A method for estimating the life of supercapacitors used in wind farm pitch control

Abstract

The present invention provides a method for estimating the life of a supercapacitor for variable pitch use in a wind farm, comprising: using wind farm environmental big data to collect big data information on wind direction and wind force throughout the year and supercapacitor environmental big data information; intelligently predicting wind farm operating status information based on the big data information on wind direction and wind force throughout the year and supercapacitor environmental big data information to obtain wind farm operating status prediction information; analyzing the estimated charging and discharging use conditions of the supercapacitor for variable pitch use in the wind farm based on the wind farm operating status prediction information; estimating the life of the supercapacitor for variable pitch use in the wind farm based on the estimated charging and discharging use conditions of the capacitor in combination with real-time status monitoring parameter information of the supercapacitor.

Description

Technical Field

[0001] The present invention relates to the technical field of new energy intelligent prediction, and more specifically, to a method for estimating the life of a supercapacitor used for variable pitch in a wind farm. Background Art

[0002] At present, the most advanced energy storage method for wind turbines is to use supercapacitors. Supercapacitors are more convenient to use than lead-acid batteries and are used to provide power for blade pitch change when the generator stops working. However, in order to ensure the starting and operation of the pitch motor, the battery pack must be able to provide sufficient voltage and current. Therefore, the battery is required to have good rate performance, especially in severe low temperature conditions, which will place higher requirements on battery performance; regular manual emergency pitch change and regular inspection of capacity internal resistance of supercapacitors, and life prediction is a relatively key technology; energy storage units widely used in pitch change are usually difficult to be maintenance-free throughout the life cycle of the wind turbine, and it is necessary to accurately estimate the life of supercapacitors used for wind farm pitch change; therefore, it is necessary to propose a method for estimating the life of supercapacitors used for wind farm pitch change to at least partially solve the problems existing in the prior art. Summary of the invention

[0003] A series of simplified concepts are introduced in the content of the invention, which will be further described in detail in the specific implementation method section; the content of the invention of the present invention does not mean to attempt to limit the key features and essential technical features of the technical solution claimed for protection, nor does it mean to attempt to determine the scope of protection of the technical solution claimed for protection.

[0004] In order to at least partially solve the above problems, the present invention provides a method for estimating the life of a supercapacitor for variable pitch operation in a wind farm, comprising:

[0005] S100, uses wind farm environmental big data to collect wind direction and wind force big data information of the wind farm throughout the year and supercapacitor environmental big data information;

[0006] S200, intelligently predicting wind farm operation status information based on the annual wind direction and wind force big data information and supercapacitor environment big data information, and obtaining wind farm operation status prediction information;

[0007] S300, analyzing the estimated charging and discharging conditions of the supercapacitor used for pitch control in the wind farm according to the wind farm operation status prediction information;

[0008] S400 estimates the life of supercapacitors used for wind farm pitch control based on the estimated charging and discharging conditions of the capacitors and combined with the real-time status monitoring parameter information of the supercapacitors.

[0009] Preferably, the S100 includes:

[0010] S101, selecting meteorological satellite cloud image data of a wind farm region where the wind farm is located through a meteorological satellite cloud image;

[0011] S102, obtaining wind farm environment big data of the area where the wind farm is located in the meteorological environment big data according to the meteorological satellite cloud image data of the wind farm area;

[0012] S103, screening the big data information of wind direction and wind force of the wind farm throughout the year and the big data information of supercapacitor environment in the big data of wind farm environment and performing statistics to obtain the big data information of wind direction and wind force of the wind farm throughout the year and supercapacitor environment.

[0013] Preferably, the S200 includes:

[0014] S201, establishing a dynamic prediction model of wind farm operation fitting characteristics for predicting wind farm operation status;

[0015] S202, inputting the annual wind direction and wind force and supercapacitor environment big data information into the fitting characteristic dynamic prediction model for rolling optimization, and obtaining the fitting characteristic dynamic rolling optimization data;

[0016] S203, dynamically rolling and optimizing data through fitting characteristics, intelligently predicting wind farm operation status information, and obtaining wind farm operation status prediction information.

[0017] Preferably, the S300 includes:

[0018] S301, performing wind farm pitch change prediction and estimation according to wind farm operation status prediction information, and obtaining wind farm pitch change prediction and estimation data;

[0019] S302, analyzing the estimated charging and discharging conditions of the supercapacitor used for wind farm pitch control according to the wind farm pitch control prediction and estimation data;

[0020] S303, the estimated charging and discharging usage condition of the capacitor includes: the estimated charging and discharging times, the estimated charging and discharging cycles and the estimated charging and discharging capacity.

[0021] Preferably, the S400 includes:

[0022] S401, presetting estimated charge and discharge state parameters of the supercapacitor according to the estimated charge and discharge usage conditions of the capacitor;

[0023] S402, performing actual parameter weight machine learning on the estimated charge and discharge state parameters and the supercapacitor real-time state monitoring parameters, and performing loop feedback to predict interference errors;

[0024] S403, performing predicted interference error correction compensation according to the loop feedback predicted interference error, and accurately estimating the life of the supercapacitor used for pitch control in the wind farm.

