A Nonlinear Wall-Wetting Model for the Complete Operating Region of a Sequential Fuel Injected SI Engine

Simons, Michael R.; Locatelli, Marzio; Onder, Christopher H.; Geering, Hans P.

doi:10.4271/2000-01-1260

Cited by 15 publications

(2 citation statements)

References 7 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Numerous modifications and enhancements of this model, including its adoption for individual cylinder injections, have formed the basis of production strategies. Off-line and on-line system identification/parameter estimation techniques have been used in [6], [7], [8], [16], [11], [3], [21], [22], [24], [17], [12], [2] to identify parameters in transient fuel models; the inverses of such models then yield transient fuel compensators. Applying offline/on-line system identification techniques can be intricate due to several reasons.…”

Section: Introductionmentioning

confidence: 99%

Sensitivity Equations Based Experiment Design and Adaptive Compensation of Transient Fuel Dynamics in Port-Fuel Injection Engines

Song

Kolmanovsky

Gibson

2007

2007 IEEE International Conference on Control Applications

View full text Add to dashboard Cite

In this paper we consider and address two topics relevant to calibration of parameters in transient fuel compensation algorithms. The first topic concerns the optimal selection of transient trajectories over which data are collected and identification of parameters in transient fuel model, the inverse of which constitutes a transient fuel compensation algorithm, is performed. We show that this problem can be formulated as an optimal control problem, and that this optimal control problem can be solved numerically. Even with the optimal transient trajectories, our results highlight a difficulty in identifying parameters in a transient fuel model if parameters in the model of exhaust gas mixing and in the model of the Universal Exhaust Gas Oxygen (UEGO) sensor are uncertain. The second topic addresses this difficulty through the use of adaptation to adjust parameters in a transient fuel compensation algorithm, until the deviation of measured fuel-to-air ratio from the commanded fuel-to-air ratio is sufficiently reduced. Our adaptation approach is shown to be robust to uncertainties in UEGO sensor and exhaust mixing dynamics. The theme common to both developments is the use of differential sensitivity equations.

show abstract

Section: Introductionmentioning

confidence: 99%

Sensitivity Equations Based Experiment Design and Adaptive Compensation of Transient Fuel Dynamics in Port-Fuel Injection Engines

Song

Kolmanovsky

Gibson

2007

2007 IEEE International Conference on Control Applications

View full text Add to dashboard Cite

show abstract

“…This forms a basis to explore RNN topology for virtual sensing of variables like lambda (non-dimensional air-fuel ratio) of the highly nonlinear internal combustion engine. Engine dynamics comprises of various subsystems like the intake mnifold (including wall wetting and air-filling phenomenon), in-cylinder processes, exhaust manifold (including transportation delay and lags) for exhaust gases, and lambda sensor dynamics [2,3]. Further, the engine parameters are unevenly sampled on the time scale.…”

Section: Introductionmentioning

confidence: 99%

Virtual air-fuel ratio sensors for engine control and diagnostics

Kamat

Javaherian

Diwanji

et al. 2006

2006 American Control Conference

View full text Add to dashboard Cite

Virtual air-fuel ratio sensors for an internal combustion engine using recurrent neural and wavelet networks have been developed. A nonlinear state-space modeling strategy is proposed for the architecture of the stated recurrent neural network which is trained using some variants of real time recurrent learning (RTRL) algorithm. A two-stage training approach is proposed for improving the accuracy of the RNN topology. Additionally, wavelets as activation functions have been employed to construct a single-layer network called wavenet. The wavenet is used to model the exhaust air-fuel ratio that has proved a more challenging task in a purely neural net-based architecture using sigmoid activation functions. The methodology has been implemented in a V8 spark ignition engine through rapid prototyping tools for the real time generalization and performance evaluation. Observations and comments are made on the test patterns used for the training. Some of the limitations of such a data driven approach are highlighted. Representative experimental results for the 8-cylinder engine test data are listed. The virtual sensor may be used for more precise average air-fuel ratio control and enhanced reliability engendered through the diagnostic capabilities of the sensor

show abstract

Identification of the relevant parameters of the wall-wetting system by extended Kalman filtering

Locatelli

Alfieri

Onder

et al. 2006

Control Engineering Practice

View full text Add to dashboard Cite

A Nonlinear Wall-Wetting Model for the Complete Operating Region of a Sequential Fuel Injected SI Engine

Cited by 15 publications

References 7 publications

Sensitivity Equations Based Experiment Design and Adaptive Compensation of Transient Fuel Dynamics in Port-Fuel Injection Engines

Sensitivity Equations Based Experiment Design and Adaptive Compensation of Transient Fuel Dynamics in Port-Fuel Injection Engines

Virtual air-fuel ratio sensors for engine control and diagnostics

Identification of the relevant parameters of the wall-wetting system by extended Kalman filtering

Contact Info

Product

Resources

About