CN113357083A - Intelligent control system and method for wind generating set - Google Patents
Intelligent control system and method for wind generating set Download PDFInfo
- Publication number
- CN113357083A CN113357083A CN202110905410.0A CN202110905410A CN113357083A CN 113357083 A CN113357083 A CN 113357083A CN 202110905410 A CN202110905410 A CN 202110905410A CN 113357083 A CN113357083 A CN 113357083A
- Authority
- CN
- China
- Prior art keywords
- edge
- level
- data
- wind
- control device
- 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 25
- 238000004422 calculation algorithm Methods 0.000 claims abstract description 148
- 238000004891 communication Methods 0.000 claims description 59
- 230000003993 interaction Effects 0.000 claims description 27
- 238000007781 pre-processing Methods 0.000 claims description 26
- 238000004364 calculation method Methods 0.000 claims description 17
- 230000004927 fusion Effects 0.000 claims description 12
- 238000012545 processing Methods 0.000 claims description 11
- 238000013500 data storage Methods 0.000 claims description 8
- 238000012544 monitoring process Methods 0.000 claims description 4
- 238000010248 power generation Methods 0.000 abstract description 5
- 206010063385 Intellectualisation Diseases 0.000 description 5
- 230000005540 biological transmission Effects 0.000 description 3
- 238000006243 chemical reaction Methods 0.000 description 3
- 238000000605 extraction Methods 0.000 description 3
- 230000006870 function Effects 0.000 description 3
- 238000012986 modification Methods 0.000 description 3
- 230000004048 modification Effects 0.000 description 3
- 230000001680 brushing effect Effects 0.000 description 2
- 238000004140 cleaning Methods 0.000 description 2
- 238000013501 data transformation Methods 0.000 description 2
- 238000013461 design Methods 0.000 description 2
- 238000011161 development Methods 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 230000010354 integration Effects 0.000 description 2
- 238000012821 model calculation Methods 0.000 description 2
- 230000008569 process Effects 0.000 description 2
- 230000009467 reduction Effects 0.000 description 2
- 241000282414 Homo sapiens Species 0.000 description 1
- 230000003044 adaptive effect Effects 0.000 description 1
- 238000007792 addition Methods 0.000 description 1
- 230000004075 alteration Effects 0.000 description 1
- 238000013473 artificial intelligence Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000007418 data mining Methods 0.000 description 1
- 238000012217 deletion Methods 0.000 description 1
- 230000037430 deletion Effects 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 230000005611 electricity Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000005457 optimization Methods 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 230000001360 synchronised effect Effects 0.000 description 1
Images
Classifications
-
- F—MECHANICAL ENGINEERING; LIGHTING; HEATING; WEAPONS; BLASTING
- F03—MACHINES OR ENGINES FOR LIQUIDS; WIND, SPRING, OR WEIGHT MOTORS; PRODUCING MECHANICAL POWER OR A REACTIVE PROPULSIVE THRUST, NOT OTHERWISE PROVIDED FOR
- F03D—WIND MOTORS
- F03D7/00—Controlling wind motors
- F03D7/02—Controlling wind motors the wind motors having rotation axis substantially parallel to the air flow entering the rotor
- F03D7/04—Automatic control; Regulation
- F03D7/042—Automatic control; Regulation by means of an electrical or electronic controller
- F03D7/043—Automatic control; Regulation by means of an electrical or electronic controller characterised by the type of control logic
- F03D7/045—Automatic control; Regulation by means of an electrical or electronic controller characterised by the type of control logic with model-based controls
-
- F—MECHANICAL ENGINEERING; LIGHTING; HEATING; WEAPONS; BLASTING
- F03—MACHINES OR ENGINES FOR LIQUIDS; WIND, SPRING, OR WEIGHT MOTORS; PRODUCING MECHANICAL POWER OR A REACTIVE PROPULSIVE THRUST, NOT OTHERWISE PROVIDED FOR
- F03D—WIND MOTORS
- F03D7/00—Controlling wind motors
- F03D7/02—Controlling wind motors the wind motors having rotation axis substantially parallel to the air flow entering the rotor
- F03D7/04—Automatic control; Regulation
- F03D7/042—Automatic control; Regulation by means of an electrical or electronic controller
- F03D7/043—Automatic control; Regulation by means of an electrical or electronic controller characterised by the type of control logic
- F03D7/046—Automatic control; Regulation by means of an electrical or electronic controller characterised by the type of control logic with learning or adaptive control, e.g. self-tuning, fuzzy logic or neural network
-
- 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
Abstract
The invention discloses an intelligent control system and method for a wind generating set, belonging to the technical field of wind power generation, wherein the system comprises a plurality of edge computing subsystems and at least one wind field level computing subsystem which are mutually communicated and connected, and each edge computing subsystem is respectively communicated and connected with at least one main control device; the main control devices communicate with the edge computing subsystems and the wind field level computing subsystems to exchange data, algorithm model operation results of the edge computing subsystems and the wind field level computing subsystems are fed back to the main control devices, intelligent control and operation state adjustment are conducted on the fans corresponding to the main control devices, wind power intelligent control and effective landing are achieved, multi-dimensional data of the fans are collected and processed, intelligent control and state adjustment of the fans are achieved based on the algorithm models deployed in the fans and the wind field, the intelligent algorithm is achieved, real landing of the intelligent algorithm is achieved, and the purpose of effectively increasing the power generation amount of the fans is achieved.