[0025] Preferably, the S103 includes:

[0026] S1031, filtering the wind farm environmental big data and the supercapacitor environmental big data information of the wind farm's annual wind direction and wind force through big data cleaning and screening;

[0027] S1032, performing data statistics on the wind direction and wind force big data information of the wind farm throughout the year and the supercapacitor environment big data information to obtain wind direction and wind force statistical information and supercapacitor environment statistical information;

[0028] S1033, storing the wind direction and wind force statistical information and the supercapacitor environment statistical information into the system database, and obtaining the wind direction and wind force and supercapacitor environment big data information of the wind farm throughout the year.

[0029] Preferably, the S201 includes:

[0030] S2011, taking the daily operation of the wind farm in the region throughout the year as the state prediction cycle, establish the prediction model input data sequence;

[0031] S2012, according to the prediction model input data sequence, the annual wind direction and wind force big data information of the area where the wind farm is located and the super capacitor environment big data information are serialized and grouped into input data;

[0032] S2013, according to the input data serialization grouping, set the wind farm operation status serialization grouping, establish the input data serialization grouping and the wind farm operation status serialization grouping corresponding to the input data sequence of the wind farm operation status serialization grouping; the frequency of wind direction and wind force changes and the severity of supercapacitor environment changes and the stability of the wind farm operation status form a cross-influence inverse relationship of multiple factors affecting multiple operation states; the cross-influence inverse relationship of multiple factors affecting multiple operation states includes: when the severity of supercapacitor environment change is within the required range of the supercapacitor environment, the main factor is the wind direction and wind force change factor; when the severity of supercapacitor environment change exceeds the required range of the supercapacitor environment, the main factor is the supercapacitor environment change factor; according to the cross-influence inverse relationship of multiple factors affecting multiple operation states, a dynamic prediction model of the fitting characteristics of wind farm operation for predicting the wind farm operation status is established.

[0033] Preferably, the S301 includes:

[0034] S3011, performing operation state prediction and pitch change prediction judgment on the wind farm operation state prediction information according to the wind farm operation state prediction information;

[0035] S3012, performing operation state prediction and pitch change prediction judgment includes: when the operation state prediction exceeds the operation state change range set by the system, executing the pitch change action of the wind turbine group in the wind farm; and adjusting the pitch change action amplitude of the wind turbine group in the wind farm according to the state change range interval in which the operation state prediction exceeds the operation state change range set by the system; obtaining the operation state prediction and pitch change prediction judgment results through the operation state prediction and pitch change prediction judgment;

[0036] S3013, performing wind farm pitch change prediction estimation according to the operation state prediction and pitch change prediction judgment results, and obtaining wind farm pitch change prediction estimation data.

[0037] Preferably, the S402 includes:

[0038] S4021, establishing an actual parameter weighted cyclic machine learning model for estimating charging and discharging state parameters and supercapacitor real-time state monitoring parameters;

[0039] S4022, inputting the estimated charge and discharge state parameters and the supercapacitor real-time state monitoring parameters into the actual parameter weight cycle machine learning model to perform actual parameter weight machine learning;

[0040] S4023, during the actual parameter weight machine learning process, the cyclic feedback prediction mechanism of the actual parameter weight cyclic machine learning model is used to cyclically predict the interference error.

[0041] Preferably, the S403 includes:

[0042] S4031, using the loop feedback prediction interference error data as index data and the error correction compensation experience data as basic data, establishing an error correction compensation experience database;

[0043] S4032, calling predicted interference error correction compensation data of the loop feedback predicted interference error index through the loop feedback predicted interference error data index;

[0044] S4033, performing predicted interference error correction compensation by predicting interference error correction compensation data, and accurately estimating the life of supercapacitors used for pitch control in wind farms.

[0045] Compared with the prior art, the present invention has at least the following beneficial effects:

[0046] The beneficial effects of the above technical solution are as follows: the present invention provides a method for estimating the life of supercapacitors for variable pitch of wind farms, comprising: using wind farm environmental big data to collect statistics on wind direction and wind force big data information and supercapacitor environmental big data information of the wind farm throughout the year; intelligently predicting the operation status information of the wind farm based on the wind direction and wind force big data information and supercapacitor environmental big data information throughout the year, and obtaining wind farm operation status prediction information; analyzing the estimated charging and discharging use conditions of the supercapacitors for variable pitch of wind farms based on the wind farm operation status prediction information; estimating the life of supercapacitors for variable pitch of wind farms based on the estimated charging and discharging use conditions of the capacitors and the real-time state monitoring parameter information of the supercapacitors; being able to select regional meteorological satellite cloud map data of the wind farm where the wind farm is located through meteorological satellite cloud maps; obtaining the wind farm environmental big data of the wind farm where the wind farm is located in the meteorological environment big data based on the regional meteorological satellite cloud map data of the wind farm; screening the wind direction and wind force big data information and supercapacitor environmental big data information of the wind farm throughout the year in the wind farm environmental big data and performing statistics to obtain the wind direction and wind force and supercapacitor environmental big data information of the wind farm throughout the year; establishing a wind A dynamic prediction model of the fitting characteristics of wind farm operation for predicting the operation status of the wind farm; inputting the big data information of wind direction, wind force and supercapacitor environment throughout the year into the dynamic prediction model of the fitting characteristics for rolling optimization to obtain the dynamic rolling optimization data of the fitting characteristics; intelligently predicting the operation status information of the wind farm through the dynamic rolling optimization data of the fitting characteristics to obtain the prediction information of the operation status of the wind farm; based on the prediction information of the operation status of the wind farm, performing wind farm pitch prediction and estimation to obtain wind farm pitch prediction and estimation data; analyzing the estimated charging and discharging use conditions of the supercapacitor used for wind farm pitch according to the wind farm pitch prediction and estimation data; the estimated charging and discharging use conditions of the capacitor include: predicted estimated charging and discharging times, predicted estimated charging and discharging cycles and predicted estimated charging and discharging capacity; according to the estimated charging and discharging use conditions of the capacitor, presetting the estimated charging and discharging state parameters of the supercapacitor; performing actual parameter weight machine learning on the estimated charging and discharging state parameters and the real-time state monitoring parameters of the supercapacitor, and loop feedback predicting interference errors; based on the loop feedback predicting interference errors, performing predicted interference error correction and compensation to accurately estimate the life of the supercapacitor used for wind farm pitch.

