Fan abnormal temperature monitoring method and device, service equipment and storage medium

Abstract

The embodiment of the invention provides a fan abnormal temperature monitoring method and device, service equipment and a storage medium. The method comprises the following steps: receiving operation data of a plurality of fans sent by data acquisition equipment; sliding and traversing each group of operation data of each fan in the evaluation period according to preset time window parameters; in the traversing process, if it is judged that all the draught fans are in the normal power generation state, the average value of the operation data of all the draught fans in the current preset time window parameters is obtained, so that multiple average values corresponding to each set of operation data of all the draught fans in the evaluation period are obtained; according to the multiple average values corresponding to each set of operation data and different operation powers, the operation data average values of all the draught fans under the different operation powers are determined; and inputting the average value of the operation data of each fan in the plurality of fans under different operation powers into a pre-constructed clustering analysis model to output abnormal temperature data. The method is used for achieving the effect of improving the abnormal temperature identification precision.

Description

Technical Field

[0001] The present application relates to the field of computer technology, and in particular to a method, device, service equipment and storage medium for monitoring abnormal temperature of a fan. Background Art

[0002] During the high-speed rotation of the fan, if the temperature is too high, it will accelerate the aging and wear of the material. By identifying abnormal temperature data, it is possible to detect and take measures in time to prevent overheating from causing damage to the fan.

[0003] At present, the existing technology for monitoring abnormal temperature of fans mainly relies on temperature sensors and temperature data abnormality judgment logic based on thresholds.

[0004] However, although the temperature data abnormality judgment logic based on the threshold value can realize basic abnormal temperature monitoring, there is a case where the abnormal temperature recognition accuracy is low. Summary of the invention

[0005] The embodiments of the present application provide a method, device, service equipment and storage medium for monitoring abnormal temperature of a fan, so as to improve the accuracy of identifying abnormal temperature.

[0006] In a first aspect, an embodiment of the present application provides a method for monitoring abnormal temperature of a fan, comprising: receiving operating data of multiple fans sent by a data acquisition device; wherein the operating data of each fan is operating data of each fan continuously operating at different operating powers within an evaluation period; one operating power corresponds to a group of operating data; according to a preset time window parameter, slidingly traversing each group of operating data of each fan within the evaluation period; during the traversal process, judging whether each fan is in a normal power generation state within the current preset time window parameter; if it is determined that each fan is in a normal power generation state, obtaining the average value of the operating data of each fan within the current preset time window parameter to obtain multiple average values ​​corresponding to each group of operating data of each fan within the evaluation period; determining the average value of the operating data of each fan at different operating powers according to the multiple average values ​​corresponding to each group of operating data and different operating powers; inputting the average value of the operating data of each fan among the multiple fans at different operating powers into a pre-built clustering analysis model to output abnormal temperature data.

[0007] In one possible implementation, the pre-constructed clustering analysis model includes a neighborhood size parameter and a minimum point number parameter; after determining the average value of the operating data of each fan at different operating powers, it also includes: using a clustering algorithm to determine multiple silhouette coefficients based on the average value of the operating data of each fan in a plurality of fans at different operating powers and different numbers of clusters; one number of clusters corresponds to a silhouette coefficient; from the multiple silhouette coefficients, selecting the number of clusters corresponding to the maximum silhouette coefficient; determining the neighborhood size parameter based on the number of clusters corresponding to the maximum silhouette coefficient and the average value of the operating data of each fan in a plurality of fans at different operating powers; determining the minimum point number parameter based on the neighborhood size parameter; obtaining the pre-constructed clustering analysis model based on the neighborhood size parameter and the minimum point number parameter.

[0008] In a possible implementation, a neighborhood size parameter is determined based on the number of clusters corresponding to the maximum silhouette coefficient and the average operating data of each of the multiple wind turbines at different operating powers, including: clustering the average operating data of each of the multiple wind turbines at different operating powers according to the number of clusters to obtain multiple cluster categories; obtaining a target cluster category and a target cluster center corresponding to the target cluster category from the multiple cluster categories; obtaining all the average operating data values ​​in the target cluster category, and calculating the intra-cluster distance between each average operating data value and the target cluster center; determining a critical intra-cluster distance based on all the intra-cluster distances, so that the intra-cluster distances of a preset number of average operating data values ​​among all the average operating data values ​​are all smaller than the critical intra-cluster distance; and determining the critical intra-cluster distance as the neighborhood size parameter.

[0009] In a possible implementation manner, the average value of the operating data of each fan within the current preset time window parameter is obtained, and the calculation formula is:

[0010]

[0011] In the formula, It represents the average value of the operating data of each fan within the current preset time window parameter, t represents the preset time window parameter, and m represents the number of operating data within the current preset time window parameter. Represents the kth running data within the current preset time window parameters.

