Optimal Artificial Neural Network Model Research Articles

Hydrogen production via sodium borohydride hydrolysis catalyzed by cobalt ferrite anchored nitrogen-and sulfur co-doped graphene hybrid nanocatalyst: Artificial neural network modeling approach

The sluggish kinetics of the Sodium borohydride (NaBH4) hydrolysis process particularly in alkaline conditions requires the design of high-performance low-cost catalysts. Herein, it was aimed to tailor cobalt ferrite anchored nitrogen-and sulfur-doped graphene architecture (CoFe2O4 @N,S-G) via a facile production pathway, to explore its potential application as a catalyst in alkaline NaBH4 hydrolysis reaction for hydrogen production, and to develop an optimal artificial neural network (ANN) architecture to predict hydrogen production rate. In this regard, the influence of several variables such as reaction temperature, NaBH4 concentration, and catalyst loading was explored to determine the optimal operational conditions for effective hydrogen generation. Furthermore, the performance metrics of ANN topologies were investigated to establish the best ANN model for predicting hydrogen generation rate under different operational conditions. The experimental results offered the outstanding catalytic activity of CoFe2O4 @N,S-G towards NaBH4 hydrolysis with the volumetric hydrogen production rate of 8.5 L.min−1.gcat−1 at 25 ℃, and catalyst loading of 0.02 g, and 1.0 M NaBH4 concentration. The CoFe2O4 @N,S-G nanocatalyst was found to retain 94.9% of its initial catalytic activity after 5 consecutive uses, according to the reusability tests. The optimum performance metrics that were determined by the mean squared error (MSE) of 0.00052 and the coefficient of determination (R2) of 0.9989 were achieved for the ANN model with the configuration of 3–10–5–1 trained by Levenberg-Marquardt backpropagation algorithm. The activation function of tansig and purelin functions at hidden and output layers, respectively. The findings revealed that the experimental data were in harmony with the ANN-predicted one, thereby inferring the optimized ANN model could be employed in the forecasting of hydrogen production rate at various operational conditions.

Artificial neural networks (ANNs) for modeling efficient factors in predicting pap smear screening behavior change stage.

Background and objectivesCervical cancer is ranked as the third most prevalent cancer that affects women all over the world and Pap smear seems to be the single most critical intervention to prevent cervical cancer. In the present study, the effects of demographic factors (age, education level, job, income level, marriage age, pregnancy, child number, breastfeeding, and menopause), insurance type, disease history and screening (sono and mammography, breast problem) and cancer information on Pap smear screening and behavior stage of change were investigated and modeled using an artificial neural network model (ANN).Materials and methodsData were collected from a descriptive-analytical cross-sectional study. This research was conducted on 1898 female employees of governmental agencies of Birjand, a city located in the east of Iran. The questionnaire consisted of four parts (socioeconomic, reproductive characteristics, information about cervical cancer screening, and stage of change for cervical cancer screening). Multilayer feed-forward back-propagation neural networks were used to detect the patterns between variables using a neural network with 14 inputs and one output. To find out the neural network with the minimum sum of squared errors, we evaluated the performance of all neural networks using varying algorithms and numbers of neurons in the hidden layer. For this purpose, the data collected from 1898 women were analyzed using SPSS-22 software.ResultsIn the optimal ANN model, the variables of marriage age, age, breastfeeding, and the number of children were identified as the most significant factors with 18.3, 16.3, 7.3, and 7.3 percent, respectively, whereas the history of cancer, job, pregnancy, and menopause had importance of lower than 5 percent.ConclusionOur findings showed that among many associated variables, the marriage age, age, breastfeeding, and the number of children were the most important predictors for the behavioral stage of change. Thus, it seems, focusing on these factors may lead to the adoption of effective programs and policies to improve cervical cancer screening practices in women.