[0047] The present invention discloses a method for estimating the life of a supercapacitor for variable pitch wind farms. Other advantages, objectives and features of the present invention will be partially reflected in the following description, and will also be partially understood by technicians in this field through research and practice of the present invention. BRIEF DESCRIPTION OF THE DRAWINGS

[0048] The accompanying drawings are used to provide a further understanding of the present invention and constitute a part of the specification. Together with the embodiments of the present invention, they are used to explain the present invention and do not constitute a limitation of the present invention. In the accompanying drawings:

[0049] Figure 1This is a step diagram of a method for estimating the life of a supercapacitor for variable pitch use in a wind farm according to the present invention.

[0050] Figure 2 This is a diagram showing an embodiment of a method for estimating the life of a supercapacitor for variable pitch operation in a wind farm according to the present invention.

[0051] Figure 3 This is a diagram of another embodiment of a method for estimating the life of a supercapacitor for variable pitch operation in a wind farm according to the present invention. DETAILED DESCRIPTION

[0052] The present invention will be further described in detail below in conjunction with the accompanying drawings and embodiments so that those skilled in the art can implement the invention with reference to the description. Figure 1-3 As shown, the present invention provides a method for estimating the life of a supercapacitor for variable pitch in a wind farm, comprising:

[0053] S100, uses wind farm environmental big data to collect wind direction and wind force big data information of the wind farm throughout the year and supercapacitor environmental big data information;

[0054] S200, intelligently predicting wind farm operation status information based on the annual wind direction and wind force big data information and supercapacitor environment big data information, and obtaining wind farm operation status prediction information;

[0055] S300, analyzing the estimated charging and discharging conditions of the supercapacitor used for pitch control in the wind farm according to the wind farm operation status prediction information;

[0056] S400 estimates the life of supercapacitors used for wind farm pitch control based on the estimated charging and discharging conditions of the capacitors and combined with the real-time status monitoring parameter information of the supercapacitors.

[0057] The working principle of the above technical solution is: a method for estimating the life of supercapacitors for wind farm pitch control, comprising: using wind farm environmental big data to collect wind direction and wind force big data information and supercapacitor environmental big data information for the whole year of the wind farm; intelligently predicting the operation status information of the wind farm based on the wind direction and wind force big data information and supercapacitor environmental big data information for the whole year, and obtaining wind farm operation status prediction information; analyzing the estimated charging and discharging conditions of the supercapacitors for wind farm pitch control based on the wind farm operation status prediction information; estimating the life of the supercapacitors for wind farm pitch control based on the estimated charging and discharging conditions of the capacitors and the real-time status monitoring parameter information of the supercapacitors.

[0058] The beneficial effects of the above technical solution are as follows: the present invention provides a method for estimating the life of supercapacitors for variable pitch of wind farms, comprising: using wind farm environmental big data to collect statistics on wind direction and wind force big data information and supercapacitor environmental big data information of the wind farm throughout the year; intelligently predicting the operation status information of the wind farm based on the wind direction and wind force big data information and supercapacitor environmental big data information throughout the year, and obtaining wind farm operation status prediction information; analyzing the estimated charging and discharging use conditions of the supercapacitors for variable pitch of wind farms based on the wind farm operation status prediction information; estimating the life of supercapacitors for variable pitch of wind farms based on the estimated charging and discharging use conditions of the capacitors and the real-time state monitoring parameter information of the supercapacitors; being able to select regional meteorological satellite cloud map data of the wind farm where the wind farm is located through meteorological satellite cloud maps; obtaining the wind farm environmental big data of the wind farm where the wind farm is located in the meteorological environment big data based on the regional meteorological satellite cloud map data of the wind farm; screening the wind direction and wind force big data information and supercapacitor environmental big data information of the wind farm throughout the year in the wind farm environmental big data and performing statistics to obtain the wind direction and wind force and supercapacitor environmental big data information of the wind farm throughout the year; establishing a wind A dynamic prediction model of the fitting characteristics of wind farm operation for predicting the operation status of the wind farm; inputting the big data information of wind direction, wind force and supercapacitor environment throughout the year into the dynamic prediction model of the fitting characteristics for rolling optimization to obtain the dynamic rolling optimization data of the fitting characteristics; intelligently predicting the operation status information of the wind farm through the dynamic rolling optimization data of the fitting characteristics to obtain the prediction information of the operation status of the wind farm; based on the prediction information of the operation status of the wind farm, performing wind farm pitch prediction and estimation to obtain wind farm pitch prediction and estimation data; analyzing the estimated charging and discharging use conditions of the supercapacitor used for wind farm pitch according to the wind farm pitch prediction and estimation data; the estimated charging and discharging use conditions of the capacitor include: predicted estimated charging and discharging times, predicted estimated charging and discharging cycles and predicted estimated charging and discharging capacity; according to the estimated charging and discharging use conditions of the capacitor, presetting the estimated charging and discharging state parameters of the supercapacitor; performing actual parameter weight machine learning on the estimated charging and discharging state parameters and the real-time state monitoring parameters of the supercapacitor, and loop feedback predicting interference errors; based on the loop feedback predicting interference errors, performing predicted interference error correction and compensation to accurately estimate the life of the supercapacitor used for wind farm pitch.

