Fan control method and system

Abstract

The invention relates to the technical field of fan control, and particularly discloses a fan control method and system, and the method comprises the following steps: constructing a fan operation deviation model; extracting a to-be-adjusted time period in the fan operation deviation model, analyzing the synchronism of the to-be-adjusted time period and the operation environment change, evaluating whether the operation rotating speed deviation of the fan is associated with the operation environment, and generating an operation environment association signal based on an evaluation result; the operation environment is monitored in real time, the occurrence of a time period to be adjusted is predicted, the influence of different operation environment factors is analyzed, the rotating speed regulation value and the rotating speed regulation time are calculated, and the fan is regulated; through real-time monitoring of the operation environment and prediction of the to-be-adjusted time period, accurate adjustment and control of the draught fan are achieved, the deviation of the operation rotating speed of the draught fan is reduced, the operation efficiency and stability of the draught fan are improved, the damage risk and the operation cost of equipment are reduced, meanwhile, multiple operation environment factors are considered, and the operation efficiency of the draught fan is improved. And the control accuracy and reliability are improved.

Description

Technical Field

[0001] The present invention relates to the technical field of fan control, and in particular to a fan control method and system. Background Art

[0002] As a general-purpose equipment widely used in industrial production and daily life, the stable and efficient operation of fans plays a key role in ensuring smooth production processes and improving energy efficiency. In the actual operation of the fan, due to the influence of various complex factors, its operating speed often deviates from the preset value, resulting in speed deviation. When the operating speed of the fan deviates greatly, it will not only reduce the working efficiency of the fan and cause energy waste, but also may cause excessive wear of the equipment, shorten the service life of the equipment, increase the maintenance cost and replacement frequency of the equipment, and even affect the stability and safety of the entire production system.

[0003] Although traditional fan control methods also monitor and adjust the operating status of the fan, they are usually limited to monitoring the fan speed itself. For example, the real-time fan speed is obtained through a simple sensor and compared with the preset speed. When the speed deviation exceeds a certain range, the fan motor is controlled to adjust the speed. However, the operating environment of the fan is a complex and changeable system. Various environmental factors such as temperature, air pressure, wind speed, and fan voltage will have a significant impact on the operation of the fan. For example, in a high temperature environment, the heat dissipation efficiency of the fan motor will decrease, causing the motor temperature to rise, thereby affecting the motor's performance and speed; changes in air pressure will change the air density, thereby affecting the fan's load and operating efficiency; the size and direction of the wind speed will directly affect the fan's air intake conditions, causing the fan's output power and speed to fluctuate; the instability of the fan voltage will directly affect the driving force of the motor, causing speed deviations.

[0004] The existing fan control methods fail to comprehensively and deeply analyze the intrinsic relationship between these operating environment factors and the fan speed deviation, and lack the real-time perception and dynamic response capabilities to changes in the operating environment. Therefore, it is difficult to adjust the fan's operating parameters in a timely and accurate manner according to environmental changes, and it is impossible to achieve precise control of the fan's operating status, which makes it difficult to effectively reduce the fan's operating energy consumption, improve equipment reliability and extend equipment life.

[0005] To sum up, there is an urgent need for a method that can comprehensively consider multiple operating environment factors, accurately analyze the correlation between the fan operating speed deviation and the operating environment, and regulate the fan in real time and accurately according to environmental changes, so as to improve the operating efficiency and stability of the fan, reduce operating costs and maintenance costs, and meet the needs of industrial production and daily life for efficient and reliable operation of the fan. Summary of the invention

[0006] The object of the present invention is to provide a fan control method and system to solve the technical problems in the above background.

[0007] The purpose of the present invention can be achieved through the following technical solutions:

[0008] In a first aspect, the present invention provides a fan control method, comprising the following steps:

[0009] Step 1: Obtain the fan's operating speed deviation and build a fan operating deviation model;

[0010] Step 2: Extract the waiting period in the fan operation deviation model, analyze the synchronization between the waiting period and the operating environment changes, evaluate whether there is a correlation between the fan's operating speed deviation and the operating environment, and generate an operating environment correlation signal based on the evaluation results;

[0011] Step 3: Based on the operating environment related signals, the operating environment is monitored in real time, and the occurrence of the waiting period is predicted, and the influence of different operating environment factors is analyzed, the speed control value and speed control time are calculated, and the fan is controlled.