Artificial Neural Network-Forecasted Compression Strength of Alkaline-Activated Slag Concretes

The utilization of ordinary Portland cement (OPC) in conventional concretes is synonymous with high carbon emissions. To remedy this, an environmentally friendly concrete, alkaline-activated slag concrete (AASC), where OPC is completely replaced by ground granulated blast-furnace slag (GGBFS) industrial waste, is one of the currently pursued research interests. AASC is not commonly used in the construction industry due to limitations in experience and knowledge on the mix proportions and mechanical properties. To circumvent great labour in the experimental works toward the determination of the optimal properties, this study, therefore, presents the compressive strength prediction of AASC by employing the back-propagation artificial neural network (ANN) modelling technique. To construct this model, a sufficiently equipped experimental databank was built from the literature covering varied mix proportion effects on the compressive strength of AASC. For this, four model variants with different input parameter considerations were examined and the ideal ANN architecture for each model with the best input number–hidden layer neuron number–output number format was identified to improve its prediction accuracy. From such a setting, the most accurate prediction model with the highest determination coefficient, R2, of 0.9817 was determined, with an ANN architecture of 8-18-1 containing inputs such as GGBFS, a fine to total aggregate ratio, sodium silicate, sodium hydroxide, mixing water, silica modulus of activator, percentage of sodium oxide and water–binder ratio. The prediction accuracy of the optimal ANN model was then compared to existing ANN-based models, while the variable selection was compared to existing AASC models with other machine learning algorithms, due to limitations in the ANN-based model. To identify the parametric influence, the individual relative importance of each input variable was determined through a sensitivity analysis using the connection weight approach, whose results indicated that the silica modulus of the activator and sodium silicate greatly affected the AASC compressive strength. The proposed methodology demonstrates that the ANN-based model can predict the AASC compressive strength with a high accuracy and, consequently, aids in promoting the utilization of AASC in the construction industry as green concrete without performing destructive tests. This prediction model can also accelerate the use of AASC without using a cement binder in the concrete matrix, leading to produce a sustainable construction material.

Modeling of water-PCM solar thermal storage system for domestic hot water application using Artificial neural networks

• Artificial Neural Network model of solar thermal storage for hot water application. • Framework to develop and optimize the artificial neural network model parameters. • Validated numerical model used to train and test the artificial neural network model. • Artificial neural network model outperforms traditional regression modeling. • Neural network model yields five orders improvement in the computational time. • Optimized model-generated design map for the solar thermal storage system. Numerical modeling of solar thermal storage systems is often challenged with limitations on the computational effort due to their transient non-linear behavior that dictates accurate modeling of the physics over long-term operations (i.e., annual). Such challenges result into scarcity of literature on comprehensive design guidelines for solar thermal storage systems. This study presents a framework through which the potential of artificial neural network (ANN) modeling of a hybrid solar thermal storage system involving phase change materials is extensively investigated. An experimentally validated numerical model for the system is used to generate the training and testing datasets for the ANN model. The effect of changing the sampling method and the number of training samples is studied on the ANN model prediction. The results show that Sobol sequence sampling is superior to other sampling methods especially for low number of samples. The best sampling method is utilized to generate the training dataset with which the hyperparameters of the learning algorithm are optimized. The optimized ANN model is ultimately used to predict the system solar fraction under various design conditions to develop design maps that offer better visualization and sizing guidelines for the hybrid solar thermal storage systems. ANN is shown to offer a potential candidate for accurate and computationally efficient modeling of complex thermal systems. Upon proper configuration and training, the ANN model can accurately (i.e., a coefficient of determination of 0.9999) predict the performance of the hybrid thermal storage system with approximately five orders of magnitude reduction in computational time compared to conventional numerical models.

Application of Artificial Neural Networks for Predicting the Stability of Rectangular Tunnels in Hoek–Brown Rock Masses

An artificial neural network (ANN) model for predicting the stability of rectangular tunnels in rock masses based on the Hoek–Brown (HB) failure criterion is presented in this study. Since the safety assessment of the tunnel stability is one critical issue for civil engineers during the construction, it is very important to develop a reliable and accurate stability analysis of such problems. The finite element limit analysis (FELA) with the HB failure criterion is used to develop the numerical upper and lower bound solutions of the problem of rectangular tunnels in rock masses. A novel machine learning-aided prediction of this problem is then developed based on the datasets of the numerical bound solutions obtained from the FELA. The inputs consist of six dimensionless parameters including the cover-depth ratio of tunnels, the width ratio of tunnels, the normalized uniaxial compressive strength, the geological strength index, the mi parameter, and the degree of disturbance of rock masses. The results show that the optimal ANN models provide very great accuracy in predicting the stability of the rectangular tunnels based on the HB failure criterion. The solutions will provide a prompt assessment of tunnel stability in rock masses for geotechnical engineers during the construction of rock tunnels.

