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.     

Hybrid boosting algorithms and artificial neural network for wind speed prediction

Energy sources are an important foundation for national economic growth. The future of energy sources depend on the energy controls. The reserves of fossil energy have declined significantly, and environmental pollution has increased dramatically due to excessive fossil fuel consumption. At this point, wind energy can be used as one of the key source of renewable energy. It has a remarkable importance among the low-carbon energy technologies. The primary aim of wind energy production is to reduce dependence on fossil fuels that affect environment adversely. Therefore, wind energy is analyzed to develop new energy resources. The main issue related to evaluation of the wind energy potential is wind speed prediction. Due to the high volatile and irregular nature of wind speed, wind speed prediction is difficult. To cope with complex data structure, this study presents the development of extreme gradient boosting (XGBoost), adaptive boosting (AdaBoost), and artificial neural network (ANN) within particle swarm optimization (PSO) parameter optimization for hourly wind speed prediction. To compare the proposed hybrid methods, various performance measures, the Pearson's test, and the Taylor diagram are used. The results showed that proposed hybrid methods provide reasonable prediction results for wind speed prediction.     

Experimental study for predicting the specific heat of water based Cu-Al2O3 hybrid nanofluid using artificial neural network and proposing new correlation

In this study, an artificial neural network model has been created in order to estimate the specific heat of Cu-Al₂O₃/water hybrid nanofluid based on temperature (T) and volume concentration (φ). Specific heat values of the Cu-Al₂O₃/water hybrid nanofluid prepared in five-volume concentration were measured experimentally in the 20°C to 65°C temperature range. The dataset was reserved into three primary parts, with the inclusion of 901 (70%) for the training, 257 (20%) for the test and 129 (10%) for the validation. As a result of comparison with experimental values, it is concluded that this model predicts specific heat with R-value of 0.99994 and an average relative error of approximately 5.84e-9. In addition, a mathematical correlation has been developed to estimate the specific heat of the Cu-Al₂O₃/water hybrid nanofluid. The data acquired from the mathematical correlation, developed, were in great correlation with all the experimental values with an average deviation of −0.005%. This result has revealed that the developed mathematical correlation is an ideal design for estimating the specific heat of the Cu-Al₂O₃/water hybrid nanofluid.     

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.     

Modelling of a cascade refrigeration system using artificial neural network

This study investigates the applicability of artificial neural networks (ANNs) to predict various performance parameters of a cascade vapour compression refrigeration system. For this aim, an experimental cascade system was set up and tested in steady‐state operating conditions. Then, utilizing some of the experimental data for training, an ANN model for the system based on the standard back propagation algorithm was developed. The ANN was used for predicting the evaporating temperature in the lower‐temperature circuit, compressor power for the lower and higher circuits and coefficients of performance for both the lower circuit and the overall cascade system. Afterwards, the performances of the ANN predictions were tested using new experimental data. The ANN predictions usually agreed well with the experimental results with correlation coefficients in the range of 0.953–0.996 and mean relative errors in the range of 0.2–6.0%. Furthermore, the ANN yielded acceptable predictions for the system performance outside the range of the experiments. The results suggest that the ANN approach can alternatively and reliably be used for modelling cascade refrigeration systems. Copyright © 2006 John Wiley & Sons, Ltd.     

CNG-diesel engine performance and exhaust emission analysis with the aid of artificial neural network

This study investigates the use of artificial neural network (ANN) modelling to predict brake power, torque, break specific fuel consumption (BSFC), and exhaust emissions of a diesel engine modified to operate with a combination of both compressed natural gas CNG and diesel fuels. A single cylinder, four-stroke diesel engine was modified for the present work and was operated at different engine loads and speeds. The experimental results reveal that the mixtures of CNG and diesel fuel provided better engine performance and improved the emission characteristics compared with the pure diesel fuel. For the ANN modelling, the standard back-propagation algorithm was found to be the optimum choice for training the model. A multi-layer perception network was used for non-linear mapping between the input and output parameters. It was found that the ANN model is able to predict the engine performance and exhaust emissions with a correlation coefficient of 0.9884, 0.9838, 0.95707, and 0.9934 for the engine torque, BSFC, NO_x and exhaust temperature, respectively.     

