CN117869181A - Optimal control method and system for rotating speed and torque - Google Patents
Optimal control method and system for rotating speed and torque Download PDFInfo
- Publication number
- CN117869181A CN117869181A CN202311684910.1A CN202311684910A CN117869181A CN 117869181 A CN117869181 A CN 117869181A CN 202311684910 A CN202311684910 A CN 202311684910A CN 117869181 A CN117869181 A CN 117869181A
- Authority
- CN
- China
- Prior art keywords
- wind
- mapping
- torque
- particle
- particles
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 31
- 238000013507 mapping Methods 0.000 claims abstract description 98
- 238000010248 power generation Methods 0.000 claims abstract description 44
- 230000007613 environmental effect Effects 0.000 claims abstract description 38
- 239000002245 particle Substances 0.000 claims description 139
- 230000005484 gravity Effects 0.000 claims description 29
- 238000011156 evaluation Methods 0.000 claims description 28
- 238000012549 training Methods 0.000 claims description 15
- 238000005457 optimization Methods 0.000 claims description 11
- 238000003062 neural network model Methods 0.000 claims description 6
- 238000005516 engineering process Methods 0.000 description 4
- 238000012544 monitoring process Methods 0.000 description 4
- 238000007726 management method Methods 0.000 description 3
- 238000004364 calculation method Methods 0.000 description 2
- 238000012545 processing Methods 0.000 description 2
- 230000004913 activation Effects 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 238000004140 cleaning Methods 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 238000012937 correction Methods 0.000 description 1
- 238000007405 data analysis Methods 0.000 description 1
- 238000013500 data storage Methods 0.000 description 1
- 238000013136 deep learning model Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 230000010354 integration Effects 0.000 description 1
- 238000010801 machine learning Methods 0.000 description 1
- 238000012423 maintenance Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 210000002569 neuron Anatomy 0.000 description 1
- 238000010606 normalization Methods 0.000 description 1
- 238000007781 pre-processing Methods 0.000 description 1
- 230000008569 process Effects 0.000 description 1
- 238000000611 regression analysis Methods 0.000 description 1
- 238000007619 statistical method Methods 0.000 description 1
Classifications
-
- 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
- Y02E10/00—Energy generation through renewable energy sources
- Y02E10/70—Wind energy
- Y02E10/72—Wind turbines with rotation axis in wind direction
Landscapes
- Wind Motors (AREA)
Abstract
The invention discloses a method and a system for optimally controlling rotating speed and torque, which relate to the technical field of wind power generation, and the method comprises the following steps: generating N historical operation data sets; searching in the N historical operation data sets to obtain N power generation sequences, and respectively identifying the power generation in the N power generation sequences; generating N optimal rotation speed-torque mapping values according to N search results; collecting environmental influence information of a target area at the current moment; transmitting the wind speed and the wind direction, N optimal rotation speed-torque mapping values and N search results to an optimal control identification network layer to generate N optimal control parameters; the N pieces of wind power equipment in the target area are optimally controlled by utilizing the N pieces of optimal control parameters, so that the problem that the power generation efficiency is low due to insufficient rigor and insufficient completeness of a cluster control system for wind power autonomous cluster control in the prior art is solved, and the power generation efficiency of a wind power plant is improved.
Description
Technical Field
The invention relates to the technical field of wind power generation, in particular to an optimal control method and system for rotating speed and torque.
Background
With the adjustment of global energy structures and the great popularization of renewable energy sources, wind power generation is receiving a great deal of attention as a clean and renewable energy source form. However, wind power generation faces a number of technical challenges, of which electrical control systems are one of the key areas. By developing new energy source from key technologies of a main industrial control system, a novel new energy source group control system architecture is established, the integration and upgrading of industrial control technology and information technology are promoted, a scientific, advanced and intelligent control architecture is provided for the new energy source power generation industry, the power generation capacity and the power quality are improved, the safe and stable operation of a field-level power station is effectively ensured, a firm technical support is provided for creating a fault-free wind field, and powerful guarantee is provided for the construction of the digital and intelligent wind power industry.
