CN113726244B - Rotor flux linkage real-time estimation method and system based on Adaline neural network - Google Patents

Rotor flux linkage real-time estimation method and system based on Adaline neural network Download PDF

Info

Publication number
CN113726244B
CN113726244B CN202111024666.7A CN202111024666A CN113726244B CN 113726244 B CN113726244 B CN 113726244B CN 202111024666 A CN202111024666 A CN 202111024666A CN 113726244 B CN113726244 B CN 113726244B
Authority
CN
China
Prior art keywords
rotor flux
neural network
flux linkage
observer
discrete
Prior art date
Legal status (The legal status 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 status listed.)
Active
Application number
CN202111024666.7A
Other languages
Chinese (zh)
Other versions
CN113726244A (en
Inventor
宋宝
杨承博
陈天航
唐小琦
周向东
李虎
钟靖龙
刘章钊
吉文博
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Huazhong University of Science and Technology
Original Assignee
Huazhong University of Science and Technology
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 Huazhong University of Science and Technology filed Critical Huazhong University of Science and Technology
Priority to CN202111024666.7A priority Critical patent/CN113726244B/en
Publication of CN113726244A publication Critical patent/CN113726244A/en
Application granted granted Critical
Publication of CN113726244B publication Critical patent/CN113726244B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

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
    • H02P21/0014—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
    • H02P21/13—Observer control, e.g. using Luenberger observers or Kalman filters
    • 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
    • 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
    • H02P25/00—Arrangements or methods for the control of AC motors characterised by the kind of AC motor or by structural details
    • H02P25/02—Arrangements or methods for the control of AC motors characterised by the kind of AC motor or by structural details characterised by the kind of motor
    • H02P25/022—Synchronous motors
    • 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
    • H02P6/00—Arrangements for controlling synchronous motors or other dynamo-electric motors using electronic commutation dependent on the rotor position; Electronic commutators therefor
    • H02P6/34—Modelling or simulation for control purposes
    • 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
    • H02P2207/05—Synchronous machines, e.g. with permanent magnets or DC excitation

Landscapes

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

Abstract

The invention relates to a rotor flux linkage real-time estimation method and a system based on an Adaline neural network, wherein the method comprises the following steps: constructing a preliminary rotor flux observer based on an Adaline neural network; determining a dynamic learning rate for ensuring the stability of the rotor flux observer according to the Lyapunov second method; and determining a final rotor flux linkage observer based on the dynamic learning rate and the preliminary rotor flux linkage observer, and estimating the rotor flux linkage to be measured according to the final rotor flux linkage observer in real time. The invention combines the Adaline neural network and the Lyapunov second method to construct a novel rotor flux observer, thereby realizing the real-time estimation of the rotor flux to be detected and being suitable for the working conditions of speed change and load change. In addition, the method disclosed by the invention has only one parameter to be designed, and does not involve any matrix operation, so that the actual use is greatly facilitated, and the calculation load is reduced.

