A Self-Organizing Fuzzy Controller Using Neural Networks

This paper proposes a design approach for a self-organizing self-tuning fuzzy logic controller, and is applied to the design of a field oriented drive system. The basic structure of a fuzzy logic controller is outlined and the design problems associated with the conventional trial-and-error schemes are addressed. The suitability of the genetic algorithm optimization technique as a means to determine and optimize the fuzzy logic controller design is discussed. In the proposed approach normalization factors and/or membership function parameters and/or the controller policy, are translated into bit-strings. These bit-strings are processed by the genetic algorithm and if the selection process as well as the objective function are chosen properly, a near-optimal solution can be found. To examine the efficiency of the proposed approach, a self-tuning and self-organizing fuzzy logic controller for an indirect field oriented induction motor drive is designed in both a sequential and a concurrent manner. A particular objective function (i.e., a performance index) is chosen to achieve a high dynamic performance. The simulation results demonstrate a significant enhancement in shortening the development time, and improving system performance over a manually tuned fuzzy logic controller.

We present a new technique to the design and real-time implementation of fuzzy control system basedon digital signal processors in order to improve the precision and robustness for system of industrial robot in this paper. The need to meet demanding control requirement in increasingly complex dynamical control systems under significant uncertainties, leads toward design of intelligent manipulation robots. The TMS320C80 is used in implementing real time fuzzy control to provide an enhanced motion control for robot manipulators. In this paper, a Self-Organizing Fuzzy Controller for the industrial robot manipulator with a actuator located at the base is studied. A fuzzy logic composed of linguistic conditional statements is employed by defining the relations of input-output variables of the controller. In the synthesis of a Fuzzy Logic Controller, one of the most difficult problems is the determination of linguistic control rules from the human operators. To overcome this difficult Self-Organizing Fuzzy Controller is proposed for a hierarchical control structure consisting of basic and high levels that modify control rules. The proposed Self-Organizing Fuzzy Controller scheme is simple in structure, fast in computation, and suitable for implementation of real-time control. Performance of the SOFC is illustrated by simulation and experimental results for a Dual-Arm robot with eight joints.

A new design method of on-line learning self-organizing fuzzy logic controller is proposed. The proposed model reference self-organizing fuzzy logic control system contains two sets of fuzzy inference logic; which are the fuzzy controller and the rule modifier. A new learning method of the rule modifier, based on a fuzzy learning algorithm, is developed. The modification value of each rule is based on the fuzzy firing weight, so the learning algorithm can proceed reasonably. The proposed design method can be applied for on-line learning real-time control and can start to work even the control values of all rules are initiated from zeros.

A power system stabilization technique with an on-line self-organizing fuzzy logic controller is developed to enhance the damping of low frequency oscillation in a power system. The frequency deviation of a synchronous machine is utilized to calculate the stabilizing signal. Control rules and membership functions for the fuzzy logic controller are generated automatically without using any plant model. The generated rules are stored in the fuzzy rule space and updated on-line by a self-organizing procedure. To show the effectiveness of the proposed controller, the comparison with a conventional controller is made for a single-machine infinite-bus system.

A self-organizing fuzzy controller (SOFC) is proposed to control an active suspension system and evaluate its control performance. In complicated nonlinear system control, the SOFC continually updates the learning strategy in the form of fuzzy rules during the control process. The learning rate and the weighting distribution value of the controller are hard to regulate, so its fuzzy control rules may be excessively modified such that the system response generally causes an oscillatory phenomenon. Two fuzzy-logic controllers were designed according to the system output error and the error change, and introduced to the SOFC to determine the appropriate parameters of the learning rate and the weighting distribution, to eliminate this oscillation. This new modifying self-organizing fuzzy-control approach can effectively improve the control performance of the system, reduce the time consumed to establish a suitable fuzzy rule table, and support practically convenient fuzzy-controller applications in an active suspension control system, as verified experimentally.

