Adaptive Neuro-fuzzy Interference System Model Research Articles

Utilizing ANFIS for strength characteristics forecasting in variable heat-cured geopolymer composites

Reducing cement usage through geopolymer concrete (GPC) can be crucial for resolving environmental concerns. The byproduct of the coal and steel industry, such as fly ash (FA) and ground granulated blast furnace slag (GGBS), is mainly used as a precursor in the production of GPC due to the availability of aluminosilicate products in it. In this work, nano silica is added to the GPC in different percentages and GPC is cured at different temperatures to study the change in the strength of GPC due to change in curing temperature. The compressive strength, flexural strength, and split tensile strength up to 68.99 MPa, 5.89 MPa, 6.82 MPa, respectively was achieved after 28 days of heat curing. However, testing GPC experimentally to anticipate its strength is time-consuming and expensive. Therefore, the ability to precisely forecast concrete strength can be achieved through machine learning. In this study, the correlation for both nano silica (%) and curing temperature towards the strength of concrete is also investigated using adaptive neuro fuzzy interference system (ANFIS) models. ANFIS results showed better compressive, split tensile, and flexural strength prediction with the highest R2 0.9801, 0.9943, and 0.9877, respectively. The performance efficiency of the developed ANFIS model is more significant minimum error for compressive strength prediction (MAE = 0.21375, RMSE = 0.02574, MAPE = 0.42), split tensile strength prediction (MAE = 0.07375, RMSE = 0.0923, MAPE = 1.46) and flexural strength prediction (MAE = 0.04, RMSE = 0.0728, MAPE = 0.78) of GPC cured under different temperature conditions. The results from experiments show that the prediction efficiency of the model is also good, as indicated by the correlation coefficient (R). This model is helpful for further designing the proportion of material for achieving good strength of GPC.

Predictive modeling of copper (II) adsorption from aqueous solutions by sawdust: a comparative analysis of adaptive neuro-fuzzy interference system (ANFIS) and artificial neural network (ANN) approaches

Heavy metal ions are considered to be the most prevalent and toxic water contaminants. The objective of thois work was to investigate the effectiveness of employing the adsorption technique in a laboratory-size reactor to remove copper (II) ions from an aqueous medium. An adaptive neuro-fuzzy inference system (ANFIS) and a feed-forward artificial neural network (ANN) were used in this study. Four operational factors were chosen to examine their influence on the adsorption study: pH, contact duration, initial Cu (II) ions concentration, and adsorbent dosage. Using sawdust from wood, prediction models of copper (II) ions adsorption were optimized, created, and developed using the ANN and ANFIS models for tests. The result indicates that the determination coefficient for copper (II) metal ions in the training dataset was 0.987. Additionally, the ANFIS model’s R 2 value for both pollutants was 0.992. The findings demonstrate that the models presented a promising predictive approach that can be applied to successfully and accurately anticipate the simultaneous elimination of copper (II) and dye from the aqueous solution.

ARTIFICIAL NEURAL NETWORKS AND ADAPTIVE NEURO FUZZY INFERENCE SYSTEM FOR WHEAT YIELD ANALYSIS AND PREDICTION

The current study evaluated the prediction of the yield of wheat crops in the Bagalkot district of Karnataka State, India. The study aimed to provide crop yield predictions to help farmers optimize their cultivation and marketing strategies. The model used various independent variables, such as temperature, humidity of air, and water resources, to predict growth in the yield of wheat crops. The correlation analysis helps determine the strength and direction of the relationship between the variables based on the results. The statistical analysis identifies the variables that have a significant impact on crop yield growth. The work developed and tested two different models (the Artificial Neural Network (ANN) model and the Adaptive Neuro-fuzzy Interference System (ANFIS) to predict crop yield growth based on the selected independent variables. The ANFIS model was particularly interesting as it can predict a mapping between the input and output parameters, which can be useful for understanding the relationships between different variables. ANFIS was considered a better predictor than ANN as the error percentage ranged from 0-3%. Overall, the work highlighted the importance of crop yield predictions and the potential benefits that simulations can generate for farmers and the agriculture sector in general.

