EPE Association: EPE 2003 - Topic 05b: Fuzzy Control, Neuronal Control

EPE 2003 - Topic 05b: Fuzzy Control, Neuronal Control
You are here: EPE Documents > 01 - EPE & EPE ECCE Conference Proceedings > EPE 2003 - Conference > EPE 2003 - Topic 05: APPLICATION OF CONTROL METHODS TO ELECTRICAL SYSTEMS > EPE 2003 - Topic 05b: Fuzzy Control, Neuronal Control

   [return to parent folder]

   A novel fuzzy direct torque control
By D. Pirjan; F. Labrique; D. Grenier [View]
[Download]

Abstract: In the paper, the concept, the implementation and the experimental results of a fuzzy direct torque control (FDTC) scheme for a PWM-inverter fed induction motor drive are presented. Two Mamdani’s fuzzy logic controllers (FLC) are used for controlling the amplitude and the position of the stator voltage vector (the voltage vector is given by its modulus |Us| and position q). The inverter switch states are determined by a classical PWM modulator on the basis of the value of this vector. For the fuzzification of the flux error and the torque error only two classes: INCREASE/DECREASE are used.

   Vector control of induction motor drive using ANN-based VPWM
By M. Kuchar; P. Brandstetter; P. Palacky [View]
[Download]

Abstract: The paper deals with development, simulation and DSP implementation of space vector modulator based on artificial neural network. the modulator is designed for a voltage source inverter utilization. In the contribution an explanation of presented ANN-based VSI-VPWM is described. Main features and advantages of used algorithm are summarized too. Entire AC electrical drive consists of frequency converter, induction motor and microprocessor control system. In the paper a description of the control system with TMS 320C40 DSP are also given. Very important part of the development is simulation, because it is necessary to verify rightness of the algorithm. Entire drive has been simulated in progrgam Matlab with Simulink toolbox. Then presented method has been implemented to vector control of induction motor too and it has been obtained experimental results from the drive. In the end of the paper there will be summarized the main advantages and the behaviour of the drive.

   Neuro-fuzzy control for a VSC-based HVDC link
By X.I. Koutiva; T.D. Vrionis; N.A. Vovos; G.B. Giannakopoulos [View]
[Download]

Abstract: This paper describes the control strategy of a High Voltage Direct Current (HVDC) link based on Voltage Sourced Converters (VSC), which uses neuro-fuzzy logic, a combination of neural networks and fuzzy logic. Computational intelligence techniques, such as fuzzy logic, neural networks and genetic algorithms, are recently attracting many control design engineers in applications of power systems, as they do not need a detailed mathematical model of the system to be controlled, but just prior knowledge of the behaviour of the system. With an Adaptive, Neuro-Fuzzy Inference System (ANFIS), the link manages to feed a weak ac network with the power derived from a Wind Farm (WF) of induction generators, which is known to be a fluctuating and unstable power source. The system was studied under steady state and transient conditions using the simulation program PSCAD/EMTDC with the Fuzzy Logic toolbox of MATLAB. The results show that the system supplies efficiently the ac network with the power of the WF. Also, due to the ability of the control system to adjust the stator frequency of the induction generators in relation to the wind velocity, maximum power absorption of the WF is achieved.

   Fuzzy logic in vector controlled induction motor drive
By L. Stepanec; P. Brandstetter [View]
[Download]

Abstract: This paper deals with vector-controlled induction motor drive which using fuzzy logic as a part of artificial intelligence. There are three phases: development, simulation and DSP implementation which are discussed in this paper. In the first part of paper there is described fuzzy logic and development to given problem. Next there is described used control structure. It has been realized important simulations, which confirm the rightness of proposed structure and good behaviour of developed fuzzy controller. Of course simulation results are also given. In the end part of the paper is presented implementation to control system with DSP TMS 320C40 and experimental results. Explanation of presented advantages of fuzzy logic is described and main features of used method are also summarized.

   Neural network control of DC-DC static converters
By J-N. Marie-Françoise; H. Gualous; A. Berthon [View]
[Download]

Abstract: Automotive application will use in the future different kinds of sources to provide energy or to store energy: fuel cells, batteries, ultra capacitors. DC-DC converters are needed to connect these voltage sources to a common DC bus. Electrical energy dispatching is a critical way to optimize the system. This study proposes artificial neural network as a good approach to control a boost DC-DC converter. A Levenberg-Marquardt learning algorithm is employed for adjustment of the network weights and bias. The artificial neural network (ANN) is training by the hypothesis model NARX.

   Speed control of a permanent magnet synchronous motor, based on a quasi-fuzzy controller
By C. Voloºencu [View]
[Download]

Abstract: The paper presents a speed control for permanent magnet synchronous motors, based on a quasi-fuzzy controller. The quasi-fuzzy controller is a PI fuzzy controller, which has a non-linear correction made to assure stability of the speed control system. The fuzzy block is implemented using a look-up table, with two inputs and one output. The control system is developed for a DSP platform.

   An adaptive fuzzy neural network control system for DC drive
By T. Or³owska-Kowalska; K. Jaszczak [View]
[Download]

Abstract: Speed control of electrical drives are often made difficult by nonlinearities, difficulties in proper system parameters identification, unpredictable parameter variations and external load disturbances. As a possibility a model reference adaptive speed control using on-line trained fuzzy neural network (FNN) is presented. In this control method fuzzy-logic controller is equipped with additional option for on-line tuning its chosen parameters. In the paper PI-type fuzzy logic controller is used as the direct speed controller, whose connective weights are trained on-line according to the error between the states of the plant and the reference model. The FNN speed controller is on-line tuned to preserve a favourable model-following characteristics under various operating conditions. The analysis, design, simulation and experimental implementation and comparison of the proposed control schemes are described.

