Adaptive Network-based Fuzzy Inference System Model Research Articles

Influence of number of membership functions on prediction of membrane systems using adaptive network based fuzzy inference system (ANFIS)

In membrane separation technologies, membrane modules are used to separate chemical components. In membrane technology, understanding the behavior of fluids inside membrane module is challenging, and numerical methods are possible by using computational fluid dynamics (CFD). On the other hand, the optimization of membrane technology via CFD needs time and computational costs. Artificial Intelligence (AI) and CFD together can model a chemical process, including membrane technology and phase separation. This process can learn the process by learning the neural networks, and point by point learning of CFD mesh elements (computing nodes), and the fuzzy logic system can predict this process. In the current study, the adaptive neuro-fuzzy inference system (ANFIS) model and different parameters of ANFIS for learning a process based on membrane technology was used. The purpose behind using this model is to see how different tuning parameters of the ANFIS model can be used for increasing the exactness of the AI model and prediction of the membrane technology. These parameters were changed in this study, and the accuracy of the prediction was investigated. The results indicated that with low number of inputs, poor regression was obtained, less than 0.32 (R-value), but by increasing the number of inputs, the AI algorithm led to an increase in the prediction capability of the model. When the number of inputs increased to 4, the R-value was increased to 0.99, showing the high accuracy of model as well as its high capability in prediction of membrane process. The AI results were in good agreement with the CFD results. AI results were achieved in a limited time and with low computational costs. In terms of the categorization of CFD data-set, the AI framework plays a critical role in storing data in short memory, and the recovery mechanism can be very easy for users. Furthermore, the results were compared with Particle Swarm Optimization (PSOFIS), and Genetic Algorithm (GAFIS). The time for prediction and learning were compared to study the capability of the methods in prediction and their accuracy.

Comparison of different techniques for estimation of incoming longwave radiation

Global warming and climate change have left developing countries fragile in terms of agricultural production, and this vulnerability is expected to increase in the near future. The surface energy budget approach is a different perspective to the investigation of energy change over a landscape. In terms of budget items, the net radiation absorbed by the earth is equal to the difference between the sum of the incoming shortwave and longwave radiation and the sum of the reflected shortwave and emitted longwave radiation. The longwave radiation has important effects on dew deposition and drying on crop leaves in agricultural meteorology. A pyranometer provides routine measurement of the daytime radiation, but the longwave part of this radiation cannot be so readily measured at night time. In this study, multiple linear regression, artificial neural networks, deep learning, adaptive network-based fuzzy inference systems (ANFIS) and empirical models have been applied to model and estimate the mean incoming longwave radiation using atmospheric parameters. The ANFIS model appears to show good agreement between the measured and the estimated values for all days considered than other models.

Hybrid connectionist models to assess recovery performance of low salinity water injection

The low salinity water injection (LSWI) is one of the emerging enhanced oil recovery techniques to improve both microscopic and macroscopic displacement efficiencies by creating a new streamline in petroleum reservoirs. While experimental studies are tedious, costly, and time-consuming, the smart connectionist tools are more reliable and cost-effective approaches to predict oil recovery factor (RF) without considerations of governing equations and physics behind production mechanisms in oil reservoirs. The main objective of this study is to investigate the data-driven model performance and variable contribution while predicting RF of LSWI processes. We introduce connectionist models using hybridized least squares support vector machine (LSSVM) with global optimization technique of coupled simulated annealing (CSA), and adaptive network-based fuzzy inference system (ANFIS). The extremely randomized tree or extra tree (ET) tool is also applied to forecast the RF and investigate the parameter contribution in the employed model. The model performance is examined using statistical parameters, including coefficient of determination, relative error, mean absolute percentage error, and mean squared error. According to the results, the ET and hybridized LSSVM-CSA models perform better than the ANFIS model in estimating RF. Utilizing the ET smart model, the total dissolved salts (TDS, ppm) is the most influential parameter, while the fluid injection rate has the minimum importance in the determination of RF. The current research confirms that LSSVM-CSA and ET techniques are able to obtain RF of LSWI with high accuracy and reliability, which can be used by researchers and engineers for better management of oil reservoirs under LSWI.

