Find in Library

Pre-strengthening hot/warm forming (PHF) technology can effectively shorten the microstructure evolution process of aluminium alloy deformation and heat treatment, and has a broad application prospect. In this paper, the process parameters in PHF are abstracted into sequence data, which is used as the input of long short-term memory neural network (LSTM) model to predict mechanical properties of aluminium alloy components after PHF process. Besides, the prediction models based on Random Forest (RF), Support Vector Regression (SVR) and Back Propagation Neural Network (BPNN) are established and compared with LSTM model. In addition, a Few-Shot Learning method based on the constitutive model is proposed to predict the properties of aluminium alloys.