[0012] As a further solution of the present invention, the process of obtaining the running speed deviation of the fan and constructing the fan running deviation model is as follows:

[0013] During the operation of the fan, with time as the X-axis and the operating speed deviation as the Y-axis, a fan operation deviation model is constructed, the real-time operating speed deviation is substituted into the fan operation deviation model, and a speed operation deviation curve is drawn;

[0014] In the fan operation deviation model, a first speed deviation threshold line and a second speed deviation threshold line are set.

[0015] As a further solution of the present invention: the waiting period is a period when the running speed deviation is in the early warning control area;

[0016] Among them, the early warning control area is the area between the first threshold line of the speed deviation and the second threshold line of the speed deviation.

[0017] As a further solution of the present invention: the process of evaluating whether there is a correlation between the operating speed deviation of the fan and the operating environment, and generating an operating environment correlation signal based on the evaluation result is:

[0018] During the operation of the fan, the fan operation environment model is constructed with time as the X-axis and the operation environment as the Y-axis. The real-time operation environment is substituted into the fan operation environment model and drawn into an operation environment curve.

[0019] Extract the inflection point in the operating environment curve and output the environment change node;

[0020] Based on any period to be adjusted, a time window is preset, all environmental change nodes within the time window are extracted, and the degree of environmental change of the environmental change nodes within the time window is analyzed, and the valid nodes are output;

[0021] Extract the mutation values ​​of all valid nodes within the time window and the node time corresponding to the valid nodes;

[0022] The process of obtaining the mutation value of a valid node is as follows:

[0023] Extract the previous and next data points of the valid node in the time series. The two data points represent the running status before and after the valid node occurs.

[0024] Calculate the difference between the slope of the next data point and the slope of the previous data point, and output the mutation value;

[0025] By formula: Calculate the environmental impact value HY, where T is the start time of the adjustment period, t i represents the node time corresponding to the i-th valid node in the time window, δ is a constant term, and δ is a positive number, TB i represents the mutation value of the i-th valid node in the time window, the value of i is 1, 2, ..., n, and n represents the total number of valid nodes in the time window;

[0026] Extract the deviation accumulation value of the time period to be adjusted, and calculate the correlation coefficient based on the deviation accumulation value and the environmental impact value;

[0027] If the correlation coefficient is greater than the correlation coefficient threshold, an operating environment correlation signal is generated, and the corresponding operating environment is marked as a correlation environment.

[0028] As a further solution of the present invention: the process of obtaining valid nodes is:

[0029] Based on any environment change node, the difference between the operating environment of the environment change node and the average operating environment in the time window is calculated, and the absolute value is taken to obtain the difference value, and then the ratio of the difference value to the average operating environment in the time window is calculated to output the standardized difference value;

[0030] If the standardized difference value is greater than the standardized difference threshold, it means that the environment change is large at the environment change node, and the environment change node is marked as a valid node.

[0031] As a further solution of the present invention: the process of obtaining the deviation cumulative value is:

[0032] Based on the fan operation deviation model, the area of ​​the area enclosed by the speed operation deviation curve in the early warning control area and the first threshold line of the speed deviation during the adjustment period is extracted, and the obtained area is normalized to obtain the deviation cumulative value.

[0033] As a further solution of the present invention: the process of obtaining the correlation coefficient is:

[0034] The Pearson correlation coefficient calculation formula is used to calculate the correlation coefficient based on the deviation cumulative value and the environmental impact value, and the absolute value is taken to output the correlation coefficient between the environmental impact value and the deviation cumulative value.

