An investigation of engine performance parameters and artificial intelligent emission prediction of hydrogen powered car

With the depletion of fossil fuel resources and the potential consequences of climate change due to fossil fuel use, much effort has been put into the search for alternative fuels for transportation. Although there are several potential alternative fuels, which have low impact on the environment, none of these fuels have the ability to be used as the sole “fuel of the future”. One fuel which is likely to become a part of the over all solution to the transportation fuel dilemma is hydrogen. In this paper, The Toyota Corolla four cylinder, 1.8 l engine running on petrol is systematically converted to run on hydrogen. Several ancillary instruments for measuring various engine operating parameters and emissions are fitted to appraise the performance of the hydrogen car. The effect of hydrogen as a fuel compares with gasoline on engine operating parameters and effect of engine operating parameters on emission characteristics is discussed. Based on the experimental setup, a suite of neural network models were tested to accurately predict the effect of major engine operating conditions on the hydrogen car emissions. Predictions were found to be ±4% to the experimental values. This work provided better understanding of the effect of engine process parameters on emissions.     

Optimising multi-objective control methodology of a hydrogen powered car

This paper presents the optimising control technique for a Toyota Corolla four-cylinder, 1.8-L hydrogen powered car. Based on the extensive experimental tuning data, statistical two stage models and calibration generation methodology are carried out, in which ignition timing, injection timing, injection duration and corresponding lambda value (indicate air to fuel ratio) are chosen as control variables while engine output torque and exhaust NOx emissions are chosen as performance index functions. The trade-off study is employed to optimise performance of hydrogen engine by considering different optimisation objectives at different engine operating states. Those engine operating states are defined by the throttle position and opening speed of throttle, except start and idle load states that need the auxiliary control parameters to be added in. Each value of ignition advance, lambda, injection duration and injection end angle are tested and the hydrogen engine is found to have good drivability and reliable on road optimisation. This work is a step towards establishing optimising control methodology of hydrogen powered car via application of advanced power train techniques while saving time, money and limiting damage for innovative hydrogen engine in early experimental fine tuning process.     

Hydrogen powered car: Two-stage modelling system

This paper presents a research work on intelligent two-stage modelling system to estimate a hydrogen internal combustion engine performances including: engine torque and oxides of nitrogen emissions. In the created models, the ignition timing is chosen as a local input, while the engine speed, throttle position, injection duration, injection end angle and lambda are chosen as global inputs. While previous papers [1], [2], [3] and [4] included tuning procedures and hydrogen engine performances, intelligent emissions prediction of hydrogen car, and two-stage modelling of torque, this paper carries on from those observations to develop a completed two-stage modelling system of the converted hydrogen engine. More details on individual two-stage models are provided based on data recorded during the fine tuning process on dynamometer. This work is a step towards establishing intelligent two-stage modelling of hydrogen powered car via application of response surface methodology with hydrogen engine in the loop simulation and testing.     

Potential application of metal-organic frameworks (MOFs) for hydrogen storage: Simulation by artificial intelligent techniques

Metal-organic frameworks are a new class of materials for hydrogen adsorption/storage applications. The hydrogen storage capacity of this structure is typically related to pressure, temperature, surface area, and adsorption enthalpy. Literature provides no reliable correlation for estimating the hydrogen uptake capacity of MOFs from these easy-measured variables. Therefore, this study introduces several straightforward and accurate artificial intelligence (AI) techniques to fill this gap, initially determining the appropriate topology of AI-based methods, then comparing their performances by statistical criteria, and introducing the most accurate. This study used artificial neural networks, hybrid neuro-fuzzy systems, and support vector machines as estimators. The general regression neural networks (GRNN) with a spread of 7.92 × 10⁻⁴ shows the highest correlation with the literature data and provides a relative absolute deviation of 5.34%, mean squared error of 0.059, and coefficient of determination of 0.9946.     

Prediction of hydrogen safety parameters using intelligent techniques

With increase in the use and application of hydrogen for stationary and mobile applications, there is an increased pressure to ensure the safety handling and monitoring of this combustible gas. The associated equipment to monitor and measure explosion limit of any leakage together with the pressure and flow rate is very expensive. Any reliable mathematical or empirical means to estimate and predict those safety features of hydrogen will greatly assist in avoiding expensive instrumentation. In this paper predictive model for accurate estimation of hydrogen parameters such as percentage lower explosive limit, hydrogen pressure and hydrogen flow rate as a function of different input conditions of power supplied (voltage and current), the feed of de‐ionized water and various Hogen®20 electrolyser system parameters is carried out. In addition, the percentage contributions of the input parameters on each hydrogen production parameters and optimum network architecture to minimize computation time and maximize network accuracy are presented. It is shown that output from the neural network predictive models of the hydrogen safety features agree well with its experimentally measured values. The hydrogen production parameters and predicted safety explosive limit were found to be less than 5% of average root mean square error. Copyright © 2008 John Wiley & Sons, Ltd.     

