CN116317800A - Permanent magnet synchronous motor temperature prediction method and system based on temperature time sequence input - Google Patents
Permanent magnet synchronous motor temperature prediction method and system based on temperature time sequence input Download PDFInfo
- Publication number
- CN116317800A CN116317800A CN202310187530.0A CN202310187530A CN116317800A CN 116317800 A CN116317800 A CN 116317800A CN 202310187530 A CN202310187530 A CN 202310187530A CN 116317800 A CN116317800 A CN 116317800A
- Authority
- CN
- China
- Prior art keywords
- temperature
- permanent magnet
- synchronous motor
- magnet synchronous
- input
- 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.)
- Pending
Links
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
- H02P23/00—Arrangements or methods for the control of AC motors characterised by a control method other than vector control
- H02P23/0004—Control strategies in general, e.g. linear type, e.g. P, PI, PID, using robust control
- H02P23/0022—Model reference adaptation, e.g. MRAS or MRAC, useful for control or parameter estimation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F30/00—Computer-aided design [CAD]
- G06F30/20—Design optimisation, verification or simulation
-
- 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
- H02P23/00—Arrangements or methods for the control of AC motors characterised by a control method other than vector control
- H02P23/0004—Control strategies in general, e.g. linear type, e.g. P, PI, PID, using robust control
- H02P23/0031—Control strategies in general, e.g. linear type, e.g. P, PI, PID, using robust control implementing a off line learning phase to determine and store useful data for on-line 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
- H02P23/00—Arrangements or methods for the control of AC motors characterised by a control method other than vector control
- H02P23/0077—Characterised by the use of a particular software algorithm
-
- 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
- H02P23/00—Arrangements or methods for the control of AC motors characterised by a control method other than vector control
- H02P23/14—Estimation or adaptation of motor parameters, e.g. rotor time constant, flux, speed, 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
- H02P29/00—Arrangements for regulating or controlling electric motors, appropriate for both AC and DC motors
- H02P29/60—Controlling or determining the temperature of the motor or of the drive
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2119/00—Details relating to the type or aim of the analysis or the optimisation
- G06F2119/08—Thermal analysis or thermal optimisation
-
- 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
- Y02T—CLIMATE CHANGE MITIGATION TECHNOLOGIES RELATED TO TRANSPORTATION
- Y02T10/00—Road transport of goods or passengers
- Y02T10/60—Other road transportation technologies with climate change mitigation effect
- Y02T10/64—Electric machine technologies in electromobility
Landscapes
- Engineering & Computer Science (AREA)
- Power Engineering (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Databases & Information Systems (AREA)
- Computer Hardware Design (AREA)
- Evolutionary Computation (AREA)
- Geometry (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Control Of Ac Motors In General (AREA)
Abstract
The invention relates to a permanent magnet synchronous motor temperature prediction method and a permanent magnet synchronous motor temperature prediction system based on temperature time sequence input, wherein the method comprises the following steps: acquiring a parameter sequence in the running process of the permanent magnet synchronous motor through a data acquisition system, and extracting a conventional model input; based on conventional model input, selecting a certain moment in the running process of the permanent magnet synchronous motor as an initial moment, and adding an initial temperature sequence and a time difference sequence; acquiring the temperature difference of a cooling water inlet and a cooling water outlet in the running process of the permanent magnet synchronous motor, and taking the temperature difference as the augmentation input of a model; and according to the conventional model input, the initial temperature sequence, the time difference sequence and the amplification input, carrying out feature selection, constructing a model input feature set for permanent magnet synchronous motor temperature prediction, and loading the model input feature set into a permanent magnet synchronous motor temperature prediction model to obtain the internal temperature of the permanent magnet synchronous motor. Compared with the prior art, the method expands the application range of various machine learning algorithms in the field of permanent magnet synchronous motor temperature prediction, and improves the prediction accuracy and calculation speed of the model.
