Number Of Membership Functions Research Articles

FUZZY MAXIMUM POWER POINT TRACKING CONTROLLERS FOR PHOTOVOLTAIC SYSTEMS: A COMPARATIVE ANALYSIS

The design of an effective fuzzy maximum power point tracking controller plays a crucial aspect in enhancing the photovoltaic system’s efficiency. This article aims to design and compare the performance of symmetric and asymmetric types of fuzzy controllers’ maximum power point tracking algorithms. Depending on the BP SX150S module’ power-voltage attributes at standard technical conditions, the input membership function parameters are derived. Moreover, the effect of fuzzy memberships’ quantity is also examined in this article. Where Five and seven triangular memberships are used. For the simulation, MATLAB is used to assess the effectiveness of the fuzzy controllers. Simulation results show that the asymmetric controller outperforms the symmetric type in terms of transient and steady-state tracking for different numbers of membership functions. Specifically, when employed with 5-triangle memberships, the asymmetric controller outperforms the symmetrical controller in terms of rise time, tracking precision, and energy output, respectively, by 83%, 0.06%, and 14.14%. While, the rise time, tracking precision, and energy yield of 7-triangle memberships are all improved by 86.7%, 0.04%, and 14.78%, respectively. Using asymmetric type, 7-triangle memberships enhance the rise time and harvested energy by around 18.2% and 0.082%, respectively. Overall, the most effective tracking technique for enhancing the photovoltaic system’s efficiency is the asymmetric type, independent of the quantity of memberships.

The Effect of Varying Artificial Neural Network and Adaptive Neuro-Fuzzy Inference System Parameters on Wind Energy Prediction: A Comparative Study

Owing to the development of technology, the majority of nations throughout the world now rely on fossil fuels and nuclear power plants to meet their energy needs. However, as academic research on this subject has shown, it has become clear that alternative energy uses are necessary due to the gradual depletion of these fuels and their significant negative effects on the environment. In order to ensure energy diversity and end the energy shortage, the development of renewable energy sources is crucial. The prediction of wind power is crucial for effectively utilizing the potential of wind energy. In this study, an adaptive neuro-fuzzy inference system (ANFIS) and an artificial neural network (ANN) have been developed for the prediction of wind power. In this study, data sets were created by taking the daily average wind speeds of the selected wind turbine, the daily average power values it produces, and the daily average wind speed values in the Velimese region. By creating single-hidden layer and multi-hidden layer ANN models, the network was trained multiple times with different activation functions and different numbers of neurons, and wind power prediction was performed. In the ANFIS model, the number of membership functions is kept constant, and wind power prediction is performed using different membership functions. With these ANFIS and ANN models developed with different parameter combinations, it is aimed to determine the most efficient model by performing daily average wind power prediction. Parameter combinations were tested to determine the appropriate models, and as a result, the ANN and ANFIS models were compared with each other.

Hybrid ANFIS-PSO algorithm for estimation of the characteristics of porous vacuum preloaded air bearings and comparison performance of the intelligent algorithm with the ANN

Air bearings are commonly used in systems requiring high precision, including semiconductor manufacturing, optical and electronic devices, and aerospace systems, and the usage of vacuum preloading and porous material provides a homogeneous pressure distribution on the bearing surface. The prediction of the characteristics of these air bearings, such as air film thickness and location, is crucial for designing and optimizing the performance of the systems. They exhibit highly nonlinear behavior and are challenging to accurately predict their characteristics using conventional analytical or numerical techniques. In this study, the characteristics of vacuum preloaded porous air bearings are estimated using a hybrid ANFIS-PSO predictor soft computing method with a certain pressure (410 kPa), vacuum (50.8 kPa), and with three different diameters (50, 75 and 90 mm). The usage of different algorithms in the characteristics and selection and design criteria of air bearing has been applied. Six different cases are simulated with different input and output parameters to predict the air film thickness and location of the air bearing. The location of the air bearing has been determined with two angle parameters, α, and β. The dataset required for training and testing the algorithm was obtained through experimental study. In the training and testing process, 40 and 20 datasets were used, respectively. Before the starting analysis, a sensitivity analysis was executed to find optimum PSO parameters such as the number of particles, acceleration coefficients, number of membership functions, and inertia weight. The proposed hybrid ANFIS-PSO method was compared with classical ANFIS and ANN, and it showed better performance and a more accurate solution to estimate the characteristics of vacuum preloaded porous air bearings in both training and testing phases with the R2 of 0.9958 and MSE value of 0.102. The maximum training performance of the ANFIS-PSO is better than ANFIS and ANN with the ratio of 6.8% and 8.5%, respectively. On the other hand, the maximum testing performance of the ANFIS-PSO algorithm is higher than ANFIS and ANN, with the ratio of 22.2% and 24.1%, respectively.

