Online dynamic optimisation for the engine management system using artificial intelligence methods

Downloads

Downloads per month over past year

Li, Ziyang ORCID: https://orcid.org/0000-0001-6052-9246 (2019). Online dynamic optimisation for the engine management system using artificial intelligence methods. University of Birmingham. Ph.D.

[img]
Preview
Li2019PhD.pdf
Text - Accepted Version
Available under License All rights reserved.

Download (8MB) | Preview

Abstract

As the degrees of freedom for engine operations increases, the traditional calibration approaches for the lookup-table-based engine management system become time-consuming and labour-intensive. Besides, the lookup-table-based control method is not robust to system uncertainty and high nonlinearity. Accordingly, artificial intelligence methods are introduced to raise the automation level of the engine management system.

This thesis presents an intelligent non-model-based multi-objective calibration approach using meta-heuristic algorithms. It relies on neither the engine model nor massive experimental data. The experiment studies show that it can automatically locate the optimum engine variable settings to provide the minimum fuel consumption and PM emissions simultaneously with high efficiency.

A proportional-integral-like fuzzy knowledge based controller with the self-adaptive capability and high robustness is developed to regulate the air/fuel ratio for engines. It can reduce the effort to be spent in tuning controller parameters, and improve the system transient response, compared to the conventional lookup-table-based proportional-integral controller.

Subsequently, the controller parameters can be further improved using the intelligent non-model-based transient calibration approach. A better air/fuel ratio transient response is thus achieved.

All the calibration and control strategies have been validated on a real gasoline direct injection engine via the rapid control prototyping platform.

Type of Work: Thesis (Doctorates > Ph.D.)
Award Type: Doctorates > Ph.D.
Supervisor(s):
Supervisor(s)EmailORCID
Xu, HongmingUNSPECIFIEDUNSPECIFIED
Wyszynski, Miroslaw L.UNSPECIFIEDUNSPECIFIED
Olatunbosun, OluremiUNSPECIFIEDUNSPECIFIED
Licence: All rights reserved
College/Faculty: Colleges (2008 onwards) > College of Engineering & Physical Sciences
School or Department: School of Engineering, Department of Mechanical Engineering
Funders: Engineering and Physical Sciences Research Council, Other
Other Funders: Jaguar Land Rover, ETAS, Shell Global Solutions, Bosch, Rheonik, Cambustion
Subjects: T Technology > TJ Mechanical engineering and machinery
URI: http://etheses.bham.ac.uk/id/eprint/9723

Actions

Request a Correction Request a Correction
View Item View Item

Downloads

Downloads per month over past year