CN116845936A - Intelligent control method of flywheel energy storage device - Google Patents
Intelligent control method of flywheel energy storage device Download PDFInfo
- Publication number
- CN116845936A CN116845936A CN202311119946.5A CN202311119946A CN116845936A CN 116845936 A CN116845936 A CN 116845936A CN 202311119946 A CN202311119946 A CN 202311119946A CN 116845936 A CN116845936 A CN 116845936A
- Authority
- CN
- China
- Prior art keywords
- fault
- control
- prediction
- determining
- energy storage
- 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
- 238000004146 energy storage Methods 0.000 title claims abstract description 95
- 238000000034 method Methods 0.000 title claims abstract description 41
- 238000012544 monitoring process Methods 0.000 claims abstract description 76
- 230000001360 synchronised effect Effects 0.000 claims abstract description 43
- 230000000694 effects Effects 0.000 claims abstract description 18
- 230000003399 chemotactic effect Effects 0.000 claims abstract description 7
- 238000012549 training Methods 0.000 claims description 30
- 238000012795 verification Methods 0.000 claims description 22
- 238000004458 analytical method Methods 0.000 claims description 20
- 238000004364 calculation method Methods 0.000 claims description 11
- 238000006243 chemical reaction Methods 0.000 claims description 10
- 230000001276 controlling effect Effects 0.000 claims description 10
- 230000004044 response Effects 0.000 claims description 9
- 230000008859 change Effects 0.000 claims description 8
- 238000004088 simulation Methods 0.000 claims description 8
- 238000010276 construction Methods 0.000 claims description 7
- 238000012545 processing Methods 0.000 claims description 6
- 230000000007 visual effect Effects 0.000 claims description 6
- 238000004891 communication Methods 0.000 claims description 5
- 238000012937 correction Methods 0.000 claims description 5
- 238000013506 data mapping Methods 0.000 claims description 5
- 230000004913 activation Effects 0.000 claims description 4
- 230000002596 correlated effect Effects 0.000 claims description 4
- 238000013528 artificial neural network Methods 0.000 claims description 3
- 238000012423 maintenance Methods 0.000 abstract description 2
- 230000000875 corresponding effect Effects 0.000 description 10
- 238000005457 optimization Methods 0.000 description 4
- 238000010586 diagram Methods 0.000 description 3
- 238000003062 neural network model Methods 0.000 description 3
- 230000035605 chemotaxis Effects 0.000 description 2
- 238000013500 data storage Methods 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 230000010354 integration Effects 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000013433 optimization analysis Methods 0.000 description 2
- 230000008569 process Effects 0.000 description 2
- 230000001105 regulatory effect Effects 0.000 description 2
- 230000003044 adaptive effect Effects 0.000 description 1
- 230000004075 alteration Effects 0.000 description 1
- 239000003990 capacitor Substances 0.000 description 1
- 230000004069 differentiation Effects 0.000 description 1
- 238000005265 energy consumption Methods 0.000 description 1
- 238000013507 mapping Methods 0.000 description 1
- 238000007619 statistical method Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/901—Indexing; Data structures therefor; Storage structures
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
-
- H—ELECTRICITY
- H02—GENERATION; CONVERSION OR DISTRIBUTION OF ELECTRIC POWER
- H02J—CIRCUIT ARRANGEMENTS OR SYSTEMS FOR SUPPLYING OR DISTRIBUTING ELECTRIC POWER; SYSTEMS FOR STORING ELECTRIC ENERGY
- H02J3/00—Circuit arrangements for ac mains or ac distribution networks
- H02J3/28—Arrangements for balancing of the load in a network by storage of energy
- H02J3/30—Arrangements for balancing of the load in a network by storage of energy using dynamo-electric machines coupled to flywheels
-
- 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
- Y02E—REDUCTION OF GREENHOUSE GAS [GHG] EMISSIONS, RELATED TO ENERGY GENERATION, TRANSMISSION OR DISTRIBUTION
- Y02E60/00—Enabling technologies; Technologies with a potential or indirect contribution to GHG emissions mitigation
- Y02E60/16—Mechanical energy storage, e.g. flywheels or pressurised fluids
Abstract
The application relates to the technical field of intelligent control, and provides an intelligent control method of a flywheel energy storage device, which comprises the following steps: constructing a fault database; determining a target power supply parameter based on a power supply scene, and determining an initialization control parameter; configuring a step interval, inputting an operation prediction model by combining a target power supply parameter and an initialization control parameter, and outputting a time sequence control link; acquiring synchronous monitoring data; configuring a preset step length and determining a chemotactic state; if the trend state meets the trend threshold, the adjustment and control of the time sequence control link are carried out, the technical problem of low control precision of the flywheel energy storage device is solved, the synchronous fault prediction, energy supply prediction and control adjustment are realized, the control precision and the use efficiency of the flywheel energy storage device are improved, the flywheel energy storage device can be better adapted to various special application scenes, meanwhile, the intelligent control method can also reduce the manual intervention and maintenance cost, reduce the equipment operation cost and improve the technical effects of the reliability and the safety of the equipment.
Description
Technical Field
The application relates to the technical field of intelligent control, in particular to an intelligent control method of a flywheel energy storage device.
Background
The flywheel energy storage device consists of a wheel rotating at high speed and a motor or a generator, stores energy by converting mechanical energy into electric energy and converts the electric energy back into mechanical energy when needed, and is widely applied to the fields of electric power systems, aerospace, transportation and the like.
PID (proportion integration differentiation, proportional-differential integral) control technology is the most common control technology of the flywheel energy storage device, and the output power of the flywheel energy storage device is controlled by adjusting parameters such as the rotation speed, the angular speed and the like of the flywheel, but on one hand, if the system is unstable, PID control may not effectively control the parameters such as the rotation speed, the angular speed and the like of the flywheel; on the other hand, if the parameters such as the flywheel rotational speed, the angular velocity, etc. are excessively adjusted, the energy storage device may be out of control or damaged. Therefore, the conventional flywheel energy storage device control method generally has the problems of low control precision, low use efficiency and the like.
In summary, the technical problem of low control accuracy of the flywheel energy storage device in the prior art exists.
