KR20040097021A - Adaptive FNN Control System for High Performance of Induction Motor - Google Patents

Adaptive FNN Control System for High Performance of Induction Motor Download PDF

Info

Publication number
KR20040097021A
KR20040097021A KR1020040082889A KR20040082889A KR20040097021A KR 20040097021 A KR20040097021 A KR 20040097021A KR 1020040082889 A KR1020040082889 A KR 1020040082889A KR 20040082889 A KR20040082889 A KR 20040082889A KR 20040097021 A KR20040097021 A KR 20040097021A
Authority
KR
South Korea
Prior art keywords
controller
adaptive
induction motor
speed
fnn
Prior art date
Application number
KR1020040082889A
Other languages
Korean (ko)
Inventor
정동화
차영두
이홍균
이정철
Original Assignee
순천대학교 산학협력단
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by 순천대학교 산학협력단 filed Critical 순천대학교 산학협력단
Priority to KR1020040082889A priority Critical patent/KR20040097021A/en
Publication of KR20040097021A publication Critical patent/KR20040097021A/en

Links

Classifications

    • H—ELECTRICITY
    • H02—GENERATION; CONVERSION OR DISTRIBUTION OF ELECTRIC POWER
    • H02P—CONTROL OR REGULATION OF ELECTRIC MOTORS, ELECTRIC GENERATORS OR DYNAMO-ELECTRIC CONVERTERS; CONTROLLING TRANSFORMERS, REACTORS OR CHOKE COILS
    • H02P21/00—Arrangements or methods for the control of electric machines by vector control, e.g. by control of field orientation
    • H02P21/0003—Control strategies in general, e.g. linear type, e.g. P, PI, PID, using robust control
    • H02P21/001—Control strategies in general, e.g. linear type, e.g. P, PI, PID, using robust control using fuzzy control
    • H—ELECTRICITY
    • H02—GENERATION; CONVERSION OR DISTRIBUTION OF ELECTRIC POWER
    • H02P—CONTROL OR REGULATION OF ELECTRIC MOTORS, ELECTRIC GENERATORS OR DYNAMO-ELECTRIC CONVERTERS; CONTROLLING TRANSFORMERS, REACTORS OR CHOKE COILS
    • H02P21/00—Arrangements or methods for the control of electric machines by vector control, e.g. by control of field orientation
    • H02P21/0003—Control strategies in general, e.g. linear type, e.g. P, PI, PID, using robust control
    • H02P21/0014—Control strategies in general, e.g. linear type, e.g. P, PI, PID, using robust control using neural networks
    • H—ELECTRICITY
    • H02—GENERATION; CONVERSION OR DISTRIBUTION OF ELECTRIC POWER
    • H02P—CONTROL OR REGULATION OF ELECTRIC MOTORS, ELECTRIC GENERATORS OR DYNAMO-ELECTRIC CONVERTERS; CONTROLLING TRANSFORMERS, REACTORS OR CHOKE COILS
    • H02P21/00—Arrangements or methods for the control of electric machines by vector control, e.g. by control of field orientation
    • H02P21/14—Estimation or adaptation of machine parameters, e.g. flux, current or voltage
    • H02P21/18—Estimation of position or speed
    • H—ELECTRICITY
    • H02—GENERATION; CONVERSION OR DISTRIBUTION OF ELECTRIC POWER
    • H02P—CONTROL OR REGULATION OF ELECTRIC MOTORS, ELECTRIC GENERATORS OR DYNAMO-ELECTRIC CONVERTERS; CONTROLLING TRANSFORMERS, REACTORS OR CHOKE COILS
    • H02P27/00—Arrangements or methods for the control of AC motors characterised by the kind of supply voltage
    • H02P27/04—Arrangements or methods for the control of AC motors characterised by the kind of supply voltage using variable-frequency supply voltage, e.g. inverter or converter supply voltage
    • H02P27/06—Arrangements or methods for the control of AC motors characterised by the kind of supply voltage using variable-frequency supply voltage, e.g. inverter or converter supply voltage using dc to ac converters or inverters
    • H02P27/08—Arrangements or methods for the control of AC motors characterised by the kind of supply voltage using variable-frequency supply voltage, e.g. inverter or converter supply voltage using dc to ac converters or inverters with pulse width modulation
    • H—ELECTRICITY
    • H02—GENERATION; CONVERSION OR DISTRIBUTION OF ELECTRIC POWER
    • H02P—CONTROL OR REGULATION OF ELECTRIC MOTORS, ELECTRIC GENERATORS OR DYNAMO-ELECTRIC CONVERTERS; CONTROLLING TRANSFORMERS, REACTORS OR CHOKE COILS
    • H02P2207/00—Indexing scheme relating to controlling arrangements characterised by the type of motor
    • H02P2207/01—Asynchronous machines