Rapid biodegradation of diazinon using a novel strain of Candida pseudolambica

Diazinon has been widely applied in the agricultural sector as an organophosphorus insecticide because of its toxicity, while it is a serious threat to the biodiversity of the environment. A yeast strain being capable of biodegrading diazinon was isolated from pesticide-contaminated agricultural soil. Analysis of sequences spanning the Intergenic Spacer (ITS) region showed that the isolated strain was Candida pseudolambica. The ability of this strain for diazinon biodegradation was evaluated, and the condition of the aqueous solution was optimized applying response surface methodology (RSM) and validated by the artificial neural network (ANN). At the optimum condition, in a mineral salt medium (MSM) containing a high concentration of diazinon (775 mg/l) and 2.25 g/l glucose as a co-substrate with an inoculum size of 8% and incubated at 30 °C, the isolated strain of C. pseudolambica demonstrated 69.6% removal of diazinon in a short period of time (24 h). Substantial biodegradation efficiency (34%) was also achieved after 24 h incubation of the isolate in a medium that 500 mg/l of diazinon was utilized as the only carbon source. The optimum ANN model obtained with 5 neurons in the hidden layer resulted in R 2 > 0.98, and for the RSM, R 2 was 0.993. Results indicated the remarkable ability of the isolated strain for rapid degradation of high concentrations of diazinon, which could be promising for large-scale bioremediation applications. • Potential yeast strain in diazinon degradation was isolated from contaminated soil. • Rapid degradation of high diazinon concentration was achieved within 24 h. • Influential parameters on diazinon biodegradation were studied using RSM method. • ANN model greatly confirmed the RSM method application.

Development of QSAR-based (MLR/ANN) predictive models for effective design of pyridazine corrosion inhibitors

Twenty pyridazine derivatives with previously reported experimental data were utilized to develop predictive models for the anticorrosion abilities of pyridazine-based compounds. The models were developed by using quantitative structure-activity relationship (QSAR) as a tool to relate essential molecular descriptors of the pyridazines with their experimental inhibition efficiencies. Chemical descriptors associated with frontier molecular orbitals (FMOs) were obtained using density functional theory (DFT) calculations, while others were obtained from additional calculations effected on Dragon 7 software. Five descriptors together with concentrations of the pyridazine inhibitors were used to develop the multiple linear regression (MLR) and artificial neural network (ANN) models. The optimal ANN model yielded the best results with 111.5910, 10.5637 and 10.2362 for MSE, RMSE and MAPE respectively. The results revealed that ANN gave better results than MLR model. The proposed models suggested that the adsorption of pyridazine derivatives is dependent on the five descriptors.Five pyridazine compounds were theoretically designed.

Evaluation of the elastic modulus of pavement layers using different types of neural networks models

Introduction. This paper studies the capability of different types of artificial neural networks (ANN) to predict the modulus of elasticity of pavement layers for flexible asphalt pavement under operating conditions. The falling weight deflectometer (FWD) was selected to simulate the dynamic traffic loads and measure the flexural bowls on the road surface to obtain the database of ANN models.Materials and Methods. Artificial networks types (the feedforward backpropagation, layer-recurrent, cascade back- propagation, and Elman backpropagation) are developed to define the optimal ANN model using Matlab software. To appreciate the efficiency of every model, we used the constructed ANN models for predicting the elastic modulus values for 25 new pavement sections that were not used in the process of training, validation, or testing to ensure its suitability. The efficiency measures such as mean absolute error (MAE), the coefficient of multiple determinations R2, Root Mean Square Error (RMSE), Mean Absolute Percent Error (MAPE) values were obtained for all models results.Results. Based on the performance parameters, it was concluded that among these algorithms, the feed-forward model has a better performance compared to the other three ANN types. The results of the best four models were compared to each other and to the actual data obtained to determine the best method.Discussion and Conclusions. The differences between the results of the four best models for the four types of algorithms used were very small, as they showed the closeness between them and the actual values. The research results confirm the possibility of ANN-based models to evaluate the elastic modulus of pavement layers speedily and reliably for using it in the structural assessment of (NDT) flexible pavement data at the appropriate time.

