CN117169613A - Abnormality detection method and device for electronic device and wind farm - Google Patents

Abstract

The disclosure provides an abnormality detection method and device for an electronic device and a wind farm, wherein the abnormality detection method comprises the following steps: acquiring operation data of each wind turbine in a plurality of wind turbines in a wind farm; determining the average value of the temperature difference between the first temperature and the second temperature of each wind turbine generator under different fan powers; determining a first statistical value and a second statistical value of the temperature difference mean value; and determining whether the electronic device installed in the unit to be detected is abnormal by comparing the first statistical value with the second statistical value. According to the abnormality detection method and device for the electronic device and the wind farm, the abnormality detection for the electronic device can be realized under the condition that the sensor is not added, the electronic device with abnormal operation can be maintained in time, and the normal operation of the unit is ensured.

Description

Abnormality detection method and device for electronic device and wind farm

Technical Field

The present disclosure relates to the field of wind power generation, and more particularly, to an abnormality detection method and apparatus for an electronic device, and a wind farm.

Background

Many electronic devices are arranged in the wind generating set (also called a wind generating set) to support the normal operation of the set, the working states of the electronic devices are closely related to the operation of the whole set, and if the electronic devices have abnormal operation, the generating power, the service life of the set parts and the like can be influenced, and even the whole set can be stopped.

However, in existing detection schemes, on the one hand, anomaly detection for some electronic devices may be lacking; on the other hand, some existing anomaly detection schemes are generally implemented by adding sensors for sensing electronics, which increase the workload and cost of unit production and maintenance, and are not convenient for application in-service units.

Disclosure of Invention

In view of the problems that the incompleteness of an abnormality detection scheme of an electronic device in an existing wind turbine generator and the workload and cost of production and maintenance are increased due to the mode of adding a sensor, the disclosure provides an abnormality detection method and device of the electronic device and a wind power plant.

A first aspect of the present disclosure provides an abnormality detection method of an electronic device, the abnormality detection method including: acquiring operation data of each wind turbine in a plurality of wind turbines in a wind power plant, wherein the operation data comprises a first temperature of a space in which an electronic device is installed in the wind turbine, a second temperature of an environment in which the wind turbine is located and fan power; determining a temperature difference average value between the first temperature and the second temperature of each wind turbine generator under different fan powers, wherein the temperature difference average value refers to: an average value of the temperature differences between the first temperature and the second temperature corresponding to all times when the same fan power occurs; determining a first statistical value and a second statistical value of the temperature difference mean value, wherein the first statistical value represents the statistical value of the temperature difference mean value of a unit to be detected in the plurality of wind turbines, and the second statistical value represents the statistical value of the temperature difference mean value of part or all of the wind turbines in the wind farm; and determining whether the electronic device installed in the unit to be detected is abnormal or not by comparing the first statistical value with the second statistical value.

Optionally, the step of determining the first statistic and the second statistic of the mean value of the temperature difference includes: determining, for each fan power, an amount of difference between the temperature difference between the first temperature and the second temperature and the temperature difference mean at each time instant when the fan power occurs; determining an average value of the difference amounts corresponding to all the moments when the fan power appears as a temperature difference amplitude; and determining the first statistical value and the second statistical value based on the temperature difference amplitude.

Optionally, before determining the average value of the difference amounts as the temperature difference amplitude, the anomaly detection method further includes: and deleting the maximum value and the minimum value in the difference amounts corresponding to all the moments when the fan power occurs.

Optionally, the first statistical value includes a first average value, and the second statistical value includes a second average value, wherein the first average value is determined by: determining an average value of temperature difference amplitudes of the unit to be detected under all fan powers as the first average value, wherein the second average value is determined by the following steps: averaging the temperature difference amplitude of at least one first reference unit in the plurality of wind turbines to obtain an amplitude average value; and averaging the average values of the amplitude values under all fan powers to obtain the second average value, wherein the at least one first reference unit is the plurality of wind turbine units or the wind turbine units except the unit to be detected in the plurality of wind turbine units.

Optionally, the step of determining whether the electronic device mounted in the unit to be detected is abnormal comprises: and determining that the electronic device in the unit to be detected is abnormal under the condition that the ratio of the second average value to the first average value is larger than a first preset value.

Optionally, the first statistical value further comprises a third average value, and the second statistical value further comprises a fourth average value, wherein the third average value is determined by: determining an average value of the temperature difference average values of the unit to be detected under all fan powers as the third average value; wherein the fourth average value is determined by: averaging the temperature difference average value of each second reference unit under all fan powers aiming at least one second reference unit in the plurality of wind turbines to obtain an average value; and averaging the average values of all the second reference units to obtain the fourth average value, wherein the second reference units are wind power units except the unit to be detected in the plurality of wind power units.

Optionally, before averaging the average values of all the second reference units to obtain the fourth average value, the anomaly detection method further includes: and deleting the maximum value and the minimum value in the average value of the mean values of all the second reference units.

Optionally, the step of determining whether the electronic device mounted in the unit to be detected is abnormal comprises: and determining that the electronic device in the unit to be detected is abnormal under the condition that the ratio of the second average value to the first average value is larger than a first preset value and the difference between the fourth average value and the third average value is larger than a second preset value.

Optionally, before determining the temperature difference average value, the anomaly detection method further includes: and determining the occurrence frequency of each fan power in the plurality of fan powers in the operation data, and deleting the data corresponding to the fan powers with occurrence frequency smaller than a frequency threshold value from the operation data.

Optionally, before determining the temperature difference average value, the anomaly detection method further includes: and deleting the operation data of which the fan power is smaller than a power threshold value from the operation data.

Optionally, the electronic device is a Du/Dt-filter.

A second aspect of the present disclosure provides an abnormality detection apparatus of an electronic device, the abnormality detection apparatus including: the system comprises an acquisition unit, a control unit and a control unit, wherein the acquisition unit is configured to acquire operation data of each wind turbine in a plurality of wind turbines in a wind power plant, and the operation data comprise a first temperature of a space in which an electronic device is installed in the wind turbine, a second temperature of an environment in which the wind turbine is located and fan power; the temperature difference average value determining unit is configured to determine a temperature difference average value between the first temperature and the second temperature of each wind turbine generator set under different fan powers, wherein the temperature difference average value refers to: an average value of the temperature differences between the first temperature and the second temperature corresponding to all times when the same fan power occurs; a statistic determining unit configured to determine a first statistic and a second statistic of the temperature difference average, wherein the first statistic represents a statistic of the temperature difference average of a unit to be detected in the plurality of wind turbines, and the second statistic represents a statistic of the temperature difference average of some or all wind turbines in the wind farm; and an abnormality detection unit configured to determine whether or not an electronic device mounted in the unit to be detected is abnormal by comparing the first statistical value and the second statistical value.

