Membership Functions Of Fuzzy Controller Research Articles

Adaptive fuzzy energy management strategy for range‐extended electric vehicles integrated with deep learning

AbstractA novel framework for adaptive energy management, rooted in deep learning principles, is proposed to minimize fuel consumption in extended‐range electric vehicles amidst intricate driving scenarios. This innovative approach integrates a long short‐term memory (LSTM) network for pattern recognition across three driving patterns and an adaptive fuzzy controller. To mitigate the impact of poor hyperparameter selection on recognition accuracy, Gray Wolf Optimization is employed to optimize the hidden layer nodes, training times, and learning rate of the LSTM. Simultaneously, a genetic algorithm is utilized to optimize the vertex coordinates of the fuzzy control membership function, enabling the adaptive adjustment of parameters in the fuzzy energy management strategy. The condition recognition model accurately identifies the vehicle's driving status and seamlessly transitions to an energy management strategy tailored to the present conditions. This ensures optimal operation, enhancing overall fuel efficiency and performance. The simulation results robustly validate the efficacy of this approach: the GWO‐LSTM network achieves an impressive 97.7% accuracy in recognizing working conditions, surpassing the 88.9% accuracy of the traditional LSTM network. Furthermore, the fuel consumption reduction achieved by the adaptive fuzzy energy management strategy amounts to 11.9% compared with the conventional fuzzy energy management approach. This outcome underscores the tangible enhancement in vehicle fuel economy resulting from the seamless integration of deep learning techniques.

Fuzzy-based metaheuristic algorithm for optimization of fuzzy controller: fault-tolerant control application

PurposeFuzzy-based metaheuristic algorithm is used to optimize the fuzzy controllers for the nonlinear level control system subject to uncertainty specially in the main actuator that has lost effectiveness (LOE). To optimize the fuzzy controller, type-1 harmonic search (HS) and interval type-2 (HS) will be used.Design/methodology/approachThe type-1 and type-2 fuzzy-based HS algorithms are designed for optimization of fuzzy controllers for Fault-Tolerant Control (FTC) applications, and this research proposes a fuzzy-based HS metaheuristic method. The performance of a fuzzy logic-based HS algorithm applied to a nonlinear two-tank level control process with a main actuator that has lost effectiveness (LOE) and also the same controller will be tested on DC motor angular position control with and without noise.FindingsThe key contribution of this work is the discovery of the best approach for generating an optimal vector of values for the fuzzy controller's membership function optimization. This is done in order to improve the controller's performance, bringing the process value of the two-tank level control process closer to the target process value (set point). It is worth noting that the type-1 fuzzy controller that has been optimized is an interval type-2 fuzzy system, which can handle more uncertainty than a type-1 fuzzy system.Originality/valueThe type-1 and type-2 fuzzy-based HS algorithms are designed for optimization of fuzzy controllers for FTC applications, and this research proposes a fuzzy-based HS metaheuristic method. The performance of a fuzzy logic-based HS algorithm applied to a nonlinear two-tank level control process with a main actuator that has LOE will be tested on DC motor angular position control with noise. Two nonlinear uncertain processes are used to demonstrate the effectiveness of the proposed control scheme.

Dynamic Modeling and Torque Feedforward based Optimal Fuzzy PD control of a High-Speed Parallel Manipulator

Dynamic modeling and control of high-speed parallel manipulators are of importance due to their industrial applications deployed in production lines. However, there are still a number of open problems, such as the development of a precise dynamic model to be used in the model-based control design. This paper presents a four-limb parallel manipulator with Schönflies motion and its simplified dynamic modeling process. Then, in order to fix the issue that computed torque method control (CTC) will spend a lot of time to calculate dynamic parameters in real-time, offline torque feedforward-based PD (TFPD) control law is adopted in the control system. At the same time, fuzzy logic is also used to tune the gains of PD controller to adapt to the variation of external disturbance and compensate the un-modeled uncertainty. Additionally, bottom widths of membership functions of fuzzy controller are optimized by bat algorithm. Finally, three controllers of CTC, TFPD and bat algorithm-based torque feedforwad fuzzy PD controller (BA-TFFPD) are compared in trajectory tracking simulation. Fro the result, compared with TFPD and CTC, BA-TFFPD can lead faster transient response and lower tracking error, which prove the validity of BA-TFFPD.