Description
Technical Field
The invention belongs to the technical field of wind power generation, and particularly relates to an intelligent control system and method for a wind generating set.
Background
Wind energy is available energy provided by nature to human beings, is a conversion form of solar energy, and belongs to renewable energy sources. Wind energy is converted into electric energy through a wind generating set (hereinafter referred to as a fan), and the electric energy obtained through conversion is transmitted to equipment needing electricity in various places through a power grid.
With the continuous development and innovative application of industrial big data, edge computing, cloud computing and artificial intelligence technologies and the gradual maturity of fan control technologies, the fan research direction is developing towards the intellectualization of self-adaptation, self-adjustment, self-decision and the like. The intellectualization of the wind generating set is an important engine of the revolution of the wind power industry, and the intellectualization have become the mainstream trend of the development of the whole wind power industry.
In the existing technical route of the industry, basic operation data of a fan is collected by a fan main control system, collected and stored by a wind power plant monitoring System (SCADA), and then sent out to an internet cloud server, and various reference or execution parameters required by intelligent control or cluster coordination control of the fan are calculated and obtained by an algorithm model on the cloud server based on various data.
In practical applications, there are several main problems: 1. data collected by the fan master control system have a large amount of invalid data and dirty data, and data mining or algorithm model inputting cannot be directly carried out; 2. the main control system of the fan is mostly a PLC (programmable logic controller), and the preprocessing of data and the operation of an algorithm model are completed due to insufficient computing power; 3. due to the limitation of bandwidth of an internal communication network and an external network of the wind power plant, the accuracy of data transmitted to the cloud is insufficient (mostly 1S level or several S levels), and algorithm model calculation cannot be well supported; 4. and the real-time performance that the calculation result of the cloud algorithm model is fed back to the wind field or the fan cannot be guaranteed due to the limitation of a communication network. Finally, the intelligent algorithm model has inaccurate operation result and low real-time performance, and cannot effectively participate or refer to fan control and close-loop fan control, so that the fan intellectualization is greatly reduced. Meanwhile, the leaked safety loophole exists in the wind power plant outgoing data, and the safe operation of the wind power plant is not facilitated.
Disclosure of Invention
In view of the above, in order to solve the above problems in the prior art, the present invention aims to provide an intelligent control system and method for a wind turbine generator system to achieve wind power intelligent control and efficient landing, and achieve the purposes of achieving intelligent control and state adjustment of a wind turbine based on an algorithm model deployed in the wind turbine and the wind farm by collecting and processing multi-dimensional data of the wind turbine, achieving real landing of an intelligent algorithm, and effectively increasing the power generation capacity of the wind turbine.
The technical scheme adopted by the invention is as follows: an intelligent control system of a wind generating set comprises a plurality of edge computing subsystems and at least one wind field level computing subsystem which are mutually communicated and connected, wherein each edge computing subsystem is respectively communicated and connected with at least one main control device;
and each main control device is communicated with each edge computing subsystem and each wind field level computing subsystem to exchange data, and the arithmetic model operation result of each edge computing subsystem and each wind field level computing subsystem is fed back to each main control device so as to intelligently control and adjust the running state of the fan corresponding to each main control device.
Furthermore, the master control device is arranged on the corresponding fan, and data of the control device and the sensor matched with the fan are collected through the master control device.
Furthermore, a computing resource pool is constructed among the edge computing subsystems through unified scheduling of hardware resources, and the computing resource pool shares data computing capacity;
the cluster of the fan edge computing subsystems is based on big data frame design and cooperative scheduling, so that distributed computing can be performed on mass data in the multi-edge computing equipment cluster, and sharing of data and computing power among the multi-edge computing subsystems is completed.
Furthermore, the edge computing subsystem is arranged on the corresponding fan and comprises an edge level communication module, an edge level data processing module and an edge level algorithm module which are in communication connection with each other;
the wind field level computing subsystem is deployed in a wind field control center and comprises a wind field level communication module, a wind field level data storage module, a wind field level algorithm module and a man-machine interaction module which are in communication connection with one another.
Further, the edge-level communication module communicates with the corresponding main control device in real time and acquires all original data of the main control device;
the edge-level communication module is communicated with edge-level communication modules of other edge computing subsystems in real time and performs data interaction to acquire all data of the other edge computing subsystems;
and the edge-level communication module is in real-time communication with the wind field-level calculation subsystem and performs data interaction.
Further, the edge-level data processing module is used for performing data preprocessing on the original data acquired by the edge-level communication module according to the requirements of different algorithm models, finishing preprocessing by adopting data brushing, data cleaning, data integration, data transformation, data reduction and data feature extraction methods, finishing data statistics according to various application scenes, and inputting the preprocessed data to the edge-level algorithm module or sending the preprocessed data to the wind farm-level computing subsystem through the edge-level communication module.
