Purpose – Nowadays, automotive engines are controlled by electronic control units (ECUs), and the engine idle speed performance is significantly affected by the setup of control parameters in the ECU. The engine ECU tune-up is done empirically through tests on a dynamometer (dyno). In this way, a lot of time, fuel and human resources are consumed, while the optimal control parameters may not be obtained. The purpose of this paper is to propose a novel ECU setup optimization approach for engine idle speed control. Design/methodology/approach – In the first phase of the approach, Latin hypercube sampling (LHS) and a multi-input/output least squares support vector machine (LS-SVM) is proposed to build up an engine idle speed model based on dyno test data, and then a genetic algorithm (GA) is applied to obtain optimal ECU setting automatically subject to various user-defined constraints. Findings – The study shows that the predicted results using the estimated model from LS-SVM are in good agreement with the actual test results. Moreover, the optimization results show a significant improvement on idle speed performance in a test engine. Practical implications – As the methodology is generic it can be applied to different vehicle control optimization problems. Originality/value – The research is the first attempt to integrate a couple of paradigms (LHS, multi-input/output LS-SVM and GA) into a general framework for constrained multivariable optimization problems under insufficient system information. The proposed multi-input/output LS-SVM for modelling of multi-input/output systems is original, because the traditional LS-SVM modelling approach is suitable for multi-input, but single output systems. Finally, this is the first use of the novel integrated framework for automotive engine idle-speed control optimization.
[1]
Johan A. K. Suykens,et al.
Least Squares Support Vector Machines
,
2002
.
[2]
Caro Lucas,et al.
Colonial competitive algorithm: A novel approach for PID controller design in MIMO distillation column process
,
2008,
Int. J. Intell. Comput. Cybern..
[3]
S. Thompson,et al.
A comparison of idle speed control schemes
,
2000
.
[4]
Matt C. Best,et al.
On-line PID tuning for engine idle-speed control using continuous action reinforcement learning automata
,
2000
.
[5]
Liu Zhen-tao,et al.
Study of CNG/diesel dual fuel engine's emissions by means of RBF neural network
,
2004
.
[6]
Jaehong Park,et al.
Application of adaptive control to the fluctuation of engine speed at idle
,
2007,
Inf. Sci..
[7]
Ronald K. Jurgen.
Automotive Electronics Handbook
,
1999
.
[8]
Liu Bin,et al.
New predictive control algorithms based on Least Squares Support Vector Machines
,
2005
.
[9]
Erol Arcaklioğlu,et al.
Performance maps of a diesel engine
,
2005
.
[10]
Chris Manzie,et al.
A novel approach to disturbance rejection in idle speed control towards reduced idle fuel consumption
,
2003
.
[11]
Simon Haykin,et al.
Neural Networks: A Comprehensive Foundation
,
1998
.
[12]
T. Bohme,et al.
A nonlinear model for design and simulation of automotive idle speed control strategies
,
2006,
2006 American Control Conference.
[13]
A. T. Shenton,et al.
Inverse-NARMA: a robust control method applied to SI engine idle-speed regulation
,
2003
.