Energy-saving control method for axial flow fan of wind generating set

Abstract

The invention relates to the technical field of wind generating sets, and particularly discloses an axial flow fan energy-saving control method of a wind generating set, which specifically comprises the following steps of: acquiring operation parameters of the wind generating set in historical data, performing time period analysis, and determining the operation state of the wind generating set, the running state comprises a running high-efficiency period and a running low-efficiency period; carrying out regularity analysis and judgment on the basis of the determined operation state of the wind generating set, and generating a regular signal and an irregular signal; and on the basis of the regularity analysis and judgment result, the running state of the wind generating set in the future time period is predicted. According to the method, the low-efficiency time period of the wind power generation set is determined by analyzing historical data, so that mechanical energy input of the axial flow fan can be reduced in the low-efficiency time period, waste of electric energy in the low-efficiency power generation process is reduced, high-energy-consumption stages in the starting process are reduced through prediction results of the high-efficiency time period and the low-efficiency time period, and extra energy loss of equipment is reduced. Therefore, the purpose of saving energy is achieved.

Description

Technical Field

[0001] The invention relates to the technical field of wind generator sets, and in particular to an energy-saving control method for an axial flow fan of a wind generator set. Background Art

[0002] Wind turbines are key equipment for converting wind energy into electrical energy. They are mainly composed of wind rotors, generators, towers, etc. The wind rotors rotate under the action of wind, converting wind energy into mechanical energy, which is then transmitted to the generator through the transmission system and finally converted into electrical energy output.

[0003] However, when monitoring the operating data of wind turbines, the method of judging the operating status of the unit based on a simple power threshold cannot effectively distinguish the high and low operating efficiency of the unit, resulting in some periods of seemingly normal operation but actually low efficiency. The axial flow fan still consumes a lot of electricity and has low energy utilization efficiency. In the process of analyzing historical operating data, the researchers noticed that existing technologies rarely conduct in-depth research on the occurrence patterns of high-efficiency and low-efficiency periods, so when predicting future operating conditions, only a relatively single prediction method can be used. The prediction results deviate greatly from the actual situation and cannot provide a reliable basis for the operation of axial flow fans. Summary of the invention

[0004] The object of the present invention is to provide an energy-saving control method for an axial flow fan of a wind turbine generator set to solve the technical problems in the above background.

[0005] The purpose of the present invention can be achieved by the following technical solutions:

[0006] The present invention provides an energy-saving control method for an axial flow fan of a wind generator set, which specifically comprises the following steps:

[0007] Obtaining the operating parameters of the wind turbine generator set in the historical data, and performing time period analysis to determine the operating status of the wind turbine generator set, wherein the operating status includes an efficient operating period and an inefficient operating period;

[0008] Based on the determined operating status of the wind turbine generator set, regularity analysis and judgment are performed to generate regular signals and irregular signals;

[0009] Based on the regularity analysis and judgment results, the operation status of the wind turbine generator set in the future period is predicted, and based on the status prediction results in the future period, the axial flow fan is controlled.

[0010] As a further solution of the present invention: the process of determining the operating state of the wind turbine generator set is:

[0011] The operating parameters in the historical data are historical output power data. The historical data is divided into several time intervals, with each time interval as a period.

[0012] By analyzing the historical output power sequence {P1, P2, ..., P n}Process and calculate to obtain the power deviation ratio and discrete degree value of each time period;

[0013] The power deviation ratio and the discrete degree value are processed to obtain the operating efficiency judgment coefficient;

[0014] The time period when the operation efficiency judgment coefficient is less than the operation efficiency judgment coefficient threshold is marked as the high-efficiency operation period, and the time period when the operation efficiency judgment coefficient is greater than or equal to the operation efficiency judgment coefficient threshold is marked as the low-efficiency operation period.

[0015] As a further solution of the present invention: the process of obtaining the power deviation ratio is:

[0016] The historical output power data of each time period are summed and averaged to obtain the power mean, and the difference between the power mean and the rated power of the wind turbine is calculated. The absolute value of the difference is taken and the ratio is calculated with the rated power of the wind turbine to obtain the power deviation ratio.

[0017] As a further solution of the present invention: the process of obtaining the discrete degree value is:

[0018] The maximum and minimum output power values ​​in the historical output power data of each period are extracted for difference calculation to obtain the output power range.