Landscapes

  • Engineering & Computer Science (AREA)
  • Power Engineering (AREA)
  • Automation & Control Theory (AREA)
  • Fuzzy Systems (AREA)
  • Artificial Intelligence (AREA)
  • Evolutionary Computation (AREA)
  • Control Of Ac Motors In General (AREA)

Abstract

PURPOSE: An adaptive FNN(fuzzy neural network) control system is provided to achieve improved efficiency and reduce energy consumption by controlling the speed of a motor in accordance with the operating condition. CONSTITUTION: An adaptive FNN control system comprises an adaptive FNN controller(6) for outputting command current of torque component required for speed control of an induction motor(9); a speed measuring unit(10) for measuring the speed of the induction motor input from the induction motor to the adaptive FNN controller; a vector controller(7) for receiving the command current of torque component, command current of magnetic flux component, and speed of induction motor, and outputting phase voltage command values; and a PWM inverter(8) for receiving the phase voltage command values, and driving the induction motor.

Description

유도전동기의 고성능 제어를 위한 적응 FNN 제어 시스템 {Adaptive FNN Control System for High Performance of Induction Motor}Adaptive FNN Control System for High Performance Control of Induction Motors

본 발명은 전동기의 속도 제어 시스템에 관한 것으로 전동기의 운전상태에 따라 적응 FNN 제어기(6)를 이용하여 제어하는 전동기의 속도 제어 시스템에 관한 것이다. 적응 FNN 제어기(6)는 FNN 제어기(2)와 적응퍼지제어기(3)를 병렬로 연결함으로서 과도특성에서 다양한 속도추정 능력, 부하 및 관성 등 파라미터 변동에 고성능 및 강인성을 갖는 시스템이다.BACKGROUND OF THE INVENTION 1. Field of the Invention The present invention relates to a speed control system of an electric motor and to a speed control system of an electric motor controlled by using an adaptive FNN controller 6 according to an operating state of the electric motor. The adaptive FNN controller 6 is a system having high performance and robustness against parameter variations such as various speed estimation capability, load and inertia in the transient characteristics by connecting the FNN controller 2 and the adaptive purge controller 3 in parallel.

도 1은 종래의 PI 제어기(1)를 적용한 유도전동기의 벡터제어 속도제어 시스템의 구성도를 나타낸다. 전동기 속도를 사용자가 원하는 속도로 설정한 지령속도()와 유도전동기(9)의 실제속도()를 비교하여 PI 제어기(1),벡터제어기(7),전압제어 PWM 인버터(8)로 유도전동기를 제어하게 된다. 여기서, PI 제어기(1)는 유도전동기(9)의 비선형성 때문에 과도상태에서 양호한 성능을 기대하기 어렵다. 특히 PI 제어기(1)의 이득계수를 조절하여도 시스템의 성능 향상에는 한계가 있으며 외란, 속도 및 부하 등의 파라미터가 변동할 경우 고성능 및 강인성을 기대하기 어렵다.1 shows a configuration diagram of a vector control speed control system of an induction motor to which a conventional PI controller 1 is applied. Command speed that sets the motor speed to the desired speed ) And the actual speed of the induction motor (9) ), The induction motor is controlled by the PI controller (1), the vector controller (7), and the voltage control PWM inverter (8). Here, the PI controller 1 cannot expect good performance in the transient state because of the nonlinearity of the induction motor 9. In particular, even if the gain coefficient of the PI controller 1 is adjusted, there is a limit in improving the performance of the system, and it is difficult to expect high performance and robustness when parameters such as disturbance, speed, and load change.

