A multi-working-condition fan adaptive control method and system and a storage medium

Abstract

This invention discloses a multi-condition adaptive control method, system, and storage medium for fans, relating to the field of automation control. It solves the technical problem of difficulty in adaptively controlling fan speeds to adapt to environmental changes during fan regulation. The invention obtains the effective control range of each fan in a factory using a digital twin model; acquires target data within the effective control range; extracts feature values ​​from the target data to obtain characteristic target data; issues alarm signals based on the characteristic target data; determines fan control factors based on the characteristic target data; and adaptively adjusts the fans based on the fan control factors. This invention improves the adaptability and controllability of fans to the environment, and reduces ineffective energy consumption among multiple fans.

Description

Technical Field

[0001] This invention relates to the field of automation control, specifically to a multi-condition adaptive control method, system, and storage medium for wind turbines. Background Technology

[0002] Fans play a vital role in various fields such as industry, construction, and agriculture, and are used for ventilation, air conditioning, and gas transportation. In the industrial and energy sectors, fans are widely used in ventilation, air conditioning, metallurgy, and chemical industries. However, in actual operation, fans often face variable operating conditions, such as environmental changes and equipment aging, making it difficult for traditional control methods to operate efficiently and stably, resulting in prominent problems such as high energy consumption and low efficiency.

[0003] Currently, most adaptive control methods for multi-condition fans struggle to adapt the fan speed to environmental changes during fan regulation. They rely solely on fixed parameters or manual speed settings for fan speed selection. This results in ineffective energy consumption when the concentration of harmful gases is low, and a delay in the dispersion of harmful gases when the concentration is high.

[0004] Therefore, this invention discloses a multi-condition adaptive control method, system, and storage medium for wind turbines to solve the above-mentioned technical problems. Summary of the Invention

[0005] This invention aims to at least solve one of the technical problems existing in the prior art. To this end, this invention proposes a multi-condition adaptive control method, system, and storage medium for fans, which solves the technical problem of difficulty in adaptively controlling the fans to adapt to environmental changes during fan regulation. This invention obtains the effective air control range of each fan in the factory through a digital twin model, acquires target data within the effective air control range, extracts feature values ​​from the target data to obtain feature target data, determines the fan control factor based on the feature target data, and adaptively adjusts the fans based on the fan control factor, thus solving the above-mentioned problem.

[0006] To achieve the above objectives, a first aspect of the present invention provides a multi-condition adaptive control method for wind turbines, comprising:

[0007] The effective air control range of each fan in the factory is obtained through digital twin modeling;

[0008] Obtain target data within the effective wind control range; the target data includes carbon monoxide concentration, nitric oxide concentration, nitrogen dioxide concentration, and sulfur dioxide concentration.

[0009] Feature data is obtained by extracting feature values ​​from the target data; the feature data includes feature carbon monoxide concentration, feature nitric oxide concentration, feature nitrogen dioxide concentration, and feature sulfur dioxide concentration.

[0010] Issue alarm signals based on characteristic target data;

[0011] The fan control factor is determined based on the characteristic target data, and the fan is adaptively adjusted based on the fan control factor.

[0012] Preferably, obtaining the effective wind control range of each fan in the factory through a digital twin model includes:

[0013] A 3D image of the factory is obtained using 3D scanning equipment, and a 3D model is constructed from the 3D image. Information on the 3D model and fan equipment is extracted. The 3D scanning equipment includes a high-resolution camera or a 3D scanner, and the fan equipment information includes the appearance and physical characteristics of each fan involved in the factory's ventilation control.

[0014] Based on the equipment information of each wind turbine, an equipment model of each wind turbine is constructed, and a simulation model is constructed based on the 3D model. The equipment model and the simulation model are combined to generate a digital twin model.

[0015] The standard speed and the corresponding fan operating data are input into the digital twin model to obtain the effective air control range of each fan. The standard speed is obtained by manual setting, and the effective air control range is the effective working range of the corresponding fan under the standard speed.

[0016] Preferably, acquiring target data within the effective wind control range includes:

[0017] Within the effective wind control range of each wind turbine, the carbon monoxide concentration is obtained through several carbon monoxide sensors, the nitric oxide concentration is obtained through several nitric oxide sensors, the nitrogen dioxide concentration is obtained through several nitrogen dioxide sensors, and the sulfur dioxide concentration is obtained through several sulfur dioxide sensors.

[0018] Preferably, the step of extracting feature values ​​from the target data to obtain feature target data includes:

[0019] The concentrations of carbon monoxide, nitric oxide, nitrogen dioxide, and sulfur dioxide are grouped into concentration groups A1, A2, A3, and A4 according to their type.

[0020] Extract each concentration group sequentially, obtain the variance of the concentration group, and determine whether the variance is greater than the concentration variance threshold. When the variance is not greater than the concentration variance threshold, retain the data of the current concentration group. When the variance is greater than the concentration variance threshold, remove the concentration with the largest absolute value of the difference from the average concentration in the current concentration group, and re-determine the variance until the variance of the current concentration group is less than the corresponding concentration variance threshold. Then retain the remaining data of the current concentration group. The concentration variance threshold is determined empirically.

