ANN based simulation and experimental verification of analytical four- and five-parameters models of PV modules

In this article, artificial neural network (ANN) is adopted to predict photovoltaic (PV) panel behaviors under realistic weather conditions. ANN results are compared with analytical four and five parameter models of PV module. The inputs of the models are the daily total irradiation, air temperature and module voltage, while the outputs are the current and power generated by the panel. Analytical models of PV modules, based on the manufacturer datasheet values, are simulated through Matlab/Simulink environment. Multilayer perceptron is used to predict the operating current and power of the PV module. The best network configuration to predict panel current had a 3–7–4–1 topology. So, this two hidden layer topology was selected as the best model for predicting panel current with similar conditions. Results obtained from the PV module simulation and the optimal ANN model has been validated experimentally. Results showed that ANN model provide a better prediction of the current and power of the PV module than the analytical models. The coefficient of determination (R²), mean square error (MSE) and the mean absolute percentage error (MAPE) values for the optimal ANN model were 0.971, 0.002 and 0.107, respectively. A comparative study among ANN and analytical models was also carried out. Among the analytical models, the five-parameter model, with MAPE = 0.112, MSE = 0.0026 and R² = 0.919, gave better prediction than the four-parameter model (with MAPE = 0.152, MSE = 0.0052 and R² = 0.905). Overall, the 3–7–4–1 ANN model outperformed four-parameter model, and was marginally better than the five-parameter model.     

Engine performance and optimum injection timing for 4-cylinder direct injection hydrogen fueled engine

This paper presents the engine performance and optimum injection timing for 4-cylinder direct injection hydrogen fueled engine. The 4-cylinder direct injection hydrogen engine model was developed utilizing the GT-Power commercial software. This model employed one dimensional gas dynamics to represent the flow and heat transfer in the components of engine model. Sequential pulse injectors are adopted to inject hydrogen gas fuel within the compression stroke. Injection timing was varied from 110° before top dead center (BTDC) until top dead center (TDC) timing. Engine speed was varied from 2000 rpm to 6000 rpm, while the equivalence ratio was varied from 0.2 to 1.0. The validation was performed with the existing previous experimental results. The negative effects of the interaction between ignition timing and injection duration was highlighted and clarified. The results showed that optimum injection timing and engine performance are related strongly to the air fuel ratio and engine speed. The acquired results show that the air fuel ratio and engine speed are strongly influence on the optimum injection timing and engine performance. It can be seen that the indicated efficiency increases with increases of AFR while decreases of engine speed. The power and torque increases with the decreases of AFR and engine speed. The indicated specific fuel consumption (ISFC) decreases with increases of AFR from rich conditions to lean while decreases of engine speed. The injection timing of 60° BTDC was the overall optimum injection timing with a compromise.     

Piezoelectric fuel injection: Cycle-to-cycle control of tightly spaced injections

Piezoelectric fuel injectors will require closed-loop control to realize tightly spaced injections. This paper describes an estimation algorithm for cycle-to-cycle determination of an injection flow profile for use as feedback for closed-loop control. A control design-amenable, 2-pulse approximate model is outlined to represent the dynamics of simultaneously controlling the quantity of, and realized dwell time between, injection pulses. A control law is developed to provide an overdamped response of realized dwell time to prevent pulse bleeding. Closed-loop performance is validated with the experimental data. Desired fuel quantity, and very short dwell times of 0.0002 s (two crank angle degrees at 1800 RPM), are realized with tracking error convergence time constants of approximately four engine cycles (0.27 s at 1800 RPM).     

Prediction and reduction of diesel engine emissions using a combined ANN–ACO method

In this study, the combination of artificial neural network (ANN) and ant colony optimization (ACO) algorithm has been utilized for modeling and reducing NO_x and soot emissions from a direct injection diesel engine. A feed-forward multi-layer perceptron (MLP) network is used to represent the relationship between the input parameters (i.e., engine speed, intake air temperature, rate of fuel mass injected, and power) on the one hand and the output parameters (i.e., NO_x and soot emissions) on the other hand. The ACO algorithm is employed to find the optimum air intake temperatures and the rates of fuel mass injected for different engine speeds and powers with the purpose of simultaneous reduction of NO_x and soot. The obtained results reveal that the ANN can appropriately model the exhaust NO_x and soot emissions with the correlation factors of 0.98, 0.96, respectively. Further, the employed ACO algorithm gives rise to 32% and 7% reduction in the NO_x and soot, respectively. The response time of the optimization process was obtained to be less than 4 min for the particular PC system used in the present work. The high accuracy and speed of the model show its potential for application in intelligent controlling systems of the diesel engines.     

