Ahmed Rubaai

Development and implementation of an adaptive fuzzy-neural-network controller for brushless drives

A brushless DC motor drive with a proposed adaptive fuzzy-neural-network controller is introduced in this paper. First, a neural network-based architecture is introduced for fuzzy logic control. The characteristic rules and their membership functions of fuzzy systems are represented as the processing nodes in the neural network structure. Then, the fuzzy rules and input/output of the system are tuned by the supervised gradient descent learning algorithm. Using an experimental setup, the performance of the proposed controller is evaluated under various operating conditions. Test results are presented and discussed in the paper. The presented controller is shown to be robust, adaptive and capable of learning. To demonstrate the effectiveness of the controller, a proportional-integral controller has been used to perform comparative studies with encouraging results.

Online identification and control of a DC motor using learning adaptation of neural networks

This paper tackles the problem of the speed control of a DC motor in a very general sense. Use is made of the power of feedforward artificial neural networks to capture and emulate detailed nonlinear mappings, in order to implement a full nonlinear control law. The random training for the neural networks is accomplished online, which enables better absorption of system uncertainties into the neural controller. An adaptive learning algorithm, which attempts to keep the learning rate as large as possible while maintaining the stability of the learning process is proposed. This simplifies the learning algorithm in terms of computation time, which is of special importance in real-time implementation. The effectiveness of the control topologies with the proposed adaptive learning algorithm is demonstrated. It is found that the proposed adaptive leaning mechanism accelerates training speed. Promising results have also been observed when the neural controller is trained in an environment contaminated with noise.

Design and Implementation of Parallel Fuzzy PID Controller for High-Performance Brushless Motor Drives: An Integrated Environment for Rapid Control Prototyping

This paper presents an integrated environment for the rapid prototyping of a robust fuzzy proportional-integral-derivative (PID) controller that allows rapid realization of novel designs. Both the design of the fuzzy PID controller and its integration with the classical PID in a global control system are developed. The architecture of the fuzzy PID controller is basically composed of three parallel fuzzy subcontrollers. Then, the parallel subcontrollers are grouped together to form the overall fuzzy PID controller. The fuzzy proportional, integral, and derivative gains are direct output from the parallel fuzzy subcontrollers and are derived in the error domain. Thus, the proposed architecture presents an alternative to control schemes employed so far. The integrated controller is formulated and implemented in real time, using the speed control of a brushless drive system as a test bed. The design, analysis, and implementation stages are carried out entirely using a dSPACE DS1104 digital-signal-processor-based real-time data acquisition control system and MATLAB/Simulink environment. Experimental results show that the proposed hybrid fuzzy PID controller produces superior control performance than the conventional PID controllers, particularly in handling nonlinearities and external disturbances.

DSP-Based Laboratory Implementation of Hybrid Fuzzy-PID Controller Using Genetic Optimization for High-Performance Motor Drives

This paper presents a real-time implementation of a genetic-based hybrid fuzzy-proportional-integral-derivative (PID) controller for industrial motor drives. Both the design of fuzzy-PID (FPID) controller and its integration with the conventional PID in global control system to produce a hybrid design are demonstrated. A genetic optimization technique is used to determine the optimal values of the scaling factors of the output variables of the FPID controller. The objective is to utilize the best attributes of the PID and FPID controllers to provide a controller which will produce better response than either the PID or FPID controller. The principle of the hybrid controller is to use a PID controller, which performs satisfactorily in most cases, while keeping in the background a FPID controller, which is ready to take over the PID controller when severe disturbances occur. The hybrid controller is formulated and implemented in real time, using the speed control of a brushless drive system as a testbed. The design, analysis, and implementation stages are carried out entirely using a dSPACE DS1104 digital-signal-processor-based real-time data acquisition control system and MATLAB/Simulink environment. Experimental results show that the proposed FPID controller-based genetic optimization produces better control performance than the conventional PID controllers, particularly in handling nonlinearities and external disturbances.

Experimental verification of a hybrid fuzzy control strategy for a high-performance brushless DC drive system

This paper presents the design and experiment of a hybrid fuzzy control scheme for a high performance brushless DC motor drive system. Both the design of the fuzzy controller and its integration with the proportional integral (PI) in a global control scheme are discussed. The principle of the proposed control scheme is to use a PI controller, which performs satisfactorily in most cases, while keeping in the background, a fuzzy controller, which, is ready to take over the PI controller when severe perturbations occur. Performance of the hybrid fuzzy-PI controller is evaluated through a laboratory implementation. The laboratory implementation is based on a linguistic fuzzy controller whose design is derived from the expert knowledge during disturbed phases. Experimental results have shown excellent tracking performance of the hybrid control system, and have convincingly demonstrated the usefulness of the hybrid fuzzy controller in high performance drives with uncertainties.

