Objective Assessment of Pilling of Knitted Fabrics Based on Improved BP Neural Network and Genetic Algorithm

Abstract

Pilling assessment is an important work in fabric performance specifications. This paper describes a kind of objective assessment method of pilling of knitted fabrics. Improved BP (IBP) neural network is used for giving the degree of the pilling. To avoid standard BP algorithm's shortcoming of trapping to a local optimum and to take advantage of the genetic algorithm (GA)'s globe optimal searching, a new kind of hybrid algorithm was formed based on the IBP neural network and GA. BP neural network was improved by adding the inertia impulse and self-adaptation learning rate to lessen convergence vibration and increase the learning speed. Then the initialized weights and thresholds of IBP neural network were optimized with GA. Three feature parameters are selected for the input of BP network. The experiment result shows that using this method can satisfy the demand.