CN110007232A - A kind of prediction technique and relevant apparatus of squirrel cage asynchronous motor operational efficiency - Google Patents
A kind of prediction technique and relevant apparatus of squirrel cage asynchronous motor operational efficiency Download PDFInfo
- Publication number
- CN110007232A CN110007232A CN201910434258.5A CN201910434258A CN110007232A CN 110007232 A CN110007232 A CN 110007232A CN 201910434258 A CN201910434258 A CN 201910434258A CN 110007232 A CN110007232 A CN 110007232A
- Authority
- CN
- China
- Prior art keywords
- asynchronous motor
- squirrel cage
- cage asynchronous
- neural network
- prediction
- 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
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01R—MEASURING ELECTRIC VARIABLES; MEASURING MAGNETIC VARIABLES
- G01R31/00—Arrangements for testing electric properties; Arrangements for locating electric faults; Arrangements for electrical testing characterised by what is being tested not provided for elsewhere
- G01R31/34—Testing dynamo-electric machines
- G01R31/343—Testing dynamo-electric machines in operation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F30/00—Computer-aided design [CAD]
- G06F30/30—Circuit design
- G06F30/36—Circuit design at the analogue level
- G06F30/367—Design verification, e.g. using simulation, simulation program with integrated circuit emphasis [SPICE], direct methods or relaxation methods
Landscapes
- Engineering & Computer Science (AREA)
- Computer Hardware Design (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Microelectronics & Electronic Packaging (AREA)
- Evolutionary Computation (AREA)
- Geometry (AREA)
- General Engineering & Computer Science (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
- Control Of Electric Motors In General (AREA)
Abstract
This application discloses a kind of prediction techniques of squirrel cage asynchronous motor operational efficiency, including establish squirrel cage asynchronous motor simulation model；It is emulated to obtain emulation data to the squirrel cage asynchronous motor simulation model input harmonics voltage；BP neural network training, which is carried out, based on the emulation data obtains BP neural network prediction model；It obtains the actual operating data of current squirrel cage asynchronous motor and the actual operating data is inputted into the BP neural network prediction model and obtain the operational efficiency of the current squirrel cage asynchronous motor.The prediction technique can carry out the prediction of precise and high efficiency to the operational efficiency of all types of squirrel cage asynchronous motors, provide effective reference for the type selecting of squirrel cage asynchronous motor and use.Disclosed herein as well is forecasting system, device and the computer readable storage mediums of a kind of squirrel cage asynchronous motor operational efficiency, all have above-mentioned technical effect.
Description
Technical field
This application involves technical field of motors, in particular to a kind of prediction technique of squirrel cage asynchronous motor operational efficiency；
Further relate to forecasting system, device and the computer readable storage medium of a kind of squirrel cage asynchronous motor operational efficiency.
Background technique
With industrial continuous development, squirrel cage asynchronous motor is due to high revolving speed, high efficiency, larger speed tune
It controls the advantages such as range and is widely used.And with the aggravation of the power quality problems such as voltage distortion, harmonic wave, cause squirrel-cage different
It walks motor operation stability and operational efficiency declines, area especially poor in power quality, power grid is to squirrel cage asynchronous motor
The influence of operation stability and operational efficiency is particularly evident.In view of this, being carried out to the operational efficiency of squirrel cage asynchronous motor pre-
It surveys, is effectively asked with reference to the technology urgently to be resolved as those skilled in the art for the type selecting of squirrel cage asynchronous motor and using providing
Topic.
Summary of the invention
The purpose of the application is to provide a kind of prediction technique of squirrel cage asynchronous motor operational efficiency, can be to all types of
The operational efficiency of squirrel cage asynchronous motor carries out the prediction of precise and high efficiency；It is different that the another object of the application is to provide a kind of squirrel-cage
Forecasting system, device and the computer readable storage medium for walking motor operation efficiency, all have above-mentioned technical effect.
In order to solve the above technical problems, this application provides a kind of prediction technique of squirrel cage asynchronous motor operational efficiency,
Include:
Establish squirrel cage asynchronous motor simulation model；
It is emulated to obtain emulation data to the squirrel cage asynchronous motor simulation model input harmonics voltage；
BP neural network training, which is carried out, based on the emulation data obtains BP neural network prediction model；
It obtains the actual operating data of current squirrel cage asynchronous motor and the actual operating data is inputted into the BP mind
The operational efficiency of the current squirrel cage asynchronous motor is obtained through Network Prediction Model.
It is optionally, described to establish squirrel cage asynchronous motor simulation model, comprising:
The 2D of the squirrel cage asynchronous motor is established by Maxwell software based on the structural parameters of squirrel cage asynchronous motor
Electromagnetic finite meta-model；
Structural parameters based on the squirrel cage asynchronous motor establish the squirrel-cage asynchronism by Solid works software
The 3D stator structure model of motor；
Material parameter based on the squirrel cage asynchronous motor establishes the squirrel-cage asynchronism electricity by Workbench software
The electromagnetic field of machine and the coupling model of structure field.
