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

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.

Download Full-text

Transient “Single-Fuel” RCCI Operation With Customized Pistons in a Light-Duty Multicylinder Engine

Journal of Engineering for Gas Turbines and Power ◽

10.1115/1.4034445 ◽

2016 ◽

Vol 139 (3) ◽

Author(s):

Christopher W. Gross ◽

Rolf D. Reitz

Keyword(s):

Steady State ◽

Compression Ratio ◽

Fuel Injection ◽

Pressure Rise ◽

Operating Conditions ◽

Maximum Pressure ◽

Engine Operation ◽

Volume Percentage ◽

Light Duty ◽

Brake Mean Effective Pressure

Reactivity controlled compression ignition (RCCI) combustion in a light-duty multicylinder engine (MCE) over transient operating conditions using fast response exhaust unburned hydrocarbon (UHC1), nitric oxide (NO), and particulate matter (PM) measurement instruments was investigated. RCCI has demonstrated improvements in efficiency along with low NOx and PM emissions by utilizing in-cylinder fuel blending, generally using two fuels with different reactivity in order to optimize stratification. In the present work, a “single-fuel” approach for RCCI combustion using port-injected gasoline and direct-injected gasoline mixed with a small amount of the cetane improver 2-ethylhexyl nitrate (EHN) was studied with custom designed, compression ratio (CR) of 13.75:1, pistons under transient conditions. The EHN volume percentage in the mixture for the direct-injected fuel was set at 3%. In an experimental investigation, comparisons were made to transient RCCI combustion operation with gasoline/diesel. The experiments were performed over a step load change from 1 to 4 bar brake mean effective pressure (BMEP) at constant 1500 rev/min on a General Motors (GM) Z19DTH 1.9-L diesel engine. The transients were conducted by changing the accelerator pedal command to provide a desired torque output with a DRIVVEN engine control unit (ECU) that replaced the original Bosch ECU. All relevant engine parameters are adjusted accordingly, based on 2D-tables. Previous to the transient engine operation, four steady-state points were used to obtain performance and emission values. Engine calibration at these four points, as well as the interpolation of the intermediate points, allowed for smooth operation during the instantaneous step changes. Differences between the steady-state and transient results indicate the complexity of transient operation and show the need for additional controls to minimize undesirable effects. The steady-state points were calibrated by modifying the fuel injection strategy (actual start of injection (aSOI) timing, port-fuel injection (PFI) fraction, etc.), exhaust gas recirculation (EGR), and rail pressure in order to obtain predefined values for the crank-angle at 50% of total heat release (CA50). Furthermore, emission targets (HC1 < 1500 ppmC3, NO < 10 ppm, filter smoke number (FSN)<0.1 with a maximum pressure rise rate (MPRR) < 10 bar/deg) and noise level targets (<95 dB) for RCCI combustion were maintained during the calibration and mapping. The tests were performed with a closed-loop (CL) calibration by using a next-cycle (NC) controller to adjust the PFI ratio of each cycle in order to reach the steady-state CA50 values in the table. The results show that single-fuel RCCI operation can be achieved, but requires significant alteration of the operating conditions, and NOx emissions were significantly elevated for gasoline/gasoline–EHN operation. While combustion phasing could not be matched, UHC1 emissions were at a similar level as for gasoline/diesel combustion. It is expected that the implementation of different injection strategies and boosted operation, combined with use of higher compression ratio pistons in order to compensate for the lower reactivity direct injection (DI) fuel, could raise the potential for improved performance.

Download Full-text

Transient “Single-Fuel” RCCI Operation With Customized Pistons in a Light Duty Multi-Cylinder Engine

Volume 1: Large Bore Engines; Fuels; Advanced Combustion ◽

10.1115/icef2015-1051 ◽

2015 ◽

Cited By ~ 1

Author(s):

Christopher W. Gross ◽

Rolf D. Reitz

Keyword(s):

