Modelling the Exhaust Gas Aftertreatment System of a SI Engine Using Artificial Neural Networks

Schürholz, Klemens; Bruckner, Daniel; Abel, Dirk

doi:10.1007/s11244-018-1089-9

Cited by 9 publications

(6 citation statements)

References 14 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Holder et al, 9 Ramanathan and co-workers, 11,14 Weilenmann, 15 Della Torre et al, 12 and Okajima et al 45 Mitsouridis et al 27 control oriented real-time oxygen storage dynamics Auckenthaler et al, 28 Kumar et al, 46 Bickel et al, 29 Guardiola et al, 47 and Schurholz et al 30 Arunachalam et al 48 a…”

Section: Driving Cyclementioning

confidence: 99%

“…The third group of models is control-oriented. These methods are often capable of real-time estimation of the current oxygen storage level using the λ-sensor or a raw exhaust gas composition model as the input but are calibrated to a specific catalyst design. − Therefore, these approaches do not offer possibilities for design parameter variation. As can be seen in Table , for the relatively new cGPF technology, there are only few modeling approaches available yet.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Modeling the Catalytic Performance of Coated Gasoline Particulate Filters under Various Operating Conditions

Walter

Neumann

Hinrichsen

2021

Ind. Eng. Chem. Res.

View full text Add to dashboard Cite

Coated gasoline particulate filters (cGPFs) can reduce gaseous as well as particulate emissions with the same device. However, their more complex design compared to conventional open monoliths requires accurate models in the development phase. We therefore present a new global kinetic model for cGPFs considering standard three-way catalyst reactions and extend it with the impact of lean–rich cycling, referred to as dithering. Submodels are introduced for the oxygen storage and for the extent of oxidation of the active centers. Therefore, the model captures the enhanced conversion of the catalyst under various dithering as well as steady-state conditions. Several steady-state and transient experiments were conducted on a specially equipped dynamic engine test bench in order to calibrate the approach. The proposed model accurately predicts the tailpipe emissions released in a worldwide harmonized light vehicles test procedure driving cycle that is not part of the original calibration data.

show abstract

Section: Driving Cyclementioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Modeling the Catalytic Performance of Coated Gasoline Particulate Filters under Various Operating Conditions

Walter

Neumann

Hinrichsen

2021

Ind. Eng. Chem. Res.

View full text Add to dashboard Cite

show abstract

“…A network architecture that models the physical processes of the system can also improve prediction accuracy. Schürholz et al [12] employs a recurrent architecture with additional forward connections between recurrent units, which correspond to the physical information flow between components further improving the prediction accuracy.…”

Section: Related Workmentioning

confidence: 99%

“…The lack of accuracy can be reduced by deep neural networks (DNN), which have shown to be capable at simulating dynamical systems over large time spans for various domains, such as unmanned aerial vehicles [8], [7], [9], ships [10], [11], engines [12], aerodynamics [13], and lake temperatures [14]. DNN-based models require little domain knowledge in comparison to physical models.…”

Section: Introductionmentioning

confidence: 99%

Hybrid Physics and Deep Learning Model for Interpretable Vehicle State Prediction

Baier¹,

Boukhers²,

Staab³

2021

Preprint

View full text Add to dashboard Cite

Physical motion models offer interpretable predictions for the motion of vehicles. However, some model parameters, such as those related to aero-and hydrodynamics, are expensive to measure and are often only roughly approximated reducing prediction accuracy. Recurrent neural networks achieve high prediction accuracy at low cost, as they can use cheap measurements collected during routine operation of the vehicle, but their results are hard to interpret. To precisely predict vehicle states without expensive measurements of physical parameters, we propose a hybrid approach combining deep learning and physical motion models including a novel two-phase training procedure. We achieve interpretability by restricting the output range of the deep neural network as part of the hybrid model, which limits the uncertainty introduced by the neural network to a known quantity. We have evaluated our approach for the use case of ship and quadcopter motion. The results show that our hybrid model can improve model interpretability with no decrease in accuracy compared to existing deep learning approaches.

show abstract

“…The literature consists of numerous studies that have effectively applied ANN models to predict engine parameters such as volumetric efficiency, 9 after-treatment system performance, 10–12 fuel quality, 13,14 and engine performance quality regarding the combustion of substitute fuels. 15–17 ANNs have been used to describe non-linear relationships between input and output parameters such as the air/fuel ratio, 18 ignition timing, 19 and actuator control system.…”

Section: Introductionmentioning

confidence: 99%

Design of a virtual test cell based on GMDH-type neural network for a heavy-duty diesel engine

Ghanaati

Sjöblom

Faghani

2020

Proceedings of the Institution of Mechanical Engineers, Part D:

View full text Add to dashboard Cite

The engine development process faces big challenges from new strict emission regulations in addition to the need for fuel efficiency improvements. The Software-in-the-Loop (SiL) and Hardware-in-the-Loop (HiL) environments decreases the required time during engine development, calibration, verification, and validation of the product. An accurate and easy to build dyno-engine model with real-time operational ability is required for this purpose. Artificial Neural Networks (ANN) have shown ability to model dynamic and complex systems like internal combustion engines. In this paper, the Group Method of Data Handling (GMDH) algorithm was utilized to build an ANN model of a heavy-duty diesel engine. One objective is to reduce the amount of manual labor on the results during the ANN model development process. The GMDH algorithm is a self-organizing process that will find the system laws and optimize the model structure automatically in one iteration. The GMDH model results were compared with a model developed by Levenberg-Marquardt Backpropagation (LM-BP) algorithm. The ANN models used actuator signals from an Engine Management System (EMS) to simulate the engine operation parameters. As revealed by the simulation results, the ANN models successfully predicted engine torque, fuel flow, and NOx concentration. The GMDH model as a self-organized model reduced lead time, had slightly higher transient cycle accuracy, had fewer inconsistent predictions, and demonstrated better extrapolation capability. The prediction accuracy for transient operation was improved by shifting the predicted value by calculating time delay and a decrease of 76.66% for fuel flow and 66.51% for NOX concentration in model accuracy were achieved. The GMDH dyno-engine model can be effectively applied as a virtual test cell instrument for testing, calibration, and optimization purposes.

show abstract

Modelling the Exhaust Gas Aftertreatment System of a SI Engine Using Artificial Neural Networks

Cited by 9 publications

References 14 publications

Modeling the Catalytic Performance of Coated Gasoline Particulate Filters under Various Operating Conditions

Modeling the Catalytic Performance of Coated Gasoline Particulate Filters under Various Operating Conditions

Hybrid Physics and Deep Learning Model for Interpretable Vehicle State Prediction

Design of a virtual test cell based on GMDH-type neural network for a heavy-duty diesel engine

Contact Info

Product

Resources

About