Attempts are being made to enhance the drive performance by intelligent control using fuzzy logic (FL) and neural network techniques. One of the frequently discussed applications of artificial intelligence in control is the replacement of a standard proportional plus integral (PI) speed controller with an FL or artificial neural network (ANN) speed controller. Regardless of all the work, it appears that a thorough comparison of the drive behavior under PI, FL, and ANN speed control is necessary. This article attempts to compare PI, fuzzy, and ANN controllers that are implemented in an embedded system for closed-loop speed control of DC drive fed by a buck-type DC–DC power converter. The PI controller is designed based on the small signal modeling of the system. The PI-like fuzzy controller structure is considered for comparison. Two ANN controllers are designed. One controller uses training data obtained from the simulation of a fuzzy controller and the other uses training data from the simulation of a PI controller. The performance of the controllers is studied for a variety of operating conditions, such as step change in speed command and step change in load torque. The parameters selected for the comparison are the steady-state error and the rise time of the response. It is shown that ANN speed controllers provide a superior speed response in terms of rise time and the steady-state error compared to PI and FL controllers. This advantage arises from the fact that the neural network has the property of generalization and the control surface of the neural controller is smooth. The designed neural network controller is simple, with three neurons only, and so it is best suited for embedded system implementation. It is also found that the ANN controller trained with the training data from a PI controller has a better response compared to the ANN controller trained with data from a fuzzy controller.

A self-organizing fuzzy controller to augment a sliding-mode control (SOFSMC) scheme for a class of nonlinear systems is proposed. The motivation behind this scheme is to combine the best features of self-organizing fuzzy control and sliding-mode control to achieve rapid and accurate tracking control of a class of nonlinear systems. The chatter encountered by most sliding-mode control schemes is greatly alleviated without sacrificing invariant properties. A stability analysis is presented; the design guidelines and the class of applicable systems are clearly identified. To verify the scheme, the authors performed experiments on its implementation in a magnetic levitation system. The results show that both alleviation of chatter and robust performance are achieved; the advantages of the scheme are indicated in comparison with the conventional sliding-mode design. >

In this paper, a semi-active control method for seismically excited nonlinear benchmark buildings equipped with controllable fluid viscous dampers is presented and evaluated. A Fuzzy Logic Controller (FLC) is designed to alter the damping coefficient of controllable viscous dampers during an earthquake. A Genetic Algorithm (GA) is employed to find optimum fuzzy controller rules, as well as adjusting the membership functions to minimize the overall damage index. This combination of a Genetic algorithm and a Fuzzy Logic Controller (GFLC) is also used to minimize the peak value of the top story displacement response, in order to verify the effectiveness of minimizing displacement on the damage index. The effectiveness of the FLC is verified and illustrated using the simulated response of 3-story and 20-story full-scale nonlinear benchmark buildings excited by several historical earthquake records, through a computer simulation on MATLAB. For comparison, a Linear Quadratic Gaussian (LQG) active controller is designed to minimize the peak value of the top story displacement response. Moreover, the results of a study that has used Self-Organizing Fuzzy Logic Controllers (SOFLC) with active actuators are used. The results demonstrate that the GFLCs are quite effective in overall damage reduction for a wide range of motions, compared with the SOFLC and LQG controllers.

This paper deals with the real time implementation of Fuzzy logic controllers on a liquid level control system. By applying fuzzy logic controller based on two different rule sets, it is shown that the selection of proper rules is critical for acheiving good system performance. The ability of the Self-organising fuzzy logic controller(SOFLC) to learn and modify a crude set of rules to acheive a good performance is demonstrated. The SOFLC algorithm used in this work needs less computation time and hence suitable for real time control applications.

