Adaptive Neuro-fuzzy Inference System Prediction Research Articles

Optimising building heat load prediction using advanced control strategies and Artificial Intelligence for HVAC system

Amid the dynamic challenges posed by the COVID-19 era, this study offers a nuanced exploration, delving into the complexities of optimising building heat load prediction. This study addresses the imperative challenge of optimising building heat load prediction by implementing advanced control strategies and integrating Artificial Intelligence (AI) into air conditioning systems. The study emphasises the need to design HVAC devices for minimal energy consumption without compromising comfort conditions. The study introduces an intelligent predictive adaptive neuro-fuzzy inference system (ANFIS) model that proves highly capable of accurately predicting HVAC performance outcomes while contributing to the development of a comprehensive dataset. The uncertainty percentage is evaluated across various membership functions, with the trapezoidal membership exhibiting the lowest error rate, followed by the Gaussian membership function. Weather parameters crucial to ventilation efficiency and heat load are examined, leading to the identification of an optimal combination involving 45 % relative humidity, 13 °C dry bulb temperature, and 5 km/h wind speed. The current system demonstrates significant efficiency improvements, with ventilation and heat load rates reaching 93 % and 97 %, respectively, compared to pre-COVID-19 conditions. The findings underscore the importance of considering these parameters in future HVAC designs, particularly in the context of COVID-19 guidelines (75 % and 79 %, respectively).

Modeling of dielectric behavior of polymers nanocomposites using adaptive neuro-fuzzy inference system (ANFIS)

The research presents a theoretical study on modeling of dielectric properties of polymer nanocomposites based on adaptive neuro-fuzzy inference system (ANFIS). The research contributes a better utilizing of ANFIS model in the prediction of dielectric behavior of polymers nanocomposites. In this respect, three different samples are trained (Mg1−xCuxO/PMMA, PPy-DBSA-Y2O3 and PVC/PEMA with [Zn(CF3SO3)2]). Inputs are obtained from earlier experimental studies. ANFIS Takagi–Sugeno type is trained. The model is applied based on weighted average as a defuzzification method. The optimal network structures, which produce the most acceptable results, are implemented in MATLAB. Six ANFIS networks are trained to simulate and predict dielectric permittivity and dielectric loss in terms of nanocomposite weight % (0–0.2%, 0–8% and 10–30% for each sample, respectively) and frequency (10−2–103 kHz). ANFIS simulation results are very close to their targets. Predictions of dielectric properties at nanocomposite weights % that are measured experimentally as a testing step and predictions of other values that are not implicated in the experimental data extent are achieved. Also, predictions of individual points are processed using ANFIS rule viewer. It is found that ANFIS predictions provide excellent results. Three-dimensional illustrations that represent the mapping from frequency and nanocomposite weight% to the dielectric permittivity and dielectric loss are obtained using MATLAB surface viewer. Histogram error plot is obtained to indicate the degree of noisy. Mean error, mean squared error, root-mean-squared error and standard division error are calculated. Their values improve the efficiency of the modeling process. A key goal of this paper is to develop a mechanism to predict the dielectric properties of polymers nanocomposites. In accordance with the modeling results, the ANFIS technique achieves the purpose. It can also form a great link between practical and theoretical domains.

Machine learning approaches for predicting geometric and mechanical characteristics for single P420 laser beads clad onto an AISI 1018 substrate

The final mechanical and physical properties should be predicted in tandem with the bead geometry characteristics for effective additive manufacturing (AM) solutions for processes such as directed energy deposition. Experimental approaches to investigate the final geometry and the mechanical properties are costly, and simulation solutions are time-consuming. Alternative artificial intelligent (AI) systems are explored as they are a powerful approach to predict such properties. In the present study, the geometrical properties as well as the mechanical properties (residual stress and hardness) for single bead clads are investigated. Experimental data is used to calibrate multi-physics finite element models, and both data sets are used to seed the AI models. The adaptive neuro-fuzzy inference system (ANFIS) and a feed-forward back-propagation artificial neural network (ANN) system are utilized to explore their effectiveness in the 1D (discrete values), 2D (bead cross-sections), and 3D (complete bead) domains. The prediction results are evaluated using the mean relative error measure. The ANFIS predictions are more precise than those from the ANN for the 1D and 2D domains, but the ANN had less error for the 3D scenario. These models are capable of predicting the geometrical and the mechanical properties values very well, including capturing the mechanical properties in transient regions; however, this research should be extended for multi-bead scenarios before a conclusive “best approach” strategy can be determined.

