Skip to main page content
U.S. flag

An official website of the United States government

Dot gov

The .gov means it’s official.
Federal government websites often end in .gov or .mil. Before sharing sensitive information, make sure you’re on a federal government site.

Https

The site is secure.
The https:// ensures that you are connecting to the official website and that any information you provide is encrypted and transmitted securely.

Access keys NCBI Homepage MyNCBI Homepage Main Content Main Navigation
. 2023 Dec 30;24(1):226.
doi: 10.3390/s24010226.

LSTM-Based Virtual Load Sensor for Heavy-Duty Vehicles

Abdurrahman İşbitirici  1   2 , Laura Giarré  2 , Wen Xu  3 , Paolo Falcone  2   4
Affiliations

LSTM-Based Virtual Load Sensor for Heavy-Duty Vehicles

Abdurrahman İşbitirici et al. Sensors (Basel). .

Abstract

In this paper, a special recurrent neural network (RNN) called Long Short-Term Memory (LSTM) is used to design a virtual load sensor that estimates the mass of heavy vehicles. The estimation algorithm consists of a two-layer LSTM network. The network estimates vehicle mass based on vehicle speed, longitudinal acceleration, engine speed, engine torque, and accelerator pedal position. The network is trained and tested with a data set collected in a high-fidelity simulation environment called Truckmaker. The training data are generated in acceleration maneuvers across a range of speeds, while the test data are obtained by simulating the vehicle in the Worldwide harmonized Light vehicles Test Cycle (WLTC). Preliminary results show that, with the proposed approach, heavy-vehicle mass can be estimated as accurately as commercial load sensors across a range of load mass as wide as four tons.

Keywords: long short-term memory; mass estimation; recurrent neural network.

PubMed Disclaimer

Conflict of interest statement

The authors declare no conflict of interest.

Figures

Figure 1
Figure 1
Longitudinal vehicle dynamics.
Figure 2
Figure 2
Perceptron.
Figure 3
Figure 3
Feedforward neural network.
Figure 4
Figure 4
Activation functions: ReLU, tanh, and sigmoid.
Figure 5
Figure 5
LSTM network for mass estimation.
Figure 6
Figure 6
Training data with 60 kph initial velocity, 0% initial accelerator pedal percentage, and 100% final accelerator pedal percentage in 0.5 s.
Figure 7
Figure 7
WLTC based test data in the highest gear.
Figure 8
Figure 8
Performance of the network N1 with the test data set.
Figure 9
Figure 9
Performance of the network N2 with the test data set.
Figure 10
Figure 10
Performance of the network N3 with the test data set.
Figure 11
Figure 11
Performance of the network N4 with the test data set.
See this image and copyright information in PMC

References

    1. Xu C., Geyer S., Fathy H.K. Formulation and comparison of two real-time predictive gear shift algorithms for connected/automated heavy-duty vehicles. IEEE Trans. Veh. Technol. 2019;68:7498–7510. doi: 10.1109/TVT.2019.2921702. - DOI
    1. Chen Y.L., Shen K.Y., Wang S.C. Forward collision warning system considering both time-to-collision and safety braking distance; Proceedings of the 2013 IEEE 8th Conference on Industrial Electronics and Applications (ICIEA); Melbourne, Australia. 19–21 June 2013; pp. 972–977.
    1. Ritter A. Ph.D. Thesis. ETH Zurich; Zurich, Switzerland: 2021. Optimal Control of Battery-Assisted Trolley Buses.
    1. Kober W., Hirschberg W. On-board payload identification for commercial vehicles; Proceedings of the 2006 IEEE International Conference on Mechatronics; Budapest, Hungary. 3–5 July 2006; pp. 144–149.
    1. Technoton Axle Load Sensors. 2023. [(accessed on 26 November 2023)]. Available online: https://jv-technoton.com/products/axle-load-sensors/

LinkOut - more resources