Disclosure of Invention
The application provides an intelligent control method of a flywheel energy storage device, and aims to solve the technical problem of low control precision of the flywheel energy storage device in the prior art.
In view of the above problems, the present application provides an intelligent control method for a flywheel energy storage device.
According to a first aspect of the disclosure, an intelligent control method of a flywheel energy storage device is provided, wherein the method comprises the following steps: calling a historical fault record in a preset time window of the frequency converter, and constructing a fault database; determining a target power supply parameter based on a power supply scene, and determining an initialization control parameter, wherein the target power supply parameter and the initialization control parameter are dynamic parameters in a preset time interval; the step length interval is configured, an operation prediction model is input by combining the target power supply parameter and the initialization control parameter, a time sequence control link is output, the operation prediction model comprises a fault prediction branch, an energy supply prediction branch and a control tuning unit, and the fault database is embedded in the fault prediction branch; performing variable frequency control and operation monitoring of the target device based on the time sequence control link to acquire synchronous monitoring data; configuring a preset step length, calling the synchronous monitoring data based on the preset step length, and performing correction analysis with the target power supply parameters to determine a trend change state; and if the trend state meets the trend threshold, adjusting and controlling the time sequence control link.
In another aspect of the disclosure, an intelligent control system of a flywheel energy storage device is provided, where the system includes: the database construction module is used for calling a historical fault record in a preset time window of the frequency converter and constructing a fault database; the control parameter determining module is used for determining a target power supply parameter based on a power supply scene and determining an initialization control parameter, wherein the target power supply parameter and the initialization control parameter are dynamic parameters in a preset time interval; the time sequence control link output module is used for configuring a step interval, inputting an operation prediction model by combining the target power supply parameter and the initialization control parameter, and outputting a time sequence control link, wherein the operation prediction model comprises a fault prediction branch, an energy supply prediction branch and a control tuning unit, and the fault prediction branch is embedded with the fault database; the synchronous monitoring data acquisition module is used for carrying out variable frequency control and operation monitoring on the target device based on the time sequence control link to acquire synchronous monitoring data; the calibration analysis module is used for configuring a preset step length, calling the synchronous monitoring data based on the preset step length, performing calibration analysis on the synchronous monitoring data and the target power supply parameters, and determining a trend state; and the adjusting and controlling module is used for adjusting and controlling the time sequence control link if the chemotactic state meets the chemotactic threshold value.
One or more technical schemes provided by the application have at least the following technical effects or advantages:
because the historical fault record in the preset time window of the frequency converter is called, a fault database is built; determining a target power supply parameter based on a power supply scene, and determining an initialization control parameter, wherein the target power supply parameter and the initialization control parameter are dynamic parameters in a preset time interval; the step length interval is configured, an operation prediction model is input by combining the target power supply parameter and the initialization control parameter, a time sequence control link is output, the operation prediction model comprises a fault prediction branch, an energy supply prediction branch and a control tuning unit, and a fault database is embedded in the fault prediction branch; performing variable frequency control and operation monitoring of the target device based on the time sequence control link to acquire synchronous monitoring data; configuring a preset step length, calling synchronous monitoring data based on the preset step length, performing calibration analysis on the synchronous monitoring data and a target power supply parameter, and determining a trend change state; if the trend state meets the trend threshold, the adjustment and control of the time sequence control link are carried out, so that the synchronous fault prediction, energy supply prediction and control adjustment are realized, the control precision and the use efficiency of the flywheel energy storage device are improved, the flywheel energy storage device can be better adapted to various special application scenes, meanwhile, the intelligent control method can also reduce the manual intervention and maintenance cost, reduce the running cost of equipment and improve the technical effects of the reliability and the safety of the equipment.
The foregoing description is only an overview of the present application, and is intended to be implemented in accordance with the teachings of the present application in order that the same may be more clearly understood and to make the same and other objects, features and advantages of the present application more readily apparent.
Drawings
Fig. 1 is a schematic diagram of a possible flow chart of an intelligent control method of a flywheel energy storage device according to an embodiment of the present application;
FIG. 2 is a schematic diagram of a possible flow chart for generating an operation prediction model in an intelligent control method of a flywheel energy storage device according to an embodiment of the present application;
fig. 3 is a schematic flow chart of a possible process of acquiring synchronous monitoring data in an intelligent control method of a flywheel energy storage device according to an embodiment of the present application;
fig. 4 is a schematic diagram of a possible structure of an intelligent control system of a flywheel energy storage device according to an embodiment of the present application.
Reference numerals illustrate: the system comprises a database construction module 100, a control parameter determination module 200, a time sequence control link output module 300, a synchronous monitoring data acquisition module 400, a correction analysis module 500 and an adjustment and control module 600.
Detailed Description
The embodiment of the application provides an intelligent control method for a flywheel energy storage device, which solves the technical problem of low control precision of the flywheel energy storage device, realizes synchronous fault prediction, energy supply prediction and control tuning, improves the control precision and the use efficiency of the flywheel energy storage device, and can better adapt to various special application scenes.
Having described the basic principles of the present application, various non-limiting embodiments of the present application will now be described in detail with reference to the accompanying drawings.
Embodiment one:
as shown in fig. 1, an embodiment of the present application provides an intelligent control method for a flywheel energy storage device, where the method includes:
s10: calling a historical fault record in a preset time window of the frequency converter, and constructing a fault database;
step S10 includes the steps of:
s11: based on the historical fault record, identifying fault events and extracting fault characteristics to generate a time sequence fault set;
s12: based on the time sequence fault set, taking the same fault type as a division standard, attributing and determining N fault groups;
s13: based on the N fault groups, carrying out fault frequency statistics on the fault groups to determine N fault frequencies, and carrying out mean value calculation of the electric effect fault duration to determine N fault durations;
s14: determining N fault reference sequences based on the N fault frequencies and N fault durations, wherein the N fault reference sequences are characterized as type information-frequency-duration;
s15: and integrating the N fault reference sequences to generate the fault database, wherein each fault reference sequence is marked with a reference coefficient and a tolerance interval.