Optionally, described to be emulated to obtain emulation number to the squirrel cage asynchronous motor simulation model input harmonics voltage
According to, comprising:
It is imitated respectively to squirrel cage asynchronous motor simulation model input single harmonic component voltage with multiple harmonic voltage
Really obtain corresponding operation curve；Wherein, the operation curve includes: that torque curve, electric power curves and mechanical output are bent
Line；
Read when the squirrel cage asynchronous motor stable state corresponding data on the operation curve；
The torque changing value and electric efficiency value of the squirrel cage asynchronous motor are obtained according to the data.
Optionally, described that BP neural network is trained based on the emulation data to obtain BP neural network prediction mould
Type, comprising:
The BP neural network after particle swarm algorithm optimization is trained based on the emulation data to obtain the BP nerve
Network Prediction Model.
Optionally, described that the BP neural network after particle swarm algorithm optimization is trained to obtain based on the emulation data
The BP neural network prediction model, comprising:
Initialize the BP neural network and the particle swarm algorithm；
Based on the emulation data after normalized, using the particle swarm algorithm be iterated optimizing obtain it is optimal
Threshold value and best initial weights；
Using the optimal threshold and the best initial weights as the initial value of the BP neural network, and it is based on the emulation number
According to being trained to obtain the BP neural network prediction model to the BP neural network.
In order to solve the above technical problems, present invention also provides a kind of prediction systems of squirrel cage asynchronous motor operational efficiency
System, comprising:
Model building module, for establishing squirrel cage asynchronous motor simulation model；
Harmonic voltage input module, for being emulated to the squirrel cage asynchronous motor simulation model input harmonics voltage
Obtain emulation data；
Neural metwork training module obtains BP neural network for carrying out BP neural network training based on the emulation data
Prediction model；
Operational efficiency prediction module, for obtaining the actual operating data of current squirrel cage asynchronous motor and by the reality
Operation data inputs the BP neural network prediction model and obtains the operational efficiency of the squirrel cage asynchronous motor.
Optionally, the neural metwork training module is specifically used for after being optimized based on the emulation data to particle swarm algorithm
BP neural network be trained to obtain the BP neural network prediction model.
In order to solve the above technical problems, present invention also provides a kind of prediction of squirrel cage asynchronous motor operational efficiency dresses
It sets, comprising:
Memory, for storing computer program；
Processor realizes squirrel cage asynchronous motor fortune as described in any one of the above embodiments when for executing the computer program
The step of prediction technique of line efficiency.
In order to solve the above technical problems, the computer can present invention also provides a kind of computer readable storage medium
It reads storage medium and is stored with computer program, the computer program is realized as described in any one of the above embodiments when being executed by processor
The step of prediction technique of squirrel cage asynchronous motor operational efficiency.
The prediction technique of squirrel cage asynchronous motor operational efficiency provided herein, including establish squirrel cage asynchronous motor
Simulation model；It is emulated to obtain emulation data to the squirrel cage asynchronous motor simulation model input harmonics voltage；Based on institute
It states emulation data progress BP neural network training and obtains BP neural network prediction model；Obtain the reality of current squirrel cage asynchronous motor
The actual operating data is simultaneously inputted the BP neural network prediction model to obtain the current squirrel-cage different by border operation data
Walk the operational efficiency of motor.
As it can be seen that the prediction technique of squirrel cage asynchronous motor operational efficiency provided herein, different by establishing squirrel-cage
Simulation model of motor is walked, and input harmonics voltage is emulated to squirrel cage asynchronous motor simulation model and largely emulated
Data, and then BP neural network training is carried out based on this emulation data, obtain the BP mind suitable for universal squirrel cage asynchronous motor
Through Network Prediction Model, thus when carrying out operational efficiency prediction, by the actual operating data of corresponding squirrel cage asynchronous motor
Inputting this BP neural network can be obtained corresponding operational efficiency, realize the operational efficiency to all types of squirrel cage asynchronous motors
Accurate, efficient prediction, provide effective reference for the type selecting of squirrel cage asynchronous motor and use.
It the forecasting system of the operational efficiency of squirrel cage asynchronous motor provided herein, device and computer-readable deposits
Storage media all has above-mentioned technical effect.
Detailed description of the invention
It in order to more clearly explain the technical solutions in the embodiments of the present application, below will be to needed in the embodiment
Attached drawing is briefly described, it should be apparent that, the drawings in the following description are only some examples of the present application, for ability
For the those of ordinary skill of domain, without creative efforts, it can also be obtained according to these attached drawings other attached
Figure.
