Adaptive Neuro-fuzzy Inference System Technique Research Articles

Multi-response optimization of FSW parameters for Al–Mg–Zn alloys using Box–Behnken design and gray relational analysis and comparative study with ANFIS technique

In this study, cast Al–Mg–Zn and aging Al–Mg–Zn alloys were joined using the friction stir welding technique, with the welding parameters being the rotational speed of the tool, welding speed, tilt angle, and D/d ratio. The effects of these input parameters on output responses such as ultimate tensile strength, elongation percentage, hardness, and wear rate were investigated using Box–Behnken experimental design. Multi-response optimization was performed using the Box–Behnken Design (BBD) combined with Gray Relational Analysis (GRA). A rotational speed of 1200 rpm, welding speed of 100 mm/min, tilt angle of 1.5°, and D/d ratio of 2.25 were found to significantly enhance the mechanical properties and wear resistance. Furthermore, the Adaptive Neuro-Fuzzy Inference System (ANFIS) model was developed to predict outcomes based on the gray relational coefficient grades, leveraging its architecture to improve prediction accuracy. Finally, a comparative analysis was conducted between the BBD-GRA methods and the ANFIS technique. Results indicated that the ANFIS model was highly effective for predicting output parameters, achieving superior precision and accuracy with fewer iterative calculations. By selecting an appropriate ANFIS structure, the model’s performance is better than that of the BBD-GRA method.

Predicting chlorophyll-a dynamics in the Ashtamudi estuary using ANN and ANFIS techniques

Excessive nutrients and associated high chlorophyll-a concentration are of growing concern to the public health due to the occurrence of eutrophication in aquatic bodies. Continuous monitoring of chlorophyll-a has limitations, thereby necessitating the development of prediction models. Even though chlorophyll-a prediction models are numerous, they rarely fit into estuarine conditions, which is encountered with dynamic mixing of freshwater and sea water. Thus, the present study identifies the most appropriate driving factors that are relevant for estuarine conditions through chlorophyll-a prediction models developed using Artificial Neural Network and Adaptive Neuro Fuzzy Inference System (ANFIS) approaches in the Ashtamudi estuary, India. Salinity, which is an indirect measure of the estuarine mixing intensity, has been used to replicate the dynamic mixing in the estuary. The results indicate that the model incorporating salinity along with total nitrogen, total phosphorous and turbidity well-predicted chlorophyll-a concentration with a coefficient of determination ranging from 0.73 to 0.99. General Regression Neural Network (GRNN) and ANFIS models outperformed Back Propagation Neural Network (BPNN) and Recurrent Neural Network (RNN) models. Of the various ANFIS models, the ones that used Gaussian and Generalized Bell membership functions were most appropriate for the prediction of chlorophyll-a than the models with triangular and trapezoidal membership functions. The study identified that the models that considered salinity were less sensitive and can be used for modelling chlorophyll-a. The chlorophyll-a was observed to have a direct influence of salinity at salinity values greater than 5‰. The study highlighted that estuarine mixing further enhances the primary productivity through increased penetration of light leading to higher chlorophyll-a concentration. Further the study emplasized that the predictive models are important tools fitting well within estuarine environments due to its replicability.

From experimentation to prediction: comprehensive study of dielectric properties through experimental research and theoretical modeling

This study discusses the experimental findings on the frequency & temperature influences on the dielectric (constant (ε1) and loss (ε2)) of some chalcogenide materials based on Se83Bi17 composition performed in the temperature range 303 K–393 K and frequency range (100–1000000 Hz). As the frequency increases, multiple polarization mechanisms contribute to the reduction of the dielectric constant. The addition of germanium (Ge) to a composition increases ε1 more than tellurium (Te). The dielectric loss decreases with frequency while increasing with temperature and AC conductivity. Understanding these behaviors is important for material characterization and applications in fields like electronics and solar cells. The theoretical section introduces adaptive neuro-fuzzy inference systems (ANFIS), which are utilized in the estimation of the dielectric characteristics of Se83Bi17 (SB), Se83Bi17Te5 (SB-T), and Se83Bi17Ge5 (SB-G). Experimentation-related data are a source of input. ANFIS model of the Takagi–Sugeno type has been trained. With MATLAB, the most effective networks are created. The outcomes of the ANFIS modeling are exceptional. The accuracy of the modeling process is due to the error values. This study demonstrates that the ANFIS technique can accurately anticipate the dielectric properties of the compositions under consideration when they are formed into thin films. The ANFIS can describe the experimental data of the dielectric (constant (ε1) and loss (ε2)) of some chalcogenide materials for all the mentioned temperatures and frequencies. This leads to using the ANFIS model to produce the dielectric (constant (ε1) and loss (ε2)) of some chalcogenide materials for various temperatures and frequencies which there are no experimental data yet to compare with.