DSP-Based Real-Time Implementation of a Hybrid

An embedded hybrid Hinfin adaptive fuzzy control structure is implemented for trajectory tracking control of a brushless servo drive system. The control structure employs a fuzzy logic controller incorporating an Hinfin tracking controller via an acceleration feedback signal. The fuzzy logic controller is equipped with an adaptive-law-based Lyapunov synthesis approach to compensate for system uncertainty and random changes in the external load acting on the drive system. The proposed control structure is experimentally verified on a state-of-the-art dSPACE DS1104 digital signal processor (DSP)-based data acquisition and control system in a laboratory 1-hp brushless drive system. The controllers are first designed in Simulink. Then, the Real-Time Workshop is used to automatically generate optimized C code for real-time applications. Afterward, the interface between MATLAB/Simulink and the dSPACE DS 1104 allows the control algorithm to run on the hardware processor of the DSP. The result is a powerful testbed for the rapid design and implementation of the hybrid tracking controllers for a wide variety of operating conditions. Experimental results are provided to verify the effectiveness of the proposed controller. Considerable improvement in the performance generated by the hybrid controller is compared with the traditional Hinfin controller

H \infty

This paper presents the development of a fuzzy-neural-network (FNN) proportional-integral (PI)-/proportional-derivative (PD)-like controller with online learning for speed trajectory tracking of a brushless drive system. The design implements the novel use of the extended Kalman filter (EKF) to train FNN structures as part of the PI-/PD-like fuzzy design. The FNN structure has two parallel FNN PI-/PD-like controllers, each with four internal layers. EKF trains each FNN by modifying the weights and the membership function parameters. Thus, the proposed EKF-based architecture presents an alternative to control schemes employed so far. The objective is to replace the conventional PI-derivative (PID) controller with the proposed FNN PI-/PD-like controller with EKF learning mechanism. Comparisons of the algorithm performances provide evidence of improvement of the FNN PI-/PD-like controller over PID control. A test bench enables design implementation in the laboratory on hardware using a dSPACE DS1104 DSP and MATLAB/Simulink environment. Experimental testing results show that the proposed controller learns and robustly responds to a wide range of operating conditions in real time.

Adaptive Fuzzy Tracking Controller for Servo-Motor Drives

This paper describes a single-phase transformer design suitable for classroom use. The scope of this design is limited to the specification for the core and coils of the transformer. Both shell and core configured transformers are designed in this paper. A computer program is developed for the purpose of illustrating the design procedure and demonstrating how it works. The objective is to meet all performance requirements at minimum cost. >

EKF-Based PI-/PD-Like Fuzzy-Neural-Network Controller for Brushless Drives

This paper presents an adaptive parallel control architecture, using an artificial neural network (ANN) which is trained while the controller is operating online. The proposed control structure incorporates five-multilayer feedforward ANNs, which are online trained using the Marquardt-Levenberg least-squares learning algorithm. The five networks are used exclusively for system estimation. The estimation mechanism uses online training to learn the unknown model dynamics and estimate the rotor fluxes of an inverter-fed induction motor. Subsequently, the estimated stator currents are fed into an adaptive controller to track the desired stator current trajectories. The adaptive controller is constructed as a feedback signal (a nonlinear control law), depending on estimated stator currents supplied by the neural estimators and the desired reference trajectories to be tracked by the output. The control of the direct and quadrature components of the stator current successfully tracked a wide variety of reference trajectories after relatively short online training periods.

Computer aided instruction of power transformer design in the undergraduate power engineering class

This paper presents a successful implementation of a fuzzy logic controller structure for switch-mode power-stage dc-dc converters and evaluates experimentally its sensitivity for variable supply voltages and load resistance variations. The optimum topology of the controller structure is determined using experimental tests. An advanced test-bed system is used to evaluate the robustness capacities of the controller under varying loading conditions and input voltage variations. The experiment is performed using a low-cost microcontroller PIC16F877 to verify the design performance over a wide range of operating conditions. The controller shows very interesting tracking features and is able to cope with load changes and input voltage variations. The proposed controller structure is general and can be directly applied to any dc-dc converter topologies. The fuzzy controller structure is compared experimentally with the existing proportional-integral control used in industry. It yields a better dynamic performance without overshoot