A third aspect of the present disclosure provides an electronic device, comprising: a processor; a memory storing computer executable instructions, wherein the computer executable instructions, when executed by the processor, cause the processor to perform an anomaly detection method for an electronic device according to the present disclosure.

A fourth aspect of the present disclosure provides a computer-readable storage medium, which when executed by a processor, causes the processor to perform an abnormality detection method of an electronic device according to the present disclosure.

A fifth aspect of the present disclosure provides a wind farm comprising an anomaly detection device of an electronic device according to the present disclosure, or an electronic apparatus according to the present disclosure.

According to the abnormality detection method and device for the electronic device and the wind power plant, the temperature of the space where the electronic device is located, the ambient temperature where the wind power generation sets are located and the fan power can be utilized, and whether the electronic device in the set to be detected is abnormal or not is determined by counting the temperature difference average value of the two temperatures according to the plurality of wind power generation sets in the wind power plant.

Drawings

Fig. 1 is a schematic flowchart illustrating an abnormality detection method of an electronic device according to an exemplary embodiment of the present disclosure.

Fig. 2 is a schematic flowchart showing steps of determining a temperature difference amplitude in an abnormality detection method of an electronic device according to an exemplary embodiment of the present disclosure.

Fig. 3 is a schematic flowchart showing an example of an abnormality detection method of an electronic device according to an exemplary embodiment of the present disclosure.

Fig. 4 is a schematic block diagram illustrating an abnormality detection apparatus of an electronic device according to an exemplary embodiment of the present disclosure.

Fig. 5 is a schematic block diagram showing an example of an abnormality detection apparatus of an electronic device according to an exemplary embodiment of the present disclosure.

Fig. 6 is a schematic diagram showing an example of a parameter configuration interface of an abnormality detection apparatus of an electronic device according to an exemplary embodiment of the present disclosure.

Fig. 7 is a schematic diagram showing a detection result example of an abnormality detection scheme of an electronic device according to an exemplary embodiment of the present disclosure.

Detailed Description

The following detailed description is provided to assist the reader in obtaining a thorough understanding of the methods, apparatus, and/or systems described herein. However, various changes, modifications, and equivalents of the methods, apparatus, and/or systems described herein will be apparent after an understanding of the present disclosure. For example, the order of operations described herein is merely an example and is not limited to those set forth herein, but may be altered as will be apparent after an understanding of the disclosure of the application, except for operations that must occur in a specific order. Furthermore, descriptions of features known in the art may be omitted for clarity and conciseness.

The features described herein may be embodied in different forms and should not be construed as limited to the examples described herein. Rather, the examples described herein have been provided to illustrate only some of the many possible ways to implement the methods, devices, and/or systems described herein that will be apparent after an understanding of the present disclosure.

As used herein, the term "and/or" includes any one of the listed items associated as well as any combination of any two or more.

Although terms such as "first," "second," and "third" may be used herein to describe various elements, components, regions, layers or sections, these elements, components, regions, layers or sections should not be limited by these terms. Rather, these terms are only used to distinguish one element, component, region, layer or section from another element, component, region, layer or section. Thus, a first member, first component, first region, first layer, or first portion referred to in the examples described herein may also be referred to as a second member, second component, second region, second layer, or second portion without departing from the teachings of the examples.

In the description, when an element (such as a layer, region or substrate) is referred to as being "on" another element, "connected to" or "coupled to" the other element, it can be directly "on" the other element, be directly "connected to" or be "coupled to" the other element, or one or more other elements intervening elements may be present. In contrast, when an element is referred to as being "directly on" or "directly connected to" or "directly coupled to" another element, there may be no other element intervening elements present.

The terminology used herein is for the purpose of describing various examples only and is not intended to be limiting of the disclosure. Singular forms also are intended to include plural forms unless the context clearly indicates otherwise. The terms "comprises," "comprising," and "having" specify the presence of stated features, amounts, operations, components, elements, and/or combinations thereof, but do not preclude the presence or addition of one or more other features, amounts, operations, components, elements, and/or combinations thereof.

Unless defined otherwise, all terms (including technical and scientific terms) used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this disclosure belongs after understanding this disclosure. Unless explicitly so defined herein, terms (such as those defined in a general dictionary) should be construed to have meanings consistent with their meanings in the context of the relevant art and the present disclosure, and should not be interpreted idealized or overly formal.

In addition, in the description of the examples, when it is considered that detailed descriptions of well-known related structures or functions will cause a ambiguous explanation of the present disclosure, such detailed descriptions will be omitted.

As described above, in order to ensure the normal operation of the wind turbine, it is necessary to detect whether an abnormality occurs in an electronic device in the wind turbine, so as to be able to perform maintenance in time. Here, the electronic device may refer to any type of element, part, instrument, machine, etc. installed in the wind turbine to perform a function by supplying power, such as, but not limited to, a filter, a circuit breaker, etc.

For such electronic devices, on the one hand, anomaly detection of part of the electronic device may be lacking; on the other hand, in the proposed abnormality detection scheme, it is generally necessary to collect the operation characteristics of the electronic device by the sensor signal and then analyze the characteristics, for example, the characteristic amount may be input to an extreme learning machine, to output the result of whether or not abnormality has occurred in the electronic device by the extreme learning machine, or to make a judgment by comparing the characteristic amount with a threshold value. However, in the above solution, depending on the signal acquisition of the sensor, this requires adding additional sensors, increasing the workload and cost of production and maintenance of the unit, and for the in-service unit, it may also be necessary to perform structural transformation, rewiring, etc., and the implementation process is relatively complex.

In this regard, the present disclosure recognizes that, when the electronic device is operating normally, as the electronic device operates, a certain amount of heat is generated, which may cause a change in temperature in a space where the electronic device is installed.

Specifically, taking the Du/Dt filter as an example, du/Dt is a filter that filters and consumes spike voltages, which can reduce high frequency and spike voltages in a circuit while reducing the voltage change rate. The main components of the Du/Dt-filter comprise a series filter reactor (L), a filter capacitor (C) and a resistor (R), which is therefore also called RLC-filter. The Du/Dt filter can be applied to a direct-drive wind turbine generator set and used for filtering high-frequency spike voltage, preventing the high-frequency spike voltage from damaging insulation and protecting a generator.