Controlling the effectiveness of STATCOM using ANFIS based on PI controller

This research achieves two goals, the first is the modelling of the static synchronous compensator (STATCOM) and design of the control circuits for current, voltage and d.c capacitor voltage (Vd.c) to improve the power factor (PF) by preparing the reactive power by STATCOM so that its work is similar to the work of a synchronous condenser, and the second goal is to use smart techniques to control the Vd.c loop. For comparison, smart technical methods such as fuzzy logic type 1 (FL-T1), fuzzy logic type 2 (FL-T2), and adaptive neuro fuzzy inference system (ANFIS) were used to regulate the Vd.c on the capacitor instead of the traditional controller proportional integral (PI). Simulation was performed in MATLAB 2021 to determine the efficiency of the suggested method or approach controllers for STATCOM. The use of the proposed method improves the signal value of both the current and the voltage and the phase difference between them, which reaches almost zero. Proved that an ANFIS technique provides best Vd.c response in different values of balance and unbalance load compared with the other methods by obtaining the minimum peak overshoot (P-ov) and minimum settling time (ST).

Comparison of Wavelet Artificial Neural Network, Wavelet Support Vector Machine, and Adaptive Neuro-Fuzzy Inference System Methods in Estimating Total Solar Radiation in Iraq

Estimating the amount of solar radiation is very important in evaluating the amount of energy that can be received from the sun for the construction of solar power plants. Using machine learning tools to estimate solar energy can be a helpful method. With a high number of sunny days, Iraq has a high potential for using solar energy. This study used the Wavelet Artificial Neural Network (WANN), Wavelet Support Vector Machine (WSVM), and Adaptive Neuro-Fuzzy Inference System (ANFIS) techniques to estimate solar energy at Wasit and Dhi Qar stations in Iraq. RMSE, EMA, R2, and IA criteria were used to evaluate the performance of the techniques and compare the results with the actual measured value. The results showed that the WANN and WSVM methods had similar results in solar energy modeling. However, the results of the WANN technique were slightly better than the WSVM technique. In Wasit and Dhi Qar stations, the value of R2 for the WANN and WSVM methods was 0.89 and 0.86, respectively. The value of R2 in the WANN and WSVM methods in Wasit and Dhi Qar stations was 0.88 and 0.87, respectively. The ANFIS technique also obtained acceptable results. However, compared to the other two techniques, the ANFIS results were lower, and the R2 value was 0.84 and 0.83 in Wasit and Dhi Qar stations, respectively.

Cancer Regions in Mammogram Images Using ANFIS Classifier Based Probability Histogram Segmentation Algorithm

Every year, the number of women affected by breast tumors is increasing worldwide. Hence, detecting and segmenting the cancer regions in mammogram images is important to prevent death in women patients due to breast cancer. The conventional methods obtained low sensitivity and specificity with cancer region segmentation accuracy. The high-resolution standard mammogram images were supported by conventional methods as one of the main drawbacks. The conventional methods mostly segmented the cancer regions in mammogram images concerning their exterior pixel boundaries. These drawbacks are resolved by the proposed cancer region detection methods stated in this paper. The mammogram images are classified into normal, benign, and malignant types using the Adaptive Neuro-Fuzzy Inference System (ANFIS) approach in this paper. This mammogram classification process consists of a noise filtering module, spatial-frequency transformation module, feature computation module, and classification module. The Gaussian Filtering Algorithm (GFA) is used as the pixel smooth filtering method and the Ridgelet transform is used as the spatial-frequency transformation module. The statistical Ridgelet feature metrics are computed from the transformed coefficients and these values are classified by the ANFIS technique in this paper. Finally, Probability Histogram Segmentation Algorithm (PHSA) is proposed in this work to compute and segment the tumor pixels in the abnormal mammogram images. This proposed breast cancer detection approach is evaluated on the mammogram images in MIAS and DDSM datasets. From the extensive analysis of the proposed tumor detection methods stated in this work with other works, the proposed work significantly achieves a higher performance. The methodologies proposed in this paper can be used in breast cancer detection hospitals to assist the breast surgeon to detect and segment the cancer regions.