Idle characteristics of a hydrogen fueled SI engine

This paper investigates the effect of the equivalence ratio Φ and ignition advance angle θ_i on idle characteristics of a turbocharged hydrogen fueled SI engine. The experimental data was conducted under various operating conditions including different Φ and θ_i. It is found that, the ignition advance angle at MBT point decreases gradually with the equivalence ratio increasing from 0.4 to 0.9. Indicated thermal efficiency decreases as Φ increases. Emissions of NOx increase as Φ increases. When Φ is kept constant, the stated emissions increase as θ_i increases. During idle conditions of a hydrogen fueled engine, a lean mixture with an Φ less than 0.4 is suitable, and the θ_i should be increased appropriately. The maximum cylinder pressure rises with an increase of Φ and θ_i. The trend of the maximum rate of pressure rise is similar at different Φ. Only under the conditions of Φ = 0.4 and θ_i < 10 °CA, the maximum pressure rise rate remains almost unchanged.     

An experimental study on performance and emission characteristics of a hydrogen fuelled spark ignition engine

In the present paper, the performance and emission characteristics of a conventional four cylinder spark ignition (SI) engine operated on hydrogen and gasoline are investigated experimentally. The compressed hydrogen at 20  MPa has been introduced to the engine adopted to operate on gaseous hydrogen by external mixing. Two regulators have been used to drop the pressure first to 300 kPa, then to atmospheric pressure. The variations of torque, power, brake thermal efficiency, brake mean effective pressure, exhaust gas temperature, and emissions of _NOx${\mathrm{NO}}_x$, CO, _CO2${\mathrm{CO}}_2$, HC, and _O2${\mathrm{O}}_2$ versus engine speed are compared for a carbureted SI engine operating on gasoline and hydrogen. Energy analysis also has studied for comparison purpose. The test results have been demonstrated that power loss occurs at low speed hydrogen operation whereas high speed characteristics compete well with gasoline operation. Fast burning characteristics of hydrogen have permitted high speed engine operation. Less heat loss has occurred for hydrogen than gasoline. _NOx${\mathrm{NO}}_x$ emission of hydrogen fuelled engine is about 10 times lower than gasoline fuelled engine. Finally, both first and second law efficiencies have improved with hydrogen fuelled engine compared to gasoline engine. It has been proved that hydrogen is a very good candidate as an engine fuel. The obtained data are also very useful for operational changes needed to optimize the hydrogen fueled SI engine design.     

The cycle life prediction of Mg-based hydrogen storage alloys by artificial neural network

Mg-based hydrogen storage alloys are a type of promising cathode material of Nickel-Metal Hydride (Ni-MH) batteries. But inferior cycle life is their major shortcoming. Many methods, such as element substitution, have been attempted to enhance its life. However, these methods usually require time-consuming charge–discharge cycle experiments to obtain a result. In this work, we suggested a cycle life prediction method of Mg-based hydrogen storage alloys based on artificial neural network, which can be used to predict its cycle life rapidly with high precision. As a result, the network can accurately estimate the normalized discharge capacities vs. cycles (after the fifth cycle) for Mg_0.8Ti_0.1M_0.1Ni (M = Ti, Al, Cr, etc.) and Mg_0.9 − xTi_0.1Pd_xNi (x = 0.04–0.1) alloys in the training and test process, respectively. The applicability of the model was further validated by estimating the cycle life of Mg_0.9Al_0.08Ce_0.02Ni alloys and Nd₅Mg₄₁–Ni composites. The predicted results agreed well with experimental values, which verified the applicability of the network model in the estimation of discharge cycle life of Mg-based hydrogen storage alloys.     