The Du/Dt filter can be arranged in a cabin of the wind turbine generator, and the body temperature is high and easy to damage due to the fact that the Du/Dt filter works in an electric heating high-temperature state for a long time, however, fault detection measures for the Du/Dt filter are lacking at present, faults of the Du/Dt filter are difficult to discover in time, and potential threats are caused to the wind turbine generator and the converter.

In this case, the present disclosure further finds that temperature measuring elements are often provided in different locations of the wind turbine, for example temperature measuring elements provided inside the nacelle, but that there are no temperature measuring elements for electronics such as Du/Dt-filters, which makes it difficult to achieve abnormal state monitoring of the individual electronics from a temperature measuring point of view. However, the heat of the electronic device may cause a change in temperature in the space where the electronic device is installed.

For example, in the nacelle, the influence of the heating value of the Du/Dt-filter on the overall temperature change in the nacelle is relatively obvious, so that when the Du/Dt-filter in the nacelle fails, the temperature of the nacelle changes, and the temperature distribution law in the nacelle changes accordingly.

Based on the above study, the disclosure provides an electronic device abnormality detection scheme based on analysis of local space temperature data during operation of a wind turbine generator, and through characteristic processing of temperature data, failures of electronic devices such as a Du/Dt filter can be effectively detected, and loss caused by fan shutdown and electronic device operation with diseases is avoided.

In this regard, exemplary embodiments according to the present disclosure provide an abnormality detection method of an electronic device, an abnormality detection apparatus of an electronic device, a wind farm, an electronic device, and a computer-readable storage medium to solve at least one of the above problems.

According to a first aspect of the present disclosure, there is provided an abnormality detection method of an electronic device. Fig. 1 shows a schematic flowchart of an abnormality detection method of an electronic device according to an exemplary embodiment of the present disclosure.

As shown in fig. 1, the abnormality detection method of the electronic device may include the steps of:

in step S11, operational data for each of a plurality of wind turbines in a wind farm may be obtained.

In this step, the operation data may include a first temperature of a space in the wind turbine in which the electronic device is installed, a second temperature of an environment in which the wind turbine is located, and fan power.

Specifically, a plurality of wind turbines can be arranged in a wind power plant, and each wind turbine can be provided with the same type of electronic device. In addition, the plurality of wind turbines described herein may be the same type of wind turbines to improve accuracy of the detection results.

Here, the first temperature may be acquired by a separate physical temperature sensor provided in the space where the electronic device is installed, or may be calculated by a temperature at another location related to the temperature of the space, for example, may be determined by an algorithmically implemented virtual temperature sensor.

For example, taking electronics as an example of a Du/Dt-filter provided in the cabin, the first temperature may be a temperature sensed by a temperature sensor provided in the cabin.

The second temperature may be obtained by a temperature sensor provided in the wind turbine, or may be obtained by a temperature sensor provided outside the wind turbine.

It should be noted that, according to the exemplary embodiment of the present disclosure, the first temperature, the second temperature, and the fan power may be acquired in any suitable manner, which is not particularly limited by the present disclosure.

In this step S11, the operation data may be real-time data (e.g., SCADA data) of the wind farm within a certain period of time, for example, may be data of at least 7 days, so that a sufficient data amount may be ensured, and accuracy of the detection result is ensured.

The operation data acquired in this step may be data extracted from the whole data recorded during the operation of the wind farm, for example, the extraction may be performed according to the fields of the following table 1:

TABLE 1

Chinese name	Blower power	Cabin temperature	Ambient temperature
				English name	Power	Nacelle temperature	Ambient temperature

In addition, in the step, during or after the operation data is acquired, the data can be filtered to ensure the validity of the data, for example, the data participating in the anomaly detection calculation can be ensured to be the data of the wind turbine generator in the operation state.

As an example, from the obtained operation data, operation data with fan Power smaller than the Power threshold may be deleted, for example, when the operation data is extracted from the whole data recorded in the wind farm operation, all fields (for example, the fields shown in table 1) may be selected to be: data when Power is greater than p1, wherein p1 is a Power threshold value, and the data is used for representing the running state of the wind turbine, namely, when the Power threshold value is greater than the Power threshold value, the wind turbine can be considered to be in the running state; and when the power threshold value is smaller than or equal to the power threshold value, the wind turbine generator is considered to be in a non-running state. The power threshold p1 may be set according to practical situations, for example, it may be the power of the wind turbine generator during normal power generation.

Furthermore, as previously mentioned, the electronics described herein may be any type of element, part, instrument, machine, etc. installed in a wind turbine that performs a function by supplying power, such as, but not limited to, a filter, a circuit breaker, etc.

As an example, the electronic device may be the above-mentioned Du/Dt-filter. The Du/Dt filter is a main heating element in the nacelle of the wind turbine, and the rest heating elements have little influence on the total temperature of the nacelle, so that the temperature of the nacelle is mainly influenced by the ambient temperature and the heating value of the Du/Dt filter. Therefore, when the Du/Dt filter is abnormal, the Du/Dt filter also shows an appearance in the cabin temperature, specifically, when the Du/Dt filter in the cabin fails, a main heat source affecting the cabin temperature changes, so that the temperature distribution rule in the cabin also changes correspondingly.

However, the electronic device according to the exemplary embodiments of the present disclosure is not limited to the Du/Dt-filter, but may be other electronic devices that generate heat in operation, for example, may be small heat source devices such as yaw motors, frequency converters of radiators, cabin cabinets, etc., and the exemplary embodiments of the present disclosure are directed to giving a basic idea of analyzing the operation state of the electronic device based on the local spatial temperature data when the wind turbine generator is operated, and those skilled in the art may implement the present disclosure according to the actual electronic device, the installation location, and the environment in which it is actually located.

In step S12, a mean value of the temperature difference between the first temperature and the second temperature of each wind turbine at different fan powers may be determined.

Here, the temperature difference average value means: an average value of the temperature difference between the first temperature and the second temperature corresponding to all times when the same fan power occurs.

Specifically, for each wind turbine in the wind farm, the fan power, the first temperature, and the second temperature at each moment may be collected in time series, and thus, the collected fan power at each moment corresponds to a temperature difference (hereinafter may be denoted as "temperature_rise"), that is, a value obtained by subtracting the second temperature from the first temperature (may also be referred to as "temperature rise").

Here, because the fan power reflects the overall working state of the wind turbine generator, and the running state of the electronic device has correlation with the overall working state of the wind turbine generator, the fan power has certain coupling or dependency with the working state of the electronic device. In this regard, according to the abnormality detection method of the present disclosure, the temperature difference may be counted in consideration of the change of the fan power, and the operation state of the electronic device may be more effectively analyzed by counting the temperature difference under different fan powers, thereby realizing more accurate abnormality detection.