Description

Rotor flux linkage real-time estimation method and system based on Adaline neural network
Technical Field
The invention belongs to the field of flux linkage measurement of a permanent magnet synchronous motor driving system, and relates to a rotor flux linkage real-time estimation method and system based on an Adaline neural network.
Background
The permanent magnet synchronous motor has been widely used in industrial robot, machine tool, electric automobile and other industrial fields due to its excellent characteristics of large torque inertia ratio, high power density, high efficiency, good reliability and the like. As the demand for high performance control increases, permanent magnet synchronous motor drive systems have to incorporate advanced control algorithms such as load torque compensation and speed loop parameter self-tuning. The load torque compensation and the self-tuning of the speed loop parameters involve the identification of the relevant mechanical parameters of the drive system (such as the identification of the load torque and the moment of inertia) which require accurate electromagnetic torque information during the identification process. Typically, in a permanent magnet synchronous motor drive system, the electromagnetic torque is calculated indirectly through the rotor flux linkage. Thus, accurate flux linkage information is critical to ensuring the performance of these methods. However, due to temperature variations and different degrees of magnetic saturation, the actual value of the rotor flux always does not match the nominal value, i.e. the rotor flux is not constant. Therefore, it is necessary to estimate the rotor flux in real time.
Currently, the estimation techniques of rotor flux linkage mainly include two types. One class is designed using an electrical model of permanent magnet synchronous motor steady state, such as the method of Liu et al (k.liu and z.q.zhu, "Mechanical parameter estimation of permanent-magnet synchronous machines with aiding from estimation of rotor PM flux linkage," IEEE trans.ind.appl., vol.51, no.4, pp.3115-3125, july-aug.2015). This type of method cannot be used to estimate rotor flux linkage under variable speed and variable load conditions. Another class of schemes that can overcome this drawback were developed based on transient electrical models, mainly including extended Kalman filters (Y.Shi, K.Sun, L.Huang, and y. Li, "Online identification of permanent magnet flux based on extended Kalman filter for interior PMSM drive with position sensorless control," IEEE trans.ind.electron, vol.59, no.11, pp.4169-4178, nov.2012.), recursive least squares methods (s.j. Underwood and i.humilin, "Online parameter estimation and adaptive control of permanent-magnet synchronous machines," IEEE trans.ind.electron, vol.57, no.7, pp.2435-2443, july 2010), and affine projection algorithms (M.S.Rafaq, S.A.Q.Mohammed, and j. Jung, "Online multiparameter estimation for robust adaptive decoupling PI controllers of an IPMSM drive: variable Regularized APAs," IEEE/ASME, mecartron, vol.24, no.3, pp.1386-1395, june 2019).
While the second type of methods can effectively obtain rotor flux information, they still face some challenges in practical use: 1) These mentioned methods involve a large number of matrix operations, which in turn makes their industrial implementation quite time-consuming and renders it likely to be impractical in low-and medium-end drive systems; 2) These methods involve a number of parameters to be designed, so that their practical use is difficult.
Disclosure of Invention
In order to overcome the defects of poor real-time performance, difficult practical use and the like in the existing estimation technology of the rotor flux of the permanent magnet synchronous motor, the first aspect of the invention provides a rotor flux real-time estimation method based on an Adaline neural network, which comprises the following steps: constructing a preliminary rotor flux observer based on an Adaline neural network; determining a dynamic learning rate for ensuring the stability of the rotor flux observer according to the Lyapunov second method; and determining a final rotor flux linkage observer based on the dynamic learning rate and the preliminary rotor flux linkage observer, and estimating the rotor flux linkage to be measured according to the final rotor flux linkage observer in real time.
In some embodiments of the invention, the constructing an Adaline neural network-based preliminary rotor flux observer comprises:
determining the preliminary rotor flux observer according to a discrete mathematical model of a q-axis voltage equation of a permanent magnet synchronous motor driving system; the discrete mathematical model is expressed as:
wherein ,iq For q-axis current, n is discrete time, T c For discrete periods, u q For q-axis voltage, R s Is resistance, L is inductance, omega e For rotor electromagnetic angleSpeed lambda m For rotor flux linkage, u q (n)、i q (n)、ω e (n) u is the corresponding value of the nth discrete time q 、i q 、ω e 。
Further, the preliminary rotor flux observer is constructed by:
i is i q (n-1)、As input to the Adaline neural network and with estimated values of +1, and rotor flux linkage, respectively +.>As a weight of the corresponding input.
