Management method and system for safety detection information of wind power

Abstract

The invention relates to a management method and system for safety detection information of wind power, and the method comprises the steps: carrying out the abnormality analysis of values of various safety detection parameters in a current management period, and obtaining candidate abnormal values and the abnormality types of the candidate abnormal values; finding out corresponding event information from the event record; determining a target abnormal event matched with the event information and an abnormal type of the target abnormal event; if the exception type of the candidate exception value is consistent with the exception type of the target exception event, the exception is caused by the current exception event; and if the abnormal type of the candidate abnormal value is inconsistent with the abnormal type of the target abnormal event, indicating that the value is abnormal. According to the method, the abnormal value of the data can be effectively identified, and correction and storage management are carried out. And subsequent data use is facilitated.

Description

Technical Field

[0001] The present invention relates to the technical field of digital processing, and in particular to a management method and system for wind power safety detection information. Background Art

[0002] Regular safety inspections are essential to ensure the safe and stable operation of wind farms. Through regular inspections, potential safety hazards and failures of equipment can be discovered in a timely manner, thereby avoiding unexpected downtime or more serious accidents during operation. Regular inspections help maintain the good condition of equipment, extend the service life of equipment, and improve the reliability and stability of equipment. Regular inspections can also detect and deal with equipment problems in a timely manner, which can reduce the repair and replacement costs caused by equipment failures, thereby reducing the overall operation and maintenance costs of wind farms.

[0003] However, due to complex environmental conditions, equipment failures, data processing and human factors, the regular inspection data of wind power stations may have various problems, such as abnormal data values, which will affect the use of data in the later stage. Summary of the invention

[0004] In view of this, an object of the present invention is to provide a method and system for managing safety detection information of wind power, so as to solve the problem of abnormal values ​​that may exist in the periodic detection data of wind power stations.

[0005] In order to achieve the above object, the present invention adopts the following technical solutions:

[0006] A method for managing wind power safety detection information of the present invention comprises the following steps:

[0007] Obtain values ​​of various safety detection parameters and event records of the wind power station stored at multiple time points;

[0008] Performing anomaly analysis on values ​​of various safety detection parameters of the wind power station stored at multiple time points to obtain candidate anomaly values ​​and anomaly types of the candidate anomaly values;

[0009] Determine event information at the same time point as the candidate abnormal value from the event record; and determine a target abnormal event matching the event information and an abnormal type of the target abnormal event based on a pre-built event model;

[0010] Compare the abnormal type of the candidate abnormal value with the abnormal type of the target abnormal event; when the abnormal type of the candidate abnormal value is consistent with the abnormal type of the target abnormal event, take the candidate abnormal value as a normal value; when the abnormal type of the candidate abnormal value is inconsistent with the abnormal type of the target abnormal event, take the candidate abnormal value as an abnormal value;

[0011] Verification management and storage management are performed on the values ​​of the stored multiple safety detection parameters based on the abnormal values.

[0012] In an embodiment of the present application, anomaly analysis is performed on the values ​​of multiple safety detection parameters of a wind power station stored at multiple time points to obtain candidate abnormal values ​​and abnormal types of the candidate abnormal values, including:

[0013] Perform mutation anomaly analysis on the values ​​of each safety detection parameter at multiple time points to obtain mutation anomaly values ​​and mutation anomaly types; perform associated anomaly analysis on the values ​​of the associated safety detection parameters corresponding to each time point to obtain associated anomaly values ​​and associated anomaly types;

[0014] The mutation outlier and the associated outlier are taken as candidate outliers.

[0015] In one embodiment of the present application, mutation anomaly analysis is performed on the values ​​of each safety detection parameter at multiple time points to obtain mutation anomaly values ​​and mutation anomaly types, including:

[0016] Mapping the values ​​of each safety detection parameter at multiple time points into a two-dimensional coordinate system, wherein the horizontal axis of the two-dimensional coordinate system is time, and the vertical axis of the two-dimensional coordinate system is the value of the safety detection parameter;

[0017] Slide along the two-dimensional coordinate system based on a pre-constructed sliding window and a sliding step size, and calculate the variance of all values ​​in the sliding window each time the sliding window is slid;

[0018] The segment where the sliding window is located and whose variance is greater than a preset variance threshold is taken as the target segment;

[0019] Calculate the average value A of the values ​​within the target segment i , and calculate the value D of each value in the target segment ij With the average value A i The deviation rate between them is ρ, ρ=|A i -D ij | / A i , i is the serial number of the target segment, j is the serial number of the value in the target segment i;

[0020] When the deviation rate ρ is greater than the preset deviation rate threshold, and A i -D ij >0, the value i in the target segment i is regarded as abnormal decline; when the deviation rate ρ is greater than the preset deviation rate threshold, and A i -D ij When <0, the value i in the target segment i is regarded as abnormal increase as the abnormal type.

