Application of Learning Methodologies in Control of Power Electronics Drives J. L. da Silva Neto, L.G. Rolim, W. I. Suemitsu, L. O. A. P. Henriques, P.J.

Slides:



Advertisements
Similar presentations
IMPROVING DIRECT TORQUE CONTROL USING MATRIX CONVERTERS Technical University of Catalonia. Electronics Engineering Department. Colom 1, Terrassa 08222,
Advertisements

WP3 High Availability Drives Electrical Machines and Drives Research Group University of Sheffield Dr. Georges El Murr
Permanent Magnet Synchronous Motor Drive Using Hybrid PI Speed Controller With Inherent and Noninherent Switching Functions IEEE TRANSACTIONS ON MAGNETICS,
9.11. FLUX OBSERVERS FOR DIRECT VECTOR CONTROL WITH MOTION SENSORS
Hybrid Terminal Sliding-Mode Observer Design Method for a Permanent-Magnet Synchronous Motor Control System 教授 : 王明賢 學生 : 胡育嘉 IEEE TRANSACTIONS ON INDUSTRIAL.
Model of Permanent Magnet Synchronous Motor
DEVELOPMENT OF A METHOD FOR RELIABLE AND LOW COST PREDICTIVE MAINTENANCE Jacopo Cassina.
Department of Electrical Engineering Southern Taiwan University Robot and Servo Drive Lab. 2015/5/19 Reduction of Torque Ripple Due to Demagnetization.
WRSTA, 13 August, 2006 Rough Sets in Hybrid Intelligent Systems For Breast Cancer Detection By Aboul Ella Hassanien Cairo University, Faculty of Computer.
Development of a Neuro Fuzzy Technique for Position Sensor Elimination in a SRM L. O. Henriques, L.G. Rolim, W. I. Suemitsu, P.J. Costa Branco.
SOUTHERN TAIWAN UNIVERSITY Department of Electrical Engineering DESIGN OF FUZZY PID CONTROLLER FOR BRUSHLESS DC (BLDC)MOTOR Student: Dang Thanh Trung Subject:
Fuzzy Adaptive Internal Model Control Schemes for PMSM Speed-Regulation System Shihua Li; Hao Gu Industrial Informatics, IEEE Transactions on Volume: 8,
8/17/ Introduction to Neuro-fuzzy and Soft computing G.Anuradha (Lecture 1)
Neuro-fuzzy Systems Xinbo Gao School of Electronic Engineering Xidian University 2004,10.
A Computational Semiotics Approach for Soft Computing Ricardo R. Gudwin Fernando A.C. Gomide DCA-FEEC-UNICAMP.
CHAPTER 12 ADVANCED INTELLIGENT SYSTEMS © 2005 Prentice Hall, Decision Support Systems and Intelligent Systems, 7th Edition, Turban, Aronson, and Liang.
A Shaft Sensorless Control for PMSM Using Direct Neural Network Adaptive Observer Authors: Guo Qingding Luo Ruifu Wang Limei IEEE IECON 22 nd International.
Intelligent Control Applied to Motor Drives Reference: 1. Selected technical papers. 2. Modern Power Electronics and AC Drives, B. K. Bose, Prentice Hall,
Robust Fault analysis Technique for Permanent Magnet DC Motor In safety Critical Applications Wathiq Abed Wathiq Abed Supervisor - Sanjay Sharma University.
1 An FPGA-Based Novel Digital PWM Control Scheme for BLDC Motor Drives 學生 : 林哲偉 學號 :M 指導教授 : 龔應時 IEEE TRANSACTIONS ON INDUSTRIAL ELECTRONICS, VOL.
System/Plant/Process (Transfer function) Output Input The relationship between the input and output are mentioned in terms of transfer function, which.
Shihua Li; Hao Gu Industrial Informatics, IEEE Transactions on Volume: 8, Issue: 4 Digital Object Identifier: /TII Publication Year:
Southern Taiwan University of Science and Technology
RECENT DEVELOPMENTS OF INDUCTION MOTOR DRIVES FAULT DIAGNOSIS USING AI TECHNIQUES 1 Oly Paz.
The Design of High-Speed High-Power Density Machines Liping Zheng.
Sensorless Sliding-Mode Control of Induction Motors Using Operating Condition Dependent Models 教 授: 王明賢 學 生: 謝男暉 南台科大電機系.
T L = 0.5 Fig. 6. dq-axis stator voltage of mathematical model. Three Phase Induction Motor Dynamic Modeling and Behavior Estimation Lauren Atwell 1, Jing.
Fuzzy Logic Control of Blood Pressure During Anesthesia
Approaches to task solution of complex objects identification as example of an induction motor Mubarakzyanov N.R.