Preferably, the preliminary rotor flux observer is expressed as:
wherein ：e iq (n) represents the error between the expected and actual outputs of the Adaline neural network at the nth discrete time instant; /> and />Representing the actual output of the Adaline neural network and the estimated value of the rotor flux linkage at the nth discrete time respectively; kappa indicates the learning rate.
In some embodiments of the invention, determining a dynamic learning rate that ensures stability of a rotor flux observer according to the lyapunov second method comprises the steps of:
constructing a Lyapunov function according to the estimation error of the rotor flux linkage;
determining a dynamic learning rate according to the Lyapunov function and the Lyapunov stability criterion, wherein the learning rate is expressed as:
wherein ：κλ0 Is a constant; kappa (kappa) λ (n) is the learning rate of the Adaline neural network at the nth discrete time; e, e iq (n) is the estimated error of the rotor flux linkage; t (T) c Is a discrete period; p is the pole pair number; omega m_max The maximum rotation speed allowed by the permanent magnet synchronous motor driving system; l is inductance.
Further, the final rotor flux observer is expressed as:
wherein ：e iq (n) represents the error between the expected and actual outputs of the Adaline neural network at the nth discrete time instant; /> and />Representing the actual output of the Adaline neural network and the estimated value of the rotor flux linkage at the nth discrete time respectively; r is R s Is a resistor; i.e q Is q-axis current; u (u) q Is q-axis voltage; u (u) q (n)、i q (n)、ω e (n) u is the corresponding value of the nth discrete time q 、i q 、ω e 。
In a second aspect of the present invention, there is provided a rotor flux real-time estimation system based on an Adaline neural network, comprising: the construction module is used for constructing a preliminary rotor flux observer based on an Adaline neural network; the determining module is used for determining a dynamic learning rate for ensuring the stability of the rotor flux observer according to the Lyapunov second method; and the estimation module is used for determining a final rotor flux linkage observer based on the dynamic learning rate and the preliminary rotor flux linkage observer and estimating the rotor flux linkage to be measured in real time according to the final rotor flux linkage observer.
Further, the determining module comprises a constructing unit and a determining unit, wherein the constructing unit is used for constructing a Lyapunov function according to the estimation error of the rotor flux linkage; the determining unit is used for determining the dynamic learning rate according to the Lyapunov function and the Lyapunov second method.
In a third aspect of the present invention, there is provided an electronic apparatus comprising: one or more processors; and the storage device is used for storing one or more programs, and when the one or more programs are executed by the one or more processors, the one or more processors realize the rotor flux linkage real-time estimation method based on the Adaline neural network provided by the first aspect of the invention.
In a fourth aspect of the present invention, a computer readable medium is provided, on which a computer program is stored, wherein the computer program, when executed by a processor, implements the method for estimating rotor flux linkage based on an Adaline neural network according to the first aspect of the present invention.
The beneficial effects of the invention are as follows:
1. the invention provides an Adaline neural network technology with a dynamic learning rate to accurately estimate a rotor flux linkage in real time. The method is designed based on a transient q-axis voltage equation, so that the method is applicable to variable speed and variable load conditions;
2. the invention has only one parameter to be determined (the parameter has an extremely clear value range) and does not involve any matrix operation, so that the invention is simpler to use and easier to realize industrially, and a good foundation is laid for the subsequent application of the estimated rotor flux linkage.
Drawings
Fig. 1 is a basic flow diagram of a rotor flux real-time estimation method based on an Adaline neural network according to some embodiments of the present invention;
fig. 2 is a schematic diagram of a rotor flux real-time estimation method based on an Adaline neural network according to some embodiments of the present invention;
FIG. 3 is a schematic diagram of simulation results of a rotor flux real-time estimation method based on an Adaline neural network in the case of linear flux change according to some embodiments of the present invention;
fig. 4 is a schematic diagram of simulation results of a rotor flux real-time estimation method based on an Adaline neural network in the case of nonlinear flux change according to some embodiments of the present invention;
FIG. 5 is a graph showing the actual execution time of an extended Kalman filter in an STM32F103 microprocessor with the rotor flux real-time estimation system of the present invention;
FIG. 6 is a schematic diagram of a rotor flux real-time estimation system based on an Adaline neural network in some embodiments of the invention;
