The Experts below are selected from a list of 33036 Experts worldwide ranked by ideXlab platform
Sevgi Demirel - One of the best experts on this subject based on the ideXlab platform.
-
artificial neural network ann approach for modeling of pb ii adsorption from aqueous solution by antep pistachio pistacia vera l shells
Journal of Hazardous Materials, 2008Co-Authors: Kaan Yetilmezsoy, Sevgi DemirelAbstract:Abstract A three-layer artificial neural network (ANN) model was developed to predict the efficiency of Pb(II) ions removal from aqueous solution by Antep pistachio ( Pistacia Vera L.) shells based on 66 experimental sets obtained in a laboratory batch study. The effect of operational parameters such as adsorbent dosage, initial concentration of Pb(II) ions, initial pH, operating temperature, and contact time were studied to optimise the conditions for maximum removal of Pb(II) ions. On the basis of batch test results, optimal operating conditions were determined to be an initial pH of 5.5, an adsorbent dosage of 1.0 g, an initial Pb(II) concentration of 30 ppm, and a temperature of 30 °C. Experimental results showed that a contact time of 45 min was generally sufficient to achieve equilibrium. After backpropagation (BP) training combined with principal component analysis (PCA), the ANN model was able to predict adsorption efficiency with a tangent sigmoid Transfer Function ( tansig ) at hidden layer with 11 neurons and a Linear Transfer Function ( purelin ) at output layer. The Levenberg–Marquardt algorithm (LMA) was found as the best of 11 BP algorithms with a minimum mean squared error (MSE) of 0.000227875. The Linear regression between the network outputs and the corresponding targets were proven to be satisfactory with a correlation coefficient of about 0.936 for five model variables used in this study.
-
artificial neural network ann approach for modeling of pb ii adsorption from aqueous solution by antep pistachio pistacia vera l shells
Journal of Hazardous Materials, 2008Co-Authors: Kaan Yetilmezsoy, Sevgi DemirelAbstract:A three-layer artificial neural network (ANN) model was developed to predict the efficiency of Pb(II) ions removal from aqueous solution by Antep pistachio (Pistacia Vera L.) shells based on 66 experimental sets obtained in a laboratory batch study. The effect of operational parameters such as adsorbent dosage, initial concentration of Pb(II) ions, initial pH, operating temperature, and contact time were studied to optimise the conditions for maximum removal of Pb(II) ions. On the basis of batch test results, optimal operating conditions were determined to be an initial pH of 5.5, an adsorbent dosage of 1.0 g, an initial Pb(II) concentration of 30 ppm, and a temperature of 30 degrees C. Experimental results showed that a contact time of 45 min was generally sufficient to achieve equilibrium. After backpropagation (BP) training combined with principal component analysis (PCA), the ANN model was able to predict adsorption efficiency with a tangent sigmoid Transfer Function (tansig) at hidden layer with 11 neurons and a Linear Transfer Function (purelin) at output layer. The Levenberg-Marquardt algorithm (LMA) was found as the best of 11 BP algorithms with a minimum mean squared error (MSE) of 0.000227875. The Linear regression between the network outputs and the corresponding targets were proven to be satisfactory with a correlation coefficient of about 0.936 for five model variables used in this study.
Kaan Yetilmezsoy - One of the best experts on this subject based on the ideXlab platform.
-
artificial neural network ann approach for modeling of pb ii adsorption from aqueous solution by antep pistachio pistacia vera l shells
Journal of Hazardous Materials, 2008Co-Authors: Kaan Yetilmezsoy, Sevgi DemirelAbstract:Abstract A three-layer artificial neural network (ANN) model was developed to predict the efficiency of Pb(II) ions removal from aqueous solution by Antep pistachio ( Pistacia Vera L.) shells based on 66 experimental sets obtained in a laboratory batch study. The effect of operational parameters such as adsorbent dosage, initial concentration of Pb(II) ions, initial pH, operating temperature, and contact time were studied to optimise the conditions for maximum removal of Pb(II) ions. On the basis of batch test results, optimal operating conditions were determined to be an initial pH of 5.5, an adsorbent dosage of 1.0 g, an initial Pb(II) concentration of 30 ppm, and a temperature of 30 °C. Experimental results showed that a contact time of 45 min was generally sufficient to achieve equilibrium. After backpropagation (BP) training combined with principal component analysis (PCA), the ANN model was able to predict adsorption efficiency with a tangent sigmoid Transfer Function ( tansig ) at hidden layer with 11 neurons and a Linear Transfer Function ( purelin ) at output layer. The Levenberg–Marquardt algorithm (LMA) was found as the best of 11 BP algorithms with a minimum mean squared error (MSE) of 0.000227875. The Linear regression between the network outputs and the corresponding targets were proven to be satisfactory with a correlation coefficient of about 0.936 for five model variables used in this study.
