Air filtering system of wind driven generator and control method
By obtaining and optimizing the power generation of the fan, air index and wind speed, and building an operating model of the air filtration system, the energy waste and unstable output power when the control of the air filtration system of the wind turbine is solved, and a reasonable filtration system is enabled and Save energy.
Patent Information
- Application Number
- CN202410975113.7
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-07-19
- Publication Date
- 2024-11-12
AI Technical Summary
The air filtration system of existing wind turbines has problems of waste of energy and unstable output power when the control is turned on, and it is impossible to reasonably adjust the opening and closing of the filter system according to the operating status of the fan.
By obtaining the fan power generation power, the generator internal air index and current wind speed as constraint parameters, the parameter optimization is carried out and the operation model of the air filtration system is constructed. The opening and closing of the air filtration system is controlled according to the model results, and the air exchange is compared when it is turned on. Rate to send maintenance signals to ensure the system is operated under reasonable conditions.
The air filtration system is enabled to turn on under reasonable conditions, avoid turning on the filtration system when the fan output power is insufficient, save energy, and avoid energy waste caused by poor filtration effect.
Smart Images

Figure CN118938658A_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the technical field of fan control, and in particular to an air filtering system and a control method for a wind turbine generator. Background Art
[0002] In recent years, with the adjustment of national energy policies, the scale of wind power generation in my country has increased year by year, and has occupied an important position in the overall energy layout. Among them, wind power generation is a renewable energy technology that converts wind energy into electrical energy. Wind energy is converted into mechanical energy through wind turbines, and then converted into electrical energy through generators. Wind power generation has the advantages of environmental protection, renewability, and stability, so it has been widely used around the world. Wind power generation is highly environmentally friendly, does not produce greenhouse gases such as carbon dioxide, and has little pollution to the environment. At the same time, wind power resources are widely distributed and can be developed and utilized worldwide. However, wind power generation also has some problems, such as the impact on birds and the impact on the landscape, which require reasonable planning and management during construction and use.
[0003] During the operation of the wind turbine, the blades of the wind turbine will inhale a large amount of air, so an air filtration system is needed to prevent dust and impurities from entering the blades, affecting their operating efficiency and life. At the same time, the generator also needs an air filtration system to keep it clean and prevent dust and impurities from entering, causing malfunctions and damage.
[0004] However, the current filtration system is generally always on or controlled to be turned on or off according to the air pollution index inside the generator. However, always on may cause energy waste, and controlling the on and off according to the pollution index may affect the power generation at the time, resulting in unstable output power. Therefore, a more reasonable method of controlling the on and off of the filtration system is urgently needed. Summary of the invention
[0005] The purpose of the present invention is to provide an air filtration system and a control method for a wind turbine generator to solve the above-mentioned problems in the prior art.
[0006] The embodiments of the present invention are implemented by the following technical solutions:
[0007] In a first aspect, the present invention provides a method for controlling an air filtration system of a wind turbine, comprising:
[0008] Obtain constraint parameters, where the constraint parameters include wind turbine power generation, generator internal air index, and current wind speed;
[0009] And optimize the constraint parameters to obtain more accurate constraint parameters;
[0010] The operation model of the air filtration system is constructed through constraint parameters, and the opening and closing of the air filtration system is controlled according to the results of the operation model;
[0011] Determine whether the air filtration system is turned on. If the air filtration system is turned on, obtain the ventilation rate of the air filtration system and compare it with the rated ventilation rate of the current power of the air filtration system;
[0012] It is determined whether the ventilation rate of the air filtration system obtained in real time is consistent with the rated ventilation rate of the current power. If not, a maintenance signal is sent to the remote end.
[0013] In one embodiment of the present invention, the optimizing the constraint parameters includes:
[0014] Obtain the wind turbine power generation, the air index inside the generator, and the current wind speed, build a sample data set, set the type and threshold of the required optimization parameters, and set the objective function;
[0015] Set the maximum number of iterations and the number of starting sample points for optimization;
[0016] Optimize the wind turbine power generation, generator internal air index and current wind speed parameters in the data set;
[0017] The best feasible solution obtained after the optimization is completed is used as the optimal parameter setting.