[0035] As a further solution of the present invention: the process of calculating the speed control value and the speed control time and controlling the fan is as follows:

[0036] Based on the operation environment correlation signal, modeling is performed based on the node data of the effective node and the waiting time period data of the waiting time period to obtain a waiting time period prediction model;

[0037] The node data includes: the operating environment type corresponding to the valid node, the node time of the valid node, and the mutation value of the valid node;

[0038] The data of the waiting period include: the start time of the waiting period, the accumulated deviation value of the waiting period;

[0039] During the operation of the wind turbine, the real-time collected associated environment is preprocessed to obtain the real-time effective nodes and the mutation values ​​of the real-time effective nodes;

[0040] Input the real-time effective nodes and the mutation values ​​of the real-time effective nodes into the waiting-for-adjustment period prediction model, and output the predicted waiting-for-adjustment period;

[0041] The start time of the predicted waiting-for-adjustment period is extracted and marked as the speed control time. At the same time, the accumulated deviation value of the predicted waiting-for-adjustment period is extracted, and the speed control coefficient is calculated. The speed control coefficient is multiplied by the current operating speed to obtain the speed control value.

[0042] As a further solution of the present invention: the process of obtaining the speed control coefficient is:

[0043] The total number of preset associated environments is m, which are E1, E2, ..., E j ,…E m , the influence coefficients corresponding to each associated environment are a1, a2, ..., a j , …, a m , establish the regression equation: ΔR=a0+a1E1+a2E2+…+a j E j …+a m E m+∈, where ΔR is the speed deviation of the fan, a0 is the constant term, ∈ is the error term, and the influence coefficients of each associated environment a1, a2, ..., a j , …, a m ;

[0044] By formula: Calculate the comprehensive environmental impact value HY z , where e ij represents the mutation value of the jth associated environment at the i-th valid node, T is the start time of the waiting period, t i represents the node time corresponding to the i-th valid node in the time window, θ is a constant term, and θ is a positive number, the value of i is 1, 2, ..., n, n represents the total number of valid nodes in the time window, and the value of j is 1, 2, ..., m, m represents the total number of associated environments;

[0045] By formula: The speed control coefficient k is calculated, where α, β, and γ are weight coefficients, and α+β+γ=1, HY zmax is the maximum value of the comprehensive value of historical environmental impact, r max is the maximum value of the historical correlation coefficient, D max It is the maximum value of the historical deviation accumulation value.

[0046] In a second aspect, the present invention provides a fan control system, the system comprising:

[0047] Fan operation deviation model building module: obtains the fan operation speed deviation and builds the fan operation deviation model;

[0048] Wind turbine operating environment correlation assessment module: extracts the waiting period in the wind turbine operating deviation model, analyzes the synchronization between the waiting period and the operating environment changes, assesses whether there is a correlation between the wind turbine operating speed deviation and the operating environment, and generates an operating environment correlation signal based on the assessment results;

[0049] Fan operation control module: Based on the operating environment related signals, it monitors the operating environment in real time, predicts the occurrence of the waiting period, analyzes the impact of different operating environment factors, calculates the speed control value and speed control time, and controls the fan.

[0050] Beneficial effects of the present invention:

[0051] (1) The present invention can accurately analyze the relationship between the fan operating speed deviation and the operating environment by constructing a fan operating deviation model and an operating environment model;

[0052] (2) The present invention realizes precise control of the fan through real-time monitoring of the operating environment and prediction of the adjustment period, reduces the deviation of the fan operating speed, improves the operating efficiency and stability of the fan, reduces the risk of equipment damage and operating costs, and at the same time, takes into account a variety of operating environment factors to improve the accuracy and reliability of control. BRIEF DESCRIPTION OF THE DRAWINGS

[0053] The present invention will be further described below in conjunction with the accompanying drawings.