[0059] In one embodiment, the S100 includes:

[0060] S101, selecting meteorological satellite cloud image data of a wind farm region where the wind farm is located through a meteorological satellite cloud image;

[0061] S102, obtaining wind farm environment big data of the area where the wind farm is located in the meteorological environment big data according to the meteorological satellite cloud image data of the wind farm area;

[0062] S103, screening the big data information of wind direction and wind force of the wind farm throughout the year and the big data information of supercapacitor environment in the big data of wind farm environment and performing statistics to obtain the big data information of wind direction and wind force of the wind farm throughout the year and supercapacitor environment.

[0063] The working principle of the above technical solution is: select the meteorological satellite cloud map data of the wind farm area where the wind farm is located through the meteorological satellite cloud map; obtain the wind farm environment big data of the wind farm area in the meteorological environment big data according to the meteorological satellite cloud map data of the wind farm area; screen the wind farm's annual wind direction and wind speed big data information and supercapacitor environment big data information in the wind farm environment big data and perform statistics to obtain the wind farm's annual wind direction and wind speed and supercapacitor environment big data information.

[0064] The beneficial effects of the above technical scheme are: selecting meteorological satellite cloud map data of the wind farm area where the wind farm is located through meteorological satellite cloud maps; obtaining the wind farm environment big data of the wind farm area in the meteorological environment big data based on the wind farm area meteorological satellite cloud map data; screening the wind farm's annual wind direction and wind force big data information and supercapacitor environment big data information in the wind farm environment big data and performing statistics to obtain the wind farm's annual wind direction and wind force and supercapacitor environment big data information.

[0065] In one embodiment, the S200 includes:

[0066] S201, establishing a dynamic prediction model of wind farm operation fitting characteristics for predicting wind farm operation status;

[0067] S202, inputting the annual wind direction and wind force and supercapacitor environment big data information into the fitting characteristic dynamic prediction model for rolling optimization, and obtaining the fitting characteristic dynamic rolling optimization data;

[0068] S203, dynamically rolling and optimizing data through fitting characteristics, intelligently predicting wind farm operation status information, and obtaining wind farm operation status prediction information.

[0069] The working principle of the above technical solution is: establish a dynamic prediction model of the fitting characteristics of the wind farm operation for predicting the operating status of the wind farm; input the big data information of wind direction, wind force and supercapacitor environment throughout the year into the dynamic prediction model of the fitting characteristics for rolling optimization, and obtain the dynamic rolling optimization data of the fitting characteristics; through the dynamic rolling optimization data of the fitting characteristics, intelligently predict the operating status information of the wind farm, and obtain the prediction information of the operating status of the wind farm.

[0070] The beneficial effects of the above technical solution are: establishing a dynamic prediction model of the fitting characteristics of wind farm operation for predicting the operating status of the wind farm; inputting the big data information of wind direction, wind force and supercapacitor environment throughout the year into the dynamic prediction model of the fitting characteristics for rolling optimization, and obtaining the dynamic rolling optimization data of the fitting characteristics; through the dynamic rolling optimization data of the fitting characteristics, intelligently predicting the operating status information of the wind farm, and obtaining the prediction information of the operating status of the wind farm.

[0071] In one embodiment, the S300 includes:

[0072] S301, performing wind farm pitch change prediction and estimation according to wind farm operation status prediction information, and obtaining wind farm pitch change prediction and estimation data;

[0073] S302, analyzing the estimated charging and discharging conditions of the supercapacitor used for wind farm pitch control according to the wind farm pitch control prediction and estimation data;

[0074] S303, the estimated charging and discharging usage condition of the capacitor includes: the estimated charging and discharging times, the estimated charging and discharging cycles and the estimated charging and discharging capacity.

[0075] The working principle of the above technical solution is: based on the wind farm operation status prediction information, the wind farm pitch change prediction and estimation are performed to obtain the wind farm pitch change prediction and estimation data; based on the wind farm pitch change prediction and estimation data, the capacitance estimated charging and discharging use conditions of the supercapacitor used for wind farm pitch change are analyzed; the capacitance estimated charging and discharging use conditions include: predicted estimated charging and discharging times, predicted estimated charging and discharging cycles and predicted estimated charging and discharging capacity.