Virtual Multiphase Flowmetering Using Adaptive Neuro-Fuzzy Inference System (ANFIS): A Case Study of Hai Thach-Moc Tinh Field, Offshore Vietnam

Summary For any oil and gas company, well-testing and performance-monitoring programs are expensive because of the cost of equipment and personnel. In addition, it may not be possible to obtain all of the necessary data for a reservoir for a period of time because of production demand constraints or changes in surface process conditions. To overcome these challenges, there are many studies on the implementation and value of virtual flowmetering (VFM) for real-time well performance prediction without any need for a comprehensive well-testing program. This paper presents the VFM model using an adaptive neuro-fuzzy inference system (ANFIS) at Hai Thach-Moc Tinh (HT-MT) gas-condensate field, offshore Vietnam. The ANFIS prediction model can tune all its membership functions (MFs) and consequent parameters to formulate the given inputs to the desired output with minimum error. In addition, ANFIS is a successful technique used to process large amounts of complex time series data and multiple nonlinear inputs-outputs (Salleh et al. 2017), thereby enhancing predictability. The authors have built ANFIS models combined with large data sets, data smoothing, and k-fold cross-validation methods based on the actual historical surface parameters such as choke valve opening, surface pressure, temperature, the inlet pressure of the gas processing system, etc. The prediction results indicate that the local regression “loess” data smoothing method reduces the processing time and gives both clustering algorithms the best results among the different data preprocessing techniques [highest value of R and lowest value of mean squared error (MSE), error mean, and error standard deviation]. The k-fold cross-validation technique demonstrates the capability to avoid the overfitting phenomenon and enhance prediction accuracy for the ANFIS subtractive clustering model. The fuzzy C-mean (FCM) model in the present study can predict the gas condensate production with the smallest root MSE (RMSE) of 0.0645 and 0.0733; the highest coefficient of determination (R2) of 0.9482 and 0.9337; and the highest variance account of 0.9482 and 0.9334 for training and testing data, respectively. Applied at the HT-MT field, the model allows the rate estimation of the gas and condensate production and facilitates the virtual flowmeter workflow using the ANFIS model.

Development of computational methods for estimation of current efficiency and cell voltage in a Chlor-alkali membrane cell

ABSTRACT This work presents proposing two artificial intelligence methods including Least squares support vector machine (LSSVM) and Adaptive neuro fuzzy inference system (ANFIS) for the prediction of caustic current efficiency (CCE) and cell voltage as a function of pH, current density, brine concentration, electrolyte velocity, operating temperature, and run time. The predictions of LSSVM and ANFIS models were evaluated by the experimental values of this process graphically and statistically. The overall R-squared values of LSSVM and ANFIS for prediction of CCE were 0.999 and 0.972, respectively. On the other hand, these values for cell voltage prediction were 1 and 0.998. According to the CCE and cell voltage predictions results, LSSVM algorithm has great performance in prediction of chlor-alkali membrane cell processes. Furthermore, artificial intelligence methods can have wide use in electrolytic processes to enhance power consumption.

Adaptive neuro-fuzzy inference system prediction model for the mechanical behaviour of rice husk ash and periwinkle shell concrete blend for sustainable construction

Adaptive neuro-fuzzy inference system prediction model for the mechanical behaviour of rice husk ash and periwinkle shell concrete blend for sustainable construction

Estimation of biogas yields produced from combination of waste by implementing response surface methodology (RSM) and adaptive neuro-fuzzy inference system (ANFIS)

A creative algorithm, response surface methodology (RSM) and hybrid algorithm, adaptive neuro-fuzzy inference system (ANFIS) have been implemented to optimize biogas production from 2 different biodegradable animal waste (substrates of poultry wastes (PW) and cow dung (CW)) in a lightweight biodigester system. A maximum biogas yield of 51.3% was achieved with 38:23 CD/PW within the retention time of nine (9) days. The computed coefficient of determination (R2) of 0.9998, root-mean-square-error (RMSE) of 0.0055, standard error of prediction (SEP) of 0.00011092, mean average error (MAE) of 0.0015, and average absolute deviation (AAD) of 0.0030 was estimated by implementing the RSM model. This was compared with the ANFIS result with R2 (1.0), RMSE (1.0), SEP (0), MAE (0), and AAD (− 0.00022483). From the analysis of the RSM and ANFIS results, the result obtained from the ANFIS prediction is statistically marginal and gave a faster and better prediction compared to the RSM model.