[0054] Figure 1 is a flowchart of Embodiment 1 of the present invention;

[0055] Figure 2 It is a system block diagram of embodiment 2 of the present invention. DETAILED DESCRIPTION

[0056] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0057] Embodiment 1:

[0058] See also Figure 1 As shown, a fan control method according to an embodiment of the present invention comprises the following steps:

[0059] Step 1: Obtain the fan's operating speed deviation and build a fan operating deviation model;

[0060] The operating speed deviation is the difference between the operating speed of the fan and its preset operating speed;

[0061] In some embodiments, during the operation of the fan, a fan operation deviation model is constructed with time as the X-axis and the operation speed deviation as the Y-axis, and the real-time operation speed deviation is substituted into the fan operation deviation model, and a speed operation deviation curve is drawn;

[0062] Wherein, in the fan operation deviation model, a first speed deviation threshold line and a second speed deviation threshold line are set;

[0063] It should be explained that the first speed deviation threshold line is below the second speed deviation threshold line, the area between the first speed deviation threshold line and the X-axis is the acceptable deviation area, the area between the first speed deviation threshold line and the second speed deviation threshold line is the early warning control area, and the first speed deviation threshold line and the second speed deviation threshold line are both empirical values, which are set by the staff based on experience;

[0064] It should be explained that when the speed deviation of the fan is in the acceptable deviation zone, it means that the operation state of the fan is normal and can continue to work. When the speed deviation of the fan is in the control area, it means that the operation state of the fan is abnormal and the fan speed needs to be controlled.

[0065] Step 2: Extract the waiting period in the fan operation deviation model (i.e., the period when the operating speed deviation is in the early warning control zone), analyze the synchronization between the waiting period and the operating environment changes, evaluate whether there is a correlation between the fan's operating speed deviation and the operating environment, and generate an operating environment correlation signal based on the evaluation results;

[0066] The operating environment includes, but is not limited to: air temperature, air pressure, wind speed, and fan voltage;

[0067] In some implementation schemes, during the operation of the wind turbine, a wind turbine operation environment model is constructed with time as the X-axis and the operation environment as the Y-axis, and the real-time operation environment is substituted into the wind turbine operation environment model and drawn into an operation environment curve, so that the change of the operation environment can be presented in an intuitive curve form, which is convenient for comparison and analysis with the wind turbine operation deviation model;

[0068] Extract the inflection point in the operating environment curve and output the environment change node;

[0069] It should be explained that the inflection point refers to the point where the slope of the operating environment curve changes significantly, which usually indicates that the environmental factors have undergone important changes or reached a certain critical value;

[0070] Based on any period to be adjusted, a time window is preset to search for environmental change nodes that may be related to it;

[0071] It should be explained that the end time of the time window is the start time of the corresponding waiting period, and the size of the time window should be set according to the specific situation, including the response time of the fan to the change of environmental factors, the typical cycle of the change of environmental factors, etc.

[0072] All environmental change nodes within the time window are extracted, and based on the degree of environmental change, the environmental change nodes are divided into invalid nodes and valid nodes. The screening mechanism of environmental change nodes can remove environmental change nodes with insignificant environmental changes and only retain valid nodes that may have a significant impact on the operating status of the wind turbine, thereby improving the accuracy and efficiency of subsequent analysis. The specific process is as follows:

[0073] Based on any environment change node, the difference between the operating environment of the environment change node and the average operating environment in the time window is calculated, and the absolute value is taken to obtain the difference value, and then the ratio of the difference value to the average operating environment in the time window is calculated to output the standardized difference value;

[0074] Preset a standardized difference threshold, and compare and analyze the standardized difference value with the standardized difference threshold;

[0075] If the standardized difference value is less than or equal to the standardized difference threshold, it means that the environment at the environment change node is not changed much, and the environment change node is marked as an invalid node;

[0076] If the standardized difference value is greater than the standardized difference threshold, it means that the environment change is large at the environment change node, and the environment change node is marked as a valid node;

[0077] Extract the mutation values ​​of all valid nodes within the time window and the node time corresponding to the valid nodes;

[0078] The process of obtaining the mutation value of a valid node is as follows:

[0079] Extract the previous and next data points of the valid node in the time series. The two data points represent the running status before and after the valid node occurs.

