Adaptive Neural Fuzzy Inference System Model Research Articles

Prophesying egg production based on energy consumption using multi-layered adaptive neural fuzzy inference system approach

Adaptive neural fuzzy inference system (ANFIS) is an intelligent neuro-fuzzy technique used for modeling and control of uncertain systems. In this paper, we proposed an ANFIS based modeling approach (called MLANFIS) where the number of data pairs employed for training was adjusted by application of clustering method. By employing this method, the number of data required for learning step and thereby its complexity were significantly reduced. The results obtained were compared with those obtained by using artificial neural networks (ANNs). Inputs to the first group were feed supply, fuel and machinery and the ones to second cluster were pullet, electricity and labor energies. Finally, the outputs of aforementioned networks were considered as inputs to ANFIS 3 network and predicted values of egg yield were derived. The coefficient of determination (R2), root mean square error (RMSE) and mean absolute percentage error (MAPE) parameters of ANFIS 3 network were calculated as 0.92, 448.126, 0.014, respectively showing that ANFIS compared with ANNs with statistical parameters as 0.81, 751.96 and 0.019 respectively, can properly predict the egg yield of poultry farms. As a recommendation for future studies, ANFIS models with multi-layered structures can be developed to find the optimum number of layers.

Evaluation of hydrological and data-based models in estimation of daily runoff in Galikesh watershed

Estimating the runoff in a watershed is important not only in the management and proper land-use utilisation, but also plays an important role in minimising the flood damages. In this paper, four methods were used to simulate daily runoff in the Galikesh watershed. In the first method, IHACRES hydrological model was used and in other methods three data-based models, namely, artificial neural network (ANN), K-nearest neighbourhood (KNN) and adaptive neural-fuzzy inference system (ANFIS) were applied. First calibration and training of hydrological and ANN, KNN and ANFIS models, then the performance of all models were compared for both calibration and test periods. Results showed that the data-based models had better performance in simulating the rainfall-runoff process than the hydrological model. Based on observed and simulated runoffs, the correlation coefficient for KNN, ANN and ANFIS were calculated as 0.85, 0.83 and 0.85 and the root mean square error equalled to 1.106, 1.1667 and 1.1168 m³/s, respectively. This is while for IHACRES hydrological model, the correlation coefficient and root mean square error were derived as 0.67 and 1.54 m³/s, respectively.

Empirical modeling for processing parameters’ effects on coating properties in plasma spraying process

In order to model the effects of processing parameters (primary gas flow rate, stand-off distance, powder flow rate, and arc current) on the plasma spraying coating properties (thickness, porosity and micro-hardness), adaptive neural fuzzy inference system (ANFIS) and neural network (NN) based empirical models were proposed to estimate process parameters and understand the spraying process. To overcome the difficulty of the small size of sample data, and to balance the trade-off between model complexity and prediction accuracy, the bootstrap method was applied for the resampling technique, and cross validation was applied for the performance evaluation. The ANFIS and NN models were compared on the performance metrics of (1) mean square error (MSE), and (2) determination coefficient (R2). With the limited size of experiment data, both models illustrated high accuracy. In the training stage: on the R2, ANFIS has the value of 1, and NN has the minimum value of 0.84; on the MSE, ANFIS has the minimum value of 1.3e−5, and NN has the minimum value of 0.32. In the validation stage: on the R2, ANFIS has the minimum mean value of 0.42, and NN has the minimum mean value of 0.512; on the MSE, ANFIS has the minimum mean value of 23.67, and NN has the minimum mean value of 89.50. The comparisons illustrated that ANFIS model showed significant superiority over the NN model. This may be due to the fact that ANFIS combines the strength of NN's learning capability and fuzzy logic's knowledge interpretation ability. With the obtained ANFIS model, the physical mechanisms – including (1) melting states of particles, (2) loading effect, and (3) oxidation – were interpreted as processing parameters’ effects on the coating properties. The empirical models and that physical mechanism are viable to be effectively integrated with feedback control strategy to regulate the coating quality in plasma spraying process.

