Simulating weld hot crack of T-type joints of aluminum plates with ANN

来源期刊：中国有色金属学报(英文版)2005年第z2期

论文作者：董志波 魏艳红 B. Yakushin D. Semin

文章页码：25 - 29

Key words：artificial neural network； aluminum alloy； weld hot crack

Abstract: Artificial neural network(ANN) technology was applied to predict weld hot crack susceptibility of the T-type welded joints of aluminum alloys. A primary prediction model was established by training and testing models with different structures and committee models with different numbers of sub models. The models were improved by decreasing the input variables and data-covering space. Then welding hot crack prediction model committee for T-type joints of aluminum plates was developed. Its input parameters include base metal composition, filler metal composition and welding technique, the output parameter is the total length of the weld hot crack. The performance analysis shows that the predicted trend agrees well with the previous research work.