[0021] In one embodiment of the present application, an associated anomaly analysis is performed on the values ​​of the associated security detection parameters corresponding to each time point to obtain an associated anomaly value and an associated anomaly type, including:

[0022] The values ​​of each safety detection parameter at multiple time points are trend-marked, wherein when the value at the current time point is greater than the value at the previous time point, the trend of the value at the current time point is marked as rising; when the value at the current time point is less than the value at the previous time point, the trend of the value at the current time point is marked as falling; when the value at the current time point is equal to the value at the previous time point, the trend of the value at the current time point is marked as maintaining;

[0023] Determining, from the plurality of safety detection parameters, a reference parameter, a reference parameter associated with the reference parameter, and a relation between the reference parameter and the associated parameter based on a pre-constructed relation table, wherein the relation includes a positive correlation and a negative correlation;

[0024] Determine whether the trend marks of the values ​​of the benchmark parameters at multiple time points and the trend marks of the values ​​of the associated parameters at corresponding time points conform to the association relationship; if not, mark the values ​​that do not conform to the association relationship as associated abnormal values, and determine the associated abnormality type.

[0025] In one embodiment of the present application, the correlation relationship between the reference parameter and the associated parameter is positively correlated, the trend mark of the reference parameter is rising, and the trend mark of the associated parameter is falling, and the associated abnormality type is abnormal rise of the reference parameter or abnormal fall of the associated parameter;

[0026] When the correlation relationship between the reference parameter and the associated parameter is positively correlated, the trend of the reference parameter is marked as decreasing, and the trend of the associated parameter is marked as increasing, the associated abnormality type is an abnormal decrease in the reference parameter or an abnormal increase in the associated parameter;

[0027] When the correlation relationship between the reference parameter and the associated parameter is negatively correlated, the trend mark of the reference parameter is rising, and the trend mark of the associated parameter is rising, the associated abnormality type is abnormal rise of the reference parameter or abnormal rise of the associated parameter;

[0028] The correlation relationship between the reference parameter and the associated parameter is negatively correlated, the trend of the reference parameter is marked as decreasing, and when the trend of the associated parameter is marked as decreasing, the associated abnormality type is an abnormal decrease in the reference parameter or an abnormal decrease in the associated parameter.

[0029] In one embodiment of the present application, the method for constructing the association relationship table includes:

[0030] Acquiring historical reference data, wherein the historical reference data includes values ​​of multiple safety detection parameters at multiple historical time points after manual verification;

[0031] Mark the trend of each safety detection parameter at multiple historical time points;

[0032] For all the same historical time points of any two safety detection parameters, when there are historical time points with values ​​exceeding the percentage threshold whose trend marks are the same or opposite, the two safety detection parameters are marked as the baseline parameter and the associated parameter, and the corresponding associated relationship is marked;

[0033] An association relationship table is constructed based on all the benchmark parameters, the associated parameters of the benchmark parameters, and the association relationship between the benchmark parameters and the associated parameters.

[0034] In one embodiment of the present application, the method for constructing the event model includes:

[0035] Obtain historical values ​​of various safety detection parameters and historical event records of wind power stations stored at multiple historical time points;

[0036] Filtering out a target time point corresponding to an abnormal event from the historical event records;

[0037] Determine abnormal values ​​and abnormal types of all safety detection parameters corresponding to the target time point, wherein the abnormal type includes an abnormal increase or abnormal decrease of the target safety detection parameter;

[0038] The abnormal type corresponding to each abnormal event is counted, and the abnormal type whose occurrence frequency exceeds the preset frequency threshold is taken as the abnormal type of the corresponding abnormal event;

[0039] An event model is constructed based on multiple abnormal events and abnormal types of multiple abnormal events.

[0040] In an embodiment of the present application, verification management is performed on the values ​​of the stored multiple safety detection parameters based on the abnormal value, including:

[0041] sending the location of the outlier to a target object;

[0042] When a modification command is received from the target object, the abnormal value is removed to obtain a blank value, and the blank value is interpolated, wherein the modification command is generated based on the position of the abnormal value, and the interpolation method is one of linear interpolation, polynomial interpolation, quadratic interpolation and spline interpolation.

[0043] In an embodiment of the present application, the values ​​of the stored multiple security detection parameters are stored and managed based on the abnormal value, including:

[0044] The verified values ​​of the various safety detection parameters at multiple time points are stored in the target area, and after the target time period, the original values ​​of the various safety detection parameters at multiple time points are cleared.