본 발명의 목적은 적응 FNN 제어기(6)를 사용하여 유도전동기(9)의 고성능 속도 제어 시스템과 유도전동기(9)용 벡터제어 시스템을 제공하는 것이다.It is an object of the present invention to provide a high performance speed control system for an induction motor 9 and a vector control system for an induction motor 9 using an adaptive FNN controller 6.

이러한 목적 달성을 위하여 본 발명의 고성능 속도제어 시스템은 퍼지제어와 입력층, 은닉층, 출력층으로 구성되는 신경회로망을 결합한 FNN 제어기(2)를 포함하고 퍼지제어기와 일차지연 모델(5)을 혼합한 적응 퍼지제어기(3)를 포함하고 상기의 적응 퍼지제어기(3)와 FNN 제어기(2)를 결합한 적응 FNN 제어기(6)를 포함한다.In order to achieve this purpose, the high performance speed control system of the present invention includes an FNN controller 2 which combines a fuzzy control and a neural network composed of an input layer, a hidden layer, and an output layer, and adopts a mixture of a fuzzy controller and a primary delay model 5. It includes a fuzzy controller (3) and an adaptive FNN controller (6) combining the above-described adaptive fuzzy controller (3) and the FNN controller (2).

도 1은 종래의 PI 제어기를 적용한 유도전동기의 벡터제어 속도제어 시스템의 구성도1 is a configuration diagram of a vector control speed control system of an induction motor using a conventional PI controller

도 2는 본 발명에 따른 FNN 제어기의 구성도2 is a block diagram of a FNN controller according to the present invention;

도 3은 본 발명에 따른 퍼지제어기의 구성도3 is a block diagram of a fuzzy controller according to the present invention

도 4는 본 발명에 따른 FNN 제어기의 세부구성도4 is a detailed configuration diagram of a FNN controller according to the present invention;

도 5는 본 발명에 따른 적응 FNN 제어기의 세부구성도5 is a detailed configuration diagram of an adaptive FNN controller according to the present invention.

도 6는 본 발명에 따른 일차지연모델을 포함한 적응 퍼지제어기의 구성도6 is a block diagram of an adaptive fuzzy controller including a primary delay model according to the present invention.

도 7은 본 발명의 적응 FNN 제어기를 적용한 유도전동기의 벡터제어 속도 제어 시스템의 구성도7 is a configuration diagram of a vector control speed control system of an induction motor to which the adaptive FNN controller of the present invention is applied.

＜도면의 주요 부분에 대한 부호의 설명＞<Description of the code | symbol about the principal part of drawing>

1 : PI 제어기 2 : FNN(Fuzzy-Neural Network) 제어기1: PI controller 2: FNN (Fuzzy-Neural Network) controller

3 : 적응퍼지제어기 4 : 적분기3: adaptive purge controller 4: integrator

5 : 1차 지연 모델 6 : 적응 FNN 제어기5: First Delay Model 6: Adaptive FNN Controller

7 : 벡터제어기 8 : 전압제어 PWM 인버터7: Vector controller 8: Voltage control PWM inverter

9 : 유도전동기 10 : 속도측정기9: induction motor 10: speed measuring instrument

이하, 본 발명에 대해서 첨부한 도면을 참조하여 보다 상세히 설명한다.Hereinafter, the present invention will be described in more detail with reference to the accompanying drawings.

본 발명에서는 과도특성에서 다양한 속도추정 능력, 부하 및 관성 등 파라미터 변동에 고성능 및 강인성을 위해 적응 FNN 제어기(6)를 채택한다. 본 발명에 따른 적응 FNN 제어기(6)는 최적의 제어를 위해 퍼지제어와 신경회로망 그리고 적응제어기법을 상호 결합한 제어이다.In the present invention, the adaptive FNN controller 6 is adopted for high performance and robustness against parameter variations such as various speed estimation capability, load and inertia in the transient characteristics. The adaptive FNN controller 6 according to the present invention is a control combining a fuzzy control, a neural network and an adaptive control technique for optimal control.

도 2는 전동기 속도를 사용자가 원하는 속도로 설정한 지령속도()와 유도전동기(9)의 실제속도()를 비교하여 속도오차()와 속도오차의 변화분()을 계산하여 FNN 제어기의 입력으로 사용하여 지령전류()를 출력하는 개략적인 블록도 이다.2 is a reference speed in which the motor speed is set to a speed desired by the user ( ) And the actual speed of the induction motor (9) ) To compare the speed error ( ) And change in speed error ( ) And use it as the input of FNN controller to ) Is a schematic block diagram that outputs.