Fig. 1 shows for a kind of process of the prediction technique of squirrel cage asynchronous motor operational efficiency provided by the embodiment of the present application
It is intended to；
Fig. 2 is a kind of signal of the forecasting system of squirrel cage asynchronous motor operational efficiency provided by the embodiment of the present application
Figure；
Fig. 3 is a kind of signal of the prediction meanss of squirrel cage asynchronous motor operational efficiency provided by the embodiment of the present application
Figure.
Specific embodiment
The core of the application is to provide a kind of prediction technique of squirrel cage asynchronous motor operational efficiency, can be to all types of
The operational efficiency of squirrel cage asynchronous motor carries out the prediction of precise and high efficiency；It is different that the another object of the application is to provide a kind of squirrel-cage
Forecasting system, device and the computer readable storage medium for walking motor operation efficiency, all have above-mentioned technical effect.
To keep the purposes, technical schemes and advantages of the embodiment of the present application clearer, below in conjunction with the embodiment of the present application
In attached drawing, the technical scheme in the embodiment of the application is clearly and completely described, it is clear that described embodiment is
Some embodiments of the present application, instead of all the embodiments.Based on the embodiment in the application, those of ordinary skill in the art
Every other embodiment obtained without making creative work, shall fall in the protection scope of this application.
Referring to FIG. 1, Fig. 1 is a kind of prediction side of squirrel cage asynchronous motor operational efficiency provided by the embodiment of the present application
The flow diagram of method；In conjunction with Fig. 1, which includes:
S101: squirrel cage asynchronous motor simulation model is established；
Specifically, this step is intended to establish squirrel cage asynchronous motor simulation model, specifically establishes under different air gap width and have
There are multiple squirrel cage asynchronous motor simulation models of identical capacity, to be emulated using each squirrel cage asynchronous motor simulation model
Operation, obtains largely emulating data, the building for BP neural network prediction model provides data basis.
In a kind of specific embodiment, above-mentioned squirrel cage asynchronous motor simulation model of establishing may include: based on mouse
The structural parameters of cage asynchronous machine establish the 2D electromagnetic finite meta-model of squirrel cage asynchronous motor by Maxwell software；Base
The 3D stator structure mould of squirrel cage asynchronous motor is established by Solid works software in the structural parameters of squirrel cage asynchronous motor
Type；Based on the material parameter of squirrel cage asynchronous motor by Workbench software establish the electromagnetic field of squirrel cage asynchronous motor with
The coupling model of structure field.Can specifically be respectively set squirrel cage asynchronous motor width of air gap be 0.5mm, 1mm and 1.5mm,
Squirrel cage asynchronous motor simulation model is established by above-mentioned simulation software.
S102: it is emulated to obtain emulation data to squirrel cage asynchronous motor simulation model input harmonics voltage；
Specifically, for known to 3 subharmonic:
To which the magnetomotive force of 3 subharmonic synthesis can be obtained are as follows:
As it can be seen that the magnetomotive force of 3 subharmonic synthesis is zero, and in symmetrical squirrel cage asynchronous motor, 3 multiple subharmonic synthesis
Magnetomotive force also there is above-mentioned property, i.e., the magnetomotive force of 3 multiple subharmonic synthesis is zero, for example, the magnetic of 9 subharmonic synthesis
Kinetic potential is that the magnetomotive force of zero, 15 subharmonic synthesis is zero.
In addition, being mainly 5 subharmonic, 7 subharmonic and 11 by the harmonic wave for influencing squirrel cage asynchronous motor known to analysis
Subharmonic, it is thus determined that input voltage are as follows:
Wherein, UHC0、UHC5、UHC7、UHC11Respectively fundamental wave content, 5 subharmonic contents, 7 subharmonic contents and 11 times are humorous
Wave content.And harmonic contentIn above formula, i indicates harmonic wave type, when i=7, corresponding UHC7As 7 times
Harmonic content, UrmsFor virtual value, UhnFor nth harmonic.
Further, defeated to the squirrel cage asynchronous motor simulation model under each width of air gap according to the input voltage of above-mentioned determination
Enter harmonic voltage to be emulated to obtain emulation data.
It is above-mentioned to be imitated to squirrel cage asynchronous motor simulation model input harmonics voltage in a kind of specific embodiment
Emulation data are really obtained, including respectively to squirrel cage asynchronous motor simulation model input single harmonic component voltage and multiple harmonic voltage
It is emulated to obtain corresponding operation curve；Wherein, operation curve includes: torque curve, electric power curves and mechanical output
Curve；Corresponding data on operation curve when reading squirrel cage asynchronous motor stable state；Squirrel cage asynchronous motor is obtained according to data
Torque changing value and electric efficiency value.
