 出版日期:2011-07-19 发布日期:2010-01-03

Development decision evaluation method of complex product based on fuzzy neural network

WU Yan-xun1,2, QIN Xian-sheng1, ZHANG Hai-feng1,3   

  1. 1. School of Mechanical Engineering, Northwestern Polytechnical University, Xi’an 710072, China; 
    2. Beijing Simulation Center, Beijing 100854, China; 
    3. Beijing Institute of Aerospace Information, Beijing 100854, China
  • Online:2011-07-19 Published:2010-01-03

摘要:

针对复杂产品研发决策评估系统的多维性、时变性特点,参照经典系统辨识的多输入、多输出模型结构原理,提出一种适用于复杂产品研发决策过程支持系统模型化、数字化、自动化、规范化而又具有实时性的多个并行时变模糊神经网络组合算法系统。通过对300组某系统研发过程实际获取与研讨结果数据组的应用实验证明,此种模型结构与算法切实可行,便于计算机实现。

Abstract:

A computerhardware/softwaresupported algorithm system based on multidimensional timevarying parallel/serial BP neural network is proposed, which is designed for simulating the analysis/research process of economics and industrial products so as to realize modelized, digitalized, automatized and standardized intelligent process.The algorithm system is tested by using 300 data groups from application experiments. The experimental results show that the proposed algorithm is feasilble and is easy to perform in computers.