[0019] By formula: The discrete characterization value LS is calculated, where P max-min It indicates that the output power is very poor. The power mean, P i represents the i-th historical output power value in the historical output power value sequence, n represents the number of historical output power values, and PJ represents the average of all adjacent output power values ​​of the i-th historical output power value.

[0020] As a further solution of the present invention: the process of regularity analysis and judgment is:

[0021] By processing and calculating the efficient operation period and the inefficient operation period, the regular characterization value of the efficient period group and the regular characterization value of the inefficient period group are obtained respectively;

[0022] The law characterization value of the efficient time period group and the law characterization value of the inefficient time period group are weighted and summed to obtain the law judgment coefficient;

[0023] If the regularity judgment coefficient is less than the regularity judgment coefficient threshold, a regularity signal is generated;

[0024] If the regularity determination coefficient is greater than or equal to the regularity determination coefficient threshold, an irregular signal is generated.

[0025] As a further solution of the present invention: the process of obtaining the regularity characterization value of the high-efficiency time period group is as follows:

[0026] Integrate the continuous high-efficiency operation time periods to obtain a high-efficiency operation time period group;

[0027] Count the number of efficient time periods in each efficient time period group, obtain the efficient time period number value sequence of all efficient time period groups, and perform mean processing to obtain the mean value of the number of efficient time periods;

[0028] Calculate the difference between each value in the high-efficiency period quantity value sequence and the mean value of the high-efficiency period quantity, take the absolute value of the difference, and obtain the high-efficiency quantity deviation value;

[0029] Compare the high-efficiency quantity deviation value with the high-efficiency quantity deviation limit value, extract the high-efficiency time period group whose high-efficiency quantity deviation value is less than or equal to the high-efficiency quantity deviation limit value, mark it as the concentrated high-efficiency time period group, and count the number of concentrated high-efficiency time period groups, and then calculate the ratio with the total number of high-efficiency time period groups to obtain the high-efficiency concentrated quantity ratio;

[0030] Extract the maximum and minimum values ​​in the sequence of the number of efficient time periods, calculate the difference, and calculate the ratio of the difference to the mean number of efficient time periods to obtain the efficient value change ratio;

[0031] The weighted sum of the high-efficiency concentrated quantity ratio and the high-efficiency value change ratio is calculated to obtain the regular characterization value of the high-efficiency time period group.

[0032] As a further solution of the present invention: the process of obtaining the regular characterization value of the inefficient time period group is:

[0033] Integrate the continuous inefficient operation time periods to obtain an inefficient operation time period group, and count the number of inefficient time periods in each inefficient operation time period group to obtain a sequence of inefficient time period number values ​​for all inefficient operation time period groups;

[0034] And sum and average the values ​​in the sequence of inefficient time period quantity values ​​to obtain the mean value of inefficient time period quantity;

[0035] Calculate the difference between each value in the inefficient period quantity value sequence and the mean value of the inefficient period quantity, take the absolute value of the difference, and obtain the inefficient quantity deviation value;

[0036] Compare the inefficient quantity deviation value with the inefficient quantity deviation limit value, extract the efficient time period group whose inefficient quantity deviation value is less than or equal to the inefficient quantity deviation limit value, mark it as the concentrated inefficient time period group, and count the number of concentrated inefficient time period groups, and then calculate the ratio with the total number of inefficient time period groups to obtain the inefficient concentrated quantity ratio;

[0037] Extract the maximum and minimum values ​​in the sequence of inefficient time period quantities, calculate the difference, and calculate the ratio of the difference to the mean value of the inefficient time period to obtain the inefficient value change ratio;

[0038] The weighted sum of the inefficient concentration quantity ratio and the inefficient value change ratio is calculated to obtain the regular characterization value of the inefficient time period group.

[0039] As a further solution of the present invention: the process of predicting the operating status of the wind turbine generator set in the future period is:

[0040] Based on regular signals, the fixed interval pattern prediction method is used to predict the operation status of future time periods, specifically:

[0041] Obtain the mean number of efficient time periods and the mean number of inefficient time periods, use the mean number of efficient time periods and the mean number of inefficient time periods as the interval number, and obtain the operation status of the future time period based on the operation status of the current time period combined with the interval number;

[0042] Based on irregular signals, the moving average method is used to predict the operating status in future periods.

