一种基于知识和耦合神经网络实例混合推理的智能CAPP策略研究

Research on A Hybrid Reasoning Strategy for An Intelligent Capp System Based on Knowledge and Cases Coupled with Neural Network

提出一种新的耦合神经网络的实例与知识混合推理策略。采用面向对象的方法表达实例和知识 ,并将神经网络用于实例推理中 ,在此基础上实现了 CAPP的变异设计。建立了基于零件及其工艺数据知识的分层分解表达模式与层次式优化推理机制 ,从而实现了 CAPP的创成式设计。给出智能化 CAPP系统的总体结构 ,对基于神经网络的实例相似性判定算法、知识表示模型和知识推理控制策略作了讨论。由于吸收了派生法的类比设计思想 ,又具有创成功能 ,整个

A new hybrid reasoning strategy based on case and knowledge integrated with neural network is proposed in this paper.With the object-oriented representation of case and knowledge,variant process planning CAPP based on case-based reasoning integrated with neural network is realized.Meanwhile,generative process planning CAPP based on hierarchical knowledge classification and successive reasoning is achieved.After the general structure of the CAPP system is presented,several key techniques such as decision algorithm based on neural network for case resemblance,knowledge representation and inference mechanism of process design in knowledge-based reasoning are discussed in detail.This system possesses higher efficiency and better quality for its analogic designing ideals and creative functions.