Specifically, the flywheel energy storage device is a device capable of converting mechanical energy into electrical energy and releasing the electrical energy when needed; the frequency converter can adjust the frequency and the voltage of the flywheel energy storage device and is used for controlling the output power of the flywheel energy storage device; the frequency converter preset time window is the frequency and voltage regulation time window of the frequency converter, the fault database comprises historical fault records in the past year, data support is provided for subsequent analysis, and the fault database is built by calling the historical fault records in the frequency converter preset time window based on a data storage unit of an intelligent control system of the flywheel energy storage device;
further, calling a historical fault record in a preset time window of the frequency converter, and building a fault database, wherein the step of identifying fault events and extracting fault characteristics in the historical fault record, wherein the fault characteristics can be fault types, fault occurrence time and fault reasons, so that the time sequence fault set is obtained, and the fault occurrence time of each element in the time sequence fault set comprises fault starting time and fault ending time;
dividing the faults in the time sequence fault set into different fault groups according to fault types to form N fault groups, wherein the fault types of the frequency converter can be, for example, frequency converter input phase-failure faults, frequency converter undervoltage faults and frequency converter overheat faults, and the corresponding N fault groups comprise, but are not limited to, frequency converter input phase-failure fault groups, frequency converter undervoltage fault groups and frequency converter overheat fault groups; counting the fault frequency of each of the N fault groups, correspondingly calculating N fault frequencies, wherein the fault frequency can be the number of times that a certain fault type occurs in one working day, and carrying out average value calculation on the electric effect fault duration in each fault group to obtain N fault duration, and the fault duration is the duration of time when the certain fault type occurs;
determining a reference sequence of each fault type corresponding to the N fault groups by using the N fault frequencies and the N fault durations, wherein the fault reference sequences are represented by type information, frequencies and durations, and the fault reference sequences of all fault types corresponding to the N fault groups are N fault reference sequences, and meanwhile, integrating the N fault reference sequences to obtain the fault database, wherein each fault reference sequence in the fault database identifies a reference coefficient and a tolerance interval, and the reference coefficient refers to a coefficient for evaluating the reliability and the accuracy of a certain reference sequence; the tolerance interval refers to a range allowing errors of the reference sequence, and faults can be rapidly identified and positioned by establishing a fault database, so that the reliability and stability of the equipment are improved.
Step S15 includes the steps of:
s151: traversing the N fault groups, identifying fault time nodes, determining a time interval by combining the current time nodes, performing mean value calculation, and determining N time sequence intervals;
s152: determining N reference coefficients based on the N fault frequencies and the N time sequence intervals, wherein the reference coefficients are positively correlated with the fault frequencies and the time sequence intervals;
s153: traversing the N fault groups, and combining the N fault time lengths and the electric effect fault time lengths to perform variance calculation to determine a tolerance interval.
Specifically, integrating the N fault reference sequences to generate the fault database, wherein each fault reference sequence is marked with a reference coefficient and a tolerance interval, and further comprising traversing the N fault groups, determining occurrence identification fault time nodes of each fault on a time axis, determining a time interval of each fault according to a current time node and the fault time node, calculating an average value of fault occurrence times in the time interval, calculating a time sequence interval between each fault time node to obtain N time sequence intervals, and calculating N reference coefficients according to the N fault frequencies and the N time sequence intervals, wherein the reference coefficients are positively correlated with the fault frequencies and the time sequence intervals, in short terms, the longer the fault duration is, the higher the corresponding fault frequencies are; traversing the N fault groups, calculating variances according to the time length of the N faults and the time length of the electric effect faults, and determining the tolerance interval by using a statistical method according to the confidence level and the confidence interval set by related technicians and using the calculated variance value. By calculating the tolerance interval, the fault in which range of the system can be tolerated can be determined, so that the fault tolerance and reliability of the system are improved, and the completeness and practicability of a fault database are further ensured.
S20: determining a target power supply parameter based on a power supply scene, and determining an initialization control parameter, wherein the target power supply parameter and the initialization control parameter are dynamic parameters in a preset time interval;
s30: the step length interval is configured, an operation prediction model is input by combining the target power supply parameter and the initialization control parameter, a time sequence control link is output, the operation prediction model comprises a fault prediction branch, an energy supply prediction branch and a control tuning unit, and the fault database is embedded in the fault prediction branch;
as shown in fig. 2, step S30 includes the steps of:
s31: invoking sample target power supply parameters, sample initialization control parameters, sample energy supply prediction results and fault prediction results, and performing sample data mapping and combining to generate a fault prediction sample and an energy supply prediction sample;
s32: training to generate a fault prediction branch based on the fault prediction sample;
s33: training to generate an energy supply prediction branch based on the energy supply prediction sample;
s34: and the pre-step processing layer is used for carrying out parallel arrangement on the fault prediction branch and the energy supply prediction branch, and the control tuning unit is arranged at the rear end to generate the operation prediction model.
Step S33 includes the steps of:
s331: based on the energy supply prediction sample, training a neural network to generate a first energy supply prediction model;
s332: verifying the first energy supply prediction model based on the energy supply prediction sample, and determining a retraining sample which is the energy supply prediction sample with verification accuracy smaller than an accuracy threshold;
s333: training a second energy supply prediction model based on the one retraining sample, and determining two retraining samples;
s334: repeating iterative training until convergence conditions are met, and acquiring an Mth energy supply prediction model;
s335: and integrating the first energy supply prediction model and the second energy supply prediction model until an Mth energy supply prediction model to generate the energy supply prediction branch.
Specifically, the target power supply parameter refers to a target state parameter, such as voltage, power, etc., that the power supply system needs to reach in a predetermined time interval; the initialization control parameters refer to control parameters in the initial state of the system, such as output power of a generator, configuration of a capacitor inductor and the like; determining a target power supply parameter based on a power supply scene, and determining an initialization control parameter, wherein the target power supply parameter and the initialization control parameter are dynamic parameters in a preset time interval; the preset time interval is a time period preset in the control system, generally, the length of the preset time interval is not more than 1min, and in the preset time interval, a target power supply parameter is determined according to a power supply scene and combined with an initialization control parameter to form a preset dynamic parameter, wherein the preset dynamic parameter is the variation between the initialization control parameter and the current control parameter;
the step interval refers to the change speed of the control parameter in a preset time interval, in the actual control process, the system needs to realize the control and adjustment of the system by adjusting the value of the initialized control parameter according to the target power supply parameter and the current state, wherein the step interval refers to the change amount of the control parameter in each adjustment, and the interval length of the step interval directly influences the control precision and stability;
the step interval is configured, the target power supply parameter and the initialization control parameter are combined to input an operation prediction model, a time sequence control link is output, the operation prediction model comprises a fault prediction branch, an energy supply prediction branch and a control tuning unit, wherein the fault prediction branch predicts and diagnoses possible fault conditions, the energy supply prediction branch predicts and optimizes energy supply conditions, the control tuning unit adjusts and optimizes system parameters, the fault database is embedded in the fault prediction branch, accurate control and adjustment of a power supply system are achieved, operation stability and reliability of the system are improved, and meanwhile energy consumption and operation cost can be reduced.
