基于ISSA-BP神经网络的棉纱条干均匀度预测OACSTPCD

In order to solve the problem that the evenness of cotton yarn was difficult to predict,a prediction method of BP neural network optimized by improved sparrow search algorithm(ISSA)was proposed.Firstly,12 raw cotton indexes collected during the cotton yarn forming process were extracted as the input variables of BP neural network prediction model.Then,the sparrow search algorithm(SSA)was improved by using the good point set strategy,Levy flight strategy and tournament learning strategy.Finally,the ISSA-BP neural network model was established by using ISSA to search the optimal initial weights and thresholds of BP neural network.In order to verify the effectiveness of the improved algorithm,Python was used for training and simulation.The predicted results were compared with BP model,GA-BP model,PSO-BP model and SSA-BP model.The results showed that the mean relative error in cotton evenness prediction with ISSA-BP model was 1.52%.The prediction performance of ISSA-BP was the best,the error was the smallest and the prediction result was the most ideal,which could effectively predict the evenness of cotton yarn.