Optimized ANN Model Research Articles

Measurement of Moisture in Transformer Insulation Using the Intelligent High-Frequency Sensor System

High-frequency sensor-based system is proposed for evaluating the degradation of the transformer insulation through the measurement of moisture concentration. The proposed system employs an intelligent open-ended coaxial probe microwave technique. An optimized ANN model is designed by selecting appropriate features to obtain accurate dielectric characterisation. Redundant feature elimination reduces the computational burden and also bypasses the repeated calibration refresh required to complete RF measurement in the conventional technique. ANN model is trained in such a way that measured impedance mismatch due to the termination by the sample at the probe end is related to its permittivity. The introduction of an intelligent standardization procedure led to a low error in the measurement of moisture (< ±3%) with a sensitivity of 0.027/ppm. This method is found to be simple and faster compared to other existing techniques. Due to the advantage of high-speed measurement and low error, this sensing technique is very suitable for transformer condition monitoring.

ANN model for prediction of thermo-hydraulic performance of a solar air heater with vertical cylindrical ribs

A hybrid computational fluid dynamics-artificial neural network approach is applied to predict the thermo-hydraulic performance factor (THPF) of a solar air heater with vertical cylindrical ribs. 3-D CFD analysis considering effects of rib height, rib diameter, rib pitches are simulated for Re ranging 5000–24000. A total of 504 data sets for different cases are generated using CFD. Based on these data sets, an optimized ANN model is developed to predict the thermo-hydraulic performance. The optimized ANN model has an architecture of 5-25-1 and the mean squared error for this ANN model is 0.000051 for the testing data sets. The maximum THPF value achieved is 1.43 for rib height of 3.5 mm, rib diameter of 3 mm, rib transverse pitch of 20 mm and relative roughness pitch of 10 at Re = 8000. Global sensitivity analysis is also performed based on SHAP (SHapley Additive exPlanations) for the ANN model—Reynolds number is observed to be the most influencing factor with mean absolute SHAP value of 0.031 in predicting THPF along with transverse pitch which has SHAP value very close to Re. Computational CPU time comparison is also performed and approximately 100% reduction is achieved using the optimized ANN model. This research proposed a novel approach that could be successfully implemented in assessing thermal performance of solar-thermal collector systems.

Solar air heater with rotating circular ribs: Hybrid CFD-ANN approach for prediction of thermo-hydraulic performance

A hybrid computational fluid dynamics-artificial neural network approach is implemented to predict the thermo-hydraulic performance factor of a solar air heater with rotating circular ribs. Effects of rib height, rib pitch, and rib rotating speed are investigated for Reynolds numbers ranging from 3800 to 18000. A total of 432 different cases are simulated using CFD. Based on these data sets, an optimized ANN model is developed to predict thermo-hydraulic performance. The optimized ANN model has an architecture of 4-17-17-1 and it has a mean squared error of 3.89 × 10−6 for the testing data sets. The maximum thermo-hydraulic performance achieved is 1.57 for rib height of 1.4 mm, rib pitch of 25 mm, rib rotating speed of 10000 rpm at Reynolds number = 3800. The generalization capacity of the optimized ANN model is tested using experimental results and it is found that ANN predictions are in agreement with CFD simulation results. A comparison of computational time is also performed and approximately 100% reduction in computational time is achieved using the optimized artificial neural network model. This research establishes that ANN can be an excellent design tool for assessing the performance of novel solar air heaters.

Prediction of the effects of climate change on hydroelectric generation, electricity demand, and emissions of greenhouse gases under climatic scenarios and optimized ANN model

In this study, an attempt is made to manage the gap between energy demand and energy supply by predicting hydropower production, energy demand, and greenhouse gas emissions. The interaction between climatic, hydrological, and socio-economic parameters creates a nonlinear and uncertain relationship. The complexity of this nonlinear relationship necessitate the use of ANN to estimate energy demand. To predict energy demand, ANN model is used along with improved Electromagnetic Field Optimization (IEFO) algorithms. The results show, hydroelectric generation in the near future under RCP2.6, RCP4.5, and RCP8.5 is decreased 10.981 MW, 12.933MW, and 14.765MW and in the far future decreased 21.922 MW, 23.649 MW, and 26.742 MW. The energy demand increases in the near future 513 MW and far future 1168 MW. According to forecasting hydropower generation and energy demand, the gap between the demand-supply will increase. Also, the greenhouse gases emissions is increase due to the increase in fossil fuel consumption.