Retraction Note: Prediction microhardness profile of functionally graded steels by ANFIS

In the present study, the Vickers microhardness profile of ferritic and austenitic functionally graded steel produced by electroslag remelting process has been modeled by adaptive network-based fuzzy inference system (ANFIS). To produce functionally graded steels, a spot-welded electrode that consists of two slices of plain carbon steel and austenitic stainless steel was used. Functionally graded steel containing graded layers of ferrite and austenite may be fabricated via diffusion of alloying elements during remelting stage. Vickers microhardness profile of the specimen has been obtained experimentally and modeled with ANFIS. To build the model for graded ferritic and austenitic steels, training, testing and validation using, respectively, 174 and 120 experimental data were conducted. According to the input parameters, the Vickers microhardness of each layer was predicted. The training, testing and validation results in the ANFIS models have shown a strong potential for predicting microhardness profile of both graded ferritic and austenitic steels. It was shown that the Vickers microhardness can be predicted by ANFIS in the range of the examined data.

Effective modelling of hydrogen and energy recovery in microbial electrolysis cell by artificial neural network and adaptive network-based fuzzy inference system

This study aims to analyze and model cathodic H2 recovery (rcat), coulombic efficiency (CE) with inputs of voltage, electrical conductivity (EC) and anode potential, and H2 production rate and total energy recovery with inputs of rcat and CE in a microbial electrolysis cell using artificial neural network (ANN) and adaptive network-based fuzzy inference system (ANFIS) procedures. Both ANN and ANFIS models demonstrated great goodness of fit for rcat, CE, H2 production rate and total energy recovery prediction with high R2 values. The sum square error values for rcat (0.0017), CE (0.0163), H2 production rate (0.1062) and total energy recovery (0.0136) in ANN models were slightly higher than those in ANFIS models at 0.0005, 0.0091, 0.1247 and 0.0148 respectively. Sensitivity analysis by ANN models demonstrated that voltage, EC, rcat and rcat were the most effective factors for rcat, CE, H2 production rate and total energy recovery, respectively.

The feasibility of PSO–ANFIS in estimating bearing capacity of strip foundations rested on cohesionless slope

This study aimed to assess particle swarm optimization (PSO) optimized with an adaptive network-based fuzzy inference system (ANFIS) for the prediction of the ultimate bearing capacity of strip footing resting on a sloping crest. To make datasets, a 2524 finite element model (FEM) simulation analysis was performed. In this sense, the k-fold validation technique selected for the selection of the testing and validation purposes. Also, the variables of the ANFIS algorithm (i.e., the number of clusters), and the PSO algorithm (the population size were optimized using a series of trial and error process. The second main objective of the current study was to assess the applicability of PSO–ANFIS in estimating the ultimate bearing capacity of the strip footing resting on a single cohesionless slope when it was subjected to an external vertical applied stress. The input parameters were the soil properties (Stype) (classified into five different classes from the weakest, shown as S1, to the strongest type, displayed in higher order), slope angle (β), setback distance ratio (b/B) (the distance of the footing from the slope crest to the footing width), and vertical settlement (Uy) of the footing, while the main output was the applied vertical stresses (Fy) that can be applied on the footing. Note that the ultimate bearing capacity (Fult) is the maximum vertical stress when Uy = 0.1 B. A thorough comparison between the measured FEM simulations, the proposed ANFIS and PSO–ANFIS models were carried out to demonstrate their effectiveness in predicting a reliable Fult resting on cohesionless slopes.

A New Method for Predicting Indirect Tensile Strength of Sandstone Rock Samples

The tensile strength (σt) of a rock plays an important role in the reliable construction of several civil structures such as dam foundations and types of tunnels and excavations. Determination of σt in the laboratory can be expensive, difficult, and time-consuming for certain projects. Due to the difficulties associated with the experimental procedure, it is usually preferred that the σt is evaluated in an indirect way. For these reasons, in this work, the adaptive network-based fuzzy inference system (ANFIS) is used to build a prediction model for the indirect prediction of σt of sandstone rock samples from their physical properties. Two ANFIS models are implemented, i.e. ANFIS-subtractive clustering method (SCM) and ANFIS-fuzzy c-means clustering method (FCM). The ANFIS models are applied to the data available in the open source literature. In these models, the porosity, specific gravity, dry unit weight, and saturated unit weight are utilized as the input parameters, while the measured σt is the output parameter. The performance of the proposed predictive models is examined according to two performance indices, i.e. mean square error (MSE) and coefficient of determination (R2). The results obtained from this work indicate that ANFIS-SCM is a reliable method to predict σt with a high degree of accuracy.

