基于特征和知识的车身点焊智能CAPP方法研究

建立了车身零部件面向装配的特征模型,提出了装配过程中“特征演化”的概念,以简化零部件特征的定义;研究了点焊工艺知识结构,包括知识的总体结构、工艺事实和工艺条件表达,并面向知识匹配过程对知识结构进行了优化;分析了基于零部件特征和工艺知识的推理技术,包括规则匹配的算法、冲突消解的策略和产生式推理方法,采用线性模型和神经网络模型对工艺方法与工艺条件之间的映射关系进行了模拟。模拟结果表明,采用提出的方法能取得与实际相符的效果。

A Feature and Knowledge Based Intelligent CAPP Method for Auto-body Spot-welding

An assembly-oriented feature model of auto-body parts was established,and the concept of "feature evolvement" was proposed to simplify the feature defining process.Then,the architecture of the spot-welding knowledge,i.e.the framework of the knowledge and the expression of the process facts and conditions,was researched.The architecture was optimized for the rule matching process.Finally,a feature and knowledge based inferring techniques were analyzed in detail,including rule matching algorithms,confliction resolution strategies and production inferring methods.A linear model and a nonlinear model based on Artificial Neural Networks(ANN) were used to simulate the mapping relationship between the processing method and condition.The testing instances indicate that the methods can bring quite good results.