Aviation emission inventory development and analysis

An up to date and accurate aviation emission inventory is a prerequisite for any detailed analysis of aviation emission impact on greenhouse gases and local air quality around airports. In this paper we present an aviation emission inventory using real time air traffic trajectory data. The reported inventory is in the form of a 4D database which provides resolution of 1° × 1° × 1000 ft for temporal and spatial emission analysis. The inventory is for an ongoing period of six months starting from October 2008 for Australian Airspace.In this study we show 6 months of data, with 492,936 flights (inbound, outbound and over flying). These flights used about 2515.83 kt of fuel and emitted 114.59 kt of HC, 200.95 kt of CO, 45.92 kt of NO_x, 7929.89 kt of CO₂, and 2.11 kt of SO_x. From the spatial analysis of emissions data, we found that the CO₂ concentration in some parts of Australia is much higher than other parts, especially in some major cities. The emission results also show that NO_x emission of aviation may have a significant impact on the ozone layer in the upper troposphere, but not in the stratosphere.It is expected that with the availability of this real time aviation emission database, environmental analysts and aviation experts will have an indispensable source of information for making timely decisions regarding expansion of runways, building new airports, applying route charges based on environmentally congested airways, and restructuring air traffic flow to achieve sustainable air traffic growth.     

Investigation of pollution flashover on high voltage insulators using artificial neural network

High voltage insulators form an essential part of the high voltage electric power transmission systems. Any failure in the satisfactory performance of high voltage insulators will result in considerable loss of capital, as there are numerous industries that depend upon the availability of an uninterrupted power supply. The importance of the research on insulator pollution has been increased considerably with the rise of the voltage of transmission lines. In order to determine the flashover behavior of polluted high voltage insulators and to identify to physical mechanisms that govern this phenomenon, the researchers have been brought to establish a modeling. Artificial neural networks (ANN) have been used by various researches for modeling and predictions in the field of energy engineering systems. In this study, model of V_C = f (H, D, L, σ, n, d) based on ANN which compute flashover voltage of the insulators were performed. This model consider height (H), diameter (D), total leakage length (L), surface conductivity (σ) and number of shed (d) of an insulator and number of chain (n) on the insulator.     

Modelling of residual stresses in the shot peened material C-1020 by artificial neural network

This study consists of two cases: (i) The experimental analysis: Shot peening is a method to improve the resistance of metal pieces to fatigue by creating regions of residual stress. In this study, the residual stresses induced in steel specimen type C-1020 by applying various strengths of shot peening, are investigated using the electrochemical layer removal method. The best result is obtained using 0.26 mm A peening strength and the stress encountered in the shot peened material is ?276 MPa, while the maximum residual stress obtained is ?363 MPa at a peening strength of 0.43 mm A. (ii) The mathematical modelling analysis: The use of ANN has been proposed to determine the residual stresses based on various strengths of shot peening using results of experimental analysis. The back-propagation learning algorithm with two different variants and logistic sigmoid transfer function were used in the network. In order to train the neural network, limited experimental measurements were used as training and test data. The best fitting training data set was obtained with four neurons in the hidden layer, which made it possible to predict residual stress with accuracy at least as good as that of the experimental error, over the whole experimental range. After training, it was found the R² values are 0.996112 and 0.99896 for annealed before peening and shot peened only, respectively. Similarly, these values for testing data are 0.995858 and 0.999143, respectively. As seen from the results of mathematical modelling, the calculated residual stresses are obviously within acceptable uncertainties.     