The cluster control system for wind power autonomous cluster control in the prior art has the problem of low power generation efficiency due to insufficient rigor and insufficient completeness, so that the power generation efficiency of a wind power plant is not improved finally.
Disclosure of Invention
The application provides an optimal control method and system for rotating speed and torque, which solve the problem of low power generation efficiency caused by insufficient rigor and insufficient completeness of a cluster control system for wind power autonomous group control in the prior art, so that the power generation efficiency of a wind power plant is improved.
In view of the above, the present application provides a method for optimally controlling rotational speed and torque.
In a first aspect, the present application provides a method for optimally controlling rotational speed and torque, the method comprising: acquiring operation data of N wind power devices of a wind power cluster in a target area in historical time, and generating N historical operation data sets; searching in the N historical operation data sets by taking the generated power as an index to obtain N generated power sequences, and respectively identifying the generated power in the N generated power sequences based on the rotating speed-torque mapping values corresponding to the N generated power sequences; respectively performing performance peak value search on N wind power equipment based on N power generation sequences, and generating N optimal rotation speed-torque mapping values according to N search results; collecting environmental influence information of a target area at the current moment, wherein the environmental influence information comprises wind speed and wind direction; transmitting the wind speed and the wind direction, the N optimal rotation speed-torque mapping values and the N search results to an optimal control identification network layer to generate N optimal control parameters, wherein the optimal control parameters comprise rotation speed control parameters and torque control parameters; and optimally controlling the N wind power devices in the target area by utilizing the N optimal control parameters.
In a second aspect, the present application provides an optimized control system for rotational speed and torque, the system comprising: historical operation data module: acquiring operation data of N wind power devices of a wind power cluster in a target area in historical time, and generating N historical operation data sets; and a generating power sequence module: searching in the N historical operation data sets by taking the generated power as an index to obtain N generated power sequences, and respectively identifying the generated power in the N generated power sequences based on the rotating speed-torque mapping values corresponding to the N generated power sequences; performance peak search module: respectively performing performance peak value search on N wind power equipment based on N power generation sequences, and generating N optimal rotation speed-torque mapping values according to N search results; environmental impact information module: collecting environmental influence information of a target area at the current moment, wherein the environmental influence information comprises wind speed and wind direction; and (3) an optimal control parameter module: transmitting the wind speed and the wind direction, the N optimal rotation speed-torque mapping values and the N search results to an optimal control identification network layer to generate N optimal control parameters, wherein the optimal control parameters comprise rotation speed control parameters and torque control parameters; and the equipment optimization control module is used for: and optimally controlling the N wind power devices in the target area by utilizing the N optimal control parameters.
One or more technical solutions provided in the present application have at least the following technical effects or advantages:
according to the method and the system for optimizing control of the rotating speed and the torque, the N historical operation data sets are generated by acquiring the operation data of N wind power equipment of a wind power cluster in a target area in historical time, the generated power is taken as an index, the N historical operation data sets are searched to obtain N generated power sequences, the generated power in the N generated power sequences is respectively identified based on the rotating speed-torque mapping values corresponding to the N generated power sequences, then the N wind power equipment is respectively subjected to performance peak search based on the N generated power sequences, N optimal rotating speed-torque mapping values are generated according to the N search results, the environmental influence information of the target area at the current moment is acquired, the wind speed and the wind direction, the N optimal rotating speed-torque mapping values and the N search results are transmitted to an optimizing control identification network layer, N optimizing control parameters are generated, and finally the N wind power equipment in the target area is optimally controlled by the N optimizing control parameters, so that the problem that the wind power cluster control system in the prior art is low in generating efficiency due to insufficient precision and completeness is solved, and the generating efficiency of the wind power plant is improved.