Description
Technical Field
The invention relates to the technical field of motor temperature prediction, in particular to a permanent magnet synchronous motor temperature prediction method and system based on temperature time sequence input.
Background
The method has the advantages that the internal temperature field information of the permanent magnet synchronous motor (Permanent Magnet Synchronous Motor, PMSM) is estimated through the prediction means, the method has a large research value and good application prospect, the internal temperature field of the permanent magnet synchronous motor can be predicted through the structural data or the operation parameters of the motor under the condition that the operation of the motor is not influenced, the service life of the motor is prolonged, and the reliability of an electric driving system is improved. Since the machine learning method is driven by the data set, for the permanent magnet synchronous motor temperature prediction model based on the machine learning algorithm, the determination of model input is critical to the prediction accuracy and calculation speed of the model.
At present, the determination of a temperature prediction model input set of the permanent magnet synchronous motor depends on mechanism analysis and manual experience, and conventional model input is obtained by analyzing the coupling relation between a thermal force field and an electric field, a magnetic field and the like, wherein the conventional model input comprises electromagnetic related physical quantities (such as voltage and current), cooling conditions (such as cooling water temperature and flow), operation conditions (such as torque and rotating speed) and the like. However, conventional model inputs do not contain temperature timing information, and most are only suitable for machine learning algorithms with timing prediction capabilities, which also puts limitations on the machine learning algorithms used for temperature prediction modeling.
The invention discloses a real-time prediction method for the rotor temperature of a permanent magnet synchronous motor, which selects 8 variables as model inputs based on a mathematical model of a motion equation and a current equation under a synchronous rotation coordinate system of rotor flux orientation, namely d-axis voltage, q-axis voltage, d-axis current, q-axis current, mechanical angular speed, load torque, the running environment temperature of the motor and cooling liquid temperature, and establishes an LSTM-CNN network prediction model for predicting the real-time temperature of the rotor of the permanent magnet synchronous motor.
The invention with publication number CN112395815A discloses a temperature prediction method of a permanent magnet synchronous motor, which constructs a PSNLSTMs model for predicting the temperature of the permanent magnet synchronous motor, wherein model inputs comprise continuous moment environment temperature, cooling liquid temperature, motor rotating speed, motor torque, d-axis voltage, q-axis voltage, d-axis current and q-axis current, and the model inputs have 8 dimensions in total.
The invention with publication number CN112183835A discloses a machine learning-based water guide shoe temperature trend early warning method, device and system, which determine input factors influencing the water guide shoe temperature through multiple experiments and priori experience, and further establish a neural network-based water guide shoe temperature prediction model, wherein model input comprises the following steps: the output of the unit, the oil temperature of the outlet 1, the oil temperature of the outlet 2, the swing degree 1 and the swing degree 2.
The invention with publication number CN114444382A discloses a wind turbine generator gearbox fault diagnosis analysis method based on a machine learning algorithm, which obtains 16 operation parameters of a wind field site as model inputs to predict temperatures, including wind speed, wind power, gearbox oil temperature, wind direction, yaw angle, pitch angle, voltage, current, generator instantaneous rotation speed, grid active power, gearbox intermediate shaft driving end bearing temperature, gearbox intermediate shaft non-driving end bearing temperature, motor side gearbox high-speed shaft bearing temperature, gearbox lubricating oil pool temperature, gearbox lubricating oil inlet temperature and gearbox oil way filter screen front oil pressure.
According to the scheme, the motor temperature prediction model input set is determined according to a physical mechanism and priori experience, the model input set comprises related variables such as an electric field, a magnetic field, a thermal force field and an operation condition, but the model input set does not comprise a temperature time sequence, so that the model input set is only suitable for a machine learning algorithm with time sequence prediction capability, and for other non-time sequence prediction machine learning algorithms, the model input set cannot make up for the defect of the time sequence prediction capability. In addition, the scheme directly uses the motor operation parameters, does not carry out input augmentation and feature selection, and does not necessarily obtain the optimal or better model input set.