[0021] The maximum and average values ​​of the data retained for each concentration group are weighted to obtain the characteristic values ​​of each concentration group; the characteristic values ​​corresponding to the A1 concentration group are marked as characteristic carbon monoxide concentration, the characteristic values ​​corresponding to the A2 concentration group are marked as characteristic nitric oxide concentration, the characteristic values ​​corresponding to the A3 concentration group are marked as characteristic nitrogen dioxide concentration, and the characteristic values ​​corresponding to the A4 concentration group are marked as characteristic sulfur dioxide concentration.

[0022] Preferably, the step of issuing an alarm signal based on feature target data includes:

[0023] Extract each concentration from the feature target data. When the feature carbon monoxide concentration N1 in the feature target data exceeds the carbon monoxide alarm threshold, issue an alarm signal for excessive carbon monoxide.

[0024] When the concentration of nitric oxide (N2) in the characteristic target data exceeds the nitric oxide alarm threshold, an alarm signal for excessive nitric oxide is issued.

[0025] When the concentration of nitrogen dioxide (N3) in the characteristic target data exceeds the nitrogen dioxide alarm threshold, an alarm signal for excessive nitrogen dioxide is issued.

[0026] When the sulfur dioxide concentration (N4) in the characteristic target data exceeds the sulfur dioxide alarm threshold, an alarm signal for excessive sulfur dioxide is issued. The alarm thresholds for carbon monoxide, nitrogen monoxide, nitrogen dioxide, and sulfur dioxide are determined based on standard values ​​set by experts and the natural ventilation conditions within the effective wind control range of the current fan.

[0027] Preferably, determining the wind turbine control factor based on the feature target data includes:

[0028] Extract the characteristic carbon monoxide concentration N1, characteristic nitric oxide concentration N2, characteristic nitrogen dioxide concentration N3, and characteristic sulfur dioxide concentration N4 from the characteristic target data. Determine whether any of these concentrations exceeds the corresponding concentration judgment value. If yes, set the fan control factor FZ to 1; otherwise, determine the fan control factor FZ based on the characteristic carbon monoxide concentration N1, characteristic nitric oxide concentration N2, characteristic nitrogen dioxide concentration N3, and characteristic sulfur dioxide concentration N4. The concentration judgment value is obtained empirically.

[0029] The wind turbine control factor FZ satisfies the calculation formula (1):

[0030]

[0031] Among them, α1, α2, α3 and α4 are proportional adjustment coefficients determined based on the number of times each concentration exceeds the corresponding concentration judgment value; Y1 is the concentration judgment value corresponding to the characteristic carbon monoxide concentration N1, Y2 is the concentration judgment value corresponding to the characteristic nitric oxide concentration N2, Y3 is the concentration judgment value corresponding to the characteristic nitrogen dioxide concentration N3, and Y4 is the concentration judgment value corresponding to the characteristic sulfur dioxide concentration N4.

[0032] Preferably, α1, α2, α3, and α4 are determined based on the number of times each concentration exceeds its corresponding concentration threshold, including:

[0033] Extract the number of times (DC) each concentration exceeds its corresponding concentration threshold from the feature target data recorded by the current factory in the previous n days. i Based on the number of DC i Determine the proportional adjustment coefficient αi corresponding to each concentration in the feature target data; where i is the number corresponding to each concentration in the feature target data; n is obtained manually and is generally taken as 180 days;

[0034] The proportional adjustment coefficient αi satisfies the calculation formula (2):

[0035]

[0036] Among them, BDC is a frequency limit set based on experience, used to reduce the impact of excessively exceeding the concentration judgment value on other proportional adjustment coefficients.

[0037] Preferably, the adaptive adjustment of the fan based on the fan control factor includes:

[0038] Extract the fan control factor FZ, and determine the fan speed FV corresponding to the current fan based on the calculation formula (3). The calculation formula (3) is:

[0039] FV = max(FZ·DZ,AZ) (3);

[0040] Where DZ is the maximum speed of the fan corresponding to the blower, and AZ is the minimum speed manually set for the fan corresponding to the blower.

[0041] A second aspect of the present invention provides a multi-condition wind turbine adaptive control system, comprising: an intelligent analysis module, and a data collection module and an adaptive control module connected to the intelligent analysis module;

[0042] The data collection module is used to obtain the effective air control range of each fan in the factory through a digital twin model, and acquire target data within the effective air control range; wherein, the target data includes carbon monoxide concentration, nitric oxide concentration, nitrogen dioxide concentration, and sulfur dioxide concentration.