-
artificial neural network ann approach for modeling of pb ii adsorption from aqueous solution by antep pistachio pistacia vera l shells
Journal of Hazardous Materials, 2008Co-Authors: Kaan Yetilmezsoy, Sevgi DemirelAbstract:A three-layer artificial neural network (ANN) model was developed to predict the efficiency of Pb(II) ions removal from aqueous solution by Antep pistachio (Pistacia Vera L.) shells based on 66 experimental sets obtained in a laboratory batch study. The effect of operational parameters such as adsorbent dosage, initial concentration of Pb(II) ions, initial pH, operating temperature, and contact time were studied to optimise the conditions for maximum removal of Pb(II) ions. On the basis of batch test results, optimal operating conditions were determined to be an initial pH of 5.5, an adsorbent dosage of 1.0 g, an initial Pb(II) concentration of 30 ppm, and a temperature of 30 degrees C. Experimental results showed that a contact time of 45 min was generally sufficient to achieve equilibrium. After backpropagation (BP) training combined with principal component analysis (PCA), the ANN model was able to predict adsorption efficiency with a tangent sigmoid Transfer Function (tansig) at hidden layer with 11 neurons and a Linear Transfer Function (purelin) at output layer. The Levenberg-Marquardt algorithm (LMA) was found as the best of 11 BP algorithms with a minimum mean squared error (MSE) of 0.000227875. The Linear regression between the network outputs and the corresponding targets were proven to be satisfactory with a correlation coefficient of about 0.936 for five model variables used in this study.
Mehrorang Ghaedi - One of the best experts on this subject based on the ideXlab platform.
-
the performance of nanorods material as adsorbent for removal of azo dyes and heavy metal ions application of ultrasound wave optimization and modeling
Ultrasonics Sonochemistry, 2017Co-Authors: Mehrorang Ghaedi, Arash AsfaramAbstract:Abstract The present research is focused on the synthesis and characterization of zinc (II) oxide nanorods loaded on activated carbon (ZnO-NRs-AC) to prepare an outstanding adsorbent for the simultaneous adsorption of heavy metals and dyes as hazardous pollutant using ultrasound energy. The adsorbent was identified by Scanning Electron Microscope (SEM), Transmission Electron Microscopy (TEM), Energy-dispersive X-ray spectroscopy (EDS) and X-ray diffraction (XRD) analysis. The individual effects and possible interactions between the most effective variables including initial metal ions (Cd2+ and Co2+) and azo dyes (methylene blue (MB) and crystal violet (CV)) concentration, adsorbent dosage and ultrasonic time on the responses were investigated by response surface methodology (RSM) and optimum conditions was fixed at Cd2+, Co2+, MB and CV concentrations were 25, 24, 18 and 14 mg L−1, respectively, 0.025 g of ZnO-NRs-AC and 5.1 min sonication to achieve maximum removal percentage (>97.0%) for targets compounds. The artificial neural network (ANN) model was applied for prediction of data with Levenberg–Marquardt algorithm (LMA), a Linear Transfer Function (purelin) at output layer and a tangent sigmoid Transfer Function (tansig) in the hidden layer with 14 neurons. The minimum mean squared error (MSE) of 0.9646, 0.0402 and 0.0753 with high determination coefficient (R2) of 0.9996, 0.9991 and 0.9999 for train, test and validation, respectively, were able to predict and model the adsorption process. The results of examination of the time on experimental adsorption data and their subsequent fitting reveal applicability of pseudo-second-order and intraparticle diffusion model. The experimental equilibrium data was analyzed by Langmuir, Freundlich, Temkin and D–R isotherm models and explored that the data well presented by Langmuir model with maximum adsorption capacity of 97.1, 92.6, 83.9 and 81.6 mg g−1 for Cd+2, Co+2 ions, MB and CV dyes, respectively.
