A Neural Estimator for Cylinder Pressure and Engine Torque

Winsel, Thomas; Ayeb, Mohamed; Lichtenthäler, D.; Theuerkauf, H. J.

doi:10.4271/1999-01-1165

Cited by 21 publications

(7 citation statements)

References 8 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Batch normalization 32 was also applied to prevent gradient vanishing or gradient exploding during training the neural network, which caused by the internal covariance shift. To reduce the internal covariance shift, mean and variance are calculated for each feature as equations (10) and (11), and features are normalized using mean and variance as equation (12). As shown equation (13), scale factor (g) and shift factor (b) are finally applied to insert non-linearity during training process because non-linearity of the activation function in hidden layers is missed by the result, mean 0 and variance 1 from equation (11) m…”

Section: Model Structurementioning

confidence: 99%

“…For internal combustion engine research, several studies using deep learning have been conducted in the last 20 years. In 1999, a basic study was introduced to estimate cylinder pressure and engine torque using a neural network called “neural estimator.” 12 Multi-layer perceptron was divided into regions and tuned systematically, then it was combined with a conventional modeling approach. In 2007, an ANN was used to predict the performance and emissions of a gasoline engine.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Deep learning procedure for knock, performance and emission prediction at steady-state condition of a gasoline engine

Shin

Lee

Kim

et al. 2020

Proceedings of the Institution of Mechanical Engineers, Part D:

View full text Add to dashboard Cite

Recently, deep learning has played an important role in the rise of artificial intelligence, and its accuracy has gained recognition in various research fields. Although engine phenomena are very complicated, they can be predicted with high accuracy using deep learning because they are based on the fundamentals of physics and chemistry. In this research, models were built with deep neural networks for gasoline engine prediction. The model consists of two sub-models. The first predicts the knock occurrence, and the second predicts performance, combustion, and emissions. This includes maximum cylinder pressure, crank angle at maximum cylinder pressure, maximum pressure rise rate, and brake mean effective pressure, brake-specific fuel consumption, brake-specific nitrogen oxides, and brake-specific carbon oxide, which are representative results of the engine (for normal combustion cases without knock). Model input parameters were selected considering engine operating conditions, and physically measurable sensor values. For test cases, the accuracy of the first model for knock classification is 99.0%, and the coefficient of determination (R2) values for the second model are all above 0.99. Test times of both models were approximately 2 ms. The robustness of all the models was verified using K-fold cross-validation. A sensitivity study of accuracy, according to the amount of training utilized, was also conducted to determine how many data points are required to effectively train the deep learning model. Accordingly, a deep learning approach was applied to predict the steady-state conditions of a gasoline engine. Achieved model accuracies and robustness proved deep learning to be an effective modeling approach, and test time was recognized to be able to apply for the real-time prediction. The sensitivity analysis can be applied for the preliminary study to define the number of experimental points for the deep learning model.

show abstract

Section: Model Structurementioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Deep learning procedure for knock, performance and emission prediction at steady-state condition of a gasoline engine

Shin

Lee

Kim

et al. 2020

Proceedings of the Institution of Mechanical Engineers, Part D:

View full text Add to dashboard Cite

show abstract

“…The inverted piston crank model (Cavina et al, 1999;Citron et al, 1989;Schagerberg and McKelvey, 2003), frequency analysis (Cavina et al, 1999;Lee et al, 2001), the stochastic method (Lee et al, 2001), neural networks (Gu et al, 1996;Johnsson, 2006;Murphy et al, 2003;Saraswati and Chand, 2010;Winsel et al, 1999) and a closed-loop observer using sliding mode control (Chen and Moskwa, 1997;Haskara and Mianzo, 2001;Kao and Moskwa, 1995;Shiao and Moskwa, 1995) are some methods for determining the indicated torque and cylinder pressure indirectly using crankshaft speed fluctuations. The inverted piston crank model approach uses a non-linear crank-slider model to determine the indicated torque (Connoly and Rizzoni, 1994;Drakunov et al, 1995;Rizzoni, 1989) and cylinder pressure (Brown and Neill, 1992;Citron et al, 1989;Schagerberg and McKelvey, 2003) from crankshaft speed fluctuations.…”

