CN115102444A - Self-adaptive integral sliding mode prediction control method for permanent magnet synchronous motor - Google Patents
Self-adaptive integral sliding mode prediction control method for permanent magnet synchronous motor Download PDFInfo
- Publication number
- CN115102444A CN115102444A CN202210825408.7A CN202210825408A CN115102444A CN 115102444 A CN115102444 A CN 115102444A CN 202210825408 A CN202210825408 A CN 202210825408A CN 115102444 A CN115102444 A CN 115102444A
- Authority
- CN
- China
- Prior art keywords
- sliding mode
- rotating speed
- adaptive
- neural network
- self
- 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.)
- Granted
Links
- 238000000034 method Methods 0.000 title claims abstract description 20
- 230000001360 synchronised effect Effects 0.000 title claims abstract description 17
- 238000013528 artificial neural network Methods 0.000 claims abstract description 29
- 238000012549 training Methods 0.000 claims abstract description 29
- 230000003044 adaptive effect Effects 0.000 claims description 12
- 238000013459 approach Methods 0.000 claims description 11
- 238000012360 testing method Methods 0.000 claims description 9
- 230000008569 process Effects 0.000 claims description 6
- 239000000126 substance Substances 0.000 claims description 6
- 238000010606 normalization Methods 0.000 claims description 4
- 230000004907 flux Effects 0.000 claims description 3
- 238000013178 mathematical model Methods 0.000 claims description 3
- 238000003062 neural network model Methods 0.000 claims description 3
- 238000011217 control strategy Methods 0.000 abstract description 10
- 230000007547 defect Effects 0.000 abstract description 4
- 230000000694 effects Effects 0.000 description 3
- 230000004044 response Effects 0.000 description 3
- 230000001276 controlling effect Effects 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 230000006872 improvement Effects 0.000 description 2
- 230000004075 alteration Effects 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000001105 regulatory effect Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
Images
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
- H02P21/0007—Control strategies in general, e.g. linear type, e.g. P, PI, PID, using robust control using sliding mode 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
- H02P21/22—Current control, e.g. using a current control loop
-
- 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
- H02P25/024—Synchronous motors controlled by supply frequency
-
- 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
- H02P6/00—Arrangements for controlling synchronous motors or other dynamo-electric motors using electronic commutation dependent on the rotor position; Electronic commutators therefor
- H02P6/28—Arrangements for controlling current
-
- 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
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
- Y02P80/00—Climate change mitigation technologies for sector-wide applications
- Y02P80/10—Efficient use of energy, e.g. using compressed air or pressurized fluid as energy carrier
Abstract
The invention provides a self-adaptive integral sliding mode prediction control method of a permanent magnet synchronous motor, which realizes self-adaptive adjustment control of a rotating speed ring controller by constructing a self-adaptive integral sliding mode prediction control model of a rotating speed ring and a current ring, introducing self-adaptive factors into the rotating speed ring part to improve, and training a BP neural network by using an operation condition and optimal control parameters, thereby effectively overcoming the defect of inconvenient parameter setting of the controller in the prior art and obviously improving the steady state and dynamic control performance of a double closed-loop control strategy.
Description
Technical Field
The invention belongs to the technical field of permanent magnet synchronous motor control, and particularly relates to a permanent magnet synchronous motor double-closed-loop control technology based on a BP neural network and parameter self-adjustment.
Background
The permanent magnet synchronous motor has higher requirements on the performances of system stability, control precision, dynamic response speed, anti-interference capability and the like in control, vector control is a widely applied means in the existing permanent magnet synchronous motor speed regulating system, and the most common control strategy at present is a rotating speed loop and current loop double closed loop control strategy. However, the vector control strategy still has some defects, such as the PI linear control which is used more frequently in the closed-loop control, and the control dynamic performance and the control accuracy are poor; the nonlinear strategy based on sliding mode control also has the problem of buffeting because the system state always shakes back and forth near the sliding mode surface. In addition, the control parameters directly influence the performance of the controller, and the control parameters corresponding to different working conditions are different, so that the defect of complicated parameter setting exists in both linear and nonlinear control strategies.