Comparison of two models for the biosorption of Pb(II) using untreated and chemically treated olive stone: Experimental design methodology and adaptive neural fuzzy inference system (ANFIS)

The main objective of this work is to fit results from lead biosorption by untreated and chemically treated olive stone (OS) using two models: means of full factorial design methodology and fuzzy neural network. Concretely, OS was modified by three chemical agents: HNO3, H2SO4 and NaOH, in order to improve its biosorption capacity. The examined operational variables were: concentration of chemical agent (0.1–2 M), pH (3–5) and initial lead concentration (50–250 mg/L), and the studied response was biosorption capacity (mg/g).Results obtained from full factorial design methodology showed that all these factors considerably affected the studied response. Experimental results were fitted by a second-order equation showing the influence of each factor and their interactions. While the application of a fuzzy neural network model allowed to predict the results for the dependent variables as a function of the operating conditions used with errors less than 5% in all cases. Observed results were different when the biosorbent was treated with acid treatment or with basic one, although for all treatments the highest biosorption capacity was obtained with a concentration 2 M. Finally, models were compared and it is showed that ANFIS model predicted better experimental data with higher R2 values.

Development of an intelligent model for wax deposition in oil pipeline

Crude oil transport is one important part of the oil industry. Wax deposition is a very complex phenomenon that in recent years is one of the major challenges in oil industry. Wax deposited on the inner surface of crude oil pipelines are capable to reduce or completely stop the oil flow and the oil industry imposing large costs. The main objective of this study was to present a novel approach for predication of wax deposition thickness in single-phase turbulent flow rate. Using experimental data set and Adaptive neural-fuzzy inference system (ANFIS) model was developed. From the results predicted by this model, it can be pointed out that the ANFIS model can be used as powerful tools for prediction of wax deposition thickness in single-phase turbulent flow rate with mean square error, absolute relative deviation error and average absolute deviation error which are 0.00077034, 0.015720 and 0.097961, respectively.

Adaptive Neural Fuzzy Inference System Models for Predicting the Shear Strength of Reinforced Concrete Deep Beams

A reinforced concrete member in which the total span or shear span is especially small in relation to its depth is called a deep beam. In this study, a new approach based on the Adaptive Neural Fuzzy Inference System (ANFIS) is used to predict the shear strength of reinforced concrete (RC) deep beams. A constitutive relationship was obtained correlating the ultimate load with seven mechanical and geometrical parameters. These parameters contain Web width, Effective depth, Shear span to depth ratio, Concrete compressive strength, Main reinforcement ratio, Horizontal shear reinforcement ratio and Vertical shear reinforcement ratio.The ANFIS model is developed based on 214 experimental database obtained from the literature. The data used in the present study, out of the total data, 80% was used for training the model and 20% for checking to validate the model. The results indicated that ANFIS is an effective method for predicting the shear strength of reinforced concrete (RC) deep beams and has better accuracy and simplicity compared to the empirical methods.

Modeling output energy based on fossil fuels and electricity energy consumption on dairy farms of Iran: Application of adaptive neural-fuzzy inference system technique

This research examined an adaptive neural-fuzzy inference system to model output energy on the basis of energies of fossil fuels and electricity inputs. Energy use especially non-renewable forms are widely considered in livestock farming management in recent years. Data were collected randomly from 50 dairy farms in Tehran province of Iran in 2011. A review of the published literature indicated that the adaptive neural-fuzzy inference system (ANFIS) has rarely been used or tested to model agricultural energy demand. ANFIS model based on energy consumption was developed for dairy farm units in Tehran province, Iran. In this research, fossil fuels and electrical energy required and energy output produced were treated as inputs and output of ANFIS model, respectively. The computational results demonstrated that ANFIS model is generally comparable with linear regression analysis approach and is promising in modeling fossil fuels and electricity energy consumption. The comparison of the coefficient of determination (R2) (0.79 and 0.11), the root mean square error (RMSE) (0.11 and 0.22) and the mean absolute percentage error (MAPE) (0.007 and 0.014) demonstrated the above mentioned result for both proposed methods, respectively. The accurate model performance is beneficial to predict energy usage as the first step toward energy management and it would be constructive in developing future energy related researches and planning strategies.

Performance Evaluation of Adaptive Neural Fuzzy Inference System for Sediment Transport in Sewers

The application of models capable of estimating sediment transport in sewers has been a frequent practice in the past years. Considering the fact that predicting sediment transport within the sewer is a complex phenomenon, the existing equations used for predicting densimetric Froude number do not present similar results. Using Adaptive Neural Fuzzy Inference System (ANFIS) this article studies sediment transport in sewers. For this purpose, five different dimensionless groups including motion, transport, sediment, transport mode and flow resistance are introduced first and then the effects of various parameters in different groups on the estimation of the densimetric Froude number in the motion group are presented as six different models. To present the models, two states of grid partitioning and sub-clustering were used in Fuzzy Inference System (FIS) generation. Moreover, the training algorithms applied in this article include back propagation and hybrid. The results of the proposed models are compared with the experimental data and the existing equations. The results show that ANFIS models have greater accuracy than the existing sediment transport

