Simulating weld hot crack of T-type joints of aluminum plates with ANN
(3.Department of Welding, Bauman Moscow State Technical University, Moscow 105005, Russian Federation)
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.
Key words: artificial neural network； aluminum alloy； weld hot crack