Application of artificial neural networks for the prediction of performance and exhaust emissions in SI engine using ethanol- gasoline blends

This study deals with artificial neural network (ANN) modeling of a spark ignition engine to predict the engine brake power, output torque and exhaust emissions (CO, CO₂, NO_x and HC) of the engine. To acquire data for training and testing of the proposed ANN, a four-cylinder, four-stroke test engine was fuelled with ethanol-gasoline blended fuels with various percentages of ethanol (0, 5, 10,15 and 20%), and operated at different engine speeds and loads. An ANN model based on standard back-propagation algorithm for the engine was developed using some of the experimental data for training. The performance of the ANN was validated by comparing the prediction dataset with the experimental results. Results showed that the ANN provided the best accuracy in modeling the emission indices with correlation coefficient equal to 0.98, 0.96, 0.90 and 0.71 for CO, CO₂, HC and NO_x, and 0.99 and 0.96 for torque and brake power respectively. Generally, the artificial neural network offers the advantage of being fast, accurate and reliable in the prediction or approximation affairs, especially when numerical and mathematical methods fail.     

State-of-charge prediction of batteries and battery-supercapacitor hybrids using artificial neural networks

The state-of-charge (SOC) of batteries and battery-supercapacitor hybrid systems is predicted using artificial neural networks (ANNs). Our technique is able to predict the SOC of energy storage devices based on a short initial segment (less than 4% of the average lifetime) of the discharge curve. The prediction shows good performance with a correlation coefficient above 0.95. We are able to improve the prediction further by considering readily available measurements of the device and usage. The prediction is further shown to be resilient to changes in operating conditions or physical structure of the devices.     

Effect of excess hydrogen on hydrogen fueled internal combustion engine under full load

Detailed hydrogen-air chemical reaction mechanisms were coupled with three dimension grids of an experimental hydrogen fueled internal combustion engine (HICE) to establish a combustion model based on CONVERGE software. The influence of excess hydrogen coefficient on the combustion and emission characteristics of HICE under full load was studied based on the CFD model. Simulation results showed that excess hydrogen leaded to higher concentration of OH species in flame front, and quicker hydrogen-oxygen reaction and flame propagation speed, which in turn leaded to higher pressure and temperature in cylinder. The rise of pressure and temperature in turn contributed to the increase of indicate power but un-burned hydrogen leaded to decrease of efficiency. NOx, especially NO emissions decreased significantly with excess hydrogen under full load not only because increased of H concentration, and decreased of O and OH concentration, which leaded to reverse reaction of NO formation through thermal NO routes. Low excess hydrogen coefficient can achieve a good trade-off between power and emissions under full load.     

Drive cycle simulation of light duty mild hybrid vehicles powered by hydrogen engine

In the ongoing efforts to reduce CO2 and pollutant emissions, hydrogen combustion engine can provide immediately available mature technology for carbon-free transportation. Hydrogen combustion does not produce on-site CO2 emissions, the principal pollutant is NOx (which can be minimized using appropriate combustion control and aftertreatment), and the available ICE technology can be readily modified to accommodate for hydrogen use. The paper provides a prediction of the performance of a hydrogen combustion engine in passenger vehicles, aiming at extending or updating the available research with the current powertrain trends, namely downsizing, turbocharging, and hybridization. Data gathered from a single-cylinder engine fueled by a lean hydrogen mixture are used as input into a mild hybrid vehicle model, which is used for quasi-static drive cycle simulations. The results show NOx emission around the EURO VI limit without the use of any aftertreatment and fuel consumption as low as 1.1 kgH2/100 km in WLTC.     

Prediction of hydrogen production by magnetic field effect water electrolysis using artificial neural network predictive models

Developing an efficient water electrolysis (WE) configuration is essential for high-efficiency hydrogen evolution reaction (HER) activity. In this regard, it has been proven that adding a magnetic field (MF) to the electrolysis system greatly improves the hydrogen output rate. In this study, we developed a method based on a machine learning approach to further improve the hydrogen production (HP) system with MF effect WE. An artificial neural network (ANN) model was developed to estimate the effect of input parameters such as MF, electrode material (cathode type), electrolyte type, supplied power (onset voltage), surface area, temperature, and time on HP in different electrolyzer systems. The network was built using 104 experimental data sets from various electrolysis studies. In the study, the percentage contributions of the input parameters to the HP rate and the optimum network architecture to minimize computation time and maximize network accuracy are presented. The model architecture of 7–12–1 was obtained using the best-hidden neurons. The Levenberg-Marquardt (LM) algorithm was used to train the multi-layer feed-forward neural network. Moreover, the utilization of a range of categorical variables to improve ANN prediction accuracy is a significant novelty in this work. Results demonstrated that the output of the trained ANN model fitted well with the experimental data. The test's correlation coefficient (R) and mean squared error (MSE) were 0.973 and 0.01125, respectively, confirming its powerful predictive performance. This ANN application is the first novel viable model to perform prediction using a neural network algorithm in the electrolysis process for MF effect HP using both categorical and continuous data inputs.     