Furthermore, the edge-level algorithm module is integrated with an edge algorithm model library, and selects original data and/or preprocessed data corresponding to the fan and other fans of the full wind field as input according to the requirements of the current algorithm model, and obtains a corresponding edge-level algorithm result after the operation of the algorithm model;
and the edge-level algorithm result is sent to the corresponding main control device by the edge-level communication module, and the operation of the fan is controlled by the main control device.
Furthermore, the wind farm level communication module is used for communicating with each main control device and the edge computing subsystem in the full wind farm in real time and acquiring data.
Furthermore, the wind farm level algorithm module is integrated with a wind farm level algorithm model library, and corresponding wind farm level algorithm results or cluster cooperative control instructions are obtained after the operation of the algorithm model by inputting the original data and/or the preprocessed data of the single fan or the whole fan into the corresponding algorithm model;
and the wind field level algorithm result or the cluster cooperative control instruction is sent to the main control device by the edge communication module, and the main control device is used for controlling the operation and adjusting the parameters of the fan.
Further, the wind farm level data storage module is used for storing original data of each main control device in the full wind farm, preprocessed data of each edge computing subsystem, edge level algorithm results and wind farm level algorithm results operated by the wind farm level algorithm module.
Furthermore, the human-computer interaction module is used for managing each fan edge computing subsystem and each wind field level computing subsystem of the full wind field;
the human-computer interaction module is used for monitoring the running states of each fan edge computing subsystem and each wind field level computing subsystem in the full wind field;
the man-machine interaction module is used for calling query data from the wind field level computing subsystem and displaying the query data;
and the human-computer interaction module is used for operating the coordination control of each fan in the whole wind field.
The invention also provides an intelligent control method of the wind generating set, which comprises the following steps:
acquiring all original data of all fans in the whole wind farm corresponding to the main control device, and acquiring preprocessed data of all edge computing subsystems in the whole wind farm according to the requirements of the algorithm model;
each edge computing subsystem carries out data preprocessing and fusion according to original data and preprocessing data required by the edge-level algorithm model and the wind field-level algorithm model so as to obtain preprocessing and fusion data;
the method comprises the steps that original data, preprocessing and fusion data are sent to a wind field level computing subsystem and are input into a wind field level algorithm model in the wind field level computing subsystem as required, wind field level algorithm results or a machine group cooperative control instruction are output through the wind field level algorithm model and fed back to a main control device, and the main control device controls the operation of a fan;
and inputting required original data, preprocessing and fusion data into an edge-level algorithm model in an edge calculation subsystem, outputting an edge-level algorithm result through the edge-level algorithm model and feeding back the edge-level algorithm result to a main control device, and controlling the operation of the fan by the main control device.
The invention has the beneficial effects that:
1. the intelligent control system of the wind generating set provided by the invention is mainly composed of a fan main control device, a fan edge computing subsystem and a wind field level computing subsystem, based on industrial big data and edge computing concepts, the edge computing subsystem is arranged at the end part of the fan to realize synchronous acquisition and processing of multi-dimensional high-frequency data of the fan, high-quality extraction and conversion, a plurality of fan edge computing subsystems are built into a big data framework, an intelligent algorithm model is arranged at the end part of the fan or the wind field level while sharing data and computing power, the operation of the intelligent algorithm model is completed in the wind field, the operation control and parameter adjustment of the local closed-loop fan of the wind field are realized by the support algorithm model, the intelligent adaptive control and more optimal state adjustment of the fan are finally realized, the cooperative optimization control of the fan group is realized, and the intelligent algorithm really falls to the ground, effectively increase fan generated energy, improve operation safety and stability.
2. The intelligent control method for the wind generating set is different from the design idea that local data needs to be sent out to the internet cloud in traditional big data, improves the real-time performance and effectiveness of the operation result of the algorithm model in control, avoids the risk of wind field data leakage, and saves the network transmission cost of data sending out.
Drawings
FIG. 1 is a schematic system architecture diagram of an intelligent control system of a wind generating set provided by the invention;
fig. 2 is a work flow chart of an intelligent control method of a wind generating set provided by the invention.
Detailed Description
Reference will now be made in detail to embodiments of the present application, examples of which are illustrated in the accompanying drawings, wherein like or similar reference numerals refer to the same or similar modules or modules having the same or similar functionality throughout. The embodiments described below with reference to the drawings are exemplary only for the purpose of explaining the present application and are not to be construed as limiting the present application. On the contrary, the embodiments of the application include all changes, modifications and equivalents coming within the spirit and terms of the claims appended hereto.
Example 1
In order to solve the problem of intellectualization in the existing wind power industry, the embodiment provides an intelligent control system for a wind generating set, and the system comprises a plurality of edge computing subsystems and at least one wind farm level computing subsystem which are in communication connection with each other, wherein each edge computing subsystem is in communication connection with at least one main control device. As shown in fig. 1, in this embodiment, four fan ends and a wind field center level are specifically provided, each fan end is composed of an edge computing subsystem and a main control device, and the wind field center level is composed of a wind field level computing subsystem. Each main control device is respectively in communication connection with the edge computing subsystems where the fan ends are located, and the edge computing subsystems and the wind field level computing subsystems are also in communication connection with each other.
And each main control device is communicated with each edge computing subsystem and each wind field level computing subsystem to exchange data, and the arithmetic model operation result of each edge computing subsystem and each wind field level computing subsystem is fed back to each main control device so as to intelligently control and adjust the running state of the fan corresponding to each main control device.