Fuzzy logic approach for seismic fragility analysis of RC frames with applications to earthquake-induced damage and construction quality

This study presents a fuzzy logic model which is able to consider various uncertainties for predicting the seismic fragility curves of the structure. The fuzzy models are generated based on a database (generated by the Latin Hypercube Sampling technique) which includes structure’s modeling parameters as input variables. Also, the output section of the database comprises the structure’s fragility parameters at three different limit states. Several classification decision tree-based Mamdani fuzzy logic models are constructed by converting the above-mentioned numerical database to qualitative labels. The appropriate number of membership functions and also pruning levels of the related decision tree are detected by automatically introducing the classification tree-based rules to the fuzzy model and performing about two million fuzzy analyses while evaluating the associated error versus the number of rules. On the basis of 200 structural models, a set of interpretable Mamdani fuzzy models are generated to predict the fragility curve parameters at different seismic performance levels. These fuzzy models can effortlessly perform further assessments such as sensitivity analysis and seismic performance assessment while considering the impact of earthquake damage and construction quality.

On the performance and interpretability of Mamdani and Takagi-Sugeno-Kang based neuro-fuzzy systems for medical diagnosis

PurposeNeuro-fuzzy systems aim to combine the benefits of artificial neural networks and fuzzy inference systems: a neural network can learn patterns from data and achieves high performance, whereas a fuzzy system matches inputs and outputs using linguistic and interpretable rules. The combination of these two techniques yields models that can both perform well and provide interpretability in a fuzzy linguistic manner. DesignIn this paper, the performance and interpretability of five neuro-fuzzy classifiers were evaluated (three Takagi-Sugeno-Kang (TSK) classifiers: adaptive neuro-fuzzy inference system (ANFIS), dynamic evolving neuro-fuzzy system (DENFIS), self-organizing fuzzy neural network (SOFNN), and two Mamdani classifiers: hybrid fuzzy inference system (HyFIS) and neuro-fuzzy classifier (NEFCLASS)). All the empirical evaluations were over four benchmark medical datasets (Wisconsin breast cancer dataset, SPECTF heart dataset, Parkinsons dataset, and diabetic retinopathy Debrecen dataset), and used five performance criteria (accuracy, precision, recall, f score, and training time) and two interpretability criteria (number of rules and number of membership functions). FindingsResults showed that the TSK-based self-organizing fuzzy neural network classifier, in general, outperformed the others. In terms of interpretability, DENFIS and NEFCLASS were the best Takagi-Sugeno-Kang and Mamdani classifiers respectively. The findings also suggested that three classifiers: DENFIS, SOFNN, and NEFCLASS achieved a good performance-interpretability tradeoff. OriginalityTo the best of our knowledge, no study has compared the neuro-fuzzy techniques presented in this paper in terms of performance and interpretability in the medical domain.

Training Neuro-Fuzzy by Using Meta-Heuristic Algorithms for MPPT

It is one of the topics that have been studied extensively on maximum power point tracking (MPPT) recently. Traditional or soft computing methods are used for MPPT. Since soft computing approaches are more effective than traditional approaches, studies on MPPT have shifted in this direction. This study aims comparison of performance of seven meta-heuristic training algorithms in the neuro-fuzzy training for MPPT. The meta-heuristic training algorithms used are particle swarm optimization (PSO), harmony search (HS), cuckoo search (CS), artificial bee colony (ABC) algorithm, bee algorithm (BA), differential evolution (DE) and flower pollination algorithm (FPA). The antecedent and conclusion parameters of neuro-fuzzy are determined by these algorithms. The data of a 250 W photovoltaic (PV) is used in the applications. For effective MPPT, different neuro-fuzzy structures, different membership functions and different control parameter values are evaluated in detail. Related training algorithms are compared in terms of solution quality and convergence speed. The strengths and weaknesses of these algorithms are revealed. It is seen that the type and number of membership function, colony size, number of generations affect the solution quality and convergence speed of the training algorithms. As a result, it has been observed that CS and ABC algorithm are more effective than other algorithms in terms of solution quality and convergence in solving the related problem.