Exhaust emissions control and engine parameters optimization using artificial neural network virtual sensors for a hydrogen-powered vehicle

This paper presents an alternative tool for vehicle tuning applications by incorporating the use of artificial neural network (ANN) virtual sensors for a hydrogen-powered car. The objective of this study is to optimize simple engine process parameters to regulate the exhaust emissions. The engine process parameters (throttle position, lambda, ignition advance and injection angle) and the exhaust emission variables (CO, CO₂, HC and NO_x) form the basis of the virtual sensors. Experimental data were first obtained through a comprehensive experimental and tuning procedure for neural network training and validation. The optimization layer-by-layer neural network was used to construct two ANN virtual sensors; the engine and emissions models. The performance and accuracy of the proposed virtual sensors were found to be acceptable with the maximum predictive mean relative errors of 0.65%. With its accurate predictive capability, the virtual sensors were then employed and simulated as a measurement tool for vehicle tuning and optimization. Simulation results showed that the exhaust emissions can be regulated by optimizing simple engine process parameters. This study presents an alternative tool for vehicle tuning applications for a hydrogen-powered vehicle. In addition, this work also provided a tool to better understand the effects of various engine conditions on the exhaust emissions without the need for any vehicle modifications.     

Design and implementation of hydrogen economy using artificial neural network on field programmable gate array

In this study, economic analysis of the hydrogen generation and liquefaction system has been modeled using Multi-Layer Feed-Forward Artificial Neural Network (MLFFANN) and implemented on Field Programmable Gate Array (FPGA). Firstly, the 100X6 data set has been created to be used in the ANN-based modeling of the system using the Engineering Equation Solver (EES) program. This data set has been divided into two data sets as 80X6 for training and 20X6 for testing. The structure of the ANN-based economic analysis of hydrogen generation and liquefaction has been composed of 3 neurons in the input layer, ten neurons in the hidden layer, and three neurons in the output layer. Elliott-2-based TanSig transfer function and Purelin transfer function have been used in the neurons of the hidden layer and the output layer, respectively. Then, the ANN-model has been trained and tested using the Matlab program. The MSE values, 1.40x10E-7 and 2.07x10E-5, have been obtained as the results of the training phase and test phase of the ANN-based system, respectively. After getting fruitful results from training and testing phases, the economic analyses of hydrogen generation and liquation systems have been modeled in VHDL using bias and weight values located in the constructed ANN-based system using Matlab. The modeling has been performed in the Xilinx ISE Design Tools program using a 32-bit IEEE-754-1985 floating-point number standard. Then, the modeled ANN-based economic analysis of the hydrogen generation and liquation system has been implemented on the Xilinx Virtex-7 FPGA chip by performing the Place&Route process. The maximum operating frequency of the ANN-based hydrogen generation and liquefaction economy system implemented on FPGA has been obtained as 281.702 MHz using Xilinx ISE Design Tools.     

Performance prediction of a direct expansion solar assisted heat pump using artificial neural networks

This paper presents the suitability of artificial neural network (ANN) to predict the performance of a direct expansion solar assisted heat pump (DXSAHP). The experiments were performed under the meteorological conditions of Calicut city (latitude of 11.15 °N, longitude of 75.49 °E) in India. The performance parameters such as power consumption, heating capacity, energy performance ratio and compressor discharge temperature of a DXSAHP obtained from the experimentation at different solar intensities and ambient temperatures are used as training data for the network. The back propagation learning algorithm with three different variants (such as, Lavenberg–Marguardt (LM), scaled conjugate gradient (SCG) and Pola-Ribiere conjugate gradient (CGP)) and logistic sigmoid transfer function were used in the network. The results showed that LM with 10 neurons in the hidden layer is the most suitable algorithm with maximum correlation coefficients (R²) of 0.999, minimum root mean square (RMS) value and low coefficient of variance (COV). The reported results conformed that the use of ANN for performance prediction of DXSAHP is acceptable.     

