Joint strength prediction in a pulsed MIG welding process using hybrid neuro ant colony-optimized model

详细信息    查看全文

• 作者：N. Raghavendra ; Rakshit Koranne ; Sukhomay Pal ; Surjya K. Pal and Arun K. Samantaray
• 关键词：Back ; propagation neural network ; Ant colony optimization ; PMIGW ; Weld strength
• 刊名：The International Journal of Advanced Manufacturing Technology
• 出版年：2009
• 出版时间：April, 2009
• 年：2009
• 卷：41
• 期：7-8
• 页码：694-705
• 全文大小：401.7 KB

文摘

In this work, a pulsed metal inert gas welding (PMIGW) process is modeled by using a hybrid soft computing technique. Ant colony optimization (ACO) and back-propagation neural network (BPNN) models are combined to predict the ultimate tensile strength of butt-welded joints. A large number of experiments have been conducted, and comparative study shows that the hybrid neuro ant colony-optimized model produces faster and also better weld-joint strength prediction than the conventional back propagation model.