fig. 7 is a schematic structural diagram of an electronic device according to some embodiments of the present invention.
Detailed Description
The principles and features of the present invention are described below with reference to the drawings, the examples are illustrated for the purpose of illustrating the invention and are not to be construed as limiting the scope of the invention.
Example 1
Referring to fig. 1, in a first aspect of the present invention, there is provided a rotor flux real-time estimation method based on an Adaline neural network, including: s100, constructing a preliminary rotor flux observer based on an Adaline neural network; s200, determining a dynamic learning rate for ensuring the stability of a rotor flux observer according to a Lyapunov (Lyapunov) second method; s300, determining a final rotor flux linkage observer based on the dynamic learning rate and the preliminary rotor flux linkage observer, and estimating the rotor flux linkage to be measured in real time according to the final rotor flux linkage observer.
In step S100 of some embodiments of the present invention, the constructing an Adaline neural network-based preliminary rotor flux observer includes the steps of: determining the input, output and weight of the preliminary rotor flux observer according to a discrete mathematical model of a q-axis voltage equation of the permanent magnet synchronous motor driving system;
in particular, permanent magnet synchronous motor drive systems typically employThe q-axis voltage equation of the permanent magnet synchronous motor drive system can thus be simplified represented as follows:
wherein ,ωe Is electromagnetic angular velocity lambda m I is the rotor flux linkage q For q-axis current, L is inductance, R s Is a resistor. Based on the above equation, the discrete mathematical model of the q-axis voltage equation at the nth time instant can be derived as:
wherein n is a discrete time, T c For discrete periods, u q (n)、i q (n)、ω e (n) u is the corresponding value of the nth discrete time q 、i q 、ω e . Alternatively, n is a time or sequence number, e.g., n represents the nth discrete time or the nth iteration.
Adaline neural networks have low computational burden on-line and simple concepts, which make them widely used in industry. Its mathematical model can be described by the following equation:
wherein ,Im (m=1, 2, …, N) represents the input of the Adaline neural network, y o Representing the actual output of the Adaline neural network, W m (m=1, 2, …, N) is the correspondingInput I m (m=1, 2, …, N). In Adaline theory, a least mean square algorithm is often used to update weights. Based on the least mean square algorithm, the update equation of the weights can be expressed specifically as follows:
W m (n+1)＝W m (n)+κI m (n)[y do (n)-y o (n)](m=1, 2, …, N), where y do Is the expected output of the Adaline neural network; kappa is the learning rate, satisfying kappa>0。
Referring to FIG. 2, in some preferred embodiments, in i q (n-1)、 As input to the Adaline neural network and with estimated values of +1, and rotor flux linkage, respectively +.>As a weight of the corresponding input. Therefore, the preliminary rotor flux observer can be designed based on the Adaline neural network as follows:
wherein ：e iq (n) represents the error between the expected and actual outputs of the Adaline neural network at the nth discrete time instant; /> and />Representing the actual output of the Adaline neural network and the estimated value of the rotor flux linkage at the nth discrete time respectively; kappa indicates the learning rate.
In step S200 of some embodiments of the present invention, the determining a dynamic learning rate for ensuring stability of a rotor flux observer according to the lyapunov second method includes the steps of: s201, constructing a Lyapunov function according to an estimation error of a rotor flux linkage; s202, determining the dynamic learning rate according to the Lyapunov function and the Lyapunov second method.
Specifically, first, by definitionIt is possible to derive:
then, a Lyapunov function is selected as V (n) =e λm (n) 2 It is possible to obtain:
it will be appreciated that from Lyapunov stability theory, ΔV (n). Ltoreq.0 should be satisfied to ensure the stability of the primarily designed rotor flux observer. Thus, it is possible to deriveNote I 4 The composition of (1) includes electromagnetic angular velocity omega e . Due to omega e Are often variable and therefore taking a fixed value for κ may lead to instability. The Lyapunov function is determined according to the correlation definition of the second method of Lyapunov.
In view of this, the learning rate is expressed as:
wherein ：κλ0 Is a constant; kappa (kappa) λ (n) is the learning rate of the Adaline neural network at the nth discrete time; omega m_max The maximum rotation speed allowed by the permanent magnet synchronous motor driving system. When the learning rate is designed as above, it is possible to obtain:
due toTherefore, deltaV (n). Ltoreq.0 is true. From this, the designed time-varying learning rate satisfies Lyapunov stability theory. Through the design of the time-varying learning rate, potential instability is prevented, and the corresponding rotor flux observer is enabled to have a parameter to be designed with a definite value range.
