Logistic Sigmoid Transfer Function Research Articles

Application of GA-Optimized ANNs to Predict the Water Content, CO2 and H2S Absorption Capacity of Diethanolamine (DEA) in Khangiran Gas Sweetening Plant

In this work, with the aim of accurate prediction of water content, H2S and CO2 absorption capacity of diethanolamine (DEA) solvent in Khangiran gas sweetening plant, an artificial neural network (ANN) model of feed-forward multilayer perceptron, with the learning algorithm of Levenberg–Marquardt has been developed. The training, validation, and testing of the ANN model, respectively, was performed using 70, 15, and 15% of all of the gathered operation data. An optimization procedure on the basis of the genetic algorithm (GA) was implemented to select the optimum ANN architecture. Accordingly, a three layer feed-forward neural network with Levenberg–Marquardt back-propagation training algorithm was designed and developed. The structure of the model comprised of 12 variables as inputs and three as outputs, 13 neurons in the hidden layer, the log-sigmoid transfer function in the hidden layer, and the output layer containing linear transfer function. The results, based on statistical analysis, showed very little difference between the predicted and actual operation data with a remarkably low mean square error (MSE) value and a coefficient of determination (R2) value approaching one. The mentioned factors are strong indicators of the proposed model’s high accuracy in predicting the output variables.

Prediction of frictional pressure losses in annulus with artificial neural network modeling

Pressure loss of single phase in annular flow for non-Newtonian drilling mud have been predicted utilizing an artificial neural network (ANN). Based on statistical study, an optimization procedure was performed to choose the optimum of ANN technique. With Levenberg-Marquardt back-propagation training algorithm, six variables as input and once as outcome were modeled and trained using a three-layer feed forward neural network. Three neurons, the log sigmoid transfer function in the hidden layer and the linear transfer function inside the result layer were introduced in this article. Simulated results of ANN technique are been demonstrated that there is an outstanding agreement among predicting values and measuring pressure drops in annulus for test data and training sets. Additionally, typical model used (power law model) that were applied to calculate the performance of ANN model and comparison the three wells results. Based on the analysis of the results obtained, it is shown that the ANN method outperforms other models significantly and delivers excellent predictions, the correlation coefficient (R2) of 0.9999 average absolute relative error (AARE) equal to 0.00001.

A New Response Approximation Model of the Quadrant Detector Using the Optimized BP Neural Network

In this paper, a new response approximation model for quadrant detector is proposed based on a BP Neural Network by employing different training algorithms. A total of 1001 data points are gathered to train and test the proposed network. Through optimal configuration, the network with 1 hidden layer and 8 hidden neurons with Log-sigmoid transfer functions in the hidden layer is determined to have the optimum performance. Furthermore, Levenberg-Marquardt (LM) is the best train algorithm while in this case the model is more precise than others. Besides, it shows a good ability to suppress the non-uniformity. The results of experiment reveal that the root mean square error using this model is about 1/5 of that using Fusion method when the beam radius is ${0.75} \textit {mm} $ . Meanwhile, its maximum errors under different radii are all less than ${6}\times {10}^{\text {-3}} \textit {mm} $ . Therefore, the new model would have a good application prospect in beam position measurements.

Artificial neural network (ANNs) and mathematical modelling of hydration of green chickpea

The present study was aimed to model the hydration characteristics of green chickpea (GC) using mathematical modelling and examine predictive ability of artificial neural network (ANN) modelling. Hydration of GC was performed at different temperatures 25, 35, 45, 55 and 65 °C. Different mathematical models were tested for the hydration at different temperatures. In ANN modelling, the hydration time and hydration temperature were used as input variables and moisture ratio, moisture content and hydration ratio were taken as output variables. Peleg model best described the hydration behavior at 25 °C; while hydration at high-temperature was better described by Page model and Ibarz et al. model. The optimum temperature obtained for hydration was 35 °C. Effective mass diffusion coefficient (De) increased from 1.55 × 10-11-1.79 × 10-9 m2/s with the increase in the hydration temperature. The low activation energy (39.66 kJ/moL) shows the low-temperature sensitiveness of GC. Low temperature hydration (25 °C) required higher time (>200 min) to achieve the equilibrium moisture content (EMC), however high temperature hydration (35–65 °C) reduced the EMC time (150 min). ANN was used to predict the hydration behavior and K fold cross validation was performed to check the over fitting of ANN model. Results show that the LOGSIGMOID transfer function showed better performance when used at the hidden layer input node in conjunction to both PURELIN and TANSIGMOID. TANSIGMOID was found suitable for moisture ratio (MR) and hydration ratio (HR) prediction, as opposed to PURELIN for moisture content (MC) data. Satisfactory model prediction was obtained when the number of neurons in the hidden layer for MC, MR and HR was 12, 8 and 15, respectively. Mathematical and ANN modelling results are useful to improve/predict the MC, MR and HR during hydration process of GC at different temperature and other similar process.