Further, the target power supply parameter and the initialization control parameter are combined to input an operation prediction model, a time sequence control link is output, and the method further comprises the steps of calling a sample target power supply parameter, a sample initialization control parameter, a sample energy supply prediction result and a fault prediction result based on data acquisition of a data storage unit of an intelligent control system of the flywheel energy storage device, wherein the sample target power supply parameter is a target parameter which needs to be controlled and regulated in an electric power system, such as voltage, current and frequency of the flywheel energy storage device of a model; the control parameters are set when the control system starts to operate, such as controller gain, integration time, differential time and the like, which are set in the flywheel energy storage device of the model; the sample energy supply prediction result is the energy supply condition in the next time period corresponding to the sample target power supply parameter; the fault prediction result is a possible fault condition in the next time period corresponding to the sample target power supply parameter; carrying out sample data mapping combination on the sample target power supply parameter, the sample initialization control parameter and the sample energy supply prediction result to generate an energy supply prediction sample; carrying out sample data mapping combination on the sample target power supply parameter, the sample initialization control parameter and the fault prediction result to generate a fault prediction sample;
training to generate a fault prediction branch based on the fault prediction sample; training to generate an energy supply prediction branch based on the energy supply prediction sample; the pre-step processing layer is used for carrying out parallel arrangement on the fault prediction branch and the energy supply prediction branch before control so as to improve the response speed and the control precision of the control system. The post control tuning unit is used for tuning the operation prediction model to further improve the performance of the control system, the post control tuning unit is a weight adjusting functional unit, the interior of the post control tuning unit follows a coefficient of variation method, the coefficient of variation method is an objective weighting method, information contained in an input end of the post control tuning unit is directly utilized, corresponding weight is obtained through calculation, and a pre step processing layer is connected with the post control tuning unit, so that the operation prediction model is obtained;
on one hand, the target power supply parameters are controlled and regulated by predicting faults and energy supply conditions in a future period of time, so that the stable operation of the power system is realized; on the other hand, the response speed and the control precision of the control system can be improved through the front step processing layer and the rear control optimizing unit, so that the reliability and the safety of the power system are improved.
Further, training to generate an energy-providing prediction branch based on the energy-providing prediction sample, further comprising training a first energy-providing prediction model using the energy-providing prediction sample with the neural network model as a model basis: taking the neural network model as a model basis, adopting the energy supply prediction sample as construction data, constructing new combination characteristics based on sample target power supply parameters and sample initialization control parameters in the energy supply prediction sample, taking a sample energy supply prediction result as an identification result, transmitting the identification result into the neural network model for model convergence learning, constructing and training to obtain the first energy supply prediction model, determining the first energy supply prediction model, and providing a model basis for predicting energy supply conditions in the next time period;
randomly dividing the energy supply prediction samples according to the proportion of 33%, 33% and 34% to obtain a first verification sample, a second verification sample and a third verification sample, substituting the first verification sample, the second verification sample and the third verification sample into the first energy supply prediction model respectively for verification, and taking the first verification sample and/or the second verification sample and/or the third verification sample with verification accuracy smaller than an accuracy threshold value as a retraining sample if the verification accuracy of the first verification sample and/or the second verification sample and/or the third verification sample is smaller than the accuracy threshold value, namely, taking the retraining sample as the energy supply prediction sample with verification accuracy smaller than the accuracy threshold value;
training a second energy supply prediction model based on the first energy supply prediction model by taking the one retraining sample as secondary training data: inputting a retraining sample as training data into the first energy supply prediction model for training, randomly dividing the training sample according to the proportion of 33%, 33% and 34% to obtain a fourth verification sample, a fifth verification sample and a sixth verification sample, and repeating the steps to obtain two retraining samples; repeating iterative training until convergence conditions are met, and acquiring an Mth energy supply prediction model; integrating the first energy supply prediction model and the second energy supply prediction model until an Mth energy supply prediction model to generate the energy supply prediction branch; meanwhile, the step of training and generating the fault prediction branch corresponds to the step of training and generating the fault prediction branch, and the energy supply prediction branch is obtained through training, so that the energy supply condition of the flywheel energy storage device is predicted in real time, and the efficiency and the reliability of the flywheel energy storage device are improved.
The embodiment of the application also comprises the following steps:
s351: identifying a target energy storage mode, wherein the target energy storage mode is an integrated system mode or a split system mode, and the target energy storage mode is in communication connection with the control and tuning unit;
s352: determining a link node power requirement, configuring a target device and enabling activation control, wherein the target device is identified with distributed power and comprises at least one flywheel energy storage device;
s353: and performing simulated tuning analysis in the control tuning unit by taking the target device and the target energy storage mode as references, wherein the control tuning unit is communicated with a visual simulation platform.
Specifically, the target energy storage mode, namely the working mode of the flywheel energy storage device, can be an integrated system mode or a split system mode, and the target energy storage mode is identified so as to determine whether the flywheel energy storage device is the integrated system mode or the split system mode, and then the target energy storage mode is in communication connection with the control optimizing unit;
the target device is an adaptive flywheel energy storage device which is idle in a preset time interval and meets energy supply standards (stored electric quantity), the target device is marked with distributed power and used for representing power distribution based on storage and running states of all devices, the power distribution is carried out by including storage and running states of at least one flywheel energy storage device, and preferably, step length time of each link node is analyzed;
the link node power requirement is used for representing energy or power required by a flywheel energy storage device for a specific link node, when a target device is configured and activated, corresponding power is required to be distributed according to the size and the change of the link node power requirement, namely the target device and the target energy storage mode are simply taken as references, the target device and the target energy storage mode are taken as references, the control tuning unit is used for performing simulation tuning analysis, the control tuning unit is communicated with a visual simulation platform, and the flywheel energy storage device output power and the requirement are mutually adapted, adjusted and changed for visual output; on one hand, the accurate control and the optimization of the output power of the flywheel energy storage device are realized, the efficiency and the reliability of the flywheel energy storage device are improved, and on the other hand, the performance of the flywheel energy storage device can be predicted through the simulation optimization analysis, and the possibility of faults is reduced.