-
isotherm and kinetics study of malachite green adsorption onto copper nanowires loaded on activated carbon artificial neural network modeling and genetic algorithm optimization
Spectrochimica Acta Part A: Molecular and Biomolecular Spectroscopy, 2015Co-Authors: Mehrorang Ghaedi, A M Ghaedi, E Shojaeipour, Reza SahraeiAbstract:In this study, copper nanowires loaded on activated carbon (Cu-NWs-AC) was used as novel efficient adsorbent for the removal of malachite green (MG) from aqueous solution. This new material was synthesized through simple protocol and its surface properties such as surface area, pore volume and Functional groups were characterized with different techniques such XRD, BET and FESEM analysis. The relation between removal percentages with variables such as solution pH, adsorbent dosage (0.005, 0.01, 0.015, 0.02 and 0.1g), contact time (1-40min) and initial MG concentration (5, 10, 20, 70 and 100mg/L) was investigated and optimized. A three-layer artificial neural network (ANN) model was utilized to predict the malachite green dye removal (%) by Cu-NWs-AC following conduction of 248 experiments. When the training of the ANN was performed, the parameters of ANN model were as follows: Linear Transfer Function (purelin) at output layer, Levenberg-Marquardt algorithm (LMA), and a tangent sigmoid Transfer Function (tansig) at the hidden layer with 11 neurons. The minimum mean squared error (MSE) of 0.0017 and coefficient of determination (R(2)) of 0.9658 were found for prediction and modeling of dye removal using testing data set. A good agreement between experimental data and predicted data using the ANN model was obtained. Fitting the experimental data on previously optimized condition confirm the suitability of Langmuir isotherm models for their explanation with maximum adsorption capacity of 434.8mg/g at 25°C. Kinetic studies at various adsorbent mass and initial MG concentration show that the MG maximum removal percentage was achieved within 20min. The adsorption of MG follows the pseudo-second-order with a combination of intraparticle diffusion model.
-
artificial neural network genetic algorithm based optimization for the adsorption of phenol red pr onto gold and titanium dioxide nanoparticles loaded on activated carbon
Journal of Industrial and Engineering Chemistry, 2015Co-Authors: Mehrorang Ghaedi, Ali Daneshfar, A Ahmadi, M S MomeniAbstract:Abstract The artificial neural network (ANN) model based on application of Levenberg–Marquardt algorithm (LMA) composed of Linear Transfer Function (purelin) at output layer and tangent sigmoid Transfer Function (tansig) at hidden layer with 15 and 19 neurons for Au-NP-AC and TiO2-NP-AC, respectively was applied for optimization and prediction of adsorption system behavior. The judgment about applicability of this model was criterion such as mean squared error (MSE) (3.19e−04) and coefficient of determination (R2) 0.9962 were found for removal efficiency of Au-NP-AC. For TiO2-NP-AC, the obtained values for MSE and R2 were 0.0022 and 0.9729, respectively. It was seen that a good agreement between the experimental data and predicted values based on ANN model was found. The novel approximately green adsorbents with unique advantages such as low cost, locally available and relatively new are applicable for the removal of dyes from aqueous solutions. The optimization has been carried out by fitting the experimental parameters including initial pH, dye concentration, sorbent dosage and contact time to ANN. At initial pH lower than 2 the removal percentage and adsorption of dye on both adsorbent was complete that suggest and confirm their suitability for removal of this dye from complicated real matrices. The isothermal data for adsorption followed the Freundlich and Langmuir models with high monolayer adsorption capacity in short time that confirm their applicability and suggest their attractive candidates for removal of under study dye.