Change in Normal Health Condition Due to COVID-19 Infection: Analysis by ANFIS Technique.

The COVID-19 pandemic has crippled the world population. Our present work aims to formulate a model to analyze the change in normal health conditions due to COVID-19 infection. For this purpose, we have collected data of seven parameters, namely, age, systolic pressure (SP), diastolic paper (DP), respiratory distress (RD), fasting blood sugar (FBS), cholesterol (CHL), and insomnia (INS) of 156 persons of Birnagar municipality, Nadia, India; before and after COVID-19 infection. Ultimately, using an adaptive neuro-fuzzy inference system (ANFIS), we have formulated our desired model, a Takagi–Sugeno fuzzy inference system. Further, with the help of this model, we have established one’s change in health condition with age due to COVID-19 infection. Finally, we have derived that older people are more affected by COVID-19 infection than younger people.

Efficient Neuro-Fuzzy Identification Model for Electrocardiogram Signal

This paper addresses the performance of the Artificial Neural Networks (ANNs), Fuzzy inference systems (FISs) and Adaptive Neuro-Fuzzy Inference System (ANFIS) for the identification of some nonlinear systems with certain degree of uncertainty. The efficiency of the suggested methods in modeling and identification the responses were analyzed and compared. The Back-propagation algorithm and Takagi-Sugeno (TS) approach are used to train the ANNs, FISs and ANFIS, respectively. In this study we will show how ANFIS can be put in order to form nets that able to train from external data and information compared to ANNs and FISs. In order, it is proposed forms of inputs that can be used along with ANNs, FISs and ANFIS to modeling nonlinear systems. Two nonlinear systems with an electrocardiogram (ECG) signal in the form of simulation and complexity were used to test the identification of the structure presented. Because ANFIS has an inherent capacity to approximate unknown functions and to adjust the changes in inputs and parameters, it can be used to identify the proposed systems with a very high level of complexity. The results show that the ANFIS technique can provide the most ideal approximation when the right structures are employed.

Prediction of coal wettability using machine learning for the application of CO2 sequestration

Carbon capture, utilization, and storage (CCUS) is an essential greenhouse gas-reducing technology that can be employed throughout the energy system. Carbon dioxide (CO2) sequestration in underground stratas is one of the effecient ways of reducing carbon emissions. CO2 sequestration in coal formations can be used to improve the methane recovery from coal formations (ECBM). The efficiency of this process highly depend on the wettability of the coal in contact with CO2. Different experimental methods including contact angle (CA) measurments can be used to estimate the wettability. However, the experimental techniques are expensive, incosistant, and time-consuming. Therefore, this study introduces the application of artificial neural network (ANN) and adaptive neuro-fuzzy inference system (ANFIS) to estimate the CA in coal–water–CO2 system. ANN and ANFIS techniques were built using 250 point dataset to calculate the contact angle of coal formation. The input parameters were the coal properties, operating pressure, and temperature. 70% of the data set was used to train the model, while 30% of the data was used for the testing process. The models were then validated with a set of unseen data. The results showed that ANN and ANFIS models accurately predicted the contact angle in the coal–water–CO2 system as a function of coal properties and the operating conditions. The correlation coefficient (R) and the average absolute percent error (AAPE) between the actual and estimated contact angle were used as indicators for the model performance. ANN and ANFIS models predicted the contact angle with R values higher than 0.96 for the different datasets. AAPE was less than 7% in both models for the training and testing datasets. An empirical equation was built using the weight and biases from the developed ANN model. The new equation was validated with the unseen data set and the R-value was found to be higher than 0.96 with an AAPE less than 6%.these results confirm the reliability of the proposed models to get the contact angle in the coal formation without laboratory work or complex calculations. These models can be used to screen the coal formation targets for carbon storage.