Performance comparison of CFCs with their substitutes using artificial neural network

In order to decrease global pollution due to chlorofluorocarbons (CFCs), the usage of HFC‐ and HC‐based refrigerants and their mixtures are considered instead of CFCs (R12, R22, and R502). This was confirmed by an international consensus (i.e. Montreal Protocol signed in 1987). This paper offers to determine coefficient of performance (COP) and total irreversibility (TI) values of vapour‐compression refrigeration system with different refrigerants and their mixtures mentioned above using artificial neural networks (ANN). In order to train the network, COPs and TIs of refrigerants and their some binary, ternary and quartet mixtures of different ratios have been calculated in a vapour‐compression refrigeration system with liquid/suction line heat exchanger. In the calculations thermodynamic properties of refrigerants have been taken from REFPROP 6.01 which was prepared based on Helmholtz energy equation of state. To achieve this, a new software has been written in FORTRAN programming language using sub‐programs of REFPROP, and all related calculations have been performed using this software using constant temperature method as reference. Scaled conjugate gradient, Pola–Ribiere conjugate gradient, and Levenberg–Marquardt learning algorithms and logistic sigmoid transfer function were used in the network. Mixing ratios of refrigerants, and evaporator temperature were used as input layer; COP and TI values were used as output layer. It is shown that R² values are about 0.9999, maximum errors for training and test data are smaller than 2 and 3%, respectively. It is concluded that, ANNs can be used for prediction of COP and TI as an accurate method in the systems. Copyright © 2004 John Wiley & Sons, Ltd.     

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.     

The prediction of convective heat transfer in floor-heating systems by artificial neural networks

In this study the floor Nusselt and Rayleigh numbers for the floor-heating systems are estimated by the artificial neural networks (ANN). Numerical data for the floor Nusselt and Rayleigh numbers are available in the literature. A piece of the numerical values are used for training the ANN. The values estimated by the ANN are compared with the numerical values and the results of an equation given in the literature. It has been seen that the results of the ANN are very close to the numerical data and the results of the equation.     

Modeling the effect of non-linear process parameters on the prediction of hydrogen production by steam reforming of bio-oil and glycerol using artificial neural network

Biomass-derived substrates such as bio-oil and glycerol are gaining wide acceptability as feedstocks to produce hydrogen using a steam reforming process. The wide acceptability can be attributed to a huge amount of glycerol and bio-oil obtained as by-products of biodiesel production and pyrolysis processes. Several parameters have been reported to affect the production of hydrogen by biomass steam reforming. This study investigates the effect of non-linear process parameters on the prediction of hydrogen production by biomass (bio-oil and glycerol) steam reforming using artificial neural network (ANN) modeling technique. Twenty different multilayer ANN model architectures were tested using datasets obtained from the bio-oil and glycerol steam reforming. Two algorithms namely Levenberg-Marquardt and Bayesian regularization were employed for the training of the ANNs. An optimized network configuration consisting of 3 input layer 14 hidden neurons, 1 output layer, and 3 input layer, 5 hidden neurons, and 1 output layer were obtained for the Levenberg-Marquardt and Bayesian regularization trained network, respectively for hydrogen production by bio-oil steam reforming. While an optimized network configuration consisting of 5 input nodes, 9 hidden neurons, 1 output node, and 5 input nodes, 8 hidden neurons, and 1 output node were obtained for Levenberg-Marquardt and Bayesian regularization trained network, respectively for hydrogen production by glycerol steam reforming. Based on the optimized network, the predicted hydrogen production from the bio-oil and glycerol steam agreed with the actual values with the coefficient of determination (R²) > 0.9. A low mean square error of 3.024 × 10⁻²⁴ and 6.22 × 10⁻¹⁵ for the optimized for Levenberg-Marquardt and Bayesian regularization-trained ANN, respectively. The neural network analyses of the two processes showed that reaction temperature and glycerol-to-water molar ratio were the most relevant factors that influenced the production of hydrogen by bio-oil and glycerol steam reforming, respectively. This study has demonstrated the robustness of the ANN as a technique for investigating the effect of non-linear process parameters on hydrogen production by bio-oil and glycerol steam reforming.     

应用人工神经网络处理HVAC非线性计算

介绍了将人工神经网络用于计算人体热感觉的PMV指标和绘制焓湿图。根据有关数据显示利用神经网络的计算值与实际值相吻合 ,说明神经网络是一种新颖、可靠的HVAC非线性计算方法。其结构在HVAC非线性实时控制中优势显著     

Optimal operation conditions for a single-stage heat transformer by means of an artificial neural network inverse

Analysis based on first and second law of thermodynamics together with direct and artificial neural networks inverse (ANNi) have been used to develop a methodology to decrease the total irreversibility of an experimental single-stage heat transformer. With the proposed methodology it is possible to calculate the optimal input parameters that should be used in order to operate the heat transformer with the lower irreversibilities. Mathematical validation of ANNi was carried out together with the comparison between the total cycle irreversibility (I_cycle) obtained thermodynamically and the I_cycle determined by using the ANNi. The results showed a mean discrepancy of 0.9% of the I_cycle values. The proposed new methodology can be very useful to control on-line the performance of a single-state heat transformer obtaining lower I_cycle values.     

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.     