A Technique for Transformer Remnant Cellulose Life Cycle Prediction Using Adaptive Neuro-Fuzzy Inference System

This article presents an ultramodern modelling algorithm for predicting the remnant cellulose life cycle for oil-submerged power transformers based on the adaptive neuro-fuzzy interference system (ANFIS). The polymer characteristics, degree of polymerization (DP), and 2-furaldehyde (2FAL) of 100 power transformers were measured and collated, which were apportioned into 70 training databanks and 30 as testing datasets. The remnant cellulose life cycle of the transformer was predicted using the proposed ANFIS model characterized by polymer characteristics, DP and 2FAL as inputs. The proposed approach returns 98.23% training and 99.86% testing reliability. The proposed model was applied to 10 transformer case studies in predicting their remnant cellulose life cycle. To corroborate the proposed ANFIS, a comparative study was carried out by employing existing approaches in predicting the remnant life cycle of the case studies, and significant error margins were observed. At large, the results presented in this article certify the dominance of the proposed ANFIS algorithm over compared models. The proposed ANFIS furnishes a pathway to obliterate the constraints of classical techniques in evaluating the transformer DP and remnant cellulose life cycle.

Swelling Prediction in Compacted Soils Using Adaptive Neuro-Fuzzy Inference System

Swelling in compacted soils may lead to some damages to structures and buildings. For the sake of reducing such damages, soil swelling should be determined, so as to make the structures exhibit adequate resistance against such a phenomenon. For most cases, fully non-linear relations have been observed between soil swelling and the parameters contributing to swelling in compacted soil. As such, soil swelling should be determined via either experimentations or prediction models. However, being extremely timely, swelling tests require special expensive equipment. Accordingly, there is a need for models which can use available data to theoretically give swelling estimations of a relatively high accuracy without getting busy with swelling tests and associated issues. Investigated and evaluated in this research are the ability and application of an adaptive neuro-fuzzy interference system (ANFIS) developed by subtractive clustering and fuzzy c-mean clustering to determine and predict swelling in compacted soils. The results along with the obtained values of root mean squared error (RMSE), mean absolute error (MAE) and coefficient of correlation (R) indicated that the proposed ANFIS model succeeded to predict swelling in compacted soils at a good level of accuracy. Therefore, ANFIS models can be used to predict swelling without getting busy with swelling tests and associated issues. KEYWORDS: Swelling of compacted soil, Subtractive clustering, Fuzzy c-mean clustering, ANFIS, Prediction.

Data-Driven Machine Learning Intelligent Tools for Predicting Chromium Removal in an Adsorption System

This study investigates chromium removal onto modified maghemite nanoparticles in batch experiments based on a central composite design. The effect of modified maghemite nanoparticles on the adsorptive removal of chromium was quantitatively elucidated by fitting the experimental data using artificial neural network (ANN) and adaptive neuro-fuzzy interference system (ANFIS) modeling approaches. The ANN and ANFIS models, relating the inputs, i.e., pH, adsorbent dose, and initial chromium concentration to the output, i.e., chromium removal efficiency (RE), were developed by comparing the predicted value with that of the experimental values. The RE of chromium ranged from 49.58% to 92.72% under the influence of varying pH (i.e., 2.6–9.4) and adsorbent dose, i.e., 0.8 g/L to 9.2 g/L. The developed ANN model fits the experimental data exceptionally well with correlation coefficients of 1.000 and 0.997 for training and testing, respectively. In addition, the Pearson’s Chi-square measure (χ2) of 0.0004 and 0.0673 for the ANN and ANFIS models, respectively, indicated the superiority of ANN over ANFIS. However, a small discrepancy in the predictability of the ANFIS model was observed owing to the fuzzy rule-based complexity and overtraining of data. Thus, the developed models can be used for the online prediction of RE onto synthesized maghemite nanoparticles with different sets of input parameters and it can also predict the operational errors in the system.

Deep learning approach to estimate foot pressure distribution in walking with application for a cost-effective insole system

BackgroundFoot pressure distribution can be used as a quantitative parameter for evaluating anatomical deformity of the foot and for diagnosing and treating pathological gait, falling, and pressure sores in diabetes. The objective of this study was to propose a deep learning model that could predict pressure distribution of the whole foot based on information obtained from a small number of pressure sensors in an insole.MethodsTwenty young and twenty older adults walked a straight pathway at a preferred speed with a Pedar-X system in anti-skid socks. A long short-term memory (LSTM) model was used to predict foot pressure distribution. Pressure values of nine major sensors and the remaining 90 sensors in a Pedar-X system were used as input and output for the model, respectively. The performance of the proposed LSTM structure was compared with that of a traditionally used adaptive neuro-fuzzy interference system (ANFIS). A low-cost insole system consisting of a small number of pressure sensors was fabricated. A gait experiment was additionally performed with five young and five older adults, excluding subjects who were used to construct models. The Pedar-X system placed parallelly on top of the insole prototype developed in this study was in anti-skid socks. Sensor values from a low-cost insole prototype were used as input of the LSTM model. The accuracy of the model was evaluated by applying a leave-one-out cross-validation.ResultsCorrelation coefficient and relative root mean square error (RMSE) of the LSTM model were 0.98 (0.92 ~ 0.99) and 7.9 ± 2.3%, respectively, higher than those of the ANFIS model. Additionally, the usefulness of the proposed LSTM model for fabricating a low-cost insole prototype with a small number of sensors was confirmed, showing a correlation coefficient of 0.63 to 0.97 and a relative RMSE of 12.7 ± 7.4%.ConclusionsThis model can be used as an algorithm to develop a low-cost portable smart insole system to monitor age-related physiological and anatomical alterations in foot. This model has the potential to evaluate clinical rehabilitation status of patients with pathological gait, falling, and various foot pathologies when more data of patients with various diseases are accumulated for training.

