Home/Alexandria Engineering Journal/Article Record
Peer-Reviewed Article July 16, 2020

Control of a new low-cost semi-active vehicle suspension system using artificial neural networks

Are you an author of this work?Link to your sovereign AfriScholar profile
Published in: Alexandria Engineering Journal
Publisher: Elsevier BV • Egypt • 1110-0168
DOI: https://doi.org/10.1016/j.aej.2020.07.007

Abstract

This work proposes a new suspension system for vehicles through replacing passive ordinary suspension with a new low-cost semi-active suspension. The new proposed system consists of a hydraulic piston with proportional throttle valve mounted outside the piston’s cylinder between the two inlet ports. The throttle valve will be used to dissipate the hydraulic energy in the cylinder’s oil. The throttle valve will be controlled via artificial neural network (ANN) controller to regulate the valve opening to achieve the needed equivalent damping coefficient. The proposed system will be controlled first by a PID controller and different cases have been simulated to acquire data needed to train the artificial neural network. The proposed system is easily constructed compared with commercially available magneto-rheological (MR) damping systems with a cost down to one quarter of the (MR) dampers’ cost. MATLAB/SIMSCAPE is utilized to construct the physical model of the proposed suspension system. The response of the vehicle with the proposed low-cost semi-active suspension system will be compared with traditional suspension system and MR suspension system to evaluate the effectiveness of the proposed low-cost semi-active suspension system. The results showed good performance in terms of vibration reduction and response time compared with the MR semi-active systems and traditional systems.

Download Full Text PDFView at PublisherCrossref RecordCrossref XML

Verified Citation Velocity

Recorded scholarly citations in African and international peer-reviewed literature

69
Total Citations

Citations are continuously tracked and harvested across continental OJS endpoints and OpenAlex feeds.