[0043] As a further solution of the present invention: the prediction method based on irregular signals is:

[0044] Setting a window size k of the moving average method, wherein the window size k is adjusted based on an adjustment coefficient;

[0045] Obtain the historical operating status data of the wind turbine generator set, that is, {s1, s2, …, s m}, where s j Represents the operating status data of the jth period;

[0046] Moving average M j The calculation formula is: Where, j = 1, 2, ..., m-k+1;

[0047] Among them, p represents the sum index variable, which is used to traverse the data points in the interval from j+k-1, and then the corresponding s p Sum, j represents the starting position index of the moving average calculation, m is the total number of historical operating status data, S p Indicates the pth running status data;

[0048] Set a prediction threshold. If the moving average value is greater than the prediction threshold, the prediction period is marked as an efficient period. If the moving average value is less than or equal to the prediction threshold, the prediction period is marked as an inefficient period.

[0049] As a further solution of the present invention: the process of obtaining the adjustment coefficient is:

[0050] Fluctuation Factor F B The calculation formula is: Among them, bcg and jzg represent the standard deviation of the number of efficient time period groups and the mean number of efficient time periods, respectively; bcd and jzd represent the standard deviation of the number of inefficient time period groups and the mean number of inefficient time periods, respectively;

[0051] Comprehensive impact factor of concentration change F JB The calculation formula is: JB =a1*rjg+a2*rjd-b1*rbg-b2*rbd, where a1, a2, b1, b2 are weight coefficients, rjg and rbg represent the ratio of efficient concentration quantity and the ratio of efficient value change, rjd and rbd represent the ratio of inefficient concentration quantity and the ratio of inefficient value change;

[0052] The adjustment coefficient is obtained by calculating the ratio of the comprehensive impact factor of concentrated changes to the fluctuation impact factor.

[0053] Beneficial effects of the present invention:

[0054] (1) The present invention determines the inefficient time period of the wind power generation group by analyzing historical data, thereby reducing the mechanical energy input of the axial flow fan during the inefficient time period and reducing the waste of electric energy in the inefficient power generation process. By predicting the results of the high-efficiency and low-efficiency time periods, the high energy consumption stage during the startup process is reduced, and the additional energy loss of the equipment is reduced, thereby achieving the purpose of energy saving;

[0055] (2) The present invention analyzes whether the occurrence time of high-efficiency periods and low-efficiency periods is regular, so as to facilitate the subsequent prediction of high-efficiency periods and low-efficiency periods. At the same time, the prediction method can be selected according to the regularity results to more accurately arrange the operation of the axial flow fan, reduce the speed of the axial flow fan or adjust the blade angle during the low-efficiency period, reduce unnecessary mechanical energy input, effectively avoid the waste of electrical energy in the operation process that cannot be efficiently converted into electrical energy, and reduce the ineffective energy consumption of the fan during the low-output period. BRIEF DESCRIPTION OF THE DRAWINGS

[0056] The present invention will be further described below in conjunction with the accompanying drawings.

[0057] Figure 1 It is a flow chart of an energy-saving control method for an axial flow fan of a wind generator set according to the present invention;

[0058] Figure 2 It is a structural diagram of an axial flow fan energy-saving control system of a wind generator set according to the present invention. DETAILED DESCRIPTION

[0059] 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.

[0060] Embodiment 1:

[0061] See also Figure 1 , Figure 2 As shown, an energy-saving control method for an axial flow fan of a wind turbine generator set according to an embodiment of the present invention comprises the following steps:

[0062] Step 1: Obtain the operating parameters of the wind turbine generator set in historical data, and perform time period analysis to determine the efficient and inefficient operating periods of the wind turbine generator set;

[0063] In some embodiments, for data sources such as a monitoring system and a sensor network of a wind turbine, historical operating parameters are collected;

[0064] The historical operating parameters include, but are not limited to: wind speed data obtained by an anemometer, output power data obtained by a power measurement device, and ambient temperature data obtained by a temperature sensor;

[0065] In a possible embodiment, the output power data is used to determine the high-efficiency operation period and the low-efficiency operation period of the wind power generation group. The specific process is as follows:

[0066] Divide the historical data into several time intervals, with each time interval being a period, wherein the time interval is summarized and set by technicians in this field based on experience and the operating characteristics of the wind turbine generator set;

[0067] Based on any time period, obtain the historical output power value sequence of each time period: {P1, P2, ..., P n};

[0068] The historical output power data of each period is summed and averaged to obtain the power mean, the difference between the power mean and the rated power of the wind turbine generator set is calculated, the absolute value of the difference is taken, and the ratio is calculated with the rated power of the wind turbine generator set to obtain the power deviation ratio;

[0069] The maximum and minimum output power values ​​in the historical output power data of the period are extracted for difference calculation to obtain the output power range.

