Prediction of Yarn Quality Based on Differential Evolutionary BP Neural Network

In order to improve the prediction accuracy of yarn quality based on BP neural network, in this paper, differential evolution algorithm is applied to train BP neural network. By using six parameters of raw cotton as the input node, and single yarn strength value and evenness CV value which characterize yarn quality indicators as the output node, a prediction model of yarn quality is developed. In the test of real data, it shows that the algorithm has a good effect, improves the prediction accuracy of the BP neural network algorithm and provides effective support for the prediction of yarn quality in enterprise.