Comparison of FIS and ARIMA models in runoff estimating

The ability to surface runoff modelling plays an important role in the water resources management, and the possibility of estimating and predicting of runoff values takes on particular importance in the case of gaps in the recorded time series. Therefore, this study aims to compare between fuzzy inference system (FIS) models and autoregressive integrated moving average (ARIMA) models in estimating of the surface runoff at Al-Jawadiyah hydrometric station on the Orontes River in Syria. The MATLAB program was used to build the fuzzy inference models and the Minitab program to build the ARIMA models. A large number of fuzzy inference models were built with the change in the model parameters such as the type and number of membership functions and training algorithms. Likewise, a large number of ARIMA models were built with the change in autoregressive components, moving average components, and differences. The effect of seasonality on the model was also studied. Several criteria were used to compare the models and choose the best model, such as correlation coefficient and root mean square errors. The results showed that fuzzy inference models are superior to estimating surface runoff values with high reliability compared with ARIMA models. This study recommends creating complete databases for all factors related to water resources in the study area that can be relied upon in future studies.

Prediction of safe bearing capacity for settlement criteria using neuro-fuzzy inference system for Clayey soils

Safe bearing capacity (SBC) may be estimated for cohesive soil using the IS Code it is essential to conduct shear tests in order to identify the angle of internal friction and cohesion, SPT tests in order to determine the N-value of the soil, as well as tests in order to determine the dry density of the soil and the relative density of the soil. The SBC of soil is estimated as per settlement criteria using laboratory evaluations of its essential properties. This study suggests the use of ANFIS to predict the Safe Bearing Capacity of cohesive soil as a function of foundation depth, foundation depth, dry density, liquid limit, plasticity index, percentage fine fraction, width/length ratio (in case of square/rectangular footing), and N-Value. An attempt is in the present work with inputs such as foundation depth, dry density, liquid limit, plasticity index, percentage fine fraction, width/length ratio, and N-Value and output as safe bearing capacity. Each input parameter has a different number of membership functions and gaussbell is used in five ANFIS models. The most accurate model, MODEL-IV, with an RMSE of 9.762 and an R2 of 0.9485. For cohesive soil, the results indicate that ANFIS can be used to predict the SBC.

A Novel Intelligent ANFIS for the Dynamic Model of Photovoltaic Systems

Developing accurate models for photovoltaic (PV) systems has a significant impact on the evaluation of the accuracy and testing of PV systems. Artificial intelligence (AI) is the science of developing machine jobs to be more intelligent, similar to the human brain. Involving AI techniques in modeling has a significant modification in the accuracy of the developed models. In this paper, a novel dynamic PV model based on AI is proposed. The proposed dynamic PV model was designed based on an adaptive neuro-fuzzy inference system (ANFIS). ANFIS is a combination of a neural network and a fuzzy system; thus, it has the advantages of both techniques. The design process is well discussed. Several types of membership functions, different numbers of training, and different numbers of membership functions are tested via MATLAB simulations until the AI requirements of the ANFIS model are satisfied. The obtained model is evaluated by comparing the model accuracy with the classical dynamic models proposed in the literature. The root mean square error (RMSE) of the real PV system output current is compared with the output current of the proposed PV model. The ANFIS model is trained based on input–output data captured from a real PV system under specified irradiance and temperature conditions. The proposed model is compared with classical dynamic PV models such as the integral-order model (IOM) and fractional-order model (FOM), which have been proposed in the literature. The use of ANFIS to model dynamic PV systems achieves an accurate dynamic PV model in comparison with the classical dynamic IOM and FOM.

