Real-Time Estimation of the Exhaust Gas Recirculation Ratio Based on Cylinder Pressure Signals

2007 ◽  
Author(s):  
P. Klein ◽  
R. Grüter ◽  
O. Loffeld
Keyword(s):  
Real Time ◽  
Time Estimation ◽  
Exhaust Gas Recirculation ◽  
Exhaust Gas ◽  
Cylinder Pressure ◽  
Real Time Estimation ◽  
Gas Recirculation

scholarly journals Impact of EGR control at in-cylinder pressure and ecological properties of CI off-road vehicle engine

2017 ◽  
Vol 170 (3) ◽  
pp. 88-95
Author(s):  
Andrzej BIENIEK ◽  
Jarosław MAMALA ◽  
Mariusz GRABA ◽  
Krystian HENNEK
Keyword(s):  
System Analysis ◽  
Cooling System ◽  
Exhaust Gas Recirculation ◽  
Exhaust Gas ◽  
Cylinder Pressure ◽  
Compression Ignition Engine ◽  
Road Vehicle ◽  
Exhaust Gases ◽  
Recirculation System ◽  
Gas Recirculation

An attempt has been made to clarify the effect of wide-ranging control of the exhaust gas recirculation system on the cylinder pressure and ecological engine performance. This publication contains the results of tests performed on the CI (compression ignition) engine of the off-road vehicle mounted on the test bench. The study was based on advanced EGR control with a proportional valve and a very efficient exhaust gases cooling system. Analysis of the test results is based on the cylinder pressure and the concentration of NOx and PM components at exhaust gases. The study included the influence of the exhaust gas recirculation system control on parameters such as differential pressure, MBF, and relative NOx and PM emissions. As demonstrated by the analysis conducted, the EGR valve control method and the exhaust gas cooling intensity significantly affect the cylinder pressure and its ecological performance.

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

2018 ◽  
Vol 141 (4) ◽  
Author(s):  
Donghyuk Jung ◽  
Haksu Kim ◽  
Seungwoo Hong ◽  
Yeongseop Park ◽  
Hyungbok Lee ◽  
...  
Keyword(s):  
Heat Release ◽  
Mass Flow ◽  
Exhaust Gas Recirculation ◽  
Low Pressure ◽  
Central Moment ◽  
Estimation Methods ◽  
Exhaust Gas ◽  
Cylinder Pressure ◽  
Wide Range ◽  
Gas Recirculation

This paper proposes three different methods to estimate the low-pressure cooled exhaust gas recirculation (LP-EGR) mass flow rate based on in-cylinder pressure measurements. The proposed LP-EGR models are designed with various combustion parameters (CP), which are derived from (1) heat release analysis, (2) central moment calculation, and (3) principal component analysis (PCA). The heat release provides valuable insights into the combustion process, such as flame speed and energy release. The central moment calculation enables quantitative representations of the shape characteristics in the cylinder pressure. The PCA also allows the extraction of the influential features through simple mathematical calculations. In this paper, these approaches focus on extracting the CP that are highly correlated to the diluent effects of the LP-EGR, and the parameters are used as the input states of the polynomial regression models. Moreover, in order to resolve the effects of cycle-to-cycle variations on the estimation results, a static model-based Kalman filter is applied to the CP for the practically usable estimation. The fast and precise performance of the proposed models was validated in real-time engine experiments under steady and transient conditions. The proposed LP-EGR mass flow model was demonstrated under a wide range of steady-states with an R2 value over 0.98. The instantaneous response of the cycle-basis LP-EGR estimation was validated under transient operations.

Multi-zone reaction-based modeling of combustion for multiple-injection diesel engines

2018 ◽  
Vol 21 (6) ◽  
pp. 1012-1025 ◽  
Author(s):  
Yifan Men ◽  
Ibrahim Haskara ◽  
Guoming Zhu
Keyword(s):  
Diesel Engines ◽  
Exhaust Gas Recirculation ◽  
Operating Conditions ◽  
Computational Time ◽  
Zone Model ◽  
Exhaust Gas ◽  
Cylinder Pressure ◽  
Multiple Injections ◽  
Burn Rate ◽  
Gas Recirculation