[0076] The beneficial effects of the above technical solution are: based on the wind farm operation status prediction information, the wind farm pitch change prediction and estimation are performed to obtain the wind farm pitch change prediction and estimation data; based on the wind farm pitch change prediction and estimation data, the capacitance estimated charging and discharging use conditions of the supercapacitor used for wind farm pitch change are analyzed; the capacitance estimated charging and discharging use conditions include: predicted estimated charging and discharging times, predicted estimated charging and discharging cycles and predicted estimated charging and discharging capacity.

[0077] In one embodiment, the S400 includes:

[0078] S401, presetting estimated charge and discharge state parameters of the supercapacitor according to the estimated charge and discharge usage conditions of the capacitor;

[0079] S402, performing actual parameter weight machine learning on the estimated charge and discharge state parameters and the supercapacitor real-time state monitoring parameters, and performing loop feedback to predict interference errors;

[0080] S403, performing predicted interference error correction compensation according to the loop feedback predicted interference error, and accurately estimating the life of the supercapacitor used for pitch control in the wind farm.

[0081] The working principle of the above technical solution is: according to the estimated charging and discharging operating conditions of the capacitor, the estimated charging and discharging state parameters of the supercapacitor are pre-set; the estimated charging and discharging state parameters and the real-time state monitoring parameters of the supercapacitor are subjected to actual parameter weight machine learning, and the interference error is predicted through loop feedback; based on the predicted interference error through loop feedback, the predicted interference error correction compensation is performed to accurately estimate the life of the supercapacitor used for variable pitch in wind farms.

[0082] The beneficial effects of the above technical solution are: pre-setting the estimated charging and discharging state parameters of the supercapacitor according to the estimated charging and discharging operating conditions of the capacitor; performing actual parameter weight machine learning on the estimated charging and discharging state parameters and the real-time state monitoring parameters of the supercapacitor, and predicting the interference error through loop feedback; performing predicted interference error correction compensation based on the predicted interference error through loop feedback, and accurately estimating the life of the supercapacitor used for variable pitch in wind farms.

[0083] In one embodiment, the S103 includes:

[0084] S1031, filtering the wind farm environmental big data and the supercapacitor environmental big data information of the wind farm's annual wind direction and wind force through big data cleaning and screening;

[0085] S1032, performing data statistics on the wind direction and wind force big data information of the wind farm throughout the year and the supercapacitor environment big data information to obtain wind direction and wind force statistical information and supercapacitor environment statistical information;

[0086] S1033, storing the wind direction and wind force statistical information and the supercapacitor environment statistical information into the system database, and obtaining the wind direction and wind force and supercapacitor environment big data information of the wind farm throughout the year.

[0087] The working principle of the above technical solution is: through big data cleaning and screening, the wind farm environmental big data of the wind direction and wind force of the wind farm throughout the year and the supercapacitor environmental big data information are screened; the wind direction and wind force big data information of the wind farm throughout the year and the supercapacitor environmental big data information are statistically analyzed to obtain wind direction and wind force statistical information and supercapacitor environmental statistical information; the wind direction and wind force statistical information and the supercapacitor environmental statistical information are stored in the system database to obtain the wind direction and wind force and supercapacitor environmental big data information of the wind farm throughout the year.

[0088] The beneficial effects of the above technical solution are: through big data cleaning and screening, the wind farm environmental big data of the wind direction and wind force of the wind farm throughout the year and the supercapacitor environmental big data information are screened; the wind direction and wind force big data information of the wind farm throughout the year and the supercapacitor environmental big data information are statistically analyzed to obtain wind direction and wind force statistical information and supercapacitor environmental statistical information; the wind direction and wind force statistical information and the supercapacitor environmental statistical information are stored in the system database to obtain the wind direction and wind force and supercapacitor environmental big data information of the wind farm throughout the year.

[0089] In one embodiment, the S201 includes:

[0090] S2011, taking the daily operation of the wind farm in the region throughout the year as the state prediction cycle, establish the prediction model input data sequence;

[0091] S2012, according to the prediction model input data sequence, the annual wind direction and wind force big data information of the area where the wind farm is located and the super capacitor environment big data information are serialized and grouped into input data;

[0092] S2013, according to the input data serialization grouping, set the wind farm operation status serialization grouping, establish the input data serialization grouping and the wind farm operation status serialization grouping corresponding to the input data sequence of the wind farm operation status serialization grouping; the frequency of wind direction and wind force changes and the severity of supercapacitor environment changes and the stability of the wind farm operation status form a cross-influence inverse relationship of multiple factors affecting multiple operation states; the cross-influence inverse relationship of multiple factors affecting multiple operation states includes: when the severity of supercapacitor environment change is within the required range of the supercapacitor environment, the main factor is the wind direction and wind force change factor; when the severity of supercapacitor environment change exceeds the required range of the supercapacitor environment, the main factor is the supercapacitor environment change factor; according to the cross-influence inverse relationship of multiple factors affecting multiple operation states, a dynamic prediction model of the fitting characteristics of wind farm operation for predicting the wind farm operation status is established.