In steps S100 or S200 of some embodiments of the present invention, the resulting final designed rotor flux observer may be expressed as:
example 2
Referring to fig. 6, in a second aspect of the present invention, there is provided a rotor flux real-time estimation system 1 based on an Adaline neural network, comprising: the construction module 11 is used for constructing a preliminary rotor flux observer based on an Adaline neural network; a determining module 12, configured to determine a dynamic learning rate for ensuring stability of the rotor flux observer according to the lyapunov second method; and the estimation module 13 is used for determining a final rotor flux observer based on the dynamic learning rate and the preliminary rotor flux observer and estimating the rotor flux to be measured in real time according to the final rotor flux observer.
Further, the determining module 12 includes a constructing unit and a determining unit, where the constructing unit is configured to construct a lyapunov function according to an estimation error of the rotor flux linkage; the determining unit is used for determining the dynamic learning rate according to the Lyapunov function and the Lyapunov second method.
In order to verify the feasibility and effectiveness of the method, the invention builds a simulation model. The built simulation model adoptsVector control strategy of (a). Note that in the simulation, the relevant parameters are set as: p=4; r is R s = 0.801 Ω; moment of inertia j=3×10 -3 Kg.m 2 The method comprises the steps of carrying out a first treatment on the surface of the L=3.675 mH; viscous friction coefficient b=0.0001 n.m.s/rad; the load torque is set as a periodically varying square wave with amplitude alternating between 1 and 3n.m and period of 0.6s; the maximum rotational speed allowed by the system is set to omega m_max =157 rad/s; the only parameter to be designed is chosen to be kappa λ0 =0.2; the speed command is selected as a periodic square wave with amplitude of-200 and 800r/min alternately, and period of 0.1s.
Referring to fig. 3 to 5, first, the rotor flux linkage is set to linearly vary with time, i.e., λ m =0.27783+0.05t, and the corresponding simulation results are shown in fig. 3. As can be seen from fig. 3, the provided rotor flux observer is capable of tracking flux changes with high accuracy under variable speed and variable load conditions. To further evaluate the performance of the provided rotor flux observer, the rotor flux is set to vary non-linearly with time, i.e. λ m =0.3+0.1sin (2ρt). The corresponding simulation results are shown in fig. 4. It can be seen from fig. 4 that the variations of the rotor flux linkage can still be accurately tracked. Furthermore, the present invention also takes the example of an extended Kalman filter (Y.Shi, K.Sun, L.Huang, and y. Li, "Online identification of permanent magnet flux based on extended Kalman filter for interior PMSM drive with position sensorless control," IEEE trans. Ind. Electron., vol.59, no.11, pp.4169-4178, nov. 2012.) which is compared with the actual execution time of the designed flux linkage observer in a drive system based on an STM32F103 microprocessor. The comparison result is shown in fig. 5. The results show that the designed rotor flux observer only requires a computational time of 2.32 mus, which is significantly lower than the computational time of 11.82 mus of the extended Kalman filter. The above results highlight the present inventionAdvantages of the rotor magnetic connection observer (rotor magnetic connection observation equation).
Example 3
Referring to fig. 7, a third aspect of the present invention provides an electronic device, including: one or more processors; and the storage device is used for storing one or more programs, and when the one or more programs are executed by the one or more processors, the one or more processors realize the rotor flux linkage real-time estimation method based on the Adaline neural network provided by the first aspect of the invention.
The electronic device 500 may include a processing means (e.g., a central processing unit, a graphics processor, etc.) 501 that may perform various appropriate actions and processes in accordance with programs stored in a Read Only Memory (ROM) 502 or loaded from a storage 508 into a Random Access Memory (RAM) 503. In the RAM503, various programs and data required for the operation of the electronic apparatus 500 are also stored. The processing device 501, the ROM502, and the RAM503 are connected to each other via a bus 504. An input/output (I/O) interface 505 is also connected to bus 504.
The following devices may be connected to the I/O interface 505 in general: input devices 506 including, for example, a touch screen, touchpad, keyboard, mouse, camera, microphone, accelerometer, gyroscope, etc.; an output device 507 including, for example, a Liquid Crystal Display (LCD), a speaker, a vibrator, and the like; storage 508 including, for example, a hard disk; and communication means 509. The communication means 509 may allow the electronic device 500 to communicate with other devices wirelessly or by wire to exchange data. While fig. 7 shows an electronic device 500 having various means, it is to be understood that not all of the illustrated means are required to be implemented or provided. More or fewer devices may be implemented or provided instead. Each block shown in fig. 7 may represent one device or a plurality of devices as needed.
