Overload and Load Centroid Recognition Method Based on Vertical Displacement of Body

摘要

The heavy-duty vehicles have large transportation capacity. Load value and load centroid position of the heavy-duty vehicles vary with the cargo mass and the driving condition, which affect driving safety and handling stability. Load value and load centroid position of the vehicles are usually measured on fixed test platform, and the vehicles are stationary or pass the platform slowly in the measurement process. This paper proposes a vehicle load and load centroid measurement system based on the machine vision and vertical displacement of the body, which is measured during the driving process. First, a mathematical model of the body displacement and vehicle load corresponding to the axles is established, and load centroid recognition model is established. Then, roadbed facilities are arranged according to specific requirements, and the identification environment is built. Based on the machine vision technology, the vertical characteristic distance is recognized by the side camera. Finally, the vehicle load value can be obtained by resolve the parameters. Compared with the rated load data in the database, the overload judgment of the vehicle is obtained. The load centroid of the vehicle can also be identified. By filtering the characteristic distance data recognized by the machine vision, the characteristic distance measurement error is effectively reduced. The vehicle experiments were carried out with ISUZU QL5050and Yuejin Shangjun X500. The experimental results verify the effectiveness of the system and can be used to identify overloads and offset loads, the load identification error is less than 20%, and the position of the load centroid is obtained. The result guide the driver to load cargoes reasonably and drive safely. Load value and load centroid position of the heavy-duty vehicles could be also used as the inputs of active safety system, which could improve the adaptability of active safety system to complex conditions.