HiL-Calibration of SI Engine Cold Start and Warm-Up Using Neural Real-Time Model

Winsel, Thomas; Ayeb, Mohamed; Theuerkauf, H. J.; Pischinger, Stefan; Schernus, Christof; Lütkemeyer, Georg

doi:10.4271/2004-01-1362

Cited by 21 publications

(4 citation statements)

References 8 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The following variables have been used as inputs for the engine torque estimation based on the diagonal recurrent neural network architecture presented above: engine speed, manifold pressure, valve actuation, EGR (Exhaust Gas Recirculation) actuation, ignition timing and fuel injection [1], [2].…”

Section: Engine Torque Modelmentioning

confidence: 99%

Robust identification of nonlinear dynamic systems using Design of Experiment

Ayeb

Theuerkauf

Wilhelm

et al. 2006

2006 IEEE Conference on Computer Aided Control System Design, 2006 IEEE International Conference on Control Applications, 2006

View full text Add to dashboard Cite

Modern combustion engines are becoming increasingly complex, with more control variables, to meet the newest emissions regulations and improve the dynamic torque characteristics. However, the large number of control variables presents a challenge for the calibration process. The effects of all control variables and their interactions on the engine characteristics should be quantified in an accurate way to be able to derive the best control strategies aiming to minimise fuel consumption and emissions while generating the desired torque within acceptable time delays. Design of Experiment DoE methods have been used successfully to cope with the difficulties related to the characterisation of the underlying process in the presence of a large number of control variables. DoE provides experiment design methods aiming to reduce the number of measurements needed while ensuring the best quality of information related to a given optimisation criterion.In this paper a procedure is proposed to derive global dynamic models based on dynamic neural networks. The selection of the training data is derived by a D-optimality criterion to enhance the model quality. This ensures a reduction of the amount of measurement data needed for the training and hence an acceleration of the training process. It also improves the model quality by reducing the uncertainty on the model parameters. 1 1 (6) The matrix J J T is usually bad conditioned and its inversion can lead to numeric problems. The iteration is then improved leading finally to the Levenberg-Marquardtiteration [7], [8]:

show abstract

Section: Engine Torque Modelmentioning

confidence: 99%

Robust identification of nonlinear dynamic systems using Design of Experiment

Ayeb

Theuerkauf

Wilhelm

et al. 2006

2006 IEEE Conference on Computer Aided Control System Design, 2006 IEEE International Conference on Control Applications, 2006

View full text Add to dashboard Cite

show abstract

“…One of the engine control system development is based on the prediction result of such a model. Then, the attention in last years has been paid to engine and complete power train control using the knowledge of the models [15], [16].…”

Section: Diesel Engine Modeling a Transient Control With Model Pmentioning

confidence: 99%

Combustion Property Analysis and Control System for the Dynamics of a Single Cylinder Diesel Engine

Wahono

Wang²,

Ogai

2013

J. Mechatron. Electr. Power Veh. Technol.

View full text Add to dashboard Cite

Corresponding to global environment problems in recent year, the technology for reducing fuel consumption and exhaust gas emission of engine was needed. Simulation of transient engine response is needed to predict engine performance that frequently experience rapid changes of speed. The aim of this research is to develop a non-linear dynamic control model for direct injection single cylinder diesel engine which can simulate engine performance under transient conditions. In this paper, the combustion model with multistage injection and conducted experiments in the transient conditions to clarify the combustion characteristics was proposed. In order to perform the analysis of acceleration operation characteristics, it was built a Model Predictive Control (MPC) to reproduce the characteristic values of the exhaust gas and fuel consumption from the control parameters in particular. Finally, MPC is an effective method to perform the analysis of characteristic in diesel engine under transient conditions.

show abstract

“…Therefore, hybrid MVEM that combine physical based models of the engine gas path with surrogate approaches (i.e., Static Neural Networks (e.g., [2,3]) or Support (e.g., [4]) and Relevance Vector Machines (e.g., [5])) to model engine-block are often used in HiL tasks. This modeling approach provides besides information on engine speed and load signals also sensor values of additional parameters of the engine gas path, e.g., intake manifold pressure and/or air mass flow, pressure before exhaust aftertreatment devices, several temperatures in the engine gas path…, which are the required inputs of modern ECUs.…”

Section: Introductionmentioning

confidence: 99%

Transient Momentum Balance—A Method for Improving the Performance of Mean-Value Engine Plant Models

Katrašnik

2013

Energies

View full text Add to dashboard Cite

Mean-value engine models (MVEMs) are frequently applied in system-level simulations of vehicle powertrains. In particular, MVEMs are a common choice in engine simulators, where real-time execution is mandatory. In the case of real-time applications with prescribed, fixed sampling times, the use of explicit integration schemes is almost mandatory. Thus the stability of MVEMs is one of the main limitations when it comes to optimizing their performance. It is limited either by the minimum size of the gas volume elements or by the maximum integration time step. An innovative approach that addresses both constraints arises from the fact that the mass flow through the transfer elements of the MVEM is not modelled considering the quasi-steady assumption, but instead the mass-flow is calculated using a single transient momentum balance (TMB) equation. The proposed approach closely resembles phenomena in the physical model, since it considers both the flow-field history and the inertial effects arising from the time variation of the mass flow. It is shown in this paper that a consideration of the TMB equation improves the stability and/or the computational speed of the MVEMs, whereas it also makes it possible to capture physical phenomena in a more physically plausible manner. Keywords

show abstract

HiL-Calibration of SI Engine Cold Start and Warm-Up Using Neural Real-Time Model

Cited by 21 publications

References 8 publications

Robust identification of nonlinear dynamic systems using Design of Experiment

Robust identification of nonlinear dynamic systems using Design of Experiment

Combustion Property Analysis and Control System for the Dynamics of a Single Cylinder Diesel Engine

Transient Momentum Balance—A Method for Improving the Performance of Mean-Value Engine Plant Models

Contact Info

Product

Resources

About