The state prediction method of the silk dryer based on the GA-BP model

Abstract

Abstract Considering the under-maintenance and over-maintenance of existing equipment maintenance methods, this paper studies a Condition Based Maintenance method for silk dryers. The entropy method is used to eliminate the influence of subjective factors to more objectively reflect the weight of different input parameters; optimizing the number of nodes in the hidden layer of the network to improve the prediction accuracy; and using the GA-BP neural network to establish a state prediction model of the equipment to solve the disadvantages of the BP neural network, for example, unstable prediction, easily falling into local optimum, and slow global search ability. Simulation experiments show that this method can effectively compensate for the shortcomings of the existing maintenance methods, and provide an effective scientific basis for dryer state maintenance.