Adsorption of tetracycline antibiotic onto modified zeolite: Experimental investigation and modeling

Artificial Neural Networks (ANNs) model and Adaptive Neuro-Fuzzy Inference System (ANFIS) were used to estimate and predict the removal efficiency of tetracycline (TC) using the adsorption process from aqueous solutions. The obtained results demonstrated that the optimum condition for removal efficiency of TC were 1.5 g L−1 modified zeolite (MZ), pH of 8.0, initial TC concentration of 10.0 mg L−1, and reaction time of 60 min. Among the different back-propagation algorithms, the Marquardt–Levenberg learning algorithm was selected for ANN Model. The log sigmoid transfer function (log sig) at the hidden layer with ten neurons in the first layer and a linear transfer function were used for prediction of the removal efficiency. Accordingly, a correlation coefficient, mean square error, and absolute error percentage of 0.9331, 0.0017, and 0.56% were obtained for the total dataset, respectively. The results revealed that the ANN has great performance in predicting the removal efficiency of TC.•ANNs used to estimate and predict tetracycline antibiotic removal using the adsorption process from aqueous solutions.•The model's predictive performance evaluated by MSE, MAPE, and R2.

Artificial neural networks and multiple linear regression as potential methods for modelling body surface temperature of pig

ABSTRACT An experiment was conducted to evaluate modelling relationships between pig’s body surface temperature and ambient environment including inside and outside of pig barn. For this purpose, four different artificial neural network (ANN), including Feed Forward Back-propagation (FFB), Layer recurrent (LR), Elman (EL) and Cascade Forward Back-propagation (CFB) with different learning algorithms, transfer functions, hidden layers and neuron in each layer, and multi-linear regression (MLR) models have been performed to predict body temperature of pig. Six two-month-old pigs were studied over a period of 92 days during two years (2017–2018) to develop and evaluate the ANN and MLR models. The performance of the models in predicting pig’s body temperature was determined using statistical quality parameters, including coefficient of determination (R 2), root mean square error (RMSE) and mean absolute percentage error (MAPE). The FFB model with the Levenberg-Marquardt training function, Gradient descent weight and bias learning function, Log-sigmoid transfer function and two hidden layers with 20 neurons was found as the best model. Sensitivity analysis indicated that the temperature-humidity index (THI) inside the room is the most influential factor in predicting pig’s body temperature in the MLR/ANN models.

Theoretical analysis and mathematical modeling of deformation and stresses of the grooving tool

Machining operations involving complex multivariate parameters are defined by many machining parameters. Correct selection of these parameters is crucial for an efficient and economical cutting operation. The grooving operation required in many cases is one of the most problematic methods in all metal cutting operations, especially in terms of chip control. This paper covers theoretical analysis and mathematical modeling of deformation and stresses of the grooving tool. Cutting forces affecting the service life of the grooving tool were measured by various cutting experiments. Deformation and stresses of grooving tool caused by cutting forces were analyzed by finite element method using Ansys software. In modeling with artificial neural networks (ANN), grooving insert width, cutting speed, feed rate, radial force and primary cutting force are inputs in the model and deformation and stresses of the grooving tool are outputs. An algorithm, which is a Matlab script file, was developed to determine the optimal combination of neural network parameters such as the normalization method, number of hidden neurons, transfer function and training algorithm. The best-fitting set determined by the algorithm developed for the model was achieved with the Levenberg–Marquardt backpropagation algorithm, logistic sigmoid transfer function, nine hidden neurons and normalization method with a scaling factor. The MSE, R2, MAPE values of the ANN model are 2.0327 × 10−6, 0.999992 and 0.379227, respectively. Performance results have shown that the proposed approach can also be used for ANN modeling of machining parameters in other cutting operations other than grooving.