Disclosure of Invention
The invention aims to overcome the defects of the prior art and provide a permanent magnet synchronous motor temperature prediction method and a permanent magnet synchronous motor temperature prediction system based on temperature time sequence input, which overcome the defects of a machine learning algorithm without time sequence prediction capability.
The aim of the invention can be achieved by the following technical scheme:
a permanent magnet synchronous motor temperature prediction method based on temperature time sequence input comprises the following steps:
acquiring a parameter sequence in the running process of the permanent magnet synchronous motor through a data acquisition system, and extracting a conventional model input;
based on the conventional model input, a certain moment in the running process of the permanent magnet synchronous motor is selected as an initial moment, a temperature sequence and a time difference sequence are added, wherein the temperature sequence is the motor temperature at the initial moment, and the time difference sequence is a timing difference value between the follow-up running moment of the permanent magnet synchronous motor and the initial moment;
acquiring the temperature difference of a cooling water inlet and a cooling water outlet in the running process of the permanent magnet synchronous motor, and taking the temperature difference as the augmentation input of a model;
according to the conventional model input, the temperature sequence, the time difference sequence and the augmentation input, carrying out feature selection, and constructing a model input feature set for permanent magnet synchronous motor temperature prediction;
and loading the model input feature set into a pre-established permanent magnet synchronous motor temperature prediction model to obtain the internal temperature of the permanent magnet synchronous motor.
Further, the model input feature set includes a time difference, an initial time temperature, a cooling variable, an electromagnetic variable, and an operating condition, the cooling variable including an ambient temperature, a cooling water inlet temperature, a cooling water outlet temperature, and a cooling water flow rate.
Further, the electromagnetic variables include bus voltage, bus current, three-phase voltage, and three-phase current, and the operating conditions include rotational speed and torque.
Further, the feature selection is performed in combination with recursive feature elimination and principal component analysis.
Further, the permanent magnet synchronous motor temperature prediction model is a machine learning model, and the machine learning model is a Gaussian process regression model.
The invention also provides a permanent magnet synchronous motor temperature prediction system based on temperature time sequence input, which comprises:
the conventional model input acquisition module is used for acquiring a parameter sequence in the running process of the permanent magnet synchronous motor through the data acquisition system and extracting conventional model input;
the time sequence increasing module is used for selecting a certain moment in the running process of the permanent magnet synchronous motor as an initial moment based on the conventional model input, adding a temperature sequence and a time difference sequence, wherein the temperature sequence is the motor temperature at the initial moment, and the time difference sequence is the timing difference value between the follow-up running moment of the permanent magnet synchronous motor and the initial moment;
the input augmentation module is used for acquiring the temperature difference of the cooling water inlet and outlet in the running process of the permanent magnet synchronous motor and taking the temperature difference as the augmentation input of the model;
the feature selection module is used for carrying out feature selection according to the conventional model input, the temperature sequence, the time difference sequence and the augmentation input, and constructing a model input feature set for permanent magnet synchronous motor temperature prediction;
and the temperature prediction module is used for loading the model input feature set into a pre-established permanent magnet synchronous motor temperature prediction model to obtain the internal temperature of the permanent magnet synchronous motor.
Further, the model input feature set includes a time difference, an initial time temperature, a cooling variable, an electromagnetic variable, and an operating condition, the cooling variable including an ambient temperature, a cooling water inlet temperature, a cooling water outlet temperature, and a cooling water flow rate.
Further, the electromagnetic variables include bus voltage, bus current, three-phase voltage, and three-phase current, and the operating conditions include rotational speed and torque.
Further, the feature selection is performed in combination with recursive feature elimination and principal component analysis.
Further, the permanent magnet synchronous motor temperature prediction model is a machine learning model, and the machine learning model is a Gaussian process regression model.