A NUMERICAL STUDY AIMED AT FINDING OPTIMAL ARTIFICIAL NEURAL NETWORK MODEL COVERING EXPERIMENTALLY OBTAINED HEAT TRANSFER CHARACTERISTICS OF HYDRONIC UNDERFLOOR RADIANT HEATING SYSTEMS RUNNING VARIOUS NANOFLUIDS

A NUMERICAL STUDY AIMED AT FINDING OPTIMAL ARTIFICIAL NEURAL NETWORK MODEL COVERING EXPERIMENTALLY OBTAINED HEAT TRANSFER CHARACTERISTICS OF HYDRONIC UNDERFLOOR RADIANT HEATING SYSTEMS RUNNING VARIOUS NANOFLUIDS

Clean technology for sequestering Rhodamine B dye on modified mango pod using artificial intelligence techniques

In this study, an acid-modified mango pod (AMMP) was prepared as adsorbent for removal of Rhodamine dye and the adsorption uptake was also determined using machine learning algorithms namely, Artificial Neural network (ANN) and Adaptive neuro-fuzzy inference systems (ANFIS) respectively. The prepared adsorbent was characterized with SEM, FTIR, EDX, and PXRD techniques. Surface chemistry revealed the presence of O–H stretching of free hydroxyls and alcohols and phenols, C–H stretch of alkanes, C≡C stretch of alkynes, CO stretch of ketones, lactones, and carboxylic anhydrides, –CC- stretching of alkenes, C–N stretch of aliphatic amines and O–H bend of carboxylic acids. Surface morphologies of the AMMP revealed well-developed and open porous surfaces needed for an efficient adsorption of the dye molecule. EDX analysis showed an increase in the carbon contents from 79.94% (raw) to 80.12% (AMMP) by weight and 86.89% (raw) to 89.11% (AMMP) by atom. The crystallinity structure revealed the new and intense peak formations and the presence of ordered (organized) crystalline structures on AMMP. Optimal ANN architectures, activation functions and training algorithms were selected after several stimulations with different network parameters while the ANFIS model was tested with three clustering approaches namely, Grid partitioning, fuzzy c-means, and subtractive clustering to carry out the extensive studies to optimally predict the adsorption efficiency/capacity of Rhodamine dye onto AMMP. The performance of the developed models was evaluated using the following statistical metrics; the optimal ANN model gave RMSE ​= ​10.422, MAD ​= ​3.673, MAPE ​= ​5.409, R2 ​= ​0.977 while with optimal ANFIS model gave a RMSE ​= ​9.246, MAD ​= ​4.938, MAPE ​= ​4.672, R2 ​= ​0.984 ​at the testing phase. The lower value of the statistical parameters indicates better performance in both models. Batch adsorption studies gave qmax of 456.67 ​mg/g, 389.51 ​mg/g, and 410.56 ​mg/g for the experimental data, ANN and ANFIS models respectively thus, suggesting their good correlations. Technoeconomic aspects of the study present that AMMP is approximately 8 times cheaper, translating to saving cost of 225.2 USD/kg when compared with 259.5 USD/kg for commercial activated carbon.

Performance Analysis of an Optimized ANN Model to Predict the Stability of Smart Grid

The stability of the power grid is concernment due to the high demand and supply to smart cities, homes, factories, and so on. Different machine learning (ML) and deep learning (DL) models can be used to tackle the problem of stability prediction for the energy grid. This study elaborates on the necessity of IoT technology to make energy grid networks smart. Different prediction models, namely, logistic regression, naïve Bayes, decision tree, support vector machine, random forest, XGBoost, k‐nearest neighbor, and optimized artificial neural network (ANN), have been applied on openly available smart energy grid datasets to predict their stability. The present article uses metrics such as accuracy, precision, recall, f1‐score, and ROC curve to compare different predictive models. Data augmentation and feature scaling have been applied to the dataset to get better results. The augmented dataset provides better results as compared with the normal dataset. This study concludes that the deep learning predictive model ANN optimized with Adam optimizer provides better results than other predictive models. The ANN model provides 97.27% accuracy, 96.79% precision, 95.67% recall, and 96.22% F1 score.

Optimized Artificial Neural Network for Evaluation: C4 Alkylation Process Catalyzed by Concentrated Sulfuric Acid.

In this work, an artificial neural network was first achieved and optimized for evaluating product distribution and studying the octane number of the sulfuric acid-catalyzed C4 alkylation process in the stirred tank and rotating packed bed. The feedstock compositions, operating conditions, and reactor types were considered as input parameters into the artificial neural network model. Algorithm, transfer function, and framework were investigated to select the optimal artificial neural network model. The optimal artificial neural network model was confirmed as a network topology of 10-20-30-5 with Bayesian Regularization backpropagation and tan-sigmoid transfer function. Research octane number and product distribution were specified as output parameters. The artificial neural network model was examined, and 5.8 × 10–4 training mean square error, 8.66 × 10–3 testing mean square error, and ±22% deviation were obtained. The correlation coefficient was 0.9997, and the standard deviation of error was 0.5592. Parameter analysis of the artificial neural network model was employed to investigate the influence of operating conditions on the research octane number and product distribution. It displays a bright prospect for evaluating complex systems with an artificial neural network model in different reactors.