Whale Optimization Algorithm-Based LQG-Adaptive Neuro-Fuzzy Control for Seismic Vibration Mitigation with MR Dampers

Design of effective control strategies to protect structural buildings from seismic hazards is gaining increasing attention. In this paper, an intelligent semiactive control strategy, which combines linear-quadratic-Gaussian (LQG), whale optimization algorithm (WOA), and adaptive neuro-fuzzy inference system (ANFIS) strategy is designed to mitigate structural vibration by using magnetorheological (MR) dampers, here known as WLQG-ANFIS control. Firstly, considering that the performance of the LQG control for the structures under seismic excitations strongly depends on skill and experience of the experts in determining the weighting matrix of the feedback gain, a WOA with constraints is adopted to optimally design the LQG control due to the strong ability to avoid local optima. Secondly, the inverse dynamic model of the MR damper is developed with the ANFIS technique which combines the fuzzy system and artificial neural network. Finally, according to the active force estimated by the proposed LQG control, the developed inverse model is utilized to calculate the MR damper command signal. Numerical analyses are conducted for a 10-story structural building installed with MR dampers under earthquake excitation. Through a test called analysis of variance in optimizing the LQG control, the superiority of WOA over other three meta-heuristic algorithms, i.e. GA, DE, and ABC, in terms of convergence performance and robustness is validated. The proposed WLQG-ANFIS control can reduce the maximum displacement, interstory drift and acceleration responses by 64%, 65%, and 53%, respectively, which can achieve better overall performance than on-off control, LQG-ANFIS control, fuzzy control, and H∞-ANFIS control. Moreover, this control strategy exhibits the ability to handle the uncertainties in structural parameters as well as seismic excitations.

Using an Adaptive Neuro-Fuzzy Inference System to Predict Dilution Characteristics of Vertical Buoyant Jets Subjected to Lateral Confinement

In order to predict the dilution characteristics of vertical buoyant jets constrained by lateral obstructions, we propose a new method based on a commonly used machine learning algorithm: the adaptive neuro-fuzzy inference system (ANFIS). By using experimental data to train and test the ANFIS model, this study shows that it had better performance than commonly used empirical equations for laterally confined jets and another artificial intelligence technique—genetic programming. The RMSE values of the ANFIS-based model were lower, and the R2 values were higher, compared with those of the empirical equation and genetic programming models. The reduction in RMSE achieved by using ANFIS to replace the empirical equations or genetic programming algorithm exceeded 20%. This research confirms that the ANFIS technique has real potential in the development of effective and accurate models that can be used to estimate the dilution characteristics of a vertical buoyant jet subjected to lateral confinement, providing a new avenue for the prediction of dilution characteristics using artificial intelligence techniques, which can also be utilized for other effluent mixing problems in marine systems.

An alternative approach for measuring the mechanical properties of hybrid concrete through image processing and machine learning

Image processing (IP), artificial neural network (ANN), and adaptive neuro-fuzzy inference system (ANFIS) are innovative techniques in computer science that have been widely used to predict the properties of materials in structural engineering. The stability of reinforced concrete structures mainly depends on the mechanical properties of concrete, i.e., its compressive strength fc and tensile strength ft. Different kinds of inexpensive cement replacement materials (CRM) can be used to form hybrid concrete (HC) with enhanced mechanical and other properties. In this study, the IP, ANN, and ANFIS methods are properly combined and used to predict the mechanical properties of hybrid concrete. For this, 162 cylindrical specimens of HC with 0%, 15%, and 25% silica fume and fly ash as replacement material with three mix ratios, 1:3:6, 1:2:4, and 1:1.5:3 were cast at 14 days and 28 days curing. The specimens were divided into three equal sets as follows: (i) the first to find the compressive strength, (ii) the second to find the split cylinder strength, and (iii) the third to develop a database of images. For the image acquisition, each cylinder of the third set is cut into three slices using a stone cutting saw, resulting in six faces and a total of 324 images (6 × 54). Photos (digital images) are then taken in fully controlled lighting conditions from a height of 600 mm between the concrete surface and the camera lens. The acquired images are pre-processed (converted to grayscale, cropped, and resized to 256 × 256 pixels), and the statistical features are extracted to predict the fc and ft by using ANN and ANFIS techniques. Finally, the predicted values are tested and validated through nondestructive testing methods. The actual values of the compressive and the tensile strength of concrete were compared to the corresponding values estimated by the proposed methods, i.e. (IP, ANN) and (IP, ANFIS). The accuracy of the results largely depends on the data set. The accuracy obtained by IP/ANN is 99.7% while the one obtained with IP/ANFIS is 97.8%.

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.