[0043] The intelligent analysis module is used to extract feature values ​​from the target data to obtain feature target data; wherein, the feature target data includes feature carbon monoxide concentration, feature nitric oxide concentration, feature nitrogen dioxide concentration, and feature sulfur dioxide concentration;

[0044] The adaptive control module is used to issue alarm signals based on characteristic target data; determine the fan control factor based on the characteristic target data; and adaptively adjust the fan based on the fan control factor.

[0045] A third aspect of the present invention provides a storage medium, characterized in that it is used to store a computer program, which, when executed, implements a multi-condition adaptive control method for a wind turbine.

[0046] Compared with the prior art, the beneficial effects of the present invention are:

[0047] 1. This invention obtains the effective air control range of each fan in a factory through a digital twin model, acquires target data within the effective air control range, extracts feature values ​​from the target data to obtain feature target data, determines the fan control factor based on the feature target data, and adaptively adjusts the fan based on the fan control factor. This solves the technical problem of difficulty in adaptively controlling the fan to adapt to environmental changes in fan control. This invention can improve the adaptability and control capability of fans to the environment, and reduce the ineffective energy consumption among multiple fans.

[0048] 2. This invention constructs a 3D model of the factory using digital twin technology and combines it with fan equipment information to accurately plan the effective airflow control range of each fan, thereby significantly improving the efficiency and accuracy of factory ventilation control. This application can identify the effective working area of ​​the fans in advance, avoiding ineffective energy consumption caused by multiple fans operating simultaneously due to excessive concentration at one location, thus optimizing energy utilization and reducing operating costs. Through simulation analysis of the digital twin model, the working efficiency of the fans at standard speeds can be more accurately evaluated, providing a scientific basis for adaptive fan control and improving system flexibility and response speed. Furthermore, this application constructs a high-precision digital twin model through 3D scanning technology and extraction of fan equipment information, capable of simulating fan operating states under different conditions, providing data support for optimizing fan layout and parameter settings, thereby further improving the overall ventilation effect of the factory and the safety of the production environment. Attached Figure Description

[0049] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0050] Figure 1 This is a schematic diagram of the operation steps of the present invention;

[0051] Figure 2 This is a schematic diagram illustrating the operation steps for obtaining feature target data according to the present invention;

[0052] Figure 3 This is a schematic diagram of the system modules of the present invention. Detailed Implementation

[0053] The technical solution of the present invention will be clearly and completely described below with reference to the embodiments. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0054] Please see Figure 1 The first aspect of this invention provides a multi-condition adaptive control method for wind turbines, comprising:

[0055] The effective air control range of each fan in the factory is obtained through digital twin modeling;

[0056] Obtain target data within the effective wind control range; the target data includes carbon monoxide concentration, nitric oxide concentration, nitrogen dioxide concentration, and sulfur dioxide concentration.

[0057] Feature data is obtained by extracting feature values ​​from the target data; the feature data includes feature carbon monoxide concentration, feature nitric oxide concentration, feature nitrogen dioxide concentration, and feature sulfur dioxide concentration.

[0058] Issue alarm signals based on characteristic target data;

[0059] The fan control factor is determined based on the characteristic target data, and the fan is adaptively adjusted based on the fan control factor.

[0060] This application uses a digital twin model to obtain the effective air control range of each fan in the factory, including:

[0061] A 3D image of the factory is obtained using 3D scanning equipment, and a 3D model is constructed from the 3D image. Information on the 3D model and fan equipment is extracted. The 3D scanning equipment includes a high-resolution camera or a 3D scanner, and the fan equipment information includes the appearance and physical characteristics of each fan involved in the factory's ventilation control.

[0062] Based on the equipment information of each wind turbine, an equipment model of each wind turbine is constructed, and a simulation model is constructed based on the 3D model. The equipment model and the simulation model are combined to generate a digital twin model.

[0063] The standard speed and the corresponding fan operating data are input into the digital twin model to obtain the effective air control range of each fan. The standard speed is obtained by manual setting, and the effective air control range is the effective working range of the corresponding fan under the standard speed.

[0064] It is worth noting that this invention constructs a 3D model of the factory using digital twin technology and combines it with fan equipment information to accurately plan the effective air control range of each fan, thereby significantly improving the efficiency and accuracy of factory ventilation control. This application can identify the effective working area of ​​the fans in advance, avoiding ineffective energy consumption caused by multiple fans operating simultaneously due to excessive concentration at a certain location, thus optimizing energy utilization and reducing operating costs. Through simulation analysis of the digital twin model, the working efficiency of the fans at standard speeds can be more accurately evaluated, providing a scientific basis for adaptive fan control and improving system flexibility and response speed. Furthermore, this application constructs a high-precision digital twin model through 3D scanning technology and extraction of fan equipment information, which can simulate the fan operating status under different working conditions, providing data support for optimizing fan layout and parameter settings, thereby further improving the overall ventilation effect of the factory and the safety of the production environment. In summary, this application not only improves the intelligence level of fan adaptive control but also provides strong technical support for the efficient operation and sustainable development of the factory.

