基于GA的仪表新产品功能结构方案推理机模型关键技术研究

Study of Key Techniques of the Inference Machine Model for Function-Structure Project of the New Instrument Product Development Based on Genetic Algorithm(GA)

虚拟原型逼真设计是近几年发展起来的新技术,主要研究虚拟环境下的产品建模问题以及基于仿真的集成产品和过程设计问题.产品功能结构方案推理机模型是虚拟原型逼真设计实现的关键技术之一.针对功能模块组合方案优化问题的复杂性,研究了基于遗传算法(GA)的功能结构方案推理机模型的实现技术,提出了双链异或杂交算子和自适应调节杂交概率和突变算子选择等算法,结合仪表产品设计应用实例,验证了模型的优越性,并将其应用于仪表新产品开发决策支持系统———仪表LCQDPDS软件系统中.

Virtual prototype reality design （VPRD） is a new technique that has developed recently. Here studied are the problem of product modeling as well as the problem of integration product and process design based on virtual environment simulation. The inference machine model for function-structure project is one of important modules which consist of the framework of VRPD. According to the complexity of functionmodule combination on project optimization issue, the realizing techniques on building the inference machine model for function-structure project based on genetic algorithm（GA） are given. The algorithms of doublestranded exclusive OR crossover operator and adaptive communication selection to crossover operation are proposed. The advantage of GA-model is verified by the empirical test of instruments. The presented techniques have been applied to a decision support system （DSS） for the new product development of instruments.