[0018] In one embodiment of the present invention, the optimizing of the wind turbine power generation, the generator internal air index and the current wind speed parameters of the data set includes:
[0019] The DBSCAN algorithm is used to divide the sample data set features into data cluster categories and remove some abnormal data clusters;
[0020] A benchmark index of constraint parameters is established, and the quartile algorithm is used to identify a small number of abnormal data with accumulated abnormalities and outlier data with unclear characteristics, and the abnormal data are eliminated again.
[0021] In one embodiment of the present invention, dividing the sample data set features into data cluster categories by using the DBSCAN algorithm includes:
[0022] Predetermine the parameter domain radius and the minimum number of data point sets;
[0023] Starting from a point in the sample data that has never been visited, if the number of other data points distributed within this neighborhood radius is greater than or equal to the number of sets, it is marked as normal data; if it is less than the number of sets, it is marked as abnormal data;
[0024] Return to the previous step and substitute new data points for calculation until all data are calculated;
[0025] Remove abnormal data sets and retain the data.
[0026] In one embodiment of the present invention, the use of the quartile algorithm to identify a small number of abnormal data with accumulated abnormalities and abnormal points with unclear outlier data characteristics includes:
[0027] In the sample data set, the number of samples in the data set is counted as n, and they are arranged from bottom to top in terms of size;
[0028] When (n+1) / 3 is divisible, it is as follows:
[0029]
[0030] Wherein, Q1 is the data value of the 0.25(n+1)th bit, Q2 is the data value of the 0.5(n+1)th bit, and Q3 is the data value of the 0.75(n+1)th bit;
[0031] When (n+1) / 3 is not divisible, and n=3k, (k=1, 2, 3, ...), the formula is as follows:
[0032]
[0033] Where, Q1 is the sum of 0.75 times the value of the 0.25nth data and 0.25 times the value of the (0.25n+1)th data; Q2 is the average value of the 0.5nth data and the (0.5n+1)th data; Q3 is the sum of 0.25 times the value of the 0.75nth data and 0.75 times the value of the (0.75n+1)th data:
[0034] When (n+1) / 3 is not divisible, and n=3k+1, (k=1, 2, 3, ...);
[0035]
[0036] Wherein, Q1 is the sum of 0.25 times the value of the (0.25n-0.5)th data and 0.25 times the value of the (0.25n+0.5)th data; Q2 is the average value of the 0.5nth data and the (0.5n+1)th data; Q3 is the sum of 0.75 times the value of the (0.75n+0.5)th data and 0.25 times the value of the (0.75n+1.5)th data;
[0037] Eliminate outliers and set the upper edge limit, as shown in the formula;
[0038] L low =Q1-1.5(Q3-Q1)
[0039] Set the upper edge limit, as shown in the formula;
[0040] L high =Q3+1.5(Q3-Q1)
[0041] Set the data position to L lo w~L high Data outside the range are considered abnormal data and are removed, and the remaining data are normal data.
[0042] In one embodiment of the present invention, constructing an operation model of the air filtration system by using constraint parameters includes:
[0043] Obtain the optimized wind turbine power generation, generator internal air index and current wind speed value, and set the wind turbine power generation threshold, air index threshold and wind speed threshold;
[0044] Build a computational model:
[0045]
[0046] In the formula, F is the judgment index, W1 is the current wind turbine power generation, W2 is the wind turbine power generation threshold, T1 is the current generator internal air index, T2 is the generator internal air index threshold, V1 is the current wind speed, and V2 is the wind speed threshold;
[0047] If F is a positive number, the air filtration system is turned on, otherwise it is turned off.
[0048] In a second aspect, the present invention provides an air filtration system for a wind turbine generator, comprising:
[0049] A parameter acquisition module is configured to acquire constraint parameters, wherein the constraint parameters include wind turbine power generation, generator internal air index and current wind speed; and optimize the constraint parameters to obtain more accurate constraint parameters;
[0050] A model building module is configured to build an operation model of the air filtration system through constraint parameters, and control the opening and closing of the air filtration system according to the result of the operation model;
[0051] The control module is configured to determine whether the air filtration system is turned on. If the air filtration system is turned on, the ventilation rate of the air filtration system is obtained and compared with the ventilation rate rated by the current power of the air filtration system; determine whether the ventilation rate of the air filtration system obtained in real time is consistent with the ventilation rate rated by the current power, and if they are inconsistent, send a maintenance signal to the remote end;
[0052] A main control module, the main control module is used to connect with the parameter acquisition module, the model building module and the control module, and is used for the above-mentioned wind turbine air filtration system control method.
