Prediction of NO<sub>x</sub> Emissions of a Heavy Duty Diesel Engine with a NLARX Model

Maass, Bastian; Stobart, Richard; Deng, Jiamei

doi:10.4271/2009-01-2796

Cited by 12 publications

(5 citation statements)

References 10 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In this paper, we assess the intake manifold pressure and engine torque as the main outputs for MLP network design. In some literature [16], it is noted that emissions such as NO x or CO are also chosen as the MLP network output. Here we focus on the pressure and torque as they are the primary variables in engine calibration and control.…”

Section: Multi-layer Perceptron (Mlp) Neural Networkmentioning

confidence: 99%

“…In the last decade, the artificial Neural Networks (NN) have been seen as an attractive approach for dynamic system modelling and control. There are many studies on the application of NN on engine modelling, e.g., [12,13,14,15,16,17] therein. NN can be regarded as a black-box system identification approach that is conceptually simple, easy to use, and have excellent approximation properties.…”

mentioning

confidence: 99%

See 1 more Smart Citation

Control-Oriented Modelling of a Wankel Rotary Engine: A Synthesis Approach of State Space and Neural Networks

Chen

Vorraro

Turner³

et al. 2020

SAE Technical Paper Series

View full text Add to dashboard Cite

T he use of Wankel rotary engines as a range extender has been recognised as an appealing method to enhance the performance of Hybrid Electric Vehicles (HEV). They are effective alternatives to conventional reciprocating piston engines due to their considerable merits such as lightness, compactness, and higher power-to-weight ratio. However, further improvements on Wankel engines in terms of fuel economy and emissions are still needed. The objective of this work is to investigate the engine modelling methodology that is particularly suitable for the theoretical studies on Wankel engine dynamics and new control development.In this paper, control-oriented models are developed for a 225CS Wankel rotary engine produced by Advanced Innovative Engineering (AIE) UK Ltd. Through a synthesis approach that involves State Space (SS) principles and the artificial Neural Networks (NN), the Wankel engine models are derived by leveraging both first-principle knowledge and engine test data. We first re-investigate the classical physicsbased Mean Value Engine Model (MVEM). It consists of differential equations mixed with empirical static maps, which are inherently nonlinear and coupled. Therefore, we derive a SS formulation which introduces a compact control-oriented structure with low computational demand. It avoids the cumbersome structure of the MVEM and can further facilitate the advanced modern control design. On the other hand, via black-box system identification techniques, we compare the different NN architectures that are suitable for engine modelling using time-series test data: 1) the Multi-Layer Perceptron (MLP) feedforward network; 2) the Elman recurrent network; 3) the Nonlinear AutoRegressive with eXogenous inputs (NARX) recurrent network. The NN models overall tend to achieve higher accuracy than the MVEM and the SS model and do not require a priori knowledge of the underlying physics of the engine.

show abstract

Section: Multi-layer Perceptron (Mlp) Neural Networkmentioning

confidence: 99%

mentioning

confidence: 99%

Control-Oriented Modelling of a Wankel Rotary Engine: A Synthesis Approach of State Space and Neural Networks

Chen

Vorraro

Turner³

et al. 2020

SAE Technical Paper Series

View full text Add to dashboard Cite

show abstract

“…Many manufacturers have developed corresponding in-house calibration tools. Several areas of academic enquiry have emerged in the last decade or so, such as the optimum methods of collecting data for empirical models to be used for calibration, 12–19 online calibration in the test cell, 20 adaptive calibration, 21 fast data acquisition for calibration, 22 transient calibration, 3–5,23,24 calibration of integrated engine-aftertreatment systems, 25,26 empirical modeling methods 27–39 and the computational optimization process. 40–44 Books on model-based calibration addressing the last two areas have started appearing, see, for example, works by Edwards et al, 45 Alberer et al 46 and Röpke et al 47 There is a growing body of literature addressing the application of model-based calibration and DoE techniques for regular engine development, for example, Suzuki et al 48 and Jiang et al, 49 and for unique applications such as noise reduction 50 and dual-fuel calibration 51 and calibration for gas-to-liquid (GTL) fuel vehicle conversion.…”

Section: Introductionmentioning

confidence: 99%

Advantages and applications of transforming empirical model input space with dimensional models

Brahma

2014

International Journal of Engine Research

View full text Add to dashboard Cite

Model-based calibration of steady-state engine operation is commonly performed with highly parameterized empirical models that are accurate but not very robust, particularly when predicting highly nonlinear responses such as diesel smoke emissions. To address this problem, and to boost the accuracy of more robust non-parametric methods to the same level, GT-Power was used to transform the empirical model input space into multiple input spaces that simplified the input-output relationship and improved the accuracy and robustness of smoke predictions made by three commonly used empirical modeling methods: Multivariate Regression, Neural Networks and the k-Nearest Neighbor method. The availability of multiple input spaces allowed the development of two committee techniques: a 'Simple Committee' technique that used averaged predictions from a set of 10 pre-selected input spaces chosen by the training data and the ''Minimum Variance Committee'' technique where the input spaces for each prediction were chosen on the basis of disagreement between the three modeling methods. This latter technique equalized the performance of the three modeling methods. The successively increasing improvements resulting from the use of a single best transformed input space (Best Combination Technique), Simple Committee Technique and Minimum Variance Committee Technique were verified with hypothesis testing. The transformed input spaces were also shown to improve outlier detection and to improve k-Nearest Neighbor performance when predicting dynamic emissions with steady-state training data. An unexpected finding was that the benefits of input space transformation were unaffected by changes in the hardware or the calibration of the underlying GT-Power model.

show abstract

“…The work reported in the paper demonstrates an architecture of controllable injection that meets the needs of multi-cycle control in a form of predictive optimal control that includes objectives to address exhaust gas qualities and engine output. If this control approach is adopted in practical application, virtual sensors based on neural networks could be used for the emissions and exhaust temperature measurement (Maass, et. al, 2009).…”

Section: Introductionmentioning

confidence: 99%

The Challenge of Fuel Path Control at High Load Conditions

Deng

Stobart

Maass

2011

IFAC Proceedings Volumes

Self Cite

View full text Add to dashboard Cite

Prediction of NO_x Emissions of a Heavy Duty Diesel Engine with a NLARX Model

Cited by 12 publications

References 10 publications

Control-Oriented Modelling of a Wankel Rotary Engine: A Synthesis Approach of State Space and Neural Networks

Control-Oriented Modelling of a Wankel Rotary Engine: A Synthesis Approach of State Space and Neural Networks

Advantages and applications of transforming empirical model input space with dimensional models

The Challenge of Fuel Path Control at High Load Conditions

Contact Info

Product

Resources

About

Prediction of NOx Emissions of a Heavy Duty Diesel Engine with a NLARX Model

Cited by 12 publications

References 10 publications

Control-Oriented Modelling of a Wankel Rotary Engine: A Synthesis Approach of State Space and Neural Networks

Control-Oriented Modelling of a Wankel Rotary Engine: A Synthesis Approach of State Space and Neural Networks

Advantages and applications of transforming empirical model input space with dimensional models

The Challenge of Fuel Path Control at High Load Conditions

Contact Info

Product

Resources

About

Prediction of NO_x Emissions of a Heavy Duty Diesel Engine with a NLARX Model