Mass Flow Rate Prediction of Electronic Expansion Valve Based on Improved Particle Swarm Optimization Back-Propagation Neural Network Algorithm

Electronic expansion valve as a throttle element is widely used in heat pump systems and flow characteristics are its most important parameter. The flow characteristics of the electronic expansion valve (EXV) with a valve port diameter of 3mm are studied, when the refrigerant R134a is used as the working fluid. The main factors affecting the flow characteristics are researched by adopting the orthogonal experiment method and single factor control method, for example, inlet pressure, inlet temperature, outlet pressure and valve opening. The results show that the expansion valve opening degree has the greatest influence on mass flow rate. In view of the complicated phase change of the refrigerant passing through electronic expansion valve, it is difficult to model the flow characteristics accurately. Based on the measured experimental data, an improved particle swarm optimization algorithm whose learning factor can be dynamically adjusted is used to optimize the initial weights and thresholds of the back propagation(BP) neural network. Then BP neural network with the optimized initial weights and thresholds is used to predict the mass flow rate of the valve, whose prediction results are compared and analyzed with the ordinary BP neural network prediction results and prediction results of BP neural network with initial weights and thresholds optimized by ordinary particle swarm optimization algorithm. The results show that the model with the initial weights and thresholds optimized by the improved particle swarm algorithm has the highest prediction accuracy.The mean square error is significantly reduced and the coefficient of determination is closer to 1.