[0080] Calculate the difference between the slope of the next data point and the slope of the previous data point, and output the mutation value;

[0081] It should be explained that if the mutation value is a positive number, it means that at the effective node, the change trend of the operating environment has an upward acceleration or a positive change in direction; if the mutation value is a plural number, it means that at the effective node, the change trend of the operating environment has a downward deceleration, reversal or a negative change in direction; the larger the absolute value of the mutation value, the faster the change rate or the more significant the change in direction;

[0082] By formula: The environmental impact value HY is calculated, where T is the start time of the adjustment period (i.e. the end time of the time window), t i represents the node time corresponding to the i-th valid node in the time window, δ is a constant term, and δ is a positive number, TB i represents the mutation value of the i-th valid node in the time window, the value of i is 1, 2, ..., n, and n represents the total number of valid nodes in the time window;

[0083] It needs to be explained that Tt i represents the time difference between the i-th valid node and the waiting period, δ -(T-ti) It is expressed as the weight of the mutation value of the i-th valid node in the time window, Tt i The smaller the value of is, the smaller the time difference between the ith valid node and the period to be adjusted is, that is, the higher the weight is;

[0084] At the same time, the accumulated deviation value of the period to be adjusted is extracted. The specific process is as follows:

[0085] Based on the fan operation deviation model, the area of ​​the speed operation deviation curve in the waiting period is extracted between the warning control area and the first threshold line of the speed deviation. In order to remove the dimension, the obtained area is normalized to obtain the deviation cumulative value.

[0086] Then, the Pearson correlation coefficient calculation formula is used to calculate the correlation coefficient based on the deviation cumulative value and the environmental impact value, and the absolute value is taken to output the correlation coefficient between the environmental impact value and the deviation cumulative value;

[0087] Preset the correlation coefficient threshold, compare and analyze the correlation coefficient with the correlation coefficient threshold, so as to accurately judge whether there is a correlation between the fan speed deviation and the operating environment, and provide a reliable basis for whether the operating environment needs to be monitored and the fan needs to be controlled in the future;

[0088] If the correlation coefficient is ≤ the correlation coefficient threshold, it means that there is no strong correlation between the environmental impact value and the deviation accumulation value, that is, there is no connection between the operating speed deviation of the fan and the operating environment, and an operating environment-independent signal is generated;

[0089] If the correlation coefficient is greater than the correlation coefficient threshold, it indicates that there is a strong correlation between the environmental impact value and the deviation accumulation value, that is, there is a correlation between the operating speed deviation of the fan and the operating environment, an operating environment correlation signal is generated, and the corresponding operating environment is marked as a correlated environment;

[0090] Step 3: Based on the operating environment related signals, the operating environment is monitored in real time, and the occurrence of the waiting period is predicted. The influence of different operating environment factors is analyzed, the speed control value and speed control time are calculated, and the fan is controlled to reduce the possibility of the predicted waiting period.

[0091] In some implementation schemes, based on the operating environment associated signal, modeling is performed based on the node data of the effective node and the to-be-adjusted period data of the to-be-adjusted period to obtain a to-be-adjusted period prediction model, which can learn the relationship patterns and rules between the effective nodes and the to-be-adjusted period in the historical data, and provides a powerful tool for predicting the occurrence of the future to-be-adjusted period;

[0092] The node data includes: the operating environment type corresponding to the valid node, the node time of the valid node, and the mutation value of the valid node;

[0093] The data of the waiting period include: the start time of the waiting period, the accumulated deviation value of the waiting period;

[0094] During the operation of the wind turbine, the real-time collected associated environment is preprocessed to obtain the real-time effective nodes and the mutation values ​​of the real-time effective nodes;

[0095] Input the real-time effective node and the mutation value of the real-time effective node into the prediction model of the waiting period, and output the predicted waiting period (including the start time of the predicted waiting period and its accumulated deviation value);