A neuro-fuzzy approach to predict the shear contribution of end-anchored FRP U-jackets

The current study targets to estimate the contribution of the end-anchored FRP composites in resisting shear force using a soft computing tool i.e., adaptive neuro-fuzzy inference system (ANFIS). A total of 107 sets of data accumulated from literature was utilized for the development and evaluation of the current ANFIS model. A comparative analysis between the ANFIS predictions and the acquired experimental results has shown that the ANFIS predictions are in very good agreement with that of experimental ones. Additionally, the accuracy of the current ANFIS model has been weighed up against the estimates of nine widely adopted design guidelines. Based on various statistical parameters, it has been deduced that the effectiveness of the current ANFIS model is better than the considered design guidelines. Besides this, a parametric study was carried out to explore the combined effect of different parameters as well as the impact of individual parameters.

A neuro-fuzzy approach to estimate the shear contribution of externally bonded FRP composites

The wide usage of fiber-reinforced polymer (FRP) composites as an external shear strengthening material have resulted in the development of various design guidelines. However, the accuracy of the design guidelines is a matter of concern since the shear behavior of the RC beam becomes more complex with the addition of FRP composites. On the other side, soft computing methods have been proved to be efficient enough to analyze complex systems. However, their application in structural engineering is limited. Therefore, in the current investigation, an effort has been made to evaluate the shear contribution of the EB-FRP composites with the help of adaptive neuro-fuzzy inference system (ANFIS). A total of 151 sets of data assembled from literature was utilized for the development and evaluation of the ANFIS model. The ANFIS predictions were validated against the obtained experimental results as well as with the estimations of six widely implemented design guidelines. The comparative study has shown that the ANFIS estimates are in decent agreement with that of experimental outcomes and the accurateness of the current ANFIS model is superior to the considered design guidelines. Finally, a parametric investigation was performed to explore the combined effect of various parameters as well as the impact of independent parameters.

Application of ANN and ANFIS in prediction of color strength of plasma-treated wool yarns dyed with a natural colorant

Purpose Despite the increasing popularity of natural dyeing of textiles, the low substantivity between the fibers and the natural dyes is a problem. Several methods have been used to overcome this problem. In this study, wool fibers were pretreated with oxygen plasma under different conditions and dyed with the extract of grape leaves. The purpose of this study is to investigate the effects of plasma treatment parameters on the color strength of the dyed samples using artificial neural network (ANN) and adaptive neuro-fuzzy inference system (ANFIS) and evaluate the ability of these methods for predicting the color strength. Design/methodology/approach Woolen yarns were modified under different conditions of oxygen plasma treatment. Oxygen flow rate, power and time were considered as the treatment variable factors. Plasma-treated samples were dyed under constant conditions with the extract of grape leaves as a natural dye. ANN and ANFIS were applied to model and analyze the effect of plasma treatment parameters on the color strength of the dyed samples. Findings The results showed that increasing all the plasma treatment process variables, including oxygen flow rate, power and time increased the color strength of the dyed samples. The results showed that the developed ANN and ANFIS could accurately predict the experimental data with correlation coefficients of 0.986 and 0.997, respectively. According to the obtained correlation coefficients, ANFIS had a higher accuracy in prediction of the results of this study compared with the ANN and RSM models (correlation coefficient = 0.902, from our previous study). Originality/value This study uses ANN and ANFIS for predicting color strength of naturally dyed textiles for the first time. The use of computational intelligence for the optimization and prediction of the effects plasma treatment for the improvement of natural dyeing of wool is another novelty of this study.

