Depending on the amount of data to process, file generation may take longer.

If it takes too long to generate, you can limit the data by, for example, reducing the range of years.

Article

Download BibTeX

Title

A Neural-network-based Control System for a Dynamic Model of Tractor With Multiple Trailers System

Authors

[ 1 ] Instytut Technologii Mechanicznej, Wydział Inżynierii Mechanicznej, Politechnika Poznańska | [ P ] employee

Scientific discipline (Law 2.0)

[2.9] Mechanical engineering

Year of publication

2023

Published in

International Journal of Control, Automation and Systems

Journal year: 2023 | Journal volume: vol. 21 | Journal number: no. 10

Article type

scientific article

Publication language

english

Keywords
EN
  • dynamic model
  • multibody
  • neural network
  • tractor
  • trailers
  • vehicle dynamics
Abstract

EN Tractors with multiple trailers are widely applied means of transport in manufacturing systems. There exist numerous designs of trailers and tractors, making the estimation of the system trajectory and the required transportation corridor a complex task. It is also difficult to achieve the same trajectory for a manually operated tractor for multiple runs. The problem is complicated if there are multiple towed trailers or a dynamic drive on slippery ground. One approach is to replace the driver with an automated steering system. This paper presents a dynamic model of a tractor with multiple trailer system, based on the Lagrange formalism, which is controlled by artificial neural networks. To account for the slip phenomenon, a sigmoidal tire model was used. The algorithm of the artificial neural network provides the most appropriate input parameters for tractor steering for a given transportation area. The input parameters are the torques applied to the tractor wheels and are determined by the algorithm based on the data collected by the LiDAR scanner during the train run. These data include distances for each unit from the obstacle (e.g., wall), information about the occurrence of a collision, and the distance traveled by the tractor. The simulation results of the integration of the dynamic model and the neural network modeled are presented in a graphic form. The proposed algorithm ensures a collision-free ride of the system.

Date of online publication

25.08.2023

Pages (from - to)

3456 - 3469

DOI

10.1007/s12555-022-0741-0

URL

https://link.springer.com/article/10.1007/s12555-022-0741-0

Ministry points / journal

100

Impact Factor

2,5

This website uses cookies to remember the authenticated session of the user. For more information, read about Cookies and Privacy Policy.