Modelling evaporator in organic Rankine cycle using hybrid GD-LSE ANFIS and PSO ANFIS techniques

Internal combustion engines (ICEs) are likely to be used in heavy-duty applications for many years and it is important to continue improving their efficiency. One approach is to recover waste heat from the exhaust of heavy-duty diesel engines (HDDEs) using waste heat recovery (WHR) technologies. WHR based on Organic Rankine Cycle (ORC) is a promising technology, which offers potential to reduce the fuel consumption of HDDEs by transferring the wasted thermal energy to alternative useful electrical or mechanical energy. In the ORC, the evaporator is considered the most critical component, because it has a high thermal inertia. Previous numerical models of evaporator are computationally expensive due to non-linearity of evaporator governing equations and cannot be deployed for real-time control applications. This study uses an Adaptive Network-based Fuzzy Inference System (ANFIS) modelling technique to provide efficient control-oriented evaporator models for prediction of heat source and refrigerant temperatures at the evaporator outlet. Hybrid gradient decent, least square estimate (GD-LSE) and particle swarm optimization (PSO) algorithms for training the ANFIS model have been investigated and show that training ANFIS using the PSO method results in an improvement in accuracy. Furthermore, the systematic and adaptive approach of the ANFIS modelling technique makes the procedure of evaporator modelling less dependent on expert knowledge, reducing the modelling effort.

Modeling water flux in osmotic membrane bioreactor by adaptive network-based fuzzy inference system and artificial neural network

Osmotic Membrane Bioreactor (OMBR) is an emerging technology for wastewater treatment with membrane fouling as a major challenge. This study aims to develop Adaptive Network-based Fuzzy Inference System (ANFIS) and Artificial Neural Network (ANN) models in simulating and predicting water flux in OMBR. Mixed liquor suspended solid (MLSS), electrical conductivity (EC) and dissolved oxygen (DO) were used as model inputs. Good prediction was demonstrated by both ANFIS models with R2 of 0.9755 and 0.9861, and ANN models with R2 of 0.9404 and 0.9817, for thin film composite (TFC) and cellulose triacetate (CTA) membranes, respectively. The root mean square error for TFC (0.2527) and CTA (0.1230) in ANFIS models was lower than in ANN models at 0.4049 and 0.1449. Sensitivity analysis showed that EC was the most important factor for both TFC and CTA membranes in ANN models, while EC (TFC) and MLSS (CTA) are key parameters in ANFIS models.

Determination of bubble point pressure and oil formation volume factor: Extra trees compared with LSSVM-CSA hybrid and ANFIS models

