Study on vehicle load estimation considering the temperature effect of air suspension

Abstract

With the rapid development of the automotive industry, an increasing number of vehicles are equipped with air spring. Meanwhile, the continuous improvement of on-board weighing technology has further advanced vehicle load estimation methods based on air spring. However, few studies have addressed the effect of rubber temperature in air spring on vehicle load estimation. To fill this gap, this study designs an on-board weighing system based on air spring and proposes a novel load estimation method that incorporates the influence of air spring rubber temperature. The system integrates temperature sensors, laser displacement sensors, and pressure sensors to collect the temperature and state parameters of the air spring. Based on these data, the vehicle load is estimated and displayed on the in-cab screen. Through theoretical derivation and experiments, a load estimation method is developed, in which a neural network is used to train air spring parameters under varying temperature conditions to establish the load estimation model. Furthermore, a finite element model of an air spring load estimation system is constructed and its accuracy is validated. Results demonstrate that air spring rubber temperature significantly influences its load-bearing characteristics. The proposed estimation model achieves an accuracy within 1%, meeting the high-precision requirements of on-board weighing systems.