[0096] It should be explained that, since the prediction model for the waiting period is established based on the node data of the effective nodes and the waiting period data of the waiting period, the pre-processed real-time operating environment data is input into the prediction model for the waiting period during prediction. The model will analyze and calculate the input data according to the patterns and rules learned during training, and output a predicted start time of the waiting period and its cumulative deviation value, which is based on the model's learning and inference of the relationship between the effective nodes and the waiting period in the historical data; for example, if the model finds that a certain operating environment change pattern (represented by the effective nodes and their mutation values) always triggers the waiting period after a period of time, then when a similar pattern appears in the real-time data, the model will predict the corresponding start time of the waiting period and its cumulative deviation value;

[0097] Extract the start time of the predicted waiting-for-adjustment period and mark it as the speed control time. At the same time, extract the cumulative deviation value of the predicted waiting-for-adjustment period and calculate the speed control coefficient. Multiply the speed control coefficient by the current running speed to obtain the speed control value.

[0098] Among them, the process of obtaining the speed control coefficient is:

[0099] Different associated environments may have different degrees of influence on the speed deviation of the fan. It is necessary to determine the influence coefficient of each associated environment on the speed deviation based on historical data through methods such as multivariate regression analysis.

[0100] The total number of preset associated environments is m, which are E1, E2, ..., E j ,…E m , the influence coefficients corresponding to each associated environment are a1, a2, ..., a j , …, a m , establish the regression equation: ΔR=a0+a1E1+a2E2+…+a j E j …+a m E m +∈, where ΔR is the speed deviation of the fan, a0 is the constant term, ∈ is the error term, and the influence coefficients of each associated environment a1, a2, ..., a j , …, a m ;

[0101] By formula: Calculate the comprehensive environmental impact value HY z , where e ijrepresents the mutation value of the jth associated environment at the i-th valid node, T is the start time of the waiting period, t i represents the node time corresponding to the i-th valid node in the time window, θ is a constant term, and θ is a positive number, the value of i is 1, 2, ..., n, n represents the total number of valid nodes in the time window, and the value of j is 1, 2, ..., m, m represents the total number of associated environments;

[0102] By formula: The speed control coefficient k is calculated, where α, β, and γ are weight coefficients, and α+β+γ=1, HY zmax is the maximum value of the comprehensive value of historical environmental impact, r max is the maximum value of the historical correlation coefficient, D max is the maximum value of the historical deviation accumulation;

[0103] The technical solution of the embodiment of the present invention is mainly as follows: by obtaining the deviation between the fan operating speed and the preset speed, a fan operating deviation model is constructed with time and deviation as the axis, and a speed operating deviation curve is drawn. The first and second threshold lines for the speed deviation are set to divide the acceptable deviation area and the early warning control area; the waiting period when the operating deviation is in the early warning control area is extracted, the fan operating environment model is constructed and a curve is drawn, the environmental change nodes are extracted, and for the preset time window of the waiting period, the standardized difference values ​​of the environmental change nodes in the window are calculated, the valid and invalid nodes are distinguished and the mutation values ​​of the valid nodes are calculated, the environmental impact value and the cumulative value of the deviation of the waiting period are calculated, and the correlation between the two is determined by the Pearson correlation coefficient, and an operating environment related or unrelated signal is generated; if there is an operating environment related signal, the valid node and the waiting period data are used to model the waiting period prediction model, and the real-time related The model is input after environmental preprocessing, and the predicted waiting period is output. The start time of the predicted waiting period is extracted as the speed control time, and the speed control coefficient and control value are calculated to control the fan. By constructing the fan operation deviation model and the operation environment model, the relationship between the fan operation speed deviation and the operation environment can be accurately analyzed. Through real-time monitoring of the operation environment and prediction of the waiting period, the fan is precisely controlled, the fan operation speed deviation is reduced, the fan operation efficiency and stability are improved, and the equipment damage risk and operation cost are reduced. At the same time, a variety of operation environment factors are considered to improve the accuracy and reliability of control.

