分布式专家系统中覆盖综合案例集的神经网络综合求解策略  

Neural Network Strategies for Solving Synthesis Problems in Partial Overlap Synthesis Cases in Distributed Expert Systems

作　　者：唐智勇[1] 韦东鹏 顾雁宏[2] 

机构地区：[1]军械工程学院研究生队,石家庄050003 [2]军械工程学院网管中心,石家庄050003

出　　处：《计算机工程与应用》2000年第2期43-45,共3页Computer Engineering and Applications

摘　　要：解决分布式专家系统（ＤＥＳｓ）中信念冲突的传统方法是基于数学分析的综合策略。讨论了采用神经网络进行信念冲突的解决和问题综合求解。对非冲突案例集特别是部分覆盖综合案例集（Ｐａｒｔｉａｌ Ｏｖｅｒｌａｐ Ｓｙｎｔｈｅｓｉｓ Ｃａｓｅ）的综合策略进行了较详细的研究。Traditional methods of solving belief conflicts in DESs are synthesis strategies based on mathematical analysis,which the proposer of the strategy must know the detail relationships between the inputs and the outputs. To avoiding the above problems,the synthesis solving of the belief conflict problem based on neural network is addressed.it focuses on the synthesis solving of the Partial Overlap Synthesis Cases

关 键 词：分布式专家系统 综合求解策略 POSC 神经网络 

分 类 号：TP18[自动化与计算机技术—控制理论与控制工程]