As an example, the acquired operational data may be binned according to fan power, and operational data at different fan powers may be counted. In particular, the same fan power may occur at different times, and for each fan power, the first temperature and the second temperature at their corresponding different times may be divided, i.e., the same fan power may correspond to one or more temperature differences.

For example, fan powers may be selected at predetermined power intervals (e.g., at 1 watt (W) intervals) and the temperature difference for each fan power at all times determined.

Alternatively, when the binning is performed in accordance with the fan powers, the number of times each of the plurality of fan powers appears in the operation data may be determined, and the data corresponding to the fan power whose number of occurrences is smaller than the number-of-times threshold (hereinafter may be denoted as "p 2") may be deleted from the operation data.

Specifically, the number of data (i.e. the number of occurrences in the operation data) corresponding to each fan power may be counted, and fan powers and related data thereof having a number of data greater than the number threshold may be screened out for subsequent calculations. The frequency threshold is the minimum value for counting the temperature data under the condition of power binning, so that the data quantity under each power binning in the anomaly detection calculation can be ensured, and the detection accuracy is improved.

After determining the temperature difference at all times for each fan power, an average of the temperature differences, that is, an average of the temperature differences (hereinafter, may be denoted as "wt_power_temp_mean"), for each fan power may be calculated. For each wind turbine, each fan power may correspond to a unique mean value of the temperature differences.

Furthermore, in this step, optionally, the operation data may be preprocessed before binning according to fan power. For example, the blank data in the operation data may be filled, specifically, the data may be averaged for a predetermined length of time (e.g., 1 minute), and the blank data in the operation data may be filled according to the adjacent values; and/or jump data in the operation data can be removed. The present disclosure is not limited thereto, and other preprocessing of the operation data may be performed according to actual needs.

In step S13, a first statistic and a second statistic of the mean temperature difference may be determined.

In this step, the first statistical value may represent a statistical value of a temperature difference average value of a set to be detected in the plurality of wind turbines, and the second statistical value may represent a statistical value of a temperature difference average value of some or all wind turbines in the wind farm.

Specifically, according to the method disclosed by the invention, any one of a plurality of wind turbines in the wind power plant can be used as a to-be-detected unit, and other wind turbines in the plurality of wind turbines can be used as a reference unit, so that reference data are provided for measuring the working states of electronic devices of the to-be-detected unit. Therefore, the method disclosed by the disclosure can be used for sequentially detecting all units in the plurality of wind turbines, and when any unit is selected as the unit to be detected, other units can be used as reference units.

According to the method disclosed by the invention, the first statistical value can reflect the change rule of the temperature difference of the unit to be detected, and the second statistical value can reflect the change rule of the temperature difference of the whole plurality of wind turbines in the wind power plant, so that whether the unit to be detected is in abnormal operation can be determined by comparing the first statistical value and the second statistical value.

Here, the second statistics are determined for all or part of the wind turbines in the wind farm, and in an example, the second statistics may be determined for all other wind turbines (i.e. all reference turbines) of the plurality of wind turbines except for the one to be detected.

In one case, the first statistic and the second statistic may be determined based on the temperature difference magnitude.

As an example, as shown in fig. 2, the process of determining the first statistic and the second statistic of the mean value of the temperature difference may include the steps of:

in step S21, for each fan power, an amount of difference between the temperature difference between the first temperature and the second temperature at each time when the fan power occurs and the temperature difference average value may be determined.

Specifically, as described in step S12 above, the same fan power corresponds to one or more temperature differences temperature_rise, and may correspond to a unique temperature difference average value wt_power_temp_mean, based on which, in this step S21, a difference between each temperature difference and the temperature difference average value, i.e., a difference amount (hereinafter may be expressed as "wt_power_temp_error") may be found. The difference is one-to-one with the temperature difference, that is, each fan power corresponds to one or more differences.

In step S22, an average value of the difference amounts corresponding to all the times at which the fan power occurs may be determined as the temperature difference amplitude.

Specifically, for each wind turbine in the wind farm, an average of the absolute values of all of the above-described difference amounts wt_power_temp_error at each fan power may be determined as a temperature difference amplitude (hereinafter may be denoted as "wt_power_temp_error_abs").

Here, each fan power of each wind turbine unit corresponds to a unique temperature difference magnitude, which may represent an absolute temperature difference loss (MAE) at each fan power, and the data may be saved, for example, in the form of the following table 2:

TABLE 2

Alternatively, before determining the average value of the difference amounts as the temperature difference amplitude, the maximum value and the minimum value of the difference amounts corresponding to all the moments when the fan power occurs may be deleted to improve the accuracy of the calculation.

In step S23, a first statistic and a second statistic may be determined based on the magnitude of the temperature difference.

As an example, the first statistic may include a first average value, the second statistic may include a second average value, and the first average value and the second average value may be determined based on the temperature difference amplitude.

Specifically, as described above, for each wind turbine, each of the different fan powers corresponds to a unique temperature difference amplitude, where an average value of the temperature difference amplitudes wt_power_temp_error_abs of the to-be-detected turbine at all fan powers (e.g., the plurality of fan powers selected in step S12) may be determined as a first average value (hereinafter may be denoted as "wt_temp_error_mean").

The second average value may be determined by: averaging the temperature difference amplitude of at least one first reference unit in the plurality of wind turbines to obtain an amplitude average value; and averaging the average values of the amplitude values under all fan powers to obtain a second average value.

Specifically, the at least one first reference unit may be all of the plurality of wind turbines in the wind farm described in step S11, or wind turbines of the plurality of wind turbines except for the to-be-detected unit. That is, the at least one first reference unit may or may not include a unit to be detected.

Here, for each first reference unit, it may correspond to the temperature difference magnitudes wt_power_temp_error_abs at all fan powers, for example, in case of n fan powers, each first reference unit may correspond to n temperature difference magnitudes.

Thus, in this step, the magnitudes of the temperature differences at each fan power for all the first reference units may be averaged as a magnitude average (hereinafter may be denoted as "wf_power_temp_error_abs") for each fan power. Each fan power may correspond to an average value of the magnitudes

Further, the average values of the magnitudes of all fan powers may be averaged to obtain a second average value (hereinafter may be denoted as "wf_temp_error_mean") to reflect the temperature difference variation condition of all the first reference units.

In this way, it is possible to determine whether the electronic device of the unit to be detected is abnormal by comparing the first average value wt_temp_error_mean and the second average value wf_temp_error_mean, which will be described in detail in step S13 below.

In another case, the first statistic and the second statistic may be determined based on the temperature difference mean.

As an example, the first statistical value may include a third average value, the second statistical value may include a fourth average value, and the third average value and the fourth average value may be determined based on the temperature difference average value.