Specifically, single harmonic component voltage, so-called single harmonic component electricity can be inputted to squirrel cage asynchronous motor simulation model first
Pressure only contains comprising fundamental wave content with any harmonic wave in above-mentioned 5 subharmonic content, 7 subharmonic contents, 11 subharmonic contents
The harmonic voltage of amount, such as only comprising fundamental wave content and 5 subharmonic contents, then the harmonic voltage inputted are as follows:
It certainly, can be by the single harmonic component electricity comprising fundamental wave content and 5 subharmonic contents to obtain a large amount of emulation data
Pressure, the single harmonic component voltage comprising fundamental wave content and 7 subharmonic contents and the list comprising fundamental wave content Yu 11 subharmonic contents
Input squirrel cage asynchronous motor simulation model is emulated subharmonic voltage respectively, to obtain under all kinds of single harmonic component voltages
Operation curve.
Further, as a control group, then to squirrel cage asynchronous motor simulation model multiple harmonic voltage is inputted.Relative to list
Subharmonic voltage, multiple harmonic voltage are to contain comprising fundamental wave content and above-mentioned 5 subharmonic content, 7 subharmonic contents, 11 subharmonic
The harmonic voltage of the harmonic content of any combination in amount.For example, including fundamental wave content, 5 subharmonic contents and 11 subharmonic
Content, the then harmonic voltage inputted are as follows:
Equally, to obtain a large amount of emulation data, the harmonic voltage under all kinds of combined situations can be inputted squirrel-cage asynchronism
Simulation model of motor is emulated, and then obtains the operation curve under all kinds of multiple harmonic voltages.
Further, (including the torque curve, electricity of the operation curve in the case where obtaining single harmonic component voltage and multiple harmonic voltage
Power curve and mechanical output curve) on the basis of, it is counted accordingly on operation curve when reading squirrel cage asynchronous motor stable state
According to, and respectively correspond to obtain squirrel cage asynchronous motor under single harmonic component voltage and multiple harmonic voltage according to the data of reading
Torque changing value and electric efficiency value.
Specifically, reading corresponding torque data when squirrel cage asynchronous motor stable state from torque curve, and then basisObtain torque mean valueIn above formula, n is the data volume read, for example, that reads is humorous comprising fundamental wave content and 5 times
Under the single harmonic component voltage of wave content, width of air gap be 1mm squirrel cage asynchronous motor torque data data volume；TiFor mouse
Cage asynchronous machine reaches torque instantaneous value when stable state.Further, according toCurrent harmonic voltage is calculated
The torque changing value Δ T of lower cage formula asynchronous machine；Wherein, T in above formulanFor nominal torque.In addition, being read from electric power curves
Corresponding electrical power data when taking squirrel cage asynchronous motor stable state, and according toElectrical power mean value is calculatedN is the data volume read, pjReach electrical power instantaneous value when stable state for squirrel cage asynchronous motor.And from mechanical work
Corresponding mechanical output data when reading squirrel cage asynchronous motor stable state on rate curve, and according toIt is calculated
Mechanical output mean valueN is the data volume read, pmMechanical output when reaching stable state for squirrel cage asynchronous motor is instantaneous
Value.Further, according toThe electric efficiency value of squirrel cage asynchronous motor is calculated.
S103: BP neural network training is carried out based on emulation data and obtains BP neural network prediction model；
Specifically, one three layers (including input layer, hidden layer and output layer) of BP mind can be constructed in MATLAB software
BP neural network training is carried out through network, and then using a large amount of emulation data obtained through the above steps, obtains BP nerve
Network Prediction Model carries out operational efficiency prediction with this BP neural network prediction model of later use.
It is above-mentioned that BP neural network is trained based on emulation data to obtain BP nerve in a kind of specific embodiment
Network Prediction Model, including based on emulation data, the BP neural network after being optimized using particle swarm algorithm is trained to obtain BP
Neural network prediction model.
Specifically, for Support Training result, the forecasting accuracy of raising BP neural network prediction model, the present embodiment is utilized
Particle swarm algorithm optimizes BP neural network, and then is trained to obtain to the BP neural network after particle swarm algorithm optimization
BP neural network prediction model.
In a kind of specific embodiment, it is above-mentioned based on emulation data to particle swarm algorithm optimization after BP neural network
It is trained to obtain BP neural network prediction model, including initialization BP neural network and particle swarm algorithm；Based on normalization
Emulation data that treated, are iterated optimizing using particle swarm algorithm and obtain optimal threshold and best initial weights；By optimal threshold
Initial value with best initial weights as BP neural network, and BP neural network is trained to obtain BP nerve net based on emulation data
Network prediction model.