[0045] The present application also provides a management system for wind power safety detection information, including:

[0046] An acquisition module, used to acquire values ​​of various safety detection parameters and event records of the wind power station stored at multiple time points;

[0047] An abnormality analysis module is used to perform abnormality analysis on the values ​​of various safety detection parameters of the wind power station stored at multiple time points to obtain candidate abnormal values ​​and abnormal types of the candidate abnormal values;

[0048] A matching module, configured to determine event information at the same time point as the candidate abnormal value from the event record; and determine a target abnormal event matching the event information and an abnormal type of the target abnormal event based on a pre-built event model;

[0049] A judgment module, used to compare the abnormal type of the candidate abnormal value with the abnormal type of the target abnormal event; when the abnormal type of the candidate abnormal value is consistent with the abnormal type of the target abnormal event, the candidate abnormal value is used as a normal value; when the abnormal type of the candidate abnormal value is inconsistent with the abnormal type of the target abnormal event, the candidate abnormal value is used as an abnormal value;

[0050] The management module is used to perform verification management and storage management on the values ​​of various stored safety detection parameters based on abnormal values.

[0051] The beneficial effects of the present invention are as follows: a method and system for managing safety detection information for wind power of the present invention first performs an abnormal analysis on the values ​​of multiple safety detection parameters in the current management cycle to obtain candidate abnormal values ​​and abnormal types of candidate abnormal values; finds corresponding event information from event records; determines the target abnormal event that matches the event information and the abnormal type of the target abnormal event; if the abnormal type of the candidate abnormal value is consistent with the abnormal type of the target abnormal event, it means that the abnormality is caused by the abnormal event at that time; if the abnormal type of the candidate abnormal value is inconsistent with the abnormal type of the target abnormal event, it means that the value is abnormal. The present application can effectively identify abnormal values ​​of data, and perform correction and storage management. To facilitate subsequent data use. BRIEF DESCRIPTION OF THE DRAWINGS

[0052] The present invention will be further described below in conjunction with the accompanying drawings and embodiments:

[0053] Figure 1 It is an application scenario diagram of a method for managing safety detection information for wind power shown in an embodiment of the present application;

[0054] Figure 2is a flow chart of a method for managing safety detection information for wind power shown in an embodiment of the present application;

[0055] Figure 3 It is a structural diagram of a management system for wind power safety detection information shown in one embodiment of the present application. DETAILED DESCRIPTION

[0056] The following describes the embodiments of the present invention by specific examples, and those skilled in the art can easily understand other advantages and effects of the present invention from the contents disclosed in this specification. The present invention can also be implemented or applied through other different specific embodiments, and the details in this specification can also be modified or changed in various ways based on different viewpoints and applications without departing from the spirit of the present invention. It should be noted that the following embodiments and features in the embodiments can be combined with each other without conflict.

[0057] It should be noted that the illustrations provided in the following embodiments are only schematic illustrations of the basic concept of the present invention, and thus the drawings only show the layers related to the present invention rather than being drawn according to the number, shape and size of the layers in actual implementation. In actual implementation, the type, quantity and proportion of each layer may be changed arbitrarily, and the layer layout may also be more complicated.

[0058] In the following description, numerous details are discussed to provide a more thorough explanation of embodiments of the present invention; however, it is apparent to one skilled in the art that embodiments of the present invention may be practiced without these specific details.

[0059] Figure 1 is an application scenario diagram of a method for managing wind power safety detection information shown in an embodiment of the present application, such as Figure 1 As shown, various devices and sensors are used in the wind power station to regularly collect the operating parameters of the power station, such as wind speed, blade speed, generator power, generator temperature, generator frequency and voltage, etc. In some cases, data such as ambient temperature and power generation are also collected. The collected data is stored in the temporary storage area of ​​the memory 110, and then the processing device 120 retrieves the data from the temporary storage area of ​​the memory 110 for verification and storage management, and stores the verified data in the long-term storage area of ​​the memory 110. The data in the temporary storage area is cleared regularly. In the present application, management is performed once per cycle, so the amount of data processed by the processing device 120 each time is basically fixed.

[0060] Figure 2 is a flow chart of a method for managing wind power safety detection information shown in an embodiment of the present application. Figure 2As shown: A method for managing safety detection information for wind power in this embodiment may include steps S210 to S250:

[0061] S210, obtaining values ​​of various safety detection parameters and event records of the wind power station stored at multiple time points;

[0062] The values ​​of various safety detection parameters of wind power stations stored at multiple time points are the operating parameters collected regularly during the daily operation of the wind power station, which are generally stored in CSV, JSON and other formats. Event records are files automatically recorded by the management system when some events occur in the wind power station, such as log files.

[0063] S220, performing anomaly analysis on values ​​of various safety detection parameters of the wind power station stored at multiple time points to obtain candidate anomaly values ​​and anomaly types of the candidate anomaly values;

[0064] This application first performs an abnormal analysis on the values ​​of various safety detection parameters to determine whether the abnormal value is too large or too small, so that in the subsequent process, the event information at the corresponding time point can be combined for analysis.

