第2种方法，借助于BP神经网络的非线性映射能力与自适应能力来模拟纱线实

The second method uses BP neural network's non-linear mapping ability and self-adaptive ability to simulate the complex non-linear relationship between each input factor and output factor in the actual production of yarn, using key process factors and raw cotton quality factors as input variables The yarn quality prediction method based on three-layer BP neural network and the yarn quality prediction method based on four-layer BP neural network were designed respectively, and the prediction effects of the two prediction methods were compared and analyzed.

The second method, with the help of bp neural network's nonlinear mapping ability and adaptive ability to simulate the complex nonlinear relationship between the input factors and output factors in the actual production of yarn, takes the key process factors and raw cotton quality factors as input variables, designs the yarn quality prediction method based on the three-layer BP neural network and the yarn mass prediction method based on the four-layer BP neural network, and compares and analyzes the prediction effect of the two prediction methods.

The second method is to simulate the complex nonlinear relationship between input factors and output factors in the actual production of yarn by means of the nonlinear mapping and adaptive ability of BP neural network. The key process factors and raw cotton quality factors are taken as input variables, and the yarn quality prediction method based on three-layer BP neural network and the yarn quality prediction method based on four-layer BP neural network are designed respectively The prediction results of the two methods are compared and analyzed.<br>