Specifically, initialization BP neural network, be arranged particle swarm algorithm parameter (including setting population scale, evolve
Number, speed undated parameter, individual extreme value and population extreme value).Emulation data are normalized, and based on normalization
Treated, and emulation data carry out the optimizing of particle swarm algorithm iteration, generate fitness curve, and judge based on this fitness curve
Whether particle swarm algorithm meets error precision or reaches maximum number of iterations, if so, exiting particle swarm algorithm, and will change at this time
In generation, obtains weight and threshold value i.e. best initial weights and initial value of the optimal threshold as BP neural network, further, utilizes emulation data
BP neural network is trained to obtain BP neural network prediction model.In addition, can also from emulation data in selected part data
BP neural network is inputted as prediction data, and after the prediction data is normalized, obtains prediction output data, into
One step carries out anti-normalization processing to prediction output data.
S104: obtaining the actual operating data of current squirrel cage asynchronous motor and actual operating data is inputted BP nerve net
Network prediction model obtains the operational efficiency of current squirrel cage asynchronous motor.
Specifically, when the operational efficiency for needing to predict the i.e. current defeated squirrel cage asynchronous motor of some squirrel cage asynchronous motor
When, obtain the actual operating data of the squirrel cage asynchronous motor first, including harmonic wave type, harmonic content, width of air gap and
Torque changing value, and BP neural network prediction model is inputted using above-mentioned actual operating data as input quantity, BP neural network is pre-
The output quantity for surveying model is operational efficiency.
In conclusion the prediction technique of squirrel cage asynchronous motor operational efficiency provided herein, by establishing mouse cage
Formula asynchronous machine simulation model, and input harmonics voltage to squirrel cage asynchronous motor simulation model is emulated and is obtained largely
Data are emulated, and then carry out BP neural network training based on this emulation data, are obtained suitable for universal squirrel cage asynchronous motor
BP neural network prediction model, thus when carrying out operational efficiency prediction, by the actual motion of corresponding squirrel cage asynchronous motor
Data, which input this BP neural network, can be obtained corresponding operational efficiency, realize the operation to all types of squirrel cage asynchronous motors
Accurate, the efficient prediction of efficiency, provides effective reference for the type selecting of squirrel cage asynchronous motor and use.
Present invention also provides a kind of forecasting system of squirrel cage asynchronous motor operational efficiency, the system described below can
To correspond to each other reference with method as described above.Referring to FIG. 2, Fig. 2 is a kind of squirrel-cage provided by the embodiment of the present application
The schematic diagram of the forecasting system of asynchronous machine operational efficiency, in conjunction with Fig. 2, which includes:
Model building module 10, for establishing squirrel cage asynchronous motor simulation model；
Harmonic voltage input module 20, for emulate to squirrel cage asynchronous motor simulation model input harmonics voltage
To emulation data；
Neural metwork training module 30, it is pre- for obtaining BP neural network using emulation data progress BP neural network training
Survey model；
Operational efficiency prediction module 40, for obtaining the actual operating data of current squirrel cage asynchronous motor and by practical fortune
Row data input BP neural network prediction model obtains the operational efficiency of current squirrel cage asynchronous motor.
On the basis of the above embodiments, optionally, neural metwork training module 30 is specifically used for based on emulation data pair
BP neural network after particle swarm algorithm optimization is trained to obtain BP neural network prediction model.
Present invention also provides a kind of prediction meanss of squirrel cage asynchronous motor operational efficiency, refering to what is shown in Fig. 3, the prediction
Device includes: memory 11 and processor 12；
Wherein, memory 11 is for storing computer program；It is realized when processor 12 is for executing computer program as follows
The step of:
Establish squirrel cage asynchronous motor simulation model；It is imitated to squirrel cage asynchronous motor simulation model input harmonics voltage
Really obtain emulation data；BP neural network training, which is carried out, using emulation data obtains BP neural network prediction model；It obtains current
Actual operating data input BP neural network prediction model is simultaneously obtained current mouse by the actual operating data of squirrel cage asynchronous motor
The operational efficiency of cage asynchronous machine.
The embodiment of the above method is please referred to for the introduction of prediction meanss provided herein, the application is not done herein
It repeats.
Present invention also provides a kind of computer readable storage medium, calculating is stored on the computer readable storage medium
Machine program, the computer program realize following step when being executed by processor:
Establish squirrel cage asynchronous motor simulation model；It is imitated to squirrel cage asynchronous motor simulation model input harmonics voltage
Really obtain emulation data；BP neural network training, which is carried out, using emulation data obtains BP neural network prediction model；It obtains current
Actual operating data input BP neural network prediction model is simultaneously obtained current mouse by the actual operating data of squirrel cage asynchronous motor
The operational efficiency of cage asynchronous machine.
The computer readable storage medium may include: USB flash disk, mobile hard disk, read-only memory (Read-Only
Memory, ROM), random access memory (Random Access Memory, RAM), magnetic or disk etc. is various to deposit
Store up the medium of program code.
Above method embodiment is please referred to for the introduction of computer readable storage medium provided by the present invention, the present invention
This will not be repeated here.