[0012] In a possible implementation, according to multiple average values ​​corresponding to each set of operating data and different operating powers, the average value of the operating data of each fan under different operating powers is determined, and the calculation formula is:

[0013]

[0014] In the formula, represents the average value of the operating data of each fan at the ith operating power among different operating powers, N represents the number of different operating powers, represents the number of multiple average values ​​corresponding to each set of operating data at the i-th operating power, and j represents the j-th average value of each set of operating data.

[0015] In a possible implementation, after the abnormal temperature data is output, the method further includes: determining whether the abnormal temperature data conforms to a preset abnormal mode; and if it is determined that the abnormal temperature data conforms to the preset abnormal mode, activating an alarm mechanism to sound an alarm.

[0016] In a second aspect, an embodiment of the present application provides a device for monitoring abnormal temperature of a fan, comprising:

[0017] The receiving module is used to receive the operating data of multiple fans sent by the data acquisition device; the operating data of each fan is the operating data of each fan running continuously at different operating powers during the evaluation period; one operating power corresponds to a group of operating data.

[0018] The traversal module is used to slide through each set of operating data of each wind turbine within the evaluation period according to the preset time window parameters; during the traversal process, it is determined whether each wind turbine is in a normal power generation state within the current preset time window parameters.

[0019] The first acquisition module is used to obtain the average value of the operating data of each wind turbine within the current preset time window parameters if it is determined that each wind turbine is in a normal power generation state, so as to obtain multiple average values ​​corresponding to each group of operating data of each wind turbine within the evaluation period.

[0020] The second acquisition module is used to determine the average value of the operating data of each wind turbine under different operating powers according to multiple average values ​​corresponding to each group of operating data and different operating powers.

[0021] The output module is used to input the average value of the operating data of each fan in the multiple fans at different operating powers into the pre-built cluster analysis model to output abnormal temperature data.

[0022] In a third aspect, an embodiment of the present application provides a service device, including: a memory, a processor;

[0023] The memory stores computer-executable instructions;

[0024] The processor executes the computer-executable instructions stored in the memory, so that the processor executes the above first aspect and / or various possible implementations of the first aspect.

[0025] In a fourth aspect, an embodiment of the present application provides a computer-readable storage medium, in which computer-executable instructions are stored. When the computer-executable instructions are executed by a processor, they are used to implement the first aspect above and / or various possible implementations of the first aspect.

[0026] In a fifth aspect, an embodiment of the present application provides a computer program product, including a computer program, which, when executed by a processor, implements the above first aspect and / or various possible implementation methods of the first aspect.

[0027] The embodiments of the present application provide a method, device, service equipment and storage medium for monitoring abnormal temperature of a fan. According to the operating data of multiple fans, each group of operating data of each fan is traversed in a sliding manner within an evaluation period; during the traversal process, if it is determined that each fan is in a normal power generation state, the average value of the operating data of each fan within the current preset time window parameter is obtained to obtain multiple average values ​​corresponding to each group of operating data of each fan within the evaluation period; according to the multiple average values ​​corresponding to each group of operating data and different operating powers, the average value of the operating data of each fan at different operating powers is obtained; through a pre-constructed cluster analysis model, the average value of the operating data of each fan at different powers is analyzed to monitor the abnormal temperature data of the fan during operation, which can avoid reacting when the temperature reaches the set threshold, thereby improving the recognition accuracy of abnormal temperature. BRIEF DESCRIPTION OF THE DRAWINGS

[0028] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present application and, together with the description, serve to explain the principles of the present application.

[0029] Figure 1 A schematic diagram of a scenario of a method for monitoring abnormal temperature of a fan provided in an embodiment of the present application;

[0030] Figure 2 A flow chart of a method for monitoring abnormal temperature of a fan provided in an embodiment of the present application;

[0031] Figure 3 A graph showing the relationship between different numbers of clusters and silhouette coefficients provided in the embodiments of the present application;

[0032] Figure 4 A schematic diagram of the structure of a fan abnormal temperature monitoring device provided in an embodiment of the present application;

[0033] Figure 5 A schematic diagram of the structure of the service equipment provided in the embodiment of the present application.

[0034] The above drawings have shown clear embodiments of the present application, which will be described in more detail later. These drawings and text descriptions are not intended to limit the scope of the present application in any way, but to illustrate the concept of the present application to those skilled in the art by referring to specific embodiments. DETAILED DESCRIPTION

[0035] Exemplary embodiments will be described in detail herein, examples of which are shown in the accompanying drawings. When the following description refers to the drawings, the same numbers in different drawings represent the same or similar elements unless otherwise indicated. The implementations described in the following exemplary embodiments do not represent all implementations consistent with the present application. Instead, they are merely examples of devices and methods consistent with some aspects of the present application as detailed in the appended claims.