[0053] In one embodiment of the present invention, a general selection module is also included, which is used to send the maintenance signal to a remote end.
[0054] In a third aspect, the present invention further provides a computer-readable storage medium, wherein a computer program is stored on the computer-readable storage medium, and when the computer program is executed by a processor, the above-mentioned method for controlling an air filtration system of a wind turbine generator is implemented.
[0055] The technical solution of the embodiment of the present invention has at least the following advantages and beneficial effects:
[0056] The above method of the present invention mainly includes obtaining constraint parameters, which include the power generated by the fan, the air index inside the generator and the current wind speed; optimizing the constraint parameters to obtain more accurate constraint parameters; constructing an operation model of the air filtration system through the constraint parameters, and controlling the opening and closing of the air filtration system according to the results of the operation model. Through the above method, a variety of parameters are integrated to control the opening or closing of the air filtration system, so that the air filtration system is turned on at a more reasonable time, and the air filtration system is avoided as much as possible when the fan output power is insufficient. Turning on the air filtration system also avoids the air filtration system being always on to save energy.
[0057] Secondly, it also includes judging whether the air filtration system is turned on. If the air filtration system is turned on, the ventilation rate of the air filtration system is obtained and compared with the ventilation rate rated by the current power of the air filtration system; judging whether the ventilation rate of the air filtration system obtained in real time is consistent with the ventilation rate rated by the current power, if they are inconsistent, a maintenance signal is sent to the remote end. This can avoid the problem of poor filtration effect and energy waste due to blockage of the filter when the air filtration system is turned on. BRIEF DESCRIPTION OF THE DRAWINGS
[0058] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings required for use in the embodiments are briefly introduced below. It should be understood that the following drawings only show certain embodiments of the present invention and therefore should not be regarded as limiting the scope. For ordinary technicians in this field, other related drawings can be obtained based on these drawings without creative work.
[0059] Figure 1 It is a control flow chart of the present invention. DETAILED DESCRIPTION
[0060] In order to make the purpose, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Generally, the components of the embodiments of the present invention described and shown in the drawings here can be arranged and designed in various different configurations.
[0061] In addition, the connection, coupling or communication in the present application may be a direct connection, coupling or communication between related objects, or an indirect connection, coupling or communication through other devices. In addition, the connection, coupling or communication between objects may be electrical or other similar forms, which are not limited in the present application. Independently described modules or submodules may be physically separated or not: they may be implemented by software or hardware, and some modules or submodules may be implemented by software, and the processor calls the software to implement the functions of these modules or submodules, and other parts of the templates or submodules may be implemented by hardware, such as by hardware circuits. In addition, some or all of the modules may be selected according to actual needs to achieve the purpose of the present application.
[0062] Please refer to Figure 1 ,The present invention provides a method for controlling an air filtration system of a wind turbine generator, comprising:
[0063] S101: Obtain constraint parameters, where the constraint parameters include wind turbine power generation, generator internal air index, and current wind speed;
[0064] The power generation of the fan is obtained by the rotation of the fan blades. When the power output requirements of the fan are high and the load is high, it is obviously not suitable to start the air filtration system to filter the air.
[0065] Secondly, the air index inside the generator is an important parameter indicator, which can directly affect whether the air filtration system is turned on. The current wind speed can determine the size of the power generation at this time. Increasing the wind speed will facilitate subsequent more accurate control of the air filtration system.
[0066] S102: Optimizing the constraint parameters to obtain more accurate constraint parameters;
[0067] In the process of obtaining parameters, affected by external environmental interference, wind turbine operation failures, wind power curtailment and other factors, there are a lot of abnormal data in the wind farm data acquisition and monitoring control system. If these data are directly used without processing, poor data quality will cause the fitted wind turbine actual power curve to be distorted, affecting the subsequent evaluation results of the air filtration system switch. Therefore, the next step requires the optimization of various constraint parameters, and the specific process is described below.
[0068] S103: constructing an operation model of the air filtration system through constraint parameters, and controlling the opening and closing of the air filtration system according to the result of the operation model;
[0069] In this embodiment, the opening and closing of the air filtration system can be determined based on the final result of the running model.