Drawings
FIG. 1 is a schematic flow chart of a method for optimizing and controlling rotational speed and torque;
fig. 2 is a schematic structural diagram of an optimized control system for rotational speed and torque.
Reference numerals illustrate: the system comprises a historical operation data module 11, a generated power sequence module 12, a performance peak value searching module 13, an environment influence information module 14, an optimization control parameter module 15 and a device optimization control module 16.
Detailed Description
According to the method and the system for optimizing control of the rotating speed and the torque, N historical operation data sets are generated by acquiring operation data of N wind power devices of a wind power cluster in a target area in historical time, generating N historical operation data sets, then taking power generation power as an index, searching in the N historical operation data sets to obtain N power generation sequences, respectively identifying the power generation power in the N power generation sequences based on rotating speed-torque mapping values corresponding to the N power generation sequences, respectively performing performance peak search on the N wind power devices based on the N power generation sequences, generating N optimal rotating speed-torque mapping values according to N search results, acquiring environmental influence information of the target area at the current moment, transmitting the wind speed and the wind direction, the N optimal rotating speed-torque mapping values and the N search results into an optimizing control identification network layer, generating N optimizing control parameters, and finally performing optimizing control on the N wind power devices in the target area by utilizing the N optimizing control parameters. The cluster control system solves the problem of low power generation efficiency caused by insufficient rigor and insufficient completeness of a cluster control system for wind power autonomous cluster control in the prior art, so that the power generation efficiency of a wind power plant is improved.
Example 1
As shown in fig. 1, the present application provides a method for optimally controlling rotational speed and torque, including:
acquiring operation data of N wind power devices of a wind power cluster in a target area in historical time, and generating N historical operation data sets;
the target area is an area where the wind power equipment is located, a plurality of wind power equipment forms a wind power cluster, each wind power equipment is provided with corresponding data monitoring equipment, the wind power equipment is monitored through the data monitoring equipment, and corresponding operation data are obtained. One wind power device corresponds to one historical operation data set, and how many wind power devices correspond to how many historical operation data sets. The historical operational data set includes operational data for each wind power plant. The operational data includes wind speed, power output, temperature, pressure, and maintenance records. The operation data of the wind power equipment are obtained through the data monitoring equipment, the operation data are preprocessed, a historical operation data set is generated, and the historical event data set is stored in a proper data storage system, so that the safety of the data is ensured. And searching in the N historical operation data sets by taking the generated power as an index for the follow-up, obtaining N generated power sequences, and respectively marking the generated power in the N generated power sequences based on the rotating speed-torque mapping values corresponding to the N generated power sequences to provide a data basis.
Searching in the N historical operation data sets by taking the generated power as an index to obtain N generated power sequences, and respectively identifying the generated power in the N generated power sequences based on the rotating speed-torque mapping values corresponding to the N generated power sequences;
traversing the N power generation sequences, and calling operation record data in a wind power equipment management system;
and respectively searching the operation record data at the same moment by the rotating speed and the torque, thereby obtaining the rotating speed-torque mapping value.
Traversing the N power generation sequences, calling operation record data in the wind power equipment management system, acquiring a plurality of power generation powers after the operation record data are called, and carrying out serialization arrangement on the plurality of power generation powers to obtain a plurality of power generation sequences. Determining operation record data at the same moment in each power generation sequence, selecting the value with the same or closest timestamp in each power generation sequence as the operation record data at the same moment, traversing corresponding rotation speed and torque values according to the operation record data at the same moment, establishing a mapping relation between the rotation speed and the torque through regression analysis, calculating a mapping value according to the mapping relation, and taking the mapping value as a rotation speed-torque mapping value. The generated power of each generated power sequence is identified as a corresponding rotation speed-torque combination according to the rotation speed and torque value of the generated power sequence. This is accomplished by looking up corresponding rotational speed and torque values in the map and using these values to identify the generated power in the generated power sequence. After the mapping relation between the rotating speed and the torque is obtained, a nonlinear relation exists between the rotating speed and the torque. Therefore, the nonlinear mapping relation is required to be used for identifying the generated power in the generated power sequence more accurately, the nonlinear mapping relation is subjected to linear processing, performance peak search is respectively carried out on N wind power devices based on N generated power sequences, and a data base is provided for generating N optimal rotation speed-torque mapping values according to N search results.