In particular, according to embodiments of the present disclosure, the processes described above with reference to flowcharts may be implemented as computer software programs. For example, embodiments of the present disclosure include a computer program product comprising a computer program embodied on a computer readable medium, the computer program comprising program code for performing the method shown in the flowcharts. In such an embodiment, the computer program may be downloaded and installed from a network via the communication means 509, or from the storage means 508, or from the ROM 502. The above-described functions defined in the methods of the embodiments of the present disclosure are performed when the computer program is executed by the processing device 501. It should be noted that the computer readable medium described in the embodiments of the present disclosure may be a computer readable signal medium or a computer readable storage medium or any combination of the two. The computer readable storage medium can be, for example, but not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or a combination of any of the foregoing. More specific examples of the computer-readable storage medium may include, but are not limited to: an electrical connection having one or more wires, a portable computer diskette, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing. In an embodiment of the present disclosure, a computer readable storage medium may be any tangible medium that can contain, or store a program for use by or in connection with an instruction execution system, apparatus, or device. Whereas in embodiments of the present disclosure, the computer-readable signal medium may comprise a data signal propagated in baseband or as part of a carrier wave, with computer-readable program code embodied therein. Such a propagated data signal may take any of a variety of forms, including, but not limited to, electro-magnetic, optical, or any suitable combination of the foregoing. A computer readable signal medium may also be any computer readable medium that is not a computer readable storage medium and that can communicate, propagate, or transport a program for use by or in connection with an instruction execution system, apparatus, or device. Program code embodied on a computer readable medium may be transmitted using any appropriate medium, including but not limited to: electrical wires, fiber optic cables, RF (radio frequency), and the like, or any suitable combination of the foregoing.
The computer readable medium may be contained in the electronic device; or may exist alone without being incorporated into the electronic device. The computer readable medium carries one or more computer programs which, when executed by the electronic device, cause the electronic device to:
computer program code for carrying out operations of embodiments of the present disclosure may be written in one or more programming languages, including an object oriented programming language such as Java, smalltalk, C ++, python and conventional procedural programming languages, such as the "C" programming language or similar programming languages. The program code may execute entirely on the user's computer, partly on the user's computer, as a stand-alone software package, partly on the user's computer and partly on a remote computer or entirely on the remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer through any kind of network, including a Local Area Network (LAN) or a Wide Area Network (WAN), or may be connected to an external computer (for example, through the Internet using an Internet service provider).
The flowcharts and block diagrams in the figures illustrate the architecture, functionality, and operation of possible implementations of systems, methods and computer program products according to various embodiments of the present disclosure. In this regard, each block in the flowchart or block diagrams may represent a module, segment, or portion of code, which comprises one or more executable instructions for implementing the specified logical function(s). It should also be noted that, in some alternative implementations, the functions noted in the block may occur out of the order noted in the figures. For example, two blocks shown in succession may, in fact, be executed substantially concurrently, or the blocks may sometimes be executed in the reverse order, depending upon the functionality involved. It will also be noted that each block of the block diagrams and/or flowchart illustration, and combinations of blocks in the block diagrams and/or flowchart illustration, can be implemented by special purpose hardware-based systems which perform the specified functions or acts, or combinations of special purpose hardware and computer instructions.
The foregoing description of the preferred embodiments of the invention is not intended to limit the invention to the precise form disclosed, and any such modifications, equivalents, and alternatives falling within the spirit and scope of the invention are intended to be included within the scope of the invention.