[0065] Specifically, the anomaly types in this application include mutation type and correlation type. The mutation type anomaly is mainly a data point that suddenly becomes larger or smaller. However, for a wind power station, the time interval between adjacent time points is small, so the mutation data is abnormal. In addition, various parameters in a wind power station are correlated, for example, wind speed is positively correlated with power generation, wind speed is positively correlated with generator speed, etc. The changes between these parameters can also be used to verify the data, and the specific process is as follows:

[0066] (1) Perform mutation anomaly analysis on the values ​​of each safety detection parameter at multiple time points to obtain mutation anomaly values ​​and mutation anomaly types, including:

[0067] (1-1) Mapping the values ​​of each safety detection parameter at multiple time points into a two-dimensional coordinate system, wherein the horizontal axis of the two-dimensional coordinate system is time, and the vertical axis of the two-dimensional coordinate system is the value of the safety detection parameter;

[0068] (1-2) sliding along the two-dimensional coordinate system based on a pre-constructed sliding window and a sliding step size, and calculating the variance of all values ​​in the sliding window each time the sliding window is slid;

[0069] The width of the sliding window is generally 1-2 days. The climate and power generation data for 1-2 days are relatively stable, ensuring that the data corresponding to the time point within the sliding window will not change significantly. Each time the sliding window slides, the variance of all values ​​in the sliding window can reflect the stability of the values ​​of the safety detection parameters at multiple time points.

[0070] (1-3) The segment where the sliding window is located and whose variance is greater than a preset variance threshold is taken as the target segment;

[0071] If the variance is large, it means that the value segment of the corresponding security detection parameter at the corresponding position of the sliding window is not very stable, so it can be determined that there are abnormal mutation points inside. At this time, execute the subsequent steps.

[0072] In the above process, the value segment is first extracted based on the sliding window, and then the value stability analysis is performed on each value segment. If it is unstable, the specific abnormal point is determined later. This can effectively improve the efficiency of abnormal point verification.

[0073] (1-4) Calculate the average value A of the values ​​in the target segment i , and calculate the value D of each value in the target segment ij With the average value A i The deviation rate between them is ρ, ρ=|A i -D ij | / A i , i is the serial number of the target segment, j is the serial number of the value in the target segment i;

[0074] (1-5) When the deviation rate ρ is greater than the preset deviation rate threshold, and A i -D ij >0, the value i in the target segment i is regarded as abnormal decline; when the deviation rate ρ is greater than the preset deviation rate threshold, and A i -D ij When <0, the value i in the target segment i is regarded as abnormal increase as the abnormal type.

[0075] For steps (1-4) and (1-5), after determining the target segment, calculate the average value A of the target segment. i , and calculate the deviation rate of each value in the target segment from the average value, and use the deviation rate to evaluate whether each specific value has a mutation abnormality. If the deviation rate is large, it means that the value has a mutation abnormality. And determine whether it is an abnormal rise or an abnormal fall.

[0076] (2) Performing an associated anomaly analysis on the values ​​of the associated security detection parameters corresponding to each time point to obtain associated anomaly values ​​and associated anomaly types, including:

[0077] (2-1) Trend marking is performed on the values ​​of each safety detection parameter at multiple time points, wherein when the value at the current time point is greater than the value at the previous time point, the trend of the value at the current time point is marked as rising; when the value at the current time point is less than the value at the previous time point, the trend of the value at the current time point is marked as falling; when the value at the current time point is equal to the value at the previous time point, the trend of the value at the current time point is marked as maintaining;

[0078] In this application, for any safety detection parameter, the value at the current time point is compared with the value at the previous time point. If the value at the current time point is greater than the value at the previous time point, the trend of the value at the current time point is marked as rising; otherwise, it is marked as falling. Thus, the trend marking of all values ​​is completed.

[0079] (2-2) determining a baseline parameter, an associated parameter of the baseline parameter, and an associated relationship between the baseline parameter and the associated parameter from the plurality of safety detection parameters based on a pre-constructed associated relationship table, wherein the associated relationship includes a positive correlation and a negative correlation;

[0080] The association table is established in advance, and a pair of safety detection parameters (including reference parameters and associated parameters) that are associated are determined by means of data statistics. In this embodiment, multiple parameters are related to wind speed, such as power generation, fan blade speed, etc. Therefore, wind speed is used as the reference parameter.

[0081] The construction process of the association table is as follows:

[0082] (2-2-1) Acquiring historical reference data, wherein the historical reference data includes values ​​of multiple safety detection parameters at multiple historical time points after manual verification;

[0083] The historical reference data is the data generated by the current wind power plant or other wind power plants during their historical operation. Then, the correct data is retained through manual verification, and the error data is eliminated.

[0084] (2-2-2) Mark the trend of the values ​​of each safety detection parameter at multiple historical time points;

[0085] Among them, the method of trend marking is as described above and will not be repeated here.

[0086] (2-2-3) For all identical historical time points of any two safety detection parameters, when there are historical time points where the values ​​exceed the percentage threshold and the trend mark is the same or opposite, the two safety detection parameters are marked as a baseline parameter and an associated parameter, and the corresponding associated relationship is marked;

[0087] If any two safety detection parameters have the same trend mark at 90% of the time points, the two parameters are positively correlated. If any two safety detection parameters have opposite trend marks at 90% of the time points, the two parameters are negatively correlated.