Efficacy evaluation of oxide-MWCNT water hybrid nanofluids: An experimental and artificial neural network approach

The temperature dependencies of the thermophysical properties of different hybrid nanofluids have been investigated in the present work. Laboratory experiments were performed and optimized ANN model was developed for prediction and regression analysis. MWCNT-water based Al2O3, TiO2, ZnO and CeO2 nanofluids were used for this purpose. Metal oxide based nanofluids and MWCNT nanofluids were prepared and mixed in the 80:20 volumetric ratio. Nanofluids were prepared for volumetric concentrations varying from 0.25% to 2.0%. Thermophysical properties of hybrid nanofluids were measured at temperatures varying from 25 °C to 50 °C. Thermal conductivity ratios, specific heat, dynamic viscosity ratio and density were obtained against varying parameters. The CeO2 - MWCNT/water hybrid nanofluid showed highest efficacy with excellent thermophysical properties and highest Mouromtseff number (MO). A hyper-parameter optimized ANN model predicted the properties of hybrid nanofluids across four thermophysical parameters. The ANN predicted results provide good accuracy with experimental results (R > 0.999, MSE < 0.001, Deviations < ± 5%).

Applications of electronic tongue system for quantification of safranal concentration in saffron (Crocus sativus L.)

In the present research the electronic tongue system was proposed consisted of an array of 4 voltammetric sensors to discriminate saffron samples based on the safranal concentration. Different samples were provided by blending saffron samples with distilled water and pure safranal with ethanol. The provided signals by the electronic tongue system were analyzed using the PCA and ANN methods. The total variance among safranal concentrations by PCA method were 90% and 100% in pure safranal and saffron samples, respectively. Also, it was revealed that the electronic tongue could provide good prediction for safranal concentration in saffron as 98.81% accuracy by means of optimized ANN model. Results showed that there are some relationships between HPLC and electronic tongue signals to determine safranal concentration levels in different saffron samples.

Application of Particle Swarm Optimization Algorithm for Optimizing ANN Model in Recognizing Ripeness of Citrus

This paper shows findings of the application of Particle Swarm Optimization (PSO) algorithm in optimizing an Artificial Neural Network that could categorize between ripeness and unripeness stage of citrus suhuensis. The algorithm would adjust the network connections weights and adapt its values during training for best results at the output. Initially, citrus suhuensis fruit’s skin is measured using optically non-destructive method via spectrometer. The spectrometer would transmit VIS (visible spectrum) photonic light radiation to the surface (skin of citrus) of the sample. The reflected light from the sample’s surface would be received and measured by the same spectrometer in terms of reflectance percentage based on VIS range. These measured data are used to train and test the best optimized ANN model. The accuracy is based on receiver operating characteristic (ROC) performance. The result outcomes from this investigation have shown that the achieved accuracy for the optimized is 70.5% with a sensitivity and specificity of 60.1% and 80.0% respectively.

An integrated approach for estimating static Young’s modulus using artificial intelligence tools

Elastic parameters play a key role in managing the drilling and production operations. Determination of the elastic parameters is very important to avoid the hazards associated with the drilling operations, well placement, wellbore instability, completion design and also to maximize the reservoir productivity. A continuous core sample is required to be able to obtain a complete profile of the elastic parameters through the required formation. This operation is time-consuming and extremely expensive. The scope of this paper is to build an advanced and accurate model to predict the static Young’s modulus using artificial intelligence techniques based on the wireline logs (bulk density, compressional time, and shear time). More than 600 measured core data points from different fields were used to build the AI models. The obtained results showed that ANN is the best AI technique for estimating the static Young’s modulus with high accuracy [R2 was 0.92 and the average absolute percentage error (AAPE) was 5.3%] as compared with ANFIS and SVM. For the first time, an empirical correlation based on the weights and biases of the optimized ANN model was developed to determine the static Young’s modulus. The developed correlation outperformed the published correlations for static Young’s modulus prediction. The developed correlation enhanced the accuracy of predicting the static Young’s modulus. (R2 was 0.96 and AAPE was 6.2%.) The developed empirical correlation can help geomechanical engineers determine the static Young’s modulus where laboratory core samples are not available.

Artificial neural network application to microstructure design of Nb-Si alloy to improve ultimate tensile strength

In this paper, a feed forward neural network with back propagation artificial neural network (BP ANN) was developed to predict ultimate tensile strength (UTS) and optimize microstructure. The alloys were produced by directional solidification and heat treatment. The UTS was measured for ANN output. Five characteristic factors used for ANN input were abstracted and measured. As the result of this study, the ANN model with high accuracy and good generalization ability to predict UTS within the range of 343.5–1063.3MPa was established and mutual verified with sensitivity analysis. Based on the optimized ANN model, a new way to design microstructure of Nb-Si alloy to obtain required UTS was proposed. With silicide design maps made by ANN model, the microstructure of the sample of 343.5MPa was optimized and the UTS reached the target UTS (600MPa) successfully.