[0036] When the fan is rotating at high speed, if the temperature is too high, it will accelerate the aging and wear of the material. By identifying abnormal temperature, it is possible to detect and take measures in time to prevent overheating from damaging the fan. At present, the existing technology for monitoring abnormal temperature of fans mainly relies on temperature sensors and threshold-based temperature data abnormality judgment logic. However, although the threshold-based temperature data abnormality judgment logic can achieve basic abnormal temperature monitoring, it has low accuracy in abnormal temperature recognition.

[0037] In order to solve the above technical problems, the embodiment of the present application proposes the following technical ideas: analyze the operating data of multiple fans to obtain the average operating data of each fan in the multiple fans at different operating powers. Analyze the average operating data of each fan in the multiple fans at different operating powers through a cluster analysis model to monitor the abnormal temperature data of the fan during operation, which can avoid reacting when the temperature reaches the set threshold, thereby improving the recognition accuracy of abnormal temperature.

[0038] The abnormal temperature monitoring method for a fan provided in the present application is intended to solve the above technical problems in the prior art.

[0039] The technical solution of the present application and how the technical solution of the present application solves the above-mentioned technical problems are described in detail below with specific embodiments. The following specific embodiments can be combined with each other, and the same or similar concepts or processes may not be repeated in some embodiments. The embodiments of the present application will be described below in conjunction with the accompanying drawings.

[0040] Figure 1 A schematic diagram of a scenario of a method for monitoring abnormal temperature of a fan provided in an embodiment of the present application, such as Figure 1 As shown, the specific application scenarios of the present application include: data acquisition equipment 101, service equipment 102 and operation and maintenance terminal 103.

[0041] refer to Figure 1 The data acquisition device 101 sends the operating data of the multiple fans to the service device 102. The service device 102 performs a series of processing on the operating data of the multiple fans and inputs the processed operating data into a pre-built cluster analysis model to output abnormal temperature data. If the service device 102 determines that the abnormal temperature data meets the preset abnormal mode, it activates the alarm mechanism and sends the abnormal temperature data to the operation and maintenance terminal 103 for processing.

[0042] Figure 2 A flow chart of a method for monitoring abnormal fan temperature provided in an embodiment of the present application. The execution subject of this embodiment may be Figure 1 The service device 102 in the embodiment may also be other devices with similar functions, which is not particularly limited in this embodiment. Figure 2 As shown, the method includes:

[0043] S201: Receive operating data of multiple fans sent by a data acquisition device; wherein the operating data of each fan is the operating data of each fan continuously operating at different operating powers within an evaluation period; and one operating power corresponds to a group of operating data.

[0044] Among them, the sampling frequency of the data acquisition device for collecting operating data is greater than 0.1 Hz.

[0045] Optionally, the operating data includes data such as wind speed, wind angle, operating power, fan status, generator speed, temperature data and fan number.

[0046] Optionally, the operating power may be 50kw, 100kw, 150kw, etc. One operating power corresponds to a set of operating data, that is, any wind turbine corresponds to a set of operating data when the operating power is 50kw; corresponds to a set of operating data when the operating power is 100kw; corresponds to a set of operating data when the operating power is 150kw.

[0047] S202: According to the preset time window parameters, each set of operating data of each wind turbine is traversed in a sliding manner within the evaluation period; during the traversal process, it is determined whether each wind turbine is in a normal power generation state within the current preset time window parameters.

[0048] Optionally, the preset time window parameter may be 10 minutes. It is determined based on the operating data whether each wind turbine is in a normal power generation state within the current 10 minutes.

[0049] For example, the evaluation period is 20 minutes, and the step length of the sliding traversal is 1 minute. The first traversal is for the operation data within the 1st to 10th minute, the second traversal is for the operation data within the 2nd to 11th minute, the third traversal is for the operation data within the 3rd to 12th minute, and so on, and the last traversal is for the operation data within the 11th to 20th minute.

[0050] S203: If it is determined that each wind turbine is in a normal power generation state, then an average value of the operating data of each wind turbine within the current preset time window parameter is obtained to obtain multiple average values ​​corresponding to each group of operating data of each wind turbine within the evaluation period.

[0051] Specifically, the average value of the operating data of each fan within the current preset time window parameters is obtained, and the calculation formula is:

[0052]

[0053] In the formula, It represents the average value of the operating data of each fan within the current preset time window parameter, t represents the preset time window parameter, and m represents the number of operating data within the current preset time window parameter. Represents the kth running data within the current preset time window parameters.

[0054] In this embodiment, it is determined based on the operating data whether each wind turbine is in a normal power generation state within the current preset time window parameters.

[0055] In this embodiment, the calculation formula involves temperature data in the operating data.