A computer screen-based simulator for hierarchical fuzzy logic monitoring and control of depth of anaesthesia

Aiming at the existing problems of conventional substation voltage and reactive power integrated control method, a new fuzzy logic based dynamic reactive power boundary voltage and reactive power integrated control method is proposed. Fuzzy logic control rules, membership function, dynamic reactive power boundary and system structure are introduced. In accordance with this fuzzy logic control strategies, decoupling control of voltage and reactive power in tight coupled zone can be obtained. Simulation results indicate that this approach shows better effect compared with the conventional nine-area control method, the adjust times of transformer tap and capacitors can be reduced effectively to increase the service life time of the transformer tap changer and capacitor switch. This fuzzy logic control method can improve the performance index of the substation voltage and reactive power integrated control device and also preferably adapted to the load characteristics through the dynamic reactive power boundary.

Fuzzy logic controllers (FLC's) have the following advantages over the conventional controllers: they are cheaper to develop, they cover a wider range of operating conditions, and they are more readily customizable in natural language terms. A self-organizing fuzzy controller can automatically refine an initial approximate set of fuzzy rules. Application of PI-type fuzzy controller increases the quality factor. In this paper, the voltage raising type-pulse controller is considered. Two types of fuzzy controllers used for the control of boost converter are investigated; the simulation results confirm the above mentioned advantages. In order to prove the dynamic characteristics of the PID fuzzy controller being fast and robust, simulation studies using PSIM program are carried out and compared to the results of the conventional loop gain design method for which MATLAB program is used.

This paper presents a fuzzy logic control strategy on four-wheel steering(4WS) vehicle based on a multi-body vehicle dynamic model. The multi-body vehicle dynamic model based on ADAMS can accurately predict the dynamics performance of the vehicle. Fuzzy logic is applied to track the yaw velocity of the two degrees of freedom ideal model through the co-simulation of ADAMS and Matlab Fuzzy control unit with the optimized membership function. The fuzzy control parameters are optimized and analyzed by a combined optimization algorithm (Genetic Algorithm (GA) and Nonlinear Programming Quadratic Line search (NLPQL) method) combined with response surface model (RSM). Single lane change test is chosen to validate the fuzzy control logic strategy. Simulation result shows that four-wheel steering vehicle with the fuzzy control logic strategy can improve vehicle handling stability greatly comparing with traditional front wheel steering.

In this study, interval type2 fuzzy logic (IT2FL) and PID controller is designed for swing-up position control of double inverted pendulum (DIP) system. The double inverted pendulum system consists of two rigid bars connected by a revolute joint. Mass of the revolute joint is included in the dynamic model.Rigid bars in the system are assumed to experience planar motion. The pendulum system is connected to the base by means of a revolute joint. Torque provided through a motor mounted to the base is used for position control of the system. PID (Proportional-Derivative-Integral) and interval type2 fuzzy logic controllers are developed by using the same performance criteria for position control of double inverted pendulum system. IT2FL controller is similar with type1 fuzzy logic controller. IT2FL system provides soft decision boundaries, whereas a type-1 fuzzy logic system provides a hard decision boundary. Membership function in interval type2 fuzzy logic set as an area called Footprint of Uncertainty (FOU) which limited by two type1 membership function those are upper membership function (UMF) and lower membership function (LMF).System behaviour is obtained by computer simulation using developed controllers respectively. Computer simulation results are compared in order to evaluate applicability of developed controllers. MATLAB/Simulink software is used in computer simulations.

In this chapter, the design and implementation of Self-Organizing Fuzzy Logic Controller (SOFLC) is explored with a particular application to control a multivariable model of anesthesia. A concept called decomposition of multivariable self-organizing fuzzy logic structure is proposed in this chapter. Hence, the basic forms of a simple 2 terms SOFLC to a multi-term complex multi-input/multi-output (MIMO) controller will be presented. Different design strategies of MIMO will be outlined and the application of SOFLC systems to muscle relaxation and depth of anesthesia control will be explored in the simulations. After comparison with four different MIMO controllers, the successful simulation results have given confidence to perform on-line clinical trials at the operating theatre in the near future.