Optimal Adaptive Neuro-Fuzzy Inference System Architecture for Time Series Forecasting with Calendar Effect

This paper discusses a procedure for model selection in ANFIS for time series forecasting with a calendar effect. Calendar effect is different from the usual trend and seasonal effects. Therefore, when it occurs, it will affect economic activity during that period and create new patterns that will result in inaccurate forecasts for decision making if not considered. The focus is on the model selection strategy to find the appropriate input variable and the number of membership functions (MFs) based on the Lagrange Multiplier (LM) test. The ARIMAX stochastic model is used at the preprocessing stage to capture calendar variations in the data. The calendar effect observed is the Eid al-Fitr holiday in Indonesia, a country with the largest Muslim population in the world. The data of Tanjung Priok port passengers used as a case study. The result shows that hybrid ARIMAX-ANFIS based on the LM test can be an effective procedure for model selection in ANFIS for time series with calendar effect forecasting. Empirical results show that the use of the calendar effect variable provides more accurate predictions as indicated by smaller RMSE and MAPE values than without the calendar effect variable.

Design of stabilized fuzzy relation-based neural networks driven to ensemble neurons/layers and multi-optimization

In this study, a design methodology based on fuzzy relation-based neural networks for stabilized network structure is introduced to cope with over-fitting as well as multi-collinearity problems which generally appear in conventional fuzzy neural networks. The design method of the proposed self-organizing network structure provides an efficient solution to construct the stabilized Fuzzy Relation-based Neural Networks (FRNN) through a synergy of multi-techniques such as ensemble neurons/layers, L2-norm regularization, compromise technique, and multi-optimization, in order to generate the structure of the multi-layered self-organizing network designed with the aid of the learning as well as novel structural design.The overall network structure is realized with the aid of parallel network structure with newly added layers as well as effective node selection method through the combination technique of both a sum of squared coefficients (SSC) and performance index (PI) as a node selection criterion for each layer in FRNN. Ensemble neurons consist of the current inputs and the original inputs, and they serve to reduce the bias of the proposed FRNN by maintaining the information of the original inputs. Also, ensemble layers stand for the combination of the current layer and the front layer, and they play a role for control the variance of the model by taking into account the output of the previous layers. The least square error estimation (LSE)-based learning method with L2-norm regularization is used for constructing the stabilized network architecture, and their ensuring design methodologies result in alleviating the overfitting phenomenon and also enhancing the generalization ability. For the performance enhancement of FRNN directly affected by some parameters such as the number of input variables, collocation of the specific subset of input variables, the number of membership functions per each variable, and the order of polynomial in the consequent parts of the fuzzy rules, multi-particle swarm optimization (MPSO) is exploited for the effectively structural as well as parametric optimization of the proposed networks. That is, the multi-optimization helps achieve a compromise between the better generation performance and the alleviated over-fitting leading to the stabilization of the proposed multi-layered self-organizing network structure realized with the aid of synergistic multi-techniques and ensemble structures such as a) L2-norm regularization-based LSE learning, b) combination technique for effective node selection through the combination of SSC and PI, and c) a novel parallel network structure including newly added layers and node selection method. The performance of the proposed network structure is quantified by comprehensive experiments and comparative analysis.

Hierarchically Reorganized Multi-Layer Fuzzy Neural Networks Architecture Driven With the Aid of Node Selection Strategies and Structural Network Optimization

In this study, a design methodology based on fuzzy sets inference and polynomial neural network(PNN) for hierarchically reorganized self-organizing network architecture is introduced to cope with over-fitting as well as multi-collinearity problems which generally appear in a conventional fuzzy neural network. The design method of the proposed self-organizing network structure provides an efficient solution to construct the hierarchically reorganized multi-layer fuzzy neural networks (HRmFNN) architecture through a synergy of multi-techniques such as L <sub xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">2</sub> -norm regularization, probability theory, and multi-optimization. The overall network structure is realized with the aid of parallel network structure with newly added inputs as well as effective neuron selection method through the exponential-based roulette selection technique for each layer in HRmFNN, and the least square error estimation (LSE)-based learning method with L2-norm regularization is used for constructing the stabilized network architecture, and their ensuring design methodologies result in alleviating the overfitting phenomenon and also enhancing the generalization ability. For the performance enhancement of HRmFNN directly affected by some parameters such as the number of input variables, collocation of the specific subset of input variables, the number of membership functions per each variable, and the order of polynomial in the consequent parts of the fuzzy rules, multi-particle swarm optimization (MPSO) is exploited for the effectively structural as well as parametric optimization of the proposed network. That is, the multi-optimization helps achieve a compromise between the better generation performance and the alleviated over-fitting leading to the stabilization of the proposed multi-layered self-organizing network structure with the aid of synergistic multi-techniques such as a) L <sub xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">2</sub> -norm regularization-based LSE learning, b) probability theory for effective neuron selection, and c) novel parallel network structure including newly added inputs and neuron selection method. The performance of the proposed network structure is quantified by comprehensive experiments and comparative analysis. It is also demonstrated through the application to cement compressive strength.

