In-Cylinder Pressure-Based Low-Pressure-Cooled Exhaust Gas Recirculation Estimation Methods for Turbocharged Gasoline Direct Injection Engines

Jung, Donghyuk; Kim, Haksu; Hong, Seungwoo; Park, Yeongseop; Lee, Hyungbok; Han, Dong; Han, Manbae; Sunwoo, Myoungho

doi:10.1115/1.4040578

Cited by 4 publications

(4 citation statements)

References 53 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Figure 11 compares the proposed CNN model with the previous LP-EGR model based on the in-cylinder pressure measurements. The previous method 23 was a polynomial regression model based on the combustion parameters extracted from the cylinder pressure traces, as illustrated in Figure 3. This polynomial model also contained static model-based discrete Kalman filter algorithms to deal with the adverse effects of the cycle-to-cycle variations.…”

Section: Resultsmentioning

confidence: 99%

“…Figure 3 compares the overall concept of the proposed CNN model with the conventional approach. 23 In the previous approach, the LP-EGR rate is estimated in the form of the polynomial regression model based on the combustion parameters, which are manually extracted and analyzed through the heat release analysis, central moment calculation, and PCA. On the other hand, the proposed CNN directly estimates the final LP-EGR rate from the raw data of the cylinder pressure traces through end-to-end learning.…”

Section: Cnn Modelmentioning

confidence: 99%

“…In this regard, various studies have highlighted the remarkable potential of in-cylinder pressure-based virtual sensor design for estimating the LP-EGR rate. 21–23 Since the in-cylinder pressure provides direct information on the combustion process, it allows accurate estimation of the LP-EGR rate into the cylinders without any transport delay from the LP-EGR path. Moreover, the estimation is attainable for fast response on a cycle-by-cycle basis.…”

Section: Introductionmentioning

confidence: 99%

“…Okunishi and Ogawa 22 found a clear correlation between the LP-EGR rate and the combustion pressure difference at a certain crank angle in the compression stroke. Furthermore, Jung et al 23 evaluated the LP-EGR models using various combustion parameters that were obtained from heat release analysis, central moment calculation, and principal component analysis (PCA). The previous studies proposed valuable combustion characteristics that are highly correlated with the effects of LP-EGR; however, the process of manually extracting and analyzing these characteristics for a wide range of engine operations is a significant engineering burden that requires considerable time and effort.…”

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

In-cylinder pressure-based convolutional neural network for real-time estimation of low-pressure cooled exhaust gas recirculation in turbocharged gasoline direct injection engines

Jung

Hwang

et al. 2019

International Journal of Engine Research

Self Cite

View full text Add to dashboard Cite

Low-pressure cooled exhaust gas recirculation is one of the most promising technologies for improving fuel efficiency of turbocharged gasoline direct injection engines. To realize the beneficial effects of the low-pressure cooled exhaust gas recirculation, the accurate estimation of the low-pressure cooled exhaust gas recirculation rate is essential for precise low-pressure cooled exhaust gas recirculation control. In this respect, previous studies have suggested in-cylinder pressure-based low-pressure cooled exhaust gas recirculation models to obtain the low-pressure cooled exhaust gas recirculation rate into the cylinders with fast response. However, these methods require considerable manual process of feature engineering to extract and analyze the combustion characteristics from the cylinder pressure traces. Furthermore, the performance of the entire model is limited solely to certain hand-crafted characteristics and their mathematical formulations. To resolve these limitations, we propose an in-cylinder pressure-based convolutional neural network for low-pressure cooled exhaust gas recirculation estimation. Because the convolutional neural network model automatically learns the complex function between the raw input of the high-dimensional cylinder pressure traces and the low-pressure cooled exhaust gas recirculation rate through an end-to-end deep learning framework, this convolutional neural network model provides a more effective and precise modeling process compared to the conventional combustion characteristics-based regression models. The proposed convolutional neural network model consists of the input layer with the previous consecutive cycles of the pressure traces to resolve the model uncertainty from cycle-to-cycle variations. This input layer is connected to one convolutional layer, two fully connected layers, and the final output layer that is the target low-pressure cooled exhaust gas recirculation rate. The proposed model was trained, validated, and tested using a total of 50,000 cycles of engine experimental data under various transient driving conditions. The remarkable accuracy of the proposed model was evaluated with R2 values over 0.99 and root mean square error values of less than 1.5% under the transient conditions. Moreover, the real-time performance and low memory requirement were also verified on the target embedded platform.

show abstract

Section: Resultsmentioning

confidence: 99%

Section: Cnn Modelmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

In-cylinder pressure-based convolutional neural network for real-time estimation of low-pressure cooled exhaust gas recirculation in turbocharged gasoline direct injection engines