[0070] S104: determining whether the air filtration system is turned on; if the air filtration system is turned on, obtaining a ventilation rate of the air filtration system and comparing it with a rated ventilation rate of the current power of the air filtration system;
[0071] S105: Determine whether the ventilation rate of the air filtration system obtained in real time is consistent with the rated ventilation rate of the current power. If not, send a maintenance signal to the remote end.
[0072] This can avoid the problem of poor filtering effect and energy waste due to clogging of the filter when the air filtration system is turned on.
[0073] Through the above method, a variety of parameters are integrated to control the opening or closing of the air filtration system, so that the air filtration system is turned on at a more reasonable time, and the air filtration system is avoided as much as possible when the fan output power is insufficient. Turning on the air filtration system also saves energy by avoiding the air filtration system being kept on all the time.
[0074] In one embodiment of the present invention, the optimizing the constraint parameters includes:
[0075] Obtain the wind turbine power generation, generator internal air index and current wind speed, construct a sample data set, set the type and threshold of the required optimization parameters, and set the objective function; set the maximum number of iterations and the starting number of sample points for optimization; optimize the wind turbine power generation, generator internal air index and current wind speed parameters of the data set; and use the best feasible solution obtained after the optimization as the optimal parameter setting.
[0076] Specifically, the optimization of the wind turbine power generation, generator internal air index and current wind speed parameters of the data set includes: dividing the sample data set characteristics into data cluster categories through the DBSCAN algorithm, and eliminating some abnormal data clusters; establishing a benchmark index for constraint parameters, using the quartile algorithm to identify a small number of abnormal points with unclear characteristics of accumulated abnormal data and outlier data, and eliminating the abnormal data again.
[0077] In this embodiment, the wind turbine power generation is used as an example for illustration:
[0078] For example, the sampling interval is 5 minutes, and a total of 168 sets of data are collected in one day. The kernel function neighborhood radius and the minimum number of data point sets can be determined by the k-distance method. The parameter optimization results are substituted into the standard DBSCAN method. After testing, the kernel function Minpts = 19, Eps = 0.006 has the best effect on abnormal data identification.
[0079] Other data, such as current wind speed or air index, can be eliminated through this method to eliminate abnormal data.
[0080] In one embodiment of the present invention, dividing the sample data set features into data cluster categories by using the DBSCAN algorithm includes:
[0081] Predetermine the parameter domain radius and the minimum number of data point sets; start with a point in the sample data that has never been visited. If the number of other data points distributed within this neighborhood radius is greater than or equal to the number of sets, mark it as normal data; if it is less than the number of sets, mark it as abnormal data; return to the previous step and substitute new data points for calculation until all data are calculated; remove abnormal data sets and retain the data.
[0082] In one embodiment of the present invention, the use of the quartile algorithm to identify a small number of abnormal data with accumulated abnormalities and abnormal points with unclear outlier data characteristics includes:
[0083] In the sample data set, the number of statistical sample data sets is n, and they are arranged from bottom to top in order of size. The sample data set can be any one of the wind turbine power generation, the generator internal air index and the current wind speed. Of course, the three data types in this example all need to be eliminated through this method for legacy data.
[0084] In this embodiment, three final calculation parameters Q1, Q2, and Q3 are set, and the three parameters have different value assignment methods according to the number of data, as shown below.
[0085] When (n+1) / 3 is divisible, it is as follows:
[0086]
[0087] Wherein, Q1 is the data value of the 0.25(n+1)th bit, Q2 is the data value of the 0.5(n+1)th bit, and Q3 is the data value of the 0.75(n+1)th bit;
[0088] When (n+1) / 3 is not divisible, and n=3k, (k=1, 2, 3, ...), the formula is as follows:
[0089]
[0090] Where, Q1 is the sum of 0.75 times the value of the 0.25nth data and 0.25 times the value of the (0.25n+1)th data; Q2 is the average value of the 0.5nth data and the (0.5n+1)th data; Q3 is the sum of 0.25 times the value of the 0.75nth data and 0.75 times the value of the (0.75n+1)th data:
[0091] When (n+1) / 3 is not divisible, and n=3k+1, (k=1, 2, 3, ...);
[0092]
[0093] Wherein, Q1 is the sum of 0.25 times the value of the (0.25n-0.5)th data and 0.25 times the value of the (0.25n+0.5)th data; Q2 is the average value of the 0.5nth data and the (0.5n+1)th data; Q3 is the sum of 0.75 times the value of the (0.75n+0.5)th data and 0.25 times the value of the (0.75n+1.5)th data;
[0094] Eliminate outliers and set the upper edge limit, as shown in the formula;
[0095] L low =Q1-1.5(Q3-Q1)
[0096] Set the upper edge limit, as shown in the formula;
[0097] L high =Q3+1.5(Q3-Q1)
[0098] Set the data position to L low ~L high Data outside the range are considered abnormal data and are removed, and the remaining data are normal data.