Section: Introductionmentioning

confidence: 99%

Cycle-by-cycle estimation of cylinder pressure and indicated torque waveform using crankshaft speed fluctuations

Ali

Saraswati

2014

Transactions of the Institute of Measurement and Control

View full text Add to dashboard Cite

In this work, frequency response functions (FRFs) are used for estimation of cycle-by-cycle cylinder pressure and indicated torque waveform, using crankshaft speed fluctuations. The FRFs are mapped as a function of the discrete Fourier transform of engine speed, mean speed and manifold pressure using a multilayer neural network. The accuracy of the model is analysed using some of the parameters derived from the cylinder pressure. These include the indicated mean effective pressure and peak pressure. The load torque on the engine is also estimated using a closed-loop observer. The model is tested on a test rig consisting of single-cylinder engine coupled with an eddy current dynamometer. The results show that the model is suitable for the estimation of cylinder pressure and other variables related to it at the operating points where the cyclic variations are within a driveability limit.

show abstract

“…Earliest instances to be mentioned here are monitoring the life cycle of engine components and diagnosis of engine failures [18], and aircraft engine control modeling [19]. Since then encouraging results of ANN approaches in different fields of engine studies have been magnificent including prediction of mechanical efficiency [20], real-time assessment of vehicle drivability [21], estimating cylinder pressure and engine torque [22] and modeling human subjective responses [23]. Although during the time the most extended area of applications came out to be the engine control [24,25].…”

Section: Literature Reviewmentioning

confidence: 99%

Effects of artificial neural networks characterization on prediction of diesel engine emissions

Tehranian¹

View full text Add to dashboard Cite

Effects of Artificial Neural Networks Characterization on Prediction of Diesel Engine Emissions Azadeh Tehranian More than a century after its invention, diesel remains the fuel of choice for buses and freight trucks. Diesel exhaust contains three gases that are regulated by the United States Environmental Protection Agency (EPA), as well as particulate matter (PM). There is a societal need both to lower emissions and to predict or model emissions more accurately for inventory purposes. Engine modeling, and real time control are the most indispensable steps towards lowering engine emissions, and it is argued that this modeling can be achieved by implementation of Artificial Neural Networks (ANN). Effects of ANN design, architecture, and learning parameters on the accuracy of emissions predictions were studied along with the variation of embedded activation functions. An optimization strategy was followed to attain the most suitable network in the defined framework for five emissions of NO x , PM, HC, CO, and CO 2. The emissions data were obtained from five engine transient test schedules, namely the E-CSHVR, ETC, FTP, E-Highway and E-WVU-5 Peak schedules. These were performed on a 550 hp General Electric DC engine dynamometer-testing unit at the West Virginia University Alternative Fuels, Engine and Emissions Research Center. The 3-Layer and Jump Connection networks were the most promising architectures and it was found that the radial basis functions such as the Gaussian and Gaussian Complement functions outperform the sigmoidal functions in all of the examined architectures. The accuracy of an excellent typical instance of CO 2 prediction was as good as 0.009% error of accumulated value over the course of a FTP cycle. DEDICATION To Afsaneh, for her profound empathy, To Nick and Roya, for their remarkable nobility, To Nasser, for his exclusive sincerity. iii WBP Weight associated with back propagation algorithm ŷ ANN prediction of variable y xxii 157 .

show abstract

A Neural Estimator for Cylinder Pressure and Engine Torque

Cited by 21 publications

References 8 publications

Deep learning procedure for knock, performance and emission prediction at steady-state condition of a gasoline engine

Deep learning procedure for knock, performance and emission prediction at steady-state condition of a gasoline engine

Cycle-by-cycle estimation of cylinder pressure and indicated torque waveform using crankshaft speed fluctuations

Effects of artificial neural networks characterization on prediction of diesel engine emissions

Contact Info

Product

Resources

About