Successful field development relies on effective reservoir management, which, in turn, is, to a great extent, influenced by the knowledge of reservoir fluid properties and phase behaviour. Laboratory experiments, known as Pressure-Volume-Temperature (PVT) tests, are the most reliable sources of detailed information on reservoir fluid properties required for different recovery stages and methods. However, these laboratory experiments are costly and time-consuming. Also, the experimental data of reservoir fluids are not readily available in many cases, particularly in early stages of field development when such data are required for estimation of the in-place fluid volumes and/or design of enhanced recovery processes. For these reasons, the development of models for prediction of reservoir fluid properties, especially the bubble point pressure (Pb) and oil formation volume factor (Bo), has been an active area of research since decades ago. In this paper, we have used the effective machine learning approaches of Extremely Randomized Trees, also called Extra Trees (ET), Least Square Support Vector Machine (LSSVM) hybridized with the Coupled Simulated Annealing (CSA) algorithm, and Adaptive Network-based Fuzzy Inference System (ANFIS) to develop models for prediction of Bo and Pb. An extensive dataset of the essential reservoir and fluid properties comprised of initial solution gas-oil ratio (Rsi), gas specific gravity (γg), oil API gravity (API), and reservoir temperature (T), in addition to the target parameters, has been used to introduce the models. The main focus of this study is on the ET modelling method which we have used as a robust tool to predict the fluid properties of interest with high accuracy over wide ranges of the input features. The other two modelling techniques, i.e. LSSVM-CSA hybrid and ANFIS, have been used in this work to provide a basis for comparison and evaluation of the models. The predictions of the developed models greatly match the real data. Through detailed model evaluation and error analysis, it is shown that the ET model outperforms the other models in terms of accuracy and robustness (with very small mean absolute percentage errors of 0.099% and 0.917% for Bo and Pb predictions, respectively, over the total dataset), although all the developed models exhibit strong performance and comparably accurate predictions. Moreover, the developed ET models show a strong correlation between the predicted data and the target values with R2 > 0.99 in almost all cases over the training, test, and total datasets. The findings of this study can help to better understand the relative importance of the different reservoir fluid parameters typically used for the prediction of Bo and Pb. Based on this work, with the ET approach, Pb and Rsi have the highest importance in determining Bo and Pb, respectively, while temperature has the lowest significance in both cases. To the best of our knowledge, this work is the first Bo and Pb modelling attempt using the ET method. Additionally, we have applied the feature selection capability of the tree-based estimators to develop a new ET model for prediction of Pb using only two parameters (Rsi and γg); an outcome that is of particular importance in case of the lack of data on other parameters which are required in almost all the other Pb predictive tools and correlations reported in the literature.

Estimating biofuel density via a soft computing approach based on intermolecular interactions

In this work, the density of biofuel is estimated using four intelligent models: a Least Square Support Vector Machine (LSSVM), a Radial Basis Function Artificial Neural Network (RBF-ANN), a Multi-layer Perceptron Artificial Neural Network (MLP-ANN), and an Adaptive Network-based Fuzzy Inference System (ANFIS). These models are used to estimate the density of biofuel based on intermolecular interactions and the van der Waals radii of the atoms. Various statistical analyses are performed on the original (experimental) and estimated data. It is found that the LSSVM model can provide more accurate predictions than the other three models. The R-squared value (R2) and the mean absolute relative error (MARE) for the LSSVM, RBF-ANN, MLP-ANN and ANFIS models are 0.847 & 0.056, 52.067 & 0.379, 57.385 & 0.371 and 65.096 & 0.678, respectively. This study shows that the LSSVM model is a promising tool for estimating the density of biofuel, offering an alternative to classic thermodynamic models.

Adaptive Neuro-Fuzzy Inference System and a Multilayer Perceptron Model Trained with Grey Wolf Optimizer for Predicting Solar Diffuse Fraction

The accurate prediction of the solar Diffuse Fraction (DF), sometimes called the Diffuse Ratio, is an important topic for solar energy research. In the present study, the current state of Diffuse Irradiance research is discussed and then three robust, Machine Learning (ML) models, are examined using a large dataset (almost 8 years) of hourly readings from Almeria, Spain. The ML models used herein, are a hybrid Adaptive Network-based Fuzzy Inference System (ANFIS), a single Multi-Layer Perceptron (MLP) and a hybrid Multi-Layer Perceptron-Grey Wolf Optimizer (MLP-GWO). These models were evaluated for their predictive precision, using various Solar and Diffuse Fraction (DF) irradiance data, from Spain. The results were then evaluated using two frequently used evaluation criteria, the Mean Absolute Error (MAE) and the Root Mean Square Error (RMSE). The results showed that the MLP-GWO model, followed by the ANFIS model, provided a higher performance, in both the training and the testing procedures.

Intelligent Machining System Based on CNC Controller Parameter Selection and Optimization

This paper introduces an intelligent machining system (IMS) using an adaptive-network-based fuzzy inference system (ANFIS) predictor and the particle swarm optimization (PSO) algorithm with a hybrid objective function. The proposed IMS provides suitable machining parameters for the users, to satisfy different machining requirements such as accuracy, surface smoothness, and speed. First, the key computer numerical control parameters are selected, and the actual trajectories under different machining parameters obtained by linear scales are collected. These data are analyzed to obtain the machining time, contouring error, and tracking error, corresponding to the speed, milling accuracy, and surface smoothness, respectively. Second, a data-driven approach using ANFIS is established to obtain the corresponding relationship model between the machining parameters and three aforementioned performance indices. Subsequently, to establish the IMS, we combine the trained ANFIS model and establish a hybrid objective function optimization problem solved by PSO algorithm according the specific requirement of the user. Finally, the performance and effectiveness of the proposed machining system is demonstrated by experimental practical machining.