Respectively performing performance peak value search on N wind power equipment based on N power generation sequences, and generating N optimal rotation speed-torque mapping values according to N search results;
constructing N mapping particle spaces based on the N generated power sequences, wherein each mapping particle space comprises a plurality of mapping particles, each mapping particle corresponds to one single power, and each mapping particle has a rotating speed-torque mapping value identifier;
respectively carrying out particle gravity center search on the N mapping particle spaces to obtain N mapping particle gravity centers, and calculating the particle density of the N mapping particle gravity centers;
searching in N mapping particle spaces according to a preset searching step length by taking the centers of gravity of N mapping particles as starting points, and obtaining N searching particles when searching to the particle closest to the centers of gravity of the N mapping particles;
calculating the particle density of the N search particles;
judging whether the particle density of the gravity centers of the N mapping particles is larger than that of the N searching particles, if so, updating the gravity centers of the N mapping particles into N searching particles;
and searching for multiple times according to the N search particles until the preset searching times are met, obtaining N target search particles, and taking the N target search particles as N search results.
The performance peak refers to the optimum value of the generated power, and the map particle space is a kind of map space. The mapped particle space exists in the mapped particle space as a basic unit of the mapped particle space. Each map particle space includes a plurality of map particles, each map particle corresponds to a particular generated power, and each map particle has a rotational speed-torque map value identification, i.e., has rotational speed and torque values corresponding to the generated power. Particle center of gravity searching is performed for each space separately. This can be done by calculating the average position of all particles in each space. The center of gravity of a particle refers to the average value of the rotational speed and torque values of all particles in each space. And calculating the ratio of the number of particles in the preset range of the N mapping particle centers to the total number of particles in the N mapping particle spaces, wherein the calculation result is the particle density of the N mapping particle centers. And searching in N mapping particle spaces according to a preset searching step length by taking the centers of gravity of the N mapping particles as starting points. The search step length refers to a search range required for one search. During the search, the particles closest to the center of gravity of each particle are determined. And by comparing the distance of each particle to the center of gravity of each particle. When a particle closest to the center of gravity of a certain particle is searched, the particle is used as a search particle for the center of gravity.
After obtaining N search particles, the particle densities of these particles are calculated, and similarly, the particle densities of the search particles are obtained by calculating the number of particles around each particle using a particle density calculation method, and the particle densities are compared, and if the particle density of the barycenter of the map particles is greater than the particle density of the search particles, the current map particles may be considered to be not optimal, and the barycenter of the N map particles may be updated to N search particles. And searching for multiple times according to the N search particles until the preset searching times are met. The current search particles are explored and evaluated in each search and the search results are updated. And after the preset searching times are met, taking the obtained N target searching particles as final searching results. These target search particles may represent optimal speed-to-torque map values for a given sequence of generated power, with N optimal speed-to-torque map values being generated from N search results. The rotation speed-torque mapping value can be further analyzed and optimized by comparing the particle density of the gravity centers of the N mapping particles with the particle density of the N searching particles and judging whether the current mapping particles need to be updated.
Collecting environmental influence information of a target area at the current moment, wherein the environmental influence information comprises wind speed and wind direction;
collecting first environmental impact information of a target area in a preset time interval at the current moment;
obtaining a wind speed interval and a wind direction interval based on the first environmental impact information;
performing stability evaluation based on the wind speed interval to obtain a first evaluation result;
performing stability evaluation based on the wind direction interval to obtain a second evaluation result;
and correcting the environmental impact information based on the first evaluation result and the second evaluation result.
