Research on truck mass estimation based on long short-term memory network

Jiazhen Hu, Xiaoyan Shen, Shasha Wang, Peifu Ma, Chenxi Liu and Xinyu Sui

Energy, 2024, vol. 307, issue C

Abstract: To address the issues of convenience, scalability, and accuracy in existing truck mass estimation technologies, a truck mass estimation model based on Long Short-Term Memory Network (LSTM) using onboard OBD data is proposed. Seven-dimensional feature parameters, including vehicle driving speed, engine speed, and net output torque of the engine, are selected as input features to achieve accurate estimation of truck mass. This study collaborated with transportation enterprises from Yulin, China to collect real-time data using onboard OBD devices. The actual vehicle mass was obtained by using the data from the weighing scales installed at the departure and unloading points. These data were divided into training and validation sets for the model, and improvements were made step by step based on the prediction results. It's showed that when estimating vehicle mass based on trips, the average relative error between the estimated validation set and other vehicle masses is around 2.3 %; Compared with existing estimation models (estimation model based on extended Kalman filter and detection device based on EPB system), LSTM model has advantages such as high estimation accuracy and strong generalization ability, and has broad application space in overload transportation monitoring, safe transportation, energy conservation and emission reduction, etc.

Keywords: LSTM model; Vehicle mass estimation; Vehicle operation data; Truck safety; Overload management (search for similar items in EconPapers)
Date: 2024
References: View references in EconPapers View complete reference list from CitEc
Citations:

Downloads: (external link)
http://www.sciencedirect.com/science/article/pii/S0360544224025039
Full text for ScienceDirect subscribers only

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:eee:energy:v:307:y:2024:i:c:s0360544224025039

DOI: 10.1016/j.energy.2024.132729

Access Statistics for this article

Energy is currently edited by Henrik Lund and Mark J. Kaiser

More articles in Energy from Elsevier
Bibliographic data for series maintained by Catherine Liu ().