Each embodiment is described in a progressive manner in specification, the highlights of each of the examples are with other realities
The difference of example is applied, the same or similar parts in each embodiment may refer to each other.For device disclosed in embodiment, dress
Set and computer readable storage medium for, since it is corresponded to the methods disclosed in the examples, thus description comparison it is simple
Single, reference may be made to the description of the method.
Professional further appreciates that, unit described in conjunction with the examples disclosed in the embodiments of the present disclosure
And algorithm steps, can be realized with electronic hardware, computer software, or a combination of the two, in order to clearly demonstrate hardware and
The interchangeability of software generally describes each exemplary composition and step according to function in the above description.These
Function is implemented in hardware or software actually, the specific application and design constraint depending on technical solution.Profession
Technical staff can use different methods to achieve the described function each specific application, but this realization is not answered
Think beyond scope of the present application.
The step of method described in conjunction with the examples disclosed in this document or algorithm, can directly be held with hardware, processor
The combination of capable software module or the two is implemented.Software module can be placed in random access memory (RAM), memory, read-only deposit
Reservoir (ROM), electrically programmable ROM, electrically erasable programmable ROM, register, hard disk, moveable magnetic disc, CD-ROM or technology
In any other form of storage medium well known in field.
Above to prediction technique, system, device and the meter of squirrel cage asynchronous motor operational efficiency provided herein
Calculation machine readable storage medium storing program for executing is described in detail.Specific case used herein to the principle and embodiment of the application into
Elaboration is gone, the description of the example is only used to help understand the method for the present application and its core ideas.It should be pointed out that pair
For those skilled in the art, under the premise of not departing from the application principle, the application can also be carried out
Some improvements and modifications, these improvement and modification also fall into the protection scope of the claim of this application.
Claims (9)
1. a kind of prediction technique of squirrel cage asynchronous motor operational efficiency characterized by comprising
Establish squirrel cage asynchronous motor simulation model；
It is emulated to obtain emulation data to the squirrel cage asynchronous motor simulation model input harmonics voltage；
BP neural network training, which is carried out, based on the emulation data obtains BP neural network prediction model；
It obtains the actual operating data of current squirrel cage asynchronous motor and the actual operating data is inputted into the BP nerve net
Network prediction model obtains the operational efficiency of the current squirrel cage asynchronous motor.
2. prediction technique according to claim 1, which is characterized in that it is described to establish squirrel cage asynchronous motor simulation model,
Include:
The 2D electromagnetism of the squirrel cage asynchronous motor is established by Maxwell software based on the structural parameters of squirrel cage asynchronous motor
Finite element model；
Structural parameters based on the squirrel cage asynchronous motor establish the squirrel cage asynchronous motor by Solid works software
3D stator structure model；
Material parameter based on the squirrel cage asynchronous motor establishes the squirrel cage asynchronous motor by Workbench software
The coupling model of electromagnetic field and structure field.
3. prediction technique according to claim 1, which is characterized in that described to the squirrel cage asynchronous motor simulation model
Input harmonics voltage is emulated to obtain emulation data, comprising:
Emulate to squirrel cage asynchronous motor simulation model input single harmonic component voltage and multiple harmonic voltage respectively
To corresponding operation curve；Wherein, the operation curve includes: torque curve, electric power curves and mechanical output curve；
Read when the squirrel cage asynchronous motor stable state corresponding data on the operation curve；
The torque changing value and electric efficiency value of the squirrel cage asynchronous motor are obtained according to the data.
4. prediction technique according to claim 1, which is characterized in that described to be based on the emulation data to BP neural network
It is trained to obtain BP neural network prediction model, comprising:
The BP neural network after particle swarm algorithm optimization is trained to obtain the BP neural network based on the emulation data
Prediction model.
5. prediction technique according to claim 4, which is characterized in that described to be based on the emulation data to particle swarm algorithm
BP neural network after optimization is trained to obtain the BP neural network prediction model, comprising:
Initialize the BP neural network and the particle swarm algorithm；
Based on the emulation data after normalized, optimizing is iterated using the particle swarm algorithm and obtains optimal threshold
With best initial weights；
Using the optimal threshold and the best initial weights as the initial value of the BP neural network, and it is based on the emulation data pair
The BP neural network is trained to obtain the BP neural network prediction model.
6. a kind of forecasting system of squirrel cage asynchronous motor operational efficiency characterized by comprising
Model building module, for establishing squirrel cage asynchronous motor simulation model；
Harmonic voltage input module, for being emulated to obtain to the squirrel cage asynchronous motor simulation model input harmonics voltage
Emulate data；
Neural metwork training module obtains BP neural network prediction for carrying out BP neural network training based on the emulation data
Model；
Operational efficiency prediction module, for obtaining the actual operating data of current squirrel cage asynchronous motor and by the actual motion
Data input the BP neural network prediction model and obtain the operational efficiency of the squirrel cage asynchronous motor.