The environmental image information is an environmental influence factor which influences the rotating speed and the torque of the wind turbine, and comprises wind speed and wind direction. And (3) the wind speed and wind direction data are acquired in real time by installing a wind speed and wind direction monitor in the target area. However, the wind speed and the wind direction are not stable values, and the wind speed and the wind direction need to be corrected. The method comprises the steps of collecting environmental influence information such as wind speed and wind direction of a target area in a preset time interval through a wind speed and wind direction monitor, analyzing first environmental influence information through a statistical method, data analysis or machine learning and other technologies, and determining a wind speed interval and a wind direction interval of the target area. The stability evaluation indicates a change in the wind speed section or the wind direction section. And evaluating the stability of the wind speed section and the wind direction section through historical data, and obtaining corresponding evaluation results, wherein the stability result of the wind speed section is a first evaluation result, and the stability evaluation result of the wind direction section is a second evaluation result. And comprehensively considering the first evaluation result and the second evaluation result, and correcting the environmental impact information. For example, if both evaluation results indicate that wind speed and wind direction exhibit high stability in a target area, the environmental impact information of the area can be considered to be reliable. Conversely, if the stability is low, further adjustments or corrections to the collected environmental impact information are required. The environmental impact information is corrected through the first evaluation result and the second evaluation result, so that the environmental impact information can be more accurate.
Transmitting the wind speed and the wind direction, the N optimal rotation speed-torque mapping values and the N search results to an optimal control identification network layer to generate N optimal control parameters, wherein the optimal control parameters comprise rotation speed control parameters and torque control parameters;
and optimally controlling the N wind power devices in the target area by utilizing the N optimal control parameters.
Acquiring a plurality of sample wind speeds, a plurality of sample wind directions, a plurality of sample optimal rotation speed-torque mapping values, a plurality of sample search results and a plurality of sample optimal control parameters as training data;
and performing supervision training on the network layer constructed based on the feedforward neural network model by utilizing training data until the output reaches convergence, so as to obtain the optimal control recognition network layer.
And transmitting the wind speed and wind direction information of the target area at the current moment to the optimal control identification network layer. The optimal control recognition network layer is a deep learning model and is constructed through a feedforward neural network model. And transmitting the wind speed and the wind direction, the N optimal rotation speed-torque mapping values and the N search results to an optimal control identification network layer. The method comprises the steps of constructing an optimal control identification network layer, firstly collecting training sample data of the network layer, acquiring a plurality of sample wind speeds, a plurality of sample wind directions, a plurality of sample optimal rotation speed-torque mapping values, a plurality of sample search results and a plurality of sample optimal control parameters based on historical data and big data, serving as training data, and preprocessing the collected data, such as data cleaning, normalization, interpolation and the like, so as to ensure the quality and consistency of the data. And sorting the preprocessed data into a training data set. The training data set should include input data (e.g., environmental impact information such as wind speed, wind direction, etc.) and corresponding target data (e.g., optimal rotational speed-torque map values, search results, optimal control parameters, etc.). Selecting a proper feedforward neural network model, configuring super parameters such as the layer number, the neuron number, the activation function and the like of the model, training the feedforward neural network model by using a training set until the output of the model reaches a convergence state, and acquiring an optimal control identification network layer.
The optimizing control identification network layer performs optimizing control processing on the N optimal rotation speed-torque mapping values and the N search results to generate optimizing control parameters. The optimization control parameters include a rotational speed control parameter and a torque control parameter, which respectively regulate the rotational speed and the torque output of the device. And transmitting the generated N optimized control parameters to a control system of each wind power device. In a control system of a wind power plant, the received optimized control parameters are applied to the rotational speed and torque control of the plant. And starting the wind power equipment and monitoring the running state and performance of the wind power equipment in real time. In the process of optimizing control, the operation data and performance of the wind power equipment are recorded, problems are found and improved, and therefore the performance and efficiency of the equipment are further improved.