Experimental and neural network modelling of polymer drag reduction in 180° bends

This research investigates the effect of small amounts of drag-reducing polymer (DRP), (Partially hydrolysed polyacrylamide) on single phase water flow in 180° bends using both experimental and artificial neural network (ANN) modelling approach. The results show that, in both straight pipes and U-bend, drag reduction (DR) generally increased with polymer concentration until an optimum concentration is reached beyond which further increase in concentration resulted in increased drag. It was observed that using different concentrations of master solution had negligible effect on the computed DR as long as there is sufficient mixing to allow for homogeneous polymer dispersion. The results further revealed that DR in straight pipes are significantly higher than that in bends of equivalent length and the highest DR reported were 65%, 42% and 45% in straight, horizontal U-bend and down-flow U-bend pipe configurations respectively. It was also reported here that DR increased with Reynolds number for all flow configurations investigated. This study was also extended to ANN modelling of the various output parameters of interest such as friction factor and bend friction coefficient. Some test cases showed that one neuron was sufficient in predicting the output parameters. This suggests that classical models would also be adequate in modelling single-phase flow drag reduction in and around bends. Model predictions were excellent with cross correlation of nearly 100% (99.99%). In this work, the ANN model coded using Levenberg–Marquardt LM algorithm and logsigmoid transfer function gave the best Neural Network model performance as indicated by its lowest value of X2 (=2.03E-04). The proposed ANN model can be used with confidence for the prediction of friction factor, bends coefficient and drag reduction DR in straight pipes and return bends.

Nonlinear Modeling of the Flux Linkage in 2-D Plane for the Planar Switched Reluctance Motor

This paper proposes a nonlinear flux linkage model in 2-D plane for the planar switched reluctance motor (PSRM). The inputs of the proposed model are the 2-D positions and the current, and the output is the flux linkage. The proposed model is established via a cascade-forward backpropagation neural network (CFNN). The designed CFNN consists of four layers: one input layer, two hidden layers, and one output layer. The first hidden layer has 20 neurons with a tan-sigmoid transfer function, and the second hidden layer has 20 neurons with a log-sigmoid transfer function. The output layer is a pure linear layer. The sample set with 179 755 samples is obtained experimentally in a dSPACE-based PSRM system by applying the dc excitation method. The sample set is divided into three sets. 35% and 30% of the samples are randomly chosen as the training sample set and validation sample set, respectively, and the remaining samples are utilized as the test sample set to assess the generalization performance of the CFNN-based model. According to the results of the test sample set, the maximum relative error is 11.05% and the mean relative error is 0.42% when the current ranges from 1 to 9 A. The CFNN has the capability to build a multi-input nonlinear model. The CFNN-based model is capable of reflecting the variations of flux linkage in 2-D plane caused by manufacturing tolerances. The effectiveness of the CFNN-based model is finally verified.

Auto-Regressive Neural-Network Models for Long Lead-Time Forecasting of Daily Flow

Accurate reservoir-inflow forecasting is especially important for optimizing operation of multi-propose reservoirs that provide hydropower generation, flood control, and water for domestic use and irrigation. There are no previous reports of successful daily flow prediction using a 1-year lead-time. This paper reports successful daily stream flow predictions for that extended lead-time. It presents the first NARX (Nonlinear Auto Regressive model with eXogenous inputs)-type recurrent neural network (NARX-RNN) model used to forecast daily reservoir inflow for a long lead-time. It is the first use of dynamic memory to extend the forecast lead-time beyond the previously reported 1-week lead-times. For new nonlinear NARX-RNN models, we present and test 1600 alternative structures, differing in transfer functions (2), and numbers of inputs (2 to 5), neurons per hidden layer (1 to 20), input delays and output delays. For predicting inflow to the reservoir of the multi-purpose Dez Dam, we contrast accuracies of forecasts from the new models, and from a conventional auto-regressive linear ARIMA model. Based upon normalized root-mean-square error $$ \mathrm{RMSE}/{\overline{Q}}_{obs} $$ the best NARX-RNN has log-sigmoid transfer functions, three inputs, one hidden layers, four neurons in the hidden layer, two input delays, and 10 output delays. That NARX-RNN structure yields $$ \mathrm{RMSE}/{\overline{Q}}_{obs} $$ values of 0.616 in training and 0.678 in forecasting. The proposed model’s forecasting $$ \mathrm{RMSE}/{\overline{Q}}_{obs} $$ is 20% lower than that of the ARIMA model.

