Development of Expert System for Grinding Operations

本研究报告提出了磨削专家系统的体系结构和基本策略。提出了一种基于模糊集理论的有效的知识库机制。该系统能够处理模糊和不确定的知识，并提出了一种与各种磨削知识库数据集成的方案。知识库建立了这三个部分，以便从功能上处理各种知识。所开发的系统在KBMS和工程工作站(Apollo DN4000)上运行1.基于框架和产生式规则的混合模型被用来表示特定领域的知识，如经验和直觉。并采用了缺省理论和基于模糊集理论的模糊逻辑来利用模糊磨削知识。开发的系统由界面、推理机、磨削知识库、实际磨削操作数据库、磨削故障知识库管理系统和若干临时框架组成。确定磨削条件所需的程序被分成模块，这些模块累积到磨削知识库中。磨削数据用于计算磨削实际运行数据库中存储的实验方程的系数因子。

This research report has presented an architecture and basic strategy for grinding expert system. We have suggested an effective mechanism for knowledge-base based on fuzzy set theory. This system can handle vague and uncertain knowledge, and presents a scheme for integrating data with various kindsof grinding knowledge knowledge-base. The knowledge-base establishes the three parts so as to functionally cope with various knowledge. The developed system performed in using the KBMS and engineering work station (Apollo DN4000).1. The hybrid model based on frames and production rules is utilized to represent domain specific knowledge such as experiences and intuitions. Also, a default theory and fuzzy logic based on fuzzy set theory are adopted to utilize the vague grinding knowledge.2. The developed system is composed of inter face, inference engine, grinding knowledge-base, actual grinding operation database, grinding trouble knowledge-base management system, and several temporary frames.3. The procedures which are necessary to determine the grinding conditions are separated into modules which are accumulated to the grinding knowledge-base. The grinding data are used to calculate coefficient factors of experimental equations stored in the grinding actual operation database.