For the master control device part
The main control device is arranged on the corresponding fan and used for controlling the automatic operation of the fan. Gather the data of supporting controlling means and the sensor of this fan through master control set, specifically do: and collecting data of all matched control devices such as an access sensor, a fan variable pitch device, a converter device and the like. In practical application, the main control device can communicate with the corresponding edge computing subsystem and the wind field level computing subsystem to exchange data, receive the algorithm model operation results output by the edge computing subsystem and the wind field level computing subsystem, and complete intelligent control and operation state adjustment according to the algorithm model operation results.
For the edge calculation subsystem part
In this embodiment, a computing resource pool is constructed among the edge computing subsystems through unified scheduling of hardware resources, and the computing resource pool shares data computing capability, that is, the current edge computing subsystem can call hardware of other edge computing subsystems to perform data computing, so as to meet the functional requirements of the current edge computing subsystem, and further, sharing of data computing capability can be achieved. In this embodiment, the cluster of the multiple fan edge computing subsystems is designed and cooperatively scheduled based on a big data frame, so that distributed computing of mass data in the multi-edge computing device cluster can be realized, and sharing of data and computing power among the multi-edge computing subsystems is completed.
Taking a single edge computing subsystem as an example, the edge computing subsystem is arranged on the corresponding fan, and the edge computing subsystem comprises an edge level communication module, an edge level data processing module and an edge level algorithm module which are in communication connection with each other.
Edge level communication module
The edge-level communication module is communicated with a corresponding main control device in real time and acquires all original data of the main control device, wherein the original data includes all IO (input/output) real-time high-frequency data (10 ms level) of the main control device, quantitative parameters of the main control device and data of all matched devices (a main control accessory device, a variable pitch device, a converter device and the like) acquired by the main control device through communication; in practical application, the edge-level communication module can adapt to a mainstream industrial control communication protocol and a system private communication protocol so as to meet the requirement of data transmission and communication.
The edge-level communication module is in real-time communication with edge-level communication modules of other edge computing subsystems and performs data interaction, and is used for acquiring all data of the other edge computing subsystems, mainly preprocessing data of the other edge computing subsystems.
The edge-level communication module is communicated with the wind field-level computing subsystem in real time and performs data interaction, original data of a main control device in a wind machine end corresponding to the current wind field-level computing subsystem and preprocessed data output by the wind field-level computing subsystem can be transmitted to the wind field-level computing subsystem, and data support is provided for operation of an algorithm model in the wind field-level computing subsystem.
② edge-level data processing module
The edge-level data processing module is used for preprocessing the original data (multidimensional data) acquired by the edge-level communication module according to various algorithm model requirements to obtain preprocessed data, wherein the preprocessing comprises data brushing, data cleaning, data integration, data transformation, data reduction, data feature extraction and the like, and the data quality is improved and the data transmission pressure is reduced through preprocessing. And inputting the preprocessed data into the edge-level algorithm module or sending the preprocessed data to the wind field-level computing subsystem through the edge-level communication module.
③ edge level algorithm module
The edge level algorithm module is integrated with an edge algorithm model library, and selects original data and/or preprocessed data corresponding to the fan and other fans of the full wind field as input according to the requirements of the current algorithm model, and obtains corresponding edge level algorithm results after the operation of the algorithm model. Specifically, taking a certain wind turbine end as an example, multiple algorithm models exist in an edge algorithm model library of an edge level algorithm module of an edge computing subsystem in the wind turbine end, some algorithm models may only need original data, some algorithm models may only need preprocessed data, and some algorithm models may need original data and preprocessed data at the same time, and after the corresponding data are obtained by the algorithm models, corresponding algorithm results are obtained through algorithm model operation.
In this embodiment, the library of edge algorithm models includes, but is not limited to, the following algorithm models to be run on the edge: the method comprises an algorithm model with high real-time performance, a virtual sensor fitting algorithm model, a mutual learning algorithm model among fans and a quantitative parameter self-optimizing algorithm model.
And the edge-level algorithm result is sent to the corresponding main control device by the edge-level communication module, and the operation of the fan is controlled by the main control device.
Based on the above, the fan edge calculation subsystem performs real-time high-frequency acquisition, synchronization and preprocessing on all operation parameters of the main control device, sends key original data and preprocessed data to the wind field level calculation subsystem, and meanwhile, the edge calculation subsystem deploys an edge level algorithm model library, and edge level algorithm model calculation results can be sent to the main control device to participate in controlling or adjusting the operation parameters.
For wind field level computing subsystem part
The wind field level computing subsystem is deployed in a wind field control center and comprises a wind field level communication module, a wind field level data storage module, a wind field level algorithm module and a man-machine interaction module which are in communication connection with one another, and the wind field level computing subsystem serves as important components of a wind field level computing subsystem part.
Wind field level communication module
The wind field level communication module is used for communicating with each main control device and the corresponding edge calculation subsystem in the full wind field in real time and acquiring data, and mainly comprises communication frequency data (1 s level) of the main control devices and preprocessing data of the edge calculation subsystem. In practical application, the wind field level communication module can be adapted to a mainstream industrial control communication protocol and a system private communication protocol.