Improving precision in the prediction of laser texturing and surface interference of 316L assessed by neural network and adaptive neuro-fuzzy inference models

Laser-based surface texturing provides highly controlled interference fit between two parts. In this work, artificial intelligence-based models were used to predict the surface properties of laser processed stainless steel 316 samples. Artificial neural network (ANN) and adaptive neuro-fuzzy inference system (ANFIS) were used to predict the characteristics of laser surface texturing. The models based on feedforward neural network (FFNN) were developed to examine the effect of the laser process parameters for surface texturing on 316L cylindrical pins. The accuracy of the models was measured by calculating the root mean square error and mean absolute error. The reliability of the ANFIS and FFNN models for the output prediction of the laser surface texturing (LST) system were investigated by using the data measured from experiments based on a 3^3 factorial design, with main processing parameters set as laser power, pulse repetition frequency, and percentage of laser spot overlap. The relative assessment of the models was performed by comparing percentage error prediction. Finally, the impact of input data was examined using predicted response surface plots. Results showed that ANFIS prediction was 48% more accurate compared with that provided by the FFNN model.

Artificial intelligence approaches for spatial modeling of streambed hydraulic conductivity

Saturated hydraulic conductivity (Ks) describes the water movement through saturated porous media. The hydraulic conductivity of streambed varies spatially owing to the variations in sediment distribution profiles all along the course of the stream. The artificial intelligence (AI) based spatial modeling schemes were instituted and tested to predict the spatial patterns of streambed hydraulic conductivity. The geographical coordinates (i.e., latitude and longitude) of the sampled locations from where the in situ hydraulic conductivity measurements were determined were used as model inputs to predict streambed Ks over spatial scale using artificial neural network (ANN), adaptive neuro-fuzzy inference system (ANFIS) and support vector machine (SVM) paradigms. The statistical measures computed by using the actual versus predicted streambed Ks values of individual models were comparatively evaluated. The AI-based spatial models provided superior spatial Ks prediction efficiencies with respect to both the strategies/schemes considered. The model efficiencies of spatial modeling scheme 1 (i.e., Strategy 1) were better compared to Strategy 2 due to the incorporation of more number of sampling points for model training. For instance, the SVM model with NSE = 0.941 (Strategy 1) and NSE = 0.895 (Strategy 2) were the best among all the models for 2016 data. Based on the scatter plots and Taylor diagrams plotted, the SVM model predictions were found to be much efficient even though, the ANFIS predictions were less biased. Although ANN and ANFIS models provided a satisfactory level of predictions, the SVM model provided virtuous streambed Ks patterns owing to its inherent capability to adapt to input data that are non-monotone and nonlinearly separable. The tuning of SVM parameters via 3D grid search was responsible for higher efficiencies of SVM models.

Tactile Comfort Prediction of Functional Fabrics from Instrumental Data Using Intelligence Systems

Subjective and objective evaluations of the handle of textile materials are very important to describe its tactile comfort for next-to-skin goods. In this paper, the applicability of artificial neural-network (ANN) and adaptive neuro-fuzzy inference system (ANFIS) modeling approaches for the prediction of the psychological perceptions of functional fabrics from mechanical properties were investigated. Six distinct functional fabrics were evaluated using human subjects for their tactile score and total hand values (THV) using tactile and comfort-based fabric touch attributes. Then, the measurement of mechanical properties of the same set of samples using KES-FB was performed. The RMSE values for ANN and ANFIS predictions were 0.014 and 0.0122 and are extremely lower than the variations of the perception scores of 0.644 and 0.85 for ANN and ANFIS, respectively with fewer prediction errors. The observed results indicated that the predicted tactile score and THV are almost very close to the actual output obtained using the human judgment. Fabric objective measurement technology, therefore, provides reliable measurement approaches for functional fabric quality inspection, control, and design specification.

PSO-ANFIS hybrid approach for prediction of wave reflection coefficient for semicircular breakwater

ABSTRACT Breakwaters are used to provide protection to the coast and are being improved over the years through research. Semicircular breakwater (SBW) is one such contribution in the area of coastal structures with an improved esthetics and stability. Advances in artificial intelligence applications in several fields have led to the increased interest in the researchers of coastal engineering to venture into it. This paper focuses on the prediction of reflection coefficient (Kr ) for SBW using adaptive neuro-fuzzy inference system (ANFIS) and a hybrid of particle swarm optimization for adaptive neuro-fuzzy inference system (PSO-ANFIS) for a wide range of wave heights. The datasets required for the study are acquired from the experimental investigations of SBW in the regular wave flume at the Marine Structure Laboratory, National Institute of Technology Karnataka, India. The data fed for training and testing were taken in two forms separately, i.e. dimensional and dimensionless form. The PSO-ANFIS based optimized prediction of reflection coefficient is compared with the prediction arrived through ANFIS-based learning. The accuracy assessment of prediction was done by correlation coefficient, scatter index, Nash–Sutcliffe efficiency, bias, and root mean square error. The PSO-ANFIS hybrid model prediction improved the ANFIS prediction for the considered cases.