Example two
Based on the same inventive concept as the method for optimizing control of rotational speed and torque in the foregoing embodiment, as shown in fig. 2, the present application provides a system for optimizing control of rotational speed and torque, the system comprising:
historical operating data module 11: the historical operation data module 11 is used for acquiring operation data of N wind power devices of the wind power cluster in the target area in historical time and generating N historical operation data sets;
the generated power sequence module 12: the power generation power sequence module 12 is configured to search in the N historical operation data sets with power generation power as an index, obtain N power generation power sequences, and identify power generation power in the N power generation power sequences based on rotational speed-torque mapping values corresponding to the N power generation power sequences, respectively;
performance peak search module 13: the performance peak search module 13 is configured to perform performance peak search on N wind power devices based on N power generation sequences, and generate N optimal rotation speed-torque mapping values according to N search results;
the environmental impact information module 14: the environmental impact information module 14 is configured to collect environmental impact information of a target area at a current moment, where the environmental impact information includes wind speed and wind direction;
the optimization control parameter module 15: the optimization control parameter module 15 is configured to transmit the wind speed and the wind direction, the N optimal rotation speed-torque mapping values, and the N search results to an optimization control identification network layer, and generate N optimization control parameters, where the optimization control parameters include a rotation speed control parameter and a torque control parameter;
the device optimization control module 16: the device optimizing control module 16 is configured to optimally control N wind power devices in the target area by using the N optimizing control parameters.
Further, the system further comprises:
traversing the N power generation sequences, and calling operation record data in a wind power equipment management system;
and respectively searching the operation record data at the same moment by the rotating speed and the torque, thereby obtaining the rotating speed-torque mapping value.
Further, the system further comprises:
constructing N mapping particle spaces based on the N generated power sequences, wherein each mapping particle space comprises a plurality of mapping particles, each mapping particle corresponds to one single power, and each mapping particle has a rotating speed-torque mapping value identifier;
respectively carrying out particle gravity center search on the N mapping particle spaces to obtain N mapping particle gravity centers, and calculating the particle density of the N mapping particle gravity centers;
searching in N mapping particle spaces according to a preset searching step length by taking the centers of gravity of N mapping particles as starting points, and obtaining N searching particles when searching to the particle closest to the centers of gravity of the N mapping particles;
further, the system further comprises:
calculating the particle density of the N search particles;
judging whether the particle density of the gravity centers of the N mapping particles is larger than that of the N searching particles, if so, updating the gravity centers of the N mapping particles into N searching particles;
and searching for multiple times according to the N search particles until the preset searching times are met, obtaining N target search particles, and taking the N target search particles as N search results.
Further, the system further comprises:
and calculating the ratio of the number of particles in the preset range of the N mapping particle centers to the total number of particles in the N mapping particle spaces, and generating the particle density of the N mapping particle centers.
Further, the system further comprises:
acquiring a plurality of sample wind speeds, a plurality of sample wind directions, a plurality of sample optimal rotation speed-torque mapping values, a plurality of sample search results and a plurality of sample optimal control parameters as training data;
and performing supervision training on the network layer constructed based on the feedforward neural network model by utilizing training data until the output reaches convergence, so as to obtain the optimal control recognition network layer.
Further, the system further comprises:
collecting first environmental impact information of a target area in a preset time interval at the current moment;
obtaining a wind speed interval and a wind direction interval based on the first environmental impact information;
performing stability evaluation based on the wind speed interval to obtain a first evaluation result;
performing stability evaluation based on the wind direction interval to obtain a second evaluation result;
and correcting the environmental impact information based on the first evaluation result and the second evaluation result.
The foregoing detailed description of a method for optimizing and controlling a rotational speed and a torque will be apparent to those skilled in the art, and the device disclosed in this embodiment is relatively simple to describe, and the relevant places refer to the method part for description.