Dynamic Modeling and Torque Feedforward based Optimal Fuzzy PD control of a High-Speed Parallel Manipulator

Dynamic modeling and control of high-speed parallel manipulators are of importance due to their industrial applications deployed in production lines. However, there are still a number of open problems, such as the development of a precise dynamic model to be used in the model-based control design. This paper presents a four-limb parallel manipulator with Schonflies motion and its simplified dynamic modeling process. Then, in order to fix the issue that computed torque method control (CTC) will spend a lot of time to calculate dynamic parameters in real-time, offline torque feedforward-based PD (TFPD) control law is adopted in the control system. At the same time, fuzzy logic is also used to tune the gains of PD controller to adapt to the variation of external disturbance and compensate the un-modeled uncertainty. Additionally, bottom widths of membership functions of fuzzy controller are optimized by bat algorithm. Finally, three controllers of CTC, TFPD and bat algorithm-based torque feedforwad fuzzy PD controller (BA-TFFPD) are compared in trajectory tracking simulation. Fro the result, compared with TFPD and CTC, BA-TFFPD can lead faster transient response and lower tracking error, which prove the validity of BA-TFFPD.

Application Research of Fuzzy PID Control Optimized by Genetic Algorithm in Medium and Low Speed Maglev Train Charger

China’s railways are developing rapidly, and the charger of the auxiliary power supply system is an indispensable part of the maglev train. The existing maglev train charger usually uses the traditional PID controller to control the output of the charger which has a simple structure. To meet the requirements of the maglev train charger output performance which is getting higher and higher, it is necessary to optimize the control strategies which can achieve adaptive control of the system. In this paper, taking Qingyuan maglev train as the research object, the control principle of the charger of the maglev train is studied, and the simulation model of the charger of Qingyuan speed maglev train is built in MATLAB/Simulink. After verifying its feasibility, the paper proposes fuzzy PID control to improve the charger control method, and uses genetic algorithm to optimize fuzzy control membership function and fuzzy rules. Finally, the paper builds a fuzzy PID controller simulation model, compares the output performance of the charger under different control methods, and verifies the superiority of the new control method.

An adaptive compensation droop control strategy for reactive power sharing in islanded microgrid

In a parallel distributed generation system, the conventional droop control strategy makes it difficult for the inverter to output reactive power precisely due to the line impedance uncertainty and load fluctuation, which leads to a voltage deviation of the microgrid system. In order to precisely distribute reactive power, this paper advances an adaptive compensation strategy based on fuzzy control. The fuzzy controller detects the load power of AC bus terminal and output adaptive power coefficient to adjust amplitude voltage to generate compensation voltage. The compensation voltage is fed back to the d-axis voltage of the power loop for reactive power redistribution. Because the fuzzy control membership function value is difficult to determine accurately, this paper puts forward a method which combines neural network with fuzzy control to determine membership function values and fuzzy rules. Simulations and experimental results show that the adaptive compensation control strategy can share power accurately with good dynamic characteristics and robustness.

Improvement of MPPT Control Performance Using Fuzzy Control and VGPI in the PV System for Micro Grid

This paper proposes the method for maximum power point tracking (MPPT) of the photovoltaic (PV) system. The conventional PI controller controls the system with fixed gains. Conventional PI controllers with fixed gains cannot satisfy both transient and steady-state. Therefore, to overcome the shortcomings of conventional PI controllers, this paper presents the variable gain proportional integral (VGPI) controllers that control the gain value of PI controllers using fuzzy control. Inputs of fuzzy control used in the VGPI controller are the slope from the voltage-power characteristics of the PV module. This paper designs fuzzy control’s membership functions and rule bases using the characteristics that the slope decreases in size, as it approaches the maximum power point and increases as it gets farther. In addition, the gain of the PI controller is adjusted to increase in transient-state and decrease in steady-state in order to improve the error in steady-state and the tracking speed of maximum power point of the PV system. The performance of the VGPI controller has experimented in cases where the solar radiation is constant and the solar radiation varies, to compare with the performance of the P&O method, which is traditionally used most often in MPPT, and the performance of the PI controller, which is used most commonly in the industry field. Finally, the results from the experiment are presented and the results are analyzed.