[0056] For example, if the preset time window parameter is 10 minutes, then t is 10 minutes. Taking a set of operating data corresponding to any wind turbine when the operating power is 50 kW as an example, if the wind turbine is in a normal power generation state from the 2nd to the 11th minute, then m is the number of temperature data in the set of operating data from the 2nd to the 11th minute.

[0057] Exemplarily, taking a set of operating data corresponding to any wind turbine when the operating power is 50 kW as an example, the wind turbine is in a normal power generation state within the 2nd to 11th minute, 3rd to 12th minute, 6th to 15th minute, 9th to 18th minute, 10th to 19th minute, and 11th to 20th minute, respectively, that is, the wind turbine is in a normal power generation state within the 6 time windows, then there are 6 average values ​​of the temperature data in this set of operating data.

[0058] S204: Determine an average value of the operating data of each wind turbine under different operating powers according to multiple average values ​​corresponding to each group of operating data and different operating powers.

[0059] Specifically, according to the multiple average values ​​corresponding to each set of operating data and the different operating powers, the average values ​​of the operating data of each fan under different operating powers are determined, and the calculation formula is:

[0060]

[0061] In the formula, represents the average value of the operating data of each fan at the ith operating power among different operating powers, N represents the number of different operating powers, represents the number of multiple average values ​​corresponding to each set of operating data at the i-th operating power, and j represents the j-th average value of each set of operating data.

[0062] In this embodiment, the calculation formula involves temperature data in the operating data.

[0063] For example, let's take a set of operating data corresponding to any fan when the operating power is 50kw as an example. The temperature data in this set of operating data has 6 average values. =6, add up the 6 average values, and then perform average calculation, the value obtained is the average value of the temperature data of any fan when the operating power is 50kw.

[0064] In this embodiment, any fan corresponds to only one average value of temperature data at different powers.

[0065] S205: inputting an average value of operating data of each fan among the multiple fans at different operating powers into a pre-built cluster analysis model to output abnormal temperature data.

[0066] In this embodiment, the calculation formula involves temperature data in the operating data.

[0067] For example, Table 1 shows the average value of temperature data of each fan in a plurality of fans at different operating powers. For example, the average value of temperature data of the fan numbered 1 when the operating power is 50 kW is 39.9951661; the average value of temperature data of the fan numbered 1 when the operating power is 100 kW is 40.12305409; the average value of temperature data of the fan numbered 11 when the operating power is 150 kW is 40.38804; the average value of temperature data of the fan numbered 19 when the operating power is 550 kW is 42.10810625.

[0068] Table 1 Average temperature data of each fan under different operating powers among multiple fans

[0069]

[0070] Optionally, the pre-built clustering analysis model may be a DBSCAN model.

[0071] Exemplarily, the average temperature data of each fan in the plurality of fans at different operating powers are input into the pre-built cluster analysis model; the pre-built cluster analysis model divides all the average temperature data into different cluster categories according to the density of all the average temperature data, and the average temperature data in each cluster category are dense with each other, but sparse with the average temperature data in other cluster categories. The average temperature data that do not belong to any cluster category indicates abnormal temperature, and the abnormal temperature data is output.

[0072] In summary, according to the operating data of multiple wind turbines, each group of operating data of each wind turbine is traversed in the evaluation period; during the traversal process, if it is determined that each wind turbine is in a normal power generation state, the average value of the operating data of each wind turbine within the current preset time window parameters is obtained to obtain multiple average values ​​corresponding to each group of operating data of each wind turbine in the evaluation period; according to the multiple average values ​​corresponding to each group of operating data, and different operating powers, the average value of the operating data of each wind turbine under different operating powers is obtained; through the pre-constructed clustering analysis model, the average value of the operating data of each wind turbine under different powers is analyzed to monitor the abnormal temperature data of the fan during operation, which can avoid responding when the temperature reaches the set threshold, thereby improving the recognition accuracy of abnormal temperature.

[0073] On the basis of the above embodiment, an abnormal point counting threshold is set for each fan. When the number of abnormal temperature data of each fan reaches the abnormal point counting threshold, it is considered that the fan is abnormal.

[0074] In summary, fans whose number of abnormal temperature data exceeds the abnormal point counting threshold are identified as abnormal fans, which helps to detect abnormal fans; at the same time, it also provides data support for preventive maintenance and optimized operation of fans.

[0075] Based on the above embodiment, in this embodiment, the process of obtaining a pre-built cluster analysis model is introduced, which is described in detail as follows:

[0076] S301: using a clustering algorithm, determining a plurality of silhouette coefficients according to average values ​​of operating data of each of a plurality of wind turbines at different operating powers and different numbers of clusters; one silhouette coefficient corresponds to one number of clusters.

[0077] Optionally, the clustering algorithm may be K-means.

[0078] Optionally, different numbers of clusters may be 2, 3, 4, 5, 6, 7, 8, 9, etc.

[0079] Specifically, when the number of clusters is 2, the process of determining the silhouette coefficient is:

[0080] Sa: Randomly select the average values ​​of 2 running data as the initial cluster center points.

[0081] Sb: Calculate the distance from each running data average to the two initial cluster center points respectively, and assign each running data average to the initial cluster center point closest to it to obtain two cluster categories.

[0082]

[0083] In the formula, Represents the distance from the average value of the i-th running data to the j-th initial cluster center point; The horizontal axis represents the average value of the i-th running data, The ordinate represents the average value of the i-th running data; represents the horizontal coordinate of the jth initial cluster center point, Represents the ordinate of the jth initial cluster center point. Through this formula, the distance from the average value of each running data to the two initial cluster centers can be calculated respectively.

[0084] Sc: Update the cluster center point of each cluster according to the average of the running data means assigned to each initial cluster center to obtain the updated cluster center point of each cluster.

[0085] Specifically, the calculation formula is:

[0086]

[0087] In the formula, Represents the horizontal coordinate of the updated cluster center of each cluster, represents the ordinate of the updated cluster center of each cluster; i represents the number of average values ​​of all running data in each cluster, represents the sum of the abscissas of all running data means in each cluster, The ordinate represents the sum of the mean values ​​of all runs in each cluster.

[0088] Sd: Repeat steps Sb and Sc until the cluster center of each cluster no longer changes.

[0089] Se: Calculate the silhouette coefficient when the number of clusters is 2.

[0090] Specifically, the calculation formula of the silhouette coefficient is:

[0091]

[0092] In the formula, represents the average distance within a cluster, Represents the average distance between clusters.

[0093] S302: Selecting the number of clusters corresponding to the maximum silhouette coefficient from multiple silhouette coefficients.

[0094] In this embodiment, Figure 3 The relationship between the number of clusters and the silhouette coefficient provided in the embodiment of the present application is shown in FIG. Figure 3 As shown, the maximum silhouette coefficient is 0.85, and the corresponding number of clusters is 2.

[0095] S303: Determine a neighborhood size parameter according to the number of clusters corresponding to the maximum silhouette coefficient and an average value of operating data of each of the plurality of wind turbines at different operating powers.

[0096] Specifically, step S303 includes S3031 to S3035:

[0097] S3031: Clustering the average values ​​of the operating data of each of the multiple wind turbines at different operating powers according to the number of clusters to obtain multiple cluster categories.

[0098] Specifically, the number of clusters corresponds to the number of multiple cluster categories.

[0099] S3032: Obtain a target cluster category and a target cluster center corresponding to the target cluster category from multiple cluster categories.

[0100] In this embodiment, the cluster category with the most dense data among the multiple cluster categories is used as the target cluster category.

[0101] S3033: Obtain the average values ​​of all running data in the target cluster category, and calculate the intra-cluster distance between each running data average value and the target cluster center.

[0102] Specifically, the intra-cluster distance between the average value of each running data and the target cluster center is calculated using the following formula:

[0103]

[0104] In the formula, It represents the intra-cluster distance between the average value of any running data and the target cluster center. represents the coordinates of the mean of any running data in the target cluster category, Represents the coordinates of the target cluster center.

[0105] S3034: Determine a critical intra-cluster distance according to all intra-cluster distances, so that among all the average values ​​of the operating data, there are a preset number of intra-cluster distances of the operating data that are smaller than the critical intra-cluster distance.

[0106] Optionally, the preset number may be 90% of the number of average values ​​of all running data.

[0107] Specifically, all intra-cluster distances are sorted in ascending order to obtain an ascending sorted sequence; the first 90% of the intra-cluster distances in the ascending sorted sequence are intercepted, and the last intra-cluster distance in the intercepted sequence is determined as the critical intra-cluster distance.

[0108] S3035: Determine the critical intra-cluster distance as a neighborhood size parameter.

[0109] S304: Determine a minimum point number parameter according to the neighborhood size parameter.

[0110] In this embodiment, the value obtained by adding one to the neighborhood size parameter is determined as the minimum point number parameter.

[0111] S305: Obtain a pre-constructed cluster analysis model according to the neighborhood size parameter and the minimum point number parameter.

[0112] Among them, the pre-built cluster analysis model includes neighborhood size parameters and minimum point number parameters.

[0113] In summary, a clustering algorithm is used to determine multiple silhouette coefficients according to the average values ​​of the operating data of each fan in multiple fans at different operating powers and different numbers of clusters. The silhouette coefficient is used to evaluate the effect of clustering under different numbers of clusters. The larger the silhouette coefficient, the better the clustering effect. According to the number of clusters corresponding to the maximum silhouette coefficient, the average values ​​of the operating data of each fan in multiple fans at different operating powers are clustered, and the target cluster category and the target cluster center are determined. The average values ​​of all operating data in the target cluster category are obtained, and the intra-cluster distance between each operating data average value and the target cluster center is calculated, and then the neighborhood size parameter and the minimum number of points parameter are determined to obtain a pre-constructed cluster analysis model. The neighborhood size parameter and the minimum number of points parameter can be automatically determined according to the distribution of the average value of the operating data, which improves the ability of the pre-constructed cluster analysis model to identify abnormal temperature data, thereby improving the recognition accuracy of abnormal temperature.

[0114] Based on the above embodiment, in this embodiment, the processing process after abnormal temperature is detected is introduced, which is detailed as follows:

[0115] S401: Determine whether the abnormal temperature data conforms to a preset abnormal mode.

[0116] Optionally, the preset abnormal mode may be a sudden increase or decrease in temperature.

[0117] S402: If it is determined that the abnormal temperature data meets the preset abnormal mode, the alarm mechanism is activated to issue an alarm.

[0118] Specifically, the alarm mechanism includes but is not limited to sending real-time alarm information to the operation and maintenance terminal, recording abnormal events and triggering automated security protection programs.

[0119] Optionally, after receiving the alarm, the operation and maintenance terminal will conduct an on-site or remote inspection and feed back the diagnosis results to the service equipment. The service equipment adjusts the parameters of the cluster analysis model or presets the abnormal mode according to the feedback results to optimize the subsequent abnormal temperature monitoring.

[0120] In summary, if it is determined that the abnormal temperature data meets the preset abnormal mode, the alarm mechanism is activated to alarm so that the operation and maintenance terminal can handle it in time.

[0121] Figure 4 The structural diagram of the abnormal temperature monitoring device for a fan provided in the embodiment of the present application is as follows: Figure 4 As shown, the device for monitoring abnormal temperature of a fan provided in this embodiment includes: a receiving module 401 , a traversal module 402 , a first acquisition module 403 , a second acquisition module 404 and an output module 405 .

[0122] The receiving module 401 is used to receive the operating data of multiple fans sent by the data acquisition device; wherein the operating data of each fan is the operating data of each fan continuously running at different operating powers during the evaluation period; and one operating power corresponds to a group of operating data;

[0123] The traversal module 402 is used to slide through each set of operating data of each wind turbine within the evaluation period according to the preset time window parameters; during the traversal process, it is determined whether each wind turbine is in a normal power generation state within the current preset time window parameters;

[0124] The first acquisition module 403 is used to acquire the average value of the operating data of each wind turbine within the current preset time window parameter if it is determined that each wind turbine is in a normal power generation state, so as to obtain multiple average values ​​corresponding to each group of operating data of each wind turbine within the evaluation period;

[0125] The second acquisition module 404 is used to determine the average value of the operating data of each wind turbine under different operating powers according to multiple average values ​​corresponding to each set of operating data and different operating powers;

[0126] The output module 405 is used to input the average value of the operating data of each fan in the multiple fans at different operating powers into the pre-built cluster analysis model to output abnormal temperature data.

[0127] In a possible implementation, the abnormal temperature monitoring device for a fan also includes a construction module, which is specifically used to: use a clustering algorithm to determine multiple silhouette coefficients based on the average values ​​of operating data of each fan in a plurality of fans at different operating powers and different numbers of clusters; one silhouette coefficient corresponds to one number of clusters; from the multiple silhouette coefficients, select the number of clusters corresponding to the maximum silhouette coefficient; determine a neighborhood size parameter based on the number of clusters corresponding to the maximum silhouette coefficient and the average values ​​of operating data of each fan in a plurality of fans at different operating powers; determine a minimum number of points parameter based on the neighborhood size parameter; and obtain a pre-constructed clustering analysis model based on the neighborhood size parameter and the minimum number of points parameter.

[0128] In a possible implementation, the construction module is further used to cluster the average operating data of each wind turbine in the multiple wind turbines at different operating powers according to the number of clusters to obtain multiple cluster categories; obtain a target cluster category and a target cluster center corresponding to the target cluster category from the multiple cluster categories; obtain all the average operating data values ​​in the target cluster category, and calculate the intra-cluster distance between each average operating data value and the target cluster center; determine a critical intra-cluster distance based on all the intra-cluster distances, so that the intra-cluster distances of a preset number of average operating data values ​​among all the average operating data values ​​are all less than the critical intra-cluster distance; and determine the critical intra-cluster distance as a neighborhood size parameter.

[0129] In a possible implementation, the calculation formula of the first acquisition module 403′ is:

[0130]

[0131] In the formula, It represents the average value of the operating data of each fan within the current preset time window parameter, t represents the preset time window parameter, and m represents the number of operating data within the current preset time window parameter. Represents the kth running data within the current preset time window parameters.

