Proposed Adaptive Neuro-Fuzzy Inference System Controller Research Articles

Intelligent robust adaptive attitude controller for small satellites

This work addresses the issue of small-satellite attitude control. This satellite’s Attitude-Control-System (ACS) is managed by an intelligent controller built on Adaptive Neuro-Fuzzy Inference System (ANFIS). ANFIS control approach is designed to improve the satellite’s angular mobility along its axes. Two simulation scenarios have been tackled. In the first scenario, ACS system efficiency was evaluated and contrasted with ACS based on a PD controller optimized by a genetic-algorithm for the nonlinear system model and a Linear-Quadratic-Regulator (LQR) in the existence of input environmental disturbances. The simulation outcomes demonstrate that the proposed control technique successfully addresses the mobility issue of a small satellite. Inaccuracies in the satellite’s parameters, torque noise brought on by the vibration of the actuators, and external disturbances were added in the second scenario. The proposed ANFIS controller has demonstrated robust, reliable performance for control of the ACS.

Modeling and design of an automatic generation control for hydropower plants using Neuro-Fuzzy controller

This paper presents the modeling, design, and experimental analysis of an Automatic Generation Control (AGC) for a hydropower plant using Adaptive-Neuro-Fuzzy Inference system (ANFIS). This was aimed at reducing the frequency deviations which occur during power generation. The Adaptive-Neuro-Fuzzy Inference system (ANFIS) was used to intelligently control the selection of parameters for the effective control of power in the hydropower plant. The proposed ANFIS was trained with input–output data of the fuzzy logic controller (FLC). The ANFIS model is used as a hybrid learning model which includes the Least Square Estimate (LSE) and back propagation algorithm (BPA). The conventional PID, FLC, and ANFIS controllers were investigated using MATLAB. In order to determine the best controller, the controllers were experimented and compared to determine the controller with the best performance. The results show that frequency deviations occur as a result of a continuous variation of loads, which make the deviations difficult to control when a governor is not applied. Furthermore, the response of the AGC of the hydropower plant (in the single and double area) with step load changes was studied. The simulation results show that the ANFIS controller performs better compared to the PID as well as the FLC. Further results indicate that the proposed ANFIS controller helps to speed up the performance of the AGC of the hydropower plant. The ANFIS controller not only improved the performance but also made the fuzzy inference system (FIS) less dependent on the expert system.

Intelligent control of islanded AC microgrids based on adaptive neuro-fuzzy inference system

In inverter-based AC microgrids, active power sharing between Distributed Generation (DG) units is achieved by introducing a droop frequency control for the inverter. The purpose of the secondary controller is to regulate the frequency deviation caused by the primary controller while maintaining the droop characteristic of active power sharing among DG units. In this paper, Adaptive Neuro-Fuzzy Inference System (ANFIS) is employed to effectively control frequency and power sharing among DG units in a 100% renewable based microgrid while working in different areas of the operating points. Rules and configuration of ANFIS are introduced to handle the complexity of larger microgrids. The effectiveness of the proposed method is demonstrated in two case studies. The simulation results suggest that the proposed ANFIS controller, compared to the conventional controllers, is able to satisfy the power sharing among DG units while better regulating the frequency.

Adaptive neuro-fuzzy inference system based output power controller in grid-connected photovoltaic systems

ABSTRACT The power obtained from the photovoltaic (PV) module is greatly influenced by module temperature and the Sun’s irradiations. To extract optimal power from PV modules, usually a maximum power point tracking controller is incorporated in the system. Previously, methods like Perturb & Observe and Incremental Conductance were used to control output power. These methods, though easy to implement, face certain challenges. They have low tracking speed, poor convergence rate and face rapid variations even during steady-state conditions. Alternatively, artificially intelligent (AI) techniques are more robust and are known to effectively handle non-linearities associated with any system. In this study, the Adaptive Neuro Fuzzy Inference System (ANFIS) has been developed to extract maximum power from a non-linear PV module. The designed ANFIS controller directly take the irradiance and temperature as input parameters to give the crisp value of voltage, which can deliver the maximum power in all situations. For optimal design of the ANFIS controller, Taguchi’s method-based optimization approach has been implemented. The extensive simulations reveal satisfactory power tracking performance of the PV module by using the proposed ANFIS controller. RMSE value of 0.0054 and R2 value of 0.993 verifies the effectiveness of the proposed ANFIS controller. The proposed controller shows a faster track response with negligible oscillations in comparison to the conventional Perturb & Observe controller.