Performance investigation of modified hysteresis current controller with the permanent magnet synchronous motor drive A.N. Tiwari1 P. Agarwal2 S.P. Srivastava2;
Features of Biological Neural Networks 1)Robustness and Fault Tolerance. 2)Flexibility. 3)Ability to deal with variety of Data situations. 4)Collective.
Course presentation: FLA Fuzzy Logic and Applications 4 CTI, 2 nd semester Doru Todinca in Courses presentation.
Sensorless Control of the Permanent Magnet Synchronous Motor Using Neural Networks 1,2Department of Electrical and Electronic Engineering, Fırat University.
Features of Biological Neural Networks 1)Robustness and Fault Tolerance. 2)Flexibility. 3)Ability to deal with variety of Data situations. 4)Collective.
© 2005 Prentice Hall, Decision Support Systems and Intelligent Systems, 7th Edition, Turban, Aronson, and Liang 12-1 Chapter 12 Advanced Intelligent Systems.
Control systems KON-C2004 Mechatronics Basics Tapio Lantela, Nov 5th, 2015.
ELECTRIC DRIVES INTRODUCTION TO ELECTRIC DRIVES. Electrical Drives Drives are systems employed for motion control Require prime movers Drives that employ.
Model of Reluctance Synchronous Motor
Chapter 1: Introduction to Neuro-Fuzzy (NF) and Soft Computing (SC)
Authors : Chun-Tang Chao, Chi-Jo Wang,
Professor : Ming – Shyan Wang Department of Electrical Engineering Southern Taiwan University Thesis progress report Sensorless Operation of PMSM Using.
Disturbance rejection control method
Department of Electrical Engineering Southern Taiwan University of Science and Technology Robot and Servo Drive Lab. 2016/2/21 A Novel Rotor Configuration.
Intelligent Control Methods Lecture 1: Introduction. Reasons for ICM, Basic Concepts Slovak University of Technology Faculty of Material Science and Technology.
A field of study that encompasses computational techniques for performing tasks that require intelligence when performed by humans. Simulation of human.
Mohammed Mahdi Computer Engineering Department Philadelphia University Monzer Krishan Electrical Engineering Department Al-Balqa.
Investigation on the Bipolar-Starting and Unipolar-Running Method to Drive a Brushless DC Motor at High Speed with Large Starting Torque PREM, Department.
Control Engineering. Introduction What we will discuss in this introduction: – What is control engineering? – What are the main types of control systems?
Department of Electrical Engineering Southern Taiwan University Robot and Servo Drive Lab. 2016/6/13 Design of a Synchronous Reluctance Motor Drive T.
A Presentation on Adaptive Neuro-Fuzzy Inference System using Particle Swarm Optimization and it’s Application By Sumanta Kundu (En.R.No.
A PID Neural Network Controller
VIDYA PRATISHTHAN’S COLLEGE OF ENGINEERING, BARAMATI.
Han Ho Choi, Member, IEEE, Nga Thi-Tuy Vu, and Jin-Woo Jung IEEE TRANSACTIONS ON INDUSTRIAL ELECTRONICS, VOL. 59, NO. 8, AUGUST 2012,pp /9/241.
CONTINUOUS-DRIVE ACTUATORS**
Adviser: Ming-Shyan Wang Student: Feng-Chi Lin
Soft Computing Introduction.
Study on maximum torque generation for sensorless controlled brushless DC motor with trapezoidal back EMF.
P. Janik, Z. Leonowicz, T. Lobos, Z. Waclawek
Hak-Jun Lee and Seung-Ki Sul Power Electronics Laboratory
TECHNOLOGY GUIDE FOUR Intelligent Systems.
Improved Speed Estimation in Sensorless PM Brushless AC Drives
Stepper motor.
ECE 382. Feedback Systems Analysis and Design
BEIJING INSTITUTE OF TECHNOLOGY
EXPERT SYSTEMS.
Chapter 12 Advanced Intelligent Systems
Mathematical Model and Characteristics Analysis of the BLDC motor
Tuğçe DEMİRDELEN INTECH 2017 A Fuzzy Neural Network Approach
Objective: The main aim of this project is to control the speed of the brush less direct current motor based on the single current sensor is proposed.
Department of Electrical Engineering National Central University
Presentation transcript:

Application of Learning Methodologies in Control of Power Electronics Drives J. L. da Silva Neto, L.G. Rolim, W. I. Suemitsu, L. O. A. P. Henriques, P.J. Costa Branco, M. G. Simões

Presentation Introduction –Artificial Intelligence Fuzzy Control of Synchronous Motors Learning controller for torque ripple reduction in SR drives Conclusions

Introduction Learning methodologies: Expert Systems: knowledge represented at a symbolic level. Genetic Algorithms: Computational models based on the theory of evolution (fitness, mutation and reproduction) Fuzzy Logic Systems: linguistic technique Neural Networks: mathematical model of artificial neurons

Fuzzy Logic and/or Neural Networks Some characteristics: –Capability to model unclearly correlated information –Parameter estimation (e.g torque and flux) –In last ten years, appliance drives have be increasely use a Fuzzy and Neural systems. –Replacement of classical controllers by controllers with learning methodologies.

Electrical Drive Control Evolution of digital signal processors, and circuit integration, make possible the implementation of complex control Several types of motors can use the features of “Intelligent” drives: –AC machines (Induction Motors, Synchronous Machine) –Switched Reluctance Motors

Fuzzy Control of Synchronous Motors Fuzzy Logic Adaptation Mechanism (FLAM) –Objective is to change the rule definitions in the fuzzy logic controller (FLC) base table, according the comparison between the reference model and the system output. –Composed by a fuzzy inverse model and knowledge base modifier –It was used to prove the effectiveness of the control in a TMS320C30 DSP-based speed fuzzy control of a permanent magnet synchronous motor (PMSM)

KeKe z -1 e ee  + KeKe PMSM Reference Model W mm +  rr KK  + emem emem KmKm KmKm z -1 Fuzzy Inverse Model +  KuKu  Fuzzy Controller Fuzzy Learning of Synchronous Motors

Experimental result – Tracking Problem

Experimental result – Regulation Problem

Neuro Fuzzy Control of SR Drives  Low cost (material and manufacturing)  Good thermal behavior  Fault tolerance  Reliable  Easy to repair  Torque ripple  Nonlinear model

Neuro Fuzzy Control of SR Drives Input signals –Motor speed –Rotor position –Reference current Output: current increment (  I) Training signal: oscillating torque

Neuro Fuzzy Control of SR Drives

Neuro Fuzzy Position Estimation

Neuro Fuzzy position estimation

Conclusions The adaptive fuzzy strategy presented applied for PMSM drives has proved to be very effective when applied for motion control applications. It has been implemented on a speed control of a PM motor, it can be extended for other kinds closed loop motor control. One highlighted characteristic of this algorithm is that it can compensate non-linear load variations without the need of a completely modeled load.

Conclusions For the SR drive the neuro-fuzzy strategy has shown to be effective to reduce torque oscillations The adaptive algorithm automatically learns a current profile without the need of observers and state estimators.