[0070] By formula: The discrete characterization value LS is calculated, where P max-minIt indicates that the output power is very poor. The power mean, P i represents the i-th output power value in the historical output power value sequence, n represents the number of historical output power values, and PJ represents the average of all adjacent output power values ​​of the i-th historical output power value;

[0071] By calculating the power deviation ratio and the discrete characterization value, it is reflected that: first, the operating efficiency judgment coefficient is obtained by multiplying the power deviation ratio and the discrete characterization value, which comprehensively reflects the operating efficiency and stability of the wind turbine generator set during the period; second, through the discrete characterization value, the maximum value, minimum value, mean value and the mean value of adjacent values ​​of the output power are comprehensively considered, which can accurately capture the slight fluctuations in power output and more accurately reflect the stability of output power changes; third, it can be used as an early warning indicator for potential equipment failures. Compared with the existing technology, which is usually detected only when a failure occurs and the power output is obviously abnormal, if a wind turbine generator set has an early minor failure, it may be reflected when the power output has a slight fluctuation;

[0072] In the operation of wind turbines, the extreme value difference can quickly reflect the maximum fluctuation range of the operating status. For example, the drastic change of power when encountering strong gusts can be more clearly reflected through the discrete representation value. When analyzing the output power fluctuation, the change of adjacent power values ​​is very important for judging the operation stability. This method can better reflect the continuity and trend of the output power change.

[0073] It should be noted that if i = 1, then PJ = P2, and if i = n, then PJ = P n-1 ;

[0074] The power deviation ratio is multiplied by the discrete degree value to obtain the operating efficiency judgment coefficient;

[0075] Setting an operating efficiency judgment coefficient threshold, wherein the operating efficiency judgment coefficient threshold is set by practitioners in this field based on a large amount of data analysis and experience summary;

[0076] Mark the time period when the operation efficiency judgment coefficient is less than the operation efficiency judgment coefficient threshold as the high-efficiency operation time period, and mark the time period when the operation efficiency judgment coefficient is greater than or equal to the operation efficiency judgment coefficient threshold as the low-efficiency operation time period;

[0077] Step 2: Based on the determined high-efficiency operation period and low-efficiency operation period of the wind turbine generator set, regularity analysis is performed and regularity judgment is made;

[0078] In some embodiments, obtaining a high-efficiency operation period and a low-efficiency operation period of a wind turbine generator set;

[0079] Integrate the continuous high-efficiency operation time periods to obtain the high-efficiency operation time period group, and count the number of high-efficiency time periods in each high-efficiency operation time period group to obtain the high-efficiency time period number value sequence of all the high-efficiency operation time period groups;

[0080] For example, if there is a high-efficiency time period sequence of [1-3 o'clock, 3-5 o'clock, 7-9 o'clock, 9-11 o'clock], it can be integrated into two high-efficiency time period groups: [1-5 o'clock] and [7-11 o'clock];

[0081] And sum and average the values ​​in the sequence of the number of efficient time periods to obtain the mean number of efficient time periods;

[0082] Calculate the difference between each value in the high-efficiency period quantity value sequence and the mean value of the high-efficiency period quantity, take the absolute value of the obtained difference, and obtain the high-efficiency quantity deviation value;

[0083] Compare the high-efficiency quantity deviation value with the high-efficiency quantity deviation limit value, extract the high-efficiency time period group whose high-efficiency quantity deviation value is less than or equal to the high-efficiency quantity deviation limit value, mark it as the concentrated high-efficiency time period group, and count the number of concentrated high-efficiency time period groups, and then calculate the ratio with the total number of high-efficiency time period groups to obtain the high-efficiency concentrated quantity ratio;

[0084] Extract the maximum and minimum values ​​in the sequence of the number of efficient time periods, calculate the difference, and calculate the ratio of the difference to the mean number of efficient time periods to obtain the efficient value change ratio;

[0085] The weighted sum of the high-efficiency concentration ratio and the high-efficiency value change ratio is calculated to obtain the regularity characterization value of the high-efficiency time period group;

[0086] Integrate the continuous inefficient operation time periods to obtain an inefficient operation time period group, and count the number of inefficient time periods in each inefficient operation time period group to obtain a sequence of inefficient time period number values ​​for all inefficient operation time period groups;

[0087] And sum and average the values ​​in the sequence of inefficient time period quantity values ​​to obtain the mean value of inefficient time period quantity;