Adaptive neuro-fuzzy inference system based under-frequency load shedding for Tamil Nadu

Under-frequency load shedding (UFLS) is a popular technique around the world, especially in India for maximizing the power system stability and to avoid blackout in case of contingency. Electricity demand–supply gap due to generation failure is the main cause for power shortage, which leads to frequency degradation and major collapse of the whole system. Load shedding helps utility to restore the system stability. But the traditional load shedding methods shed incorrect as well as excess load which increases economic loss to utility and discomfort to customers. In this paper, an adaptive neuro-fuzzy inference system (ANFIS) based UFLS controller using back-propagation and least-square estimation algorithm is simulated and tested for Tamil Nadu power system, a leading industrialized state of India with an objective to shed minimum possible load. The simulations are carried out using MATLAB toolbox. The performance of the proposed ANFIS based UFLS controller is compared with an artificial neural network (ANN) based controller. The comparison of ANN and ANFIS based UFLS shows that by using the proposed ANFIS controller, the amount of load shed could be reduced between 83 and 1264 MW for various generation–load scenarios, which significantly benefits both utility and customers to enhance energy security and revenue up to 7.5 million INR per hour.

Automatic Load Frequency Control of Six Areas’ Hybrid Multi-Generation Power Systems Using Neuro-Fuzzy Intelligent Controller

This manuscript deals with the implementation of adaptive neuro-fuzzy inference system (ANFIS) approach to automatic load frequency control (ALFC) of six unequal areas’ multi-generation hybrid interconnected power system. ANFIS controller has the advantages of fuzzy as well as neural network and stands for adaptive neuro-fuzzy inference system. Areas 1 and 2 comprise thermal and reheat thermal plants, area 3 consists of hydro plant with hydraulic governor system whereas areas 4, 5 and 6 comprise nuclear, diesel and gas turbine power plants, respectively. The hybrid model of interconnected power plant is developed with intelligent ANN (artificial neural network) and hybrid neuro-fuzzy controllers, i.e. proposed ANFIS and existing proportional and integral (PI) controller separately. The simulation work was carried out and the performance evaluation is checked by the proposed control approaches with similar step load change in each areas. Sliding surface is introduced with each controller to enhance the performance of controllers. Evaluation of ANN, ANFIS and PI-based approaches exhibits the advantage of the proposed ANFIS controller over conventional PI controller and ANN controller for tie-line power and frequency deviation in all six areas of interconnected hybrid power system.

ANFIS Based Space Vector Modulation-DTC for Switched Reluctance Motor Drive

Direct torque control (DTC) of Switched reluctance motor is known straightforward control structure with similar execution to that of field situated control strategies. In any case, the part of ideal determination of the voltage space vector is one of the weakest focuses in a routine DTC drive because of adjustable switching frequency and high torque ripple. In this paper, ideal choice of voltage space vectors is accomplished utilizing ANFIS (Adaptive Neuro Fuzzy Inference System) with space vector Modulation. SVM-DTC gives consistent switching frequency and the proposed ANFIS controller’s structure manages the torque and stator flux error signals through the fuzzy deduction to get a yield that takes the type of space voltage vector. Simulation results accept the proposed evolutionary system with quick torque and flux reaction with minimized torque ripple and flux ripple.

Load Frequency Control of Multi-area Power Systems Using Neuro-Fuzzy Hybrid Intelligent Controllers

ABSTRACTIn this paper, artificial neural network (ANN) and fuzzy-based adaptive neuro-fuzzy inference system (ANFIS) approach to automatic generation control of three unequal area hydro-thermal power systems has been introduced. The proposed ANFIS controller combines the advantages of fuzzy controller as well as quick response and adaptability nature of ANN. Area 1 and area 2 consist of thermal reheat power plant whereas area 3 consists of hydro power plant with electric governor. Performance evaluation is carried out by using ANN, fuzzy, and ANFIS control approaches. To enhance the performance of intelligent controller, sliding surface is included. The performances of the controllers are simulated using MATLAB/SIMULINK software. A comparison of ANFIS, ANN, fuzzy-based approaches shows the superiority of proposed ANFIS over ANN, fuzzy for change in frequency and tie-line power deviation in three area interconnected power system.