[0132] In a possible implementation, the calculation formula of the second acquisition module 404′ is:

[0133]

[0134] In the formula, represents the average value of the operating data of each fan at the ith operating power among different operating powers, N represents the number of different operating powers, represents the number of multiple average values ​​corresponding to each set of operating data at the i-th operating power, and j represents the j-th average value of each set of operating data.

[0135] In a possible implementation, the abnormal temperature monitoring device for a fan further includes an alarm module, which is specifically used to: determine whether the abnormal temperature data conforms to a preset abnormal mode; if it is determined that the abnormal temperature data conforms to the preset abnormal mode, activate an alarm mechanism to sound an alarm.

[0136] The abnormal temperature monitoring device for a fan provided in this embodiment can execute the method provided in the above method embodiment. Its implementation principle and technical effect are similar, and will not be described in detail in this embodiment.

[0137] Figure 5 This is a schematic diagram of the structure of the service device provided in the embodiment of the present application. Figure 5 As shown, the service device provided in this embodiment includes: at least one processor 501 and a memory 502. Optionally, the service device further includes a communication component 503. The processor 501, the memory 502 and the communication component 503 are connected via a bus.

[0138] In a specific implementation process, at least one processor 501 executes the computer-executable instructions stored in the memory 502, so that at least one processor 501 executes the above method.

[0139] The specific implementation process of the processor 501 can be found in the above method embodiment, and its implementation principle and technical effect are similar, so this embodiment will not be repeated here.

[0140] In the above embodiments, it should be understood that the processor can be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), etc. A general-purpose processor can be a microprocessor or any conventional processor. The steps of the method disclosed in the invention can be directly implemented as a hardware processor, or can be implemented by a combination of hardware and software modules in the processor.

[0141] The memory may include a high-speed memory (Random Access Memory, RAM), and may also include a non-volatile memory (NVM), such as at least one disk storage.

[0142] The bus can be an Industry Standard Architecture (ISA) bus, a Peripheral Component Interconnect (PCI) bus, or an Extended Industry Standard Architecture (EISA) bus, etc. The bus can be divided into an address bus, a data bus, a control bus, etc. For ease of representation, the bus in the drawings of this application is not limited to only one bus or one type of bus.

[0143] The present application also provides a computer program product, including a computer program, which implements the above method when executed by a processor.

[0144] The present application also provides a computer-readable storage medium, in which computer-executable instructions are stored. When a processor executes the computer-executable instructions, the above method is implemented.

[0145] The above-mentioned readable storage medium can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic memory, flash memory, magnetic disk or optical disk. The readable storage medium can be any available medium that can be accessed by a general or special-purpose computer.

[0146] An exemplary readable storage medium is coupled to a processor so that the processor can read information from the readable storage medium and write information to the readable storage medium. Of course, the readable storage medium can also be a component of the processor. The processor and the readable storage medium can be located in an application specific integrated circuit (Application Specific Integrated Circuits, referred to as: ASIC). Of course, the processor and the readable storage medium can also exist in the device as discrete components.

[0147] The division of units is only a logical function division, and there may be other divisions in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be an indirect coupling or communication connection through some interface, device or unit, which can be electrical, mechanical or other forms.

[0148] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0149] In addition, each functional unit in each embodiment of the present invention may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit.

[0150] If the function is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art, or the part of the technical solution, can be embodied in the form of a software product. The computer software product is stored in a storage medium, including several instructions for a computer device (which can be a personal computer, server, or network device, etc.) to perform all or part of the steps of the methods of each embodiment of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk, etc. Various media that can store program codes.

[0151] Those skilled in the art can understand that all or part of the steps of implementing the above-mentioned method embodiments can be completed by hardware related to program instructions. The aforementioned 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, disk or optical disk and other media that can store program codes.

[0152] Finally, it should be noted that those skilled in the art will readily conceive of other embodiments of the present invention after considering the specification and practicing the invention disclosed herein. The present invention is intended to cover any variations, uses or adaptations of the present invention, which follow the general principles of the present invention and include common knowledge or customary technical means in the art not disclosed by the present invention, are not limited to the precise structure described above and shown in the drawings, and may be modified and changed in various ways without departing from the scope thereof. The scope of the present invention is limited only by the appended claims.

Claims

1. A method for monitoring abnormal temperature of a fan, characterized in that: Applied to service equipment, including: Receive operation data of multiple fans sent by a data acquisition device; wherein the operation data of each fan is the operation data of each fan continuously running at different operation powers during an evaluation period; and one operation power corresponds to a group of operation data; According to the preset time window parameters, each set of operating data of each wind turbine is traversed in the evaluation period; during the traversal process, it is determined whether each wind turbine is in a normal power generation state within the current preset time window parameters; If it is determined that each wind turbine is in a normal power generation state, then obtaining an average value of the operating data of each wind turbine within a current preset time window parameter to obtain multiple average values ​​corresponding to each group of operating data of each wind turbine within the evaluation period; Determine the average value of the operating data of each wind turbine at the different operating powers according to the multiple average values ​​corresponding to each group of operating data and the different operating powers; The average value of the operating data of each of the plurality of fans at the different operating powers is input into a pre-built cluster analysis model to output abnormal temperature data.