S40: performing variable frequency control and operation monitoring of the target device based on the time sequence control link to acquire synchronous monitoring data;
s50: configuring a preset step length, calling the synchronous monitoring data based on the preset step length, and performing correction analysis with the target power supply parameters to determine a trend change state;
s60: and if the trend state meets the trend threshold, adjusting and controlling the time sequence control link.
As shown in fig. 3, step S40 includes the steps of:
s41: transmitting the time sequence control link to a centralized controller to perform variable frequency control of the target device;
s42: synchronously performing control monitoring to obtain operation monitoring data;
s43: determining situation index parameters based on the operation monitoring data, wherein the situation index parameters comprise response speed, mechanical conversion effect and same-frequency control state;
s44: and determining the synchronous monitoring data based on the operation monitoring data and the situation indexes, wherein the operation monitoring data corresponds to the situation index time sequence.
Specifically, the variable frequency control refers to controlling the running speed of a motor in the flywheel energy storage device by adjusting the frequency of the flywheel energy storage device, the synchronous monitoring data refers to data obtained by monitoring the running state of the flywheel energy storage device in real time, and the variable frequency control and the running monitoring of the target device are performed based on the time sequence control link to obtain the synchronous monitoring data; configuring a preset step length, wherein the preset step length is generally not more than 5S, calling the synchronous monitoring data based on the preset step length, performing correction analysis on the synchronous monitoring data and the target power supply parameter, and determining a trend state, wherein the trend state is used for representing the deviation trend between the synchronous monitoring data and the target power supply parameter; the trend threshold is a threshold which is set and used for judging whether the running state of the equipment has trend; and if the chemotaxis state meets the chemotaxis threshold, adjusting and controlling the time sequence control link, and by predicting the fault condition and monitoring the running state of the equipment, the running state of the flywheel energy storage device can be controlled and adjusted in real time, and the running efficiency and stability of the flywheel energy storage device are improved.
Further, performing frequency conversion control and operation monitoring of the target device based on the time sequence control link to obtain synchronous monitoring data, wherein the step of transmitting a control signal in the time sequence control link to a centralized controller and performing frequency conversion control of the target device through the control signal; synchronous control monitoring is carried out on the flywheel energy storage device, and relevant operation monitoring data are obtained, wherein the operation monitoring data comprise, but are not limited to, real-time power monitoring data and real-time voltage monitoring data;
the situation index parameters comprise response speed, mechanical conversion effect and same-frequency control state, wherein the same-frequency control state is the cooperative control state of a plurality of flywheel energy storage devices, such as synchronous control time difference and the like, the response speed and the mechanical conversion effect of the plurality of flywheel energy storage devices are synchronously monitored to obtain operation monitoring data, the operation monitoring data comprise response speed information and mechanical conversion information, the same-frequency control state corresponding to the plurality of flywheel energy storage devices is determined by comparing time sequence information of the operation monitoring data, and the same-frequency control state is corresponding to the time sequence information to obtain a determined situation index parameter, wherein the situation index parameter comprises the response speed, the mechanical conversion effect and the same-frequency control state;
and performing association mapping on the operation monitoring data and the situation indexes to obtain the synchronous monitoring data, wherein the operation monitoring data corresponds to the situation index time sequence, so that the accurate control and optimization of the flywheel energy storage device are realized, and the efficiency and reliability of a control system of the flywheel energy storage device are improved. In addition, through simulation optimization analysis, the performance of the flywheel energy storage device can be predicted, and the possibility of fault occurrence is reduced. Meanwhile, automatic control is realized, the working efficiency is improved, and the requirement of manual intervention is reduced.
In summary, the intelligent control method of the flywheel energy storage device provided by the embodiment of the application has the following technical effects:
1. because the historical fault record in the preset time window of the frequency converter is called, a fault database is built; determining a target power supply parameter based on a power supply scene, and determining an initialization control parameter, wherein the target power supply parameter and the initialization control parameter are dynamic parameters in a preset time interval; the step length interval is configured, an operation prediction model is input by combining the target power supply parameter and the initialization control parameter, a time sequence control link is output, the operation prediction model comprises a fault prediction branch, an energy supply prediction branch and a control tuning unit, and a fault database is embedded in the fault prediction branch; performing variable frequency control and operation monitoring of the target device based on the time sequence control link to acquire synchronous monitoring data; configuring a preset step length, calling synchronous monitoring data based on the preset step length, performing calibration analysis on the synchronous monitoring data and a target power supply parameter, and determining a trend change state; if the trend state meets the trend threshold value, the adjustment and control of the time sequence control link are carried out, and the intelligent control method of the flywheel energy storage device realizes synchronous fault prediction, energy supply prediction and control and optimization, improves the control precision and the use efficiency of the flywheel energy storage device, and enables the flywheel energy storage device to be better suitable for various special application scenes.
2. Because the target energy storage mode is identified, the target energy storage mode is an integrated system mode or a split system mode, and the target energy storage mode is in communication connection with the control and optimization unit; determining a link node power requirement, configuring a target device and enabling activation control, wherein the target device is identified with distributed power and comprises at least one flywheel energy storage device; and performing simulated tuning analysis in a control tuning unit by taking the target device and the target energy storage mode as references, wherein the control tuning unit is communicated with the visual simulation platform, so that on one hand, the accurate control and tuning of the output power of the flywheel energy storage device are realized, the efficiency and reliability of the flywheel energy storage device are improved, and on the other hand, the performance of the flywheel energy storage device can be predicted and the possibility of fault occurrence is reduced through simulated tuning analysis.