Compared with the prior art, the invention has the following advantages:
(1) According to the invention, by means of motor operation mechanism and machine learning knowledge, a permanent magnet synchronous motor temperature prediction model input set containing temperature time sequence is obtained through feature engineering, and the temperature field information in the motor can be rapidly and accurately predicted by acquiring the 15 parameter values of the motor operation time. The model input set is obtained through input augmentation and feature selection, on one hand, the prediction precision and the calculation speed of the model are improved, and proper data information is fully utilized; on the other hand, the defect that part of machine learning algorithms cannot conduct time sequence prediction is overcome to a certain extent, so that more machine learning algorithms can be used for predicting the internal temperature field of the permanent magnet synchronous motor.
(2) According to the invention, an initial temperature sequence and a time difference sequence are added to construct a model input set containing temperature time sequence information, temperature and time sequence attributes are added for data samples in a training set and a test set, and the application range of a machine learning algorithm in the field of permanent magnet synchronous motor temperature prediction is widened.
(3) The invention combines different feature selection methods to construct the optimal model input set, simplifies the number of model inputs, extracts data information beneficial to model prediction precision and calculation speed, and improves model performance.
(4) The permanent magnet synchronous motor temperature prediction model input set containing the temperature sequence designed according to the invention is subjected to machine learning modeling and experimental verification, and proves that the model input set shows superiority in improving the model performance.
The specific application process is as follows: after conventional model inputs from the sensors are selected using laboratory-acquired motor operating data, using human experience and physical knowledge, temperature and time series are supplemented and model inputs are augmented. Finally, based on the model input, the feature selection is carried out by combining the recursive feature elimination and the principal component analysis method, a permanent magnet synchronous motor temperature prediction model input set containing a temperature time sequence is finally established, and the comparison of prediction results shows that the model prediction precision after the initial temperature sequence and the time difference sequence are added is greatly improved, and the model prediction performance and the calculation speed after the feature selection are also remarkably improved.
Drawings
Fig. 1 is a schematic flow chart of a permanent magnet synchronous motor temperature prediction method based on temperature time sequence input provided in an embodiment of the invention;
fig. 2 is a flow chart of the construction of a model input set according to an embodiment of the present invention.
Detailed Description
For the purpose of making the objects, technical solutions and advantages of the embodiments of the present invention more apparent, the technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention, and it is apparent that the described embodiments are some embodiments of the present invention, but not all embodiments of the present invention. The components of the embodiments of the present invention generally described and illustrated in the figures herein may be arranged and designed in a wide variety of different configurations.
Thus, the following detailed description of the embodiments of the invention, as presented in the figures, is not intended to limit the scope of the invention, as claimed, but is merely representative of selected embodiments of the invention. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
It should be noted that: like reference numerals and letters denote like items in the following figures, and thus once an item is defined in one figure, no further definition or explanation thereof is necessary in the following figures.
In the description of the present invention, it should be noted that, directions or positional relationships indicated by terms such as "center", "upper", "lower", "left", "right", "vertical", "horizontal", "inner", "outer", etc., are directions or positional relationships based on those shown in the drawings, or are directions or positional relationships conventionally put in use of the inventive product, are merely for convenience of describing the present invention and simplifying the description, and are not indicative or implying that the apparatus or element to be referred to must have a specific direction, be constructed and operated in a specific direction, and thus should not be construed as limiting the present invention.
It should be noted that the terms "first," "second," and "second" are used for descriptive purposes only and are not to be construed as indicating or implying a relative importance or implying a number of technical features being indicated. Thus, a feature defining "a first" or "a second" may explicitly or implicitly include one or more such feature. In the description of the present application, the meaning of "a plurality" is two or more, unless explicitly defined otherwise.
Furthermore, the terms "horizontal," "vertical," and the like do not denote a requirement that the component be absolutely horizontal or overhang, but rather may be slightly inclined. As "horizontal" merely means that its direction is more horizontal than "vertical", and does not mean that the structure must be perfectly horizontal, but may be slightly inclined.