Effect of SnO2, ZrO2, and CaCO3 nanoparticles on water transport and durability properties of self-compacting mortar containing fly ash: Experimental observations and ANFIS predictions

This paper investigates the influence of the addition of nanoparticles, namely SnO2, ZrO2 and CaCO3, at different doses on the durability and the microstructure of self-compacting mortar (SCM). Rheological characteristics were observed through mini slump flow diameter and mini V-funnel flow time. Transport properties were studied by the water absorption and capillary absorption tests. Mechanical properties were determined by the compression tests. Durability properties were examined by the electrical resistivity and rapid chloride permeability tests. Microstructure of SCMs was investigated through scanning electron microscopy (SEM). The mixtures containing nanoparticles exhibit improved transport properties, with increased compressive strengths and resistance to water and chloride ion penetration. These improvements are attributed to the compact microstructures, as the micro pore system was refined in the presence of nanoparticles. Based on fresh and hardened mortar properties, it is found that 5 wt% SnO2, 4 wt% ZrO2, and 3 wt% CaCO3 would serve as suitable replacement levels in optimizing the overall performance. An adaptive neuro-fuzzy inference system (ANFIS) was employed to predict the SCM properties. The numerical results show that the metamodels provide accurate estimates of experimental results.

Prediction of Groundwater Level Fluctuation by ANN and ANFIS Techniques

Development of regional groundwater model isan important phase to understand the mechanism of groundwater resource and its sustainability. This model is extensively restricted by the requirement of large number of field data and specific interconnected constraints. A choice of intelligent soft computing technique is always constantly open for such model development. Recently ANN (Artificial Neural Network) and ANFIS (Adaptive Neuro Fuzzy Inference System) techniques are having a massive strength to deal with such interconnected constrains model. The present study is carried outto perform the comparative prediction between ANN, ANFIS, CWTFT-ANN (Continuous Wavelet Fast Fourier Transform), CWTFT-ANFIS, WT-ANN (Wavelet Transform) and WT-ANFIS on Groundwater Level prediction at different reaches (Top, Middle and End) of Lower Bhavani River Basin (LBRB) on monthly stress basis(from 2009 to 2015). From the results, the performance of CWTFT-ANFIS is 9.36%, 13.3% and 4.45% better than the ANFIS prediction and the performance of CWTFT-ANN is 47.17%, 25.6% and 47.45% better than the ANN prediction at Top, Middle and End reaches of LBRB respectively. Overall the prediction of CWTFT-ANFIS is about15.3% better than the other identified models, which is further fed for the forecasting of groundwater level to next one time stress level.

Modeling of waste brine nanofiltration process using artificial neural network and adaptive neuro-fuzzy inference system

In this study, artificial neural network (ANN) and adaptive neuro-fuzzy inference system (ANFIS) models were used to predict the average permeate fluxes and sodium chloride rejection of waste brine nanofiltration process. The ANFIS and ANN models were fed with three inputs: feed concentration (40, 60, 80, and 100 g/l), pressure (1.0, 1.25, 1.5, 1.75, and 2.0 MPa), and temperature (30, 40, and 50°C). Both models were trained with 30% of total experimental data. Thirty percent of the experimental data were used to test the prediction ability of ANFIS and ANN models. Independent permeate flux and NaCl rejection predictions were calculated for the remaining of total data (40%). The results revealed that ANN predictions agreed well with variety of experimental data. It was found that ANN with 1 hidden layer comprising 8 neurons gives the best fitting quality, which made it possible to predict flux and rejection with acceptable correlation coefficients (r = 0.90 and r = 0.87, respectively). A hybrid method (the combination of least squares and back propagation algorithms) was used as the training method of the ANFIS. The overall agreement between ANFIS predictions and experimental data was excellent for both permeate flux and salt rejection (r = 0.96 and r = 0.94, respectively).