Wind field level algorithm module
The wind field level algorithm module is integrated with a wind field level algorithm model library, and the corresponding wind field level algorithm result or the cluster cooperative control instruction is obtained after the operation of the algorithm model by inputting the original data and/or the preprocessed data of the single fan or the whole fan into the corresponding algorithm model. In this embodiment, a wind farm level algorithmic model library, which includes but is not limited to the following algorithmic models operating at wind farm level: the system comprises a single-machine virtual sensor fitting algorithm model, a cluster shared sensor fitting algorithm model, a performance deviation identification algorithm model, a quantitative parameter self-optimizing algorithm model, a cluster benchmarking algorithm model and a cluster coordination control algorithm model.
The wind field level algorithm result or the cluster cooperative control instruction is sent to the main control device by the edge communication module, and the main control device is used for controlling the operation and adjusting the parameters of the fans so as to realize the intelligent control of each fan in the full wind field.
Wind field level data storage module
The wind field level data storage module is used for acquiring high-frequency original data (acquired by a main control device corresponding to the edge computing subsystem), preprocessed data (acquired after preprocessing by the edge computing subsystem), an edge level algorithm result (acquired by computing an edge algorithm model of the edge computing subsystem) and a wind field level algorithm result operated by the wind field level algorithm module from each edge computing subsystem in the full wind field.
Man-machine interaction module
The man-machine interaction module is used for managing each fan edge computing subsystem and each wind field level computing subsystem of the full wind field. In practical application, the method comprises the steps of receiving modification, deletion and addition instructions of a user through a human-computer interaction module, and modifying, deleting and adding algorithms in an algorithm model library of a fan edge computing subsystem and a wind field level computing subsystem according to the instructions. The method also comprises the steps of receiving a configuration instruction of a user through a human-computer interaction module, and completing automatic configuration of data acquisition and data processing of the fan edge computing subsystem, wind field level data storage configuration, and operation configuration of each algorithm model in the fan edge computing subsystem and the wind field level computing subsystem according to the instruction.
And the human-computer interaction module is used for monitoring the running states of each fan edge computing subsystem and each wind field level computing subsystem in the full wind field and performing human-computer interaction on the running states.
The man-machine interaction module is used for calling query data (including original data, preprocessed data, algorithm result data and the like) from the wind field level computing subsystem and displaying the data, and the displaying form includes but is not limited to: tables, graphs, etc. show the data. For example: and displaying the unit performance parameters and the benchmarking results calculated by the unit benchmarking class algorithm model.
The human-computer interaction module is used for operating the coordination control of all fans in the whole wind field, and a user carries out manual operation on a human-computer interaction interface of the human-computer interaction module.
The wind field level calculation subsystem can acquire data sent by the fan edge calculation subsystem and the main control device in real time, a wind field level algorithm model library is deployed, and the calculation result of the wind field level algorithm model can be sent to the main control device to participate in controlling or adjusting operation parameters; the edge computing subsystem and the wind field level computing subsystem are deployed in an algorithm model, and the calculation of virtual sensing data of the fan and the calculation of an operation parameter adjustment target are completed based on data of the main control device and preprocessed data of the edge computing subsystem;
the wind field level algorithm model deployed by the wind field level computing subsystem can also be realized, cluster sharing sensing data calculation and whole-field fan operation state adjustment are completed based on main control device data of a fan in a whole wind field and preprocessing data of the edge computing subsystem, high-real-time algorithm model operation results can be realized at the edge end of the fan to participate in fan closed-loop control, and non-high-real-time performance and fan control closed-loop based on cluster big data intelligent algorithm model operation results are realized at the wind field level.
Example 2
The embodiment 1 specifically provides an intelligent control system for a wind generating set, and on the basis of the embodiment 1, the embodiment further provides an intelligent control method for the wind generating set, and the method includes:
acquiring all original data of all fans in the whole wind farm corresponding to the main control device, and acquiring preprocessed data of all edge computing subsystems in the whole wind farm according to the requirements of the algorithm model;
and each edge computing subsystem carries out data preprocessing and fusion according to the original data and the preprocessing data required by the edge level algorithm model and the wind field level algorithm model so as to obtain preprocessing and fusion data. As shown in fig. 2, taking an edge computing subsystem as an example, according to data required by various edge algorithm models in the current edge computing subsystem, the edge computing subsystem acquires all original data of the current main control device from the corresponding main control device and acquires all data required by the edge computing subsystem from all preprocessed data acquired from other edge computing subsystems, and performs preprocessing and fusion on the data through the edge computing subsystem to obtain preprocessed and fused data.
From the wind farm level section: the method comprises the steps of inputting original data of all fans corresponding to a main control device into a wind field level computing subsystem (centralized control end/wind field centralized control end), sending preprocessed and fused data into the wind field level computing subsystem, inputting the preprocessed and fused data into a wind field level algorithm model in the wind field level computing subsystem as required, outputting wind field level algorithm results or machine group cooperative control instructions through the wind field level algorithm model, feeding the wind field level algorithm results or machine group cooperative control instructions back to the main control device, and controlling the operation of the fans through the main control device.