Embodiment two:
based on the same inventive concept as the intelligent control method of the flywheel energy storage device in the foregoing embodiment, as shown in fig. 4, an embodiment of the present application provides an intelligent control system of the flywheel energy storage device, where the system includes:
the database construction module 100 is used for calling a historical fault record in a preset time window of the frequency converter and constructing a fault database;
the control parameter determining module 200 is configured to determine a target power supply parameter based on a power supply scenario, and determine an initialization control parameter, where the target power supply parameter and the initialization control parameter are dynamic parameters within a predetermined time interval;
the time sequence control link output module 300 is configured to configure a step interval, input an operation prediction model by combining the target power supply parameter and the initialization control parameter, and output a time sequence control link, wherein the operation prediction model comprises a fault prediction branch, an energy supply prediction branch and a control tuning unit, and the fault prediction branch is embedded with the fault database;
the synchronous monitoring data acquisition module 400 is configured to perform variable frequency control and operation monitoring of the target device based on the timing control link, so as to acquire synchronous monitoring data;
the calibration analysis module 500 is configured to configure a preset step length, call the synchronous monitoring data based on the preset step length, perform calibration analysis with the target power supply parameter, and determine a trend state;
the adjustment and control module 600 is configured to perform adjustment and control of the timing control link if the chemotactic state meets a chemotactic threshold.
The database construction module 100 includes the steps of:
based on the historical fault record, identifying fault events and extracting fault characteristics to generate a time sequence fault set;
based on the time sequence fault set, taking the same fault type as a division standard, attributing and determining N fault groups;
based on the N fault groups, carrying out fault frequency statistics on the fault groups to determine N fault frequencies, and carrying out mean value calculation of the electric effect fault duration to determine N fault durations;
determining N fault reference sequences based on the N fault frequencies and N fault durations, wherein the N fault reference sequences are characterized as type information-frequency-duration;
and integrating the N fault reference sequences to generate the fault database, wherein each fault reference sequence is marked with a reference coefficient and a tolerance interval.
The database construction module 100 further comprises the steps of:
traversing the N fault groups, identifying fault time nodes, determining a time interval by combining the current time nodes, performing mean value calculation, and determining N time sequence intervals;
determining N reference coefficients based on the N fault frequencies and the N time sequence intervals, wherein the reference coefficients are positively correlated with the fault frequencies and the time sequence intervals;
traversing the N fault groups, and combining the N fault time lengths and the electric effect fault time lengths to perform variance calculation to determine a tolerance interval.
The timing control link output module 300 includes the steps of:
invoking sample target power supply parameters, sample initialization control parameters, sample energy supply prediction results and fault prediction results, and performing sample data mapping and combining to generate a fault prediction sample and an energy supply prediction sample;
training to generate a fault prediction branch based on the fault prediction sample;
training to generate an energy supply prediction branch based on the energy supply prediction sample;
and the pre-step processing layer is used for carrying out parallel arrangement on the fault prediction branch and the energy supply prediction branch, and the control tuning unit is arranged at the rear end to generate the operation prediction model.
The timing control link output module 300 further includes the steps of:
based on the energy supply prediction sample, training a neural network to generate a first energy supply prediction model;
verifying the first energy supply prediction model based on the energy supply prediction sample, and determining a retraining sample which is the energy supply prediction sample with verification accuracy smaller than an accuracy threshold;
training a second energy supply prediction model based on the one retraining sample, and determining two retraining samples;
repeating iterative training until convergence conditions are met, and acquiring an Mth energy supply prediction model;
and integrating the first energy supply prediction model and the second energy supply prediction model until an Mth energy supply prediction model to generate the energy supply prediction branch.
The timing control link output module 300 further includes the steps of:
identifying a target energy storage mode, wherein the target energy storage mode is an integrated system mode or a split system mode, and the target energy storage mode is in communication connection with the control and tuning unit;
determining a link node power requirement, configuring a target device and enabling activation control, wherein the target device is identified with distributed power and comprises at least one flywheel energy storage device;
and performing simulated tuning analysis in the control tuning unit by taking the target device and the target energy storage mode as references, wherein the control tuning unit is communicated with a visual simulation platform.
The synchronization monitoring data acquisition module 400 includes the steps of:
transmitting the time sequence control link to a centralized controller to perform variable frequency control of the target device;
synchronously performing control monitoring to obtain operation monitoring data;
determining situation index parameters based on the operation monitoring data, wherein the situation index parameters comprise response speed, mechanical conversion effect and same-frequency control state;
and determining the synchronous monitoring data based on the operation monitoring data and the situation indexes, wherein the operation monitoring data corresponds to the situation index time sequence.
Any of the steps of the methods described above may be stored as computer instructions or programs in a non-limiting computer memory and may be called by a non-limiting computer processor to identify any method for implementing an embodiment of the present application, without unnecessary limitations.
Further, the first or second element may not only represent a sequential relationship, but may also represent a particular concept, and/or may be selected individually or in whole among a plurality of elements. It will be apparent to those skilled in the art that various modifications and variations can be made to the present application without departing from the scope of the application. Thus, the present application is intended to include such modifications and alterations insofar as they come within the scope of the application or the equivalents thereof.
Claims (8)
1. An intelligent control method of a flywheel energy storage device is characterized by comprising the following steps:
calling a historical fault record in a preset time window of the frequency converter, and constructing a fault database;
determining a target power supply parameter based on a power supply scene, and determining an initialization control parameter, wherein the target power supply parameter and the initialization control parameter are dynamic parameters in a preset time interval;
the step length interval is configured, an operation prediction model is input by combining the target power supply parameter and the initialization control parameter, a time sequence control link is output, the operation prediction model comprises a fault prediction branch, an energy supply prediction branch and a control tuning unit, and the fault database is embedded in the fault prediction branch;
performing variable frequency control and operation monitoring of the target device based on the time sequence control link to acquire synchronous monitoring data;
configuring a preset step length, calling the synchronous monitoring data based on the preset step length, and performing correction analysis with the target power supply parameters to determine a trend change state;
and if the trend state meets the trend threshold, adjusting and controlling the time sequence control link.
