基于人工神经网络的冲裁件缺陷诊断专家系统

Artificial Neural Network Based Expert System for Diagnosing of Blanking Parts' Defects

说明了冲裁件成形缺陷分析人工神经网络专家系统的总体结构框架 .系统分为综合信息处理模块和缺陷分析推理模块两大部分 ,有针对性地综合提取了冲裁件缺陷信息加以分类 ,采用了双3层 BP神经网络来分析和处理输入参数 ,并对系统知识表示、知识获取、知识库的构造及推理机策略的选用进行了深入的阐述 .同时还对根据系统原理编写的 BDAES(v1 .0 )

The paper showed the function frame of artificial neural network based expert system for the analysis of blanking parts' defects. Including the integrated information processing module and defect analysis reasoning module, the system pertinently selects important information on the defects of blanking parts, makes use of two three-layer BP neural networks to analyze and treat with the input parameters. It demonstrates the knowledge representation, knowledge acquisition, knowledge database structure and the selection of reasoning mechanism. The article also introduced the BDAES (v1.0) which was established according to the mechanism of the system.