Disclosure of Invention
In view of this, aiming at the technical problems existing in the foregoing field, the present invention provides a method for prediction control of a permanent magnet synchronous motor by using an adaptive integral sliding mode, which specifically includes the following steps:
step one, constructing an equivalent mathematical model of the permanent magnet synchronous motor, and establishing a self-adaptive integral sliding mode prediction controller model aiming at a rotating speed ring and a current ring in sequence, wherein the sliding mode surfaces of the rotating speed ring and the current ring can be expressed as follows:
wherein s (t) and e (t) are respectively a sliding mode surface and a tracking error at the time t; c represents an integral gain coefficient and c > 0;
and the following exponential approach law is adopted:
wherein, the approach law coefficient q is more than 0, epsilon is more than 0, and the superscript is used for representing the first derivative of the corresponding parameter;
step two, in a sliding mode prediction controller model of the rotating speed ring, rotating speed ring s is converted ω First derivative of slip form surface
Introducing an adaptive factor, and improving the adaptive factor into the following form:
wherein the content of the first and second substances,
c ω integral gain coefficient of slip form surface of rotating speed ring and c ω ＞0，ω m For the rotor mechanical angular speed, the reference values of the corresponding parameters are indicated by superscripts;
selecting control parameters of a rotating speed loop sliding mode prediction controller model which enable the control performance to reach the optimal under different target rotating speeds and load torques: integral gain coefficient c ω And an approximation law coefficient q ω Lambda, establishing a training set together with the corresponding target rotating speed and the corresponding load torque to train the BP neural network; the BP neural network takes a target rotating speed and a load torque as input layer nodes, c ω 、q ω And λ as an output layer node;
and step four, utilizing the trained BP neural network to combine with a sliding mode prediction controller model of the rotating speed loop and the current loop to realize the self-adaptive adjustment and control of the parameters of the rotating speed loop.
Further, in the step one, a voltage equation under the following rotating coordinate system is specifically established for the permanent magnet synchronous motor:
in the formula u d And u q The stator voltage components of d and q axes respectively; i all right angle d And i q D and q axis stator current components respectively; r is s ，L s And Ψ f Respectively stator resistance, stator inductance and rotor permanent magnet flux, omega e Is the electrical angular velocity; t is a time variable;
and establishing the following electromagnetic torque equations and dynamics equations:
in the formula, T e Is the electromagnetic torque; p is the number of pole pairs, T l Is the load torque; b is viscous friction coefficient, and J is rotor moment of inertia;
after discretization is carried out by utilizing a first-order forward Euler formula, the concrete form of the sliding mode prediction controller model of the rotating speed ring is as follows:
in the formula, r ωlaw Representing the self-adaptive approach law of the rotating speed ring sliding mode prediction controller model; t is the control period of the rotating speed loop;
the concrete form of the sliding mode prediction controller model of the current loop is as follows:
wherein the content of the first and second substances,
s d,q sliding mode surface of d-and q-axis stator current of current loop controller, c d,q Is the integral gain coefficient of the current loop sliding mode surface and c d,q >0，r d,qlaw Represents the adaptive approach law, q, of a current loop sliding mode controller d,q Is an approximation law coefficient and q d,q ＞0，T s The period is controlled for the current loop.
Further, in the sliding-mode predictive controller model of the rotating speed ring, the sliding-mode surface is specifically in the following form:
in the formula, superscript is used for representing the second derivative of the corresponding parameter, and subscript omega is used for representing each parameter corresponding to the rotating speed ring;
in a sliding mode prediction controller model of a current loop, a sliding mode surface is specifically in the following form:
in the formula, subscripts d and q are parameters of a d axis and a q axis corresponding to the current loop.
Further, the specific training process of the BP neural network in step three includes:
a. selecting optimal control parameters under different target rotating speeds and load torques, and constructing a training set comprising training samples and test samples;
b. normalizing training sample data;
c. constructing a BP neural network model, setting parameters such as training times, learning rate, minimum error of a training target and the like, setting a hidden layer node to be 5, and setting initial values of weight and bias;
d. normalizing the test sample;
e. predicting the test sample by using a BP neural network;
f. the prediction result is subjected to inverse normalization and is compared with a true value;
g. if the prediction result conforms to the expected error, ending the training, and outputting the weight and the bias of the neural network to obtain the trained BP neural network; otherwise, updating the weight and the bias, and repeating the steps d-g until the training is completed.