An investigation of Grid-Integrated Photovoltaic system intended for hybrid Moth Flame Optimization using ANFIS techniques

As the move towards Grid Integrated-Photovoltaic (GI-PV) system is proposed to improve the power quality development. A novel Adaptive Neuro-Fuzzy Inference System (ANFIS) based on improved Moth Flame Optimization (MFO) algorithm is described for grid integrated approach. The solar integration of Maximum Power Point (MPP) fed into modified Switched Boost Inverter (SBI) is presented, this GI-PV connected circuit has become prominent research in a recent scenario for energy demand. Proposed MFOA-ANFIS controller has generated the duty cycle pulses to each converter circuit. The benefit of grid-tied SBI is direct control outer-loop employed to obtain MFO-ANFIS techniques. To maintain a constant voltage DC-link is employed for inner-loop, this presence of constant DC-power to grid loads with support of MFO-ANFIS assists Proportional Integral Differential (PID) method. The results acquired by the simulation expressed that the proposed controller is addressed to maintain active and reactive power exchange, regulate DC bus-link voltages, grid voltage, and grid current. The effectiveness of the practical implication research is achieved by the output as represented as minimum grid harmonics, load current, and compensator current as verified in MATLAB/Simulink platform.

Prognosis of forest production using machine learning techniques

Forest production and growth are obtained from statistical models that allow the generation of information at the tree or forest stand level. Although the use of regression models is common in forest measurement, there is a constant search for estimation procedures that provide greater accuracy. Recently, machine learning techniques have been used with satisfactory performance in measuring forests. However, methods such as Adaptive Neuro-Fuzzy Inference System (ANFIS) and Random Forest are relatively poorly studied for predicting the volume of wood in eucalyptus plantations in Brazil. Therefore, it is essential to check whether these techniques can provide gains in terms of accuracy. Thus, this study aimed to evaluate the use of Random Forest and ANFIS techniques in the prognosis of forest production. The data used come from continuous forest inventories carried out in stands of eucalyptus clones. The data were divided into 70% for training and 30% for validation. The algorithms used to generate rules in ANFIS were Subtractive Clustering and Fuzzy-C-Means. Besides, training was done with the hybrid algorithm (descending gradient and least squares) with the number of seasons ranging from 1 to 20. Several RFs were trained, varying the number of trees from 50 to 850 and the number of observations by five leaves to 35. Artificial neural networks and decision trees were also trained to compare the feasibility of the techniques. The evaluation of the estimates generated by the techniques for training and validation was calculated based on the following statistics: correlation coefficient (r), relative Bias (RB), and the relative root mean square error (RRMSE) in percentage. In general, the techniques studied in this work showed excellent performance for the training and validation data set with RRMSE values <6%, RB < 0.5%, and r > 0.98. The RF presented inferior statistics about the ANFIS for the prognosis of forest production. The Subtractive Clustering (SC) and Fuzzy-C-Means (FCM) algorithms provide accurate baseline and volume projection estimates; both techniques are good alternatives for selecting variables used in modeling forest production.

Experimental and theoretical study of the conduction mechanism and dielectric behavior of quaternary defect chalcopyrite CdInGaSe4 using adaptive neuro-fuzzy inference system (ANFIS) model

The first part is an experimental study of Ac. conduction and dielectric behavior of CdInGaSe4 defect chalcopyrite. CdInGaSe4 thin films were obtained by the thermal evaporation method. Measurements were investigated at temperatures (292.9–393.4 K), thicknesses (71–198 nm) and frequencies (100–1 MHz). The ac. conductivity σac.(ω) is temperature dependent and discussed by the correlated barrier hopping model CBH. Values of dielectric constant ε1(ω) and loss ε2(ω) are increased by temperature and decreased by frequency. The second part introduces estimation of ac conductivity and dielectric properties of CdInGaSe4 using adaptive neuro-fuzzy inference systems (ANFIS). Experimental data is used as inputs. Takagi-Sugeno type of ANFIS model is trained. The optimal networks are accomplished using MATLAB. ANFIS modeling outputs provide excellent results. Error values support the success of the modeling process. According to this research, the ANFIS technique is considered a successful tool to predict ac. conductivity and dielectric properties of CdInGaSe4.