[0093] The working principle of the above technical solution is: taking every day of the whole year in the region where the wind farm is located as the state prediction cycle, establishing a prediction model input data sequence; according to the prediction model input data sequence, the wind direction and wind force big data information and supercapacitor environment big data information of the region where the wind farm is located are input data serialization grouping; according to the input data serialization grouping, the wind farm operation state serialization grouping is set, and the input data sequence of the input data serialization grouping and the wind farm operation state serialization grouping corresponds to the wind farm operation state sequence; the frequency of wind direction and wind force changes and the intensity of supercapacitor environment changes and the stability of the wind farm operation state form a cross-influence inverse relationship of multiple factors affecting multiple operation states; the cross-influence inverse relationship of multiple factors affecting multiple operation states includes: when the intensity of supercapacitor environment changes is within the supercapacitor environment requirement range, the main factor is the wind direction and wind force change factor; when the intensity of supercapacitor environment changes exceeds the supercapacitor environment requirement range, the main factor is the supercapacitor environment change factor; according to the cross-influence inverse relationship of multiple factors affecting multiple operation states, a dynamic prediction model of the fitting characteristics of wind farm operation for predicting the wind farm operation state is established.

[0094] The beneficial effects of the above technical solution are as follows: taking each day of the whole year in the region where the wind farm is located as the state prediction cycle, establishing a prediction model input data sequence; according to the prediction model input data sequence, the wind direction and wind force big data information of the whole year in the region where the wind farm is located and the supercapacitor environment big data information are grouped into input data serialization; according to the input data serialization grouping, the wind farm operation state serialization grouping is set, and the input data sequence of the wind farm operation state serialization grouping corresponds to the wind farm operation state sequence; the frequency of wind direction and wind force changes and the drastic changes in the supercapacitor environment are calculated. The degree of supercapacitor environment change is inversely proportional to the stability of the wind farm operation state, and multiple factors affect multiple operation states in an inversely proportional relationship; the multiple factors affect multiple operation states in an inversely proportional relationship including: when the degree of supercapacitor environment change is within the supercapacitor environment requirement range, the main factor is the wind direction and wind force change factor; when the degree of supercapacitor environment change exceeds the supercapacitor environment requirement range, the main factor is the supercapacitor environment change factor; according to the inversely proportional relationship of multiple factors affecting multiple operation states, a dynamic prediction model of the fitting characteristics of wind farm operation for predicting the wind farm operation state is established.

[0095] In one embodiment, the S301 includes:

[0096] S3011, performing operation state prediction and pitch change prediction judgment on the wind farm operation state prediction information according to the wind farm operation state prediction information;

[0097] S3012, performing operation state prediction and pitch change prediction judgment includes: when the operation state prediction exceeds the operation state change range set by the system, executing the pitch change action of the wind turbine group in the wind farm; and adjusting the pitch change action amplitude of the wind turbine group in the wind farm according to the state change range interval in which the operation state prediction exceeds the operation state change range set by the system; obtaining the operation state prediction and pitch change prediction judgment results through the operation state prediction and pitch change prediction judgment;

[0098] S3013, performing wind farm pitch change prediction estimation according to the operation state prediction and pitch change prediction judgment results, and obtaining wind farm pitch change prediction estimation data.

[0099] The working principle of the above technical solution is: according to the wind farm operation state prediction information, the wind farm operation state prediction information is subjected to operation state prediction and pitch change prediction judgment; the operation state prediction and pitch change prediction judgment include: when the operation state prediction exceeds the system set operation state change range, the wind farm wind turbine group pitch change action is executed; and according to the state change range interval in which the operation state prediction exceeds the system set operation state change range, the wind farm wind turbine group pitch change action amplitude is adjusted; the operation state prediction and pitch change prediction judgment results are obtained through the operation state prediction and pitch change prediction judgment; according to the operation state prediction and pitch change prediction judgment results, the wind farm pitch change prediction estimation is performed to obtain the wind farm pitch change prediction estimation data.

[0100] The beneficial effects of the above technical solution are: based on the wind farm operation state prediction information, the wind farm operation state prediction information is subjected to operation state prediction and pitch change prediction judgment; the operation state prediction and pitch change prediction judgment include: when the operation state prediction exceeds the system set operation state change range, the wind farm wind turbine group pitch change action is executed; and according to the state change range interval in which the operation state prediction exceeds the system set operation state change range, the wind farm wind turbine group pitch change action amplitude is adjusted; the operation state prediction and pitch change prediction judgment results are obtained through the operation state prediction and pitch change prediction judgment; according to the operation state prediction and pitch change prediction judgment results, the wind farm pitch change prediction estimation is performed to obtain the wind farm pitch change prediction estimation data.

[0101] In one embodiment, the S402 includes:

[0102] S4021, establishing an actual parameter weighted cyclic machine learning model for estimating charging and discharging state parameters and supercapacitor real-time state monitoring parameters;

[0103] S4022, inputting the estimated charge and discharge state parameters and the supercapacitor real-time state monitoring parameters into the actual parameter weight cycle machine learning model to perform actual parameter weight machine learning;

[0104] S4023, during the actual parameter weight machine learning process, the cyclic feedback prediction mechanism of the actual parameter weight cyclic machine learning model is used to cyclically predict the interference error.