-
artificial neural network ann method for modeling of sunset yellow dye adsorption using zinc oxide nanorods loaded on activated carbon kinetic and isotherm study
Spectrochimica Acta Part A: Molecular and Biomolecular Spectroscopy, 2015Co-Authors: M Maghsoudi, Mehrorang Ghaedi, A Zinali, A M Ghaedi, Mohammad Hossein HabibiAbstract:Abstract In this research, ZnO nanoparticle loaded on activated carbon (ZnO-NPs-AC) was synthesized simply by a low cost and nontoxic procedure. The characterization and identification have been completed by different techniques such as SEM and XRD analysis. A three layer artificial neural network (ANN) model is applicable for accurate prediction of dye removal percentage from aqueous solution by ZnO-NRs-AC following conduction of 270 experimental data. The network was trained using the obtained experimental data at optimum pH with different ZnO-NRs-AC amount (0.005–0.015 g) and 5–40 mg/L of sunset yellow dye over contact time of 0.5–30 min. The ANN model was applied for prediction of the removal percentage of present systems with Levenberg–Marquardt algorithm (LMA), a Linear Transfer Function (purelin) at output layer and a tangent sigmoid Transfer Function (tansig) in the hidden layer with 6 neurons. The minimum mean squared error (MSE) of 0.0008 and coefficient of determination (R2) of 0.998 were found for prediction and modeling of SY removal. The influence of parameters including adsorbent amount, initial dye concentration, pH and contact time on sunset yellow (SY) removal percentage were investigated and optimal experimental conditions were ascertained. Optimal conditions were set as follows: pH, 2.0; 10 min contact time; an adsorbent dose of 0.015 g. Equilibrium data fitted truly with the Langmuir model with maximum adsorption capacity of 142.85 mg/g for 0.005 g adsorbent. The adsorption of sunset yellow followed the pseudo-second-order rate equation.
-
competitive adsorption of methylene blue and brilliant green onto graphite oxide nano particle following derivative spectrophotometric and principal component artificial neural network model methods for their simultaneous determination
Journal of Industrial and Engineering Chemistry, 2014Co-Authors: N Zeinali, Mehrorang Ghaedi, G ShafieAbstract:Abstract In this work, the competitive adsorption of methylene blue (MB) and brilliant green (BG) onto graphite oxide (GO) nanoparticles followed by their accurate and reproducible determination by second order derivative spectrophotometry (SODS) and principal component–artificial neural network model (PCA–ANN) model has been studied. The evaluation of kinetic and isotherm studies was investigated at optimum experimental conditions set as pH = 7.0, 8 mg of GO and 14 min contact time in binary systems. The equilibrium amounts of MB and BG dyes in binary mixture adsorbed onto GO-NP has opposite correlation with their initial concentration. Principal component analysis (PCA) used to minimize the dimensionality of large data sets via reducing the number of spectral data by a three-layered feed-forward artificial neural network (ANN) trained by Levenberg–Marquardt back-propagation algorithm. The ANN model was able to predict the concentrations of both dyes in mixtures with a tangent sigmoid Transfer Function (tansig) at hidden layer with 20 neurons and a Linear Transfer Function (purelin) at output layer. Several isotherm models were applied to experimental data and the isotherm constants were calculated for BG and MB dyes. Among the applied models, the extended Freundlich isotherm model adequately predicts the multi-component adsorption equilibrium data at moderate ranges of concentration.
Eatock R Taylor - One of the best experts on this subject based on the ideXlab platform.
-
group dynamics and wave resonances in a narrow gap modes and reduced group velocity
Journal of Fluid Mechanics, 2020Co-Authors: Wenhua Zhao, P H Taylor, Hugh Wolgamot, Bernard Molin, Eatock R TaylorAbstract:The spatial and temporal structure of the resonant fluid response in a narrow gap (the so-called gap resonance) between two identical fixed boxes is investigated experimentally. Transient wave groups are used to excite the gap resonance from different wave approach directions. This shows a strong beating pattern and a very long duration, reflecting that gap resonance is a multi-mode resonant and weakly damped phenomenon. For head sea excitation the Linear Transfer Function of the $m=2$ gap mode is as significant as that of the $m=1$ mode. Gap resonance can be driven through different mechanisms, e.g. Linear excitation and a nonLinear frequency-doubling process. Significant wave group structure is shown in the gap, and the group structure is more distinct in the case with frequency doubling, i.e. long wave, excitation. Then it is clearer visually that the groups originate at the end of the gap, propagate along the gap and are then partially reflected from the other end. The groups within the gap are very clear because the group velocity is close to constant for the first few gap resonance modes, and much smaller than that for free waves on the open sea. In contrast, the phase speed of waves in the gap is larger than that for free waves outside. Only in the limit of short waves do the group velocity and phase speed of the gap modes tend to those of deep-water free waves. The group and phase speeds from these experiments match well the theoretical forms given by Molin et al. ( Appl. Ocean Res. , vol. 24 (5), 2002, pp. 247–260), albeit for a slightly different box cross-sectional shape.
