In-Cylinder Pressure Modelling with Artificial Neural Networks

Maass, Bastian; Deng, Jiamei; Stobart, Richard

doi:10.4271/2011-01-1417

Cited by 7 publications

(3 citation statements)

References 18 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Recently, artificial intelligence technologies, such as machine learning-based models, have emerged as a popular alternative for predicting cylinder pressure [10,11]. Unlike physics-based models, machine learning models do not require knowledge of the underlying physical processes due to their data-driven nature [12].…”

Section: Introductionmentioning

confidence: 99%

LSTM for Modeling of Cylinder Pressure in HCCI Engines at Different Intake Temperatures via Time-Series Prediction

Sontheimer,

Singh,

Verma

et al. 2023

Machines

View full text Add to dashboard Cite

Modeling engines using physics-based approaches is a traditional and widely-accepted method for predicting in-cylinder pressure and the start of combustion (SOC). However, developing such intricate models typically demands significant effort, time, and knowledge about the underlying physical processes. In contrast, machine learning techniques have demonstrated their potential for building models that are not only rapidly developed but also efficient. In this study, we employ a machine learning approach to predict the cylinder pressure of a homogeneous charge compression ignition (HCCI) engine. We utilize a long short-term memory (LSTM) based machine learning model and compare its performance against a fully connected neural network model, which has been employed in previous research. The LSTM model’s results are evaluated against experimental data, yielding a mean absolute error of 0.37 and a mean squared error of 0.20. The cylinder pressure prediction is presented as a time series, expanding upon prior work that focused on predicting pressure at discrete points in time. Our findings indicate that the LSTM method can accurately predict the cylinder pressure of HCCI engines up to 256 time steps ahead.

show abstract

Section: Introductionmentioning

confidence: 99%

LSTM for Modeling of Cylinder Pressure in HCCI Engines at Different Intake Temperatures via Time-Series Prediction

Sontheimer,

Singh,

Verma

et al. 2023

Machines

View full text Add to dashboard Cite

show abstract

“…They have provided fast and robust training using crankshaft speed and crankshaft acceleration as input variables. Maass et al [18] used a NARX Neural Network to predict the cylinder pressure. The used ANN model was validated by experimental data from a diesel engine.…”

Section: Introductionmentioning

confidence: 99%

Cylinder Pressure Prediction of An HCCI Engine Using Deep Learning

Yaşar

Çağıl

Torkul

et al. 2021

Chin. J. Mech. Eng.

View full text Add to dashboard Cite

Engine tests are both costly and time consuming in developing a new internal combustion engine. Therefore, it is of great importance to predict engine characteristics with high accuracy using artificial intelligence. Thus, it is possible to reduce engine testing costs and speed up the engine development process. Deep Learning is an effective artificial intelligence method that shows high performance in many research areas through its ability to learn high-level hidden features in data samples. The present paper describes a method to predict the cylinder pressure of a Homogeneous Charge Compression Ignition (HCCI) engine for various excess air coefficients by using Deep Neural Network, which is one of the Deep Learning methods and is based on the Artificial Neural Network (ANN). The Deep Learning results were compared with the ANN and experimental results. The results show that the difference between experimental and the Deep Neural Network (DNN) results were less than 1%. The best results were obtained by Deep Learning method. The cylinder pressure was predicted with a maximum accuracy of 97.83% of the experimental value by using ANN. On the other hand, the accuracy value was increased up to 99.84% using DNN. These results show that the DNN method can be used effectively to predict cylinder pressures of internal combustion engines.

show abstract

“…For the quantitative evaluation of these relation, the in-cylinder pressure data were acquired by using pressure sensors. The highly robust sensors have been designed before for controlling the engine [27][28][29][30][31][32][33][34][35][36]. However, these sensors have not been installed in gasoline engines due to its relatively high expense compared to the small engine control effect.…”

Section: Introductionmentioning

confidence: 99%

Experimental Study of Combustion Fluctuation Reduction Using In-Cylinder Pressure Estimation in Gasoline Engine

Ichiyanagi

Anggono

Dziemińska

et al. 2018

International Journal of Industrial Research and Applied Engineering

View full text Add to dashboard Cite

Gasoline engines needs to reduce its negative emission waste and raise its thermal efficiency. Previous studies have shown an improvement of engines by regulating the ignition timing and retaining the engine at certain air-to-fuel ratio. Additional development of the thermal efficiency is anticipated by reducing the oscillation of pressure due to combustion (referred to as combustion fluctuation) during each cycle. Reducing the combustion fluctuations promotes the generation of a stable combustion field and improves fuel consumption. Since the combustion fluctuations are significantly affected by the in-cylinder pressure at compression top dead center (referred to as TDC pressure), the present study proposes a method to estimate the TDC pressure in the next cycle. The estimation was conducted by measuring the in-cylinder pressure at exhaust valve opening in the given cycle. This study also developed the method to reduce the combustion fluctuations by using the TDC pressure estimation and controlling the ignition timing. In our experiments, it was found that the developed methods reduced the fluctuations of the indicated mean effective pressure (IMEP), the maximum in-cylinder pressure, and the TDC pressure by 62.1%, 51.2%, and 38.5%, respectively.

show abstract

In-Cylinder Pressure Modelling with Artificial Neural Networks

Cited by 7 publications

References 18 publications

LSTM for Modeling of Cylinder Pressure in HCCI Engines at Different Intake Temperatures via Time-Series Prediction

LSTM for Modeling of Cylinder Pressure in HCCI Engines at Different Intake Temperatures via Time-Series Prediction

Cylinder Pressure Prediction of An HCCI Engine Using Deep Learning

Experimental Study of Combustion Fluctuation Reduction Using In-Cylinder Pressure Estimation in Gasoline Engine

Contact Info

Product

Resources

About