RELIABILITY PREDICTION OF DRYER BASED ON IMPROVED PSO＿BP NEURAL NETWORK (MT)

Abstract

When the BP neural network model is used to predict the reliability of the grain dryer, the model has problems such as slow convergence speed and easy to fall into local optimum. An improved particle swarm algorithm is used to optimize the BP neural network model and establish the PSO＿BP neural network The reliability prediction model of grain dryer is compared with MAERMSEMAPE index obtained by BP network model and GA＿BP network model. The research results show that when the improved PSO＿BP network model is used for forecasting, the three indicators are reduced by 0.051 8, 0.047 9 and 28.04% respectively compared with the BP network model; the three indicators are reduced by 0.000 4, 0.000 2 and 0.61% respectively compared with the GA＿BP network model, Which shows that it has smaller errors and better predictive ability. The methods and ideas for realizing accurate prediction of the reliability of grain dryers are provided.

Keywords

• Grain dryer;Particle swarm algorithm;BP neural network;Reliability prediction