Investigation of Mechanical Properties of Self Compacting Polymeric Concrete with Backpropagation Network

Acrylic polymer that is highly stable against chemicals and is a good choice when concrete is subject to chemical attack. In this study, self-compacting concrete (SCC) made using acrylic polymer, nanosilica and microsilica has been investigated. The results of experimental testing showed that the addition of microsilica and acrylic polymer decreased the tensile, compressive and bending strength of the concrete. The addition of nanosilica and an increase in polymer content increased the bending strength of concrete and decreased the tensile and compressive strengths. Because, in the laboratory, the number of samples were limited and the amount of variation was small, comprehensive results cannot be achieved. With the help of neural networks, estimating any amount within the range of the input data is possible. In this paper, in addition to the experimental results, a backpropagation neural network (BNN) was used to simulate the testing on the strength of self-compacting polymeric concrete. The results showed that the use of the normalized mean squared error, resilient backpropagation training, tangent-sigmoid and log sigmoid transfer functions and five neurons in each hidden layers in a two-layer BNN produced good results with a regression value of 0.95 and error of 0.17.

Multi-response optimization and neural network modeling for parameter precision in heat reflux extraction of spice oleoresins from two pepper cultivars (Piper nigrum)

Black and white peppers are important oil bearing commodity crop in tropical areas. They are highly beneficial in food industries and herbal medicine, due to their amazing aroma and therapeutic activities. In this study, heat reflux technique was employed to extract medicinal oleoresin from the two peppercorns. For this purpose, various extraction parameters were considered viz: extraction time, particle size and feed-solvent ratio. These extraction parameters were employed to optimize the extraction yield and absorbed energy via Taguchi methodology. The established optimal condition values of the yield and absorbed energy from the parametric study were 13.22mg/g and 285.60J/min, respectively in black pepper heat refluxation. Moreover, in white pepper refluxation, the extraction yield and absorbed energy were 14.04mg/g and 264.82J/min, respectively. Artificial neural network (ANN) was used for prediction purposes. This was achieved by comparing two algorithms, transfer functions and neurons. A good training and better prediction of the experimental data were observed using the Levenberg Marquardt (LM) feed forward backpropagation algorithm with log sigmoid transfer function as hidden layer and 3-4-5-1 as model topology. Furthermore, a total of 19 and 25 bioactive compounds were identified in black and white pepper extracts, respectively. The results from the Scanning Electron Spectrometry (SEM) showed a remarkable morphological changes during the heat refluxation process.

Computational Analysis and Artificial Neural Network Optimization of Dry Turning Parameters—AA2024-T351

In dry turning operation, various parameters influence the cutting force and contribute in machining precision. Generally, the numerical cutting models are adopted to establish the optimum cutting parameters and results are substantiated with the experimental findings. In this paper, the optimal turning parameters of AA2024-T351 alloy are determined through Abaqus/Explicit numerical cutting simulations by employing the Johnson-Cook thermo-viscoplastic-damage material model. Turning simulations were verified with published experimental data. Considering the constrained and nonlinear optimization problem, the artificial neural networks (ANN) were executed for training, testing, and performance evaluation of the numerical simulations data. Two feedforward backpropagation neural networks were developed with ten hidden neutrons in each hidden layer. The Log-Sigmoid transfer function and the Levenberg-Marquardt algorithm were applied in the model. The ANN models were studied with four input parameters: the cutting speed (200, 400, and 800 m/min), tool rake angle (5°, 10°, 14.8°, and 17.5°), cutting feed (0.3 and 0.4 mm), and the contact friction coefficients (0.1 and 0.15).The two target parameters include the tool-chip interface temperature and the cutting reaction force. The performance of the trained data was evaluated using root-mean-square error and correlation coefficients. The ANN predicted values were compared both with the Abaqus simulations and the published experimental findings. All of the results are found in good approximation to each other. The performance of the ANN models demonstrated the fidelity of solving and predicting the optimum process parameters.