Adaptive Neuro-Fuzzy Inference System for Modelling the Effect of Slurry Impacts on PLA Material Processed by FDM.

In this research, the effect of water-silica slurry impacts on polylactic acid (PLA) processed by fused deposition modeling (FDM) is examined under different conditions with the assistance of an adaptive neuro-fuzzy interference system (ANFIS). Building orientation, layer thickness, and slurry impact angle are considered as the controllable variables. Weight gain resulting from water, net weight gain, and total weight gain are the predicting variables. Results uncover the accomplishment of the ANFIS model to appropriately appraise slurry erosion in correlation with comparing real data. Both experimental and ANFIS results are almost identical with average percentage error less than 5.45 × 10−6. We observed during the slurry impacts tests that all specimens showed an increase in their weights. This weight gain was finally interpreted to the synergetic effect of water absorption and the solid particles fragmentations immersed within the specimens due to the successive slurry impacts.

Estimation of Viscosity of the N-Alkane (C1-C 4) in Bitumen System Using Adaptive Neuro-Fuzzy Interference System (ANFIS)

One of the important mechanisms in solvent-aided thermal recovery processes is viscosity reduction. Light n-alkane hydrocarbons are among the potential solvents for solvent-aided thermal recovery processes. In this study, the viscosity of C1- C4 n-alkanes in bitumen was investigated. Adaptive neuro-fuzzy interference system (ANFIS) was used for this aim. The result obtained by the ANFIS model analyzed with the statistical parameters (i.e., MSE, MEAE, MAAE, and R2) and graphical methods. Results show that the ANFIS has high capability to the prediction of solvent/bitumen mixture viscosity.

Estimation of cold flow properties of biodiesel using ANFIS-based models

ABSTRACT Biodiesel fuel tends to freeze at higher temperatures when compared with the traditional diesel fuel based on petroleum. Characterization and improvement of its poor cold flow properties (CFP) including cloud point (CP), pour point (PP), and cold filter plugging point (CFPP) have become one of the major challenges among researchers. The aim of the study was to develop a methodology to predict the three CFP of a biodiesel sample based on the fatty acid composition of its feedstock. CP, PP and CFPP prediction models based on Adaptive Neuro-Fuzzy Interference System (ANFIS) were developed. Saturated, monosaturated and polyunsaturated fatty acid contents were used as input variables. Seventy-five data sets including fatty acid contents of feedstocks and CFP of their biodiesels were used during training and verification stages. Biodiesel samples were produced from six different feedstocks either by base-catalyzed transesterification or by supercritical methanol transesterification methods in order to inspect the accuracy of the models. CFP of biodiesel samples were determined following the EN and also ASTM standards. It was noted that the CFP estimated by the ANFIS models were in close agreement with the measured values. The R2 values were found as 0.981, 0.985, and 0.981 for CP, PP, and CFPP, whereas the prediction performances of the models in terms of RSME were 1.066, 1.160, and 1.061, respectively. It was noteworthy that the present ANFIS models provided closer estimations than those models reported previously.

A novel ANFIS model to prediction of the density of n-alkane in different operational condition

The density has an important role in the oil and gas industries calculation. In this study, an adaptive neuro-fuzzy interference system (ANFIS) model was employed to predict the density of n-alkane. The result obtained by the ANFIS model analyzed with the statistical parameters (i.e., MSE, RMSE, and R2) and graphical method. According to the result obtained the ANFIS has the highest accuracy with R2 = 0.999, MSE = 0.1438, and RMSE = 0.3792.

