Guo, Mingxuan (Southeast University), Zhang, zhiwu (SMARTLINK), Zhuang, Weichao (Southeast University)

Cloud-Enabled Load Estimation of Heavy-Duty Truck Via Sparse Vehicle Information

Scheduled for presentation during the Invited Session "Trustworthy Diagnosis and Prognosis in Connected, Cooperative and Automated Mobility" (WeBT10), Wednesday, September 25, 2024, 14:30−14:50, Salon 18

2024 IEEE 27th International Conference on Intelligent Transportation Systems (ITSC), September 24- 27, 2024, Edmonton, Canada

This information is tentative and subject to change. Compiled on December 26, 2024

Abstract

The load estimation of heavy-duty trucks is crucial for vehicle condition monitoring and motion control. The development of cloud-based platforms for the connected vehicle provides sufficient data for vehicle condition estimation, while the sparse and poor vehicle information poses a great challenge for accurate and stable load estimation. In this paper, through feature extraction and anomaly analysis of massive sparse vehicle driving data, we propose processing measures such as interpolation/filtering for missing, noise and other anomalies in connected vehicle information. Then an online real-time load estimation model based on the Recursive Least Squares method with a forgetting factor is established. The test results of the sparse connected vehicle information show that the load estimation model established in this paper can realize less than 10% of the average error of estimation, and more than 90% of the estimation results converge within 15% of the error, which can meet the real-time and accurate load supervision of freight vehicles in the process of traveling.