Quantitative computed tomography imaging-based classification of cement dust-exposed subjects with an artificial neural network technique

Background and objectiveCement dust exposure is likely to affect the structural and functional alterations in segmental airways and parenchymal lungs. This study develops an artificial neural network (ANN) model for identifying cement dust-exposed (CDE) subjects using quantitative computed tomography-based airway structural and functional features. MethodsWe obtained the airway features in five central and five sub-grouped segmental regions and the lung features in five lobar regions and one total lung region from 311 CDE and 298 non-CDE (NCDE) subjects. The five-fold cross-validation method was adopted to train the following classification models:ANN, support vector machine (SVM), logistic regression (LR), and decision tree (DT). For all the classification models, linear discriminant analysis (LDA) and genetic algorithm (GA) were applied for dimensional reduction and hyperparameterization, respectively. The ANN model without LDA was also optimized by the GA method to observe the effect of the dimensional reduction. ResultsThe genetically optimized ANN model without the LDA method was the best in terms of the classification accuracy. The accuracy, sensitivity, and specificity of the GA–ANN model with four layers were greater than those of the other classification models (i.e., ANN, SVM, LR, and DT using LDA and GA methods) in the five-fold cross-validation. The average values of accuracy, sensitivity, and specificity for the five-fold cross-validation were 97.0%, 98.7%, and 98.6%, respectively. ConclusionsWe demonstrated herein that a quantitative computed tomography-based ANN model could more effectively detect CDE subjects when compared to their counterpart models. By employing the model, the CDE subjects may be identified early for therapeutic intervention.

Hyperparameters optimization of neural network using improved particle swarm optimization for modeling of electromagnetic inverse problems

AbstractOptimization of hyperparameters of artificial neural network (ANN) usually involves a trial and error approach which is not only computationally expensive but also fails to predict a near-optimal solution most of the time. To design a better optimized ANN model, evolutionary algorithms are widely utilized to determine hyperparameters. This work proposes hyperparameters optimization of the ANN model using an improved particle swarm optimization (IPSO) algorithm. The different ANN hyperparameters considered are a number of hidden layers, neurons in each hidden layer, activation function, and training function. The proposed technique is validated using inverse modeling of two meander line electromagnetic bandgap unit cells and a slotted ultra-wideband antenna loaded with EBG structures. Three other evolutionary algorithms viz. hybrid PSO, conventional PSO, and genetic algorithm are also adopted for the hyperparameter optimization of the ANN models for comparative analysis. Performances of all the models are evaluated using quantitative assessment parameters viz. mean square error, mean absolute percentage deviation, and coefficient of determination (R2). The comparative investigation establishes the accurate and efficient prediction capability of the ANN models tuned using IPSO compared to other evolutionary algorithms.

Congo red dye removal from aqueous environment by cationic surfactant modified-biomass derived carbon: Equilibrium, kinetic, and thermodynamic modeling, and forecasting via artificial neural network approach

Herein, it was aimed to optimize, model, and forecast the biosorption of Congo Red onto biomass-derived biosorbent. Therefore, the waste-orange-peels were processed to fabricate biomass-derived carbon, which was activated by ZnCl2 and modified with cetyltrimethylammonium bromide. The physicochemical properties of the biosorbents were explored by scanning electron microscopy and N2 adsorption/desorption isotherms. The effects of pH, initial dye concentration, temperature, and contact duration on the biosorption capacity were investigated and optimized by batch experimental process, followed by the kinetics, equilibrium, and thermodynamics of biosorption were modeled. Furthermore, various artificial neural network (ANN) architectures were applied to experimental data to optimize the ANN model. The kinetic modeling of the biosorption offered that biosorption was in accordance both with the pseudo-second-order and saturation-type kinetic model, and the monolayer biosorption capacity was calculated as 666.67 mg g−1 at 25 °C according to Langmuir isotherm model. According to equilibrium modeling, the Freundlich isotherm model was better fitted to the experimental data than the Langmuir isotherm model. Moreover, the thermodynamic modeling revealed biosorption took place spontaneously as an exothermic process. The findings revealed that the best ANN architecture trained with trainlm as the backpropagation algorithm, with tansig-purelin transfer functions, and 14 neurons in the single hidden layer with the highest coefficient of determination (R2 = 0.9996) and the lowest mean-squared-error (MSE = 0.0002). The well-agreement between the experimental and ANN-forecasted data demonstrated that the optimized ANN model can predict the behavior of the anionic dye biosorption onto biomass-derived modified carbon materials under various operation conditions.