Specifically, in the above step S12, the determination process of determining the temperature difference average value wt_power_temp_mean of each wind turbine at each fan power has been described, and here, the average value of the temperature difference average value wt_power_temp_mean of the to-be-detected wind turbine at all fan powers may be determined as a third average value (hereinafter may be denoted as "wt_temp_mean").

The fourth average value may be determined by: averaging the temperature difference average value of each second reference unit under all fan power aiming at least one second reference unit in the plurality of wind turbines to obtain an average value; and averaging the average value of all the second reference units to obtain a fourth average value.

In particular, the second reference set may be a wind set of the plurality of wind sets other than the set to be detected. When the first reference unit for calculating the integral temperature difference amplitude of the wind power plant is selected, the unit to be detected can be eliminated, and the unit to be detected can also be contained, because the influence of the data of the unit to be detected on the temperature difference amplitude is relatively small, and the influence of the data of the unit to be detected on the accuracy of a detection result is not great; and because the data of the unit to be detected possibly affects the whole temperature difference average value of the wind power plant, the unit to be detected can be eliminated when the second reference unit is selected, so that the influence of the data of the unit to be detected on the average value of the average value is avoided.

Here, for each second reference unit, there is one temperature difference average value at each fan power, for example, in case of n fan powers, each second reference unit may correspond to n temperature difference average values.

Thus, in this step, the average value of the temperature difference of each second reference unit at all fan powers may be averaged to obtain an average value (hereinafter may be denoted as "wt_temp_mean"), and then the average value of the average value wt_temp_mean of all second reference units may be averaged to obtain a fourth average value (hereinafter may be denoted as "wf_temp_mean") to reflect the temperature difference change condition of all second reference units.

Optionally, before averaging the average values of all the second reference units to obtain the fourth average value, the maximum value and the minimum value in the average values of all the second reference units may be deleted, so as to improve the accuracy of calculation.

In this way, it is possible to determine whether the electronic device of the unit to be detected is abnormal by comparing the third average value wt_temp_mean and the fourth average value wf_temp_mean, which will be described in detail in step S13 below.

Although it is described above that the first statistical value may include a first average value and/or a third average value, and the second statistical value may include a second average value and/or a fourth average value, the first statistical value and the second statistical value are not limited to the above examples, but may be other statistical values, such as mode, median, sum, maximum, minimum, variance, mean square error, etc., as long as the first statistical value may represent statistical values of temperature difference averages of units to be detected among a plurality of wind turbines and the second statistical value may represent statistical values of temperature difference averages of some or all of the wind turbines in the wind farm.

In step S14, it may be determined whether the electronic device mounted in the unit to be tested is abnormal by comparing the first statistical value and the second statistical value.

In the case where the first statistical value includes a first average value wt_temp_error_mean and the second statistical value includes a second average value wf_temp_error_mean, it may be determined whether the electronic device in the unit to be detected is abnormal by comparing the first average value and the second average value.

As an example, it may be determined whether the ratio of the second average value to the first average value is greater than a first preset value (hereinafter may be denoted as "p 3"), and the first preset value p3 may represent a minimum warning multiple for a single machine set that is lower than the temperature amplitude of the wind farm as a whole, and when the minimum warning multiple is exceeded, an abnormality may be alerted to the electronic device.

If the ratio of the second average value to the first average value is greater than the first preset value p3, that is, wf_temp_error_mean/wt_temp_error_mean > p3, it may be determined that the electronic device in the unit to be detected is abnormal; and under the condition that the ratio of the second average value to the first average value is smaller than or equal to a first preset value p3, the normal operation of the electronic devices in the unit to be detected can be determined.

In this example, the detection scheme from the angle of the temperature amplitude (for example, the first average value and the second average value) can avoid false alarm caused by inconsistent cabin temperature of the same engine due to the problems of ambient temperature and water cooling.

In the case where the first statistical value includes a third average value wt_temp_mean and the second statistical value includes a fourth average value wf_temp_mean, it may be determined whether the electronic device in the unit to be detected is abnormal by comparing the third average value and the fourth average value.

As an example, it may be determined whether or not the difference between the fourth average value and the third average value is greater than a second preset value (hereinafter may be denoted as "p 4"), and the second preset value p4 may represent a minimum warning early-warning temperature (the unit may be in the c) of the temperature difference average value of the individual wind turbine units and the wind farm as a whole, and when the minimum warning early-warning temperature is exceeded, an abnormality may occur in the alarmed electronic device.

If the difference between the fourth average value and the third average value is greater than the second preset value p4, that is, wf_temp_mean-wt_temp_mean > p4, it may be determined that the electronic device in the unit to be detected is abnormal; and under the condition that the difference between the fourth average value and the third average value is smaller than or equal to a second preset value p4, determining that the electronic devices in the unit to be detected are in normal operation.

The above description has been made separately for the example in which the first statistical value includes the first average value and the second statistical value includes the second average value and the example in which the first statistical value includes the third average value and the second statistical value includes the fourth average value, however, it should be noted that, according to the exemplary embodiment of the present disclosure, whether or not the electronic device is abnormal may be detected according to either of the above two examples, but it is not limited thereto, and the two examples may also be detected in combination.

In particular, the first statistical value may comprise a first average value and a third average value, and the second statistical value may comprise a second average value and a fourth average value.

And determining that the electronic device in the unit to be detected is abnormal under the condition that the ratio of the second average value to the first average value is larger than a first preset value p3 and the difference between the fourth average value and the third average value is larger than a second preset value p 4.

And if the ratio of the second average value to the first average value is smaller than or equal to a first preset value p3, or the difference between the fourth average value and the third average value is smaller than or equal to a second preset value p4, determining that the electronic device in the unit to be detected is in normal operation.

In this way, it is possible to comprehensively determine whether the electronic device is operating normally from the angle of the temperature amplitude (related to the first average value and the second average value) and from the angle of the temperature average value (related to the third average value and the fourth average value), respectively, and when one of the conditions is not satisfied, it is not determined that an abnormality occurs. By such multi-angle judgment, the problem of false alarm can be avoided.

According to the exemplary embodiments of the present disclosure described above, an abnormality detection method for an electronic device in a wind turbine may be provided, which may implement abnormality detection for an electronic device without adding a sensor, and repair an electronic device operating abnormally in time, ensuring normal operation of the wind turbine.

