The prediction model of air-jet texturing Yarn intensity based on the CNN-BP neural network

摘要

Air-jet texturing Yarn intensity is a important index of yarn quality. It can be well controlled by predicting yarn intensity that is yarn quality. Generally, there are many methods used to predict yarn intensity such as multiple non regression algorithms, support vector machines (SVD) and BP neural network algorithms. This paper presents an algorithm to combine convolutional neural network (CNN) with the BP neural network, which is written as the CNN-BP algorithm. We use 40 sets of data to train CNN-BP algorithm, regression, V-SVD algorithm, and BP neural network. We tested CNN-BP algorithm, regression, V-SVD algorithm and BP neural network with 5 sets of data. The experimental results show the CNN-BP neural network algorithm is the best accurate in these four algorithms.