[0105] The working principle of the above technical solution is: establish an actual parameter weighted cyclic machine learning model for estimating charging and discharging state parameters and supercapacitor real-time state monitoring parameters; input the estimated charging and discharging state parameters and supercapacitor real-time state monitoring parameters into the actual parameter weighted cyclic machine learning model to perform actual parameter weighted machine learning; in the process of performing actual parameter weighted machine learning, the cyclic feedback prediction mechanism of the actual parameter weighted cyclic machine learning model is used to predict the interference error; calculate the power consumption value of the supercapacitor for variable pitch, and the calculation formula is as follows:

[0106]

[0107] Among them, Pqzg is the power consumption value of the supercapacitor for pitch control, Rap is the safety factor value of the wind farm pitch control, Zsd is the speed value of the motor for pitch control, Fjs is the total reduction ratio value of the pitch reducer, Scdw is the total transmission efficiency value of the pitch mechanism, Myp is the blade density value, Vfl is the angular velocity value of the wind wheel, K is the total number of blade equivalent segments, k is the kth segment of the blade equivalent segment, Tm is the maximum moment of inertia of the blade section, Tl is the minimum moment of inertia of the blade section, sin represents sinusoidal operation, w is the pitch torsion angle, and Ld is the length of each blade of the blade equivalent segment; by calculating the power consumption value of the supercapacitor for pitch control, the life estimation of the supercapacitor for pitch control in wind farms can be made more accurate.

[0108] The beneficial effects of the above technical solution are: establishing an actual parameter weighted cyclic machine learning model for estimating charging and discharging state parameters and supercapacitor real-time state monitoring parameters; inputting the estimated charging and discharging state parameters and supercapacitor real-time state monitoring parameters into the actual parameter weighted cyclic machine learning model to perform actual parameter weighted machine learning; in the process of performing actual parameter weighted machine learning, the cyclic feedback prediction mechanism of the actual parameter weighted cyclic machine learning model is used to predict the interference error; calculating the power consumption value of the supercapacitor for variable pitch, where Pqzg is the power consumption value of the supercapacitor for variable pitch, and Rap is the wind The safety factor value of electric field pitch control, Zsd is the speed value of the pitch motor, Fjs is the total reduction ratio value of the pitch reducer, Scdw is the total transmission efficiency value of the pitch mechanism, Myp is the blade density value, Vfl is the angular velocity value of the wind wheel, K is the total number of blade equivalent segments, k is the kth segment of the blade equivalent segment, Tm is the maximum moment of inertia of the blade section, Tl is the minimum moment of inertia of the blade section, sin represents sinusoidal operation, w is the pitch torsion angle, Ld is the length of each blade of the blade equivalent segment; by calculating the power consumption value of the supercapacitor for pitch control, the life estimation of the supercapacitor for pitch control in wind farms can be made more accurate.

[0109] In one embodiment, the S403 includes:

[0110] S4031, using the loop feedback prediction interference error data as index data and the error correction compensation experience data as basic data, establishing an error correction compensation experience database;

[0111] S4032, calling predicted interference error correction compensation data of the loop feedback predicted interference error index through the loop feedback predicted interference error data index;

[0112] S4033, performing predicted interference error correction compensation by predicting interference error correction compensation data, and accurately estimating the life of supercapacitors used for pitch control in wind farms.

[0113] The working principle of the above technical solution is: using the loop feedback predicted interference error data as index data and the error correction compensation experience data as basic data to establish an error correction compensation experience database; through the loop feedback predicted interference error data index, the predicted interference error correction compensation data of the loop feedback predicted interference error index is retrieved; through the predicted interference error correction compensation data, predicted interference error correction compensation is performed to accurately estimate the life of supercapacitors used for variable pitch in wind farms.

[0114] The beneficial effects of the above technical solution are: using the loop feedback predicted interference error data as index data and the error correction compensation experience data as basic data to establish an error correction compensation experience database; using the loop feedback predicted interference error data index to retrieve the predicted interference error correction compensation data of the loop feedback predicted interference error index; using the predicted interference error correction compensation data to perform predicted interference error correction compensation, and accurately estimate the life of supercapacitors used for variable pitch in wind farms.

[0115] Although the embodiments of the present invention have been disclosed as above, they are not limited to the applications listed in the specification and the implementation methods. They can be fully applied to various fields suitable for the present invention. For those familiar with the art, additional modifications can be easily implemented. Therefore, without departing from the general concept defined by the claims and the scope of equivalents, the present invention is not limited to the specific details and the illustrations shown and described herein.

