Pressure Measurement of the Flexible Pipe Algorithm in Aerial Refueling based on SVR with Parameter Optimization

Abstract

Abstract. With the problem that the pressure of the flexible pipe in aerial refueling was hard to be measured directly by sensors, a pressure measurement algorithm based on support vector regression (SVR) with parameter optimization was proposed in this paper. First, a data model with a large amount of historical data based on SVR was set up. Then the parameters of the model were optimized by cross-validation and grid-search method. Experimental results show that the method has a high prediction precision and good generalization ability comparing with BP neural network.