Further, in the fourth step, the trained BP neural network is utilized, the target rotating speed and the load torque are firstly input, and the optimal parameter c is output ω 、q ω And λ;
then, the above-mentioned parameter c is used ω 、q ω And lambda is input into the established sliding mode prediction controller model, and the self-adaptive adjustment and control of the parameters of the rotating speed ring are completed.
According to the self-adaptive integral sliding mode prediction control method for the permanent magnet synchronous motor, the self-adaptive integral sliding mode prediction control model of the rotating speed ring and the current ring is constructed, self-adaptive factors are introduced into the rotating speed ring part to improve, the BP neural network is trained by using the operating condition and the optimal control parameters, the self-adaptive adjustment control of the rotating speed ring controller is realized, the defect that the parameter setting of the controller is inconvenient in the prior art can be effectively overcome, and the dynamic control performance of a double-closed-loop control strategy is obvious.
Drawings
FIG. 1 is a block diagram of a control system of the method of the present invention;
FIG. 2 is a flow chart of training a BP neural network in the method provided by the present invention;
FIG. 3 is a diagram illustrating the effect of controlling the rotation speed and current in the prior art
Fig. 4 is a graph showing the effect of the control of the rotational speed and the current in the example according to the present invention.
Detailed Description
The technical solutions of the present invention will be described clearly and completely with reference to the accompanying drawings, and it is to be understood that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
The invention provides a permanent magnet synchronous motor self-adaptive integral sliding mode prediction control method, as shown in fig. 1, which specifically comprises the following steps:
step one, constructing an equivalent mathematical model of the permanent magnet synchronous motor, and establishing a self-adaptive integral sliding mode prediction controller model aiming at a rotating speed ring and a current ring in sequence, wherein the sliding mode surfaces of the rotating speed ring and the current ring can be expressed as follows:
in the formula, s (t) and e (t) are respectively a sliding mode surface and a tracking error at the time t; c represents an integral gain coefficient and c > 0;
the exponential approximation law expression is as follows:
wherein, the approach law coefficient q is more than 0, and epsilon is more than 0.
Discretizing an integral sliding mode surface by adopting a first-order forward Euler, and obtaining by combining an index approaching law:
the expression s (T + T) is derived as:
s(t+T)＝M[s(t)]
wherein the content of the first and second substances,
a sufficient condition for the decrementing of sliding-form surface s (t) is | M | 1, i.e.:
get
And is
The following adaptive sliding mode approach law is obtained:
superscript · denotes the first derivative of the corresponding parameter;
step two, in the sliding mode prediction controller model of the rotating speed ring, rotating speed ring s is converted ω First derivative of slip form surface
Introducing an adaptive factor, and improving the adaptive factor into the following form:
wherein, the first and the second end of the pipe are connected with each other,
c ω integral gain coefficient of slip form surface of rotating speed ring and c ω ＞0，ω m For the rotor mechanical angular speed, the reference values of the corresponding parameters are indicated by superscripts;
selecting control parameters of a rotating speed loop sliding mode prediction controller model which enable the control performance to reach the optimal under different target rotating speeds and load torques: integral gain coefficient c ω And an approximation law coefficient q ω Lambda, establishing a training set together with the corresponding target rotating speed and the corresponding load torque to train the BP neural network; the BP neural network is used for controlling the target rotating speed and the load torqueAs input layer nodes, c ω 、q ω And λ as an output layer node;
and step four, utilizing the trained BP neural network to combine with a sliding mode prediction controller model of the rotating speed loop and the current loop to realize the self-adaptive adjustment and control of the parameters of the rotating speed loop.