Estimation of Arsenic Contamination in Reclaimed Agricultural Soils Using Reflectance Spectroscopy and ANFIS Model

Heavy metal contamination from anthropogenic sources is a threat to human health. To assess the feasibility of predicting surface soil arsenic (As) concentration from hyperspectral reflectance measurement, three different regression algorithms are compared in this paper, i.e., multiple linear regression (MLR), partial least squares regression (PLSR), and adaptive neural fuzzy inference system (ANFIS) modeling. Soil samples were taken from three study sites in mining/agricultural areas after reclamation. As concentration was determined by hydride generation atomic fluorescence spectrometry (HG-AFS) analysis, and the reflectance was measured with an analytical spectral devices (ASD) field spectrometer covering the spectral region of 350–2500 nm. First, after preprocessing of the original reflectance spectroscopy, the correlation coefficients between the As concentration and spectral reflectance measurement were derived. Characteristic bands were then chosen for the quantitative retrieval model. Finally, all of the 30 samples were divided into a calibration set and a validation set of 18 and 12 samples, respectively. When compared with the MLR and PLSR algorithms, the ANFIS model was the best retrieval model, with a coefficient of determination ( <formula formulatype="inline" xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"><tex Notation="TeX">${\bf R}^{\bf 2}$</tex> </formula> ) of 0.94 and a root-mean-square error (RMSE) of 0.88. ANFIS model and reflectance spectroscopy therefore have the potential to map the spatial distribution of As abundance, with the aim of improving public health.

Application of neural network and ANFIS model for earthquake occurrence in Iran

This study examined the spatial-temporal variations in seismicity parameters for the September 10th, 2008 Qeshm earthquake in south Iran. To this aim, artificial neural networks and Adaptive Neural Fuzzy Inference System (ANFIS) were applied. The supervised Radial Basis Function (RBF) network and ANFIS model were implemented because they have shown the efficiency in classification and prediction problems. The eight seismicity parameters were calculated to analyze spatial and temporal seismicity pattern. The data preprocessing that included normalization and Principal Component Analysis (PCA) techniques was led before the data was fed into the RBF network and ANFIS model. Although the accuracy of RBF network and ANFIS model could be evaluated rather similar, the RBF exhibited a higher performance than the ANFIS for prediction of the epicenter area and time of occurrence of the 2008 Qeshm main shock. A proper training on the basis of RBF network and ANFIS model might adopt the physical understanding between seismic data and generate more effective results than conventional prediction approaches. The results of the present study indicated that the RBF neural networks and the ANFIS models could be suitable tools for accurate prediction of epicenteral area as well as time of occurrence of forthcoming strong earthquakes in active seismogenic areas.

Modeling of Water Quality Parameters Using Data-Driven Models

Water has a considerable role in all aspects of human life. Thus, evaluation of water characteristics in general and water quality in particular are necessary to enhance the health of humans and ecosystems. Data-driven models are computing methods that are capable of extracting different system states without using complex relationships. Prediction and simulation are two branches of data-driven modeling that use previous and previous-current data sets to fill gaps in time series. This paper investigates the capability of an adaptive neural fuzzy inference system (ANFIS) and genetic programming (GP) as two data-driven models to predict and simulate water quality parameters (e.g., sodium, potassium, magnesium, sulfates, chloride, pH, electrical conductivity, and total dissolved solids) at the Astane station in Sefidrood River, Iran. The writers considered six combinations of data sets, including the previously noted water quality parameters and river discharge in the previous and previous-current months, as input data. Implementation of the ANFIS and GP models in this paper illustrates the flexibility of GP in time series modeling relative to ANFIS, especially in the testing data set. Accordingly, the writers calculated the coefficient of variation of root mean squared error as the error criterion in different ANFIS and GP models (for assigning achievement probability to an appropriate solution) for each quality parameter. The average of the previously noted values for the six combinations of data sets improved (decreased) 80.51 and 80.89%, respectively, in the training and testing data sets with GP relative to ANFIS. These results indicate that the writers’ proposed modeling, based on GP, is an effective tool for determining water quality parameters.