Artificial Neural Network Modeling and Numerical Simulation of Syngas Fuel and Injection Timing Effects on the Performance and Emissions of a Heavy-Duty Compression Ignition Engine.

The use of syngas as an alternative fuel in compression ignition engines is a potential way to curb the emission of pollutants and optimize the performance of these engines. The present research studied the effect of changing fuel injection timing and adding syngas on the output of a heavy-duty diesel engine. The optimal mode of the turbulence model, fuel spray model, combustion model, and pollutant emission model was used to solve computational fluid dynamics. Changing fuel injection timing from 70 to 10° before top dead center (BTDC) and diesel variants, including conventional diesel, diesel + 20% syngas, and diesel + 40% syngas, is the strategy studied here. It was found that the use of syngas could reduce emissions significantly. The in-cylinder mean effective pressure was the highest for diesel + 20% syngas. On the other hand, increasing the rate of syngas and retarding injection timing reduced the ignition period and in-cylinder temperature. The lowest rate of CO emission was obtained from diesel + 40% syngas at a fuel injection timing of 70° BTDC, whereas the lowest particulate matter emission was related to diesel + 40% syngas at 40° BTDC injection timing. The lowest rate of CO2 emission was related to diesel + 40% syngas at a fuel injection timing of 10° BTDC, while the same timing for conventional diesel exhibited the lowest NOX emission rate. Finally, the performance parameters of the engine including indicated power, indicated fuel consumption, and indicated thermal efficiency were decreased with the increase in syngas fraction, so that their highest values were obtained from the conventional diesel at the injection timing of 40° BTDC. In addition, an artificial neural network (ANN) model based on a standard back-propagation learning algorithm was developed for modeling the performance and emissions of the engine. The results for the optimum ANN model showed that the optimal ANN has two hidden layers with 20–25 neurons and the transfer function of logsig–logsig for hidden layers 1 and 2, respectively, and can predict different parameters of the engine for different modes. The correlation coefficients (R-value) of optimal topology for training, validation, and testing are 0.99992, 0.96612, and 0.93424, respectively. The results for the optimum ANN model showed that the constructed model sufficiently predicts the performance and emissions of the CI diesel engine.

Application of Artificial Neural Network Model for Optimized Control of Condenser Water Temperature Set-Point in a Chilled Water System

In this study, real-time predictive control and optimization model based on an ANN (artificial neural network) was developed to evaluate the cooling energy saving performance of the optimized control of CndWT (condenser water temperature). For this purpose, the difference in TCEC (total cooling energy consumption) between the conventional control strategy when the CndWT produced by the cooling tower is fixed and the optimized control strategy when real-time control of the CndWT through the optimal ANN model is applied was compared and analyzed. For the modeling of the building to be simulated, the co-simulation of EnergyPlus and MATLAB was built through the middleware Building Controls Virtual Test Bed. For the prediction of TCEC, an ANN model was developed through MATLAB's neural network toolbox. The model accuracy of the ANN was examined through Cv(RMSE) index and as a result, Cv(RMSE) of the optimized ANN model turned out to be approximately 25 %. More importantly, the predictive control technique was able to save TCEC by 5.6 % compared to the conventional control method constantly fixing CndWT set-point to 30 °C. These results showed that the CndWT needs to be dynamically controlled using artificial intelligence technique such as ANN model and that significant energy savings were achievable compared to the conventional fixed control.