A novel application of artificial neural network for wind speed estimation

Providing accurate multi-steps wind speed estimation models has increasing significance, because of the important technical and economic impacts of wind speed on power grid security and environment benefits. In this study, the combined strategies for wind speed forecasting are proposed based on an intelligent data processing system using artificial neural network (ANN). Generalized regression neural network and Elman neural network are employed to form two hybrid models. The approach employs one of ANN to model the samples achieving data denoising and assimilation and apply the other to predict wind speed using the pre-processed samples. The proposed method is demonstrated in terms of the predicting improvements of the hybrid models compared with single ANN and the typical forecasting method. To give sufficient cases for the study, four observation sites with monthly average wind speed of four given years in Western China were used to test the models. Multiple evaluation methods demonstrated that the proposed method provides a promising alternative technique in monthly average wind speed estimation.     

Application of artificial neural network in performance prediction of PEM fuel cell

Investigations on using artificial neural networks to predict the performance of single proton exchange membrane fuel cell has been carried out. Two sets of polarization data obtained at different temperatures and flow rates are used to create and simulate the network. Cell temperature, humidification temperatures, H₂/air flow rates and current density have been used as inputs, and voltage is used as observed (output) value to train and simulate the network. This nonlinear data are batch trained, and artificial neural network has been constructed using feed forward backpropagation algorithm. Performance of the training has been improved by increasing the number of neurons to reduce the error. Simulation results are in agreement with experimental data, and the corresponding networks are used to predict the polarization behavior for unknown inputs. Copyright © 2011 John Wiley & Sons, Ltd.     

Greek long-term energy consumption prediction using artificial neural networks

In this paper artificial neural networks (ANN) are addressed in order the Greek long-term energy consumption to be predicted. The multilayer perceptron model (MLP) has been used for this purpose by testing several possible architectures in order to be selected the one with the best generalizing ability. Actual recorded input and output data that influence long-term energy consumption were used in the training, validation and testing process. The developed ANN model is used for the prediction of 2005–2008, 2010, 2012 and 2015 Greek energy consumption. The produced ANN results for years 2005–2008 were compared with the results produced by a linear regression method, a support vector machine method and with real energy consumption records showing a great accuracy. The proposed approach can be useful in the effective implementation of energy policies, since accurate predictions of energy consumption affect the capital investment, the environmental quality, the revenue analysis, the market research management, while conserve at the same time the supply security. Furthermore it constitutes an accurate tool for the Greek long-term energy consumption prediction problem, which up today has not been faced effectively.     

Prediction of performance,combustion and emission characteristics of diesel-thermal cracked cashew nut shell liquid blends using artificial neural network

This paper explores the use of artificial neural networks (ANN) to predict performance, combustion and emissions of a single cylinder, four stroke stationary, diesel engine operated by thermal cracked cashew nut shell liquid (TC-CNSL) as the biodiesel blended with diesel. The tests were performed at three different injection timings (21°, 23°, 25°CA bTDC) by changing the thickness of the advance shim. The ANN was used to predict eight different engine-output responses, namely brake thermal efficiency (BTE), brake specific fuel consumption (BSFC), exhaust gas temperature (EGT), carbon monoxide (CO), oxide of nitrogen (NO _x ), hydrocarbon (HC), maximum pressure (P _max) and heat release rate (HRR). Four pertinent engine operating parameters, i.e., injection timing (IT), injection pressure (IP), blend percentage and pecentage load were used as the input parameters for this modeling work. The ANN results show that there is a good correlation between the ANN predicted values and the experimental values for various engine performances, combustion parameters and exhaust emission characteristics. The mean square error value (MSE) is 0.005621 and the regression value of R ² is 0.99316 for training, 0.98812 for validation, 0.9841 for testing while the overall value is 0.99173. Thus the developed ANN model is fairly powerful for predicting the performance, combustion and exhaust emissions of internal combustion engines.     

Artificial intelligence-based model prediction of biodiesel-fueled engine performance and emission characteristics: A comparative evaluation of gene expression programming and artificial neural network

The prognostic capability of gene expression programming (GEP) and artificial neural network (ANN) are compared to estimate the engine performance and emission characteristics. A stationary diesel engine was powered with linseed oil biodiesel-mineral diesel blends. A total of 60 lab-based test-run were conducted by varying the engine input operating conditions, namely fuel injection parameters, diesel/biodiesel blending ratio, and engine load. The engine output data, namely brake thermal efficiency and brake-specific fuel consumption, were calculated, while emission data for oxides of nitrogen, carbon monoxide, and unburnt hydrocarbon, were recorded. The experimental data were used for predictive model development using artificial intelligence-based GEP and ANN techniques. The developed models were tested on statistical outcomes, such as the absolute fraction of variance (0.9698–0.997 for GEP and 0.9949–0.9998 for ANN), correlation coefficient (0.9848–0.998 for GEP and 0.9974–0.9998 for ANN), establishing these two models as an efficient machine identical tool. Also, Nash–Sutcliffe efficiency (0.937–0.9999 for GEP and 0.995–0.999 for ANN) and Kling–Gupta efficiency (0.834–0.9999 for GEP and 0.989–0.999 for ANN) elevate the prediction quality of developed models. The result showed that the ANN model was slightly more accurate than the GEP-based model for the same parametric range.     

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.