Parametric Studies of a Simple Direct Expansion Solar Assisted Heat Pump Using ANN and GA

Abstract This paper reports the use of artificial neural network (ANN) integrated with genetic algorithm (GA) to predict the performance of direct expansion solar assisted heat pump (DX-SAHP), in Calicut (Latitude of 11.15 0 N, longitude of 75.49 0 E), India. The performance parameters such as power consumption, heating capacity, energy performance ratio and compressor discharge temperature of DX-SAHP 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 variants Lavenberg–Marguardt (LM) with 10 neurons in the hidden layer and logistic sigmoid transfer function were used in the network to predict the performance of DX-SAHP. Then those values obtained from the analysis using ANN are optimized further by integrating the ANN procedure with GA. The resulting computations confirmed that the use of ANN integrated with GA gives better optimized values compared to the value obtained from ANN for the performance prediction of DX-SAHP.

Isolation of Essential Oil from the Leaves of Cymbopogon martinii using Hydrodistillation: Effect on Yield of Essential Oil, Yield of Geraniol and Antimicrobial Activity

The essential oil of Cymbopogon martinii (Palmarosa) is one of the industrially important essential oil having rose like sweet aroma. Using hydrodistillation technique, essential oil from the leaves of palmarosa was extracted to maximize the yield of oil, yield of geraniol along with zone of inhibition (ZOI) as responses. These responses were influenced by solid loading, volume of water, size of leaves and extraction time. The optimization of process parameters was performed using the Taguchi method and grey relational analysis. The optimized conditions were obtained at, solid loading of 50 g, water volume of 1000 mL, 20 mm size of the leaves and extraction time of 35 min. Under optimized conditions, 1.6832% w/w yield of essential oil, 1.4230% w/w yield of geraniol and 16 mm ZOI were obtained. Artificial neural network was applied for predictive modeling, providing better accuracy (mean square error = 0.0301) in case of 4-12-2 topology and log sigmoid transfer function as hidden layer. Proximate and ultimate analyses were carried out to find the quantitative energy content of the used palmarosa leaves by finding its higher heating value (HHV). HHV of used palmarosa leaves was found to be 17.8741 MJ/kg suggesting the potential of leaves as a renewable source of energy.

Microwave assisted extraction of essential oil from the leaves of Palmarosa: Multi-response optimization and predictive modelling

Cymbopogon martinii (Palmarosa), an essential oil bearing industrial grass of India, is highly valued by cosmetics and perfumery industries for its rose like sweet odor from its inflorescences and leaves. Using microwave radiation, essential oil from the leaves of palmarosa was extracted for maximization of yield of oil, yield of geraniol and zone of inhibition (ZOI) as responses. For this purpose, various process parameters viz. solid loading, water volume, microwave power and extraction time were studied in detail and optimized using the Taguchi method and grey relational analysis. The optimized extraction conditions were obtained at, solid loading of 35g, water volume of 300mL, microwave power of 850W and extraction time of 20min. Under optimized conditions, 2.4400% (w/w) yield of essential oil, 2.1700% (w/w) yield of geraniol and 20mm ZOI were obtained. Artificial neural network (ANN) was used for the prediction of the results by studying different algorithms, transfer functions and numbers of neurons. A better prediction (overall R2=0.9997; mean squared error=0.0117) of the experimental data was observed using feed forward back propagation algorithm, log sigmoid transfer function as hidden layer and 4-7-3 topology.