As the requirements for performance and restrictions on emissions become stringent, diesel engines are equipped with advanced air, fuel, exhaust gas recirculation techniques, and associated control strategies, making them incredibly complex systems. To enable model-based engine control, control-oriented combustion models, including Wiebe-based and single-zone reaction-based models, have been developed to predict engine burn rate or in-cylinder pressure. Despite model simplicity, they are not suitable for engines operating outside the normal range because of the large error beyond calibrated region with extremely high calibration effort. The purpose of this article is to obtain a parametric understanding of diesel combustion by developing a physics-based model which can predict the combustion metrics, such as in-cylinder pressure, burn rate, and indicated mean effective pressure accurately, over a wide range of operating conditions, especially with multiple injections. In the proposed model, it is assumed that engine cylinder is divided into three zones: a fuel zone, a reaction zone, and an unmixed zone. The formulation of reaction and unmixed zones is based on the reaction-based modeling methodology, where the interaction between them is governed by Fick’s law of diffusion. The fuel zone is formulated as a virtual zone, which only accounts for mass and heat transfer associated with fuel injection and evaporation. The model is validated using test data under different speed and load conditions, with multiple injections and exhaust gas recirculation rates. It is shown that the multi-zone model outperformed the single-zone model in in-cylinder pressure prediction and calibration effort with a mild penalty in computational time.

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

2019 ◽  
pp. 146808741987900
Author(s):  
Donghyuk Jung ◽  
Inyoung Hwang ◽  
Yuhyeok Jo ◽  
Chulhoon Jang ◽  
Manbae Han ◽  
...  
Keyword(s):  
Neural Network ◽  
Convolutional Neural Network ◽  
Network Model ◽  
Neural Network Model ◽  
Exhaust Gas Recirculation ◽  
Low Pressure ◽  
Exhaust Gas ◽  
Cylinder Pressure ◽  
Recirculation Rate ◽  
Gas Recirculation

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.

scholarly journals Characterisation and optimisation of a real-time diesel engine model

2017 ◽  
Vol 231 (14) ◽  
pp. 1913-1934 ◽  
Author(s):  
Peter G Dowell ◽  
Sam Akehurst ◽  
Richard D Burke
Keyword(s):  
Diesel Engine ◽  
Real Time ◽  
Exhaust Gas Recirculation ◽  
Operating Conditions ◽  
Exhaust Gas ◽  
Step Size ◽  
Time Model ◽  
Crank Angle ◽  
Run Time ◽  
Gas Recirculation

Accurate real-time engine models are an essential step to allow the development of control algorithms in parallel to the development of engine hardware using hardware-in-the-loop applications. A physics-based model of the engine high-pressure air path and combustion chamber is presented. The model was parameterised using data from a small set of carefully selected operating conditions for a 2.0 l diesel engine. The model was subsequently validated over the complete engine operating map with exhaust gas recirculation and without exhaust gas recirculation. A high level of fit was achieved with R2 values above 0.94 for the mean effective pressure and above 0.99 for the air flow rate. The model run time was then reduced for real-time application by using forward differencing and single-precision floating-point numbers and by calculating the in-cylinder prediction for only a single cylinder. A further improvement of 25% in the run time was achieved by improving the submodels, including the strategic use of one-dimensional and two-dimensional look-up tables with optimised resolution. The model exceeds the performance of similar models in the literature, achieving a crank angle resolution of 0.5° at 4000 r/min. This simulation step size still yields good accuracy in comparison with a crank angle resolution of 0.1° and was validated against the experimental results from a New European Driving Cycle. The real-time model allows the development of control strategies before the engine hardware is available, meaning that more time can be spent to ensure that the engine can meet the performance and the emissions requirements over its full operating range.

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

2020 ◽  
Vol 142 (6) ◽  
Author(s):  
Yuhyeok Jo ◽  
Kyunghan Min ◽  
Myoungho Sunwoo ◽  
Manbae Han
Keyword(s):  
Steady State ◽  
Embedded System ◽  
Real Time ◽  
Direct Injection ◽  
Exhaust Gas Recirculation ◽  
Gasoline Direct Injection ◽  
Exhaust Gas ◽  
The Real ◽  
Ann Models ◽  
Gas Recirculation

Abstract 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.

Sign in / Sign up

Export Citation Format

Share Document