[0104] Embodiment 2:

[0105] Based on Example 1, please refer to Figure 2 As shown, a fan control system according to an embodiment of the present invention includes:

[0106] Fan operation deviation model building module: obtains the fan operation speed deviation and builds the fan operation deviation model;

[0107] Wind turbine operating environment correlation assessment module: extracts the waiting period in the wind turbine operating deviation model, analyzes the synchronization between the waiting period and the operating environment changes, assesses whether there is a correlation between the wind turbine operating speed deviation and the operating environment, and generates an operating environment correlation signal based on the assessment results;

[0108] Fan operation control module: Based on the operating environment related signals, it monitors the operating environment in real time, predicts the occurrence of the waiting period, analyzes the impact of different operating environment factors, calculates the speed control value and speed control time, and controls the fan.

[0109] The above is a detailed description of an embodiment of the present invention, but the content is only a preferred embodiment of the present invention and cannot be considered to limit the scope of implementation of the present invention. All equivalent changes and improvements made within the scope of the present invention should still fall within the scope of the patent coverage of the present invention.

Claims

1. A fan control method, characterized in that: The following steps are involved: Step 1: Obtain the fan's operating speed deviation and build a fan operating deviation model; Step 2: Extract the waiting period in the fan operation deviation model, analyze the synchronization between the waiting period and the operating environment changes, evaluate whether there is a correlation between the fan's operating speed deviation and the operating environment, and generate an operating environment correlation signal based on the evaluation results; Step 3: Based on the operating environment related signals, the operating environment is monitored in real time, and the occurrence of the waiting period is predicted, and the influence of different operating environment factors is analyzed, the speed control value and speed control time are calculated, and the fan is controlled.

2. A fan control method according to claim 1, characterized in that: The process of obtaining the fan's operating speed deviation and building a fan operating deviation model is as follows: During the operation of the fan, with time as the X-axis and the operating speed deviation as the Y-axis, a fan operation deviation model is constructed, the real-time operating speed deviation is substituted into the fan operation deviation model, and a speed operation deviation curve is drawn; In the fan operation deviation model, a first speed deviation threshold line and a second speed deviation threshold line are set.

3. A fan control method according to claim 2, characterized in that: The waiting period is the period when the running speed deviation is in the early warning control area; Among them, the early warning control area is the area between the first threshold line of the speed deviation and the second threshold line of the speed deviation.

4. A fan control method according to claim 3, characterized in that: The process of evaluating whether there is a correlation between the fan's operating speed deviation and the operating environment, and generating an operating environment correlation signal based on the evaluation result is as follows: During the operation of the fan, the fan operation environment model is constructed with time as the X-axis and the operation environment as the Y-axis. The real-time operation environment is substituted into the fan operation environment model and drawn into an operation environment curve. Extract the inflection point in the operating environment curve and output the environment change node; Based on any period to be adjusted, a time window is preset, all environmental change nodes within the time window are extracted, and the degree of environmental change of the environmental change nodes within the time window is analyzed, and the valid nodes are output; Extract the mutation values ​​of all valid nodes within the time window and the node time corresponding to the valid nodes; The process of obtaining the mutation value of a valid node is as follows: Extract the previous and next data points of the valid node in the time series. The two data points represent the running status before and after the valid node occurs. Calculate the difference between the slope of the next data point and the slope of the previous data point, and output the mutation value; By formula: Calculate the environmental impact value HY, where T is the start time of the adjustment period, t i Indicates the node time corresponding to the i-th valid node in the time window, δ is a constant term, and δ is a positive number, TB i represents the mutation value of the i-th valid node in the time window, the value of i is 1, 2, ..., n, and n represents the total number of valid nodes in the time window; Extract the deviation accumulation value of the time period to be adjusted, and calculate the correlation coefficient based on the deviation accumulation value and the environmental impact value; If the correlation coefficient is greater than the correlation coefficient threshold, an operating environment correlation signal is generated, and the corresponding operating environment is marked as a correlation environment.

