Predicting effects of diffusion welding parameters on welded joint properties by artificial neural network
来源期刊：中国有色金属学报(英文版)2001年第4期
论文作者：刘黎明 祝美丽 牛济泰 张忠典
文章页码：475 - 478
Key words：artificial neural network; diffusion welding; composite
Abstract: The static model for metal matrix composites in diffusion welding was established by means of artificial neural network method. The model presents the relationship between weld joint properties and welding parameters such as welding temperature, welding pressure and welding time. Through simulating the diffusion welding process of SiCw/6061Al composite, the effects of welding parameters on the strength of welded joint was studied and optimal technical parameters was obtained. It is proved that this method has good fault-tolerant ability and versatility and can overcome the shortage of the general experiment. The established static model is in good agreement with the actual welding process, so it becomes a new path for studying the weldability of new material.
