基于实例的工艺知识获取模型

介绍了耦合神经网络的工艺设计实例推理系统的实现方法论，提出了一种基于神经网络的工艺设计实例推理索引模型．与现存大多数实例推理系统不同，该方法用神经网络实现实例的动态分类和索引．实例层次分类的三层结构和基于特征的聚类模板概念，为实现基于符号处理的实例推理求解模式向基于神经计算的模式识别求解模式映射提供了条件．提出了基于实例的工艺知识获取模型，采用新实例的入库操作实现工艺知识的隐式获取，从而使知识获取得以简化．神经网络的自适应、自学习能力将减少系统的日常维护工作．基于实例的系统可望解决知识获取的难题．

Case Based Knowledge Acquisition Model for Process Planning

This paper deals with a methodology of case based process planning system. A new approach to neural indexing models for case based process planning of turning parts is presented. Unlike most of the existing CBR systems, it makes use of neural network to realize the dymamic classification and index of the cases. Three levels for hierarchical classification of cases and a concept of feature based clustering template are presented so as to combine the case based reasoning based on symbol proccssing with the pattern recognition based on neural calculation. On the basis of neural indexing models, a case based knowledge acquisition model, which address the knowledge acquisition bottlenecks of rule based reasoning system, is presented. The adaptive and learning capabilities of neural networks are utilized successfully in the implementation of case based machine learning.