Properties of interval type-2 fuzzy sets in decision support systems

Definitions and methods of designing interval type-2 fuzzy sets in fuzzy inference systems for control problems of complex technical objects in conditions of uncertainty are considered. The main types of uncertainties, that arise when designing fuzzy inference systems and depend on the number of expert assessments, are described. Methods for assessing intra-uncertainty and inter-uncertainty are proposed, taking into account the different number of expert assessments at the stage of determining the types and number of membership functions. Factors influencing the parameters and properties of interval type-2 fuzzy during experimental studies are determined. Such factors include the number of experiments performed, external factors, technical parameters of the control object, and the reliability of the components of the computer system decision support system. The properties of the lower and upper membership functions of interval type-2 fuzzy sets are investigated on the example of the Gaussian membership function, which is one of the most used in the problems of fuzzy inference systems design. The main features and differences in the methods of determining the lower and upper membership functions of interval type-2 fuzzy sets for different types of uncertainties are taken into account. Methods for determining the footprint of uncertainty, as well as the dependence of its size on the number of expert assessments, are considered. The footprint of uncertainty is characterized by the lower and upper membership functions, and its size directly affects the accuracy of the obtained solutions. Methods for determining interval type-2 fuzzy sets using regulation factors of membership function parameters for intra-uncertainty and weighting factors of membership functions for inter-uncertainties have been developed. The regulation factor of the function parameters can be used to describe the lower and upper membership functions while determining the size of the footprint of uncertainty. Complex interval type-2 sets are determined to take into account inter-uncertainties in the problems of fuzzy inference systems design.

Implementasi Kendali Keseimbangan Gerak Two Wheels Self Balancing Robot Menggunakan Fuzzy Logic

Self balancing robot is a two-wheeled robot that only has two fulcrums so that this robot is an unbalanced system. Therefore, a control system that can maintain the stability of the robot is needed so that the robot can keep in standing position. This study aims to design a self-balancing robot and its control system which improves the robot's performance against the maximum angle of disturbance that can be overcome. The control system used is based on fuzzy logic with 9 membership functions and 81 rules. The control system is applied to the ESP-32 microcontroller with the MPU-6050 sensor as a feedback position of the robot and DC motor as an actuator. Complementary filters are added to the MPU-6050 sensor readings to reduce noise to obtain better robotic tilt angle readings. The improvement of this research compared to previous research based on fuzzy is the addition of the number of membership functions from 7 to 9 and the embedding of a complementary filter on the MPU-6050 sensor output reading. The result shows that the designed self balancing robot which has dimensions of 10cm x 18cm x 14.5cm can cope with the maximum disturbance angle up to 17.5⁰.

Parameterized fuzzy-logic controllers for the attitude control of nanosatellites in low earth orbits. A comparative studio with PID controllers