From the edge level part: inputting required original data, preprocessing and fusion data into an edge-level algorithm model in an edge computing subsystem (edge end), outputting an edge-level algorithm result through the edge-level algorithm model and feeding back the edge-level algorithm result to a main control device, and controlling the operation of the fan by the main control device.
By adopting the intelligent control method of the wind generating set, the operational capability of each fan in the full wind field can be efficiently and cooperatively scheduled, and the wind field level computing subsystem is used as a rear shield while the edge computing capability of the fan is shared, so that a big data solution in the wind field is formed. The wind power field data do not need to be sent out to the private cloud service or the internet cloud service of the wind power field group through the network, the real-time performance of the operation result of the fan algorithm model, the flexibility and the reliability of the deployment of the algorithm model can be improved on the premise of ensuring the data safety of the wind power field, the effective operation hours of the fan is increased, and the fan is adjusted to the optimal power generation state.
It should be noted that any process or method descriptions in flow charts or otherwise described herein may be understood as representing modules, segments, or portions of code which include one or more executable instructions for implementing specific logical functions or steps of the process, and that the scope of the preferred embodiments of the present application includes additional implementations in which functions may be executed out of order from that shown or discussed, including substantially concurrently or in reverse order, depending on the functionality involved, as would be understood by those reasonably skilled in the art of the embodiments of the present application.
It should be understood that portions of the present application may be implemented in hardware, software, firmware, or a combination thereof. In the above embodiments, the various steps or methods may be implemented in software or firmware stored in memory and executed by a suitable instruction execution system. For example, if implemented in hardware, as in another embodiment, any one or combination of the following techniques, which are known in the art, may be used: a discrete logic circuit having a logic gate circuit for implementing a logic function on a data signal, an application specific integrated circuit having an appropriate combinational logic gate circuit, a Programmable Gate Array (PGA), a Field Programmable Gate Array (FPGA), or the like.
It will be understood by those skilled in the art that all or part of the steps carried by the method for implementing the above embodiments may be implemented by hardware related to instructions of a program, which may be stored in a computer readable storage medium, and when the program is executed, the program includes one or a combination of the steps of the method embodiments.
In addition, functional units in the embodiments of the present application may be integrated into one processing module, or each unit may exist alone physically, or two or more units are integrated into one module. The integrated module can be realized in a hardware mode, and can also be realized in a software functional module mode. The integrated module, if implemented in the form of a software functional module and sold or used as a stand-alone product, may also be stored in a computer readable storage medium.
The storage medium mentioned above may be a read-only memory, a magnetic or optical disk, etc.
Although embodiments of the present application have been shown and described above, it is understood that the above embodiments are exemplary and should not be construed as limiting the present application, and that variations, modifications, substitutions and alterations may be made to the above embodiments by those of ordinary skill in the art within the scope of the present application.
Claims (12)
1. An intelligent control system of a wind generating set is characterized by comprising a plurality of edge computing subsystems and at least one wind field level computing subsystem which are mutually communicated and connected, wherein each edge computing subsystem is respectively communicated and connected with at least one main control device;
and each main control device is communicated with each edge computing subsystem and each wind field level computing subsystem to exchange data, and the arithmetic model operation result of each edge computing subsystem and each wind field level computing subsystem is fed back to each main control device so as to intelligently control and adjust the running state of the fan corresponding to each main control device.
2. The intelligent control system of claim 1, wherein the master control device is arranged on the corresponding fan, and the data of the control device and the sensor matched with the fan is collected through the master control device.
3. The intelligent control system of claim 1, wherein a computing resource pool is constructed among the edge computing subsystems by unified scheduling of hardware resources, and the computing resource pool shares data computing power.
4. The intelligent control system of the wind generating set according to claim 1, wherein the edge computing subsystems are arranged on the corresponding wind turbines, and each edge computing subsystem comprises an edge-level communication module, an edge-level data processing module and an edge-level algorithm module which are in communication connection with each other;
the wind field level computing subsystem is deployed in a wind field control center and comprises a wind field level communication module, a wind field level data storage module, a wind field level algorithm module and a man-machine interaction module which are in communication connection with one another.
5. The intelligent control system of claim 4, wherein the edge-level communication module communicates with the corresponding master control device in real time and obtains all raw data of the master control device;
the edge-level communication module is communicated with edge-level communication modules of other edge computing subsystems in real time and performs data interaction to acquire all data of the other edge computing subsystems;
and the edge-level communication module is in real-time communication with the wind field-level calculation subsystem and performs data interaction.
6. The intelligent control system of claim 4, wherein the edge-level data processing module is configured to preprocess the raw data obtained by the edge-level communication module to obtain preprocessed data, and the preprocessed data is input to the edge-level algorithm module or sent to the wind farm-level computation subsystem through the edge-level communication module.
7. The intelligent control system of the wind generating set according to claim 6, wherein the edge-level algorithm module is integrated with an edge algorithm model library, and the edge-level algorithm module selects original data and/or preprocessed data corresponding to the fan and other fans of the full wind field as input according to the requirements of the current algorithm model, and obtains a corresponding edge-level algorithm result after the operation of the algorithm model;
and the edge-level algorithm result is sent to the corresponding main control device by the edge-level communication module, and the operation of the fan is controlled by the main control device.