7. forecasting system according to claim 6, which is characterized in that the neural metwork training module is specifically used for being based on
The emulation data are trained to obtain the BP neural network prediction model to the BP neural network after particle swarm algorithm optimization.
8. a kind of prediction meanss of squirrel cage asynchronous motor operational efficiency characterized by comprising
Memory, for storing computer program；
Processor is realized when for executing the computer program such as squirrel-cage asynchronism electricity described in any one of claim 1 to 5
The step of prediction technique of machine operational efficiency.
9. a kind of computer readable storage medium, which is characterized in that the computer-readable recording medium storage has computer journey
Sequence realizes that squirrel cage asynchronous motor described in any one of claim 1 to 5 such as is transported when the computer program is executed by processor
The step of prediction technique of line efficiency.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910434258.5A CN110007232B (en) | 2019-05-23 | 2019-05-23 | Method and related device for predicting running efficiency of squirrel-cage asynchronous motor |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910434258.5A CN110007232B (en) | 2019-05-23 | 2019-05-23 | Method and related device for predicting running efficiency of squirrel-cage asynchronous motor |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN110007232A true CN110007232A (en) | 2019-07-12 |
| CN110007232B CN110007232B (en) | 2021-09-03 |
Family
ID=67177738
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910434258.5A Expired - Fee Related CN110007232B (en) | 2019-05-23 | 2019-05-23 | Method and related device for predicting running efficiency of squirrel-cage asynchronous motor |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110007232B (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110187276A (en) * | 2019-06-12 | 2019-08-30 | 广东电网有限责任公司 | The analysis method that harmonic wave influences the operating status of three-phase induction motor |
| EP3907568A1 (en) * | 2020-05-08 | 2021-11-10 | Siemens Aktiengesellschaft | Method and systems for providing a simulation model of an electric rotary machine |
Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JPH05161265A (en) * | 1991-11-28 | 1993-06-25 | Toshiba Corp | Power system monitor |
| WO1997049977A1 (en) * | 1996-06-24 | 1997-12-31 | Arcelik A.S. | Model-based fault detection system for electric motors |
| CN102536774A (en) * | 2011-12-27 | 2012-07-04 | 酒泉钢铁(集团)有限责任公司 | Operation characteristics and operation energy efficiency analyzing device of industrial circulating water pump set |
| CN103344368A (en) * | 2013-06-26 | 2013-10-09 | 华北电力大学 | Squirrel-cage type asynchronous motor energy efficiency online monitoring method based on measurable electrical amount |
| CN104283393A (en) * | 2014-09-25 | 2015-01-14 | 南京工程学院 | Method for optimizing structure parameter of single-winding magnetic suspension switch reluctance machine |
| CN105740562A (en) * | 2016-02-04 | 2016-07-06 | 华北电力科学研究院有限责任公司 | Determination method for no-load characteristic curve of power generator |
| CN107179503A (en) * | 2017-04-21 | 2017-09-19 | 美林数据技术股份有限公司 | The method of Wind turbines intelligent fault diagnosis early warning based on random forest |
| CN108205110A (en) * | 2016-12-20 | 2018-06-26 | 北京金风科创风电设备有限公司 | The detection method and device of generator of wind generating set failure |
| CN108932580A (en) * | 2018-06-05 | 2018-12-04 | 浙江运达风电股份有限公司 | Wind turbines pitch variable bearings wear monitoring and method for early warning based on data modeling |
-
2019
- 2019-05-23 CN CN201910434258.5A patent/CN110007232B/en not_active Expired - Fee Related
Patent Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JPH05161265A (en) * | 1991-11-28 | 1993-06-25 | Toshiba Corp | Power system monitor |
| WO1997049977A1 (en) * | 1996-06-24 | 1997-12-31 | Arcelik A.S. | Model-based fault detection system for electric motors |
| CN102536774A (en) * | 2011-12-27 | 2012-07-04 | 酒泉钢铁(集团)有限责任公司 | Operation characteristics and operation energy efficiency analyzing device of industrial circulating water pump set |
| CN103344368A (en) * | 2013-06-26 | 2013-10-09 | 华北电力大学 | Squirrel-cage type asynchronous motor energy efficiency online monitoring method based on measurable electrical amount |
| CN104283393A (en) * | 2014-09-25 | 2015-01-14 | 南京工程学院 | Method for optimizing structure parameter of single-winding magnetic suspension switch reluctance machine |
| CN105740562A (en) * | 2016-02-04 | 2016-07-06 | 华北电力科学研究院有限责任公司 | Determination method for no-load characteristic curve of power generator |
| CN108205110A (en) * | 2016-12-20 | 2018-06-26 | 北京金风科创风电设备有限公司 | The detection method and device of generator of wind generating set failure |