Speech emotion recognition: Features and classification models

To solve the speaker independent emotion recognition problem, a three-level speech emotion recognition model is proposed to classify six speech emotions, including sadness, anger, surprise, fear, happiness and disgust from coarse to fine. For each level, appropriate features are selected from 288 candidates by using Fisher rate which is also regarded as input parameter for Support Vector Machine (SVM). In order to evaluate the proposed system, principal component analysis (PCA) for dimension reduction and artificial neural network (ANN) for classification are adopted to design four comparative experiments, including Fisher + SVM, PCA + SVM, Fisher + ANN, PCA + ANN. The experimental results proved that Fisher is better than PCA for dimension reduction, and SVM is more expansible than ANN for speaker independent speech emotion recognition. The average recognition rates for each level are 86.5%, 68.5% and 50.2% respectively.     

Precipitation forecasting by using wavelet-support vector machine conjunction model

A new wavelet-support vector machine conjunction model for daily precipitation forecast is proposed in this study. The conjunction method combining two methods, discrete wavelet transform and support vector machine, is compared with the single support vector machine for one-day-ahead precipitation forecasting. Daily precipitation data from Izmir and Afyon stations in Turkey are used in the study. The root mean square errors (RMSE), mean absolute errors (MAE), and correlation coefficient (R) statistics are used for the comparing criteria. The comparison results indicate that the conjunction method could increase the forecast accuracy and perform better than the single support vector machine. For the Izmir and Afyon stations, it is found that the conjunction models with RMSE=46.5 mm, MAE=13.6 mm, R=0.782 and RMSE=21.4 mm, MAE=9.0 mm, R=0.815 in test period is superior in forecasting daily precipitations than the best accurate support vector regression models with RMSE=71.6 mm, MAE=19.6 mm, R=0.276 and RMSE=38.7 mm, MAE=14.2 mm, R=0.103, respectively. The ANN method was also employed for the same data set and found that there is a slight difference between ANN and SVR methods.     

Application of artificial neural network (ANN)–self-organizing map (SOM) for the categorization of water,soil and sediment quality in petrochemical regions

The utilization of mathematical and computational tools for pollutant assessment frameworks has become increasingly valuable due to the capability to interpret integrated variable measurements. Artificial neural networks (ANNs) are considered as dependable and inexpensive techniques for data interpretation and prediction. The self-organizing map (SOM) is an unsupervised ANN used for data training to classify and effectively recognize patterns embedded in the input data space. Application of SOM–ANN is useful for recognizing spatial patterns in contaminated zones by integrating chemical, physical, ecotoxicological and toxicokinetic variables in the identification of pollution sources and similarities in the quality of the samples. Water (n = 11), soil (n = 38) and sediment (n = 54) samples from four areas in the Niger Delta (Nigeria) were classified based on their chemical, toxicological and physical variables applying the SOM. The results obtained in this study provided valuable assessment using the SOM visualization capabilities and highlighted zones of priority that might require additional investigations and also provide productive pathway for effective decision making and remedial actions.     

Artificial neural network application for modeling the rail rolling process

Rail rolling process is one of the most complicated hot rolling processes. Evaluating the effects of parametric values on this complex process is only possible through modeling. In this study, the production parameters of different types of rails in the rail rolling processes were modeled with an artificial neural network (ANN), and it was aimed to obtain optimum parameter values for a different type of rail. For this purpose, the data from the Rail and Profile Rolling Mill in Kardemir Iron & Steel Works Co. (Karabük, Turkey) were used. BD1, BD2, and Tandem are three main parts of the rolling mill, and in order to obtain the force values of the 49 kg/m rail in each pass for the BD1 and BD2 sections, the force and torque values for the Tandem section, parameter values of 60, 54, 46, and 33 kg/m type rails were used. Comparing the results obtained from the ANN model and the actual field data demonstrated that force and torque values were obtained with acceptable error rates. The results of the present study demonstrated that ANN is an effective and reliable method to acquire data required for producing a new rail, and concerning the rail production process, it provides a productive way for accurate and fast decision making.     

Stable white light emission from an externally modified organic light-emitting device

A blue organic light-emitting device, based on an iridium phosphorescent dopant in a polyvinylcarbazole host, has been modified by the addition of an external CaS:Eu inorganic phosphor layer. By incorporating a surfactant in the phosphor mixture, a uniform coating could be achieved by drop-casting. The resulting hybrid device exhibited white light emission, with Commission Internationale de l’Eclairage, CIE (x, y) coordinates of x = 0.32, y = 0.35. No significant change in these coordinates was observed for current densities in the range 25–510 A m^?2. The maximum power efficiencies of the white device was 2.3 lm W^?1 at a brightness of 254 cd m^?2.     