EPE 2003 - Topic 05b: Fuzzy Control, Neuronal Control
You are here: EPE Documents > 01 - EPE & EPE ECCE Conference Proceedings > EPE 2003 - Conference > EPE 2003 - Topic 05: APPLICATION OF CONTROL METHODS TO ELECTRICAL SYSTEMS > EPE 2003 - Topic 05b: Fuzzy Control, Neuronal Control
	[return to parent folder]

	A novel fuzzy direct torque control By D. Pirjan; F. Labrique; D. Grenier	[View] [Download]
Abstract: In the paper, the concept, the implementation and the experimental results of a fuzzy direct torque control (FDTC) scheme for a PWM-inverter fed induction motor drive are presented. Two Mamdani’s fuzzy logic controllers (FLC) are used for controlling the amplitude and the position of the stator voltage vector (the voltage vector is given by its modulus \|Us\| and position q). The inverter switch states are determined by a classical PWM modulator on the basis of the value of this vector. For the fuzzification of the flux error and the torque error only two classes: INCREASE/DECREASE are used.

	Vector control of induction motor drive using ANN-based VPWM By M. Kuchar; P. Brandstetter; P. Palacky	[View] [Download]
Abstract: The paper deals with development, simulation and DSP implementation of space vector modulator based on artificial neural network. the modulator is designed for a voltage source inverter utilization. In the contribution an explanation of presented ANN-based VSI-VPWM is described. Main features and advantages of used algorithm are summarized too. Entire AC electrical drive consists of frequency converter, induction motor and microprocessor control system. In the paper a description of the control system with TMS 320C40 DSP are also given. Very important part of the development is simulation, because it is necessary to verify rightness of the algorithm. Entire drive has been simulated in progrgam Matlab with Simulink toolbox. Then presented method has been implemented to vector control of induction motor too and it has been obtained experimental results from the drive. In the end of the paper there will be summarized the main advantages and the behaviour of the drive.

	Neuro-fuzzy control for a VSC-based HVDC link By X.I. Koutiva; T.D. Vrionis; N.A. Vovos; G.B. Giannakopoulos	[View] [Download]
Abstract: This paper describes the control strategy of a High Voltage Direct Current (HVDC) link based on Voltage Sourced Converters (VSC), which uses neuro-fuzzy logic, a combination of neural networks and fuzzy logic. Computational intelligence techniques, such as fuzzy logic, neural networks and genetic algorithms, are recently attracting many control design engineers in applications of power systems, as they do not need a detailed mathematical model of the system to be controlled, but just prior knowledge of the behaviour of the system. With an Adaptive, Neuro-Fuzzy Inference System (ANFIS), the link manages to feed a weak ac network with the power derived from a Wind Farm (WF) of induction generators, which is known to be a fluctuating and unstable power source. The system was studied under steady state and transient conditions using the simulation program PSCAD/EMTDC with the Fuzzy Logic toolbox of MATLAB. The results show that the system supplies efficiently the ac network with the power of the WF. Also, due to the ability of the control system to adjust the stator frequency of the induction generators in relation to the wind velocity, maximum power absorption of the WF is achieved.

	Fuzzy logic in vector controlled induction motor drive By L. Stepanec; P. Brandstetter	[View] [Download]
Abstract: This paper deals with vector-controlled induction motor drive which using fuzzy logic as a part of artificial intelligence. There are three phases: development, simulation and DSP implementation which are discussed in this paper. In the first part of paper there is described fuzzy logic and development to given problem. Next there is described used control structure. It has been realized important simulations, which confirm the rightness of proposed structure and good behaviour of developed fuzzy controller. Of course simulation results are also given. In the end part of the paper is presented implementation to control system with DSP TMS 320C40 and experimental results. Explanation of presented advantages of fuzzy logic is described and main features of used method are also summarized.

	Neural network control of DC-DC static converters By J-N. Marie-Françoise; H. Gualous; A. Berthon	[View] [Download]
Abstract: Automotive application will use in the future different kinds of sources to provide energy or to store energy: fuel cells, batteries, ultra capacitors. DC-DC converters are needed to connect these voltage sources to a common DC bus. Electrical energy dispatching is a critical way to optimize the system. This study proposes artificial neural network as a good approach to control a boost DC-DC converter. A Levenberg-Marquardt learning algorithm is employed for adjustment of the network weights and bias. The artificial neural network (ANN) is training by the hypothesis model NARX.

	Speed control of a permanent magnet synchronous motor, based on a quasi-fuzzy controller By C. Voloºencu	[View] [Download]
Abstract: The paper presents a speed control for permanent magnet synchronous motors, based on a quasi-fuzzy controller. The quasi-fuzzy controller is a PI fuzzy controller, which has a non-linear correction made to assure stability of the speed control system. The fuzzy block is implemented using a look-up table, with two inputs and one output. The control system is developed for a DSP platform.

	An adaptive fuzzy neural network control system for DC drive By T. Or³owska-Kowalska; K. Jaszczak	[View] [Download]
Abstract: Speed control of electrical drives are often made difficult by nonlinearities, difficulties in proper system parameters identification, unpredictable parameter variations and external load disturbances. As a possibility a model reference adaptive speed control using on-line trained fuzzy neural network (FNN) is presented. In this control method fuzzy-logic controller is equipped with additional option for on-line tuning its chosen parameters. In the paper PI-type fuzzy logic controller is used as the direct speed controller, whose connective weights are trained on-line according to the error between the states of the plant and the reference model. The FNN speed controller is on-line tuned to preserve a favourable model-following characteristics under various operating conditions. The analysis, design, simulation and experimental implementation and comparison of the proposed control schemes are described.