[0065] It should be noted that physical characteristics include the wind turbine's engine parameters, the energy consumption corresponding to the wind turbine's blade speed, etc.

[0066] It should be noted that when obtaining the effective working range, if there are factory areas that are not marked as effective working ranges, these factory areas will be included in the effective working range of the nearest fan.

[0067] The target data obtained in this application within the effective wind control range includes:

[0068] Within the effective wind control range of each wind turbine, the carbon monoxide concentration is obtained through several carbon monoxide sensors, the nitric oxide concentration is obtained through several nitric oxide sensors, the nitrogen dioxide concentration is obtained through several nitrogen dioxide sensors, and the sulfur dioxide concentration is obtained through several sulfur dioxide sensors.

[0069] Please see Figure 2 In this application, feature target data is obtained by extracting feature values ​​from the target data, including:

[0070] The concentrations of carbon monoxide, nitric oxide, nitrogen dioxide, and sulfur dioxide are grouped into concentration groups A1, A2, A3, and A4 according to their type.

[0071] Extract each concentration group sequentially, obtain the variance of the concentration group, and determine whether the variance is greater than the concentration variance threshold. If the variance is not greater than the concentration variance threshold, retain the data of the current concentration group. If the variance is greater than the concentration variance threshold, remove the concentration with the largest absolute value of the difference from the average concentration in the current concentration group, and re-determine the variance until the variance of the current concentration group is less than the corresponding concentration variance threshold. Then retain the remaining data of the current concentration group. The concentration variance threshold is determined empirically.

[0072] The maximum and average values ​​of the data retained for each concentration group are weighted to obtain the characteristic values ​​of each concentration group; the characteristic values ​​corresponding to the A1 concentration group are marked as characteristic carbon monoxide concentration, the characteristic values ​​corresponding to the A2 concentration group are marked as characteristic nitric oxide concentration, the characteristic values ​​corresponding to the A3 concentration group are marked as characteristic nitrogen dioxide concentration, and the characteristic values ​​corresponding to the A4 concentration group are marked as characteristic sulfur dioxide concentration.

[0073] It is worth noting that this invention extracts feature values ​​from the target data, integrating the concentrations of carbon monoxide, nitric oxide, nitrogen dioxide, and sulfur dioxide into four concentration groups respectively. Through variance assessment and outlier removal, the stability and reliability of the data are ensured. By retaining data that meets the variance requirements and calculating the weights of their maximum and average values, representative feature values ​​are extracted, thus providing accurate data support for subsequent adaptive fan control. This method not only improves the efficiency of data processing but also ensures the accuracy and reliability of feature values, providing strong technical support for the intelligent and refined control of factory ventilation. Furthermore, by empirically setting concentration variance thresholds, the data processing process becomes more flexible and applicable, adapting to the actual needs of different factories and further enhancing the system's practicality and scalability.

[0074] It should be noted that the maximum and average values ​​of the data retained for each concentration group are used to calculate the characteristic values ​​of each concentration group. The weighting coefficients of the maximum and average values ​​are set manually. For example, the weighting coefficient of the maximum value is 0.7 and the weighting coefficient of the average value is 0.3.

[0075] It should be noted that when removing the concentration with the largest absolute difference from the average concentration in the current concentration group and re-performing the variance assessment, the average concentration is the average of the concentrations retained in the current variance assessment step.

[0076] It should be noted that when removing the concentration with the largest absolute difference from the average concentration in the current concentration group, if the concentration with the largest absolute difference from the average concentration in the current concentration group has both a maximum and a minimum concentration, the minimum concentration will be removed first.

[0077] It should be noted that if, after removing 90% of the concentration data, the variance of the remaining concentrations is still not less than the concentration variance threshold, then the average value of the original concentrations in the current concentration group will be used as the characteristic value.

[0078] This application issues alarm signals based on feature target data, including:

[0079] Extract each concentration from the feature target data. When the feature carbon monoxide concentration N1 in the feature target data exceeds the carbon monoxide alarm threshold, issue an alarm signal for excessive carbon monoxide.

[0080] When the concentration of nitric oxide (N2) in the characteristic target data exceeds the nitric oxide alarm threshold, an alarm signal for excessive nitric oxide is issued.

[0081] When the concentration of nitrogen dioxide (N3) in the characteristic target data exceeds the nitrogen dioxide alarm threshold, an alarm signal for excessive nitrogen dioxide is issued.

[0082] When the sulfur dioxide concentration (N4) in the characteristic target data exceeds the sulfur dioxide alarm threshold, an alarm signal for excessive sulfur dioxide is issued. The alarm thresholds for carbon monoxide, nitrogen monoxide, nitrogen dioxide, and sulfur dioxide are determined based on standard values ​​set by experts and the natural ventilation conditions within the effective wind control range of the current fan.