Example 1
As shown in fig. 1, the embodiment provides a permanent magnet synchronous motor temperature prediction method based on temperature time sequence input, the determination of a model input set combines knowledge in the field of computer science and physical mechanism of the permanent magnet synchronous motor, and based on raw data directly collected by a sensor in the motor operation process, feature extraction and augmentation are performed, and finally a final model input set is determined through feature selection, so that temperature prediction is performed.
The method specifically comprises the following steps:
s1: acquiring a parameter sequence in the running process of the permanent magnet synchronous motor through a data acquisition system, and extracting a conventional model input;
s2: based on conventional model input, selecting a certain moment in the running process of the permanent magnet synchronous motor as an initial moment, adding a temperature sequence and a time difference sequence, wherein the temperature sequence is the motor temperature at the initial moment, and the time difference sequence is the timing difference value between the follow-up running moment of the permanent magnet synchronous motor and the initial moment;
s3: acquiring the temperature difference of a cooling water inlet and a cooling water outlet in the running process of the permanent magnet synchronous motor, and taking the temperature difference as the augmentation input of a model;
s4: according to conventional model input, temperature sequence, time difference sequence and amplification input, performing feature selection by combining recursive feature elimination and principal component analysis, and constructing a model input feature set for permanent magnet synchronous motor temperature prediction;
s5: and loading the model input feature set into a pre-established permanent magnet synchronous motor temperature prediction model to obtain the internal temperature of the permanent magnet synchronous motor.
The model input feature set comprises a time difference, an initial moment temperature, a cooling variable, an electromagnetic variable and an operation working condition, wherein the cooling variable comprises an ambient temperature, a cooling water inlet temperature, a cooling water outlet temperature, cooling water flow and the like; the electromagnetic variables comprise bus voltage, bus current, three-phase voltage, three-phase current and the like, and the operation conditions comprise rotating speed, torque and the like. The model output is the internal temperature of the permanent magnet synchronous motor.
The above-described scheme is specifically described below.
1. Conventional input directly from the sensor
Based on literature investigation results and motor physical structure knowledge, taking influence of factors such as cooling conditions and operation conditions into consideration, laboratory original data of parameters collected by the sensors are initially selected as model input, wherein the model input comprises environment temperature, cooling water inlet temperature, cooling water outlet temperature, cooling water flow, bus voltage, bus current, three-phase voltage (3 voltage values), three-phase current (3 current values), rotating speed and torque.
2. Adding temperature and timing information
Because the model built by part of the machine learning algorithm has no time series attribute, and the internal temperature of the permanent magnet synchronous motor is a series variable which is continuously changed along with time, the time series attribute among the data samples is supplemented. Taking any time point in the running process of the motor as an initial time, taking the time difference between the subsequent running time of the motor and the initial time into a model input set, and simultaneously taking the temperature of the motor at the initial time as a model input to add a time sequence prediction attribute to the machine learning modeling process.
3. Supplementing new model inputs
Since building new model inputs in combination with existing model inputs is considered one of the effective ways to build the best feature set, model inputs are augmented based on the model inputs described above.
Because the internal temperature of the motor is greatly influenced by the cooling condition of the motor, the cooling factors in the running process of the motor are supplemented, and the temperature difference of the cooling water inlet and outlet is used as the augmentation input of the model.
4. Combining feature selection methods to obtain final model inputs
The obtained model input set comprises conventional input, temperature and time sequence information and augmented model input which are directly acquired by a sensor, and two feature selection methods of recursive feature elimination and principal component analysis are combined in order to avoid the reduction of model accuracy caused by the over-fitting phenomenon.
The final model input set contains: ambient temperature, cooling water inlet temperature, cooling water outlet temperature, cooling water flow, bus voltage, bus current, three-phase voltage (3 voltage values), three-phase current (3 current values), rotation speed, time difference and initial time temperature. Wherein the time difference and the initial time temperature are used to provide temperature timing information.