도 3은 상기 기술된 본 발명의 FNN 제어기(2)에 관련하여, FNN 제어기(2)에 사용되는 보다 구체적인 구성을 하나의 실시예로서 예시한 것이다. 도 3의 (a)는 속도오차(), (b)는 속도오차의 변화분()을 퍼지화하는 기법을 예시하고 도 5에서 후술하게 될 신경회로망과 결합되어 그 출력은 도 3의 (c)로서 퍼지화된 지령전류()의 출력을 예시한다. 도 3에서 퍼지영역을 표현하기 위하여 사용된 기호는 다음과 같다.3 illustrates, as one embodiment, a more specific configuration used in the FNN controller 2 with respect to the FNN controller 2 of the present invention described above. 3 (a) shows a speed error ( ), (b) is the change in velocity error ( ) And the output is combined with the neural network, which will be described later in FIG. Exemplifies the output of Symbols used to represent the purge region in FIG. 3 are as follows.

NL : Negative LargeNL: Negative Large

NM : Negative MediumNM: Negative Medium

NS : Negative SmallNS: Negative Small

ZE : ZeroZE: Zero

PS : Positive SmallPS: Positive Small

PM : Positive MediumPM: Positive Medium

PL : Positive LargePL: Positive Large

도 4는 상기에서 기술된 본 발명의 FNN 제어기(6)에 대한 보다 구체적인 구성을 하나의 실시예로서 예시한 것이다. A1부터 A4까지는 신경회로망의 구조를 가진 것으로 A1은 입력층 A2,A3는 은닉층, A4는 출력층을 나타낸다. 신경회로망은 퍼지제어와 결합되어 FNN 제어기를 구성하는데 여기서 A1부터 A3는 퍼지규칙의 전반부(IF)에 해당하며 A3부터 A4는 퍼지규칙의 후반부(Then)에 해당한다.4 illustrates a more specific configuration for the FNN controller 6 of the present invention described above as an embodiment. A1 to A4 have a neural network structure, where A1 represents an input layer A2, A3 represents a hidden layer, and A4 represents an output layer. The neural network is combined with fuzzy control to form the FNN controller, where A1 to A3 correspond to the first half of the fuzzy rule and A3 to A4 correspond to the second half of the fuzzy rule.

신경회로망을 구성하는 가중치는 고성능의 속도제어를 위해 적합하게 학습되는데 본 실시예에서는 일반화된 오차 역전파 알고리즘에 의하여 다음 수학식(1,2,3)으로 계산된다.The weight constituting the neural network is suitably learned for high performance speed control. In this embodiment, the weight is calculated by the generalized error backpropagation algorithm using the following equation (1, 2, 3).

여기서는 신경회로망의 가중치를 나타낸다.here Represents the weight of the neural network.

수학식 1,수학식 2 그리고 수학식 3에서그리고는 상기 가중치를 학습하게 하는 인자로서 FNN 속도제어기(2)의 성능이 고성능이 되도록 신경회로망내의 파라미터들이 조정된다.In Equation 1, Equation 2 and Equation 3 And The parameter in the neural network is adjusted so that the performance of the FNN speed controller 2 is high as a factor for learning the weight.

상기에서 설명한 가중치의 변화분그리고는 다음의 수학식4, 수학식 5 그리고 수학식 6으로부터 계산된다.Change of weight explained above And Is calculated from the following equations (4), (5) and (6).

여기서,here,

는 A2층에서 신경세포의 출력,는 학습률,는 시그모이드 함수의 미분이와는 각각 A2층과 A3층에서 각 신경세포에 대한 전체 입력을 나타낸다. 그리고는 FNN 제어기(2)의 출력에서 오차신호이다. Is the output of neurons in A2 layer, Is the learning rate, Is the derivative of the sigmoid function Wow Represents the total input for each neuron in the A2 and A3 layers, respectively. And Is an error signal at the output of the FNN controller 2.