[0083] It should be noted that the natural ventilation situation within the effective control range of the current fan is the natural wind speed data within the effective control range of the current fan without fan ventilation. Furthermore, each alarm threshold is inversely proportional to the natural wind speed data value. This is because the more gas is dispersed by the natural wind speed, the lower the monitored concentration becomes. In this case, the gas leakage situation is more serious than the monitored situation. Therefore, it is necessary to lower the alarm threshold to adapt to the influence of natural wind speed on gas concentration.

[0084] This application determines wind turbine control factors based on characteristic target data, including:

[0085] Extract the characteristic carbon monoxide concentration N1, characteristic nitric oxide concentration N2, characteristic nitrogen dioxide concentration N3, and characteristic sulfur dioxide concentration N4 from the characteristic target data. Determine whether any of these concentrations exceeds the corresponding concentration judgment value. If yes, set the fan control factor FZ to 1; otherwise, determine the fan control factor FZ based on the characteristic carbon monoxide concentration N1, characteristic nitric oxide concentration N2, characteristic nitrogen dioxide concentration N3, and characteristic sulfur dioxide concentration N4. The concentration judgment value is obtained empirically.

[0086] The wind turbine control factor FZ satisfies the calculation formula (1):

[0087]

[0088] Among them, α1, α2, α3 and α4 are proportional adjustment coefficients determined based on the number of times each concentration exceeds the corresponding concentration judgment value; Y1 is the concentration judgment value corresponding to the characteristic carbon monoxide concentration N1, Y2 is the concentration judgment value corresponding to the characteristic nitric oxide concentration N2, Y3 is the concentration judgment value corresponding to the characteristic nitrogen dioxide concentration N3, and Y4 is the concentration judgment value corresponding to the characteristic sulfur dioxide concentration N4.

[0089] It is worth noting that this method uses empirically obtained concentration judgment values, combined with data and experience from practical applications, making it highly practical and operable. By judging whether the concentration of a characteristic gas exceeds the judgment value, it is possible to quickly and intuitively determine whether fan control measures need to be activated. When the concentration of any characteristic gas exceeds the judgment value, the fan control factor FZ is directly set to 1, ensuring a rapid response in emergency situations and avoiding potential safety risks. When the concentration does not exceed the judgment value, by comprehensively considering the relative deviations of multiple gas concentrations through formula (1), the operating parameters of the fan can be adjusted more precisely, achieving accurate control of environmental quality.

[0090] Furthermore, proportional adjustment coefficients α1, α2, α3, and α4 are introduced in calculation formula (1). These coefficients are determined based on the number of times each concentration exceeds the corresponding concentration judgment value, reflecting the differentiated treatment of different gas concentration exceedance situations. This design makes the calculation of the fan control factor FZ more flexible and scientific, and can dynamically adjust the adjustment coefficient based on historical data of gas concentration exceedances during actual operation, thereby optimizing the fan control effect. At the same time, calculating FZ in the form of an exponential function makes the change of the control factor smoother and more continuous, avoiding system fluctuations that may be caused by abrupt control, and improving the stability and reliability of the system.

[0091] The implementation of this method can effectively improve the intelligence level of wind turbine regulation, reduce the need for human intervention, lower operating costs, and improve the efficiency of environmental quality monitoring and control. By comprehensively considering the dynamic changes in the concentration of various gases, this method can not only promptly detect and respond to environmental quality problems, but also achieve energy conservation and emission reduction goals by optimizing wind turbine operating parameters.

[0092] It should be noted that when determining whether any of the characteristic carbon monoxide concentration N1, characteristic nitric oxide concentration N2, characteristic nitrogen dioxide concentration N3, and characteristic sulfur dioxide concentration N4 exceeds the corresponding concentration judgment value, the judgment is made in the order of N1, N2, N3, and N4. If any concentration exceeds the corresponding concentration judgment value, the fan control factor FZ is immediately set to 1, and further calculation is stopped.

[0093] In this application, α1, α2, α3, and α4 are determined based on the number of times each concentration exceeds its corresponding concentration threshold, including:

[0094] Extract the number of times (DC) each concentration exceeds its corresponding concentration threshold from the feature target data recorded by the current factory in the previous n days. i Based on the number of DC i Determine the proportional adjustment coefficient αi corresponding to each concentration in the feature target data; where i is the number corresponding to each concentration in the feature target data; n is obtained manually and is generally taken as 180 days;

[0095] The proportional adjustment coefficient αi satisfies the calculation formula (2):

[0096]

[0097] Among them, BDC is a frequency limit set based on experience, used to reduce the impact of excessively exceeding the concentration judgment value on other proportional adjustment coefficients.

[0098] It is worth noting that this application extracts the number of times each concentration exceeded the corresponding concentration judgment value from the characteristic target data recorded by the current factory in the previous n days. Based on these numbers, the proportional adjustment coefficient αi is determined, which can dynamically reflect the historical patterns and trends of different pollutant concentration exceedances. This method fully considers the statistical characteristics of historical data, making the determination of the proportional adjustment coefficient αi more scientific and reasonable, and avoiding the control deviation that may be caused by fixed coefficients. By introducing the frequency limit value (BDC), the influence of the number of times each pollutant concentration exceeds the standard on the proportional adjustment coefficient can be effectively balanced, preventing excessive suppression of the proportional adjustment coefficients of other pollutants by too many times the concentration of one pollutant exceeds the standard, thereby ensuring a fairer and more reasonable weight allocation of each pollutant in the wind turbine control.