[0088] In this application, in order to reduce the workload of trend annotation statistics, an upward trend is counted as "1" and a downward trend is counted as "0". The trends of two safety detection parameters at the same time point are combined into a two-bit binary number, such as "11", "10", "01" and "00", and then digital statistics can be directly performed.

[0089] (2-2-4) Construct an association relationship table based on all benchmark parameters, associated parameters of benchmark parameters, and association relationships between benchmark parameters and associated parameters.

[0090] (2-3) Determine whether the trend marks of the values ​​of the benchmark parameters at multiple time points and the trend marks of the values ​​of the associated parameters at corresponding time points conform to the association relationship; if not, mark the values ​​that do not conform to the association relationship as associated abnormality values, and determine the associated abnormality type.

[0091] Specifically, the associated exception types include the following four types:

[0092] (a) when the correlation relationship between the reference parameter and the associated parameter is positively correlated, the trend of the reference parameter is marked as rising, and the trend of the associated parameter is marked as falling, the associated anomaly type is an abnormal rise in the reference parameter or an abnormal fall in the associated parameter;

[0093] (b) when the correlation relationship between the reference parameter and the associated parameter is positively correlated, the trend of the reference parameter is marked as decreasing, and the trend of the associated parameter is marked as increasing, the associated anomaly type is an abnormal decrease in the reference parameter or an abnormal increase in the associated parameter;

[0094] (c) when the correlation relationship between the reference parameter and the associated parameter is negatively correlated, the trend mark of the reference parameter is rising, and the trend mark of the associated parameter is rising, the associated anomaly type is abnormal rise of the reference parameter or abnormal rise of the associated parameter;

[0095] (d) When the correlation relationship between the baseline parameter and the associated parameter is negatively correlated, the trend of the baseline parameter is marked as decreasing, and the trend of the associated parameter is marked as decreasing, the associated abnormality type is an abnormal decrease in the baseline parameter or an abnormal decrease in the associated parameter.

[0096] (3) Taking the mutation outlier and the associated outlier as candidate outliers.

[0097] S230, determining event information at the same time point as the candidate abnormal value from the event record; and determining a target abnormal event matching the event information and an abnormal type of the target abnormal event based on a pre-built event model;

[0098] Among them, the event model records various abnormal events of the wind power station, as well as the parameter changes corresponding to the abnormal events (i.e., the abnormal type). For example, blade failure, generator failure, and gearbox failure can cause a sharp drop in the output power of the generator, and in some cases can also cause the temperature of the generator to rise abnormally. In extreme weather, such as storms, thunderstorms, and low-temperature icing, the generator operation may also fail, causing the output power to rise or fall abnormally. The present application constructs an event model by extracting the parameter changes corresponding to historical abnormal events to provide reference data for the abnormal type of the candidate abnormal value at the current time point. Specifically, the method for constructing the event model includes:

[0099] (1) Obtaining historical values ​​of various safety detection parameters and historical event records of the wind power station stored at multiple historical time points;

[0100] (2) Filtering out the target time point corresponding to the abnormal event from the historical event records; wherein the target time point can be determined by manual screening or by querying the event code in the management system.

[0101] (3) determining abnormal values ​​and abnormal types of all safety detection parameters corresponding to the target time point, wherein the abnormal type includes an abnormal increase or abnormal decrease of the target safety detection parameter;

[0102] After filtering out the target time point, find the security detection parameters with abnormal values ​​and determine their abnormal types. Each abnormal event is extracted in this way. To determine whether the value of the security detection parameter is abnormal, you can refer to the mutation anomaly and correlation anomaly mentioned above. You can also judge according to the experience of relevant personnel.

[0103] (4) Counting the abnormal types corresponding to each abnormal event, and taking the abnormal type whose occurrence frequency exceeds a preset frequency threshold as the abnormal type of the corresponding abnormal event;

[0104] For the occurrence of an abnormal event, if it is always (such as 90%) accompanied by an abnormal change of a parameter (such as abnormal increase or abnormal decrease), then the abnormal change of this parameter is the abnormal type of the abnormal event. Thus, multiple abnormal events and their abnormal types can be determined to construct an event model.

[0105] (5) Construct an event model based on multiple abnormal events and abnormal types of multiple abnormal events.

[0106] S240, comparing the abnormality type of the candidate abnormal value with the abnormality type of the target abnormal event; when the abnormality type of the candidate abnormal value is consistent with the abnormality type of the target abnormal event, taking the candidate abnormal value as a normal value; when the abnormality type of the candidate abnormal value is inconsistent with the abnormality type of the target abnormal event, taking the candidate abnormal value as an abnormal value;

[0107] For example, if the generator output power at a certain time point drops abnormally, and event A occurs at the corresponding time point, which causes the power to drop abnormally, then the value of the generator output power at this time point is normal. If event B occurs at the corresponding time point or there is no event information, and event B does not cause the power to drop abnormally, then it can be determined that there is a problem with the data itself. At this time, the value of the generator output power is an abnormal value.