Steady State ◽

Compression Ratio ◽

Fuel Injection ◽

Pressure Rise ◽

Operating Conditions ◽

Maximum Pressure ◽

Engine Operation ◽

Volume Percentage ◽

Light Duty ◽

Brake Mean Effective Pressure

Reactivity Controlled Compression Ignition (RCCI) combustion in a light-duty multi-cylinder engine over transient operating conditions using fast response exhaust UHC1, NO and PM measurement instruments was investigated. RCCI has demonstrated improvements in efficiency along with low NOx and PM emissions by utilizing in-cylinder fuel blending, generally using two fuels with different reactivity in order to optimize stratification. In the present work, a “single-fuel” approach for RCCI combustion using port-injected gasoline and direct-injected gasoline mixed with a small amount of the cetane improver 2-ethylhexyl nitrate (EHN) was studied with custom designed, compression ratio of 13.75:1, pistons under transient conditions. The EHN volume percentage in the mixture for the direct-injected fuel was set at 3%. In an experimental investigation, comparisons were made to transient RCCI combustion operation with gasoline/diesel. The experiments were performed over a step load change from 1 to 4 bar brake mean effective pressure (BMEP) at constant 1,500 rev/min on a General Motors Z19DTH 1.9 liter diesel engine The transients were conducted by changing the accelerator pedal command to provide a desired torque output with a DRIVVEN engine control unit (ECU) that replaced the original Bosch ECU. All relevant engine parameters are adjusted accordingly, based on 2D-tables. Previous to the transient engine operation, 4 steady-state points were used to obtain performance and emission values. Engine calibration at these 4 points, as well as the interpolation of the intermediate points, allowed for smooth operation during the instantaneous step changes. Differences between the steady-state and transient results indicate the complexity of transient operation and show the need for additional controls to minimize undesirable effects. The steady-state points were calibrated by modifying the fuel injection strategy (actual Start of Injection (aSOI) timing, port-fuel injection (PFI) fraction, etc.), EGR and rail pressure in order to obtain predefined values for the crank angle at 50% of total heat release (CA50). Furthermore, emission targets (HC1 < 1500ppmC3, NO < 10ppm, FSN < 0.1 with a maximum pressure rise rate < 10bar/deg) and noise level targets (<95dB) for RCCI combustion were maintained during the calibration and mapping. The tests were performed with a closed-loop (CL) calibration by using a next-cycle (NC) controller to adjust the PFI ratio of each cycle in order to reach the steady-state CA50 values in the table. The results show that single-fuel RCCI operation can be achieved, but requires significant alteration of the operating conditions, and NOx emissions were significantly elevated for gasoline/gasoline-EHN operation. While combustion phasing could not be matched, UHC1 emissions were at a similar level as for gasoline/diesel combustion. It is expected that the implementation of different injection strategies and boosted operation, combined with use of higher compression ratio pistons in order to compensate for the lower reactivity direct injection (DI) fuel, could raise the potential for improved performance.

Download Full-text

Progress in developing a hybrid deep learning algorithm for identifying and locating primary vertices

EPJ Web of Conferences ◽

10.1051/epjconf/202125104012 ◽

2021 ◽

Vol 251 ◽

pp. 04012

Author(s):

Simon Akar ◽

Gowtham Atluri ◽

Thomas Boettcher ◽

Michael Peters ◽

Henry Schreiner ◽

...

Keyword(s):

Deep Learning ◽

High Efficiency ◽

Learning Algorithm ◽

Learning Model ◽

Operating Conditions ◽

Proton Collision ◽

Proton Proton ◽

Deep Learning Algorithm ◽

Proton Proton Collision ◽

Deep Learning Model

The locations of proton-proton collision points in LHC experiments are called primary vertices (PVs). Preliminary results of a hybrid deep learning algorithm for identifying and locating these, targeting the Run 3 incarnation of LHCb, have been described at conferences in 2019 and 2020. In the past year we have made significant progress in a variety of related areas. Using two newer Kernel Density Estimators (KDEs) as input feature sets improves the fidelity of the models, as does using full LHCb simulation rather than the “toy Monte Carlo” originally (and still) used to develop models. We have also built a deep learning model to calculate the KDEs from track information. Connecting a tracks-to-KDE model to a KDE-to-hists model used to find PVs provides a proof-of-concept that a single deep learning model can use track information to find PVs with high efficiency and high fidelity. We have studied a variety of models systematically to understand how variations in their architectures affect performance. While the studies reported here are specific to the LHCb geometry and operating conditions, the results suggest that the same approach could be used by the ATLAS and CMS experiments.

Download Full-text

Deep Learning Model Selection of Suboptimal Complexity

Автоматика и телемеханика ◽

10.31857/s000523100001252-1 ◽

2018 ◽

pp. 129-147

Author(s):

Oleg Bakhteev ◽

◽

Vadim Strijov ◽

Keyword(s):

Deep Learning ◽

Model Selection ◽

Learning Model ◽

Deep Learning Model ◽

Selection Of

Download Full-text

Improving Sentiment Analysis using Hybrid Deep Learning Model

Recent Advances in Computer Science and Communications ◽

10.2174/2213275912666190328200012 ◽

2020 ◽

Vol 13 (4) ◽

pp. 627-640 ◽

Cited By ~ 1

Author(s):

Avinash Chandra Pandey ◽

Dharmveer Singh Rajpoot

Keyword(s):

Neural Network ◽

Deep Learning ◽

Sentiment Analysis ◽

Classification Accuracy ◽

Short Term Memory ◽

Computational Cost ◽

Extraction Process ◽

Learning Model ◽

Sentiment Classification ◽

Deep Learning Model

Background: Sentiment analysis is a contextual mining of text which determines viewpoint of users with respect to some sentimental topics commonly present at social networking websites. Twitter is one of the social sites where people express their opinion about any topic in the form of tweets. These tweets can be examined using various sentiment classification methods to find the opinion of users. Traditional sentiment analysis methods use manually extracted features for opinion classification. The manual feature extraction process is a complicated task since it requires predefined sentiment lexicons. On the other hand, deep learning methods automatically extract relevant features from data hence; they provide better performance and richer representation competency than the traditional methods. Objective: The main aim of this paper is to enhance the sentiment classification accuracy and to reduce the computational cost. Method: To achieve the objective, a hybrid deep learning model, based on convolution neural network and bi-directional long-short term memory neural network has been introduced. Results: The proposed sentiment classification method achieves the highest accuracy for the most of the datasets. Further, from the statistical analysis efficacy of the proposed method has been validated. Conclusion: Sentiment classification accuracy can be improved by creating veracious hybrid models. Moreover, performance can also be enhanced by tuning the hyper parameters of deep leaning models.

Download Full-text