[0099] More importantly, by calculating the proportional adjustment coefficient αi using formula (2), the relative contribution of each pollutant concentration exceeding the standard can be quantified into a specific weight value, thereby enabling differentiated treatment of different pollutant concentration exceeding the standard in the subsequent calculation of the fan control factor. This method not only improves the intelligence level of fan control, but also dynamically adjusts the fan operating parameters according to changes in actual environmental conditions, thereby achieving precise control of environmental quality;

[0100] In summary, this application, through historical data statistics and dynamic weight allocation, can effectively balance the impact of pollutant concentration exceedances on fan control, ensuring the scientific and precise nature of fan control, while simultaneously improving the system's intelligence level and the efficiency of environmental quality control. This method can not only adapt to the actual environmental conditions of different factories but also dynamically adjust the control strategy based on changes in historical data, thereby achieving comprehensive, precise, and efficient control of environmental quality.

[0101] It should be noted that the number of times each concentration in the feature target data exceeds the corresponding concentration judgment value (DC) is... i Specifically, the number of times the characteristic carbon monoxide concentration exceeds the concentration judgment value Y1 is DC1, the number of times the characteristic nitric oxide concentration N2 exceeds the concentration judgment value Y2 is DC2, the number of times the characteristic nitrogen dioxide concentration N3 exceeds the concentration judgment value Y3 is DC3, and the number of times the characteristic sulfur dioxide concentration N4 exceeds the concentration judgment value Y4 is DC4.

[0102] This application describes adaptive fan adjustment based on a fan control factor, including:

[0103] Extract the fan control factor FZ, and determine the fan speed FV corresponding to the current fan based on the calculation formula (3). The calculation formula (3) is:

[0104] FV = max(FZ·DZ,AZ) (3);

[0105] Where DZ is the maximum speed of the fan corresponding to the blower, and AZ is the minimum speed manually set for the fan corresponding to the blower.

[0106] Please see Figure 3 A second aspect of the present invention provides a multi-condition adaptive control system for a wind turbine, comprising: an intelligent analysis module, a data collection module and an adaptive control module connected to the intelligent analysis module;

[0107] Data collection module: Used to determine the effective air control range of each fan in the factory through a digital twin model, and to acquire target data within the effective air control range; the target data includes carbon monoxide concentration, nitric oxide concentration, nitrogen dioxide concentration, and sulfur dioxide concentration.

[0108] Intelligent analysis module: used to extract feature values ​​from target data to obtain feature target data; among which, feature target data includes feature carbon monoxide concentration, feature nitric oxide concentration, feature nitrogen dioxide concentration, and feature sulfur dioxide concentration;

[0109] Adaptive control module: used to issue alarm signals based on characteristic target data; determine the fan control factor based on the characteristic target data; and adaptively adjust the fan based on the fan control factor.

[0110] A third aspect of the present invention provides a storage medium, characterized in that it is used to store a computer program, which, when executed, implements a multi-condition adaptive control method for a wind turbine.

[0111] Some of the data in the above formula are calculated by removing dimensions and taking their numerical values. The formula is the closest to the real situation obtained by software simulation of a large amount of collected data. The preset parameters and preset thresholds in the formula are set by those skilled in the art according to the actual situation or obtained through simulation of a large amount of data.

[0112] Working principle of the invention:

[0113] This invention first uses a digital twin model to obtain the effective air control range of each fan in the factory. This allows for the division of the fan's operating range, reducing the possibility of multiple fans operating in one location exceeding the limit. Next, target data within the effective air control range is acquired, and feature values ​​are extracted from this data to obtain characteristic target data. This step involves standardizing and analyzing the target data to provide accurate data for subsequent fan control. Finally, an alarm signal is issued based on the characteristic target data, and fan control factors are determined based on these factors. Adaptive fan adjustment is then performed based on these control factors. This step involves analyzing the fan's rotational speed to adapt to the environment, ensuring the fan speed matches environmental requirements and improving the level of automation control.

[0114] The above embodiments are only used to illustrate the technical methods of the present invention and are not intended to limit it. Although the present invention has been described in detail with reference to preferred embodiments, those skilled in the art should understand that modifications or equivalent substitutions can be made to the technical methods of the present invention without departing from the spirit and scope of the technical methods of the present invention.