The previous description of the disclosed embodiments is provided to enable any person skilled in the art to make or use the present application. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the generic principles defined herein may be applied to other embodiments without departing from the spirit or scope of the application. Thus, the present application is not intended to be limited to the embodiments shown herein but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.
Claims (8)
1. An optimized control method for rotating speed and torque is characterized by comprising the following steps:
acquiring operation data of N wind power devices of a wind power cluster in a target area in historical time, and generating N historical operation data sets;
searching in the N historical operation data sets by taking the generated power as an index to obtain N generated power sequences, and respectively identifying the generated power in the N generated power sequences based on the rotating speed-torque mapping values corresponding to the N generated power sequences;
respectively performing performance peak value search on N wind power equipment based on N power generation sequences, and generating N optimal rotation speed-torque mapping values according to N search results;
collecting environmental influence information of a target area at the current moment, wherein the environmental influence information comprises wind speed and wind direction;
transmitting the wind speed and the wind direction, the N optimal rotation speed-torque mapping values and the N search results to an optimal control identification network layer to generate N optimal control parameters, wherein the optimal control parameters comprise rotation speed control parameters and torque control parameters;
and optimally controlling the N wind power devices in the target area by utilizing the N optimal control parameters.
2. The method of claim 1, wherein the method further comprises:
traversing the N power generation sequences, and calling operation record data in a wind power equipment management system;
and respectively searching the operation record data at the same moment by the rotating speed and the torque, thereby obtaining the rotating speed-torque mapping value.
3. The method of claim 1, wherein the method further comprises:
constructing N mapping particle spaces based on the N generated power sequences, wherein each mapping particle space comprises a plurality of mapping particles, each mapping particle corresponds to one single power, and each mapping particle has a rotating speed-torque mapping value identifier;
respectively carrying out particle gravity center search on the N mapping particle spaces to obtain N mapping particle gravity centers, and calculating the particle density of the N mapping particle gravity centers;
and searching in the N mapping particle spaces according to a preset searching step length by taking the centers of gravity of the N mapping particles as starting points, and obtaining N searching particles when searching to the particle closest to the centers of gravity of the N mapping particles.
4. A method as claimed in claim 3, wherein the method further comprises:
calculating the particle density of the N search particles;
judging whether the particle density of the gravity centers of the N mapping particles is larger than that of the N searching particles, if so, updating the gravity centers of the N mapping particles into N searching particles;
and searching for multiple times according to the N search particles until the preset searching times are met, obtaining N target search particles, and taking the N target search particles as N search results.
5. The method of claim 4, wherein the particle density of the N mapped particle centers is generated by calculating a ratio of a number of particles within a predetermined range of the N mapped particle centers to a total number of particles within the N mapped particle spaces.
6. The method of claim 1, wherein the method further comprises:
acquiring a plurality of sample wind speeds, a plurality of sample wind directions, a plurality of sample optimal rotation speed-torque mapping values, a plurality of sample search results and a plurality of sample optimal control parameters as training data;
and performing supervision training on the network layer constructed based on the feedforward neural network model by utilizing training data until the output reaches convergence, so as to obtain the optimal control recognition network layer.
7. The method of claim 1, wherein the method further comprises:
collecting first environmental impact information of a target area in a preset time interval at the current moment;
obtaining a wind speed interval and a wind direction interval based on the first environmental impact information;
performing stability evaluation based on the wind speed interval to obtain a first evaluation result;
performing stability evaluation based on the wind direction interval to obtain a second evaluation result;
and correcting the environmental impact information based on the first evaluation result and the second evaluation result.
