Robust air/fuel ratio control with adaptive DRNN model and AD tuning

Yu Jia Zhai; Ding Wen Yu; Hong Yu Guo; D. L. Yu

doi:10.1016/j.engappai.2009.12.006

Robust air/fuel ratio control with adaptive DRNN model and AD tuning

Yu Jia Zhai, Ding Wen Yu, Hong Yu Guo, D. L. Yu^*

^*Corresponding author for this work

Research output: Contribution to journal › Article › peer-review

29 Citations (Scopus)

Abstract

Current production engines use look-up table and proportional and integral (PI) feedback control to regulate air/fuel ratio (AFR), which is time-consuming for calibration and is not robust to engine parameter uncertainty and time varying dynamics. This paper investigates engine modelling with the diagonal recurrent neural network (DRNN) and such a model-based predictive control for AFR. The DRNN model is made adaptive on-line to deal with engine time varying dynamics, so that the robustness in control performance is greatly enhanced. The developed strategy is evaluated on a well-known engine benchmark, a simulated mean value engine model (MVEM). The simulation results are also compared with the PI control.

Original language	English
Pages (from-to)	283-289
Number of pages	7
Journal	Engineering Applications of Artificial Intelligence
Volume	23
Issue number	2
DOIs	https://doi.org/10.1016/j.engappai.2009.12.006
Publication status	Published - Mar 2010
Externally published	Yes

Keywords

Adaptive neural networks
Air/fuel ratio control
Model predictive control
Recurrent neural networks
SI engines

Access to Document

10.1016/j.engappai.2009.12.006

Cite this

@article{c22236d1507b40d08fe3586126552640,

title = "Robust air/fuel ratio control with adaptive DRNN model and AD tuning",

abstract = "Current production engines use look-up table and proportional and integral (PI) feedback control to regulate air/fuel ratio (AFR), which is time-consuming for calibration and is not robust to engine parameter uncertainty and time varying dynamics. This paper investigates engine modelling with the diagonal recurrent neural network (DRNN) and such a model-based predictive control for AFR. The DRNN model is made adaptive on-line to deal with engine time varying dynamics, so that the robustness in control performance is greatly enhanced. The developed strategy is evaluated on a well-known engine benchmark, a simulated mean value engine model (MVEM). The simulation results are also compared with the PI control.",

keywords = "Adaptive neural networks, Air/fuel ratio control, Model predictive control, Recurrent neural networks, SI engines",

author = "Zhai, {Yu Jia} and Yu, {Ding Wen} and Guo, {Hong Yu} and Yu, {D. L.}",

year = "2010",

month = mar,

doi = "10.1016/j.engappai.2009.12.006",

language = "English",

volume = "23",

pages = "283--289",

journal = "Engineering Applications of Artificial Intelligence",

issn = "0952-1976",

number = "2",

}

TY - JOUR

T1 - Robust air/fuel ratio control with adaptive DRNN model and AD tuning

AU - Zhai, Yu Jia

AU - Yu, Ding Wen

AU - Guo, Hong Yu

AU - Yu, D. L.

PY - 2010/3

Y1 - 2010/3

N2 - Current production engines use look-up table and proportional and integral (PI) feedback control to regulate air/fuel ratio (AFR), which is time-consuming for calibration and is not robust to engine parameter uncertainty and time varying dynamics. This paper investigates engine modelling with the diagonal recurrent neural network (DRNN) and such a model-based predictive control for AFR. The DRNN model is made adaptive on-line to deal with engine time varying dynamics, so that the robustness in control performance is greatly enhanced. The developed strategy is evaluated on a well-known engine benchmark, a simulated mean value engine model (MVEM). The simulation results are also compared with the PI control.

AB - Current production engines use look-up table and proportional and integral (PI) feedback control to regulate air/fuel ratio (AFR), which is time-consuming for calibration and is not robust to engine parameter uncertainty and time varying dynamics. This paper investigates engine modelling with the diagonal recurrent neural network (DRNN) and such a model-based predictive control for AFR. The DRNN model is made adaptive on-line to deal with engine time varying dynamics, so that the robustness in control performance is greatly enhanced. The developed strategy is evaluated on a well-known engine benchmark, a simulated mean value engine model (MVEM). The simulation results are also compared with the PI control.

KW - Adaptive neural networks

KW - Air/fuel ratio control

KW - Model predictive control

KW - Recurrent neural networks

KW - SI engines

UR - http://www.scopus.com/inward/record.url?scp=75749134845&partnerID=8YFLogxK

U2 - 10.1016/j.engappai.2009.12.006

DO - 10.1016/j.engappai.2009.12.006

M3 - Article

AN - SCOPUS:75749134845

SN - 0952-1976

VL - 23

SP - 283

EP - 289

JO - Engineering Applications of Artificial Intelligence

JF - Engineering Applications of Artificial Intelligence

IS - 2

ER -

Robust air/fuel ratio control with adaptive DRNN model and AD tuning

Abstract

Keywords

Access to Document

Other files and links

Fingerprint

Cite this