Disturbance observer‐based integral fuzzy sliding‐mode control and its application to wind turbine system

In this study, a disturbance observer-based integral fuzzy sliding-mode control methodology for a wind turbine system with a non-linear permanent magnet synchronous generator (PMSG) is proposed using the Takagi–Sugeno fuzzy model. To reduce the hardware cost of the fuzzy controller membership function, an imperfect premise matching condition is considered. Considering the matched disturbance, and an external disturbance acting on the system, a novel integral fuzzy sliding surface is proposed based on a fuzzy disturbance observer (FDOB). Therefore, various forms of external disturbances can be estimated using the FDOB. In addition, a sufficient condition for guaranteeing the asymptotic stability of the sliding motion with performance is proposed using a Lyapunov function and derived using a linear matrix inequality format. Furthermore, a reachability problem of the system states over the proposed sliding surface is derived through an appropriate Lyapunov function. Finally, the simulations for a wind turbine system using a PMSG are implemented to verify the effectiveness of the proposed method as compared with previous studies.

Application of Fuzzy Controller Based on Chaos Optimal Design

It is difficult to tune parameters of fuzzy controller (FC), and control rules and membership functions of FC are hard to obtain optimization too.Therefore, the control results show strong overshoot and oscillation often.The authors propose a chaos optimal design method based on annealing strategy.According to random and ergodic features of chaos dynamics, the chaotic variables are applied to searching for parameters of FC, the optimal variables are transformed into chaotic variables by carrier-wave, the global search process is done using ergodic features of chaotic motion, and then an approximate global optimal solution is obtained. After that, the chaos local searching and optimization based on annealing strategy is cited, the parameters are optimized again within the limits of the approximate global optimal solution, which is realized by means of combination of global and partial chaos searching, which can converge quickly to global optimal value.Finally, simulations of third order and nonlinear system show that control result of the method is good.

Design of ABCF Control Scheme for Full Vehicle Nonlinear Active Suspension System with Passenger Seat

Suspension systems are essential parts in vehicles because of their usefulness for riding comfort and safety of passengers. Suspension system is used to isolate the road disturbance experienced by the tires from being transmitted to the passengers. The main objective of this paper is to propose a new intelligent control scheme based on using fuzzy logic and artificial bee colony (ABC) optimization algorithm to improve the performance of suspension systems. Effects of the nonlinearities forces that exist in damper, spring and actuator have been considered in this paper. The forces between the body of the vehicle and tires are generated using nonlinear active suspension systems. Also, the parametric uncertainty in the spring, damper and actuator has been taken into account; therefore, robust control scheme should be utilized. This necessitates a very fast and accurate controller to meet as many control objectives as possible. This paper deals with fuzzy technique to design a robust control scheme. The parameters of membership functions of fuzzy controllers have been tuned by using ABC optimization algorithm. The advantage of proposed controller is that it can handle the nonlinearities faster than other conventional controllers. The proposed control scheme attempts to minimize the vibration on each corner of the vehicle by feeding suitable forces to suspension system when passing on rough road. The comparison between passive and active suspension systems with the proposed ABCF control scheme is studied in order to illustrate the effectiveness of ABCF control scheme in terms of improving the ride comfort and safety of traveling passengers.

Selection of Fuzzy Controller Membership Functions Based on Adaptive Gaussian Cloud Transform

Aiming at the boundedness of existing methods of selecting membership functions, an adaptive Gaussian cloud transform algorithm which is guided by the threshold values of hybridization degree is proposed to construct concept hierarchy from original sample data, and then the number, shape and coverage area of membership functions can be derived from the distribution of Gaussian cloud. To test and verify the effectiveness of membership function that is extracted based on adaptive Gaussian cloud transform algorithm, a six-degree-of freedom model of unmanned aerial vehicles(UAV) is constructed, and a fuzzy controller of pitching angle is established with the platform of Simulink. The simulation results show that the fuzzy controller which includes membership functions derived from the distribution of Gaussian cloud transform can achieve perfect control performance of pitching angle and meanwhile obtain good dynamic response characteristics.