Predicting performance of SiO2 nanoparticles on filtration volume using reliable approaches: application in water-based drilling fluids

ABSTRACT Designing the drilling fluid is crucial in order to make a thin and impermeable filter cake on the wellbore that minimizes the drilling fluid filtration volume. Artificial Neural Network (ANN), Adaptive Neuro-Fuzzy Interference System (ANFIS), and Least Square Support Vector Machine (LSSVM) modeling are used to predict the drilling fluid filtration volume as a function of drilling fluid properties, SiO2 nanoparticles, and KCl salt concentration. The performance of the proposed models is evaluated using statistical parameters including Average Absolute Relative Error (AARE), Mean Square Error (MSE), and Correlation Coefficient (R2). The results show that the models could predict the filtration volume well and are in agreement with the actual measured values. The proposed ANN, ANFIS, and LSSVM models could predict the filtration volume with R2 values of 0.9926, 0.9900, and 0.9940, respectively. This indicates that the presented models are accurate enough for predicting the nanoparticles performance on filtration volume of water-based drilling fluid.

Estimation of maximum scour depth downstream of an apron under submerged wall jets

AbstractAn analysis of laboratory experimental data pertaining to local scour downstream of a rigid apron developed under wall jets is presented. The existing equations for the prediction of the maximum scour depth under wall jets are applied to the available data to evaluate their performance and bring forth their limitations. A comparison of measured scour depth with that computed by the existing equations shows that most of the existing empirical equations perform poorly. Artificial neural network (ANN)- and adaptive neuro-fuzzy interference system (ANFIS)-based models are developed using the available data, which provide simple and accurate tools for the estimation of the maximum scour depth. The key parameters that affect the maximum scour depth are densimetric Froude number, apron length, tailwater level, and median sediment size. Results obtained from ANN and ANFIS models are compared with those of empirical and regression equations by means of statistical parameters. The performance of ANN (RMSE = 0.052) and ANFIS (RMSE = 0.066) models is more satisfactory than that of empirical and regression equations.

A new adaptive neuro-fuzzy solution for optimization of the parameters in the digital holography setup

In this paper, a fuzzy interference and an adaptive neuro-fuzzy interference system models have been presented in order to accelerate designing of the digital holographic setup without experiment. The setting parameters of experimental holographic setup, which affect the quality of images obtained from reconstructed holograms, are predicted digitally by proposed models before the recording process. Hence, we reduce the required time for designing of digital holographic setup with optimization process. The adaptive neuro-fuzzy interference system model for the optimization of the digital holographic setup is first attempt in the literature. The accuracy of the proposed models is examined by comparing the presented models and actual calculated experimental root-mean-square values. As a result, the accuracy of the adaptive neuro-fuzzy interference system shows the better performance than the fuzzy interference system. Moreover, the design of experimental setup can be occurred numerically in a short time by using adaptive neuro-fuzzy interference system models.

Application of ANFIS strategy for prediction of biodiesel production using supercritical methanol

ABSTRACTResearch for finding alternative fuel sources has been concluded that the renewable fuels such as biodiesel can be used as an alternative to fossil fuels because of the energy security reasons and environmental benefits. In the present study, a modeling study based on statistical learning theory has been investigated by the adaptive neuro-fuzzy interference system (ANFIS) approach for biodiesel production in non-catalytic supercritical methanol (SCM) method. This model has been applied for estimating the biodiesel yield as a function of temperature, pressure, reaction time, and Methanol/oil ratio. The results, the high value of R-squared (0.9978) and low value of absolute deviation (1.14%), support the suggested ANFIS model for being an effective approach for prediction of the biodiesel yield. A comparison between our model and another previous ANN-based model has been also carried out that indicates a great agreement of estimations of both models.

Modeling and optimization of biogas production from cow manure and maize straw using an adaptive neuro-fuzzy inference system

This study was focused on the prediction and optimization of biogas production from cow manure with maize straw under various total solid content (TS), Carbon to Nitrogen (C/N) ratio and stirring intensity. This research used full-scale (1200 L) batch reactor under mesophilic condition. An adaptive neuro-fuzzy interference system (ANFIS) was utilized to predict and optimize biogas production from anaerobic digestion. C/N ratio, TS and stirring intensity of substrates, each of them in three levels, were considered as input variables and biogas production was regarded as the output variable of the model. The coefficient of determination (R2) between observed and predicted biogas production values was 0.99 which showed good match and accuracy of the model. Highest biogas production was achieved from C/N ratio 26.76, TS 9% and moderate stirring. Biogas production increased about 8% with optimal conditions suggested by the ANFIS model.