In a preferred embodiment of the present invention, in step one, a voltage equation under the following rotation coordinate system is specifically established for the permanent magnet synchronous motor:
in the formula u d And u q Stator voltage components of d and q axes respectively; i.e. i d And i q D and q axis stator current components respectively; r is s ，L s And Ψ f Respectively stator resistance, stator inductance and rotor permanent magnet flux, omega e Is the electrical angular velocity; t is a time variable;
and establishing the following electromagnetic torque equations and dynamics equations:
in the formula, T e Is an electromagnetic torque; p is the number of pole pairs, T l Is the load torque; b is viscous friction coefficient, and J is rotor moment of inertia;
after discretization is carried out by utilizing a first-order forward Euler formula, the concrete form of the sliding mode prediction controller model of the rotating speed ring is as follows:
in the formula, r ωlaw Representing the self-adaptive approach law of the rotating speed ring sliding mode prediction controller model; t is the control period of the rotating speed loop;
the sliding mode prediction controller model of the current loop has the specific form as follows:
wherein the content of the first and second substances,
s d,q slip form surface for d, q axis stator current of current loop controller, c d,q Is the integral gain coefficient of the current loop sliding mode surface and c d,q >0，r d,qlaw Represents the adaptive approach law, q, of a current loop sliding mode controller d,q Is an approximation law coefficient and q d,q ＞0，T s The period is controlled for the current loop.
In a preferred embodiment of the present invention, in the sliding-mode predictive controller model of the rotating speed ring, the sliding-mode surface thereof is specifically in the following form:
in the formula, superscript · represents the second derivative of the corresponding parameter, and subscript ω is each parameter corresponding to the rotation speed ring;
in the sliding mode prediction controller model of the current loop, the sliding mode surface is specifically in the following form:
in the formula, subscripts d and q are parameters of a d axis and a q axis corresponding to the current loop.
In a preferred embodiment of the present invention, a specific training process of the BP neural network in step three is shown in fig. 2, and includes:
a. selecting optimal control parameters under different target rotating speeds and load torques, and constructing a training set comprising training samples and test samples;
b. normalizing training sample data;
c. constructing a BP neural network model, setting parameters such as training times, learning rate, minimum error of a training target and the like, setting a hidden layer node to be 5, and setting initial values of weight and bias;
d. normalizing the test sample;
e. predicting the test sample by using a BP neural network;
f. the prediction result is subjected to inverse normalization and is compared with a real value;
g. if the prediction result accords with the expected error, finishing the training, and outputting the weight and the bias of the neural network to obtain the trained BP neural network; otherwise, updating the weight and the bias, and repeating the steps d-g until the training is completed.
In a preferred embodiment of the invention, in step four, a trained BP neural network is utilized, firstly, a target rotating speed and a load torque are input, and an optimal parameter c is output ω 、q ω And λ;
then, the above-mentioned parameter c is used ω 、q ω And lambda is input into the established sliding mode prediction controller model, and the self-adaptive adjustment and control of the parameters of the rotating speed ring are completed.
Fig. 3 and 4 show the comparison of the control effect of the rotating speed and the current of the existing control strategy without introducing the adaptive factor and the BP neural network with the control strategy based on the present invention, respectively. Wherein the control cycle of the rotating speed loop is 500 mus, and the control cycle of the current loop is 50 mus. The two experimental conditions are the same, including that the motor is started to rotate at 850rpm (left in figure 3 and left in figure 4) with load of 3Nm and at 400rpm (right in figure 3 and right in figure 4) with load of 5 Nm. Experimental results show that the control strategy before improvement is low in current dynamic response speed and poor in stability due to the fact that control parameters are not matched with complicated and variable actual operation conditions, and the rotation speed and current fluctuation is large during steady-state operation, while the control strategy after improvement is not limited by the operation conditions, can be automatically adjusted to the optimal control parameters, enhances the robustness of a controller, and ensures the dynamic response performance and the steady-state performance of the motor under various conditions.
It should be understood that, the sequence numbers of the steps in the embodiments of the present invention do not mean the execution sequence, and the execution sequence of each process should be determined by the function and the inherent logic of the process, and should not constitute any limitation on the implementation process of the embodiments of the present invention.