Claims

1. A multi-condition adaptive control method for a fan, characterized in that, include: The effective air control range of each fan in the factory is obtained through digital twin modeling; Obtain target data within the effective wind control range; the target data includes carbon monoxide concentration, nitric oxide concentration, nitrogen dioxide concentration, and sulfur dioxide concentration. Feature data is obtained by extracting feature values ​​from the target data; the feature data includes feature carbon monoxide concentration, feature nitric oxide concentration, feature nitrogen dioxide concentration, and feature sulfur dioxide concentration. Issue alarm signals based on characteristic target data; The fan control factor is determined based on the feature target data, and the fan is adaptively adjusted based on the fan control factor; The method of obtaining the effective air control range of each fan in the factory through a digital twin model includes: A 3D image of the factory is obtained using 3D scanning equipment, and a 3D model is constructed from the 3D image. Information on the 3D model and fan equipment is extracted. The 3D scanning equipment includes a high-resolution camera or a 3D scanner, and the fan equipment information includes the appearance and physical characteristics of each fan involved in the factory's ventilation control. Based on the equipment information of each wind turbine, an equipment model of each wind turbine is constructed, and a simulation model is constructed based on the 3D model. The equipment model and the simulation model are combined to generate a digital twin model. The standard speed and the corresponding fan operating data are input into the digital twin model to obtain the effective wind control range of each fan; whereby the effective wind control range is the effective operating range of the corresponding fan under the standard speed condition; The determination of wind turbine control factors based on feature target data includes: Extract the characteristic carbon monoxide concentration N1, characteristic nitric oxide concentration N2, characteristic nitrogen dioxide concentration N3, and characteristic sulfur dioxide concentration N4 from the characteristic target data, and determine whether any of these concentrations exceeds the corresponding concentration judgment value. If yes, set the value of the fan control factor FZ to 1; otherwise, determine the fan control factor FZ based on the characteristic carbon monoxide concentration N1, characteristic nitric oxide concentration N2, characteristic nitrogen dioxide concentration N3, and characteristic sulfur dioxide concentration N4. The wind turbine control factor FZ satisfies the calculation formula (1): (1)； in, , , and It is a proportional adjustment coefficient determined based on the number of times each concentration exceeds the corresponding concentration judgment value; Y1 is the concentration judgment value corresponding to the characteristic carbon monoxide concentration N1, Y2 is the concentration judgment value corresponding to the characteristic nitric oxide concentration N2, Y3 is the concentration judgment value corresponding to the characteristic nitrogen dioxide concentration N3, and Y4 is the concentration judgment value corresponding to the characteristic sulfur dioxide concentration N4. The , , and It is determined based on the number of times each concentration exceeds the corresponding concentration threshold, including: Extract the number of times each concentration exceeds the corresponding concentration threshold from the feature target data recorded by the current factory in the previous n days. Based on the number Determine the proportional adjustment coefficient corresponding to each concentration in the feature target data. Where i is the number corresponding to each concentration in the feature target data; The proportional adjustment coefficient Satisfies the calculation formula (2): (2)； Wherein, BDC is the limit for the number of attempts; The adaptive adjustment of the fan based on the fan control factor includes: Extract the fan control factor FZ, and determine the fan speed FV corresponding to the current fan based on the calculation formula (3). The calculation formula (3) is: (3)； Where DZ is the maximum speed of the fan corresponding to the fan, and AZ is the minimum speed of the fan corresponding to the fan.

2. The multi-condition adaptive control method for a fan according to claim 1, characterized in that, The acquisition of target data within the effective wind control range includes: Within the effective wind control range of each wind turbine, the carbon monoxide concentration is obtained through several carbon monoxide sensors, the nitric oxide concentration is obtained through several nitric oxide sensors, the nitrogen dioxide concentration is obtained through several nitrogen dioxide sensors, and the sulfur dioxide concentration is obtained through several sulfur dioxide sensors.

3. The multi-condition adaptive control method for a fan according to claim 1, characterized in that, The step of extracting feature values ​​from the target data to obtain feature target data includes: The concentrations of carbon monoxide, nitric oxide, nitrogen dioxide, and sulfur dioxide are grouped into concentration groups A1, A2, A3, and A4 according to their type. Extract each concentration group sequentially, obtain the variance of the concentration group, and determine whether the variance is greater than the concentration variance threshold. When the variance is not greater than the concentration variance threshold, retain the data of the current concentration group. When the variance is greater than the concentration variance threshold, remove the concentration with the largest absolute value of the difference from the average concentration in the current concentration group, and re-determine the variance until the variance of the current concentration group is less than the corresponding concentration variance threshold, then retain the remaining data of the current concentration group. The maximum and average values ​​of the data retained for each concentration group are weighted to obtain the characteristic values ​​of each concentration group; the characteristic values ​​corresponding to the A1 concentration group are marked as characteristic carbon monoxide concentration, the characteristic values ​​corresponding to the A2 concentration group are marked as characteristic nitric oxide concentration, the characteristic values ​​corresponding to the A3 concentration group are marked as characteristic nitrogen dioxide concentration, and the characteristic values ​​corresponding to the A4 concentration group are marked as characteristic sulfur dioxide concentration.