Performance of radial basis and LM-feed forward artificial neural networks for predicting daily watershed runoff

This study investigated the effects of upstream stations’ flow records on the performance of artificial neural network (ANN) models for predicting daily watershed runoff. As a comparison, a multiple linear regression (MLR) analysis was also examined using various statistical indices. Five streamflow measuring stations on the Cahaba River, Alabama, were selected as case studies. Two different ANN models, multi layer feed forward neural network using Levenberg–Marquardt learning algorithm (LMFF) and radial basis function (RBF), were introduced in this paper. These models were then used to forecast one day ahead streamflows. The correlation analysis was applied for determining the architecture of each ANN model in terms of input variables. Several statistical criteria (RMSE, MAE and coefficient of correlation) were used to check the model accuracy in comparison with the observed data by means of K-fold cross validation method. Additionally, residual analysis was applied for the model results. The comparison results revealed that using upstream records could significantly increase the accuracy of ANN and MLR models in predicting daily stream flows (by around 30%). The comparison of the prediction accuracy of both ANN models (LMFF and RBF) and linear regression method indicated that the ANN approaches were more accurate than the MLR in predicting streamflow dynamics. The LMFF model was able to improve the average of root mean square error (RMSE_ave) and average of mean absolute percentage error (MAPE_ave) values of the multiple linear regression forecasts by about 18% and 21%, respectively. In spite of the fact that the RBF model acted better for predicting the highest range of flow rate (flood events, RMSE_ave/RBF = 26.8 m³/s vs. RMSE_ave/LMFF = 40.2 m³/s), in general, the results suggested that the LMFF method was somehow superior to the RBF method in predicting watershed runoff (RMSE/LMFF = 18.8 m³/s vs. RMSE/RBF = 19.2 m³/s). Eventually, statistical differences between measured and predicted medians were evaluated using Mann-Whitney test, and differences in variances were evaluated using the Levene's test.     

Soot emission prediction of a waste-gated turbo-charged DI diesel engine using artificial neural network

This study is about soot emission prediction of a waste-gated turbo-charged DI diesel engine using artificial neural network (ANN). For training the ANN model, six ranges of experimental data in previous study were used, and one range of data was kept for testing the accuracy of ANN predictions. The input parameters for the ANN are inlet manifold pressure, inlet manifold temperature, inlet air mass flow rate, fuel consumption, engine torque, and speed. Output parameter is the density of soot in the exhaust. The results show the ANN approach can be used to accurately predict soot emission of a turbo-charged diesel engine in different opening ranges of waste-gate (ORWG). Root mean-squared error (RMSE), fraction of variance (R ²), and mean absolute percentage error (MAPE) for predictions were found to be 1.19 (mg/m³), 0.9998, and 6.4%, respectively.     

Using combustion net torque for estimation of combustion properties from measurements of crankshaft torque

Two methods, both based on the concept of combustion net torque, for estimation of combustion properties using measurements of crankshaft torque data are investigated in this work. The first of the proposed methods estimates entire burned mass fraction traces from corresponding combustion net torque traces. This is done by solving a convex optimization problem that is based on a derived analytical relation between the two quantities. The other proposed estimation method estimates the well established combustion phasing measure referred to as 50% burned mass fraction directly from combustion net torque using a nonlinear black-box mapping. The methods are assessed using both simulations and experimental data gathered from a 5-cylinder light-duty diesel engine equipped with a crankshaft torque sensor and cylinder pressure sensors that are used for reference measurements. The results indicate that both methods work well but the method that estimates entire burned mass fraction traces is more sensitive to torque data quality. Based on the experimental crankshaft torque data, the direct combustion phasing estimation method delivers estimates with a bias of less than 1 CAD and a cycle-to-cycle standard deviation of less than 2.7 CAD for all cylinders.     

Small molecules with pyridine backbone modified with carbazole,fluorine and bromine for white light-emitting diode applications

Seven compounds with pyridine as the backbone modified by carbazole moiety, bromine atom and fluorine atom were synthesized. Compounds 1, 2, 3 with bromo substitution at the 2-position and carbazole modification at the 5-position of pyridine emit not only a sharp blue singlet fluorescence but also a wide banded excimer-based orange emission. The two colors coming from a single molecule can be used to fabricate a simplified white light emitting device. The electroluminescence based on 1 and 2 exhibits white-light emission with CIE coordinates of x = 0.25 and y = 0.30 for 1 and x = 0.33 and y = 0.37 for 2 at high current densities, very close to pure white emission. In addition, the role of bromo-substitution at pyridine is concluded to be essential to generate molecular interaction thus an excimer emission.     