Estimation of dew point temperature using neuro-fuzzy and neural network techniques

This study investigates the ability of two different artificial neural network (ANN) models, generalized regression neural networks model (GRNNM) and Kohonen self-organizing feature maps neural networks model (KSOFM), and two different adaptive neural fuzzy inference system (ANFIS) models, ANFIS model with sub-clustering identification (ANFIS-SC) and ANFIS model with grid partitioning identification (ANFIS-GP), for estimating daily dew point temperature. The climatic data that consisted of 8 years of daily records of air temperature, sunshine hours, wind speed, saturation vapor pressure, relative humidity, and dew point temperature from three weather stations, Daego, Pohang, and Ulsan, in South Korea were used in the study. The estimates of ANN and ANFIS models were compared according to the three different statistics, root mean square errors, mean absolute errors, and determination coefficient. Comparison results revealed that the ANFIS-SC, ANFIS-GP, and GRNNM models showed almost the same accuracy and they performed better than the KSOFM model. Results also indicated that the sunshine hours, wind speed, and saturation vapor pressure have little effect on dew point temperature. It was found that the dew point temperature could be successfully estimated by using Tmean and RH variables.

Modelling and measuring the thermal conductivity of multi-metallic Zn/Cu nanofluid

A metallic nanofluid is a suspension of metallic nanoparticles in a base fluid. Multi-metallic nanoparticles are a combination of two or more types of metallic particles. Such multi-metallic nanoparticles were suspended in water using an ultrasonic vibrator for different total volume fractions and different ratios of metallic/metallic nanoparticles. A transient hot wire setup was built to measure the thermal conductivity of the nanofluid at different temperatures. The experimental results were in good agreement with the results in the literature. Then, the experimental results were used as input data for an adaptive neural fuzzy inference system (ANFIS) to predict the thermal conductivity of the multi-metallic nanofluid. The maximum deviation between the ANFIS results and experimental measurements was 1 %. The predicted results and the experimental data were compared with other models. The ANFIS model was found to have good ability to predict the thermal conductivity of the multi-metallic nanofluid over the range of the experimental results.

Predication of concrete mix design using adaptive neural fuzzy inference systems and fuzzy inference systems

The aim of this study is to design adaptive neural-fuzzy inference system (ANFIS) model and fuzzy expert system for determination of concrete mix designs and finally compare their results. Idea of these systems based on two surveys: first, ACI structures and principles, second a concrete mix designs dataset that collected via Prof. I-Cheng Yeh. Datasets that loaded in to ANFIS has 552 mix designs and based on ACI mix designs. Moreover, in this study, we have designed fuzzy expert system. Input fields of fuzzy expert system are Slump, Maximum Size of Aggregate (Dmax), Concrete Compressive Strength (CCS), and Fineness Modulus. Output fields are quantities of water, cement, fine aggregate (F.A.) and coarse aggregate (C.A.). In the ANFIS model, we have four layers (four ANFIS models): the first layer takes values of Dmax and Slump and then determines the quantity of Water, the second layer takes values of Water (computed in the past layer) and CCS then measures the value of Cement, the third layer takes values of Dmax and Slump to compute C.A. and the fourth layer takes values of Water, Cement, and C.A. (determined in past layers) and then measures the value of F.A. When these systems were designed and tested, comparison between two systems (FIS and ANFIS) results showed that results of ANFIS model are better than fuzzy expert system’s results. In the ANFIS model, for Water output field, training and average testing errors are 0.86 and 0.8. For cement field, training error and average testing error are in the orders of 0.21 and 0.22. Training and average testing error of C.A. are in the orders of 0.0001 and 0.0004 and finally, training and average testing errors of F.A. are in the orders of 0.0049 and 0.0063. Results of fuzzy expert system in comparison to ACI results follow average errors: average error of Water, Cement, C.A., and F.A. are in the orders of 9.5%, 27.6%, 96.5%, and 49%.

Real Time Monitoring and Neuro-Fuzzy Based Fault Diagnosis of Flow Process in Hybrid System

Process variables vary with time in certain applications. Monitoring systems let us avoid severe economic losses resulting from unexpected electric system failures by improving the system reliability and maintainability The installation and maintenance of such monitoring systems is easy when it is implemented using wireless techniques. ZigBee protocol, that is a wireless technology developed as open global standard to address the low-cost, low-power wireless sensor networks. The goal is to monitor the parameters and to classify the parameters in normal and abnormal conditions to detect fault in the process as early as possible by using artificial intelligent techniques. A key issue is to prevent local faults to be developed into system failures that may cause safety hazards, stop temporarily the production and possible detrimental environment impact. Several techniques are being investigated as an extension to the traditional fault detection and diagnosis. Computational intelligence techniques are being investigated as an extension to the traditional fault detection and diagnosis methods. This paper proposes ANFIS (Adaptive Neural Fuzzy Inference System) for fault detection and diagnosis. In ANFIS, the fuzzy logic will create the rules and membership functions whereas the neural network trains the membership function to get the best output. The output of ANFIS is compared with Back Propagation Algorithm (BPN) algorithm of neural network. The training and testing data required to develop the ANFIS model were generated at different operating conditions by running the process and by creating various faults in real time in a laboratory experimental model.