Although embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that changes, modifications, substitutions and alterations can be made in these embodiments without departing from the principles and spirit of the invention, the scope of which is defined in the appended claims and their equivalents.
Claims (5)
1. A permanent magnet synchronous motor self-adaptive integral sliding mode prediction control method is characterized by comprising the following steps: the method specifically comprises the following steps:
step one, constructing an equivalent mathematical model of the permanent magnet synchronous motor, and establishing a self-adaptive integral sliding mode prediction controller model aiming at a rotating speed ring and a current ring in sequence, wherein the sliding mode surfaces of the rotating speed ring and the current ring can be expressed as follows:
in the formula, s (t) and e (t) are respectively a sliding mode surface and a tracking error at the time t; c represents an integral gain coefficient and c > 0;
and adopts the following exponential approximation law:
wherein, the approach law coefficient q is more than 0, epsilon is more than 0, and the superscript is used for representing the first derivative of the corresponding parameter;
step two, in a sliding mode prediction controller model of the rotating speed ring, rotating speed ring s is converted ω First derivative of slip form surface
Introducing an adaptive factor, and improving the adaptive factor into the following form:
wherein the content of the first and second substances,
c ω integral gain coefficient of slip form face of rotating speed ring and c ω ＞0，ω m For the rotor mechanical angular speed, the superscripts indicate the reference values of the corresponding parameters;
selecting control parameters of a rotating speed loop sliding mode prediction controller model which enable the control performance to reach the optimal under different target rotating speeds and load torques: integral gain coefficient c ω And an approximation law coefficient q ω Lambda, a training set is established together with the corresponding target rotating speed and the corresponding load torque to train the BP neural network; the BP neural network takes a target rotating speed and a load torque as nodes of an input layer, c ω 、q ω And λ as an output layer node;
and step four, utilizing the trained BP neural network to combine with a sliding mode prediction controller model of the rotating speed loop and the current loop to realize the self-adaptive adjustment and control of the parameters of the rotating speed loop.
2. The method of claim 1, wherein: specifically, a voltage equation under the following rotating coordinate system is established for the permanent magnet synchronous motor in the first step:
in the formula u d And u q Stator voltage components of d and q axes respectively; i.e. i d And i q D and q axis stator current components respectively; r is s ，L s And Ψ f Respectively stator resistance, stator inductance and rotor permanent magnet flux, omega e Is the electrical angular velocity; t is a time variable;
and establishing the following electromagnetic torque equations and kinetic equations:
in the formula, T e Is an electromagnetic torque; p is the number of pole pairs, T l Is the load torque; b is viscous friction coefficient, and J is rotor moment of inertia;
after discretization is carried out by utilizing a first-order forward Euler formula, the concrete form of the sliding mode prediction controller model of the rotating speed ring is as follows:
in the formula, r ωlaw Representing the self-adaptive approach law of the rotating speed ring sliding mode prediction controller model; t is a control period of the rotating speed loop;
the concrete form of the sliding mode prediction controller model of the current loop is as follows:
wherein the content of the first and second substances,
s d,q sliding mode surface of d-and q-axis stator current of current loop controller, c d,q Is the integral gain coefficient of the current loop sliding mode surface and c d,q >0，r d,qlaw Represents the adaptive approach law, q, of a current loop sliding mode controller d,q Is an approximation law coefficient and q d,q ＞0，T s The period is controlled for the current loop.
3. The method of claim 2, wherein: in the sliding mode prediction controller model of the rotating speed ring, the sliding mode surface is specifically in the following form:
in the formula, the superscript indicates the second derivative of the corresponding parameter, and the subscript omega indicates each parameter corresponding to the rotating speed ring;
in the sliding mode prediction controller model of the current loop, the sliding mode surface is specifically in the following form:
in the formula, subscripts d and q are parameters of a d axis and a q axis corresponding to the current loop.