Jung

Hwang

et al. 2019

International Journal of Engine Research

Self Cite

View full text Add to dashboard Cite

show abstract

Implementation of Optimized Artificial Neural Networks for Real-Time Estimation of Low Pressure Cooled Exhaust Gas Recirculation in a Turbocharged Gasoline Direct Injection Engine Using a Model-Based Design Approach

Min

Sunwoo

et al. 2020

Journal of Engineering for Gas Turbines and Power

View full text Add to dashboard Cite

Low pressure cooled exhaust gas recirculation (LP-EGR) system has been widely adopted to improve energy efficiency in turbocharged gasoline direct injection (GDI) engines. In order to utilize complete beneficial effects of the LP-EGR, a technique capable of accurately observing the LP-EGR flow into the cylinder in real-time is a prerequisite. To precisely estimate the LP-EGR rate in real-time, this paper proposes artificial neural network (ANN) models and its implementation on a real-time embedded system. As inputs for the ANN models, 12 combustion parameters physically correlated with the LP-EGR in the combustion process are selected and calculated from the in-cylinder pressure. The ANN models for the real-time LP-EGR estimation were trained with the steady-state data of 30,000 cycles and their hyper-parameters were searched by a hyper-parameter optimization method. Moreover, a model-based design procedure is introduced to implement the optimized ANN models on the real-time embedded system. Since the proposed implementation performs the validation procedure for each process, it provides a systematic and seamless process for creating ANN models for real-time embedded systems. In real-time experiments under eight steady-state engine operating points, the embedded ANN models show the estimation performance with R2 of above 0.9716. The operation time of each ANN was less than 1.285 ms meaning that the target system can operate in real-time sufficiently with a mass-produced 32 bit microprocessor up to 256 MHz.

show abstract

Understanding of the asymmetric twin-stroll radial turbine under steady and pulsating inlet conditions

Wang,

Liu,

Wang

2024

Proceedings of the Institution of Mechanical Engineers, Part A:

View full text Add to dashboard Cite

Utilize asymmetrical twin-scroll turbines (ATSTs) to achieve high-pressure exhaust gas recirculation (EGR) with a single scroll while optimizing the other scroll’s design for engine scavenging optimization. ATST performance prediction relies heavily on understanding the turbine flow mechanism, which always faces the challenge posed by time-dependent non-uniform intake. This paper studied its performance and flow field under steady and unsteady intake conditions for a production ATST. Firstly, the steady performance of the ATST with different asymmetries (ASYs) under different scroll pressure ratios (SPRs) is investigated via the computational fluid dynamics (CFD) method. Results demonstrate that the distribution relationship between SPR and turbine flow parameter (MFP) has a certain symmetry based on SPR = 1. For efficiency, the imbalance of inlet conditions will lead to the reduction of turbine efficiency. Moreover, the ASY has little effect on the turbine’s efficiency under the condition of SPR = 1. Also, the unsteady CFD simulations are conducted under pulsating inlet conditions with different scroll averaged pressure ratios (SAPRs). The results show that the highest efficiency was achieved at an ASY of 0.5 under a SAPR of 1.2 conditions, and the maximum, minimum, and average efficiencies were 1.9%, 1.5%, and 0.9% higher than those at an ASY of 0.83. The turbine’s flow field at the optimal incidence angle point is analyzed. The secondary flow vortex in the volute of an ASY of 0.5 is more robust, and the volute outlet ‘s total pressure loss is more significant. However, a relatively good incidence angle is obtained at the rotor inlet, and the loss in the rotor flow field is more minor. Therefore, the turbine efficiency with an ASY of 0.5 is higher.

show abstract

In-Cylinder Pressure-Based Low-Pressure-Cooled Exhaust Gas Recirculation Estimation Methods for Turbocharged Gasoline Direct Injection Engines

Cited by 4 publications

References 53 publications

In-cylinder pressure-based convolutional neural network for real-time estimation of low-pressure cooled exhaust gas recirculation in turbocharged gasoline direct injection engines

In-cylinder pressure-based convolutional neural network for real-time estimation of low-pressure cooled exhaust gas recirculation in turbocharged gasoline direct injection engines

Implementation of Optimized Artificial Neural Networks for Real-Time Estimation of Low Pressure Cooled Exhaust Gas Recirculation in a Turbocharged Gasoline Direct Injection Engine Using a Model-Based Design Approach

Understanding of the asymmetric twin-stroll radial turbine under steady and pulsating inlet conditions

Contact Info

Product

Resources

About