ANFIS and statistical based approach to prediction the peak pressure load of concrete pipes including glass fiber

In this paper, Adaptive Neural Fuzzy Inference System (ANFIS) and Multiple Linear Regression (MLR) models are discussed to determine peak pressure load measurements of the 0, 0.2, 0.4 and 0.6% glass fibers (by weight) reinforced concrete pipes having 200, 300, 400, 500 and 600mm diameters. For comparing the ANFIS, MLR and experimental results, determination coefficient (R2), root mean square error (RMSE) and standard error of estimates (SEE) statistics were used as evaluation criteria. It is concluded that ANFIS and MLR are practical methods for predicting the peak pressure load (PPL) values of the concrete pipes containing glass fibers and PPL values can be predicted using ANFIS and MLR without attempting any experiments in a quite short period of time with tiny error rates. Furthermore ANFIS model has the predicting potential better than MLR.

Study on ANFIS Application in Coal Mining Stray Current Security Prediction

On basis of analyzing the principles and structure of adaptive neural fuzzy inference system (ANFIS), this thesis used subtractive clustering algorithm to get fuzzy inference rule numbers and confirm the network structure. In addition, the thesis built ANFIS model adapted to coal mining workface stray current security prediction. The model can do workface stray current security prediction by the easy measured parameters of non-production field. If the stray current exceeds standard, the system will alarm on time. Moreover, the thesis compared accuracy rate of the security prediction results under different membership functions. The results indicate that the prediction accuracy of ANFIS based on subtractive clustering is the highest and its computing speed is faster. The prediction results to practical project data indicate that stray current security prediction based on ANFIS has favorable practicality and effect.

Designing expert system for in situ toughened Si 3N 4 based on adaptive neural fuzzy inference system and genetic algorithms

Adaptive neural fuzzy inference system (ANFIS) combined with GAs is applied to develop an expert system for designing in situ toughened Si 3N 4 in this paper. ANFIS combines fuzzy linguistic descriptions with accurate experimental data. GAs have been successfully applied in searching and optimizing very large and varied data spaces. ANFIS models were developed in this paper to predict mechanical properties based on sintering processing or microstructure. And GAs models are developed to predict sintering processing based on mechanical properties or microstructure of this material. A software package was developed to realize the applications mentioned above easily and quickly.

CHLfuzzy: a spreadsheet tool for the fuzzy modeling of chlorophyll concentrations in coastal lagoons

CHLFuzzy is a user-friendly, flexible, multiple-input single-output Takagi-Sugeno fuzzy rule based model developed in a MS-Excel® spreadsheet environment. The model receives a raw dataset consisting of four predictor variables, e.g., water temperature, dissolved oxygen content, dissolved inorganic nitrogen concentration, and solar radiation levels. It then defines fuzzy sets according to a collection of fuzzy membership functions, allowing for the establishment of fuzzy ‘if–then’ rules, and predicts chlorophyll-a concentrations, which highly compare to the measured ones. The performance of the model was tested against the Adaptive Neural Fuzzy Inference System (ANFIS), showing satisfactory results. An extensive dataset of environmental observations in Vassova Lagoon (Northern Greece), during the years 2001–2002, was used to train the model and an independent dataset collected during 2004 was used to validate CHLFuzzy and ANFIS models. Although both models showed a similar performance on the training dataset, with quite satisfactory agreement between observed and modeled chlorophyll-a values, the best results were obtained using the CHLfuzzy model. Similarly, the CHLfuzzy model depicted a fairly good ability to hindcast chlorophyll-a concentrations for the verification dataset, thus improving ANFIS model forecasts. Overall results suggest that CHLfuzzy can potentially be used as a lagoon water quality forecasting tool requiring limited computational cost.

Nonlinear modeling of a SOFC stack based on ANFIS identification

An adaptive neural-fuzzy inference system (ANFIS) model is developed to study different flows effect on the performance of solid oxide fuel cell (SOFC). During the process of modeling, a hybrid learning algorithm combining backpropagation (BP) and least squares estimate (LSE) is adopted to identify linear and nonlinear parameters in the ANFIS. The validity and accuracy of modeling are tested by simulations and the simulation results reveal that the obtained ANFIS model can efficiently approximate the dynamic behavior of the SOFC stack. Thus it is feasible to establish the model of SOFC stack by ANFIS.