In the running process of the motor, the parameters are obtained by direct or indirect means, and a machine learning model, such as a Gaussian process regression model, is established, so that the internal temperature predicted value of the permanent magnet synchronous motor can be rapidly and accurately obtained.
As shown in fig. 2, a specific implementation of the present scheme is provided below:
1. firstly, a data acquisition system is utilized to acquire a parameter sequence in the running process of the permanent magnet synchronous motor.
2. Secondly, extracting the input of a conventional model directly acquired by a sensor, wherein the input comprises the following steps: ambient temperature, cooling water inlet temperature, cooling water outlet temperature, cooling water flow, bus voltage, bus current, three-phase voltage (3 voltage values), three-phase current (3 current values), rotational speed, torque.
3. Then, based on the input of a conventional model, a moment in the operation stage of the permanent magnet synchronous motor is selected as an initial moment, a temperature sequence and a time difference sequence are added, and a time sequence prediction attribute is added for the machine learning modeling process. Wherein the temperature sequence is based on the motor temperature at the initial time obtained by direct or indirect means, and the time difference sequence is the timing difference between the subsequent operation time of the motor and the initial time.
4. Then, the existing model input is combined, cooling factors in the running process of the motor are supplemented, and the temperature difference of the cooling water inlet and outlet is used as the model amplification input.
5. Finally, aiming at the model input, the model input set is subjected to feature selection by combining recursive feature elimination and principal component analysis, and a corresponding model is established, and the finally obtained model input feature set for permanent magnet synchronous motor temperature prediction comprises time difference, initial moment temperature, cooling water temperature difference, environment temperature, cooling water inlet temperature, cooling water outlet temperature, cooling water flow, bus voltage, bus current, three-phase voltage (3 voltage values), three-phase current (3 current values), rotating speed, torque and the like.
The foregoing describes a method embodiment, and the following further describes a system embodiment.
The embodiment also provides a permanent magnet synchronous motor temperature prediction system based on temperature time sequence input, which comprises:
the conventional model input acquisition module is used for acquiring a parameter sequence in the running process of the permanent magnet synchronous motor through the data acquisition system and extracting conventional model input;
the time sequence increasing module is used for selecting a certain moment in the operation process of the permanent magnet synchronous motor as an initial moment based on the input of a conventional model, adding a temperature sequence and a time difference sequence, wherein the temperature sequence is the motor temperature at the initial moment, and the time difference sequence is the timing difference value between the follow-up operation moment of the permanent magnet synchronous motor and the initial moment;
the input augmentation module is used for acquiring the temperature difference of the cooling water inlet and outlet in the running process of the permanent magnet synchronous motor and taking the temperature difference as the augmentation input of the model;
the feature selection module is used for carrying out feature selection according to the conventional model input, the temperature sequence, the time difference sequence and the augmentation input, and constructing a model input feature set for the temperature prediction of the permanent magnet synchronous motor;
the temperature prediction module is used for loading the model input feature set into a pre-established permanent magnet synchronous motor temperature prediction model to obtain the internal temperature of the permanent magnet synchronous motor.
The specific content and the beneficial effects of the device of the present application can be referred to the above method embodiments, and are not described herein.
The foregoing describes in detail preferred embodiments of the present invention. It should be understood that numerous modifications and variations can be made in accordance with the concepts of the invention by one of ordinary skill in the art without undue burden. Therefore, all technical solutions which can be obtained by logic analysis, reasoning or limited experiments based on the prior art by the person skilled in the art according to the inventive concept shall be within the scope of protection defined by the claims.