8. The intelligent control system of claim 4, wherein the wind farm level communication module is configured to communicate with each master control device and the edge computing subsystem in the full wind farm in real time and obtain data.
9. The intelligent control system of the wind generating set according to claim 6, wherein the wind farm level algorithm module is integrated with a wind farm level algorithm model library, and the corresponding wind farm level algorithm result or the cluster cooperative control instruction is obtained after the algorithm model is operated by inputting the original data and/or the preprocessed data of the single fan or the whole fan into the corresponding algorithm model;
and the wind field level algorithm result or the cluster cooperative control instruction is sent to the main control device by the edge communication module, and the main control device is used for controlling the operation and adjusting the parameters of the fan.
10. The intelligent control system of claim 7, wherein the wind farm level data storage module is configured to store raw data of each master control device in the full wind farm, preprocessed data of each edge computing subsystem, edge level algorithm results, and wind farm level algorithm results executed by the wind farm level algorithm module.
11. The intelligent control system of a wind generating set according to claim 4, wherein the human-computer interaction module is used for managing each fan edge computing subsystem and a wind farm level computing subsystem of a full wind farm;
the human-computer interaction module is used for monitoring the running states of each fan edge computing subsystem and each wind field level computing subsystem in the full wind field;
the man-machine interaction module is used for calling query data from the wind field level computing subsystem and displaying the query data;
and the human-computer interaction module is used for operating the coordination control of each fan in the whole wind field.
12. An intelligent control method for a wind generating set, which is applied to the intelligent control system for the wind generating set according to any one of claims 1 to 11, and comprises the following steps:
acquiring all original data of all fans in the whole wind farm corresponding to the main control device, and acquiring preprocessed data of all edge computing subsystems in the whole wind farm according to the requirements of the algorithm model;
each edge computing subsystem carries out data preprocessing and fusion according to original data and preprocessing data required by the edge-level algorithm model and the wind field-level algorithm model so as to obtain preprocessing and fusion data;
the method comprises the steps that original data, preprocessing and fusion data are sent to a wind field level computing subsystem and are input into a wind field level algorithm model in the wind field level computing subsystem as required, wind field level algorithm results or a machine group cooperative control instruction are output through the wind field level algorithm model and fed back to a main control device, and the main control device controls the operation of a fan;
and inputting required original data, preprocessing and fusion data into an edge-level algorithm model in an edge calculation subsystem, outputting an edge-level algorithm result through the edge-level algorithm model and feeding back the edge-level algorithm result to a main control device, and controlling the operation of the fan by the main control device.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110905410.0A CN113357083A (en) | 2021-08-09 | 2021-08-09 | Intelligent control system and method for wind generating set |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110905410.0A CN113357083A (en) | 2021-08-09 | 2021-08-09 | Intelligent control system and method for wind generating set |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN113357083A true CN113357083A (en) | 2021-09-07 |
Family
ID=77540562
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110905410.0A Pending CN113357083A (en) | 2021-08-09 | 2021-08-09 | Intelligent control system and method for wind generating set |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113357083A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113982854A (en) * | 2021-10-15 | 2022-01-28 | 上海电气风电集团股份有限公司 | Wind field system |
| CN114371671A (en) * | 2021-12-14 | 2022-04-19 | 东方电气风电股份有限公司 | Decentralized control system for wind farms |
Citations (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2011100744A2 (en) * | 2010-02-15 | 2011-08-18 | Zte Corporation | Method and system for implementing integrated voice over internet protocol in a cloud-based network |
| CN202914242U (en) * | 2012-09-14 | 2013-05-01 | 国电联合动力技术有限公司 | Real-time cluster control system for offshore wind plant |
| KR20180010745A (en) * | 2016-07-22 | 2018-01-31 | 전자부품연구원 | Wave-Offshore Wind Hybrid Power Generation System and Method using MEC |
| CN109274745A (en) * | 2018-09-28 | 2019-01-25 | 北京北斗方圆电子科技有限公司 | A kind of Internet of things system and method for fringe node optimization calculating |
| CN109815733A (en) * | 2019-01-09 | 2019-05-28 | 网宿科技股份有限公司 | A kind of intelligent management and system based on edge calculations |
| CN110701002A (en) * | 2019-10-18 | 2020-01-17 | 东方电气风电有限公司 | Virtual sensing implementation system for large wind generating set |
| CN111379664A (en) * | 2020-02-14 | 2020-07-07 | 深圳奇迹智慧网络有限公司 | Wind power generation equipment monitoring method and device, computer equipment and storage medium |
| CN111520282A (en) * | 2020-05-21 | 2020-08-11 | 明阳智慧能源集团股份公司 | Wind turbine measurement and control system and measurement and control method based on edge calculation and deep learning |