2. The method of claim 1, wherein the building a fault database, the method comprising:
based on the historical fault record, identifying fault events and extracting fault characteristics to generate a time sequence fault set;
based on the time sequence fault set, taking the same fault type as a division standard, attributing and determining N fault groups;
based on the N fault groups, carrying out fault frequency statistics on the fault groups to determine N fault frequencies, and carrying out mean value calculation of the electric effect fault duration to determine N fault durations;
determining N fault reference sequences based on the N fault frequencies and N fault durations, wherein the N fault reference sequences are characterized as type information-frequency-duration;
and integrating the N fault reference sequences to generate the fault database, wherein each fault reference sequence is marked with a reference coefficient and a tolerance interval.
3. The method of claim 2, wherein each fault reference sequence identifies a reference coefficient and a tolerance interval, the method comprising:
traversing the N fault groups, identifying fault time nodes, determining a time interval by combining the current time nodes, performing mean value calculation, and determining N time sequence intervals;
determining N reference coefficients based on the N fault frequencies and the N time sequence intervals, wherein the reference coefficients are positively correlated with the fault frequencies and the time sequence intervals;
traversing the N fault groups, and combining the N fault time lengths and the electric effect fault time lengths to perform variance calculation to determine a tolerance interval.
4. The method of claim 1, wherein the method comprises:
invoking sample target power supply parameters, sample initialization control parameters, sample energy supply prediction results and fault prediction results, and performing sample data mapping and combining to generate a fault prediction sample and an energy supply prediction sample;
training to generate a fault prediction branch based on the fault prediction sample;
training to generate an energy supply prediction branch based on the energy supply prediction sample;
and the pre-step processing layer is used for carrying out parallel arrangement on the fault prediction branch and the energy supply prediction branch, and the control tuning unit is arranged at the rear end to generate the operation prediction model.
5. The method of claim 4, wherein training to generate an energy-providing prediction branch based on the energy-providing prediction sample, comprises:
based on the energy supply prediction sample, training a neural network to generate a first energy supply prediction model;
verifying the first energy supply prediction model based on the energy supply prediction sample, and determining a retraining sample which is the energy supply prediction sample with verification accuracy smaller than an accuracy threshold;
training a second energy supply prediction model based on the one retraining sample, and determining two retraining samples;
repeating iterative training until convergence conditions are met, and acquiring an Mth energy supply prediction model;
and integrating the first energy supply prediction model and the second energy supply prediction model until an Mth energy supply prediction model to generate the energy supply prediction branch.
6. The method as claimed in claim 4, wherein the method comprises:
identifying a target energy storage mode, wherein the target energy storage mode is an integrated system mode or a split system mode, and the target energy storage mode is in communication connection with the control and tuning unit;
determining a link node power requirement, configuring a target device and enabling activation control, wherein the target device is identified with distributed power and comprises at least one flywheel energy storage device;
and performing simulated tuning analysis in the control tuning unit by taking the target device and the target energy storage mode as references, wherein the control tuning unit is communicated with a visual simulation platform.
7. The method of claim 1, wherein the frequency conversion control and operation monitoring of the target device are performed based on the timing control link, and synchronous monitoring data is obtained, the method comprising:
transmitting the time sequence control link to a centralized controller to perform variable frequency control of the target device;
synchronously performing control monitoring to obtain operation monitoring data;
determining situation index parameters based on the operation monitoring data, wherein the situation index parameters comprise response speed, mechanical conversion effect and same-frequency control state;
and determining the synchronous monitoring data based on the operation monitoring data and the situation indexes, wherein the operation monitoring data corresponds to the situation index time sequence.
8. An intelligent control system for a flywheel energy storage device, for implementing an intelligent control method for a flywheel energy storage device according to any of claims 1-7, comprising:
the database construction module is used for calling a historical fault record in a preset time window of the frequency converter and constructing a fault database;
the control parameter determining module is used for determining a target power supply parameter based on a power supply scene and determining an initialization control parameter, wherein the target power supply parameter and the initialization control parameter are dynamic parameters in a preset time interval;
the time sequence control link output module is used for configuring a step interval, inputting an operation prediction model by combining the target power supply parameter and the initialization control parameter, and outputting a time sequence control link, wherein the operation prediction model comprises a fault prediction branch, an energy supply prediction branch and a control tuning unit, and the fault prediction branch is embedded with the fault database;
the synchronous monitoring data acquisition module is used for carrying out variable frequency control and operation monitoring on the target device based on the time sequence control link to acquire synchronous monitoring data;
the calibration analysis module is used for configuring a preset step length, calling the synchronous monitoring data based on the preset step length, performing calibration analysis on the synchronous monitoring data and the target power supply parameters, and determining a trend state;
and the adjusting and controlling module is used for adjusting and controlling the time sequence control link if the chemotactic state meets the chemotactic threshold value.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311119946.5A CN116845936B (en) | 2023-09-01 | 2023-09-01 | Intelligent control method of flywheel energy storage device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311119946.5A CN116845936B (en) | 2023-09-01 | 2023-09-01 | Intelligent control method of flywheel energy storage device |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN116845936A true CN116845936A (en) | 2023-10-03 |
| CN116845936B CN116845936B (en) | 2023-11-21 |