Prediction of flow pattern of gas–liquid flow through circular microchannel using probabilistic neural network

The present study attempts to develop a flow pattern indicator for gas–liquid flow in microchannel with the help of artificial neural network (ANN). Out of many neural networks present in literature, probabilistic neural network (PNN) has been chosen for the present study due to its speed in operation and accuracy in pattern recognition. The inbuilt code in MATLAB R2008a has been used to develop the PNN. During training, superficial velocity of gas and liquid phase, channel diameter, angle of inclination and fluid properties such as density, viscosity and surface tension have been considered as the governing parameters of the flow pattern. Data has been collected from the literature for air–water and nitrogen–water flow through different circular microchannel diameters (0.53, 0.25, 0.100 and 0.050 mm for nitrogen–water and 0.53, 0.22 mm for air–water). For the convenience of the study, the flow patterns available in literature have been classified into six categories namely; bubbly, slug, annular, churn, liquid ring and liquid lump flow. Single PNN model is unable to predict the flow pattern for the whole range (0.53 mm–0.050 mm) of microchannel diameter. That is why two separate PNN models has been developed to predict the flow patterns of gas–liquid flow through different channel diameter, one for diameter ranging from 0.53 mm to 0.22 mm and another for 0.100 mm–0.05 mm. The predicted map and their transition boundaries have been compared with the corresponding experimental data and have been found to be in good agreement. Whereas accuracy in prediction of transition boundary obtained from available analytical models used for conventional channel is less for all diameter of channel as compared to the present work. The percentage accuracy of PNN (～94% for 0.53 mm ID and ～73% for 0.100 mm ID channel) has also been found to be higher than the model based on Weber number (～86% for 0.53 mm ID and ～36% for 0.05 mm ID channel).     

Prediction of cutting temperature in orthogonal machining of AISI 316L using artificial neural network

In this study, an approach based on artificial neural network (ANN) was proposed to predict the experimental cutting temperatures generated in orthogonal turning of AISI 316L stainless steel. Experimental and numerical analyses of the cutting forces were carried out to numerically obtain the cutting temperature. For this purpose, cutting tests were conducted using coated (TiCN + Al₂O₃ + TiN and Al₂O₃) and uncoated cemented carbide inserts. The Deform-2D programme was used for numerical modelling and the Johnson–Cook (J–C) material model was used. The numerical cutting forces for the coated and uncoated tools were compared with the experimental results. On the other hand, the cutting temperature value for each cutting tool was numerically obtained. The artificial neural network model was used to predict numerical cutting temperatures by means of the numerical cutting forces. The best results in predicting the cutting temperature were obtained using the network architecture with a hidden layer which has seven neurons and LM learning algorithm. Finally, the experimental cutting temperatures were predicted by entering the experimental cutting forces into a formula obtained from the artificial neural networks. Statistical results (R², RMSE, MEP) were quite satisfactory. This demonstrates that the established ANN model is a powerful one for predicting the experimental cutting temperatures.     

Artificial neural network-based model for predicting VO2max from a submaximal exercise test

The goal of this study is to develop an accurate artificial neural network (ANN)-based model to predict maximal oxygen uptake (VO₂max) of fit adults from a single stage submaximal treadmill jogging test. Participants (81 males and 45 females), aged from 17 to 40 years, successfully completed a maximal graded exercise test (GXT) to determine VO₂max. The variables; gender, age, body mass, steady-state heart rate and jogging speed are used to build the ANN prediction model. Using 10-fold cross validation on the dataset, the average values of standard error of estimate (SEE), Pearson’s correlation coefficient (r) and multiple correlation coefficient (R) of the model are calculated as 1.80 ml kg^?1 min^?1, 0.95 and 0.93, respectively. Compared with the results of the other prediction models in literature that were developed using Multiple Linear Regression Analysis, the reported values of SEE, r and R in this study are considerably more accurate.