Performance and exhaust emissions of a gasoline engine with ethanol blended gasoline fuels using artificial neural network

The purpose of this study is to experimentally analyse the performance and the pollutant emissions of a four-stroke SI engine operating on ethanol–gasoline blends of 0%, 5%, 10%, 15% and 20% with the aid of artificial neural network (ANN). The properties of bioethanol were measured based on American Society for Testing and Materials (ASTM) standards. The experimental results revealed that using ethanol–gasoline blended fuels increased the power and torque output of the engine marginally. For ethanol blends it was found that the brake specific fuel consumption (bsfc) was decreased while the brake thermal efficiency (η_b.th.) and the volumetric efficiency (η_v) were increased. The concentration of CO and HC emissions in the exhaust pipe were measured and found to be decreased when ethanol blends were introduced. This was due to the high oxygen percentage in the ethanol. In contrast, the concentration of CO₂ and NO_x was found to be increased when ethanol is introduced. An ANN model was developed to predict a correlation between brake power, torque, brake specific fuel consumption, brake thermal efficiency, volumetric efficiency and emission components using different gasoline–ethanol blends and speeds as inputs data. About 70% of the total experimental data were used for training purposes, while the 30% were used for testing. A standard Back-Propagation algorithm for the engine was used in this model. A multi layer perception network (MLP) was used for nonlinear mapping between the input and the output parameters. It was observed that the ANN model can predict engine performance and exhaust emissions with correlation coefficient (R) in the range of 0.97–1. Mean relative errors (MRE) values were in the range of 0.46–5.57%, while root mean square errors (RMSE) were found to be very low. This study demonstrates that ANN approach can be used to accurately predict the SI engine performance and emissions.     

Artificial Neural Network modeling of a hydrogen dual fueled diesel engine characteristics: An experiment approach

The rapid growth of vehicular pollution; mostly running on the diesel engine, emissions emerging are the concerns of the day. Owing to clean burn characteristics features, Hydrogen (H₂) as a fuel is the paradigm of the researcher. Extensive research presented in the literature on H₂ dual fueled diesel engine reveals, the significant role of H₂ in reducing emissions and enhancing the performance of a dual fueled diesel engine. With meager qualitative experiment data, the feasibility to develop an efficient Artificial Neural Network (ANN) model is investigated, the developed model can be utilized as a tool to investigate the H₂ dual fueled diesel engine further. In the process of developing an ANN model, engine load and H₂ flow rate are varied to register performance and emission characteristics. The creditability of the experiment is ascertained with uncertainty analysis of measurable and computed parameters. Leave-out-one method is adopted with 16 data sets; seven training algorithms are explored with eight transfer function combinations to evolve a competent ANN model. The efficacy of the developed model is adjudged with standard benchmark statistic indices. ANN model trained with Broyden, Fletcher, Goldfarb, & Shanno (BFGS) quasi-Newton backpropagation (trainbfg) stand out the best among other algorithms with regression coefficient ranging between 0.9869 and 0.9996.     

Research of performance and emission indicators of the compression-ignition engine powered by hydrogen - Diesel mixtures

The purpose of this study is to use the hydrogen – diesel mixture in Audi/VW 1.9 TDI turbocharged CI engine equipped with dynamometer and examine the performance and emission indicators by comparing it with sole diesel mode. The recent diesel emission scandals because of manufacturers cheating the laboratory tests, have initiated the discussions about the sustainable and environmentally friendly diesel engines. The CI engine without major engine modifications was set to operate at two speeds of 1900 rpm and 2500 rpm. At each of speed, the experiment was conducted at three BMEP: 0.4 MPa, 0.6 MPa, and 0.8 MPa. The test engine was operated using diesel fuel with amounts of 10 l/min, 20 l/min, and 30 l/min of hydrogen gas, supplied with air into intake manifold before the turbocharger. Relatively low hydrogen fraction (max. 15.74%) has effect on diesel combustion process and performance indicators at the all range of BMEP. The in-cylinder peak pressure at both speeds of 1900 rpm and 2500 rpm was lower than that with pure diesel fuel, as the small amount of hydrogen shortens the CI engine ignition delay period and decreases the rate of pressure rise. The decrease of BTE noticed, and increase of BSFC was registered with low hydrogen fraction (hydrogen amounts of 10 l/min, 20 l/min). However, with increase of hydrogen amount to 30 l/min, the BTE increased and BSFC decreased to the level, which was lower than that at the pure diesel test. The supply of hydrogen positively effects on engine emissions: the smokiness, NO_x, CO₂, CO decreased, the only hydrocarbon increased. The effect of hydrogen fraction on the combustion and emission characteristics of the diesel - hydrogen mixture was validated by AVL (Anstalt für Verbrennungskraftmaschinen List) BOOST and analysed with presentations of the main limitations and perspectives.