[0088] Calculate the difference between each value in the inefficient period quantity value sequence and the mean value of the inefficient period quantity, take the absolute value of the difference, and obtain the inefficient quantity deviation value;

[0089] Compare the inefficient quantity deviation value with the inefficient quantity deviation limit value, extract the efficient time period group whose inefficient quantity deviation value is less than or equal to the inefficient quantity deviation limit value, mark it as the concentrated inefficient time period group, and count the number of concentrated inefficient time period groups, and then calculate the ratio with the total number of inefficient time period groups to obtain the inefficient concentrated quantity ratio;

[0090] Extract the maximum and minimum values ​​in the sequence of inefficient time period quantities, calculate the difference, and calculate the ratio of the difference to the mean value of the inefficient time period to obtain the inefficient value change ratio;

[0091] The weighted sum of the inefficient concentration quantity ratio and the inefficient value change ratio is calculated to obtain the regularity representation value of the inefficient time period group;

[0092] The law characterization value of the efficient time period group and the law characterization value of the inefficient time period group are weighted and summed to obtain the law judgment coefficient;

[0093] Set the regularity judgment coefficient threshold. If the regularity judgment coefficient is less than the regularity judgment coefficient threshold, it means that the high-efficiency period and the low-efficiency period appear regularly in the historical data, and a regularity signal is generated.

[0094] If the regularity judgment coefficient is greater than or equal to the regularity judgment coefficient threshold, it means that the high-efficiency period and the low-efficiency period do not appear regularly in the historical data, and an irregular signal is generated;

[0095] The purpose of determining whether the occurrence time of high-efficiency period and low-efficiency period is regular is to facilitate the subsequent prediction of high-efficiency period and low-efficiency period. At the same time, the prediction method can be selected according to the regularity results to arrange the operation of axial flow fan more accurately, reduce the speed of axial flow fan or adjust the blade angle during the low-efficiency period, reduce unnecessary mechanical energy input, effectively avoid the waste of electric energy in the operation process that cannot be efficiently converted into electric energy, and reduce the ineffective energy consumption of the fan during the low-output period.

[0096] In addition to predicting future high-efficiency and low-efficiency periods, practitioners in this field can also compare and judge the regularity of high-efficiency and low-efficiency periods with other wind turbines, thereby discovering the advantages and disadvantages of the wind turbine in terms of operation and management, and optimizing scheduling to achieve energy saving and efficiency improvement of the entire wind power generation system, and improve the coordinated energy saving level of axial flow fans among different units;

[0097] Step 3: Based on the results of regularity analysis and judgment, the operation status of the wind turbine generator set in the future period is predicted;

[0098] In some embodiments, based on generating a regular signal, obtaining an average number of efficient time periods and an average number of inefficient time periods, and using the average number of efficient time periods and the average number of inefficient time periods as the number of intervals;

[0099] Based on the number of intervals, the operation status of future periods is predicted;

[0100] For example, if the average number of efficient time periods is 3 and the average number of inefficient time periods is 1, the predicted operating state sequence of the wind turbine generator set is: {efficient, efficient, efficient, inefficient, efficient, efficient, efficient, inefficient, ...};

[0101] Based on the generated irregular signal, the moving average method is used to predict the state of the wind turbine generator set in the future period. The specific process is as follows:

[0102] Set the window size k of the moving average method. The selection of the window size k needs to be adjusted according to the characteristics of the data and experience. Generally, it can be different values. Observe the prediction effect and select a suitable value, such as k=5 or k=7;

[0103] Obtain the historical operating status data of the wind turbine generator set, that is, {s1, s2, …, s m}, where s j Represents the operating status data of the jth period, where 1 represents an efficient period and 0 represents an inefficient period;

[0104] Moving average M j The calculation formula is: Where, j = 1, 2, ..., m-k+1;

[0105] Among them, p represents the sum index variable, which is used to traverse the data points in the interval from j+k-1 to the corresponding s p Sum, j represents the starting position index of the moving average calculation, m is the total number of historical operating status data, S p Indicates the pth running status data;

[0106] Set the prediction threshold, where 1 represents an efficient period and 0 represents an inefficient period, then the prediction threshold can be set to 0.5;

[0107] If the moving average value is greater than the prediction threshold, the prediction period is marked as an efficient period; if the moving average value is less than or equal to the prediction threshold, the prediction period is marked as an inefficient period;

[0108] The window size k of the moving average method can be adjusted according to data characteristics and experience. In different wind power generation scenarios, the change patterns and fluctuations of data are different. By flexibly adjusting the window size, it can better adapt to different data characteristics, for example, based on the number of efficient time period groups and inefficient time period groups.