[0108] S250, performing verification management and storage management on the values ​​of the stored multiple safety detection parameters based on the abnormal value, specifically including:

[0109] sending the location of the outlier to a target object;

[0110] When a modification command is received from the target object, the abnormal value is removed to obtain a blank value, and the blank value is interpolated, wherein the modification command is generated based on the position of the abnormal value, and the interpolation method is one of linear interpolation, polynomial interpolation, quadratic interpolation and spline interpolation.

[0111] In this application, the abnormal value is sent to the management personnel. After the management personnel review, if the value is confirmed to be abnormal, the system can modify it through interpolation. It can also be modified manually by the management personnel, and the modification personnel, modification time, original value and modified value are recorded during the modification.

[0112] After the inspection of the current management cycle is completed, the values ​​of the various security detection parameters at multiple time points after verification are stored in the target area, and after the target time period, the original values ​​of the various security detection parameters at multiple time points are cleared.

[0113] This application performs regular verification and storage management of data according to a fixed cycle, which is beneficial to the subsequent use of wind power station data, plays a positive auxiliary role in the management of wind power station data, and can effectively reduce the verification workload of management personnel.

[0114] A management method for safety detection information of wind power of the present invention first performs abnormal analysis on the values ​​of multiple safety detection parameters in the current management cycle to obtain candidate abnormal values ​​and abnormal types of candidate abnormal values; finds corresponding event information from event records; determines the target abnormal event that matches the event information and the abnormal type of the target abnormal event; if the abnormal type of the candidate abnormal value is consistent with the abnormal type of the target abnormal event, it means that the abnormality is caused by the abnormal event at that time; if the abnormal type of the candidate abnormal value is inconsistent with the abnormal type of the target abnormal event, it means that the value is abnormal. The present application can effectively identify abnormal values ​​of data, and perform correction and storage management. To facilitate subsequent data use.

[0115] The present application also provides a management system for wind power safety detection information, including:

[0116] An acquisition module, used to acquire values ​​of various safety detection parameters and event records of the wind power station stored at multiple time points;

[0117] An abnormality analysis module is used to perform abnormality analysis on the values ​​of various safety detection parameters of the wind power station stored at multiple time points to obtain candidate abnormal values ​​and abnormal types of the candidate abnormal values;

[0118] A matching module, configured to determine event information at the same time point as the candidate abnormal value from the event record; and determine a target abnormal event matching the event information and an abnormal type of the target abnormal event based on a pre-built event model;

[0119] A judgment module, used to compare the abnormal type of the candidate abnormal value with the abnormal type of the target abnormal event; when the abnormal type of the candidate abnormal value is consistent with the abnormal type of the target abnormal event, the candidate abnormal value is used as a normal value; when the abnormal type of the candidate abnormal value is inconsistent with the abnormal type of the target abnormal event, the candidate abnormal value is used as an abnormal value;

[0120] The management module is used to perform verification management and storage management on the values ​​of various stored safety detection parameters based on abnormal values.

[0121] A management system for wind power safety detection information of the present invention first performs an abnormal analysis on the values ​​of multiple safety detection parameters in the current management cycle to obtain candidate abnormal values ​​and abnormal types of candidate abnormal values; finds corresponding event information from event records; determines the target abnormal event that matches the event information and the abnormal type of the target abnormal event; if the abnormal type of the candidate abnormal value is consistent with the abnormal type of the target abnormal event, it means that the abnormality is caused by the abnormal event at that time; if the abnormal type of the candidate abnormal value is inconsistent with the abnormal type of the target abnormal event, it means that the value is abnormal. The present application can effectively identify abnormal values ​​of data, and perform correction and storage management. To facilitate subsequent data use.

[0122] This embodiment further provides a computer-readable storage medium on which a computer program is stored. When the program is executed by a processor, any one of the methods in this embodiment is implemented, wherein the method is the execution logic of this system.

[0123] This embodiment also provides an electronic terminal, including: a processor and a memory;

[0124] The memory is used to store a computer program, and the processor is used to execute the computer program stored in the memory, so that the terminal executes any one of the methods in this embodiment.

[0125] The computer-readable storage medium in this embodiment can be understood by ordinary technicians in this field: all or part of the steps of implementing the above-mentioned method embodiments can be completed by hardware related to the computer program. The aforementioned computer program can be stored in a computer-readable storage medium. When the program is executed, the steps of the above-mentioned method embodiments are executed; and the aforementioned storage medium includes: ROM, RAM, magnetic disk or optical disk and other media that can store program codes.