수학식 1, 수학식 2, 수학식 3은 학습과정 동안 진동을 피하고 수렴속도를 개선하기 위하여 다음의 수학식 7, 수학식 8, 수학식 9와 같이 모멘텀(momentum) 항으로 새롭게 조절된다. 모멘텀은 현재의 가중치뿐만 아니라 전단계의 가중치 변화도 고려함으로써 좀더 빨리 수렴하도록 하는 방법이다.Equations 1, 2, and 3 are newly adjusted to momentum terms as shown in Equations 7, Equations 8, and 9 to avoid vibrations and improve convergence speed during the learning process. Momentum is a method that converges faster by considering not only the current weight but also the weight change of the previous stage.

본 발명의 상기 실시예에서 파라미터 변동에 우수한 고성능의 속도제어를 위하여 신경회로망에 오차 역전파 알고리즘이 사용될 수 있고 이러한 신경회로망은학습기능을 갖게 되고, 반복 수행됨에 따라 출력 전류()는 최적치에 도달하게 된다.In the above embodiment of the present invention, an error back propagation algorithm may be used in the neural network for high speed control excellent in parameter variation, and the neural network has a learning function, and as it is repeatedly performed, ) Reaches an optimal value.

이와 같이 본 발명에 따른 FNN 제어기는 속도에 대해 온라인 학습기능이 가능하고 계속적으로 사용함에 따라 FNN 제어기(2)의 가중치는 누적된 과거의 경험 정보에 의해 최적의 상태로 수렴하게 된다. 또한 FNN 제어기는 비선형 시스템을 적절히 처리할 수 있으므로 본 발명에 따른 유도전동기(9)의 파라미터 변동에 고성능 및 강인성을 갖는다.As described above, the FNN controller according to the present invention enables the online learning function with respect to speed, and thus the weight of the FNN controller 2 converges to an optimal state based on accumulated past experience information. In addition, the FNN controller can properly handle the nonlinear system, so that the FNN controller has high performance and robustness against parameter variation of the induction motor 9 according to the present invention.

도 5는 본 발명의 적응 FNN 제어기(6)의 간단한 세부 블록도를 예시이다. 상기에서 설명한 FNN 제어기(2)와 후술하게될 적응퍼지제어기(3)를 병렬 연결한 구조이다. 지령속도()와 유도전동기(9)의 실제속도()를 비교하여 FNN 제어기(2)의 출력()과 적응퍼지제어기(3)의 출력()으로 수학식 10과 같이 출력 전류를 구한다.5 is a simple detailed block diagram of the adaptive FNN controller 6 of the present invention. The FNN controller 2 described above and the adaptive purge controller 3 to be described later are connected in parallel. Command speed ( ) And the actual speed of the induction motor (9) ), Compare the output of FNN controller 2 with ) And the output of the adaptive purge controller (3) ) To obtain the output current as shown in equation (10).

도 6은 본 발명의 적응 퍼지제어기(3)의 세부 블록도를 나타내고 있다. 적응 퍼지제어기(3)는 기준 모델을 사용하여 유도전동기(9)의 출력()과 기준모델의 출력()을 비교하여 오차()와 오차변화분()을 적응 퍼지제어기에 사용한다. 기준모델은 안정화 시간 및 오버슈트와 같은 설계기준을 만족하는 요구성능을충족시키기 위하여 1차 지연모델을 사용한다.6 shows a detailed block diagram of the adaptive fuzzy controller 3 of the present invention. The adaptive fuzzy controller 3 uses the reference model to output the induction motor 9 ) And the output of the reference model ( ) To compare the error ( ) And error variation ( ) Is used for adaptive fuzzy controller. The reference model uses a first order delay model to meet the required performance to meet design criteria such as settling time and overshoot.

도 7은 본 발명의 적응 FNN 제어기(6)를 적용한 유도전동기의 속도 제어 시스템을 나타내고 있다.7 shows a speed control system of an induction motor to which the adaptive FNN controller 6 of the present invention is applied.