-
group dynamics and wave resonances in a narrow gap modes and reduced group velocity
Journal of Fluid Mechanics, 2020Co-Authors: Wenhua Zhao, P H Taylor, Hugh Wolgamot, Bernard Molin, Eatock R TaylorAbstract:The spatial and temporal structure of the resonant fluid response in a narrow gap (the so-called gap resonance) between two identical fixed boxes is investigated experimentally. Transient wave groups are used to excite the gap resonance from different wave approach directions. This shows a strong beating pattern and a very long duration, reflecting that gap resonance is a multi-mode resonant and weakly damped phenomenon. For head sea excitation the Linear Transfer Function of the mode. Gap resonance can be driven through different mechanisms, e.g. Linear excitation and a nonLinear frequency-doubling process. Significant wave group structure is shown in the gap, and the group structure is more distinct in the case with frequency doubling, i.e. long wave, excitation. Then it is clearer visually that the groups originate at the end of the gap, propagate along the gap and are then partially reflected from the other end. The groups within the gap are very clear because the group velocity is close to constant for the first few gap resonance modes, and much smaller than that for free waves on the open sea. In contrast, the phase speed of waves in the gap is larger than that for free waves outside. Only in the limit of short waves do the group velocity and phase speed of the gap modes tend to those of deep-water free waves. The group and phase speeds from these experiments match well the theoretical forms given by Molin et al. (Appl. Ocean Res., vol. 24 (5), 2002, pp. 247–260), albeit for a slightly different box cross-sectional shape.
J A Hernandez - One of the best experts on this subject based on the ideXlab platform.
-
direct neural network modeling for separation of Linear and branched paraffins by adsorption process for gasoline octane number improvement
Fuel, 2014Co-Authors: A Bassam, R A Condegutierrez, Jesus Castillo, Georgina C Laredo, J A HernandezAbstract:Abstract An artificial neural network (ANN) approach was used to develop a new predictive model for the calculation of hydrocarbons breakthrough curves in separation of Linear and branched paraffins by adsorption process. Three-layer ANN architecture was trained using an experimental database and the concentration at t time over initial concentration ( C / C o ) was calculated as output variable. Experimental temperature ( T ), times of adsorption ( t ), octane number ( ON ) and the density ( ρ ) of the hydrocarbons were considered as main input variables for the model. For the ANN optimization process, the Levenberg–Marquardt (LM) learning algorithm, the hyperbolic tangent sigmoid Transfer-Function and the Linear Transfer-Function were applied. The best fitting training data set was acquired with an ANN architecture composed by 22 neurons in the hidden layer (4-22-1), which made possible to predict the C / C o with a satisfactory efficiency ( R 2 > 0.96). A suitable accuracy of the ANN model was achieved with a mean percentage error (MPE) of ∼5%. All the C / C o predicted with the ANN model were statistically analyzed and compared with the “true” C / C o experimental data reported in the experiments carried out in the lab. With all these results, we suggest that the ANN model could be used as a tool for the reliable prediction of the breakthrough curves obtained during the separation of Linear and branched paraffins by adsorption processes.
-
the use of artificial neural network ann for modeling the useful life of the failure assessment in blades of steam turbines
Engineering Failure Analysis, 2013Co-Authors: J A Rodriguez, El Y Hamzaoui, J E Flores, J C Garcia, J A Hernandez, A L TejedaAbstract:Abstract Steam turbines have many applications in various industrial sectors and by common experience blade failures are the main origin of operational breakdowns in these machines, causing great economic loss in turbo machinery industry. The turbines are designed to work in stable conditions of operation. Nevertheless, failure in blades has been present after a short time period of work. These failures commonly attributed to resonance stress of the blades at different stages to certain excitation frequencies. Artificial neural network (ANN) approach was developed to predict the useful life (UL) of the blades. The configuration 6–3–1 (6 inputs, 3 hidden and 1 output neurons) presented an excellent agreement (R2 = 0.9912 and RMSE = 0.00022) between experimental and simulated useful life value considering the hyperbolic tangent sigmoid and Linear Transfer Function in the hidden layer and output layer. In the following study, the sensitivity analysis was carried out, and showed, also that all studied input variables (resonance stress, frequency ratio, dynamic stress, damping, fatigue strength, mean stress) have strong effect on blades steam turbines in terms of useful life. However, the resonance stress is the most influential parameter with relative importance of 35.5%, followed by frequency ratio. The results showed that neural network modeling could effectively predict and simulate the behavior of life cycles assessment in blades of steam turbines.
