Adaptive control of track tension estimation using radial basis function neural network

Abstract

Track tension is a major factor influencing the reliability of a track. In order to reduce the risk of track peel-off, it is necessary to keep track tension constant. However, it is difficult to measure the dynamic tension during off-road operation. Based on the analysis of the relation and external forces depending on free body diagrams of the idler, idler arm, road wheel and road arm, a theoretical estimation model of track tension is built. Comparing estimation results with multibody dynamics simulation results, the rationality of track tension monitor is validated. By the aid of this monitor, a track tension control system is designed, which includes a self-tuning proportional-integral-derivative (PID) controller based on radial basis function neural network, an electro-hydraulic servo system and an idler arm. The tightness of track can be adjusted by turning the idler arm. Simulation results of the vehicle starting process indicate that the controller can reach different expected tensions quickly and accurately. Compared with a traditional PID controller, the proposed controller has a stronger anti-disturbance ability by amending control parameters online.