[0109] The specific process is as follows: by calculating the fluctuation impact factor and the comprehensive impact factor of concentrated changes, the adjustment coefficient is obtained;

[0110] Furthermore, the fluctuation factor F B The calculation formula is: Among them, bcg and jzg represent the standard deviation of the number of efficient time period groups and the mean number of efficient time periods, respectively; bcd and jzd represent the standard deviation of the number of inefficient time period groups and the mean number of inefficient time periods, respectively;

[0111] Comprehensive impact factor of concentration change F JB The calculation formula is: JB =a1*rjg+a2*rjd-b1*rbg-b2*rbd, where a1, a2, b1, b2 are weight coefficients, rjg and rbg represent the ratio of efficient concentration quantity and the ratio of efficient value change, rjd and rbd represent the ratio of inefficient concentration quantity and the ratio of inefficient value change;

[0112] Calculate the ratio of the comprehensive impact factor of concentrated changes to the fluctuation impact factor to obtain the adjustment coefficient C;

[0113] It should be noted that since the calculation process is based on irregular signals, the fluctuation impact factor is not zero;

[0114] If the initial window is K0, the window after adjustment based on the number of efficient time period groups and inefficient time period groups is KT, and the calculation formula of window KT is: KT = K0*(1+C);

[0115] If the adjustment coefficient is greater than zero, the window increases, and if the adjustment coefficient is less than zero, the window decreases;

[0116] It should be noted that, in practical applications, a large amount of historical data is used to repeatedly test and optimize the weight coefficients a1, a2, b1, and b2 in the above formula to ensure that the adjustment coefficients can accurately adjust the window size of the moving average method according to different wind power generation scenarios, thereby improving the accuracy of the prediction of the future operating status of the wind turbine generator set;

[0117] Under irregular signals, the operating status of wind turbines has no obvious regularity. Adjusting the window size can flexibly deal with this situation. According to data characteristics such as the number of high-efficiency time period groups and low-efficiency time period groups, the window is dynamically adjusted. When the number of high-efficiency and low-efficiency time period groups fluctuates greatly, the window is reduced. When the number is relatively stable, the window is increased, thereby improving the adaptability of the prediction to irregular data and making the prediction results more reliable.

[0118] Frequent starting and stopping of axial flow fans will increase energy consumption and shorten equipment life due to high current shock and mechanical stress changes at the moment of starting. With the help of accurate prediction of high-efficiency and low-efficiency periods, the start and stop time of the fan can be reasonably planned to avoid unnecessary starts, reduce the high energy consumption stage during the startup process, and reduce the additional energy loss caused by frequent starting and stopping of equipment;

[0119] Based on the prediction of the operating status in the future period, the operation of the axial flow fan can be reasonably planned and controlled, such as reducing the fan speed, adjusting the blade angle, and reducing the number of operations during the inefficient period;

[0120] The technical solution of the embodiment of the present invention is mainly as follows: first, historical data is divided into time periods, the power deviation ratio and discrete characterization value of each time period are calculated, and then the operation efficiency judgment coefficient is obtained, and the high-efficiency operation time period and the low-efficiency operation time period are determined according to the coefficient, and then the regular characterization value of the high-efficiency time period group and the regular characterization value of the low-efficiency time period group are respectively calculated for the integrated continuous high-efficiency and low-efficiency time periods, and the weighted sum of the two is obtained to obtain the regularity judgment coefficient, and a regular signal or an irregular signal is generated according to the comparison result with the regularity judgment coefficient threshold, and finally, based on the regular signal, the future operation state is predicted with the mean value of the number of high-efficiency time periods and the mean value of the number of low-efficiency time periods as the interval number, and based on the irregular signal, the future operation state is predicted by the moving average method;

[0121] This makes it possible to accurately determine high-efficiency and low-efficiency periods, and rationally plan the operation of axial flow fans. During low-efficiency periods, the fan speed can be reduced, the blade angle can be adjusted, the number of operations can be reduced, mechanical energy input can be reduced, electricity waste can be avoided, and ineffective energy consumption during low-output periods can be reduced. At the same time, accurate prediction of high-efficiency and low-efficiency periods can help rationally plan the start and stop times of fans, reduce the number of unnecessary starts, avoid high current shocks and mechanical stress changes at the moment of startup, and reduce additional energy losses caused by frequent start and stop of equipment.