An adaptive neuro fuzzy inference system controlled space cector pulse width modulation based HVDC light transmission system under AC fault conditions

Abstract In HVDC Light transmission systems, converter control is one of the major fields of present day research works. In this paper, fuzzy logic controller is utilized for controlling both the converters of the space vector pulse width modulation (SVPWM) based HVDC Light transmission systems. Due to its complexity in the rule base formation, an intelligent controller known as adaptive neuro fuzzy inference system (ANFIS) controller is also introduced in this paper. The proposed ANFIS controller changes the PI gains automatically for different operating conditions. A hybrid learning method which combines and exploits the best features of both the back propagation algorithm and least square estimation method is used to train the 5-layer ANFIS controller. The performance of the proposed ANFIS controller is compared and validated with the fuzzy logic controller and also with the fixed gain conventional PI controller. The simulations are carried out in the MATLAB/SIMULINK environment. The results reveal that the proposed ANFIS controller is reducing power fluctuations at both the converters. It also improves the dynamic performance of the test power system effectively when tested for various ac fault conditions.

Adaptive Neuro-Fuzzy Inference System based speed controller for brushless DC motor

In this paper, a novel controller for brushless DC (BLDC) motor has been presented. The proposed controller is based on Adaptive Neuro-Fuzzy Inference System (ANFIS) and the rigorous analysis through simulation is performed using simulink tool box in MATLAB environment. The performance of the motor with proposed ANFIS controller is analyzed and compared with classical Proportional Integral (PI) controller, Fuzzy Tuned PID controller and Fuzzy Variable Structure controller. The dynamic characteristics of the brushless DC motor is observed and analyzed using the developed MATLAB/simulink model. Control system response parameters such as overshoot, undershoot, rise time, recovery time and steady state error are measured and compared for the above controllers. In order to validate the performance of the proposed controller under realistic working environment, simulation result has been obtained and analyzed for varying load and varying set speed conditions.

Comparison of ANFIS and Neural Network Direct Inverse Control Applied to Wastewater Treatment System

Large disturbances and highly nonlinear nature of the wastewater treatment system makes its control very difficult and challenging. The control of the system using conventional techniques becomes hard and often impossible. This paper presents a comparison of an adaptive neuro-fuzzy inference system (ANFIS) and neural network (NN) inverse control applied to the system. The performances of the controllers were evaluated based on the rise time; percent overshot and the mean error. Simulation results revealed that the ANFIS controller performance was slightly better compared to the neural network controller. The proposed ANFIS controller is effective and useful to the process.

Incipient fault diagnostics of rotating electrical machines using adaptive neuro-fuzzy inference system

Abstract Condition monitoring and fault diagnostics of electrical machines are extremely important in any industrial setup. In some applications, such as the oil and gas industries, production units, power generation, refining and milling, the failure of critical equipment like generators, milling machines, motors, fans and pumps costs millions of dollars in reduced output, emergency maintenance costs and lost revenues. However, in the utility industry, malfunctioning of the electrical machinery is not acceptable not only because of its financial damage, but also the threat that is caused by a sudden failure or malfunctioning of the part. The research is aimed at developing a system that will detect incipient failures of electrical machinery before actual failure results in system or industrial process disruption. The objective is to make repeatable decisions based on complex relationships between large amounts of measured and estimated data. The condition of the machines will be available at all times, and the incipient detection and predictive maintenance system will provide an accurate prediction of any potential failure on demand. Two techniques are under consideration, the first one is based on pattern recognition that analyzes electrical measurements of electrical components to characterize the profile of electric machines at the beginning of life for a ‘baseline signature’. Then, at regular intervals, or when a failure is suspected, the technique will be used to derive the present profile and compare it with the ‘baseline’ profile. The other method is based on adaptive neuro-fuzzy inference system (ANFiS). The synergy of artificial neural network and expert fuzzy logic yield ANFiS that is a simple and effective diagnostic tool not requiring precise mathematical models of the motor and controllers. The proposed ANFiS controller will provide qualitative and quantitative knowledge of the health of a rotating machine through valid heuristic reasoning. Various types of electrical and mechanical faults will be investigated and the technique based on expert knowledge (ANFiS system) will be utilized for incipient fault diagnostics.