Improved frequency control of a micro-grid with a genetically tuned fuzzy controlled super-capacitor system

In this paper, genetically tuned fuzzy controlled super-capacitor energy storage system (SCESS) is employed to improve the frequency control of a hybrid wind-diesel system. Super-capacitor is interfaced with the system through voltage source converter and bidirectional DC-DC buck-boost converter. The fuzzy logic controller for SCESS is designed in such a way that the effect of load disturbance is continuously mitigated while considering the operational constraints of SCESS. The membership functions of fuzzy controller are tuned by employing genetic algorithm (GA) for optimal performance. Optimised membership functions are reached out by introducing a regulated variable based on supercapacitor voltage and frequency deviation of the system. To validate the proposed scheme, detailed model is developed and tested in MATLAB/Simulink environment.

Design and Optimization of the Power Management Strategy of an Electric Drive Tracked Vehicle

This article studies the power management control strategy of electric drive system and, in particular, improves the fuel economy for electric drive tracked vehicles. Combined with theoretical analysis and experimental data, real-time control oriented models of electric drive system are established. Taking into account the workloads of engine and the SOC (state of charge) of battery, a fuzzy logic based power management control strategy is proposed. In order to achieve a further improvement in fuel economic, a DEHPSO algorithm (differential evolution based hybrid particle swarm optimization) is adopted to optimize the membership functions of fuzzy controller. Finally, to verify the validity of control strategy, a HILS (hardware-in-the-loop simulation) platform is built based on dSPACE and related experiments are carried out. The results indicate that the proposed strategy obtained good effects on power management, which achieves high working efficiency and power output capacity. Optimized by DEHPSO algorithm, fuel consumption of the system is decreased by 4.88% and the fuel economy is obviously improved, which will offer an effective way to improve integrated performance of electric drive tracked vehicles.

Process control using genetic algorithm and ant colony optimization algorithm

Artificial life uses biological knowledge and techniques to solve different engineering, management, control and computational problems. Natural systems teach us that very simple individual organisms can form systems capable of performing highly complex tasks by dynamically interacting with each other. In this study, artificial life based approaches are handled and incorporated to enable a real-time water level control. The process was first modelled using NARX type Artificial Neural Network. A fuzzy controller was then attached to the model. For a better performance, fuzzy controller membership function boundary values and action values were optimized simultaneously. The optimization process was performed using genetic algorithm and ant colony optimization algorithm, respectively. Finally, the performance of the controllers was discussed further by considering the system outputs. The developed structure replaces the tedious process of trial-and-error for better combination of fuzzy parameters and can settle the problem of designing fuzzy controller without an expert's experience.

Use of ANFIS Control Approach for SSSC based Damping Controllers Applied in a Two-area Power System

In an interconnected power system, low frequency electromechanical oscillations are initiated by normal smallchanges in system loads, and they become much worse following a large disturbance. Flexible AC TransmissionSystem (FACTS) devices are widely recognized as powerful controllers for damping power system oscillations. Thestandard FACTS controllers are linear controllers which may not guarantee acceptable performance or stability in theevent of a major disturbance. To overcome the drawbacks of conventional controllers, ANFIS (Adaptive Neuro-FuzzyInference System) control scheme has been developed in this paper, and it has been applied for the externalcoordinated control of series connected FACTS controllers known as Static Synchronous Series Compensators(SSSCs) employed in a two-area power system. In neuro-fuzzy control method, the simplicity of fuzzy systems andthe ability of training in neural networks have been combined. The training data set the parameters of membershipfunctions in fuzzy controller. This ANFIS can track the given input-output data in order to conform to the desiredcontroller. Simulation studies carried out in MATLAB/SIMULINK environment demonstrate that the proposed ANFISbased SSSC controller shows the improved damping performance as compared to conventional SSSC baseddamping controllers under different operating conditions.