Claims

1. A method for estimating the life of a supercapacitor for wind farm pitch control, characterized in that: include: S100, collecting big data information of wind direction and wind force of the wind farm throughout the year and big data information of supercapacitor environment through big data of wind farm environment; wherein, S100 includes: S101, selecting meteorological satellite cloud image data of a wind farm region where the wind farm is located through a meteorological satellite cloud image; S102, obtaining wind farm environment big data of the area where the wind farm is located in the meteorological environment big data according to the meteorological satellite cloud image data of the wind farm area; S103, selecting and counting the big data information of wind direction and wind force of the wind farm throughout the year and the big data information of supercapacitor environment in the big data of wind farm environment, and obtaining the big data information of wind direction and wind force of the wind farm throughout the year and supercapacitor environment; S200, intelligently predicting wind farm operation status information based on the annual wind direction and wind force big data information and super capacitor environment big data information, and obtaining wind farm operation status prediction information; wherein, S200 includes, S201, establishing a dynamic prediction model of wind farm operation fitting characteristics for predicting wind farm operation status; S202, inputting the annual wind direction and wind force and supercapacitor environment big data information into the fitting characteristic dynamic prediction model for rolling optimization, and obtaining the fitting characteristic dynamic rolling optimization data; S203, dynamically rolling and optimizing data through fitting characteristics, intelligently predicting wind farm operation status information, and obtaining wind farm operation status prediction information; S300, analyzing the estimated charging and discharging conditions of the supercapacitor used for pitch control in the wind farm according to the wind farm operation status prediction information; wherein, S300 includes: S301, performing wind farm pitch change prediction and estimation according to wind farm operation status prediction information, and obtaining wind farm pitch change prediction and estimation data; S302, analyzing the estimated charging and discharging conditions of the supercapacitor used for wind farm pitch control according to the wind farm pitch control prediction and estimation data; S303, the estimated charging and discharging usage conditions of the capacitor include: the estimated charging and discharging times, the estimated charging and discharging cycles, and the estimated charging and discharging capacities; S400, estimating the life of the supercapacitor for wind farm pitch control according to the estimated charging and discharging working conditions of the capacitor and combining the real-time status monitoring parameter information of the supercapacitor; wherein, S400 includes, S401, presetting estimated charge and discharge state parameters of the supercapacitor according to the estimated charge and discharge usage conditions of the capacitor; S402, performing actual parameter weight machine learning on the estimated charge and discharge state parameters and the supercapacitor real-time state monitoring parameters, and performing loop feedback to predict interference errors; S403, performing predicted interference error correction compensation according to the loop feedback predicted interference error, and accurately estimating the life of the supercapacitor used for pitch control in the wind farm.

2. A method for estimating the life of a supercapacitor for pitch control in a wind farm according to claim 1, characterized in that: The S103 includes: S1031, filtering the wind farm environmental big data and the supercapacitor environmental big data information of the wind farm's annual wind direction and wind force through big data cleaning and screening; S1032, performing data statistics on the wind direction and wind force big data information of the wind farm throughout the year and the supercapacitor environment big data information to obtain wind direction and wind force statistical information and supercapacitor environment statistical information; S1033, storing the wind direction and wind force statistical information and the supercapacitor environment statistical information into the system database, and obtaining the wind direction and wind force and supercapacitor environment big data information of the wind farm throughout the year.

3. The method for estimating the life of a supercapacitor for pitch control in a wind farm according to claim 1, characterized in that: The S201 includes: S2011, taking the daily operation of the wind farm in the region throughout the year as the state prediction cycle, establish the prediction model input data sequence; S2012, according to the prediction model input data sequence, the annual wind direction and wind force big data information of the area where the wind farm is located and the super capacitor environment big data information are serialized and grouped into input data; S2013, according to the input data serialization grouping, set the wind farm operation status serialization grouping, establish the input data serialization grouping and the wind farm operation status serialization grouping corresponding to the input data sequence of the wind farm operation status serialization grouping; the frequency of wind direction and wind force changes and the severity of supercapacitor environment changes and the stability of the wind farm operation status form a cross-influence inverse relationship of multiple factors affecting multiple operation states; the cross-influence inverse relationship of multiple factors affecting multiple operation states includes: when the severity of supercapacitor environment change is within the required range of the supercapacitor environment, the main factor is the wind direction and wind force change factor; when the severity of supercapacitor environment change exceeds the required range of the supercapacitor environment, the main factor is the supercapacitor environment change factor; according to the cross-influence inverse relationship of multiple factors affecting multiple operation states, a dynamic prediction model of the fitting characteristics of wind farm operation for predicting the wind farm operation status is established.

4. A method for estimating the life of a supercapacitor for pitch control in a wind farm according to claim 1, characterized in that: The S301 includes: S3011, performing operation state prediction and pitch change prediction judgment on the wind farm operation state prediction information according to the wind farm operation state prediction information; S3012, performing operation state prediction and pitch change prediction judgment includes: when the operation state prediction exceeds the operation state change range set by the system, executing the pitch change action of the wind turbine group in the wind farm; and adjusting the pitch change action amplitude of the wind turbine group in the wind farm according to the state change range interval in which the operation state prediction exceeds the operation state change range set by the system; obtaining the operation state prediction and pitch change prediction judgment results through the operation state prediction and pitch change prediction judgment; S3013, performing wind farm pitch change prediction estimation according to the operation state prediction and pitch change prediction judgment results, and obtaining wind farm pitch change prediction estimation data.

5. The method for estimating the life of a supercapacitor for pitch control in a wind farm according to claim 1, characterized in that: The S402 includes: S4021, establishing an actual parameter weighted cyclic machine learning model for estimating charging and discharging state parameters and supercapacitor real-time state monitoring parameters; S4022, inputting the estimated charge and discharge state parameters and the supercapacitor real-time state monitoring parameters into the actual parameter weight cycle machine learning model to perform actual parameter weight machine learning; S4023, during the actual parameter weight machine learning process, the cyclic feedback prediction mechanism of the actual parameter weight cyclic machine learning model is used to cyclically predict the interference error.

6. The method for estimating the life of a supercapacitor for pitch control in a wind farm according to claim 1, characterized in that: The S403 includes: S4031, using the loop feedback prediction interference error data as index data and the error correction compensation experience data as basic data, establishing an error correction compensation experience database; S4032, calling predicted interference error correction compensation data of the loop feedback predicted interference error index through the loop feedback predicted interference error data index; S4033, performing predicted interference error correction compensation by predicting interference error correction compensation data, and accurately estimating the life of supercapacitors used for pitch control in wind farms.

Images