2. The method according to claim 1, characterized in that The pre-built cluster analysis model includes a neighborhood size parameter and a minimum number of points parameter; Accordingly, after determining the average value of the operating data of each wind turbine at the different operating powers, the method further includes: Using a clustering algorithm, a plurality of silhouette coefficients are determined according to an average value of the operating data of each of the plurality of wind turbines at the different operating powers and different numbers of clusters; one silhouette coefficient corresponds to one number of clusters; From the plurality of silhouette coefficients, selecting the number of clusters corresponding to the maximum silhouette coefficient; Determining the neighborhood size parameter according to the number of clusters corresponding to the maximum silhouette coefficient and an average value of the operating data of each of the plurality of wind turbines at the different operating powers; Determining the minimum number of points parameter according to the neighborhood size parameter; The pre-constructed cluster analysis model is obtained according to the neighborhood size parameter and the minimum point number parameter.

3. The method according to claim 2, characterized in that The determining the neighborhood size parameter according to the number of clusters corresponding to the maximum silhouette coefficient and the average value of the operating data of each of the plurality of wind turbines at the different operating powers includes: Clustering, according to the number of clusters, average values ​​of the operating data of each of the plurality of wind turbines at the different operating powers to obtain a plurality of cluster categories; Acquire a target cluster category and a target cluster center corresponding to the target cluster category from the multiple cluster categories; Obtaining the average values ​​of all running data in the target cluster category, and calculating the intra-cluster distance between each running data average value and the target cluster center; Determine a critical in-gathering distance according to all in-gathering distances, so that in-gathering distances of a preset number of running data average values ​​among all the running data average values ​​are smaller than the critical in-gathering distance; The critical intra-poly distance is determined as the neighborhood size parameter.

4. The method according to claim 1, characterized in that The calculation formula for obtaining the average value of the operating data of each fan within the current preset time window parameter is: In the formula, represents the average value of the operating data of each fan within the current preset time window parameter, t represents the preset time window parameter, m represents the number of operating data within the current preset time window parameter, Represents the kth running data within the current preset time window parameters.

5. The method according to claim 1, characterized in that The calculation formula for determining the average value of the operating data of each fan at the different operating powers according to the multiple average values ​​corresponding to each group of operating data and the different operating powers is: In the formula, represents the average value of the operating data of each fan at the i-th operating power among the different operating powers, N represents the number of the different operating powers, represents the number of multiple average values ​​corresponding to each set of operating data under the i-th operating power, and j represents the j-th average value of each set of operating data.

6. The method according to any one of claims 1 to 5, characterized in that: After outputting the abnormal temperature data, the method further includes: Determining whether the abnormal temperature data conforms to a preset abnormal mode; If it is determined that the abnormal temperature data meets the preset abnormal mode, the alarm mechanism is activated to alarm.

7. A fan abnormal temperature monitoring device, characterized in that: Applied to service equipment, including: A receiving module is used to receive the operating data of multiple fans sent by the data acquisition device; wherein the operating data of each fan is the operating data of each fan continuously running at different operating powers within the evaluation period; and one operating power corresponds to a group of operating data; A traversal module, used to slide and traverse each set of operating data of each wind turbine within the evaluation period according to a preset time window parameter; during the traversal process, determine whether each wind turbine is in a normal power generation state within the current preset time window parameter; A first acquisition module is used to acquire an average value of the operating data of each wind turbine within a current preset time window parameter if it is determined that each wind turbine is in a normal power generation state, so as to obtain multiple average values ​​corresponding to each group of operating data of each wind turbine within the evaluation period; A second acquisition module is used to determine the average value of the operating data of each wind turbine under the different operating powers according to the multiple average values ​​corresponding to each group of operating data and the different operating powers; The output module is used to input the average value of the operating data of each of the multiple fans at the different operating powers into a pre-built cluster analysis model to output abnormal temperature data.

8. A service device, characterized in that: include: Memory, processor; The memory stores computer-executable instructions; The processor executes the computer-executable instructions stored in the memory, so that the processor performs the method according to any one of claims 1 to 6.

9. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer-executable instructions, which are used to implement the method according to any one of claims 1 to 6 when executed by a processor.

10. A computer program product, characterized in that The invention comprises a computer program, which implements the method according to any one of claims 1 to 6 when being executed by a processor.

Images