EMD–PSO–ANFIS‐based hybrid approach for short‐term load forecasting in microgrids

Accurate renewable energy generation and electricity demand forecasting tools constitute an essential part of the energy management system functions in microgrids. This study proposes a hybrid approach for short-term load forecasting in microgrids, which integrates empirical mode decomposition (EMD), particle swarm optimisation (PSO) and adaptive network-based fuzzy inference systems (ANFISs). The proposed technique first employs EMD to decompose the complicated load data series into a set of several intrinsic mode functions (IMFs) and a residue, and PSO algorithm is then used to optimise an ANFIS model for each IMF component and the residue. The final short-term electric load forecast value could be obtained by summing up the prediction results from each component model. The performance of the proposed model is examined using load demand dataset of a case study microgrid in Beijing and is compared with four other forecasting methods using the same dataset. The results show that the proposed approach yielded superior performance for short-term forecasting of microgrid load demand compared with the other methods.

Fault disturbances classification analysis using adaptive neuro-fuzzy inferences system

This paper affords the use of neuro-fuzzy technique called the Adaptive Network–based Fuzzy Inference System (ANFIS) to highlight its ability to perform fault disturbances classification tasks using extracted features based on S-transforms methods. The ANFIS model with a five-layered architecture was trained using extracted features to classify signal data comprising various faults disturbances, namely, voltage sag, swell, impulsive, interruption, notch, and pure signal. Results obtained showed that the ANFIS model is very suitable and can generate excellent classification results provided that the right type and number of Membership Functions (MFs) are used in the classification task.

Improvement of the ANFIS-based wave predictor models by the Particle Swarm Optimization

In this paper, the Particle Swarm Optimization (PSO) algorithm is employed to deal with the Adaptive Network based Fuzzy Inference System (ANFIS) model drawbacks in prediction of wind –driven waves. In the ANFIS model selection of fuzzy IF-THEN rules structure and numbers is not an automatic process. In addition, in the ANFIS model extraction of fuzzy antecedent and consequent parameters is a gradient-based method which makes the answer susceptible to entrap in local optima. To cope with the ANFIS deficiencies, herein the PSO algorithm is coupled with the wave predictor FIS models in three viewpoints to optimize fuzzy subtractive clustering parameters, i.e. radii of clustering and quash factor, and the antecedent and consequent parameter of fuzzy IF-THEN rules. At first viewpoint, two PSO algorithms are used to optimize fuzzy subtractive clustering parameters and fuzzy IF-THEN rule parameters. In the second viewpoint, a PSO algorithm is used to optimize subtractive clustering parameters while the ANFIS model is used to tune the fuzzy IF-THEN rule parameters. In the third viewpoint, only a PSO algorithm is used to optimize the subtractive clustering parameters along with fuzzy IF-THEN rule parameters. Gathered data sets by National Data Buoy Center (NDBC) at Lake Michigan are used to evaluate the developed models for prediction of wave parameters including significant wave height and peak spectral period. Results indicate the efficiency of PSO algorithm to improve the ANFIS model accuracy.

An adaptive network-based fuzzy inference system to supply chain performance evaluation based on SCOR® metrics

