Research on on-board dynamic weighing algorithm based on two-degree-of-freedom 1/4 vehicle model. (4th April 2022)

• Record Type: Journal Article
• Authors: Fu, Hongxun; Zhang, Yu; Gang, Xianyue; Qiao, Huanbo; Wang, Yan; Ku, Laiyun
• Is Part Of: International journal of heavy vehicle systems. Volume 28:Number 6(2021)
• Page Start: 792
• Page End: 807
• Publication Date: 2022-04-04
• Subjects: on-board weighing system -- two-degree-of-freedom 1/4 vehicle model -- dynamic weighing algorithm -- wavelet threshold denoising algorithm -- BP neural network; Motor vehicles -- Design and construction -- Periodicals; Commercial vehicles -- Design and construction -- Periodicals; Motor vehicles -- Design and construction; Periodicals; 629.224
• Languages: English
• ISSNs: 1744-232X

Abstract

The moving vehicle will be disturbed in many aspects, resulting in the dynamic weighing accuracy of the airborne weighing system being significantly lower than the static accuracy. In order to improve the dynamic weighing accuracy of the system, this paper designs a dynamic weighing algorithm based on wavelet threshold denoising and BP neural network. Firstly, a two-degree-of-freedom 1/4 vehicle model was built to obtain the vehicle dynamic distance data. Then, the wavelet threshold denoising algorithm was used to denoise the dynamic distance data. Finally, the BP neural network was constructed with the signal of vehicle speed, acceleration signal and denoised weight signal as the input layer to reduce the impact of the speed and acceleration on the weight signal. The results show that after the processing of dynamic weighing algorithm, the dynamic weighing error of vehicle is less than 2%, and the algorithm meets the accuracy requirements, and has high universality.