Claims (10)
1. The permanent magnet synchronous motor temperature prediction method based on temperature time sequence input is characterized by comprising the following steps of:
acquiring a parameter sequence in the running process of the permanent magnet synchronous motor through a data acquisition system, and extracting a conventional model input;
based on the conventional model input, a certain moment in the running process of the permanent magnet synchronous motor is selected as an initial moment, a temperature sequence and a time difference sequence are added, wherein the temperature sequence is the motor temperature at the initial moment, and the time difference sequence is a timing difference value between the follow-up running moment of the permanent magnet synchronous motor and the initial moment;
acquiring the temperature difference of a cooling water inlet and a cooling water outlet in the running process of the permanent magnet synchronous motor, and taking the temperature difference as the augmentation input of a model;
according to the conventional model input, the temperature sequence, the time difference sequence and the augmentation input, carrying out feature selection, and constructing a model input feature set for permanent magnet synchronous motor temperature prediction;
and loading the model input feature set into a pre-established permanent magnet synchronous motor temperature prediction model to obtain the internal temperature of the permanent magnet synchronous motor.
2. The method for predicting the temperature of the permanent magnet synchronous motor based on temperature time sequence input according to claim 1, wherein the model input feature set comprises a time difference, an initial time temperature, a cooling variable, an electromagnetic variable and an operation condition, and the cooling variable comprises an ambient temperature, a cooling water inlet temperature, a cooling water outlet temperature and a cooling water flow.
3. The method for predicting temperature of a permanent magnet synchronous motor based on temperature time sequence input of claim 2, wherein the electromagnetic variables comprise bus voltage, bus current, three-phase voltage and three-phase current, and the operation conditions comprise rotation speed and torque.
4. The method for predicting temperature of a permanent magnet synchronous motor based on temperature time sequence input according to claim 1, wherein the feature selection is performed in combination with recursive feature elimination and principal component analysis.
5. The permanent magnet synchronous motor temperature prediction method based on temperature time sequence input of claim 1, wherein the permanent magnet synchronous motor temperature prediction model is a machine learning model, and the machine learning model is a Gaussian process regression model.
6. A permanent magnet synchronous motor temperature prediction system based on temperature time sequence input, comprising:
the conventional model input acquisition module is used for acquiring a parameter sequence in the running process of the permanent magnet synchronous motor through the data acquisition system and extracting conventional model input;
the time sequence increasing module is used for selecting a certain moment in the running process of the permanent magnet synchronous motor as an initial moment based on the conventional model input, adding a temperature sequence and a time difference sequence, wherein the temperature sequence is the motor temperature at the initial moment, and the time difference sequence is the timing difference value between the follow-up running moment of the permanent magnet synchronous motor and the initial moment;
the input augmentation module is used for acquiring the temperature difference of the cooling water inlet and outlet in the running process of the permanent magnet synchronous motor and taking the temperature difference as the augmentation input of the model;
the feature selection module is used for carrying out feature selection according to the conventional model input, the temperature sequence, the time difference sequence and the augmentation input, and constructing a model input feature set for permanent magnet synchronous motor temperature prediction;
and the temperature prediction module is used for loading the model input feature set into a pre-established permanent magnet synchronous motor temperature prediction model to obtain the internal temperature of the permanent magnet synchronous motor.
7. The temperature timing input-based permanent magnet synchronous motor temperature prediction system according to claim 6, wherein the model input feature set comprises a time difference, an initial time temperature, a cooling variable, an electromagnetic variable and an operating condition, and the cooling variable comprises an ambient temperature, a cooling water inlet temperature, a cooling water outlet temperature and a cooling water flow.
8. The temperature-time-series-input-based permanent magnet synchronous motor temperature prediction system according to claim 7, wherein the electromagnetic variables comprise bus voltage, bus current, three-phase voltage and three-phase current, and the operation conditions comprise rotational speed and torque.
9. A temperature-time-series-input-based permanent magnet synchronous motor temperature prediction system according to claim 6, wherein the feature selection is performed in combination with recursive feature elimination and principal component analysis.