4. The method of claim 3, wherein: step three, the specific training process of the BP neural network comprises the following steps:
a. selecting optimal control parameters under different target rotating speeds and load torques, and constructing a training set comprising training samples and test samples;
b. training sample data normalization;
c. constructing a BP neural network model, setting training times, learning rate and minimum error parameters of a training target, setting hidden layer nodes as 5, and setting initial values of weight and bias;
d. normalizing the test sample;
e. predicting the test sample by using a BP neural network;
f. the prediction result is subjected to inverse normalization and is compared with a real value;
g. if the prediction result conforms to the expected error, ending the training, and outputting the weight and the bias of the neural network to obtain the trained BP neural network; otherwise, updating the weight and the bias, and repeating the steps d-g until the training is completed.
5. The method of claim 4, wherein: in the fourth step, the trained BP neural network is utilized, the target rotating speed and the load torque are firstly input, and the optimal parameter c is output ω 、q ω And λ;
then, the above-mentioned parameter c is used ω 、q ω And inputting the established sliding mode prediction controller model by lambda, and completing the parameter self-adaptive adjustment and control of the rotating speed ring.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210825408.7A CN115102444B (en) | 2022-07-14 | 2022-07-14 | Permanent magnet synchronous motor self-adaptive integral sliding mode prediction control method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210825408.7A CN115102444B (en) | 2022-07-14 | 2022-07-14 | Permanent magnet synchronous motor self-adaptive integral sliding mode prediction control method |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN115102444A true CN115102444A (en) | 2022-09-23 |
| CN115102444B CN115102444B (en) | 2024-04-12 |
Family
ID=83296927
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210825408.7A Active CN115102444B (en) | 2022-07-14 | 2022-07-14 | Permanent magnet synchronous motor self-adaptive integral sliding mode prediction control method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115102444B (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116599401A (en) * | 2023-05-18 | 2023-08-15 | 南京理工大学 | Permanent magnet synchronous motor speed regulation control method based on self-adaptive sliding mode approach law |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2013176228A (en) * | 2012-02-24 | 2013-09-05 | Inst Nuclear Energy Research Rocaec | Hybrid intelligent power control system and method |
| US20160301334A1 (en) * | 2015-04-10 | 2016-10-13 | The Board Of Trustees Of The University Of Alabama | Systems, methods and devices for vector control of induction machines using artificial neural networks |
| CN110165951A (en) * | 2019-04-22 | 2019-08-23 | 浙江工业大学 | A kind of bicyclic dead beat forecast Control Algorithm of permanent magnet synchronous motor based on disturbance estimation compensation |
| CN111342720A (en) * | 2020-03-06 | 2020-06-26 | 南京理工大学 | Permanent magnet synchronous motor self-adaptive continuous sliding mode control method based on load torque observation |
| US20200266743A1 (en) * | 2019-02-14 | 2020-08-20 | The Board Of Trustees Of The University Of Alabama | Systems, methods and devices for neural network control for ipm motor drives |
| CN111711396A (en) * | 2020-04-13 | 2020-09-25 | 山东科技大学 | Method for setting control parameters of speed ring of permanent magnet synchronous motor based on fractional order sliding mode controller |
| CN114374346A (en) * | 2021-11-29 | 2022-04-19 | 浙江国际海运职业技术学院 | High-performance control method for permanent magnet synchronous motor |
| WO2022134661A1 (en) * | 2020-12-21 | 2022-06-30 | 哈尔滨工业大学 | Method for selecting magnetization state of adjustable-flux permanent magnet synchronous motor in case of optimal control of full-speed domain efficiency and online control method |
-
2022
- 2022-07-14 CN CN202210825408.7A patent/CN115102444B/en active Active
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2013176228A (en) * | 2012-02-24 | 2013-09-05 | Inst Nuclear Energy Research Rocaec | Hybrid intelligent power control system and method |
| US20160301334A1 (en) * | 2015-04-10 | 2016-10-13 | The Board Of Trustees Of The University Of Alabama | Systems, methods and devices for vector control of induction machines using artificial neural networks |