Modelling response of infiltration loss toward water table depth using RBFN, RNN, ANFIS techniques

Accurate prediction of water table depth over long-term in arid agricultural areas are very much important for maintaining environmental sustainability. Because of intricate and diverse hydrogeological features, boundary conditions, and human activities researchers face enormous difficulties for predicting water table depth. A virtual study on forecast of water table depth using various neural networks is employed in this paper. Hybrid neural network approach like Adaptive Neuro Fuzzy Inference System (ANFIS), Recurrent Neural Network (RNN), Radial Basis Function Neural Network (RBFN) is employed here to appraisal water levels as a function of average temperature, precipitation, humidity, evapotranspiration and infiltration loss data. Coefficient of determination (R2), Root mean square error (RMSE), and Mean square error (MSE) are used to evaluate performance of model development. While ANFIS algorithm is used, Gbell function gives best value of performance for model development. Whole outcomes establish that, ANFIS accomplishes finest as related to RNN and RBFN for predicting water table depth in watershed.

Investigations on the relationship among the porosity, permeability and pore throat size of transition zone samples in carbonate reservoirs using multiple regression analysis, artificial neural network and adaptive neuro-fuzzy interface system

Finding an accurate method for estimating permeability aside from well logs has been a difficult task for many years. The most commonly used methods targeted towards regression technique to understand the correlation between pore throat radii, porosity and permeability are Winland and Pittman equation approaches. While these methods are very common among petrophysicists, they do not give a good prediction in certain cases. Consequently, this paper investigates the relationship among porosity, permeability, and pore throat radii using three methods such as multiple regression analysis, artificial neural network (ANN), and adaptive neuro-fuzzy inference system (ANFIS) for application in transition zone permeability modeling. Firstly, a comprehensive mercury injection capillary pressure (MICP) test was conducted using 228 transition zone carbonate core samples from a field located in the Middle-East region. Multiple regression analysis was later performed to estimate the permeability using pore throat and porosity measurement. For the ANN, a two-layer feed-forward neural network with sigmoid hidden neurons and a linear output neuron was used. The technique involves training, validation, and testing of input/output data. However, for the ANFIS method, a hybrid optimization consisting of least-square and backpropagation gradient descent methods with a subtractive clustering technique was used. The ANFIS combines both the artificial neural network and fuzzy logic inference system (FIS) for the training, validation, and testing of input/output data. The results show that the best correlation for the multiple regression technique is achieved for pore throat radii with 35% mercury saturation (R35). However, for both the ANN and ANFIS techniques, pore throat radii with 55% mercury saturation (R55) gives the best result. Both the ANN and ANFIS are later found to be more effective and efficient and thus recommended as compared with the multiple regression technique commonly used in the industry.

Prediction of flow field in a solar chimney using ANFIS technique

Solar chimneys have been intensively studied as an effective method for natural ventilation of buildings. Though numerical methods, such as Computational Fluid Dynamics (CFD), have been widely utilized in such studies, they usually require extensive computational resources. Moreover, experimental study is quite complicated and costly. In recent years, machine learning has started to be used as a tool in the thermal-fluid field. In this study, in order to save time and cost, Adaptive Neuro-Fuzzy Inference System (ANFIS) technique, a class of adaptive networks that incorporate both neural networks and fuzzy logic principles, is combined with CFD. A simulation model was first validated by experiment from another study in the field. The result was documented as a dataset using CFD code ANSYS Fluent (Academic version 2020 R2). Then, they are used to train and validate the ANFIS model. In particular, the study is to predict the fluid flow field in a 2-dimensional typical solar chimney when heat flux changes in the range of 400 to 1000 W/m2. Inputs of the ANFIS model are position and heat flux, while outputs are temperature and velocity at that location. As a result, the 2 ANFIS models could achieve R2 values of 0.997, 0.97 (training set) and 0.994, 0.9715 (testing set); RMSE are 1.009, 0.00224 (training set) and 1.074, 0.0204 (testing set) for outputs of temperature and velocity, respectively. Those results are acceptable. By using the ANFIS model, large amounts of flow fields with different scenarios can be estimated simultaneously. Therefore, it is expected that engineers and architects can have a quick tool in the process of design.

Using ANFIS technique in prediction of reverse flow in a solar chimney

In solar chimney, in order to save resources in Computational Fluid Dynamics (CFD), this study aims to combine Adaptive Neuro-Fuzzy Inference System (ANFIS) to predict reverse flow and investigate the ventilation performance. The inputs to the model are heat flux in the range of 200-1000W/m2, gap of 0.04-0.25m and height of 1-1.4m, while outputs are penetration depth and mass flow rate. The results of R2 and RMSE are reasonable for training and testing data, hence the ANFIS model is validated.