도 7에 도시된 유도전동기의 속도제어 시스템은 상기 유도전동기(9)의 속도 제어에 필요한 토크성분의 지령전류()를 출력하는 적응 FNN 제어기(6), 상기 유도전동기(9)로부터 적응 FNN 제어기(6)에 입력되는 유도전동기의 속도()를 도출하기 위한 속도측정기(10), 유도전동기의 지령속도()와 속도()의 오차를 입력받아 지령전류()를 출력하는 적응 FNN 제어기(6), 상기 토크성분의 지령전류()와 자속성분의 지령전류() 및 유도전동기속도()를 받아 상전압 지령치()를 출력하는 벡터제어기(7) 및 상기 상전압 지령치()를 받아 상기 유도전동기(9)를 구동하는 전압제어 PWM 인버터(8)를 포함한다.The speed control system of the induction motor shown in FIG. 7 is a command current of the torque component required for the speed control of the induction motor 9. Adaptive FNN controller 6 for outputting the speed of the induction motor input to the adaptive FNN controller 6 from the induction motor 9 Speed measuring device 10 for deriving the command speed of the induction motor ( ) And speed ( Command error () Adaptive FNN controller 6 for outputting the command current of the torque component ) And command current of magnetic flux component ) And induction motor speed ( ) And the phase voltage setpoint ( And a vector controller 7 for outputting the phase voltage command value ) And a voltage controlled PWM inverter 8 for driving the induction motor 9.

상기 기술한 구성과 같이, 도 7에서 본 발명에 따른 적응 FNN 제어기는 입력으로 유도전동기 속도()를 입력받아 토크성분의 지령전류()를 생성하는 과정은 앞의 수학식 10에 근거하여 얻어진다. 적응 FNN 제어기는 지령속도()와 유도전동기 속도()와의 오차()로부터 토크성분 지령전류()를 출력한다. 토크성분의 지령전류()는 상기 자속성분의 지령전류()와 함께 벡터제어기(7)에 인가된다. 그러면, 이 벡터제어기(7)은 토크성분의 지령전류()와 자속성분의 지령전류() 그리고 유도전동기 속도()를 사용하여 상전압 지령치()를 출력한다. 출력된 상전압 지령치()는 전압제어 PWM 인버터(8)로 유도전동기(9)를 구동하게 된다.As described above, the adaptive FNN controller according to the present invention in FIG. ) Command current of torque component ) Is obtained based on Equation 10 above. The adaptive FNN controller has a command speed ( ) And induction motor speed ( Error with) Torque component command current from ) Command current of torque component Is the command current of the magnetic flux component Is applied to the vector controller 7. Then, this vector controller 7 is a command current of the torque component ( ) And command current of magnetic flux component ) And induction motor speed ( ) To set the phase voltage setpoint ( ) Output phase voltage setpoint ( ) Drives the induction motor 9 to the voltage controlled PWM inverter 8.

이와 같이, 본 발명에서 제시한 적응 FNN 제어기(6)는 최적의 지령전류()를 계산함으로 본 발명의 제어기는 시스템 적용에 고성능 및 강인성을 갖게한다.As such, the adaptive FNN controller 6 proposed in the present invention has an optimal command current ( ), The controller of the present invention gives high performance and robustness to system applications.

도 7에서는 적응 FNN 제어기(6)를 적용한 유도전동기의 속도 제어 시스템을 도시하였으나, 본 발명은 다른 유형의 전동기에 상기 발명의 속도제어 시스템을 쉽게 적용할 수 있다.7 shows the speed control system of the induction motor to which the adaptive FNN controller 6 is applied, the present invention can be easily applied to the speed control system of the present invention to other types of electric motors.

상기에서 상세히 설명한 바와 같이, 본 발명은 적응 FNN 제어기(6)를 사용함으로써 유도전동기 시스템의 비선형 특성에 적절하게 대응할 수 있고 따라서 파라미터 변동과 같은 시스템 변화에 강인성과 고성능을 유지함으로서 산업전반에 사용되는 산업기기의 효율을 높여 총체적으로 에너지 절감에 기여할 수 있다.As described in detail above, the present invention can adequately cope with the nonlinear characteristics of the induction motor system by using the adaptive FNN controller 6 and is therefore used throughout the industry by maintaining robustness and high performance against system changes such as parameter variations. Increasing the efficiency of industrial equipment can contribute to the overall energy savings.