5. A fan control method according to claim 4, characterized in that: The process of obtaining valid nodes is as follows: Based on any environment change node, the difference between the operating environment of the environment change node and the average operating environment in the time window is calculated, and the absolute value is taken to obtain the difference value, and then the ratio of the difference value to the average operating environment in the time window is calculated to output the standardized difference value; If the standardized difference value is greater than the standardized difference threshold, it means that the environment change is large at the environment change node, and the environment change node is marked as a valid node.

6. A fan control method according to claim 4, characterized in that: The process of obtaining the deviation cumulative value is: Based on the fan operation deviation model, the area of ​​the area enclosed by the speed operation deviation curve in the early warning control area and the first threshold line of the speed deviation during the adjustment period is extracted, and the obtained area is normalized to obtain the deviation cumulative value.

7. A fan control method according to claim 4, characterized in that: The process of obtaining the correlation coefficient is: The Pearson correlation coefficient calculation formula is used to calculate the correlation coefficient based on the deviation cumulative value and the environmental impact value, and the absolute value is taken to output the correlation coefficient between the environmental impact value and the deviation cumulative value.

8. A fan control method according to claim 4, characterized in that: The process of calculating the speed control value and speed control time and controlling the fan is as follows: Based on the operation environment correlation signal, modeling is performed based on the node data of the effective node and the waiting time period data of the waiting time period to obtain a waiting time period prediction model; The node data includes: the operating environment type corresponding to the valid node, the node time of the valid node, and the mutation value of the valid node; The data of the waiting period include: the start time of the waiting period, the accumulated deviation value of the waiting period; During the operation of the wind turbine, the real-time collected associated environment is preprocessed to obtain the real-time effective nodes and the mutation values ​​of the real-time effective nodes; Input the real-time effective nodes and the mutation values ​​of the real-time effective nodes into the waiting-for-adjustment period prediction model, and output the predicted waiting-for-adjustment period; The start time of the predicted waiting-for-adjustment period is extracted and marked as the speed control time. At the same time, the accumulated deviation value of the predicted waiting-for-adjustment period is extracted, and the speed control coefficient is calculated. The speed control coefficient is multiplied by the current operating speed to obtain the speed control value.

9. A fan control method according to claim 8, characterized in that: The process of obtaining the speed control coefficient is: The total number of preset associated environments is m, which are E1, E2, ..., E j ,…E m , the influence coefficients corresponding to each associated environment are a1, a2, ..., a j , …, a m , establish the regression equation: ΔR=a0+a1E1+a2E2+…+a j E j …+a m E m +∈, where ΔR is the speed deviation of the fan, a0 is the constant term, ∈ is the error term, and the influence coefficients of each associated environment a1, a2, ..., a j , …, a m ; By formula: Calculate the comprehensive environmental impact value HY z , where e ij represents the mutation value of the jth associated environment at the i-th valid node, T is the start time of the waiting period, t i represents the node time corresponding to the i-th valid node in the time window, θ is a constant term, and θ is a positive number, the value of i is 1, 2, ..., n, n represents the total number of valid nodes in the time window, and the value of j is 1, 2, ..., m, m represents the total number of associated environments; By formula: The speed control coefficient k is calculated, where α, β, and γ are weight coefficients, and α+β+γ=1, HY zmax is the maximum value of the comprehensive value of historical environmental impact, r max is the maximum value of the historical correlation coefficient, D max It is the maximum value of the historical deviation accumulation value.

10. A fan control system, applied to a fan control method according to any one of claims 1 to 9, characterized in that: The system includes: Fan operation deviation model building module: obtains the fan operation speed deviation and builds the fan operation deviation model; Wind turbine operating environment correlation assessment module: extracts the waiting period in the wind turbine operating deviation model, analyzes the synchronization between the waiting period and the operating environment changes, assesses whether there is a correlation between the wind turbine operating speed deviation and the operating environment, and generates an operating environment correlation signal based on the assessment results; Fan operation control module: Based on the operating environment related signals, it monitors the operating environment in real time, predicts the occurrence of the waiting period, analyzes the impact of different operating environment factors, calculates the speed control value and speed control time, and controls the fan.

Images