10. The temperature timing input-based permanent magnet synchronous motor temperature prediction system according to claim 6, wherein the permanent magnet synchronous motor temperature prediction model is a machine learning model, and the machine learning model is a gaussian process regression model.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310187530.0A CN116317800A (en) | 2023-02-28 | 2023-02-28 | Permanent magnet synchronous motor temperature prediction method and system based on temperature time sequence input |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310187530.0A CN116317800A (en) | 2023-02-28 | 2023-02-28 | Permanent magnet synchronous motor temperature prediction method and system based on temperature time sequence input |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN116317800A true CN116317800A (en) | 2023-06-23 |
Family
ID=86780868
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310187530.0A Pending CN116317800A (en) | 2023-02-28 | 2023-02-28 | Permanent magnet synchronous motor temperature prediction method and system based on temperature time sequence input |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116317800A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117496133A (en) * | 2024-01-03 | 2024-02-02 | 山东工商学院 | Closed bus R-CNN temperature fault monitoring method based on multi-mode data |
-
2023
- 2023-02-28 CN CN202310187530.0A patent/CN116317800A/en active Pending
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117496133A (en) * | 2024-01-03 | 2024-02-02 | 山东工商学院 | Closed bus R-CNN temperature fault monitoring method based on multi-mode data |
| CN117496133B (en) * | 2024-01-03 | 2024-03-22 | 山东工商学院 | Closed bus R-CNN temperature fault monitoring method based on multi-mode data |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Li et al. | Self-attention ConvLSTM and its application in RUL prediction of rolling bearings | |
| Choqueuse et al. | Diagnosis of three-phase electrical machines using multidimensional demodulation techniques | |
| CN114813105A (en) | Gear box fault early warning method and system based on working condition similarity evaluation | |
| CN116317800A (en) | Permanent magnet synchronous motor temperature prediction method and system based on temperature time sequence input | |
| Jiménez-Guarneros et al. | Diagnostic of combined mechanical and electrical faults in ASD-powered induction motor using MODWT and a lightweight 1-D CNN | |
| CN107701468B (en) | A kind of online integrated monitoring of mixed-flow pump and device | |
| Chen et al. | Novel data-driven approach based on capsule network for intelligent multi-fault detection in electric motors | |
| CN114004512A (en) | Multi-unit operation state outlier analysis method and system based on density clustering | |
| CN112539827B (en) | Unit mechanical vibration evaluation method and system based on frequency energy ratio | |
| Sultonov et al. | INTEL-PFC-FD: Artificial Intelligence Approaches for Power Factor Correction and Multiple Fault Diagnosis in Three Phase Induction Motor | |
| CN113655778A (en) | Underwater propeller fault diagnosis system and method based on time-frequency energy | |
| Li et al. | Joint threshold learning convolutional networks for intelligent fault diagnosis under nonstationary conditions | |
| Dabetwar et al. | Mass imbalance diagnostics in wind turbines using deep learning with data augmentation | |
| CN113128047A (en) | Aero-engine thrust calculation method, storage medium and calculation device | |
| Wang et al. | DTC of induction motor based on adaptive sliding mode control | |
| CN104793137B (en) | A kind of abnormal load type identification method based on motor movement characteristic value | |
| CN114320773B (en) | Wind turbine generator system fault early warning method based on power curve analysis and neural network | |
| CN114781259A (en) | Wind driven generator diagnosis method and system | |
| CN109653945A (en) | A kind of wind power generating set load shedding method and system | |
| CN114282580A (en) | Visual image-based permanent magnet driving motor demagnetization fault diagnosis model construction method and fault diagnosis method and system | |
| Dişli et al. | Deep transfer learning-based broken rotor fault diagnosis for Induction Motors | |
| CN116699390B (en) | Diesel engine set fault detection method and system | |
| Xing et al. | Multi-task learning for the bearing based on a one-dimensional convolutional neural network with attention guidance mechanism and multi-scale feature extraction | |
| Zhao et al. | Refined composite hierarchical multiscale Lempel-Ziv complexity: A quantitative diagnostic method of multi-feature fusion for rotating energy devices | |
| Chen et al. | A Bearing Health Monitoring Method Based on Interpretable Improved GoogLeNet |
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 |