본 발명의 적응 FNN 제어기는 퍼지제어기와 신경회로망을 병렬 연결한 구조로서 퍼지제어기와 신경회로망의 장점을 모두 흡수한 새로운 형태의 우수한 제어기랄 할 수 있다. 또한 수렴속도를 빠르게 계산하고 최적의 지령 전류값을 구할 수 있다.The adaptive FNN controller of the present invention is a structure in which a fuzzy controller and a neural network are connected in parallel, and can be a new type of excellent controller that absorbs all the advantages of the fuzzy controller and the neural network. In addition, the convergence speed can be quickly calculated and the optimum command current value can be obtained.

Claims (5)

유도전동기의 속도제어 시스템으로서, 상기 유도전동기(9)의 속도 제어에 필요한 토크성분의 지령전류()를 출력하는 적응 FNN 제어기(6), 상기 유도전동기(9)로부터 적응 FNN 제어기(6)에 입력되는 유도전동기의 속도()를 도출하기 위한 속도 측정기(10), 유도전동기의 지령속도()와 속도()의 오차를 입력받아 지령전류()를 출력하는 적응 FNN 제어기(6), 상기 토크성분의 지령전류()와 자속성분의 지령전류() 및 유도전동기 속도()를 받아 상전압 지령치()를 출력하는 벡터제어기(7) 및 상기 상전압 지령치()를 받아 상기 유도전동기(9)를 구동하는 전압제어 PWM 인버터(8)를 포함하여 구성됨을 특징으로 하는 시스템As a speed control system of an induction motor, a command current of torque component required for speed control of the induction motor 9 ( Adaptive FNN controller 6 for outputting the speed of the induction motor input to the adaptive FNN controller 6 from the induction motor 9 Speed measuring device 10 for deriving the command speed of the induction motor ( ) And speed ( Command error () Adaptive FNN controller 6 for outputting the command current of the torque component ) And command current of magnetic flux component ) And induction motor speed ( ) And the phase voltage setpoint ( And a vector controller 7 for outputting the phase voltage command value The system characterized in that it comprises a voltage controlled PWM inverter (8) for driving the induction motor (9) 제 1항에 있어 적응 FNN 제어기는 FNN 제어기와 적응 퍼지제어기를 병렬 연결하여 제어변수를 출력하는 것을 특징으로 하는 시스템The system of claim 1, wherein the adaptive FNN controller outputs control variables by connecting the FNN controller and the adaptive fuzzy controller in parallel. 제 2항에 있어 FNN 제어기는 퍼지제어기와 신경회로망을 혼합한 형태로 신경회로망의 입력층과 은닉층을 퍼지규칙의 전반부(IF)로 신경회로망의 출력층을 퍼지규칙의 후반부(THEN)로 설정하는 것을 특징으로 하는 시스템The FNN controller of claim 2, wherein the FNN controller is a mixture of a fuzzy controller and a neural network, and sets an input layer and a hidden layer of the neural network as the first half of the fuzzy rule and an output layer of the neural network as the second half of the fuzzy rule. Featured system 제 3항에 있어 신경회로망은 학습과정동안 진동을 피하고 수렴속도를 개선하기 위하여 모멘텀 항으로 새롭게 조절되는 것을 특징으로 하는 시스템4. The system of claim 3, wherein the neural network is newly adjusted with momentum terms to avoid vibrations during the learning process and to improve convergence speed. 제 1항에 있어 적응 퍼지 제어기는 일차 지연 모델을 포함하는 것을 특징으로 하는 시스템10. The system of claim 1, wherein the adaptive fuzzy controller includes a first order delay model.
KR1020040082889A 2004-10-12 2004-10-12 Adaptive FNN Control System for High Performance of Induction Motor KR20040097021A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
KR1020040082889A KR20040097021A (en) 2004-10-12 2004-10-12 Adaptive FNN Control System for High Performance of Induction Motor

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
KR1020040082889A KR20040097021A (en) 2004-10-12 2004-10-12 Adaptive FNN Control System for High Performance of Induction Motor

Publications (1)

Publication Number Publication Date
KR20040097021A true KR20040097021A (en) 2004-11-17

Family

ID=37375487

Family Applications (1)

Application Number Title Priority Date Filing Date
KR1020040082889A KR20040097021A (en) 2004-10-12 2004-10-12 Adaptive FNN Control System for High Performance of Induction Motor

Country Status (1)

Country Link
KR (1) KR20040097021A (en)

