Vertical load distribution strategy of amphibious wheel-track vehicle using neural network and particle swarm optimization

Abstract

Amphibious wheel-track vehicle (AWTV) can change the vertical load of the wheels and the tracks through the active hydro-pneumatic suspension system, which shows significant advantages in terms of maneuverability and road passing ability. However, AWTV is a strong nonlinear system. The irregularity of the road, and coupling characteristics between the vertical load of the wheel-tracks and the terrain will greatly affect the tractive efficiency of the whole vehicle. Therefore, how to effectively distribute the vertical load between the wheel and the track to improve the tractive efficiency of the whole vehicle is still a huge challenge. To address the above problems, based on the neural network (NN) and particle swarm optimization (PSO) algorithm, vertical load distribution strategy of the AWTV is proposed to improve its traction efficiency under different driving road in this paper. Firstly, the coupling dynamics model of AWTV with road and hydraulic system dynamics model of active suspension is established; Secondly, the wheel-track terrain model is built in EDEM-Recurdyn to collect data of vertical load and traction efficiency under the different soils and speeds, and the coupling function is obtained through NN; Then, the optimal vertical load of each axle is optimized through PSO; Finally, the feasibility and effectiveness of the strategy are verified by the simulation analysis under different road conditions and distribution strategies. The simulation and test results demonstrate that the proposed vertical load distribution strategy based on NN-PSO can effectively improve the traction performance of the AWTV in complex terrain environment, and have relatively superior control characteristics.