Controlling of Proton Exchange Membrane Fuel Cell by Model Predictive Controller Based on ANFIS Model

AbstractProton exchange fuel cell is one of the most promising new technologies in electrical energy production. Due to slow dynamic, nonlinearity and dependency of time changing variables of proton exchange membrane fuel cell (PEMFC), its control issue is a challenging problem. In this paper, model predictive controller (MPC) based on the adaptive neuro‐fuzzy interface model of the PEMFC is proposed to control the output voltage. First the adaptive neuro‐fuzzy interference system (ANFIS) model is identified to approximate the dynamic behavior of the PEMFC system with a set of data which are taken from a physical model of a 5 kW PEMFC setup plant. Then the branch‐and‐bound method and the greedy algorithm are used to solve the constrained optimization function of the predictive control problem. The results reveal that the ANFIS model can effectively approximate the dynamic behavior of the PEMFC and the predictive controller based on this model can successfully control the output and satisfy the constraints.

Prediction carbon dioxide solubility in presence of various ionic liquids using computational intelligence approaches

Ionic liquids (ILs) are highly promising for industrial applications such as design and development of gas sweetening processes. For a safe and economical design, prediction of carbon dioxide solubility by a trustworthy model is really essential. In this research, based on the pressure and temperature of system and the critical properties such as critical temperature (Tc) and critical pressure (Pc) and also acentric factor (ω) and molecular weight (Mw) of pure ionic liquids, a multi-layer perceptron artificial neural network (MLP-ANN) and an adaptive neuro-fuzzy interference system (ANFIS) have been developed to estimate carbon dioxide solubility in presence of various ILs over wide ranges of pressure, temperature and concentration. To this end, 728 experimental data points collected from the literature have been used for implementation of these models. To verify the proposed models, regression analysis has been conducted on the experimental and predicted solubility of carbon dioxide in ILs. Moreover, in this study, a comparison between experimental carbon dioxide solubilities and predicted values of carbon dioxide solubility by thermodynamic models based on Peng–Robinson (PR) and Soave–Redlich–Kwong (SRK) equation of states has been performed. For MLP-ANN, coefficient of determination (R2) between experimental and predicted values is 0.9972 and mean squared errors (MSEs) is 0.000133 and the values of R2=0.9336 and MSE=0.002942 were obtained for ANFIS model while, the values of R2 and MSE for PR-EOS were 0.7323 and 0.002702 respectively, and also, R2=0.6989 and MSE=0.005578 were obtained for SRK-EOS model. Therefore, in current study, ability and better performance of MLP-ANN as an accurate correlation for estimating carbon dioxide solubility in ILs was showed against other alternative models.

Application of adaptive neuro-fuzzy interference system models for prediction of forest fires in the usa on the basis of solar activity

In this research we search for a functional dependence between the occurrence of forest fires in the USA and the factors which characterize the solar activity. For this purpose we used several methods (R/S analysis, Hurst index) to establish potential links between the influx of some parameters from the sun and the occurrence of forest fires with lag of several days. We found evidence for a connection and developed a prognostic scenario based on the Adaptive neuro-fuzzy interference system (ANFIS) technique. This scenario allows the prediction between 79-93% of forest fires.

Wind turbine condition monitoring based on SCADA data using normal behavior models. Part 2: Application examples

This paper is part two of a two part series. The originality of part one was the proposal of a novelty approach for wind turbine supervisory control and data acquisition (SCADA) data mining for condition monitoring purposes. The novelty concerned the usage of adaptive neuro-fuzzy interference system (ANFIS) models in this context and the application of a proposed procedure to a wide range of different SCADA signals. The applicability of the set up ANFIS models for anomaly detection was proven by the achieved performance of the models. In combination with the fuzzy interference system (FIS) proposed the prediction errors provide information about the condition of the monitored components.Part two presents application examples illustrating the efficiency of the proposed method. The work is based on continuously measured wind turbine SCADA data from 18 modern type pitch regulated wind turbines of the 2 MW class covering a period of 35 months. Several real life faults and issues in this data are analyzed and evaluated by the condition monitoring system (CMS) and the results presented. It is shown that SCADA data contain crucial information for wind turbine operators worth extracting. Using full signal reconstruction (FSRC) adaptive neuro-fuzzy interference system (ANFIS) normal behavior models (NBM) in combination with fuzzy logic (FL) a setup is developed for data mining of this information. A high degree of automation can be achieved. It is shown that FL rules established with a fault at one turbine can be applied to diagnose similar faults at other turbines automatically via the CMS proposed. A further focus in this paper lies in the process of rule optimization and adoption, allowing the expert to implement the gained knowledge in fault analysis. The fault types diagnosed here are: (1) a hydraulic oil leakage; (2) cooling system filter obstructions; (3) converter fan malfunctions; (4) anemometer offsets and (5) turbine controller malfunctions. Moreover, the graphical user interface (GUI) developed to access, analyze and visualize the data and results is presented.