Cited By (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
KR100613860B1 (en) * 2005-03-18 2006-08-17 학교법인 유한학원 Apparatus of induction motor speed control using neural network
KR100665061B1 (en) * 2004-12-08 2007-01-09 삼성전자주식회사 Apparatus and method for control velocity of moter
KR100725543B1 (en) * 2005-08-10 2007-06-08 순천대학교 산학협력단 Self Tuning Proportional Integral Control System using Neural Network
CN110247586A (en) * 2019-07-12 2019-09-17 上海大学 The automobile-used permanent magnet synchronous motor torque distribution method of Electric Transit based on efficiency optimization
KR20200059796A (en) * 2018-11-22 2020-05-29 제주대학교 산학협력단 Control system based on learning of control parameter and method thereof

Cited By (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
KR100665061B1 (en) * 2004-12-08 2007-01-09 삼성전자주식회사 Apparatus and method for control velocity of moter
KR100613860B1 (en) * 2005-03-18 2006-08-17 학교법인 유한학원 Apparatus of induction motor speed control using neural network
KR100725543B1 (en) * 2005-08-10 2007-06-08 순천대학교 산학협력단 Self Tuning Proportional Integral Control System using Neural Network
KR20200059796A (en) * 2018-11-22 2020-05-29 제주대학교 산학협력단 Control system based on learning of control parameter and method thereof
CN110247586A (en) * 2019-07-12 2019-09-17 上海大学 The automobile-used permanent magnet synchronous motor torque distribution method of Electric Transit based on efficiency optimization

Similar Documents

Publication Publication Date Title
Lin et al. Neural-network-based adaptive control for induction servomotor drive system
WO2022252289A1 (en) Mtpa control method using d-q axis inductance parameter identification of fuzzy-logical controlled permanent-magnet synchronous electric motor
Lee et al. Performance improvement of DTC for induction motor-fed by three-level inverter with an uncertainty observer using RBFN
Jadhav et al. ANN based intelligent control of induction motor drive with space vector modulated DTC
Algreer et al. Design fuzzy self tuning of PID controller for chopper-fed DC motor drive
Kiruthika et al. Speed controller of switched reluctance motor
Lin Composite recurrent Laguerre orthogonal polynomials neural network dynamic control for continuously variable transmission system using altered particle swarm optimization
Menghal et al. Dynamic simulation of induction motor drive using neuro controller
Liu et al. Disturbance‐observer‐based speed control for SPMSM drives using modified super‐twisting algorithm and extended state observer
KR20040097021A (en) Adaptive FNN Control System for High Performance of Induction Motor
Kim et al. Vector control for loss minimization of induction motor using GA–PSO
Sulaiman et al. New methodology for chattering suppression of sliding mode control for three-phase induction motor drives
Djelamda et al. Field-oriented control based on adaptive neuro-fuzzy inference system for PMSM dedicated to electric vehicle
KR100726415B1 (en) Motor Control System with LM-FNN Controller
KR20050033601A (en) Hybrid pi(hbpi) control system for speed control of induction motor
Lin RETRACTED: Application of a V-belt continuously variable transmission system by using a composite recurrent Laguerre orthogonal polynomial neural network control system and modified particle swarm optimization
Mahmud et al. Single neuron ANN based current controlled permanent magnet brushless DC motor drives
Lin Hybrid Recurrent Laguerre‐Orthogonal‐Polynomial NN Control System Applied in V‐Belt Continuously Variable Transmission System Using Particle Swarm Optimization
Mousavi-Aghdam et al. A new method to reduce torque ripple in switched reluctance motor using fuzzy sliding mode
Yi et al. Application of fuzzy neural network in the speed control system of induction motor
Lin et al. Hybrid modified Elman NN controller design on permanent magnet synchronous motor driven electric scooter
Lin et al. Integral backstepping control for a PMLSM using adaptive RNNUO
Rafiq et al. Genetic Algorithm based PI controller tuning for induction motor drive with ANN flux estimator
Uddin et al. Model reference adaptive flux observer based neuro-fuzzy controller for induction motor drive
Shirien et al. Fuzzy logic controller based BLDC motor control for propulsion application

Legal Events

Date Code Title Description
A201 Request for examination
E902 Notification of reason for refusal
E601 Decision to refuse application