Specifically, the method can analyze the temperature change amplitude of the unit to be detected by using the cleaned data according to the actual condition of SCADA transient data of the wind power plant, compare the temperature change amplitude of the unit to be detected with the temperature change amplitude of other reference units, and analyze the activity condition of electronic devices according to the temperature data distribution condition. Because the method is based on a temperature detection scheme, the method can utilize the existing temperature measuring points to collect temperature signals, analyze the data characteristics of the temperature change amplitude, and compare the data characteristics with the same type of units in the wind power plant to complete indirect monitoring of electronic devices.

The method also considers the coupling between the fan power and the temperature in the space where the electronic device is located, takes the power as a sub-bin, simultaneously considers the data easy to be interfered, counts the data quantity of the temperature data of the sub-bin power, discards the data quantity if the data quantity is too small, takes the mode of the data quantity as the temperature amplitude of the current power point, and compares the average temperature variation amplitude of the data quantity with the cabin temperature variation amplitude of other units in the whole time period, so that the accuracy of the detection result can be improved.

In this manner, device anomaly detection can be performed using the variability of temperature data using the anomaly detection method according to an exemplary embodiment of the present disclosure, which solves the problem that temperature-free measurement point devices cannot be monitored when they fail, and achieves indirect monitoring of the temperature-free measurement point devices (e.g., du/Dt filters), compared to the existing scheme in which the temperature sensor directly detects the device temperature to determine whether it is anomalous.

In addition, the anomaly detection method according to the exemplary embodiment of the present disclosure may be used in combination with an existing detection scheme, for example, in the case of determining that the temperature change amplitude of the Du/Dt filter itself is abnormal, the method of the present disclosure may be used to determine whether the nacelle temperature performance is low in the same type of unit of the wind farm, so as to implement dual verification, and ensure the detection accuracy.

An overall flow of a specific example of the abnormality detection method of the electronic device according to an exemplary embodiment of the present disclosure will be described below with reference to fig. 3, and each step in the flow employs a certain implementation of each step described above, but is not limited thereto, and may be the above-mentioned modified implementation or other alternative implementations that can be envisioned by those skilled in the art.

As shown in fig. 3, in step S101, the early warning flag for prompting the abnormal operation of the electronic device may be initialized, that is, the first early warning flag Result 1= '0' and the second early warning flag Result 2= '0'.

In step S102, operational data may be read, the operational data including a fan power of each wind turbine in the wind farm, a first temperature (e.g., a nacelle temperature of the wind turbine), and a second temperature (i.e., a temperature of an environment in which the wind turbine is located). For example, the data as shown in Table 1 above may be extracted from SCADA data recorded during operation of the wind farm.

In step S103, the read operation data may be screened. For example, the operation data of the wind turbine generator in the operation state can be screened, and specifically, whether the fan power in each operation data meets the "fan power > power threshold p1" can be judged.

In step S104, temperature difference data may be acquired. Specifically, the difference between the first temperature and the second temperature may be calculated for each piece of operation data to determine a temperature difference, where a temperature difference field may be added to the operation data.

In step S105, the operation data may be preprocessed. For example, the blank data points in the operation data, the noise-removed data, and the like may be filled, and here, the blank data may be filled in such a manner that the data of a period (for example, 1 minute) including the time of the blank data is averaged.

In step S106, the data may be binned and screened according to fan power for each wind turbine. As an example, the operational data may be binned by integer power values, and the data within each bin (i.e., corresponding to one fan power) may also be counted, bins whose data count is greater than a predetermined threshold p2 may be screened out, and bins whose data count is less than or equal to the predetermined threshold p2 may be removed.

In step S107, for each fan power, a mean value of the temperature difference at that fan power may be calculated. Specifically, the mean value of all the temperature differences can be calculated according to the data in the bin corresponding to each fan power.

Based on the temperature difference average value obtained in step S107, whether the electronic device is abnormal or not can be judged through statistics of two aspects.

In one aspect, the temperature difference magnitude may be determined based on the temperature difference average to make the determination.

Specifically, in step S108, for each fan power, a difference amount between each temperature difference and the temperature difference average value may be calculated, and absolute values of all the difference amounts are averaged to obtain the temperature difference amplitude.

In step S109, the maximum and minimum values of the temperature difference magnitudes of the unit to be detected under all fan powers may be removed, and the remaining temperature difference magnitudes are averaged to obtain a first average value.

In step S110, the temperature difference magnitudes of all the first reference units may be averaged at each fan power to obtain a magnitude average value, and the magnitude average values at all the fan powers may be averaged to obtain a second average value.

In this step, the maximum and minimum values of the temperature difference magnitudes of all the first reference units at each fan power may also be removed, and then the magnitude average value may be calculated using the remaining temperature difference magnitudes.

Here, when abnormality detection is performed on the plurality of wind turbines one by one, in the above step, the temperature difference average value, the temperature difference amplitude value, and the first average value of each turbine may be calculated, and the binning power of each turbine may be the same or different when power binning is performed. When one wind turbine generator of the plurality of wind turbine generator sets is determined to be a to-be-detected wind turbine generator set under the condition that the power of the sub-bins is different, the data can be read from the operation data of other wind turbine generator sets according to each power point of the power sub-bins of the to-be-detected wind turbine generator set, so that the power of the plurality of fans selected for all the wind turbine generator sets is the same.

In step S111, it may be determined whether the ratio of the second average value to the first average value is greater than a first preset value p3, and in case that the ratio is greater than the first preset value p3, in step S112, the first early warning flag Result1 may be set to 1; in case of being less than or equal to the first preset value p3, step S111 may be performed.

On the other hand, the judgment can be made based on the temperature difference average value.

Specifically, in step S113, the temperature average of the unit to be detected under all fan powers may be averaged to obtain a third average value. As an example, when abnormality detection is performed on the plurality of wind turbines one by one, a third average value of each wind turbine may be calculated, and when one wind turbine of the plurality of wind turbines is determined to be a to-be-detected wind turbine, the corresponding third average value may be directly read.

In step S114, the average value of the temperature differences of the second reference units under all fan powers may be averaged to obtain an average value, and the average value of the average values of all second reference units may be averaged to obtain a fourth average value.

In this step, the maximum and minimum values in the temperature difference averages of all the second reference units at each fan power may also be removed, and then the amplitude average value may be calculated using the remaining temperature difference amplitudes.

In step S115, it may be determined whether the difference between the fourth average value and the third average value is greater than the second preset value p4, and if so, in step S116, the second early warning flag Result2 may be set to 1; in case of being less than or equal to the second preset value p4, step S111 may be performed.

In step S117, it may be determined whether the first early warning flag bit and the second early warning flag bit are both set based on the determination results of the above two aspects. In the case that the first early warning flag bit is set and the second early warning flag bit is set, that is, result 1+=1 and Result 2+=1, in step S118, early warning may be reported; and under the condition that at least one of the first early warning zone bit and the second early warning zone bit is not set, ending the detection and not giving an alarm.

The abnormality detection method of the electronic device according to the exemplary embodiment of the present disclosure has been described above in connection with fig. 1 to 3, it should be understood that various parameter values, threshold values, etc. referred to above may be adjusted according to practical applications.

Fig. 4 is a schematic block diagram illustrating an abnormality detection apparatus of an electronic device according to an exemplary embodiment of the present disclosure. As shown in fig. 4, the abnormality detection apparatus of the electronic device includes an acquisition unit 100, a temperature difference average value determination unit 200, a statistical value determination unit 300, and an abnormality detection unit 400.

The obtaining unit 100 is configured to obtain operation data of each of a plurality of wind turbines in a wind farm, where the operation data includes a first temperature of a space in which an electronic device is installed in the wind turbine, a second temperature of an environment in which the wind turbine is located, and fan power;

the temperature difference average determining unit 200 is configured to determine a temperature difference average between a first temperature and a second temperature of each wind turbine at different fan powers, where the temperature difference average refers to: an average value of the temperature differences between the first temperature and the second temperature corresponding to all times when the same fan power occurs;

the statistics determining unit 300 is configured to determine a first statistic and a second statistic of the temperature difference averages, wherein the first statistic represents a statistic of the temperature difference averages of the units to be detected in the plurality of wind turbines, and the second statistic represents a statistic of the temperature difference averages of some or all of the wind turbines in the wind farm;

The abnormality detection unit 400 is configured to determine whether or not the electronic device mounted in the unit to be detected is abnormal by comparing the first statistical value and the second statistical value.

As an example, the statistic determining unit 300 is further configured to: determining, for each fan power, an amount of difference between a temperature difference between a first temperature and a second temperature at each time instant when the fan power occurs and a temperature difference average; determining an average value of difference amounts corresponding to all moments when the fan power appears as a temperature difference amplitude; based on the temperature difference amplitude, a first statistic and a second statistic are determined.

As an example, the statistic determining unit 300 is configured to: the maximum value and the minimum value of the difference amounts corresponding to all the moments when the fan power occurs are deleted before the average value of the difference amounts is determined as the temperature difference amplitude.

As an example, the first statistic includes a first average value and the second statistic includes a second average value.

The first average value is determined by: and determining the average value of the temperature difference amplitude values of the unit to be detected under all fan powers as a first average value.

The second average value is determined by: averaging the temperature difference amplitude of at least one first reference unit in the plurality of wind turbines to obtain an amplitude average value; and averaging the amplitude average values under all fan powers to obtain a second average value, wherein at least one first reference unit is a plurality of wind power units or wind power units except a unit to be detected in the plurality of wind power units.

As an example, the abnormality detection unit 400 is further configured to: and determining that the electronic device in the unit to be detected is abnormal under the condition that the ratio of the second average value to the first average value is larger than a first preset value.

As an example, the first statistic further comprises a third average value and the second statistic further comprises a fourth average value.

The third average value is determined by: and determining the average value of the temperature difference average value of the unit to be detected under all fan powers as a third average value.

The fourth average value is determined by: averaging the temperature difference average value of each second reference unit under all fan power aiming at least one second reference unit in the plurality of wind turbines to obtain an average value; and averaging the average value of all the second reference units to obtain a fourth average value, wherein the second reference units are wind power units except for the units to be detected in the plurality of wind power units.

As an example, the statistic determining unit 300 is further configured to: and deleting the maximum value and the minimum value in the average value of all the second reference units before averaging the average value of all the second reference units to obtain a fourth average value.

As an example, the abnormality detection unit 400 is further configured to: and determining that the electronic device in the unit to be detected is abnormal under the condition that the ratio of the second average value to the first average value is larger than a first preset value and the difference between the fourth average value and the third average value is larger than a second preset value.

As an example, the statistic determining unit 300 is further configured to: before determining the temperature difference average value, determining the occurrence frequency of each fan power in the plurality of fan powers in the operation data, and deleting the data corresponding to the fan powers with occurrence frequency smaller than the frequency threshold value from the operation data.

As an example, the statistic determining unit 300 is further configured to: and deleting the operation data with fan power smaller than the power threshold value from the operation data before determining the temperature difference average value.

The specific manner in which the individual units perform the operations in relation to the apparatus of the above embodiments has been described in detail in relation to the embodiments of the method and will not be described in detail here.

Fig. 5 is a schematic block diagram showing an example of an abnormality detection apparatus of an electronic device according to an exemplary embodiment of the present disclosure.

In the example shown in fig. 5, the abnormality detection apparatus may include a data input module 10, a parameter input module 20, a data cleaning and preprocessing module 30, a feature extraction and model construction module 40, an abnormality detection module 50, and a result display module 60. As shown in fig. 5, the respective modules of the abnormality detection apparatus may be communicatively connected to the processor 2 and the display screen 3 of the hardware device 1 to perform functions of the respective modules through the processor 2 and to present processing results of the respective modules through the display screen 3. Here, the hardware device 1 may be, for example, a computer device.

Data input module 10 may obtain SCADA data for each wind turbine in the wind farm from a SCADA data source and provide the obtained operational data to parameter input module 20 for parameter input module 20 to extract data for the required data fields, which may include a wind turbine ID, a fan power, a first temperature, and a second temperature.

The data cleansing and preprocessing module 30 may perform data cleansing and preprocessing on the operational data from the parameter input module 20. The feature extraction and model construction module 40 may perform feature extraction and construct a computational model based on the operational data from the data cleansing and preprocessing module 30 to perform result determination by the anomaly detection module 50, thereby enabling effective detection of electronic device anomalies. The result display module 70 may transmit the determination result to the display screen 3 to visualize the detection result.

Fig. 6 is a schematic diagram showing an example of an abnormality detection parameter configuration interface of an abnormality detection device of an electronic device according to an exemplary embodiment of the present disclosure.

As shown in fig. 6, a wind turbine generator and wind farm difference early warning multiple value, that is, the first preset value p3 mentioned above, may be input in the anomaly detection parameter configuration interface. The wind turbine generator and the wind farm temperature difference early warning value, namely the second preset value p4, can be input into the abnormality detection parameter configuration interface. In this way, in the application of the abnormality detection apparatus for an electronic device according to the exemplary embodiment of the present disclosure, abnormality detection of the electronic device can be completed by specifying only two preset values, and the convenience of detection and the detection efficiency are improved.

Fig. 7 is a schematic diagram showing a detection result example of an abnormality detection scheme of an electronic device according to an exemplary embodiment of the present disclosure.