The pointing requirements for a satellite (e.g. for its payload or for its subsystems) determine the different attitude control system operational modes that are necessary along its mission. Two examples are: a low cost mode for nominal attitude stabilization; and a faster mode for antenna pointing during communication phases. In this work, an attitude control algorithm based on fuzzy logic is presented to achieve an optimal performance of the controller for different operational requirements of the satellite mission. After analysing the design process and the response of previous fuzzy controllers, several improvements have been implemented concerning the number of membership functions, their shape, and the contents of the fuzzy rules, obtaining a parameterized final fuzzy inference system whose performance depends on eighteen parameters, six per each of the three control axes. The design proposed in this work will be tested soon on board the European Space Agency OPS-SAT mission and it is easily extensible to most nanosatellite missions in Low Earth Orbits.Different sets of the eighteen tuning parameters have been used to analyse the design and the performance of this new fuzzy controller. The values have been selected through multi-objective genetic optimizations to deal with two conflicting objectives: low cost and accuracy. A numerical performance comparison shows that the new design provides more efficient controllers than those used in previous works. In addition, the performance of the new fuzzy controller has been evaluated against traditional Proportional Integrative Derivative (PID) controllers for different satellite operational requirements. The values of the PID gains have also been selected through the same multi-objective genetic optimization. The comparisons show that the new fuzzy design provides great advantages over the PID strategy in most of the operational modes considered, and how the PID strategy has difficulties to produce a low cost control law profile. Furthermore, the new fuzzy design is able to improve the Pareto front to optimal points that are unreachable with the PID schema. These results open new possibilities for the application of intelligent controllers in the space industry.

Prediction of turbulence eddy dissipation of water flow in a heated metal foam tube

The insertion of porous metal media inside the pipes and channels has already shown a significant heat transfer enhancement by experimental and numerical studies. Porous media could make a mixing flow and small-scale eddies. Therefore, the turbulence parameters are attractive in such cases. The computational fluid dynamics (CFD) approach can predict the turbulence parameters using the turbulence models. However, the CFD is unable to find the relation of the turbulence parameters to the boundary conditions. The artificial intelligence (AI) has shown potential in combination with the CFD to build high-performance predictive models. This study is aimed to establish a new AI algorithm to capture the patterns of the CFD results by changing the system’s boundary conditions. The ant colony optimization-based fuzzy inference system (ACOFIS) method is used for the first time to reduce time and computational effort needed in the CFD simulation. This investigation is done on turbulent forced convection of water through an aluminum metal foam tube under constant wall heat flux. The ANSYS-FLUENT CFD software is used for the simulations. The x and y of the fluid nodal locations, inlet temperature, velocity, and turbulent kinetic energy (TKE) are the inputs of the ACOFIS to predict turbulence eddy dissipation (TED) as the output. The results revealed that for the best intelligence of the ACOFIS, the number of inputs, the number of ants, the number of membership functions (MFs) and the rule are 5, 10, 93 and 93, respectively. Further comparison is made with the adaptive network-based fuzzy inference system (ANFIS). The coefficient of determination for both methods was close to 1. The ANFIS showed more learning and prediction times (785 s and 10 s, respectively) than the ACOFIS (556 s and 3 s, respectively). Finding the member function versus the inputs, the value of TED is calculated without the CFD modeling. So, solving the complicated equations by the CFD is replaced with a simple correlation.

Functional input and membership characteristics in the accuracy of machine learning approach for estimation of multiphase flow

In the current study, Artificial Intelligence (AI) approach was used for the learning of a physical system. We applied four inputs and one output in the learning process of AI. In the learning process, the inputs are space locations of a BCR (bubble column reactor), which are x, y, and z coordinate as well as the amount of gas fraction in BCR. The liquid velocity is also considered as output. A variety of functions were used in learning, such as gbellmf and gaussmf functions, to examine which functions can give the best learning. At the end of the study, all of the results were compared to CFD (computational fluid dynamics). A three-dimensional (3D) BCR was used in this research, and we studied simulation by CFD as well as AI. The data from CFD in a 3D BCR was studied in the AI domain. In AI, we tuned for various parameters to achieve the best intelligence in the system. For instance, different inputs, different membership functions, different numbers of membership functions were used in the learning process. Moreover, the meshless prediction was used, meaning that some data in the BCR have not participated in the learning, and they were predicted in the prediction process, which gives us a special capability to compare the results with the CFD outcomes. The findings showed us that AI can predict the CFD results, and a great agreement was achieved between CFD computing nodes and AI elements. This novel methodology can suggest a meshless and multifunctional AI model to simulate the turbulence flow in the BCR. For further evaluation, the ANFIS method is compared with ACOFIS and PSOFIS methods with regards to model’s accuracy. The results show that ANFIS method contains higher accuracy and prediction capability compared with ACOFIS and PSOFIS methods.