[0099] Through the above method, we can finally obtain relatively accurate data on wind turbine power generation, generator internal air index and current wind speed, which are used for the calculation of the following model.
[0100] In one embodiment of the present invention, constructing an operation model of the air filtration system by using constraint parameters includes:
[0101] Obtain the optimized wind turbine power generation, generator internal air index and current wind speed value, and set the wind turbine power generation threshold, air index threshold and wind speed threshold;
[0102] Build a computational model:
[0103]
[0104] In the formula, F is the judgment index, W1 is the current wind turbine power generation, W2 is the wind turbine power generation threshold, T1 is the current generator internal air index, T2 is the generator internal air index threshold, V1 is the current wind speed, and V2 is the wind speed threshold;
[0105] If F is a positive number, the air filtration system is turned on, otherwise it is turned off.
[0106] It should be noted that When it is greater than 0, it means that the fan has extra power to supply power to the air filtration system. The fan power generation threshold can be set to the power required by the current power grid, which can be changed at any time. When it is greater than 0, it means that the pollution is serious at this time. When it is less than 0, the pollution has not reached the set threshold. When it is greater than 0, it means that there is enough wind power to generate electricity for the wind turbine, which is used for power grid transmission and the start of the air filtration system. Otherwise, it is not enough. However, the three situations alone are not the determining factors for controlling the air filtration system, and they need to be considered comprehensively.
[0107] For example, although the pollution is not serious at this time, the fan power generation and wind speed are sufficient. If F is greater than 0, the air filtration system can be turned on to further reduce the pollution index and reduce the situation where the fan power generation is low and the pollution is high.
[0108] Similarly, although the pollution is serious at this time, the wind turbine power generation power or wind speed is insufficient, resulting in F being less than 0, then priority will be given to power supply from the grid, and the air filtration system will not be turned on to ensure the stability of the grid output.
[0109] In a second aspect, the present invention provides an air filtration system for a wind turbine generator, comprising:
[0110] A parameter acquisition module is configured to acquire constraint parameters, wherein the constraint parameters include wind turbine power generation, generator internal air index and current wind speed; and optimize the constraint parameters to obtain more accurate constraint parameters;
[0111] A model building module is configured to build an operation model of the air filtration system through constraint parameters, and control the opening and closing of the air filtration system according to the result of the operation model;
[0112] The control module is configured to determine whether the air filtration system is turned on. If the air filtration system is turned on, the ventilation rate of the air filtration system is obtained and compared with the ventilation rate rated by the current power of the air filtration system; determine whether the ventilation rate of the air filtration system obtained in real time is consistent with the ventilation rate rated by the current power, and if they are inconsistent, send a maintenance signal to the remote end;
[0113] A main control module, the main control module is used to connect with the parameter acquisition module, the model building module and the control module, and is used for the above-mentioned wind turbine air filtration system control method.
[0114] In one embodiment of the present invention, a general selection module is also included, which is used to send the maintenance signal to a remote end.
[0115] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. The computer software product is stored in a storage medium, including a number of instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the methods of various embodiments of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk and other media that can store program codes.
[0116] The above are only preferred embodiments of the present invention and are not intended to limit the present invention. For those skilled in the art, the present invention may have various modifications and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention shall be included in the protection scope of the present invention.
Claims
1. A method for controlling an air filtration system of a wind turbine, characterized in that: include; Obtain constraint parameters, where the constraint parameters include wind turbine power generation, generator internal air index, and current wind speed; And optimize the constraint parameters to obtain more accurate constraint parameters; The operation model of the air filtration system is constructed through constraint parameters, and the opening and closing of the air filtration system is controlled according to the results of the operation model; Determine whether the air filtration system is turned on. If the air filtration system is turned on, obtain the ventilation rate of the air filtration system and compare it with the rated ventilation rate of the current power of the air filtration system; It is determined whether the ventilation rate of the air filtration system obtained in real time is consistent with the rated ventilation rate of the current power. If not, a maintenance signal is sent to the remote end.
