Improving the electro-pneumatic clutch actuation control system of a heavy-duty vehicles using artificial neural network
1 Rectory Division, Federal Polytechnic, Umunneochi, Abia State, Nigeria.
2 Mechatronics Engineering Technology Department, School of Engineering, Akanu Ibiam Federal Polytechnic, Unwana, Afikpo, Ebonyi State, Nigeria.
Research Article
GSC Advanced Research and Reviews, 2024, 19(03), 018–030.
Article DOI: 10.30574/gscarr.2024.19.3.0175
Publication history:
Received on 21 March 2024; revised on 31 May 2024; accepted on 03 June 2024
Abstract:
The performance enhancement of clutch actuation control process in electro-pneumatic clutch system for heavy duty vehicles through the application of Artificial Neural Network control is addressed in this presentation. The inability of some heavy-duty vehicles to operate optimally on hilly terrains due to inadequate compression or torque and which often leads to accidents can be traced to inadequacies in clutch actuation control. Conventional control techniques in clutch actuation uses on/off, servo mechanism and other non-intelligent methods of actuation control. These conventional techniques demand for frequent calibration of clutch actuators. Often times, this important requirement is neglected with attendant ugly consequences. To eliminate calibration and its observed defects, an intelligent method of clutch actuation modelled in an Artificial Neural Network control is implemented. Conventional data obtained for piston error signals, speed, torque and power from a Mercedes Benz Actros Truck model MP 2, 2031 provided the reference points. These data were fed into a developed ANN that was subjected to a standard training algorithm to achieve the intelligence control for electro-pneumatic clutch actuation. The Backpropagation method of weight adjustments and the application of Sigmund activation functions featured. Simulink models which imbedded design parameters for both conventional and ANN controllers were also developed and simulated. Different percentages of improvements were recorded for piston error, engine torque, angular speed and power respectively. In order to justify the research, the level and percentage of improvements were determining. ANN improved by 0.4821mm or 33.04 % decrease for error, increases of 334.1 RPM or 33 % for angular speed, 0.0594NM or 33.26 % for torque and 2.79 watts or 16.53 % for power respectively were recorded. These results depicts conclusively that ANN controller application in intelligent clutch actuation control of an electro-pneumatic clutch actuation system for heavy-duty vehicle will be remarkable. Its impact in the smooth operation of heavy-duty vehicles will indeed eliminate completely the attendant calibration problems and associated poor performances with conventional controllers in electro-pneumatic clutch actuation systems.
Keywords:
Artificial Neural Network; Actuation; Control; Calibration; Transmission
Full text article in PDF:
Copyright information:
Copyright © 2024 Author(s) retain the copyright of this article. This article is published under the terms of the Creative Commons Attribution Liscense 4.0