[0126] The electronic terminal provided in this embodiment includes a processor, a memory, a transceiver and a communication interface. The memory and the communication interface are connected to the processor and the transceiver and complete communication with each other. The memory is used to store computer programs, the communication interface is used to communicate, and the processor and the transceiver are used to run computer programs so that the electronic terminal executes each step of the above method.

[0127] In this embodiment, the memory may include a random access memory (RAM), and may also include a non-volatile memory (non-volatile memory), such as at least one disk memory.

[0128] The above-mentioned processor can be a general-purpose processor, including a central processing unit (CPU), a network processor (NP), etc.; it can also be a digital signal processor (DSP), an application specific integrated circuit (ASIC), a field programmable gate array (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components.

[0129] In the above-mentioned embodiments, although the present invention has been described in conjunction with the specific embodiments of the present invention, many replacements, modifications and variations of these embodiments will be apparent to those of ordinary skill in the art based on the foregoing description. The embodiments of the present invention are intended to cover all such replacements, modifications and variations falling within the broad scope of the appended claims.

[0130] The above embodiments are merely illustrative of the principles and effects of the present invention, and are not intended to limit the present invention. Anyone familiar with the art may modify or alter the above embodiments without departing from the spirit and scope of the present invention. Therefore, all equivalent modifications or alterations made by a person of ordinary skill in the art without departing from the spirit and technical concept disclosed by the present invention shall still be covered by the claims of the present invention.

Claims

1. A method for managing safety detection information for wind power, characterized in that: Includes steps: Obtain values ​​of various safety detection parameters and event records of the wind power station stored at multiple time points; Performing anomaly analysis on values ​​of various safety detection parameters of the wind power station stored at multiple time points to obtain candidate anomaly values ​​and anomaly types of the candidate anomaly values; Determine, from the event record, event information at the same time point as the candidate outlier; and determining a target abnormal event matching the event information and an abnormal type of the target abnormal event based on a pre-built event model; Comparing the abnormality type of the candidate abnormal value with the abnormality type of the target abnormal event; when the abnormality type of the candidate abnormal value is consistent with the abnormality type of the target abnormal event, taking the candidate abnormal value as a normal value; When the abnormality type of the candidate abnormal value is inconsistent with the abnormality type of the target abnormal event, taking the candidate abnormal value as the abnormal value; Verification management and storage management are performed on the values ​​of the stored multiple safety detection parameters based on the abnormal values.

2. A method for managing safety detection information for wind power according to claim 1, characterized in that: Anomaly analysis is performed on the values ​​of various safety detection parameters of the wind power station stored at multiple time points to obtain candidate anomaly values ​​and anomaly types of the candidate anomaly values, including: Perform mutation anomaly analysis on the values ​​of each safety detection parameter at multiple time points to obtain mutation anomaly values ​​and mutation anomaly types; perform associated anomaly analysis on the values ​​of the associated safety detection parameters corresponding to each time point to obtain associated anomaly values ​​and associated anomaly types; The mutation outlier and the associated outlier are taken as candidate outliers.

3. A method for managing safety detection information for wind power according to claim 2, characterized in that: Perform mutation anomaly analysis on the values ​​of each safety detection parameter at multiple time points to obtain mutation anomaly values ​​and mutation anomaly types, including: Mapping the values ​​of each safety detection parameter at multiple time points into a two-dimensional coordinate system, wherein the horizontal axis of the two-dimensional coordinate system is time, and the vertical axis of the two-dimensional coordinate system is the value of the safety detection parameter; Slide along the two-dimensional coordinate system based on a pre-constructed sliding window and a sliding step size, and calculate the variance of all values ​​in the sliding window each time the sliding window is slid; The segment where the sliding window is located and whose variance is greater than a preset variance threshold is taken as the target segment; Calculate the average value A of the values ​​within the target segment i , and calculate the value D of each value in the target segment ij With the average value A i The deviation rate between them is ρ, ρ=|A i -D ij | / A i , i is the serial number of the target segment, j is the serial number of the value in the target segment i; When the deviation rate ρ is greater than the preset deviation rate threshold, and A i -D ij >0, the value i in the target segment i is regarded as abnormal decline; when the deviation rate ρ is greater than the preset deviation rate threshold, and A i -D ij When <0, the value i in the target segment i is regarded as abnormal increase as the abnormal type.

4. A method for managing safety detection information for wind power according to claim 2, characterized in that: Perform an associated anomaly analysis on the values ​​of the associated security detection parameters corresponding to each time point to obtain associated anomaly values ​​and associated anomaly types, including: The values ​​of each safety detection parameter at multiple time points are trend-marked, wherein when the value at the current time point is greater than the value at the previous time point, the trend of the value at the current time point is marked as rising; when the value at the current time point is less than the value at the previous time point, the trend of the value at the current time point is marked as falling; when the value at the current time point is equal to the value at the previous time point, the trend of the value at the current time point is marked as maintaining; Determining, from the plurality of safety detection parameters, a reference parameter, a reference parameter associated with the reference parameter, and a relation between the reference parameter and the associated parameter based on a pre-constructed relation table, wherein the relation includes a positive correlation and a negative correlation; Determine whether the trend marks of the values ​​of the benchmark parameters at multiple time points and the trend marks of the values ​​of the associated parameters at corresponding time points conform to the association relationship; if not, mark the values ​​that do not conform to the association relationship as associated abnormal values, and determine the associated abnormality type.

