智能化系统的有机组合推理及优化  

Organically Combinatorial Inference and Optimization in Intelligence System

作　　者：伍奎[1] 谢永春[1] 李润方[1] 朱才朝[1] 秦大同[1] 

机构地区：[1]重庆大学机械传动国家重点实验室,重庆400044

出　　处：《重庆大学学报（自然科学版）》2003年第6期1-5,共5页Journal of Chongqing University

基　　金：国家"十五""八六三"计划资助项目 ( 2 0 0 1AA42 3 2 0 0 )

摘　　要：智能化系统中推理是其中的重要组成部分 ,推理算法决定了系统智能化水平的高低。针对智能化系统的推理 ,利用专家系统推理、模糊逻辑推理、神经网络推理的互补性 ,提出了由专家系统、模糊逻辑、神经网络有机结合构成的组合推理及优化的技术 ,充分发挥各个推理的优势和克服单一推理的不足。采用公用专家知识库供各个推理的有机组合和并行运行 ,利用优化算法优化各个推理结果 ,可实现知识的共享、推理算法的有机融合及组合推理的优化 ,同时解决组合推理的推理冲突并提高组合推理的效率。分析及应用结果表明 ,有机的组合推理与优化能有效地应用于工程实际 。The inference algorithm is the most important part in intelligence system because the level of intelligence in the system is decided by it. By means of the mutual benefit for inference algorithm of expert system ,fuzzy logic and neural network ,the combinatorial inference technology which is organically composed of these three parts is put forward for inference mechanism in intelligence system. The optimization decision model is also set up. In order to bring all the advantage of every inference algorithm into play and overcome the disadvantage of single inference algorithm the common expert knowledge base is applied to organic combination and concurrent operation of all inference algorithm. In order to realize knowledge share the inference results are optimized by decision technology optimization. The research results show that the organized combinatorial inference and optimization can be applied in engineering practice effectively and is benefit for raising the inference level.

关 键 词：智能化系统 专家系统 模糊逻辑 神经网络 组合推理 优化 

分 类 号：TP18[自动化与计算机技术—控制理论与控制工程] TP273[自动化与计算机技术—控制科学与工程]