-
the use of artificial neural network ann for modeling the useful life of the failure assessment in blades of steam turbines
Engineering Failure Analysis, 2013Co-Authors: J A Rodriguez, El Y Hamzaoui, J E Flores, J C Garcia, J A Hernandez, A L TejedaAbstract:Abstract Steam turbines have many applications in various industrial sectors and by common experience blade failures are the main origin of operational breakdowns in these machines, causing great economic loss in turbo machinery industry. The turbines are designed to work in stable conditions of operation. Nevertheless, failure in blades has been present after a short time period of work. These failures commonly attributed to resonance stress of the blades at different stages to certain excitation frequencies. Artificial neural network (ANN) approach was developed to predict the useful life (UL) of the blades. The configuration 6–3–1 (6 inputs, 3 hidden and 1 output neurons) presented an excellent agreement (R2 = 0.9912 and RMSE = 0.00022) between experimental and simulated useful life value considering the hyperbolic tangent sigmoid and Linear Transfer Function in the hidden layer and output layer. In the following study, the sensitivity analysis was carried out, and showed, also that all studied input variables (resonance stress, frequency ratio, dynamic stress, damping, fatigue strength, mean stress) have strong effect on blades steam turbines in terms of useful life. However, the resonance stress is the most influential parameter with relative importance of 35.5%, followed by frequency ratio. The results showed that neural network modeling could effectively predict and simulate the behavior of life cycles assessment in blades of steam turbines.
-
optimal performance of cod removal during aqueous treatment of alazine and gesaprim commercial herbicides by direct and inverse neural network
Desalination, 2011Co-Authors: El Y Hamzaoui, J A Hernandez, S Silvamartinez, A Bassam, A Alvarez, C LizamabahenaAbstract:Abstract A direct and inverse artificial neural network (ANN and ANNi) approach was developed to predict the chemical oxygen demand (COD) removal during the degradation of alazine and gesaprim commercial herbicides under various experimental conditions. The configuration 9–9–1 (9 inputs, 9 hidden and 1 output neurons) presented an excellent agreement (R2 = 0.9913) between experimental and simulated COD value considering the hyperbolic tangent sigmoid and Linear Transfer Function in the hidden layer and output layer. The sensitivity analysis showed that all studied input variables (reaction time, pH, herbicide concentration, contaminant, US ultrasound, UV light intensity, [TiO2]o,[K2S2O8]o, and SR solar radiation) have strong effect on the degradation of the commercial herbicide in terms of COD removal. In addition, reaction time is the most influential parameter with relative importance of 33.49%, followed by initial herbicide concentration. COD optimal performance was carried out by inverting artificial neural network. Now, ANNi could calculate the optimal unknown parameter (reaction time) to obtain a COD required. Very low percentage of error and short computing makes this methodology attractive to be applied to the on-line control of Advanced Oxidation Process (AOP) over the degradation of commercial herbicide.
-
estimation of static formation temperatures in geothermal wells by using an artificial neural network approach
Computers & Geosciences, 2010Co-Authors: A Assam, E Santoyo, Jorge Andaverde, J A Hernandez, O M EspinozaojedaAbstract:An artificial neural network (ANN) approach was used to develop a new predictive model for the calculation of static formation temperature (SFT) in geothermal wells. A three-layer ANN architecture was successfully trained using a geothermal borehole database, which contains ''statistically normalised'' SFT estimates. These estimates were inferred from seven analytical methods commonly used in geothermal industry. Bottom-hole temperature (BHT) measurements and shut-in times were used as main input variables for the ANN training. Transient temperature gradients were used as secondary variables. The Levenberg-Marquardt (LM) learning algorithm, the hyperbolic tangent sigmoid Transfer Function and the Linear Transfer Function were used for the ANN optimisation. The best training data set was obtained with an ANN architecture composed by five neurons in the hidden layer, which made possible to predict the SFT with a satisfactory efficiency (R^2>0.95). A suitable accuracy of the ANN model was achieved with a percentage error less than +/-5%. The SFTs predicted by the ANN model were statistically analyzed and compared with ''true'' SFTs measured in synthetic experiments and actual BHT logs collected in geothermal boreholes during long shut-in times. These data sets were processed both to validate the new ANN model and to avoid bias. The SFT estimates inferred from the ANN validation process were in good agreement (R^2>0.95) with the ''true'' SFT data reported for synthetic and field experiments. The results suggest that the new ANN model could be used as a practical tool for the reliable prediction of SFT in geothermal wells using BHT and shut-in time as input data only.