5. A method for managing safety detection information for wind power according to claim 4, characterized in that: When the correlation relationship between the reference parameter and the associated parameter is positively correlated, the trend mark of the reference parameter is rising, and the trend mark of the associated parameter is falling, the associated abnormality type is abnormal rise of the reference parameter or abnormal fall of the associated parameter; When the correlation relationship between the reference parameter and the associated parameter is positively correlated, the trend of the reference parameter is marked as decreasing, and the trend of the associated parameter is marked as increasing, the associated abnormality type is an abnormal decrease in the reference parameter or an abnormal increase in the associated parameter; When the correlation relationship between the reference parameter and the associated parameter is negatively correlated, the trend mark of the reference parameter is rising, and the trend mark of the associated parameter is rising, the associated abnormality type is abnormal rise of the reference parameter or abnormal rise of the associated parameter; The correlation relationship between the reference parameter and the associated parameter is negatively correlated, the trend of the reference parameter is marked as decreasing, and when the trend of the associated parameter is marked as decreasing, the associated abnormality type is an abnormal decrease in the reference parameter or an abnormal decrease in the associated parameter.

6. A method for managing safety detection information for wind power according to claim 4, characterized in that: The method for constructing the association relationship table includes: Acquiring historical reference data, wherein the historical reference data includes values ​​of multiple safety detection parameters at multiple historical time points after manual verification; Mark the trend of each safety detection parameter at multiple historical time points; For all the same historical time points of any two safety detection parameters, when there are historical time points with values ​​exceeding the percentage threshold whose trend marks are the same or opposite, the two safety detection parameters are marked as the baseline parameter and the associated parameter, and the corresponding associated relationship is marked; An association relationship table is constructed based on all the benchmark parameters, the associated parameters of the benchmark parameters, and the association relationship between the benchmark parameters and the associated parameters.

7. A method for managing safety detection information for wind power according to claim 1, characterized in that: The method for constructing the event model includes: Obtain historical values ​​of various safety detection parameters and historical event records of wind power stations stored at multiple historical time points; Filtering out a target time point corresponding to an abnormal event from the historical event records; Determine abnormal values ​​and abnormal types of all safety detection parameters corresponding to the target time point, wherein the abnormal type includes an abnormal increase or abnormal decrease of the target safety detection parameter; The abnormal type corresponding to each abnormal event is counted, and the abnormal type whose occurrence frequency exceeds the preset frequency threshold is taken as the abnormal type of the corresponding abnormal event; An event model is constructed based on multiple abnormal events and abnormal types of multiple abnormal events.

8. A method for managing safety detection information for wind power according to claim 1, characterized in that: Verifying and managing the values ​​of the stored multiple safety detection parameters based on the abnormal value includes: sending the location of the outlier to a target object; When a modification command is received from the target object, the abnormal value is removed to obtain a blank value, and the blank value is interpolated, wherein the modification command is generated based on the position of the abnormal value, and the interpolation method is one of linear interpolation, polynomial interpolation, quadratic interpolation and spline interpolation.

9. A method for managing safety detection information for wind power according to claim 8, characterized in that: The stored values ​​of the various safety detection parameters are stored and managed based on the abnormal value, including: The verified values ​​of the various safety detection parameters at multiple time points are stored in the target area, and after the target time period, the original values ​​of the various safety detection parameters at multiple time points are cleared.

10. A management system for wind power safety detection information, characterized in that: include: An acquisition module, used to acquire values ​​of various safety detection parameters and event records of the wind power station stored at multiple time points; An abnormality analysis module is used to perform abnormality analysis on the values ​​of various safety detection parameters of the wind power station stored at multiple time points to obtain candidate abnormal values ​​and abnormal types of the candidate abnormal values; A matching module, used to determine event information at the same time point as the candidate outlier from the event record; and determining a target abnormal event matching the event information and an abnormal type of the target abnormal event based on a pre-built event model; A judgment module, configured to compare the abnormal type of the candidate abnormal value with the abnormal type of the target abnormal event; when the abnormal type of the candidate abnormal value is consistent with the abnormal type of the target abnormal event, the candidate abnormal value is regarded as a normal value; When the abnormality type of the candidate abnormal value is inconsistent with the abnormality type of the target abnormal event, taking the candidate abnormal value as the abnormal value; The management module is used to perform verification management and storage management on the values ​​of various stored safety detection parameters based on abnormal values.

Images