[0122] Embodiment 2:

[0123] Based on Example 1, please refer to Figure 2 As shown, an axial flow fan energy-saving control system of a wind turbine generator set according to an embodiment of the present invention specifically includes:

[0124] Operation status determination module: obtains the operation parameters of the wind turbine generator set in historical data, and performs time period analysis to determine the high-efficiency and low-efficiency operation periods of the wind turbine generator set;

[0125] Regularity recognition module: Based on the judgment results of the wind turbine generator set's high-efficiency and low-efficiency operation periods, regularity analysis and regularity judgment are performed;

[0126] Operation status prediction module: Based on the regularity judgment results, the operation status of the wind turbine generator set in the future period is predicted.

[0127] 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 method for energy-saving control of an axial flow fan of a wind turbine generator set, characterized in that: The specific steps include: Obtaining the operating parameters of the wind turbine generator set in the historical data, and performing time period analysis to determine the operating status of the wind turbine generator set, wherein the operating status includes an efficient operating period and an inefficient operating period; Based on the determined operating status of the wind turbine generator set, regularity analysis and judgment are performed to generate regular signals and irregular signals; Based on the regularity analysis and judgment results, the operation status of the wind turbine generator set in the future period is predicted, and based on the status prediction results in the future period, the axial flow fan is controlled.

2. The energy-saving control method for an axial flow fan of a wind turbine generator set according to claim 1, characterized in that: The process of determining the operating status of the wind turbine generator set is as follows: The operating parameters in the historical data are historical output power data, and the historical data are divided into several time intervals, with each time interval being a period; By analyzing the historical output power sequence {P1, P2, ..., P n }Process and calculate to obtain the power deviation ratio and discreteness value of each time period; The power deviation ratio and the discrete degree value are processed to obtain the operating efficiency judgment coefficient; The time period when the operation efficiency judgment coefficient is less than the operation efficiency judgment coefficient threshold is marked as the high-efficiency operation period, and the time period when the operation efficiency judgment coefficient is greater than or equal to the operation efficiency judgment coefficient threshold is marked as the low-efficiency operation period.

3. The energy-saving control method for an axial flow fan of a wind turbine generator set according to claim 2, characterized in that: The process of obtaining the power deviation ratio is as follows: The historical output power data of each time period are summed and averaged to obtain the power mean, and the difference between the power mean and the rated power of the wind turbine is calculated. The absolute value of the difference is taken and the ratio is calculated with the rated power of the wind turbine to obtain the power deviation ratio.

4. The energy-saving control method for an axial flow fan of a wind turbine generator set according to claim 3, characterized in that: The process of obtaining the discrete degree value is as follows: The maximum and minimum output power values ​​in the historical output power data of each period are extracted for difference calculation to obtain the output power range. By formula: The discrete characterization value LS is calculated, where P max-min It indicates that the output power is very poor. The power mean, P i represents the i-th historical output power value in the historical output power value sequence, n represents the number of historical output power values, and PJ represents the average of all adjacent output power values ​​of the i-th historical output power value.

5. The energy-saving control method for an axial flow fan of a wind turbine generator set according to claim 1, characterized in that: The process of regularity analysis and judgment is as follows: By processing and calculating the efficient operation period and the inefficient operation period, the regular characterization value of the efficient period group and the regular characterization value of the inefficient period group are obtained respectively; Perform weighted calculation on the regularity characterization value of the efficient time period group and the regularity characterization value of the inefficient time period group to obtain the regularity judgment coefficient; If the regularity judgment coefficient is less than the regularity judgment coefficient threshold, a regularity signal is generated; if the regularity judgment coefficient is greater than or equal to the regularity judgment coefficient threshold, an irregularity signal is generated.

