期刊
JOURNAL OF EXPERIMENTAL & THEORETICAL ARTIFICIAL INTELLIGENCE
卷 29, 期 5, 页码 1099-1117出版社
TAYLOR & FRANCIS LTD
DOI: 10.1080/0952813X.2017.1309692
关键词
Jaya algorithm; oppositional-based learning; welding processes; optimisation
Welding processes are characterised as a multi-input processes. Selection of optimum combination of process parameters of a welding process is a vital task in order to achieve high quality of weld and productivity. The objective of this work is to improve the performance of submerged arc welding (SAW) process, electron beam welding (EBW) process, friction stir welding (FSW) process and gas tungsten arc welding (GTAW) process through parameter optimisation using a variant of Jaya algorithm, which is fast, robust and convenient. This variant is named as Quasi-oppositional-based Jaya algorithm' (QO-Jaya). The optimisation case studies for each of the above-mentioned welding processes are considered and the results obtained by the QO-Jaya algorithm are compared with the results obtained by well-known optimisation algorithms such as genetic algorithm (GA), simulated annealing (SA), teaching-learning-based optimisation (TLBO) and basic Jaya algorithm.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据