4. The multi-condition adaptive control method for a fan according to claim 1, characterized in that, The alarm signal issued based on feature target data includes: Extract each concentration from the feature target data. When the feature carbon monoxide concentration N1 in the feature target data exceeds the carbon monoxide alarm threshold, issue an alarm signal for excessive carbon monoxide. When the concentration of nitric oxide (N2) in the characteristic target data exceeds the nitric oxide alarm threshold, an alarm signal for excessive nitric oxide is issued. When the concentration of nitrogen dioxide (N3) in the characteristic target data exceeds the nitrogen dioxide alarm threshold, an alarm signal for excessive nitrogen dioxide is issued. When the sulfur dioxide concentration (N4) in the characteristic target data exceeds the sulfur dioxide alarm threshold, an alarm signal for excessive sulfur dioxide is issued. The alarm thresholds for carbon monoxide, nitrogen monoxide, nitrogen dioxide, and sulfur dioxide are determined based on standard values ​​set by experts and the natural ventilation conditions within the effective wind control range of the current fan.

5. A multi-condition adaptive control system for a wind turbine, used to operate the multi-condition adaptive control method for a wind turbine as described in any one of claims 1 to 4, characterized in that, include: The intelligent analysis module, as well as the data collection module and adaptive control module connected to the intelligent analysis module; The data collection module is used to obtain the effective air control range of each fan in the factory through a digital twin model, and acquire target data within the effective air control range; wherein, the target data includes carbon monoxide concentration, nitric oxide concentration, nitrogen dioxide concentration, and sulfur dioxide concentration. The intelligent analysis module is used to extract feature values ​​from the target data to obtain feature target data; wherein, the feature target data includes feature carbon monoxide concentration, feature nitric oxide concentration, feature nitrogen dioxide concentration, and feature sulfur dioxide concentration; The adaptive control module is used to issue alarm signals based on feature target data; determine the fan control factor based on the feature target data; and adaptively adjust the fan based on the fan control factor. The method of obtaining the effective air control range of each fan in the factory through a digital twin model includes: A 3D image of the factory is obtained using 3D scanning equipment, and a 3D model is constructed from the 3D image. Information on the 3D model and fan equipment is extracted. The 3D scanning equipment includes a high-resolution camera or a 3D scanner, and the fan equipment information includes the appearance and physical characteristics of each fan involved in the factory's ventilation control. Based on the equipment information of each wind turbine, an equipment model of each wind turbine is constructed, and a simulation model is constructed based on the 3D model. The equipment model and the simulation model are combined to generate a digital twin model. The standard speed and the corresponding fan operating data are input into the digital twin model to obtain the effective wind control range of each fan; whereby the effective wind control range is the effective operating range of the corresponding fan under the standard speed condition; The determination of wind turbine control factors based on feature target data includes: Extract the characteristic carbon monoxide concentration N1, characteristic nitric oxide concentration N2, characteristic nitrogen dioxide concentration N3, and characteristic sulfur dioxide concentration N4 from the characteristic target data, and determine whether any of these concentrations exceeds the corresponding concentration judgment value. If yes, set the value of the fan control factor FZ to 1; otherwise, determine the fan control factor FZ based on the characteristic carbon monoxide concentration N1, characteristic nitric oxide concentration N2, characteristic nitrogen dioxide concentration N3, and characteristic sulfur dioxide concentration N4. The wind turbine control factor FZ satisfies the calculation formula (1): (1)； in, , , and It is a proportional adjustment coefficient determined based on the number of times each concentration exceeds the corresponding concentration judgment value; Y1 is the concentration judgment value corresponding to the characteristic carbon monoxide concentration N1, Y2 is the concentration judgment value corresponding to the characteristic nitric oxide concentration N2, Y3 is the concentration judgment value corresponding to the characteristic nitrogen dioxide concentration N3, and Y4 is the concentration judgment value corresponding to the characteristic sulfur dioxide concentration N4. The , , and It is determined based on the number of times each concentration exceeds the corresponding concentration threshold, including: Extract the number of times each concentration exceeds the corresponding concentration threshold from the feature target data recorded by the current factory in the previous n days. Based on the number Determine the proportional adjustment coefficient corresponding to each concentration in the feature target data. Where i is the number corresponding to each concentration in the feature target data; The proportional adjustment coefficient Satisfies the calculation formula (2): (2)； Wherein, BDC is the limit for the number of attempts; The adaptive adjustment of the fan based on the fan control factor includes: Extract the fan control factor FZ, and determine the fan speed FV corresponding to the current fan based on the calculation formula (3). The calculation formula (3) is: (3)； Where DZ is the maximum speed of the fan corresponding to the fan, and AZ is the minimum speed of the fan corresponding to the fan.

6. A storage medium, characterized in that, Used to store a computer program, which, when executed, implements the multi-condition adaptive control method for wind turbines as described in any one of claims 1 to 4.

Images