New approaches to modeling Staphylococcus aureus inactivation by ultrasound

Ultrasound (US) is an effective technology to inactivate vegetative microorganisms in foods. In this study, the effect of amplitude levels (0.4, 7.5, and 37.5), duty cycles (0.3:0.7 s, 0.7:0.3 s, and 0.9: 0.1 s) and time (0, 2, 4, 6, 8, 10, 12, and 14 days) of US on inactivation of Staphylococcus aureus were investigated. In addition, genetic algorithm-artificial neural network (GA-ANN) and adaptive neuro-fuzzy inference system (ANFIS) models were used to predict inactivation of S. aureus. The GA-ANN and ANFIS were fed with three inputs of amplitude levels, duty cycles, and time. The inactivation rate of S. aureus was increased by increasing the amplitude levels, and the best inactivation was obtained at a 37.5 μm amplitude for which the S. aureus population was reduced to 2.59 CFU/mL. The high inactivation of S. aureus was achieved under a duty cycle of 0.7:0.3 s with reduction of the population to 1.49 CFU/mL. The developed GA-ANN, which included 17 hidden neurons, could predict the S. aureus population with a coefficient of determination of 0.986. The overall agreement between ANFIS predictions and experimental data was also very good (R 2 = 0.979). Sensitivity analysis results showed that the amplitude level was the most sensitive factor for prediction of S. aureus.

Potential of adaptive neuro-fuzzy system for prediction of daily global solar radiation by day of the year

Estimating the horizontal global solar radiation by day of the year (nday) is particularly appealing since there is no need to any specific meteorological input data or even pre-calculation analysis. In this study, an intelligent optimization scheme based upon the adaptive neuro-fuzzy inference system (ANFIS) was applied to develop a model for estimation of daily horizontal global solar radiation using nday as the only input. The chief goal was identifying the suitability of ANFIS technique for this aim. Long-term measured data for Iranian city of Tabass was used to train and test the ANFIS model. The statistical results verified that the ANFIS model provides accurate and reliable predictions. Making comparisons with the predictions of six day of the year-based empirical models revealed the superiority of ANFIS model. For the ANFIS model, the mean absolute percentage error, mean absolute bias error, root mean square error and correlation coefficient were 3.9569%, 0.6911MJ/m2, 0.8917MJ/m2 and 0.9908, respectively. Also, the daily bias errors between the ANFIS predictions and measured data fell in the favorable range of –3 to 3MJ/m2. In a nutshell, the survey results highly encouraged the application of ANFIS to estimate daily horizontal global solar radiation using only nday.

GA‐ANN and ANFIS Models and Salmonella Enteritidis Inactivation by Ultrasound

AbstractIn this study, adaptive neuro‐fuzzy inference system (ANFIS) and genetic algorithm–artificial neural network (GA‐ANN) models were used to predict inactivation of Salmonella enteritidis by ultrasound. The effect of amplitude levels, duty cycles and irradiation time of ultrasound on inactivation of S. enteritidis was investigated. The inactivation rate of S. enteritidis was increased by intensifying the amplitude levels and the best inactivation was achieved at 37.5 μm amplitude that S. enteritidis population was reduced to 1.67 cfu/mL. The high inactivation rate of S. enteritidis was achieved under duty cycle of 0.7:0.3, with reduction of population to 1.02 cfu/mL. The overall agreement between ANFIS predictions and experimental data was also very good (R2 = 0.974). The developed GA‐ANN, which included 12 hidden neurons, could predict S. enteritidis population with low mean squared error, normalized mean squared error and mean absolute error equal to 0.083, 0.023 and 0.200, respectively. The results indicated that both GA‐ANN and ANFIS models could give good prediction for the population of S. enteritidis. Sensitivity analysis results showed that ultrasound time was the most sensitive factor for the prediction of S. enteritidis population.Practical ApplicationsMicrobial inactivation by thermal treatment does damage to the organoleptic properties of foods. However, using ultrasound (US) for microbial inactivation minimizes this change. Generally, the advantages of US over thermal treatment are minimal flavor loss, significant energy saving and greater homogeneity.