SOS Based Robust <inline-formula> <tex-math notation="TeX">${\cal H}_{\infty}$ </tex-math></inline-formula> Fuzzy Dynamic Output Feedback Control of Nonlinear Networked Control Systems

In this paper, a methodology for designing a fuzzy dynamic output feedback controller for discrete-time nonlinear networked control systems is presented where the nonlinear plant is modelled by a Takagi-Sugeno fuzzy model and the network-induced delays by a finite state Markov process. The transition probability matrix for the Markov process is allowed to be partially known, providing a more practical consideration of the real world. Furthermore, the fuzzy controller's membership functions and premise variables are not assumed to be the same as the plant's membership functions and premise variables, that is, the proposed approach can handle the case, when the premise of the plant are not measurable or delayed. The membership functions of the plant and the controller are approximated as polynomial functions, then incorporated into the controller design. Sufficient conditions for the existence of the controller are derived in terms of sum of square inequalities, which are then solved by YALMIP. Finally, a numerical example is used to demonstrate the validity of the proposed methodology.

Path Planning Research of Soccer Robot Based on Fuzzy Theory

Aiming at the problem of path planning of soccer robot, based on the principle that the path curve should be smooth and the total length of the path should be short, the fuzzy control method to the whole velocity and the real-time rotational angle was proposed in this paper. The membership functions of fuzzy controller were optimized by golden mean principle. Simulating use the fuzzy control method and the fuzzy control method based on golden mean. Results show that the fuzzy controller optimized by golden mean has better control effect. Robot has better real-timing when avoiding obstacles. The global path will be shorter.

COMPARISON OF ANFIS BASED SSSC, STATCOM AND UPFC CONTROLLERS FOR TRANSIENT STABILITY IMPROVEMENT

This paper presents the comparative performance of neuro- Fuzzy controlled Voltage Source Converters (VSC) based Flexible AC Transmission System (FACTS) devices, such as Static Synchronous Series Compensator (SSSC), Static Synchronous Compensator (STATCOM), and Unified Power Flow Controller (UPFC) in terms of improvement in transient stability. In neuro-fuzzy control method the simplicity of fuzzy systems and the ability of training in neural networks have been combined. The training data set the parameters of membership functions in fuzzy controller. This Adaptive Network Fuzzy Inference System (ANFIS) can track the given input-output data in order to conform to the desired controller. The maximization of energy function of UPFC is used as an objective function to generate the training data. Proposed method is tested on a single machine infinitive bus system to confirm its performance through simulation. The results prove the noticeable influence of ANFIS controlled UPFC on increasing Critical Clearing Time (CCT) of system.

LMI-Based Stability Analysis of Fuzzy-Model-Based Control Systems Using Approximated Polynomial Membership Functions

Relaxed linear-matrix-inequality-based stability conditions for fuzzy-model-based control systems with imperfect premise matching are proposed. First, the derivative of the Lyapunov function, containing the product terms of the fuzzy model and fuzzy controller membership functions, is derived. Then, in the partitioned operating domain of the membership functions, the relations between the state variables and the mentioned product terms are represented by approximated polynomials in each subregion. Next, the stability conditions containing the information of all subsystems and the approximated polynomials are derived. In addition, the concept of the S-procedure is utilized to release the conservativeness caused by considering the whole operating region for approximated polynomials. It is shown that the well-known stability conditions can be special cases of the proposed stability conditions. Simulation examples are given to illustrate the validity of the proposed approach.

Minimum real time bang-bang fuzzy control system

Minimum-time control is desired for non-linear spacecraft?satellite attitude systems to save on board thruster fuel. The regulatory time depends on the initial attitude of the satellite. Bang-bang control of satellite attitude can be accomplished with Fuzzy Logic Controller (FLC) using Largest of Maxima (LOM) defuzzification technique. In case of fuzzy controller, earlier studies show that minimum response time depends on span of the fuzzy controller membership functions. This paper shows how the non-linear relation between the initial attitude of satellite and spans of the fuzzy controller membership functions are optimised to achieve minimum response time by using Nelder?Mead simplex search method. A practical demonstration of fuzzy bang-bang control is demonstrated here by controlling angular position of a single-axis attitude application. The pneumatic rotary actuator is controlled in real time using Matlab-simulink xPC target environment.