| CN111724020A (en) * | 2019-03-22 | 2020-09-29 | 国家能源投资集团有限责任公司 | Fan state monitoring data processing method, device and system |
| US10873516B2 (en) * | 2018-05-25 | 2020-12-22 | Comcast Cable Communications, Llc | Content delivery network server testing |
| CN112398946A (en) * | 2020-11-17 | 2021-02-23 | 国网天津市电力公司 | Source network load storage scheduling control system and configuration method |
| CN113112086A (en) * | 2021-04-22 | 2021-07-13 | 北京邮电大学 | Intelligent production system based on edge calculation and identification analysis |
-
2021
- 2021-08-09 CN CN202110905410.0A patent/CN113357083A/en active Pending
Patent Citations (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2011100744A2 (en) * | 2010-02-15 | 2011-08-18 | Zte Corporation | Method and system for implementing integrated voice over internet protocol in a cloud-based network |
| CN202914242U (en) * | 2012-09-14 | 2013-05-01 | 国电联合动力技术有限公司 | Real-time cluster control system for offshore wind plant |
| KR20180010745A (en) * | 2016-07-22 | 2018-01-31 | 전자부품연구원 | Wave-Offshore Wind Hybrid Power Generation System and Method using MEC |
| US10873516B2 (en) * | 2018-05-25 | 2020-12-22 | Comcast Cable Communications, Llc | Content delivery network server testing |
| CN109274745A (en) * | 2018-09-28 | 2019-01-25 | 北京北斗方圆电子科技有限公司 | A kind of Internet of things system and method for fringe node optimization calculating |
| CN109815733A (en) * | 2019-01-09 | 2019-05-28 | 网宿科技股份有限公司 | A kind of intelligent management and system based on edge calculations |
| CN111724020A (en) * | 2019-03-22 | 2020-09-29 | 国家能源投资集团有限责任公司 | Fan state monitoring data processing method, device and system |
| CN110701002A (en) * | 2019-10-18 | 2020-01-17 | 东方电气风电有限公司 | Virtual sensing implementation system for large wind generating set |
| CN111379664A (en) * | 2020-02-14 | 2020-07-07 | 深圳奇迹智慧网络有限公司 | Wind power generation equipment monitoring method and device, computer equipment and storage medium |
| CN111520282A (en) * | 2020-05-21 | 2020-08-11 | 明阳智慧能源集团股份公司 | Wind turbine measurement and control system and measurement and control method based on edge calculation and deep learning |
| CN112398946A (en) * | 2020-11-17 | 2021-02-23 | 国网天津市电力公司 | Source network load storage scheduling control system and configuration method |
| CN113112086A (en) * | 2021-04-22 | 2021-07-13 | 北京邮电大学 | Intelligent production system based on edge calculation and identification analysis |
Non-Patent Citations (1)
| Title |
|---|
| 边晓光 等: "智慧风电5G工业终端边缘计算算法设计和调试", 《东方电气评论》 * |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113982854A (en) * | 2021-10-15 | 2022-01-28 | 上海电气风电集团股份有限公司 | Wind field system |
| CN113982854B (en) * | 2021-10-15 | 2023-10-27 | 上海电气风电集团股份有限公司 | Wind farm system |
| CN114371671A (en) * | 2021-12-14 | 2022-04-19 | 东方电气风电股份有限公司 | Decentralized control system for wind farms |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107330056B (en) | Wind power plant SCADA system based on big data cloud computing platform and operation method thereof | |
| CN113357083A (en) | Intelligent control system and method for wind generating set | |
| CN111245026B (en) | Virtual power plant regulation and control method, system and equipment | |
| CN112909992B (en) | Distributed power supply cluster grid-connected regulation and control system and method based on cloud management side end | |
| CN109151072A (en) | A kind of edge calculations system based on mist node | |
| CN104992009B (en) | Active distribution network distributed voltage control method based on multi-agent system | |
| CN103703645A (en) | Control system for photovoltaic power plant | |
| CN106230681A (en) | A kind of communication for Complex Power electronics distributed AC servo system and Tong Bu system | |
| CN115314343A (en) | Source-load-storage resource aggregation control gateway device and load and output prediction method | |
| CN105240210A (en) | Wind generation set condition monitoring system based on voice recognition | |
| CN203552029U (en) | Microgrid control system based on distributed controllers | |
| CN106484499A (en) | A kind of cloud management platform towards new forms of energy data center extending transversely | |
| WO2023050930A1 (en) | Auxiliary control method and system for wind turbine generator set, and wind turbine generator set | |
| CN110703679A (en) | Industrial controller of wind generating set | |
| CN115514097A (en) | Village domain CPS regulation and control system and method based on distributed photovoltaic supply and demand interactive coordination control | |
| CN116050754A (en) | Digital twinning-based virtual power plant collaborative management and control method and system | |
| CN111198548B (en) | Power system and information system combined scheduling system based on intelligent node overlay network | |
| CN111711228B (en) | Enhanced hydropower station AGC automatic power generation control method | |
| CN104319819B (en) | The grid-connected active tuning controller of embedded draught fan group | |
| CN203617787U (en) | Power scheduling system | |
| CN106933116A (en) | Micro-capacitance sensor emulation debugging method with MATLB interfaces | |
| CN106022543A (en) | Wind power and electric quantity diagnosing system | |
| Song et al. | Research on multi-parameter data monitoring system of distribution station based on edge computing | |
| CN111404207A (en) | Power distribution network access control method and control system for generator set | |
| CN115954900B (en) | Intelligent control system for primary frequency modulation of power grid |
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 | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20210907 |
|
| RJ01 | Rejection of invention patent application after publication |