Utilization of a double-cross-linked amino-functionalized three-dimensional graphene networks as a monolithic adsorbent for methyl orange removal: Equilibrium, kinetics, thermodynamics and artificial neural network modeling

Herein, it is aimed to develop a high-performance monolithic adsorbent to be utilized in methyl orange (MO) adsorption. Therefore, amino-functionalized three-dimensional graphene networks (3D-GNf) fulfilling the requirements of reusability and high capacity have been fabricated via hydrothermal self-assembly approach followed by a double-crosslinking strategy. The potential utilization of 3D-GNf as an adsorbent for removal MO has been assessed using both batch-adsorption studies and an artificial neural network (ANN) approach. Graphene oxide sheets have been amino-functionalized and cross-linked, by ethylenediamine (EDA) during hydrothermal treatment, following the glutaraldehyde has used as a double-crosslinking agent to facilitate the crosslinking of architecture. The successful fabrication of 3D-GNf has been confirmed by field-emission scanning electron microscopy (FESEM), Fourier transform infrared (FT-IR), Raman and X-ray photoelectron spectroscopy (XPS). Moreover, N2 adsorption/desorption isotherms have revealed the high specific surface area (1015 m2 g−1) with high pore volume (1.054 cm3 g−1) and hierarchical porous structure of 3D-GNf. The effect of initial concentration, contact time, and temperature on adsorption capacity have been thoroughly studied, and the kinetics, isotherms, and thermodynamics of MO adsorption have been modelled. The MO adsorption has been well defined by the pseudo-second-order kinetic model and Langmuir isotherm model with a monolayer adsorption capacity of 270.27 mg g−1 at 25 °C. The thermodynamic findings have revealed MO adsorption has occurred spontaneously with an endothermic process. The Levenberg-Marquardt backpropagation algorithm has been implemented to train the ANN model, which has used the activation functions of tansig and purelin functions at the hidden and output layers, respectively. An optimum ANN model with high-performance metrics (coefficient of determination, R2 = 0.9995; mean squared error, MSE = 0.0008) composed of three hidden layers with 5 neurons in each layer was constructed to forecast MO adsorption. The findings have shown that experimental results are consistent with ANN-based data, implying that the suggested ANN model may be used to forecast cationic dye adsorption.

Knowledge-Based Prediction of Load-Carrying Capacity of RC Flat Slab through Neural Network and FEM

The present research work aims to compare the results for predicting the ultimate response of Reinforced Concrete (RC) members using Current Design Codes (CDCs), an alternative method based on the Compressive Force Path (CFP) method, and Artificial Neural Network (ANN). For this purpose, the database of 145 samples of RC Flat Slab with the simple supported condition under concentrated load is developed from the latest published work. All the cases studied were Square Concrete Slabs (SCS). The critical parameters used as input for the study were column dimension, cs, depth of the slab, ds, shear span ratio, a v s / d , longitudinal percentage steel ratio, ρls, yield strength of longitudinal steel, fyls, the compressive strength of concrete, fcs, and ultimate load-carrying capacity, Vus. Seven ANN models were trained using different combinations of input parameters and different points of hidden neurons with different activation functions. The results exhibited that SCS-4 was the most optimized ANN model, having the maximum value of R (89%) with the least values of MSE (0.62%) and MAE (6.2%). It did not only reduce the error but also predicted accurate results with the least quantity of input parameters. The predictions obtained from the studied models (i.e., CDCs, CFP, and ANN) exhibited that results obtained using the ANNs model correlated well with the experimental data. Furthermore, the FEM results for the selected cases show the closer result to the ANN predictions.

Workflow to build a continuous static elastic moduli profile from the drilling data using artificial intelligence techniques

Rock mechanical properties play a crucial role in fracturing design, wellbore stability and in situ stresses estimation. Conventionally, there are two ways to estimate Young’s modulus, either by conducting compressional tests on core plug samples or by calculating it from well log parameters. The first method is costly, time-consuming and does not provide a continuous profile. In contrast, the second method provides a continuous profile, however, it requires the availability of acoustic velocities and usually gives estimations that differ from the experimental ones. In this paper, a different approach is proposed based on the drilling operational data such as weight on bit and penetration rate. To investigate this approach, two machine learning techniques were used, artificial neural network (ANN) and support vector machine (SVM). A total of 2288 data points were employed to develop the model, while another 1667 hidden data points were used later to validate the built models. These data cover different types of formations carbonate, sandstone and shale. The two methods used yielded a good match between the measured and predicted Young’s modulus with correlation coefficients above 0.90, and average absolute percentage errors were less than 15%. For instance, the correlation coefficients for ANN ranged between 0.92 and 0.97 for the training and testing data, respectively. A new empirical correlation was developed based on the optimized ANN model that can be used with different datasets. According to these results, the estimation of elastic moduli from drilling parameters is promising and this approach could be investigated for other rock mechanical parameters.