Evaluating the performance of supply chains (SC) is a critical activity to enhance the outcomes of operations along the SC tiers. In order to support this evaluation process, several studies have proposed the application of artificial intelligence techniques combined with the performance metrics suggested by the SCOR® model (Supply Chain Operations Reference). However these propositions present some limitations. While the systems based on Mamdani fuzzy inference do not allow adaptation to the environment of use based on historical performance data, the systems based on artificial neural networks are not adequate to deal with imprecise data and qualitative metrics. In order to overcome these limitations, this paper presents a new approach to support SC performance evaluation based on the combination between the SCOR® metrics with an adaptive network-based fuzzy inference systems (ANFIS). In total, 56 candidate topologies were implemented and assessed using MATLAB. The random subsampling cross-validation method was applied to select the most appropriate topological parameters for each ANFIS model. The mean square error between the target values and the values estimated by each ANFIS model demonstrate its greater accuracy of prediction. In addition, results of the hypothesis tests based on paired samples indicate that the proposed ANFIS models are adequate to support SC performance evaluation. The proposed system can help managers to develop improvement actions plans based on the outcomes of the evaluation process. When compared to previous approaches, it presents advantages such as greater accuracy of prediction, learning ability based on historical data, suitability to support decision making under uncertainty, better interpretability of results, among others.

Tensile Strength Enhancement of Aisi 304 and Aisi 1040 Dissimilar Friction Weld Joints using Anfis Modelling

Friction welding is a promising technique for the welding of dissimilar metals. This study deals with the welding of two different alloys, namely, AISI 304 and AISI 1040. The welding process parameters, namely, friction pressure, friction time, forging pressure, and forging time were optimized for maximum tensile strength using a response surface methodology (RSM)-based technique and an adaptive-network-based fuzzy inference system (ANFIS) model. The predicted responses obtained using the ANFIS model were more accurate compared to those obtained using the RSM. From among the four input parameters examined in the study, the frictional pressure was found to be the most influential. The ANFIS model developed in this study shows significant promise as a predictive technique that can provide reasonable estimates of tensile strength for different welding parameters.

Biogas production estimation using data-driven approaches for cold region municipal wastewater anaerobic digestion

The objective of this study was to estimate biogas (including methane, carbon dioxide and hydrogen sulphide) production rates from the anaerobic digesters at the Saskatoon Wastewater Treatment Plant (SWTP), Saskatchewan, Canada. Average daily ambient temperatures typically fluctuate between −40 °C and 30 °C over the year making the management of the SWTP processes challenging. Operating parameters were taken from 2014 to 2016 including volatile fatty acids (VFAs), total solids, fixed solids, volatile solids, pH, and inflow rate. The input parameters were processed using two methods including a correlation test and principal component analysis (PCA) to determine highly correlated variables prior to use in models. The two models used to estimate biogas production rates are a multi-layered perceptron feed forward artificial neural network (ANN) and an adaptive network-based fuzzy inference system (ANFIS) with grid partition (GP), subtractive clustering (SC) and fuzzy c-means clustering (FCMC). The models using PCA processed variables had reasonable performances with shorter model processing times, while reducing model input data. Among various structures of ANN and ANFIS models for estimation of biogas generation, the ANFIS-FCMC results had better agreement with the observed data. Its average approximation of emission rates of CH4, CO2 and H2S from the wastewater digesters were 3,086, 6,351, and 41.5 g/min, respectively. Our group is assessing similar estimation methodology for the remaining SWTP wastewater treatment processes that are more highly impacted by the seasonal temperature variations including primary and secondary treatment processes.

Application of ANFIS for the Selection of Optimal Wire-EDM Parameters While Machining Ti-6Al-4V Alloy and Multi-Parametric Optimization Using GRA Method

The applications of artificial intelligence (AI) are becoming more popular and relevant research have been conducted in every field of engineering and science by using these AI techniques. Therefore, this research aims to examine the influence of wire electric-discharge machining (WEDM) parameters on performance parameters to improve the productivity with a higher surface finish of titanium alloy (Ti-6Al-4V) by using the artificial intelligent technique. In this experimental analysis, the Adaptive Network Based fuzzy Inference System (ANFIS) model has been highly-developed and the multi-parametric optimization has been done to find the optimal solution for the machining of the titanium superalloy. The peak current (Ip), taper angle, pulse on time (Ton), pulse of time (Toff) and the dielectric fluid flow rate were selected as operation constraints to conduct experimental trials. The surface roughness (SR) and MRR were considered as output responses. The influence on machining performance has been analyzed by an ANFIS model and the developed model was validated with the full factorial regression models. The developed models showed the minimum mean percentage error and the optimized parameters by the GRA method showed the considerable improvement in the process.