Claims (6)

1. The rotor flux linkage real-time estimation method based on the Adaline neural network is characterized by comprising the following steps of:
constructing a preliminary rotor flux observer based on an Adaline neural network; the preliminary rotor flux observer is expressed as:
，
wherein ：，/>represents Adaline neural network at the firstnError between the desired output and the actual output at discrete times; /> and />Respectively shown in the firstnActual output of the Adaline neural network at discrete moments and estimated values of rotor flux linkage; />Representing a learning rate;
determining a dynamic learning rate for ensuring the stability of the rotor flux observer according to the Lyapunov second method: constructing a Lyapunov function according to the estimation error of the rotor flux linkage; determining a dynamic learning rate according to the Lyapunov function and the Lyapunov second method, wherein the dynamic learning rate is expressed as:
，/>，
wherein ：is a constant; />In the first place for Adaline neural networknLearning rate at discrete moments; />An estimation error for the rotor flux linkage; />Is a discrete period; />Is the pole pair number; />The maximum rotation speed allowed by the permanent magnet synchronous motor driving system; />Is an inductance;
determining a final rotor flux observer based on the dynamic learning rate and the preliminary rotor flux observer, and estimating the rotor flux to be measured according to the final rotor flux observer in real time, wherein the final rotor flux observer is expressed as:
，
wherein ：，/>represents Adaline neural network at the firstnError between the desired output and the actual output at discrete times; /> and />Respectively shown in the firstnActual output of the Adaline neural network at discrete moments and estimated values of rotor flux linkage; />Is a resistor; />Is thatqShaft current; />Is thatqAn axis voltage; />、、/>Respectively the firstnCorresponding to discrete time>、/>、/>。
2. The method for estimating rotor flux linkage in real time based on an Adaline neural network according to claim 1, wherein the constructing a preliminary rotor flux linkage observer based on the Adaline neural network comprises:
according to permanent magnet synchronous motor driving systemqDetermining the preliminary rotor flux observer by a discrete mathematical model of an axis voltage equation; the discrete mathematical model is expressed as:
，
wherein ,is thatqThe current of the shaft is applied to the shaft,nfor discrete moments>For discrete periods +.>Is thatqAxle voltage>For resistance, < >>Is an inductor (I)>For rotor electromagnetic angular velocity +.>For rotor flux linkage->、/>、/>Respectively the firstnCorresponding to discrete time>、/>、/>。
3. The method for estimating rotor flux linkage in real time based on an Adaline neural network according to claim 2, wherein the preliminary rotor flux linkage observer is constructed by:
to be used for、/>、/>、/>As input to the Adaline neural network and with estimated values of +1, and rotor flux linkage, respectively +.>As a weight of the corresponding input.
4. The rotor flux linkage real-time estimation system based on the Adaline neural network is characterized by comprising the following components:
the construction module is used for constructing a preliminary rotor flux observer based on an Adaline neural network; the preliminary rotor flux observer is expressed as:
，
wherein ：，/>represents Adaline neural network at the firstnError between the desired output and the actual output at discrete times; /> and />Respectively shown in the firstnActual output of the Adaline neural network at discrete moments and estimated values of rotor flux linkage; />Representing a learning rate;
the determining module is used for determining a dynamic learning rate for ensuring the stability of the rotor flux observer according to the Lyapunov second method: constructing a Lyapunov function according to the estimation error of the rotor flux linkage; determining a dynamic learning rate according to the Lyapunov function and the Lyapunov second method, wherein the dynamic learning rate is expressed as:
，/>，
wherein ：is a constant; />In the first place for Adaline neural networknLearning rate at discrete moments; />An estimation error for the rotor flux linkage; />Is a discrete period; />Is the pole pair number; />The maximum rotation speed allowed by the permanent magnet synchronous motor driving system; />Is an inductance;
the estimation module is used for determining a final rotor flux observer based on the dynamic learning rate and the preliminary rotor flux observer, and estimating the rotor flux to be measured according to the final rotor flux observer in real time, wherein the final rotor flux observer is expressed as:
，
wherein ：，/>represents Adaline neural network at the firstnError between the desired output and the actual output at discrete times; /> and />Respectively shown in the firstnActual output of the Adaline neural network at discrete moments and estimated values of rotor flux linkage; />Is a resistor; />Is thatqShaft current; />Is thatqAn axis voltage; />、、/>Respectively the firstnCorresponding to discrete time>、/>、/>。
5. An electronic device, comprising: one or more processors; storage means for storing one or more programs that, when executed by the one or more processors, cause the one or more processors to implement the Adaline neural network-based rotor flux real-time estimation method of any one of claims 1 to 3.
6. A computer readable medium having stored thereon a computer program, wherein the computer program when executed by a processor implements the method of real-time estimation of rotor flux linkage based on an Adaline neural network as claimed in any one of claims 1 to 3.
CN202111024666.7A 2021-09-02 2021-09-02 Rotor flux linkage real-time estimation method and system based on Adaline neural network Active CN113726244B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202111024666.7A CN113726244B (en) 2021-09-02 2021-09-02 Rotor flux linkage real-time estimation method and system based on Adaline neural network