2. A wind turbine air filtration system control method according to claim 1, characterized in that: The said optimizing the constraint parameters includes: Obtain the wind turbine power generation, the air index inside the generator, and the current wind speed, build a sample data set, set the type and threshold of the required optimization parameters, and set the objective function; Set the maximum number of iterations and the number of starting sample points for optimization; Optimize the wind turbine power generation, generator internal air index and current wind speed parameters in the data set; The best feasible solution obtained after the optimization is completed is used as the optimal parameter setting.
3. A wind turbine air filtration system control method according to claim 2, characterized in that: The optimization of the wind turbine power generation, the air index inside the generator and the current wind speed parameters of the data set includes: The DBSCAN algorithm is used to divide the sample data set features into data cluster categories and remove some abnormal data clusters; A benchmark index of constraint parameters is established, and the quartile algorithm is used to identify a small number of abnormal data with accumulated abnormalities and outlier data with unclear characteristics, and the abnormal data are eliminated again.
4. A wind turbine air filtration system control method according to claim 3, characterized in that: The method of dividing the sample data set features into data cluster categories by using the DBSCAN algorithm includes: Predetermine the parameter domain radius and the minimum number of data point sets; Starting from a point in the sample data that has never been visited, if the number of other data points distributed within this neighborhood radius is greater than or equal to the number of sets, it is marked as normal data; if it is less than the number of sets, it is marked as abnormal data; Return to the previous step and substitute new data points for calculation until all data are calculated; Remove abnormal data sets and retain the data.
5. A wind turbine air filtration system control method according to claim 3, characterized in that: The use of the quartile algorithm to identify a small number of abnormal data with accumulated abnormalities and abnormal points with unclear outlier data characteristics includes: In the sample data set, the number of samples in the statistical sample data set is n, n is greater than 10, and they are arranged from bottom to top in terms of size; Set Q1, Q2, Q3 as the X-th digit value in the sample data set, and use different digits in three cases, namely when (n+1) / 3 is divisible, when (n+1) / 3 is not divisible, and n=3k, (k=1, 2, 3, ...), and when (n+1) / 3 is not divisible, and n=3k+1, (k=1, 2, 3, ...); Eliminate outliers and set the upper edge limit, as shown in the formula; L low =Q1-1.5(Q3-Q1) Set the upper edge limit, as shown in the formula; L high = Q 3+1.5(Q3-Q1) Set the data position to L low ~L high Data outside the range are considered abnormal data and are removed, and the remaining data are normal data.
6. A wind turbine air filtration system control method according to claim 3, characterized in that: The operation model of the air filtration system constructed by using constraint parameters includes: Obtain the optimized wind turbine power generation, generator internal air index and current wind speed value, and set the wind turbine power generation threshold, air index threshold and wind speed threshold; Build a computational model: In the formula, F is the judgment index, W1 is the current wind turbine power generation, W2 is the wind turbine power generation threshold, T1 is the current generator internal air index, T2 is the generator internal air index threshold, V1 is the current wind speed, and V2 is the wind speed threshold; If F is a positive number, the air filtration system is turned on, otherwise it is turned off.
7. A wind turbine air filtration system, characterized in that: include; A parameter acquisition module is configured to acquire constraint parameters, wherein the constraint parameters include wind turbine power generation, generator internal air index and current wind speed; and optimize the constraint parameters to obtain more accurate constraint parameters; A model building module is configured to build an operation model of the air filtration system through constraint parameters, and control the opening and closing of the air filtration system according to the result of the operation model; The control module is configured to determine whether the air filtration system is turned on. If the air filtration system is turned on, the ventilation rate of the air filtration system is obtained and compared with the ventilation rate rated by the current power of the air filtration system; determine whether the ventilation rate of the air filtration system obtained in real time is consistent with the ventilation rate rated by the current power, and if they are inconsistent, send a maintenance signal to the remote end; A main control module, the main control module is used to connect with the parameter acquisition module, the model building module and the control module, and is used to execute a wind turbine air filtration system control method as described in any one of claims 1-6.
8. A wind turbine air filtration system control method according to claim 7, characterized in that: It also includes a general selection module for transmitting the maintenance signal to a remote end.
9. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, a method for controlling an air filtration system of a wind turbine generator according to any one of claims 1 to 6 is implemented.