8. An optimized control system for rotational speed and torque, the system comprising:
historical operation data module: acquiring operation data of N wind power devices of a wind power cluster in a target area in historical time, and generating N historical operation data sets;
and a generating power sequence module: searching in the N historical operation data sets by taking the generated power as an index to obtain N generated power sequences, and respectively identifying the generated power in the N generated power sequences based on the rotating speed-torque mapping values corresponding to the N generated power sequences;
performance peak search module: respectively performing performance peak value search on N wind power equipment based on N power generation sequences, and generating N optimal rotation speed-torque mapping values according to N search results;
environmental impact information module: collecting environmental influence information of a target area at the current moment, wherein the environmental influence information comprises wind speed and wind direction;
and (3) an optimal control parameter module: transmitting the wind speed and the wind direction, the N optimal rotation speed-torque mapping values and the N search results to an optimal control identification network layer to generate N optimal control parameters, wherein the optimal control parameters comprise rotation speed control parameters and torque control parameters;
and the equipment optimization control module is used for: and optimally controlling the N wind power devices in the target area by utilizing the N optimal control parameters.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311684910.1A CN117869181A (en) | 2023-12-08 | 2023-12-08 | Optimal control method and system for rotating speed and torque |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311684910.1A CN117869181A (en) | 2023-12-08 | 2023-12-08 | Optimal control method and system for rotating speed and torque |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN117869181A true CN117869181A (en) | 2024-04-12 |
Family
ID=90576297
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311684910.1A Pending CN117869181A (en) | 2023-12-08 | 2023-12-08 | Optimal control method and system for rotating speed and torque |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117869181A (en) |
-
2023
- 2023-12-08 CN CN202311684910.1A patent/CN117869181A/en active Pending
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111596604B (en) | Intelligent fault diagnosis and self-healing control system and method for engineering equipment based on digital twinning | |
| CN113112086B (en) | Intelligent production system based on edge calculation and identification analysis | |
| CN109829236B (en) | XGboost feature extraction-based compressor fault diagnosis method | |
| CN110288136B (en) | Wind power multi-step prediction model establishment method | |
| CN111639921B (en) | Intelligent equipment fault judgment and auxiliary disposal method based on expert system | |
| CN109255440B (en) | Method for predictive maintenance of power production equipment based on Recurrent Neural Networks (RNN) | |
| CN109102101B (en) | Wind speed prediction method and system for wind power plant | |
| CN114429153B (en) | Gear box increment fault diagnosis method and system based on life learning | |
| CN110929934A (en) | Equipment failure prediction method and device, computer equipment and storage medium | |
| CN106383916B (en) | Data processing method based on predictive maintenance of industrial equipment | |
| CN114856941A (en) | Offshore wind power plant and unit fault diagnosis operation and maintenance system and diagnosis operation and maintenance method thereof | |
| CN116599857B (en) | Digital twin application system suitable for multiple scenes of Internet of things | |
| Li et al. | Framework and case study of cognitive maintenance in Industry 4.0 | |
| CN114004512A (en) | Multi-unit operation state outlier analysis method and system based on density clustering | |
| Vives | Vibration analysis for fault detection in wind turbines using machine learning techniques | |
| CN114418177B (en) | New product material distribution prediction method based on digital twin workshops for generating countermeasure network | |
| Bao et al. | Wind turbine condition monitoring based on improved active learning strategy and KNN algorithm | |
| CN110188939B (en) | Wind power prediction method, system, equipment and storage medium of wind power plant | |
| CN116595353A (en) | Remote fault diagnosis and intelligent decision system for camera | |
| CN117869181A (en) | Optimal control method and system for rotating speed and torque | |
| CN116467592A (en) | Production equipment fault intelligent monitoring method and system based on deep learning | |
| CN115640980A (en) | Power grid engineering cost dynamic management system based on target control | |
| Li et al. | Research on digital twin and collaborative cloud and edge computing applied in operations and maintenance in wind turbines of wind power farm | |
| Torikka et al. | Predictive Maintenance Service Powered by Machine Learning and Big Data | |
| CN118014395A (en) | Fan cluster-oriented multi-view hypergraph power prediction method |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication |