Research on prediction of cotton yarn quality by artificial Neural Network

摘要

The objective of this research is to predict of cotton yarn quality by building a BP neural network. Training the neural networks used HVI test results of cotton and USTER TENSOJET 4 test results of yarn. The best neural network topology is 10-5-4. The error between the predicted values and the output values of the neural networks are acceptable. The result showed the proposed method has the capacity to predict the cotton yarn quality.