Abnormality detection method, system and equipment for converter of wind turbine generator and medium

Abstract

The invention discloses an anomaly detection method, system and device for a wind turbine generator converter and a medium, and relates to the technical field of wind power, and the method comprises the steps: determining a plurality of health value intervals of a wind turbine generator cluster through calculating the mean value and standard deviation of converter temperature parameters in the wind turbine generator cluster; acquiring a mean value of temperature parameters of a target converter in the wind turbine generator cluster within a preset time; and based on the plurality of health value intervals of the wind turbine generator cluster and the mean value of the target converter temperature parameter in the preset time, determining a target abnormal level of a target wind turbine generator converter corresponding to the target converter temperature parameter. The method is suitable for a scene of performing anomaly detection on the target wind turbine generator converter based on the converter temperature parameter.

Description

Technical Field

[0001] The present application relates to the field of wind power technology, and in particular to an abnormality detection method, system, equipment and medium for a wind turbine converter. Background Art

[0002] Wind power generation plays an important role in the energy system, and the safe and reliable operation of wind turbines is crucial to the healthy development of the wind power industry. During the operation of existing wind turbines, the converter, as one of the key components in the wind power system, is very easy to heat up, and a temperature sensor needs to be installed to detect its temperature in real time. The existing solution is to detect the converter temperature to determine whether the corresponding cooling device needs to be activated, whether it needs to be limited in power or shut down, so as to ensure the normal operation of the converter.

[0003] The shortcomings of existing solutions for abnormal detection of wind turbines are that, for example, the abnormal detection algorithm based on converter temperature cannot timely evaluate the abnormal state of the wind turbine converter by setting a threshold, or make advance predictions through network models. There are certain differences in model learning between different wind turbines, resulting in inaccurate predictions of abnormal states. Summary of the invention

[0004] In view of this, the present application provides a method, system, equipment and medium for detecting an abnormality of a wind turbine converter. The main purpose is to solve the technical problems that the timeliness of the existing abnormal state evaluation of the wind turbine converter by setting thresholds is low, and the model learning between different wind turbines is different, resulting in low accuracy of the predicted abnormal state.

[0005] According to one aspect of the present application, a method for detecting abnormality of a wind turbine converter is provided, the method comprising:

[0006] By calculating the mean and standard deviation of the temperature parameters of the converters in the wind turbine cluster, multiple health value intervals of the wind turbine cluster are determined;

[0007] Obtaining an average value of a temperature parameter of a target converter in the wind turbine cluster within a preset time;

[0008] Based on a plurality of health value intervals of the wind turbine cluster and an average value of the target converter temperature parameter within a preset time, a target abnormality level of the target wind turbine converter corresponding to the target converter temperature parameter is determined.

[0009] According to another aspect of the present application, a wind turbine converter abnormality detection system is provided, the system comprising:

[0010] A first determination module is used to determine multiple health value intervals of the wind turbine cluster by calculating the mean and standard deviation of the temperature parameters of the converters in the wind turbine cluster;

[0011] A second acquisition module is used to obtain the average value of the target converter temperature parameter in the wind turbine cluster within a preset time;

[0012] The second determination module is used to determine the target abnormality level of the target wind turbine converter corresponding to the target converter temperature parameter based on multiple health value intervals of the wind turbine cluster and the average value of the target converter temperature parameter within a preset time.

[0013] According to another aspect of the present application, a computer storage medium is provided, on which a computer program is stored, and when the program is executed by a processor, the above-mentioned abnormality detection method for the wind turbine converter is implemented.

[0014] According to another aspect of the present application, a computer device is provided, including a storage medium, a processor, and a computer program stored on the storage medium and executable on the processor, wherein the processor implements the above-mentioned abnormality detection method for the wind turbine converter when executing the program.

[0015] By means of the above technical scheme, the abnormality detection method, system, device and medium of the wind turbine converter provided by the present application, compared with the existing technical scheme of evaluating the abnormal temperature state of the wind turbine converter by setting a threshold value, or making advance predictions through a network model, the present application determines multiple health value intervals of the wind turbine cluster by calculating the mean and standard deviation of the converter temperature parameters in the wind turbine cluster; obtains the mean value of the target converter temperature parameter in the wind turbine cluster within a preset time; based on the multiple health value intervals of the wind turbine cluster and the mean value of the target converter temperature parameter within a preset time, determines the target abnormality level of the target wind turbine converter corresponding to the target converter temperature parameter. It can be seen that when constructing a wind turbine cluster, the target converter temperature parameter of the target wind turbine is also included in the cluster to ensure the accuracy of the set multiple health value intervals, thereby effectively reducing the false alarm rate of abnormality detection of the target wind turbine converter and ensuring the accuracy of abnormality detection of the wind turbine converter.

[0016] The above description is only an overview of the technical solution of the present application. In order to more clearly understand the technical means of the present application, it can be implemented in accordance with the contents of the specification. In order to make the above and other purposes, features and advantages of the present application more obvious and easy to understand, the specific implementation methods of the present application are listed below. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] The drawings described herein are used to provide a further understanding of the present application and constitute a part of the present application. The illustrative embodiments of the present application and their descriptions are used to explain the present application and do not constitute an improper limitation on the present application. In the drawings:

[0018] Figure 1 A schematic flow chart of an abnormality detection method for a wind turbine converter provided in an embodiment of the present application is shown;

[0019] Figure 2 A schematic flow chart of another abnormality detection method for a wind turbine converter provided in an embodiment of the present application is shown;

[0020] Figure 3 A temperature probability distribution comparison diagram of an abnormality detection system for a wind turbine converter provided in an embodiment of the present application is shown;

[0021] Figure 4 A schematic structural diagram of an abnormality detection system for a wind turbine converter provided in an embodiment of the present application is shown;

[0022] Figure 5 A structural schematic diagram of another abnormality detection system for a wind turbine converter provided in an embodiment of the present application is shown. DETAILED DESCRIPTION

[0023] The present application will be described in detail below with reference to the accompanying drawings and in combination with embodiments. It should be noted that the embodiments and features in the embodiments of the present application can be combined with each other without conflict.

[0024] The existing abnormal state evaluation of wind turbine converters by setting thresholds is not timely enough, and the model learning of different wind turbines is different, which leads to the technical problem of low accuracy of abnormal state prediction. This embodiment provides a method for detecting abnormality of wind turbine converters. When constructing a wind turbine cluster, the target converter temperature parameters of the target wind turbine are also included in the cluster to ensure the accuracy of abnormality detection of wind turbine converters. Figure 1 As shown, the above method comprises the following steps:

[0025] Step 101: Determine multiple health value intervals of the wind turbine cluster by calculating the mean and standard deviation of the converter temperature parameters in the wind turbine cluster.

[0026] In this embodiment, the initial converter temperature parameters are obtained, and the converter temperature parameters for constructing a wind turbine cluster are obtained by cleaning and preprocessing the initial converter temperature parameters. The converter temperature parameters include one or more of the converter power module temperature, the converter grid-side inverter temperature, and the converter machine-side inverter temperature. It should be noted that, depending on the type of wind turbine, the wind turbine may include one or more categories of converter temperature parameters, and a wind turbine cluster is constructed for each category of converter temperature parameters.

[0027] Step 102: Obtain an average value of a target converter temperature parameter in the wind turbine cluster within a preset time.

[0028] In this embodiment, based on the inverter temperature parameters in the wind turbine cluster obtained within the first preset time, the mean and standard deviation of the inverter temperature parameters in the wind turbine cluster are calculated, and the mean of the target inverter temperature parameter within the second preset time is calculated. The first preset time and the second preset time can be selected as the same time or different times according to the needs of the actual application scenario, and the preset time is not specifically limited here. It should be noted that if the inverter temperature parameter is at least two target inverter temperature parameters, a wind turbine cluster is constructed according to each target inverter temperature parameter, and then for each target inverter temperature parameter, the mean and standard deviation of the inverter temperature parameter in each wind turbine cluster are calculated, and the mean of the target inverter temperature parameter within the preset time is calculated.

[0029] Step 103 : determining a target abnormality level of a target wind turbine converter corresponding to the target converter temperature parameter based on a plurality of health value intervals of the wind turbine cluster and an average value of the target converter temperature parameter within a preset time.

[0030] In this embodiment, the wind turbine cluster includes the converter temperature parameters of the target wind turbine to be detected and the converter temperature parameters of the same type of wind turbines in the wind farm. By incorporating the converter temperature parameters of the target wind turbine to be detected into the wind turbine cluster, the false alarm rate of the target abnormality level of the converter of the target wind turbine to be detected determined based on the cluster benchmarking algorithm is low, thereby ensuring the accuracy of the abnormality detection of the target wind turbine converter.

[0031] For this embodiment, the above scheme can be followed to determine multiple health value intervals of the wind turbine cluster by calculating the mean and standard deviation of the converter temperature parameters in the wind turbine cluster; obtain the mean value of the target converter temperature parameter in the wind turbine cluster within a preset time; and determine the target abnormality level of the target wind turbine converter corresponding to the target converter temperature parameter based on the multiple health value intervals of the wind turbine cluster and the mean value of the target converter temperature parameter within a preset time. Compared with the existing technical schemes of evaluating the abnormal state of the wind turbine converter by setting a threshold or making advance predictions through a network model, this embodiment also includes the target converter temperature parameter of the target wind turbine in the cluster when constructing the wind turbine cluster to ensure the accuracy of the multiple health value intervals set, thereby effectively reducing the false alarm rate of abnormal detection of the target wind turbine and ensuring the accuracy of abnormal detection of the wind turbine.

[0032] Further, as a refinement and expansion of the specific implementation of the above embodiment, in order to fully illustrate the specific implementation process of this embodiment, another abnormality detection method for wind turbine converter is provided, which determines whether the wind turbine is abnormal based on the converter temperature parameters. The main function of the wind turbine converter is to control the amplitude, phase, frequency, etc. of the excitation through the converter when the speed of the wind turbine changes, so that the stator side can input a constant frequency current to the power grid. Among them, the converter includes a direct-drive converter (also known as a full-power converter) and a doubly-fed converter, and the doubly-fed converter can directly send part of the current into the power grid. This embodiment takes the converter power module temperature, the converter grid-side inverter temperature and the converter machine-side inverter temperature in the wind turbine converter temperature parameters as examples, and can evaluate the target abnormality level of the target wind turbine converter corresponding to the target converter temperature parameters through the cluster benchmarking algorithm.

[0033] like Figure 2 As shown, the method includes:

[0034] Step 201: Acquire a first converter temperature parameter with a rated power within a first preset range from an initial converter temperature parameter, and use the first converter temperature parameter as a converter temperature parameter for constructing a wind turbine cluster.

[0035] In the implementation, the variables mainly monitored by the temperature parameters of the wind turbine converter include: the converter temperature parameters include one or more of the converter power module temperature, the converter grid-side inverter temperature and the converter machine-side inverter temperature. The acquired operating condition data is cleaned and preprocessed, specifically removing the 0 value, negative value or wrong format (which is an abnormal phenomenon) in the operating condition data to obtain the initial converter temperature parameter. For example, if the length of the operating condition data is less than or equal to 10, it is cleaned and marked with status_code = '301'; further, the converter temperature parameter corresponding to 80%-120% of the rated power is selected as the first converter temperature parameter within the first preset range, and accordingly, the converter temperature parameter corresponding to the rated power outside 80%-120% is used as the second converter temperature parameter within the second preset range.

[0036] Step 202 : Determine multiple health value intervals of the wind turbine cluster by calculating the mean and standard deviation of the temperature parameters of the converters in the wind turbine cluster.

[0037] Step 203: Obtain an average value of a temperature parameter of a target converter in the wind turbine cluster within a preset time.

[0038] Step 204 : determining a target abnormality level of a target wind turbine converter corresponding to the target converter temperature parameter based on a plurality of health value intervals of the wind turbine cluster and an average value of the target converter temperature parameter within a preset time.

[0039] During implementation, a mapping strategy for the wind turbine health value interval is set, and the temperature parameters of the wind turbine cluster converter are used as a reference basis. The converter temperature parameters and the wind turbine health value form a linear mapping. Specifically, according to the first converter temperature parameter within the first preset range, the first converter temperature parameter within a certain preset time is obtained as the converter temperature parameter for constructing a wind turbine cluster, the mean μ and standard deviation σ of the converter temperature parameter of the wind turbine cluster are calculated, and the mean (health value) of the target converter temperature parameter in the wind turbine cluster is calculated. If the mean of the target converter temperature parameter is within +3σ, the first health value interval of the wind turbine cluster is (80, 100), and the health value of the target wind turbine converter is within the first health value interval, and the first health value interval is the normal boundary (80, 100). Similarly, for every increase of one σ in the mean of the target converter temperature parameter, the health value of the target wind turbine converter decreases by 20 and is within the second health value interval (60, 80), until the health value of the target wind turbine converter decreases to 0.

[0040] It should be noted that multiple health value intervals are set based on the constructed wind turbine cluster, specifically, (80, 100) corresponds to the target abnormality level of the first level (normal), (60, 80) corresponds to the target abnormality level of the second level (concern), (40, 60) corresponds to the target abnormality level of the third level (warning), (20, 40) corresponds to the target abnormality level of the third level (alarm), (0, 20) corresponds to the target abnormality level of the third level (alarm), a total of 5 health value intervals, or (0, 40) corresponds to the target abnormality level of the third level (alarm), a total of 4 health value intervals. The number of health value intervals and the division method are not specifically limited here.

[0041] In order to illustrate the specific implementation method of step 204, the step 204 also includes: obtaining the operating data curve and probability density curve of the wind turbine cluster according to the converter temperature parameters in the wind turbine cluster; and verifying whether the converter temperature parameters in the wind turbine cluster conform to the mixed Gaussian distribution according to the operating data curve and the probability density curve.

[0042] Furthermore, according to the verification result that the converter temperature parameters in the wind turbine cluster do not conform to the mixed Gaussian distribution, based on multiple health value intervals of the wind turbine cluster and the mean of the target converter temperature parameters within a preset time, the 3σ rule is used to determine the target abnormality level of the target wind turbine converter corresponding to the target converter temperature parameters.

[0043] In the implementation, based on the converter temperature parameters in the wind turbine cluster, taking the converter power module temperature as an example, the converter power module temperature of the target wind turbine is compared with the converter power module temperature of the wind turbine cluster (wind turbines of the same type in the wind farm). Although the data does not conform to the normal distribution, based on the operating data curve and the Gaussian probability density curve (kernel density function), the converter power module temperature data distribution can be fitted (or approximated) to a mixed Gaussian distribution of n=2. If it cannot be fitted to a mixed Gaussian distribution of n=2, then based on the converter power module temperature data statistical algorithm, the 3σ rule is used to further determine the target abnormal level of the target wind turbine converter corresponding to the target converter temperature parameter. Among them, when constructing a wind turbine cluster, if the number of wind turbine converters is larger, the shape of the Gaussian probability density curve (kernel density function) is closer to the theoretical statistical distribution, and the risk is smaller.

[0044] In order to illustrate the specific implementation method of step 204, the step 204 specifically includes: according to the average value of the target converter temperature parameter within the preset time, based on the cluster benchmarking algorithm, determining the target abnormality level of the target wind turbine converter corresponding to the target converter temperature parameter from multiple health value intervals of the wind turbine cluster; wherein, if there are at least two target converter temperature parameters, then selecting the minimum value from the average values ​​of at least two target converter temperature parameters as the average value of the target converter temperature parameter within the preset time.

[0045] In implementation, if there are at least two converter temperature parameters for the target wind turbine, the minimum value (minimum health value) is selected from the mean values ​​of at least two target converter temperature parameters as the mean value of the target converter temperature parameter within a preset time, and the cluster benchmarking algorithm is used to compare the mean value of the target converter temperature parameter with multiple health value intervals of the corresponding wind turbine cluster, and the abnormal level corresponding to the target converter temperature parameter is determined and used as the target abnormal level of the target wind turbine converter. Among them, for the cluster benchmarking method, since there is no need for algorithm training, the cluster benchmarking algorithm has high stability, and when determining the target abnormal level, it can effectively improve the stability of the determination result.

[0046] Specifically, based on the benchmarking method with the constructed wind turbine cluster, when the minimum healthy value of the target converter temperature parameter belongs to (80, 100), the converter temperature is considered normal, that is, the target wind turbine is normal; when the minimum healthy value of the target converter temperature parameter belongs to (60, 80), the converter temperature needs to be paid attention to, that is, the target wind turbine needs to be paid attention to; when the minimum healthy value of the target converter temperature parameter belongs to (40, 60), a converter temperature warning is generated, that is, the target wind turbine generates a warning to prompt the staff to inspect the entire wind turbine when inspecting the wind turbine, especially the converter of the target wind turbine; when the minimum healthy value of the target converter temperature parameter belongs to (0, 40), a converter temperature alarm is generated, that is, the target wind turbine generates an alarm to prompt the staff to take corresponding maintenance measures immediately for the entire wind turbine.

[0047] Step 205: Obtain a second converter temperature parameter with a rated power within a second preset range from the initial converter temperature parameter.

[0048] Step 206: Adjust the target abnormality level of the target wind turbine converter according to the second converter temperature parameter.

[0049] During implementation, in addition to the above-mentioned abnormal detection of the target wind turbine inverter, the second inverter temperature parameters outside the previously obtained 80%-120% rated power (low power) are detected to complete the detection of the missing inverter temperature parameters in the target wind turbine. For example, for the target wind turbine, when the temperature parameter of the low-power second inverter is high, if within a certain time period, the number of second inverter temperature parameters exceeding a certain temperature threshold (generally 80°C-90°C, different models have different thresholds, generally the maximum value of statistical data) and the total number of second inverter temperature parameters obtained within a certain time period are greater than the percentage threshold (2%), then the original target abnormality level is upgraded by one level, and the corresponding prompt information (warning or alarm) is updated.

[0050] According to the needs of actual application scenarios, the percentage threshold is not specifically limited. When the specific technical parameters of the target wind turbine equipment or the on-site alarm records of the target wind turbine equipment are determined, the percentage threshold can be adjusted in real time to more accurately locate the abnormality.

[0051] like Figure 3 As shown, by applying the technical solution of this embodiment, based on the frequency of running once a day, the historical data of the target converter temperature parameters of the target wind turbine set in the previous three days are selected. Taking a single converter power module temperature as an example, the target wind turbine set 1 ( Figure 3 -a2) deviates from the wind turbine cluster ( Figure 3 -a2) is more significant. Based on the horizontal axis, it can be seen that the temperature of the wind turbine of the target wind turbine 1 is higher (the temperature is proportional to the support integration of the horizontal axis), but the abnormal detection judgment based on this embodiment has not reached the warning and alarm levels; the target wind turbine 2 ( Figure 3 -b2) has a lower temperature than the wind turbine cluster, and the Gaussian probability density curve of the target wind turbine 2 is similar to that of the wind turbine cluster ( Figure 3 -b2) is closer to the Gaussian probability density curve of the curve with a lower peak, which shows that the target abnormality level of the target wind turbine 2 is the normal level.

[0052] in, Figure 3 -a1 represents the comparison of Gaussian probability density curves of target wind turbine 1 and wind turbine cluster (n=3), Figure 3 -a2 represents the comparison of Gaussian probability density curves of target wind turbine 1 and wind turbine cluster (n=46), Figure 3 -b1 represents the comparison of Gaussian probability density curves of target wind turbine 2 and wind turbine cluster (n=3), Figure 3-b2 represents the comparison of Gaussian probability density curves of target wind turbine 2 and wind turbine cluster (n=46), where the curve with higher peak value represents the probability distribution of converter temperature parameters of target wind turbine, and the curve with lower peak value represents the probability distribution of converter temperature parameters of wind turbine cluster. It can be seen that when the number of wind turbines in the cluster is more, the shape of the density function is closer to the theoretical statistical distribution, the risk is smaller, and the detection result is more accurate.

[0053] By applying the technical solution of this embodiment, it is possible to determine multiple health value intervals of a wind turbine cluster by calculating the mean and standard deviation of the converter temperature parameters in the wind turbine cluster; obtain the mean value of the target converter temperature parameter in the wind turbine cluster within a preset time; and determine the target abnormality level of the target wind turbine converter corresponding to the target converter temperature parameter based on the multiple health value intervals of the wind turbine cluster and the mean value of the target converter temperature parameter within a preset time. Compared with the existing technical solutions of evaluating the abnormal state of the wind turbine converter by setting a threshold or making advance predictions through a network model, this embodiment also incorporates the target converter temperature parameter of the target wind turbine into the cluster when constructing a wind turbine cluster to ensure the accuracy of the multiple health value intervals set, thereby effectively reducing the false alarm rate of abnormal detection of the target wind turbine and ensuring the accuracy of abnormal detection of the wind turbine.

[0054] Further, as Figure 1 The specific implementation of the method, the embodiment of the present application provides an abnormality detection system for a wind turbine converter, such as Figure 4 As shown, the system includes: a first determination module 42 , a second acquisition module 43 , and a second determination module 45 .

[0055] The first determination module 42 is used to determine a plurality of health value intervals of the wind turbine cluster by calculating the mean and standard deviation of the temperature parameters of the converters in the wind turbine cluster.

[0056] The second acquisition module 43 is used to obtain the average value of the target converter temperature parameter in the wind turbine cluster within a preset time.

[0057] The second determination module 45 is used to determine the target abnormality level of the target wind turbine converter corresponding to the target converter temperature parameter based on multiple health value intervals of the wind turbine cluster and the average value of the target converter temperature parameter within a preset time.

[0058] In specific application scenarios, such as Figure 5 As shown, the system further includes: a first acquisition module 41.

[0059] The first acquisition module 41 is used to acquire a first converter temperature parameter with a rated power within a first preset range from the initial converter temperature parameter, and use the first converter temperature parameter as the converter temperature parameter for constructing a wind turbine cluster.

[0060] In a specific application scenario, the converter temperature parameter includes one or more of the converter power module temperature, the converter grid-side inverter temperature, and the converter machine-side inverter temperature.

[0061] In a specific application scenario, the system further includes: a verification module 44 .

[0062] The verification module 44 is used to obtain the operating data curve and probability density curve of the wind turbine cluster according to the converter temperature parameters in the wind turbine cluster; and to verify whether the converter temperature parameters in the wind turbine cluster conform to the mixed Gaussian distribution according to the operating data curve and probability density curve.

[0063] In a specific application scenario, based on the verification module 44, the second determination module 45 is also used to determine the target abnormality level of the target wind turbine inverter corresponding to the target inverter temperature parameter based on the verification result that the inverter temperature parameter in the wind turbine cluster does not conform to the mixed Gaussian distribution, based on multiple health value intervals of the wind turbine cluster and the mean of the target inverter temperature parameter within a preset time, using the 3σ rule.

[0064] In a specific application scenario, the second determination module 45 is specifically used to determine the target abnormality level of the target wind turbine converter corresponding to the target converter temperature parameter from the multiple health value intervals based on the cluster benchmarking algorithm according to the average value of the target converter temperature parameter within the preset time; wherein, if there are at least two target converter temperature parameters, the minimum value is selected from the average values ​​of at least two target converter temperature parameters as the average value of the target converter temperature parameter within the preset time.

[0065] In a specific application scenario, the system further includes: an adjustment module 46 .

[0066] The adjustment module 46 is used to obtain a second converter temperature parameter with a rated power within a second preset range from the initial converter temperature parameter; and adjust a target abnormality level of the converter of the target wind turbine generator set according to the second converter temperature parameter.

[0067] It should be noted that for other corresponding descriptions of the functional units involved in the abnormality detection system for a wind turbine converter provided in the embodiment of the present application, reference can be made to Figure 1 and Figure 2 The corresponding description in will not be repeated here.

[0068] Based on the above Figure 1 and Figure 2 The method shown in the embodiment of the present application accordingly provides a computer storage medium on which a computer program is stored, and when the program is executed by a processor, the above-mentioned Figure 1 and Figure 2 The abnormality detection method of the wind turbine converter is shown.

[0069] Based on this understanding, the technical solution of the present application can be embodied in the form of a software product, which can be stored in a storage medium (which can be a CD-ROM, a USB flash drive, a mobile hard disk, etc.), and includes a number of instructions for enabling a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods described in each implementation scenario of the present application.

[0070] Based on the above Figure 1 , Figure 2 The method shown, and Figure 4 , Figure 5 In order to achieve the above-mentioned purpose, the embodiment of the present application further provides a computer device, which can be a personal computer, a server, a network device, etc. The physical device includes a storage medium and a processor; the storage medium is used to store a computer program; the processor is used to execute the computer program to achieve the above-mentioned Figure 1 and Figure 2 The abnormality detection method of the wind turbine converter is shown.

[0071] Optionally, the computer device may further include a user interface, a network interface, a camera, a radio frequency (RF) circuit, a sensor, an audio circuit, a WI-FI module, etc. The user interface may include a display, an input unit such as a keyboard, etc., and the optional user interface may also include a USB interface, a card reader interface, etc. The network interface may optionally include a standard wired interface, a wireless interface (such as a Bluetooth interface, a WI-FI interface), etc.

[0072] Those skilled in the art will appreciate that the computer device structure provided in this embodiment does not constitute a limitation on the physical device, and may include more or fewer components, or a combination of certain components, or different component arrangements.

[0073] The storage medium may also include an operating system and a network communication module. The operating system is a program that manages the hardware and software resources of a computer device and supports the operation of information processing programs and other software and / or programs. The network communication module is used to achieve communication between components within the storage medium and with other hardware and software in the physical device.

[0074] Through the description of the above implementation methods, those skilled in the art can clearly understand that the present application can be implemented by means of software plus the necessary general hardware platform, or by hardware. By applying the technical solution of the present application, compared with the existing technical solution of evaluating the abnormal state of the wind turbine converter by setting a threshold, or making advance predictions through a network model, when constructing a wind turbine cluster, the target converter temperature parameters of the target wind turbine converter are also included in the cluster to ensure the accuracy of the set multiple health value intervals, thereby effectively reducing the false alarm rate of abnormal detection of the target wind turbine converter and ensuring the accuracy of abnormal detection of the wind turbine converter.

[0075] Those skilled in the art will appreciate that the accompanying drawings are only schematic diagrams of a preferred implementation scenario, and the modules or processes in the accompanying drawings are not necessarily necessary for implementing the present application. Those skilled in the art will appreciate that the modules in the system in the implementation scenario can be distributed in the system of the implementation scenario according to the implementation scenario description, or can be changed accordingly and located in one or more systems different from the present implementation scenario. The modules of the above-mentioned implementation scenario can be combined into one module, or can be further split into multiple submodules.

[0076] The above serial numbers of this application are only for description and do not represent the advantages and disadvantages of the implementation scenarios. The above disclosure is only a few specific implementation scenarios of this application, but this application is not limited to them, and any changes that can be thought of by technicians in this field should fall within the scope of protection of this application.

Claims

1. A method for detecting abnormality of a wind turbine converter, characterized in that: include: By calculating the mean and standard deviation of the temperature parameters of the converters in the wind turbine cluster, multiple health value intervals of the wind turbine cluster are determined; Obtaining an average value of a temperature parameter of a target converter in the wind turbine cluster within a preset time; Based on a plurality of health value intervals of the wind turbine cluster and an average value of the target converter temperature parameter within a preset time, a target abnormality level of the target wind turbine converter corresponding to the target converter temperature parameter is determined.

2. The method according to claim 1, characterized in that The converter temperature parameter includes one or more of the converter power module temperature, the converter grid-side inverter temperature and the converter machine-side inverter temperature.

3. The method according to claim 1, characterized in that Before the step of determining a plurality of health value intervals of the wind turbine cluster by calculating the mean and standard deviation of the temperature parameters of the converters in the wind turbine cluster, the step further includes: A first converter temperature parameter with a rated power within a first preset range is obtained from the initial converter temperature parameter and used as the converter temperature parameter for constructing a wind turbine cluster.

4. The method according to claim 1, characterized in that: Before the step of determining the target abnormality level of the target wind turbine converter corresponding to the target converter temperature parameter based on the multiple health value intervals of the wind turbine cluster and the average value of the target converter temperature parameter within a preset time, the step further includes: According to the temperature parameters of the converters in the wind turbine cluster, obtaining the operating data curve and probability density curve of the wind turbine cluster; According to the operating condition data curve and the probability density curve, it is verified whether the temperature parameters of the converters in the wind turbine cluster conform to the mixed Gaussian distribution.

5. The method according to claim 1 or 4, characterized in that: According to the verification result that the converter temperature parameters in the wind turbine cluster do not conform to the mixed Gaussian distribution, based on multiple health value intervals of the wind turbine cluster and the mean value of the target converter temperature parameters within a preset time, the 3σ rule is used to determine the target abnormality level of the target wind turbine converter corresponding to the target converter temperature parameters.

6. The method according to claim 1, characterized in that The step of determining a target abnormality level of a target wind turbine converter corresponding to the target converter temperature parameter based on multiple health value intervals of the wind turbine cluster and an average value of the target converter temperature parameter within a preset time includes: According to the average value of the target converter temperature parameter within a preset time, determining the target abnormality level of the target wind turbine converter corresponding to the target converter temperature parameter from the multiple health value intervals based on a cluster benchmarking algorithm; If there are at least two target converter temperature parameters, a minimum value is selected from the average values ​​of the at least two target converter temperature parameters as the average value of the target converter temperature parameter within a preset time.

7. The method according to claim 1 or 3, characterized in that: The step of determining a target abnormality level of a target wind turbine converter corresponding to the target converter temperature parameter based on multiple health value intervals of the wind turbine cluster and an average value of the target converter temperature parameter within a preset time further includes: Obtaining a second converter temperature parameter having a rated power within a second preset range from the initial converter temperature parameter; The target abnormality level of the target wind turbine generator set converter is adjusted according to the second converter temperature parameter.

8. An abnormality detection system for a wind turbine converter, characterized in that: include: A first determination module is used to determine multiple health value intervals of the wind turbine cluster by calculating the mean and standard deviation of the temperature parameters of the converters in the wind turbine cluster; A second acquisition module is used to obtain the average value of the target converter temperature parameter in the wind turbine cluster within a preset time; The second determination module is used to determine the target abnormality level of the target wind turbine converter corresponding to the target converter temperature parameter based on multiple health value intervals of the wind turbine cluster and the average value of the target converter temperature parameter within a preset time.

9. A computer storage medium having a computer program stored thereon, characterized in that: When the program is executed by a processor, the abnormality detection method for a wind turbine converter according to any one of claims 1 to 7 is implemented.

10. A computer device comprising a storage medium, a processor, and a computer program stored in the storage medium and executable on the processor, characterized in that: When the processor executes the program, the abnormality detection method for the wind turbine converter according to any one of claims 1 to 7 is implemented.

Images