Hardware design and implementation of a novel ANN-based chaotic generator in FPGA

This paper presents a novel hardware implementation of Artificial Neural Networks (ANNs) for modeling of the Pehlivan–Uyaroglu Chaotic System (PUCS) on Field Programmable Gate Array (FPGA). There are two main parts in the proposed work. In the first part, a 3-8-3 Feed Forward Neural Network (FFNN) has been created using Matlab R2015a. The training results show that FFNN trained with back propagation algorithm exhibits satisfactory precision for the direct implementation. In the second part, the hardware implementation of the trained network has been carried out. The designed architecture is presented using Very High Speed Integrated Circuits Hardware Description Language (VHDL) and is implemented on a Xilinx Virtex 6 (XC6VCX240T) chip. All related parameters are defined with IEEE 754 single precision floating point number format. For the approximation of Log-Sigmoid transfer function, Xilinx's COordinate Rotation DIgital Computer (CORDIC) design has been employed. The design can be used with a clock frequency up to 266.429MHz. Finally, chip statistics of FPGA and analysis results have been presented. The proposed work have showed that chaotic systems can be successfully modeled using ANNs on FPGA. In future, chaos-based engineering applications can be performed using ANN-based chaotic oscillators on FPGA.

Prediction of Groundwater Level in Safwan-Zubair Area Using Artificial Neural Networks

Safwan-Zubair area is regarded as one of theimportant agricultural areas in Basrah province, South of Iraq.The aim of this study is to predict groundwater level in this areausing ANNs model. The data required for building the ANNmodel are generated using MODFLOW model (V.5.3).MODFLOW model was calibrated based on field measurementsof groundwater level in13 monitoring wells during a period ofone year (Nov./2013 to Oct/2014). The neural network toolboxavailable in MATLAB version 7.1 (2010B) was used to developthe ANN models. Three layers feed-forward network with Log-sigmoid transfer function was used. The networks were trainedusing Levenberg-Marquardt back-propagation algorithm. TheANN modes are divided into two groups, each of four models.The input data of the first group include hydraulic heads, while,the input data of the second group include hydraulic heads andrecharge rates. Based on results of this study it was found that;the best ANN model for predicting groundwater levels in thestudy area is obtained when the input data includes hydraulicheads and recharge rates of two successive months preceding thetarget month, the best structure of ANN model is of three layersfeed-forward network type composes of two hidden layers, eachof ten nodes, and the including of recharge rates as input data,beside the hydraulic heads has improved slightly the results.

Solar radiation and precipitable water modeling for Turkey using artificial neural networks

Artificial neural network (ANN) method was applied for modeling and prediction of mean precipitable water and solar radiation in a given location and given date (month), given altitude, temperature, pressure and humidity in Turkey (26–45oE and 36–42oN) during the period of 2000–2002. Resilient Propagation (RP) learning algorithms and logistic sigmoid transfer function were used in the network. To train the network, meteorological measurements taken by the Turkish State Meteorological Service (TSMS) and Wyoming University for the period from 2000 to 2002 from five stations distributed in Turkey were used as training data. Data from years (2000 and 2001) were used for training, while the year 2002 was used for testing and validating the model. The RP algorithm were first used for determination of the precipitable water and subsequently, computation of the solar radiation, in these stations Root Mean Square Error (RMSE) between the estimated and measured values for monthly mean daily sum for precipitable water and solar radiation values have been found as 0.0062 gr/cm2 and 0.0603 MJ/m2 (training cities), 0.5652 gr/cm2 and 3.2810 MJ/m2 (testing cities), respectively.

Intelligent Prediction of CO2 Capture in Propyl Amine Methyl Imidazole Alanine Ionic Liquid: An Artificial Neural Network Model

The objective of this paper is to create a new artificial neural network (ANN) model to predict solubility of CO2 in a new structure of task specific ionic liquids called propyl amine methyl imidazole alanine [pamim][Ala]. Equilibrium data of CO2 solubility were measured at the temperatures of 25, 40, and 60°C and the pressures up to 50 bar. For the purpose of performance comparison, the two most common types of ANNs, multilayer perceptron (MLP) network and radial basis function (RBF) network were used. Water content, ionic liquid content, temperature, and pressure set as input variables to ANN, while CO2 capture rate assigned as output. Based upon optimization process, MLP neural network with 14 neurons in the hidden layer, log-sigmoid transfer function in the hidden layer and linear transfer function in the output layer, exhibited much better performance in prediction task than RBF neural network with the same neuron numbers in the hidden layer. Results obtained demonstrated that there is a very little difference between the estimated results of ANN approach and experimental data of CO2 capture rate for the training, validation, and test data sets. Furthermore, Henry’s law constants were obtained by fitting the equilibrium data.