| US20200266743A1 (en) * | 2019-02-14 | 2020-08-20 | The Board Of Trustees Of The University Of Alabama | Systems, methods and devices for neural network control for ipm motor drives |
| CN110165951A (en) * | 2019-04-22 | 2019-08-23 | 浙江工业大学 | A kind of bicyclic dead beat forecast Control Algorithm of permanent magnet synchronous motor based on disturbance estimation compensation |
| CN111342720A (en) * | 2020-03-06 | 2020-06-26 | 南京理工大学 | Permanent magnet synchronous motor self-adaptive continuous sliding mode control method based on load torque observation |
| CN111711396A (en) * | 2020-04-13 | 2020-09-25 | 山东科技大学 | Method for setting control parameters of speed ring of permanent magnet synchronous motor based on fractional order sliding mode controller |
| WO2022134661A1 (en) * | 2020-12-21 | 2022-06-30 | 哈尔滨工业大学 | Method for selecting magnetization state of adjustable-flux permanent magnet synchronous motor in case of optimal control of full-speed domain efficiency and online control method |
| CN114374346A (en) * | 2021-11-29 | 2022-04-19 | 浙江国际海运职业技术学院 | High-performance control method for permanent magnet synchronous motor |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116599401A (en) * | 2023-05-18 | 2023-08-15 | 南京理工大学 | Permanent magnet synchronous motor speed regulation control method based on self-adaptive sliding mode approach law |
| CN116599401B (en) * | 2023-05-18 | 2024-04-23 | 南京理工大学 | Permanent magnet synchronous motor speed regulation control method based on self-adaptive sliding mode approach law |
Also Published As
| Publication number | Publication date |
|---|---|
| CN115102444B (en) | 2024-04-12 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110572091B (en) | Optimized sensorless control method for permanent magnet synchronous motor | |
| CN107179682B (en) | Passive load simulator and redundant moment restraining method | |
| CN112731805B (en) | Wind power generator maximum power tracking sensorless robust control method based on wind speed estimation | |
| CN106788046B (en) | Permanent magnet synchronous motor command filtering finite time fuzzy control method | |
| CN110401391B (en) | Fuzzy self-adaptive dynamic surface control method for asynchronous motor stochastic system | |
| CN111711396B (en) | Method for setting motor speed loop control parameters based on fractional order sliding mode controller | |
| CN111193454B (en) | Construction method of switch reluctance hub motor vibration reduction and pulsation suppression composite control system | |
| CN115102444A (en) | Self-adaptive integral sliding mode prediction control method for permanent magnet synchronous motor | |
| CN111371357A (en) | Permanent magnet synchronous motor speed regulation control method based on self-adaptive supercoiling algorithm | |
| CN114509949A (en) | Control method for presetting performance of robot | |
| CN110247586B (en) | Efficiency optimization-based permanent magnet synchronous motor torque distribution method for electric bus | |
| CN113659895B (en) | Permanent magnet synchronous motor full-state constraint finite time control method based on instruction filtering | |
| CN114578697A (en) | Multi-constraint self-adaptive control method of motor-driven manipulator | |
| Rehman et al. | A fuzzy learning—Sliding mode controller for direct field-oriented induction machines | |
| CN106655962B (en) | Electric vehicle Induction Motor-Driven system control method based on extreme learning machine | |
| CN115566954B (en) | Embedded motor speed regulation control compensation method and system | |
| CN112019111B (en) | State constraint-based fuzzy self-adaptive control method for random system of permanent magnet synchronous motor | |
| CN106685295A (en) | Servo system friction processing method | |
| CN116015134A (en) | Permanent magnet synchronous motor fixed time integral sliding mode control method based on extended state observer | |
| CN113343592B (en) | Intelligent control method for DQN (direct current) of permanent magnet synchronous motor of new energy aircraft | |
| CN113890424B (en) | Parameter identification-based tuning method for PI controller of speed ring of permanent magnet synchronous motor | |
| CN113283090B (en) | Friction compensation method for electric servo system of airplane steering engine based on bee colony algorithm | |
| CN115133828A (en) | Permanent magnet synchronous motor control method and system | |
| CN111987955B (en) | Self-adaptive sliding mode control system and method for salient pole type permanent magnet synchronous motor | |
| CN112202378B (en) | Permanent magnet synchronous motor position control method based on boundary layer approaching law |
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 |