Family
ID=88160283
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311119946.5A Active CN116845936B (en) | 2023-09-01 | 2023-09-01 | Intelligent control method of flywheel energy storage device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116845936B (en) |
Citations (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2017161126A1 (en) * | 2016-03-16 | 2017-09-21 | University Of Houston System | System and method for detecting, diagnosing, and correcting trips or failures of electrical submersible pumps |
| CN109524139A (en) * | 2018-10-23 | 2019-03-26 | 中核核电运行管理有限公司 | A kind of real-time device performance monitoring method based on equipment working condition variation |
| CN110503338A (en) * | 2019-08-26 | 2019-11-26 | 江苏方天电力技术有限公司 | A kind of ubiquitous electric power Internet of Things monitoring method |
| CN110763997A (en) * | 2019-11-04 | 2020-02-07 | 华北电力大学（保定） | Early fault early warning method for synchronous motor stator |
| CN112085930A (en) * | 2020-09-14 | 2020-12-15 | 武汉瑞莱保能源技术有限公司 | Intelligent monitoring and early warning system and method for generator set |
| CN112418474A (en) * | 2019-08-20 | 2021-02-26 | 北京国双科技有限公司 | Method and device for predicting fault handling deadline |
| CN112631240A (en) * | 2020-12-07 | 2021-04-09 | 中国人民解放军63920部队 | Spacecraft fault active detection method and device |
| US20210107539A1 (en) * | 2019-10-11 | 2021-04-15 | Progress Rail Services Corporation | System and method for predicting failures of train components |
| CN115356990A (en) * | 2022-06-10 | 2022-11-18 | 国家电投集团东北电力有限公司本溪热电分公司 | Material yard equipment fault prediction method and system based on deep learning and storage medium |
| CN116050665A (en) * | 2023-03-14 | 2023-05-02 | 淄博热力有限公司 | Heat supply equipment fault prediction method |
| CN116069079A (en) * | 2023-04-06 | 2023-05-05 | 山东海冠电气有限公司 | Intelligent heat dissipation control method and system for intelligent switch cabinet |
| CN116629455A (en) * | 2023-07-19 | 2023-08-22 | 山西阳风新能售电有限公司 | Intelligent orientation prediction method based on power supply |
-
2023
- 2023-09-01 CN CN202311119946.5A patent/CN116845936B/en active Active
Patent Citations (13)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2017161126A1 (en) * | 2016-03-16 | 2017-09-21 | University Of Houston System | System and method for detecting, diagnosing, and correcting trips or failures of electrical submersible pumps |
| US20200325766A1 (en) * | 2016-03-16 | 2020-10-15 | University Of Houston System | System and method for detecting, diagnosing, and correcting trips or failures of electrical submersible pumps |
| CN109524139A (en) * | 2018-10-23 | 2019-03-26 | 中核核电运行管理有限公司 | A kind of real-time device performance monitoring method based on equipment working condition variation |
| CN112418474A (en) * | 2019-08-20 | 2021-02-26 | 北京国双科技有限公司 | Method and device for predicting fault handling deadline |
| CN110503338A (en) * | 2019-08-26 | 2019-11-26 | 江苏方天电力技术有限公司 | A kind of ubiquitous electric power Internet of Things monitoring method |
| US20210107539A1 (en) * | 2019-10-11 | 2021-04-15 | Progress Rail Services Corporation | System and method for predicting failures of train components |
| CN110763997A (en) * | 2019-11-04 | 2020-02-07 | 华北电力大学（保定） | Early fault early warning method for synchronous motor stator |
| CN112085930A (en) * | 2020-09-14 | 2020-12-15 | 武汉瑞莱保能源技术有限公司 | Intelligent monitoring and early warning system and method for generator set |
| CN112631240A (en) * | 2020-12-07 | 2021-04-09 | 中国人民解放军63920部队 | Spacecraft fault active detection method and device |
| CN115356990A (en) * | 2022-06-10 | 2022-11-18 | 国家电投集团东北电力有限公司本溪热电分公司 | Material yard equipment fault prediction method and system based on deep learning and storage medium |
| CN116050665A (en) * | 2023-03-14 | 2023-05-02 | 淄博热力有限公司 | Heat supply equipment fault prediction method |
| CN116069079A (en) * | 2023-04-06 | 2023-05-05 | 山东海冠电气有限公司 | Intelligent heat dissipation control method and system for intelligent switch cabinet |
| CN116629455A (en) * | 2023-07-19 | 2023-08-22 | 山西阳风新能售电有限公司 | Intelligent orientation prediction method based on power supply |
Non-Patent Citations (2)
| Title |
|---|
| XIANG LI等: "Deep Learning-Based Partial Domain Adaptation Method on Intelligent Machinery Fault Diagnostics", IEEE * |
| 乔福宇;马良玉;马永光;: "基于功率曲线分析与神经网络的风电机组故障预警方法", 中国测试, no. 08 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN116845936B (en) | 2023-11-21 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN113937763B (en) | Wind power prediction method, device, equipment and storage medium | |
| CN111861023B (en) | Mixed wind power prediction method and device based on statistics | |
| CN105469216B (en) | Method and system for evaluating wind power plant operation risk by combining weather and wind speed | |
| CN115859816A (en) | Wind power minute-level prediction method and system based on CNN-LSTM algorithm | |
| CN110460038A (en) | It is a kind of to be related to more scene method for expansion planning of power transmission network of new-energy grid-connected | |
| CN115084600B (en) | Hydrogen fuel cell stack output performance analysis method based on big data | |
| CN116845936B (en) | Intelligent control method of flywheel energy storage device | |
| CN115963752A (en) | Voice coil motor position servo control system based on deep learning and training method of mathematical model | |
| CN113098912B (en) | User account abnormity identification method and device, electronic equipment and storage medium | |
| CN107179758B (en) | Dynamic signal parameter identification method and system | |
| CN116706992A (en) | Self-adaptive power prediction method, device and equipment for distributed photovoltaic cluster | |
| CN109978204B (en) | Method and device for determining prediction accuracy of wind power plant | |
| CN111258854A (en) | Model training method, alarm method based on prediction model and related device | |
| EP4131703B1 (en) | System and method for controlling a power generating system | |
| CN113271222B (en) | System state estimation method for multi-sensor information fusion under protocol scheduling | |
| CN111274687B (en) | Component failure rate prediction method and device, computer equipment and storage medium | |
| CN109492913B (en) | Modular risk prediction method and device for power distribution terminal and storable medium | |
| CN117722306A (en) | On-line monitoring method and system for water turbine speed regulator | |
| CN117606119B (en) | Air cabinet intelligent parameter adjustment control method and system based on environment analysis | |
| CN117578948B (en) | Permanent magnet motor operation deviation self-adaptive regulation and control method and system | |
| CN116979568A (en) | New energy base energy storage power configuration method and device, computer equipment and medium | |
| CN117767285A (en) | Short-term photovoltaic power generation power prediction method, device, storage medium and equipment based on time neighborhood meteorological data | |
| CN115828515A (en) | Modeling method and device for wind power plant | |
| CN114971051A (en) | Wind power prediction method | |
| CN116882269A (en) | Wind power plant error correction model construction method and device and wind power plant control system |
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 |