| CN107179503A (en) * | 2017-04-21 | 2017-09-19 | 美林数据技术股份有限公司 | The method of Wind turbines intelligent fault diagnosis early warning based on random forest |
| CN108932580A (en) * | 2018-06-05 | 2018-12-04 | 浙江运达风电股份有限公司 | Wind turbines pitch variable bearings wear monitoring and method for early warning based on data modeling |
Non-Patent Citations (1)
| Title |
|---|
| 苗敬利 等: "基于逐层预测模型的感应电机效率优化滑模控制", 《电工技术学报》 * |
Cited By (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110187276A (en) * | 2019-06-12 | 2019-08-30 | 广东电网有限责任公司 | The analysis method that harmonic wave influences the operating status of three-phase induction motor |
| EP3907568A1 (en) * | 2020-05-08 | 2021-11-10 | Siemens Aktiengesellschaft | Method and systems for providing a simulation model of an electric rotary machine |
| WO2021224003A1 (en) * | 2020-05-08 | 2021-11-11 | Siemens Aktiengesellschaft | Method and systems for providing a simulation model of an electric rotating machine |
| KR20230003300A (en) * | 2020-05-08 | 2023-01-05 | 지멘스 악티엔게젤샤프트 | Method and system for providing simulation models of electric rotating machines |
| KR102559570B1 (en) | 2020-05-08 | 2023-07-25 | 지멘스 악티엔게젤샤프트 | Method and system for providing simulation models of electric rotating machines |
| US11790135B2 (en) | 2020-05-08 | 2023-10-17 | Siemens Aktiengesellschaft | Method and systems for provision of a simulation model of an electric rotating machine |
| EP4303673A3 (en) * | 2020-05-08 | 2024-03-13 | Siemens Aktiengesellschaft | Methods and systems for providing a simulation model of an electric rotary machine |
Also Published As
| Publication number | Publication date |
|---|---|
| CN110007232B (en) | 2021-09-03 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| JP7087079B2 (en) | Robust gradient weight compression scheme for deep learning applications | |
| Chen et al. | Improved gravitational search algorithm for parameter identification of water turbine regulation system | |
| Li et al. | Parameters identification of hydraulic turbine governing system using improved gravitational search algorithm | |
| Abhyankar et al. | Solution techniques for transient stability‐constrained optimal power flow–Part I | |
| Li et al. | Piecewise function based gravitational search algorithm and its application on parameter identification of AVR system | |
| CN110007232A (en) | A kind of prediction technique and relevant apparatus of squirrel cage asynchronous motor operational efficiency | |
| Naik et al. | Multiobjective virtual machine selection for task scheduling in cloud computing | |
| Luccioni et al. | Estimating carbon emissions of artificial intelligence [opinion] | |
| Wang et al. | AP-Cloud: Adaptive Particle-in-Cloud method for optimal solutions to Vlasov–Poisson equation | |
| CN106168993A (en) | Electrical network real-time simulation analysis platform | |
| CN115730407A (en) | Motor vibration noise analysis method, device, equipment and storage medium | |
| US20090254319A1 (en) | Method and system for numerical simulation of a multiple-equation system of equations on a multi-processor core system | |
| Eswaran et al. | Augmented intelligent water drops optimisation model for virtual machine placement in cloud environment | |
| CN110504706A (en) | The transient stability prediction technique and device of virtual synchronous generator connecting in parallel with system | |
| CN104424012B (en) | Method and apparatus for providing self-defined virtual bench | |
| Bokhove et al. | From Bore–Soliton–Splash to a new wave-to-wire wave-energy model | |
| Zhai et al. | Solving the Savage–Hutter equations for granular avalanche flows with a second‐order Godunov type method on GPU | |
| Malagoli et al. | Optimal electromagnetic torque of the induction motor generated automatically with Gmsh/GetDP software | |
| Li et al. | Interactive elastic motion editing through space–time position constraints | |
| Concepcion et al. | On extended-term dynamic simulations with high penetrations of photovoltaic generation | |
| JP2023544290A (en) | Determination and use of spectral embedding of large systems by substructuring | |
| Jiang et al. | Real-time cloth simulation based on improved verlet algorithm | |
| Giacobbe et al. | J2CBROKER: A Service Broker Simulation Tool For Cooperative Clouds. | |
| CN104519096B (en) | Method and system for the deployment services in cloud computing system | |
| Zaspel et al. | Photorealistic visualization and fluid animation: coupling of Maya with a two-phase Navier-Stokes fluid solver |
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 | ||
| CF01 | Termination of patent right due to non-payment of annual fee |
Granted publication date: 20210903 |
|
| CF01 | Termination of patent right due to non-payment of annual fee |