Method for predicting yield strength of multiple types of aluminum alloys through QIO-BP neural network

The invention discloses a method for predicting the yield strength of multiple types of aluminum alloys through a QIO-BP neural network, and the method comprises the following steps: 1, constructing a three-layer BP neural network model, and enabling a hidden layer activation function to be a tansig function; 2, an activation function of an output layer is a purelin function, and the number of hidden layer nodes is determined through an empirical formula; 3, obtaining an initial weight and an output threshold value of the BP neural network through rapid convergence and rapid optimization capability of a QIO algorithm, and optimally solving the problem that the BP neural network falls into a local minimum value; and 4, optimizing an initial value and a threshold value of the BP neural network through an ASO algorithm, and selecting an average absolute error of the training set and the test set as a fitness value of the ASO. According to the method for predicting the yield strength of the multi-type aluminum al