인공신경망 기법을 이용한 터널 붕괴 예측에 관한 기초 연구

Collapse of a tunnel can occur anytime, anywhere due to the special characteristics of tunnel structures and unexpected geological conditions during construction. Tunnel collapse will lead to economic losses and casualties. So various studies are continually being conducted to prevent economic losses, casualties and accidents. In this study, we analyzed data from 56 domestic construction tunnel collapse sites, and input factors to be applied to the artificial neural network were selected by the sensitivity analysis. And for the artificial neural network model design studies were carried out with the selected input factors and optimized ANN model to predict the type of tunnel collapse was determined. By using it, in 12 sites where tunnel collapse occurred applicability evaluation was conducted. Thus, the tunnel collapse type predictability was verified. These results will be able to be used as basic data for preventing and reinforcing collapse in the tunnel construction site.

Separation of toluene/ n-heptane mixtures experimental, modeling and optimization

In this paper a composite membrane is used to separate toluene from n-heptane mixture. The aim is to optimize the separation process conditions through modeling. Therefore this model should be able to predict membrane performance demonstrated by total permeation flux and toluene selectivity as a function of operating condition. In order to create a black box model of the process, a multi layer feed forward artificial neural network is used. An algorithm based on evaluating all possible structures is employed to create an optimum ANN model. Number of hidden layers, transfer function, training method and hidden neurons are determined with the aid of this algorithm. Performance confirms that there is good agreement between the experimental data and the model predicted values, with correlation coefficients of more than 0.99 and mean square errors of less than 1%. Both model and experimental data show that increasing temperature and toluene concentration increase total flux and decrease toluene selectivity but increasing permeate pressure decreases both. Having created and trained an optimized ANN model a multi-objective genetic algorithm is employed to find optimum operating conditions with respect to permeation flux and toluene selectivity as two targets of this separation. Considering the obtained Pareto set and corresponding decision variables, it is found that permeate pressure in this set is almost constant and only variations in temperature and feed concentration eventuate to the creation of the Pareto front.

Tabu Search Algorithm Optimized ANN Model for Wind Power Prediction with NWP

Wind power prediction is of great importance for the safety and stabilization of grids. The most important and difficult problem now is to enhance the prediction precision. BP (Backward Propagation) neural network has been used extensively in wind power prediction. But BP network is apt to getting into local minima and its convergence rate is slow. Tabu search is a kind of intelligent algorithm, which can achieve the global optimizations. This paper put forward a wind power prediction model of BP neural network optimized by tabu search algorithm with memory function. The result shows that with appropriate input parameters, the wind power prediction model of neural network based on tabu search algorithm can improve the prediction precision as well as the convergence rate.

Development of Optimized ANN Model Through Genetic Algorithm to Predict the Microstructural Parameters of Aluminum Alloy Castings

i-manager's Journal on Future Engineering and Technology, i-manager's Journal on Software Engineering, i-manager's Journal on Electrical Engineering, i-manager's Journal on Electronics Engineering, i-manager's Journal of Educational Technology, i-manager's Journal on Educational Psychology, i-manager's Journal on School Educational Technology, i-manager's Journal on English Language Teaching, i-manager's Journal on Mechanical Engineering, i-manager's Journal on Civil Engineering, i-manager's Journal on Embedded Systems, i-manager's Journal on Information Technology, i-manager's Journal on Structural Engineering, i-manager's Journal on Communication Engineering and Systems, i-manager's Journal on Wireless Communication Networks, i-manager's Journal on Instrumentation and Control Engineering, i-manager's Journal on Circuits and Systems, i-manager's Journal on Digital Signal Processing, i-manager's Journal on Power Systems Engineering, i-manager's Journal on Computer Science, i-manager's Journal on Material Science, i-manager's Journal on Cloud Computing, i-manager's Journal on Image Processing, i-manager's Journal on Mobile Applications and Technologies, i-manager's Journal on Pattern Recognition, i-manager's Journal on Mathematics, i-manager's Journal on Management, i-manager's Journal on Nursing, i-manager's Journal on Physical Sciences, i-manager's Journal on Chemical Sciences, i-manager's Journal on Economics & Commerce , i-manager's Journal on Humanities & Social Sciences, i-manager's Journal on Life Sciences , i-manager's Journal on Construction Management, i-manager's Oyla , ,India best Journal Publication Website,World Best Plication SIte,Free atrticle published website,Journal Publised,Published Journal,Research Paper Published,indian research paper publications,how to published your article/research paper in india for free,journal’s instructions for authors