Gbell Learning function along with Fuzzy Mechanism in Prediction of Two-Phase Flow.

The integration of the computational fluid dynamics (CFD) and the adaptive network-based fuzzy inference system, known as ANFIS, is investigated for simulating the hydrodynamic in a bubble column reactor. The Eulerian–Eulerian two-phase model is employed as the CFD approach. For the ANFIS technique, a sensitivity analysis is done by varying the number of inputs and the number of membership functions (MFs). The x and z coordinates of the fluid location, the air velocity, and the pressure are considered as the inputs of the ANFIS, while the air vorticity is the output. The results revealed that the ANFIS with all four inputs and the MFs of five achieved the highest intelligence with the regression number close to 1. More specifically, gbell function in the learning framework is used to train all local computing nodes from solving Navier–Stokes equations. In the decision or prediction part, the fuzzy mechanism is used for the prediction of extra nodes that solve, which Navier–Stokes equations did not solve. The results show that the gbell function enables us to fully train all numerical points and also store data set in the frame of mathematical equations. Besides, this function responds well with the number of inputs and MFs for accurate prediction of reactor hydrodynamics. Additionally, a high number of MFs and input parameters influence the accuracy of the method during prediction. In the current study, gbell MF was studied to investigate its accuracy in the prediction of the two-phase flow. Also, different numbers of MFs were considered to investigate the level of accuracy and capability of prediction. ANFIS clustering methods, grid partition and fuzzy C-mean (FCM) clustering, are compared to see the ability of the method in prediction. To compare the accuracy of the ANFIS method with FCM clustering, the data were compared to the gaussmf function. The results showed that the method has high accuracy and that it could predict the flow pattern.

Neuro-Fuzzy and Soft Computing - A Computational Approach to Learning and Artificial Intelligence

Single approaches to soft computing have many limitations and disadvantages. Neural network modelling poses a challenge of architecture building, whilst fuzzy sets are characterized by problematic membership functions. The use of hybrid methods is, by contrast, a rather promising strategy. This study aims to develop a new prediction methodology by integrating Neuro-Fuzzy Systems (NFS) with a Neuro-Genetic Approach (NGA). Such a design combines the learning capacity of the neural networks and the ability of fuzzy systems to extract the linguistic knowledge. This proposal is expected to predict the suitability of parameters and models with fewer errors and high accuracy. The performance of this system is improved through the use of genetic algorithm for optimizing the neural network parameters such as the learning rate, network impulse, and the number of membership functions for each input variable. The proposed methodology was tested using electromyographic (EMG) data. The results showed high efficiency (92%) of the proposed hybrid technique.

Neuro-fuzzy control of sit-to-stand motion using head position tracking

Based on the clinical evidence that head position measured by the multisensory system contributes to motion control, this study suggests a biomechanical human-central nervous system modeling and control framework for sit-to-stand motion synthesis. Motivated by the evidence for a task-oriented encoding of motion by the central nervous system, we propose a framework to synthesize and control sit-to-stand motion using only head position trajectory in the high-level-task-control environment. First, we design a generalized analytical framework comprising a human biomechanical model and an adaptive neuro-fuzzy inference system to emulate central nervous system. We introduce task-space training algorithm for adaptive neuro-fuzzy inference system training. The adaptive neuro-fuzzy inference system controller is optimized in the number of membership functions and training cycles to avoid over-fitting. Next, we develop custom human models based on anthropometric data of real subjects. Using the weighting coefficient method, we estimate body segment parameter. The subject-specific body segment parameter values are used (1) to scale human model for real subjects and (2) in task-space training to train custom adaptive neuro-fuzzy inference system controllers. To validate our modeling and control scheme, we perform extensive motion capture experiments of sit-to-stand transfer by real subjects. We compare the synthesized and experimental motions using kinematic analyses. Our analytical modeling-control scheme proves to be scalable to real subjects’ body segment parameter and the task-space training algorithm provides a means to customize adaptive neuro-fuzzy inference system efficiently. The customized adaptive neuro-fuzzy inference system gives 68%–98% improvement over general adaptive neuro-fuzzy inference system. This study has a broader scope in the fields of rehabilitation, humanoid robotics, and virtual characters’ motion planning based on high-level-task-control scheme.