6. The energy-saving control method for an axial flow fan of a wind turbine generator set according to claim 5, characterized in that: The process of obtaining the regularity characterization value of the efficient time period group is as follows: Integrate the continuous high-efficiency operation time periods to obtain a high-efficiency operation time period group; Count the number of efficient time periods in each efficient time period group, obtain the efficient time period number value sequence of all efficient time period groups, and perform mean processing to obtain the mean value of the number of efficient time periods; Calculate the difference between each value in the high-efficiency period quantity value sequence and the mean value of the high-efficiency period quantity, take the absolute value of the difference, and obtain the high-efficiency quantity deviation value; Extract the high-efficiency time period groups whose high-efficiency quantity deviation value is less than or equal to the high-efficiency quantity deviation limit value, mark them as concentrated high-efficiency time period groups, and count their number, and then calculate the ratio with the total number of high-efficiency time period groups to obtain the high-efficiency concentrated quantity ratio; Extract the maximum and minimum values ​​in the sequence of the number of efficient time periods, calculate the difference, and calculate the ratio of the difference to the mean number of efficient time periods to obtain the efficient value change ratio; The weighted sum of the high-efficiency concentrated quantity ratio and the high-efficiency value change ratio is calculated to obtain the regular characterization value of the high-efficiency time period group.

7. The energy-saving control method for an axial flow fan of a wind turbine generator set according to claim 6, characterized in that: The process of obtaining the regular characterization value of the inefficient time period group is as follows: Integrate the continuous inefficient operation time periods to obtain an inefficient operation time period group, and count the number of inefficient time periods in each inefficient operation time period group to obtain a sequence of inefficient time period number values ​​for all inefficient operation time period groups; And sum and average the values ​​in the sequence of inefficient time period quantity values ​​to obtain the mean value of inefficient time period quantity; Calculate the difference between each value in the inefficient period quantity value sequence and the mean value of the inefficient period quantity, take the absolute value of the difference, and obtain the inefficient quantity deviation value; Compare the inefficient quantity deviation value with the inefficient quantity deviation limit value, extract the efficient time period group whose inefficient quantity deviation value is less than or equal to the inefficient quantity deviation limit value, mark it as the concentrated inefficient time period group, and count its quantity, and then calculate the ratio with the total quantity of the inefficient time period group to obtain the inefficient concentrated quantity ratio; Extract the maximum and minimum values ​​in the sequence of inefficient time period quantities, calculate the difference, and calculate the ratio of the difference to the mean value of the inefficient time period to obtain the inefficient value change ratio; The weighted sum of the inefficient concentration quantity ratio and the inefficient value change ratio is calculated to obtain the regular characterization value of the inefficient time period group.

8. The energy-saving control method for an axial flow fan of a wind turbine generator set according to claim 7, characterized in that: The process of predicting the operation status of the wind turbine generator set in the future period is as follows: Based on the regular signal, the mean number of efficient time periods and the mean number of inefficient time periods are obtained, and the mean number of efficient time periods and the mean number of inefficient time periods are used as the interval number. Based on the operation status of the current time period and the interval number, the operation status of the future time period is obtained; Based on irregular signals, the moving average method is used to predict the operating status in future periods.

9. The energy-saving control method for an axial flow fan of a wind turbine generator set according to claim 8, characterized in that: The prediction method based on irregular signals is: Setting a window size k of the moving average method, wherein the window size k is adjusted based on an adjustment coefficient; Obtain the historical operating status data of the wind turbine generator set, that is, {s1, s2, …, s m }, where s j Represents the operating status data of the jth period; Moving average M j The calculation formula is: Where, j = 1, 2, ..., m-k+1; Among them, p represents the sum index variable, which is used to traverse the data points in the interval from j+k-1, and then the corresponding s p Sum, j represents the starting position index of the moving average calculation, m is the total number of historical operating status data, S p Indicates the pth running status data; If the moving average value is greater than the prediction threshold, the prediction period is marked as an efficient period. If the moving average value is less than or equal to the prediction threshold, the prediction period is marked as an inefficient period.

10. The energy-saving control method for an axial flow fan of a wind turbine generator set according to claim 9, characterized in that: The process of obtaining the adjustment coefficient is as follows: Fluctuation Factor F B The calculation formula is: Among them, bcg and jzg represent the standard deviation of the number of efficient time period groups and the mean number of efficient time periods, respectively; bcd and jzd represent the standard deviation of the number of inefficient time period groups and the mean number of inefficient time periods, respectively; Comprehensive impact factor of concentration change F JB The calculation formula is: JB =a1*rjg+a2*rjd-b1*rbg-b2*rbd, where a1, a2, b1, b2 are weight coefficients, rjg and rbg represent the ratio of efficient concentration quantity and the ratio of efficient value change, rjd and rbd represent the ratio of inefficient concentration quantity and the ratio of inefficient value change; The adjustment coefficient is obtained by calculating the ratio of the comprehensive impact factor of concentrated changes to the fluctuation impact factor.

Images