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202111024666.7A CN113726244B (en) 2021-09-02 2021-09-02 Rotor flux linkage real-time estimation method and system based on Adaline neural network

Publications (2)

Publication Number Publication Date
CN113726244A CN113726244A (en) 2021-11-30
CN113726244B true CN113726244B (en) 2023-09-26

Family

ID=78680828

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202111024666.7A Active CN113726244B (en) 2021-09-02 2021-09-02 Rotor flux linkage real-time estimation method and system based on Adaline neural network

Country Status (1)

Country Link
CN (1) CN113726244B (en)

Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN108880351A (en) * 2018-06-28 2018-11-23 上海应用技术大学 The evaluation method and system of permanent-magnet synchronous motor rotor position
CN111313774A (en) * 2020-02-25 2020-06-19 华南理工大学 Permanent magnet synchronous motor parameter online identification method based on NLMS algorithm
CN111342728A (en) * 2020-02-25 2020-06-26 华南理工大学 Permanent magnet synchronous motor parameter identification method based on variable step size NLMS algorithm

Patent Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN108880351A (en) * 2018-06-28 2018-11-23 上海应用技术大学 The evaluation method and system of permanent-magnet synchronous motor rotor position
CN111313774A (en) * 2020-02-25 2020-06-19 华南理工大学 Permanent magnet synchronous motor parameter online identification method based on NLMS algorithm
CN111342728A (en) * 2020-02-25 2020-06-26 华南理工大学 Permanent magnet synchronous motor parameter identification method based on variable step size NLMS algorithm

Also Published As

Publication number Publication date
CN113726244A (en) 2021-11-30

Similar Documents

Publication Publication Date Title
US20200266743A1 (en) Systems, methods and devices for neural network control for ipm motor drives
Jafarzadeh et al. Square root unscented Kalman filters for state estimation of induction motor drives
Mao et al. Design and implementation of continuous finite-time sliding mode control for 2-DOF inertially stabilized platform subject to multiple disturbances
JP6485644B2 (en) Method and motor drive for controlling the angular speed of an induction motor
CN107592048A (en) The adaptive chaos control method of fractional order brushless DC motor system
Qi Rotor resistance and excitation inductance estimation of an induction motor using deep-Q-learning algorithm
JP7090734B2 (en) Control system, control method and storage medium
CN107395083A (en) PMLSM servo-control system Position And Velocity methods of estimation and device
Lin Nonlinear backstepping control design of LSM drive system using adaptive modified recurrent Laguerre orthogonal polynomial neural network
Luo et al. Anti-oscillation and chaos control of the fractional-order brushless DC motor system via adaptive echo state networks
Bhattacharjee et al. An advanced policy gradient based vector control of PMSM for EV application
CN113726244B (en) Rotor flux linkage real-time estimation method and system based on Adaline neural network
Moreno-Valenzuela et al. Lyapunov-based adaptive control for the permanent magnet synchronous motor driving a robotic load
Thakar et al. Fractional-order PI controller for permanent magnet synchronous motor: A design-based comparative study
CN114679098A (en) Feedforward compensation method and device for permanent magnet synchronous motor, computer equipment and medium
Nguyen et al. Asynchronous machine rotor speed estimation using a tabulated numerical approach
Lin et al. Sensorless inverter‐fed compressor drive system using back‐EMF estimator with PIDNN torque observer
CN113572393A (en) Intelligent MPC control method and device for embedded permanent magnet synchronous motor
Viswa Teja et al. Analysis of various speed control methods for PMSM drive-based electric vehicles
Aguilar Mejía et al. Adaptive Speed Controller for a Permanent Magnet Synchronous Motor
CN116015119B (en) Permanent magnet synchronous motor current control method and device, storage medium and electronic equipment
Toledo et al. Stabilization for a class of nonlinear systems: A fuzzy logic approach
Sabouni et al. Adaptive backstepping controller design based on neural network for pmsm speed control
WO2023124921A1 (en) Torque estimation method and apparatus for permanent magnet synchronous motor, and device and storage medium
WO2023124893A1 (en) Torque estimation method and apparatus based on neural network, and device and storage medium

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination
GR01 Patent grant
GR01 Patent grant