As shown in fig. 7, with the abnormality detection scheme of the electronic device described above, the abnormality state of the monitored electronic device may be alerted, for example, the ID of the warning unit may be directly output.

In addition, as shown in fig. 7, the difference between the temperature difference distribution of the early warning unit and the whole wind power plant can be also shown, and the visual mode is used for assisting operation and maintenance personnel in understanding actual conditions on a result page so as to intuitively embody the fault degree of the electronic device, thereby being capable of timely maintaining the electronic device.

According to a third aspect of the present disclosure, there is provided an electronic device, comprising: a processor; a memory storing computer executable instructions that, when executed by the processor, cause the processor to perform the method of anomaly detection for an electronic device according to the present disclosure.

By way of example, the electronic device may be a PC computer, tablet device, personal digital assistant, smart phone, or other device capable of executing the above-described set of instructions. Here, the electronic device is not necessarily a single electronic device, but may be any device or an aggregate of circuits capable of executing the above-described instructions (or instruction set) singly or in combination. The electronic device may also be part of an integrated control system or system manager, or may be configured as a portable electronic device that interfaces with either locally or remotely (e.g., via wireless transmission). In addition, the electronic device may also include a video display (such as a liquid crystal display) and a user interaction interface (such as a keyboard, mouse, touch input device, etc.). All components of the electronic device may be connected to each other via a bus and/or a network.

The processor may include a Central Processing Unit (CPU), a Graphics Processor (GPU), a programmable logic device, a special purpose processor system, a microcontroller, or a microprocessor. By way of example, and not limitation, processors may also include analog processors, digital processors, microprocessors, multi-core processors, processor arrays, network processors, and the like.

The processor may execute instructions or code stored in the memory, wherein the memory may also store data. The instructions and data may also be transmitted and received over a network via a network interface device, which may employ any known transmission protocol.

The memory may be integrated with the processor, for example, RAM or flash memory disposed within an integrated circuit microprocessor or the like. In addition, the memory may include a stand-alone device, such as an external disk drive, a storage array, or any other storage device usable by a database system. The memory and the processor may be operatively coupled or may communicate with each other, for example, through an I/O port, a network connection, etc., such that the processor is able to read files stored in the memory.

According to a fourth aspect of the present disclosure, a computer-readable storage medium is provided. The instructions in the computer-readable storage medium, when executed by the processor, cause the processor to perform the method of anomaly detection for an electronic device according to the present disclosure.

In particular, the abnormality detection method of the electronic device according to the embodiment of the present disclosure may be written as a computer program and stored on a computer-readable storage medium. Examples of the computer readable storage medium include: read-only memory (ROM), random-access programmable read-only memory (PROM), electrically erasable programmable read-only memory (EEPROM), random-access memory (RAM), dynamic random-access memory (DRAM), static random-access memory (SRAM), flash memory, nonvolatile memory, CD-ROM, CD-R, CD + R, CD-RW, CD+RW, DVD-ROM, DVD-R, DVD + R, DVD-RW, DVD+RW, DVD-RAM, BD-ROM, BD-R, BD-R LTH, BD-RE, blu-ray or optical disk storage, hard Disk Drives (HDD), solid State Disks (SSD), card memory (such as multimedia cards, secure Digital (SD) cards or ultra-fast digital (XD) cards), magnetic tape, floppy disks, magneto-optical data storage, hard disks, solid state disks, and any other means configured to store computer programs and any associated data, data files and data structures in a non-transitory manner and to provide the computer programs and any associated data, data files and data structures to a processor or computer to enable the processor or computer to execute the programs. In one example, the computer program and any associated data, data files, and data structures are distributed across networked computer systems such that the computer program and any associated data, data files, and data structures are stored, accessed, and executed in a distributed manner by one or more processors or computers.

According to a fifth aspect of the present disclosure, a wind farm is provided, which may comprise a plurality of wind turbines, and may further comprise an anomaly detection device according to the above-described electronic device of the present disclosure, or an electronic apparatus according to the above-described electronic device of the present disclosure.

The wind farm according to the exemplary embodiments of the present disclosure has the same advantageous effects as the abnormality detection method and apparatus of the electronic device and the electronic device described above, and thus will not be described here again.

According to the abnormality detection method and device for the electronic device and the wind power plant, a scheme for detecting the running state of the electronic device based on an indirect temperature relationship is provided, the running data of the wind power plant is used for monitoring the indirect temperature change amplitude and the temperature state of the wind turbine in real time, the abnormality in the running of the electronic device is found in time, and the running of the wind turbine is prevented from being influenced by abnormality such as failure and sub-health running of the electronic device.

The abnormality detection method and device for the electronic device and the wind farm creatively use fan power as a reference for monitoring temperature amplitude change points, and monitor the temperature difference data distribution of indirect temperature as a reference for temperature change analysis.

According to the abnormality detection method and device for the electronic device and the wind power plant, the abnormality of the electronic device is creatively detected indirectly by using the temperature data, two conditions of the temperature amplitude change and the temperature average value of the cabin can be screened out, and the conditions are respectively compared with the data of the whole wind power plant, so that the accuracy is high.

While certain embodiments have been shown and described, it would be appreciated by those skilled in the art that changes and modifications may be made to these embodiments without departing from the principles and spirit of the disclosure, the scope of which is defined in the claims and their equivalents.

Claims (15)

1. An abnormality detection method of an electronic device, characterized by comprising:

acquiring operation data of each wind turbine in a plurality of wind turbines in a wind power plant, wherein the operation data comprises a first temperature of a space in which an electronic device is installed in the wind turbine, a second temperature of an environment in which the wind turbine is located and fan power;

determining a temperature difference average value between the first temperature and the second temperature of each wind turbine generator under different fan powers, wherein the temperature difference average value refers to: an average value of the temperature differences between the first temperature and the second temperature corresponding to all times when the same fan power occurs;

determining a first statistical value and a second statistical value of the temperature difference mean value, wherein the first statistical value represents the statistical value of the temperature difference mean value of a unit to be detected in the plurality of wind turbines, and the second statistical value represents the statistical value of the temperature difference mean value of part or all of the wind turbines in the wind farm;

And determining whether the electronic device installed in the unit to be detected is abnormal or not by comparing the first statistical value with the second statistical value.

2. The anomaly detection method of claim 1, wherein determining the first and second statistics of the mean temperature difference comprises:

determining, for each fan power, an amount of difference between the temperature difference between the first temperature and the second temperature and the temperature difference mean at each time instant when the fan power occurs;

determining an average value of the difference amounts corresponding to all the moments when the fan power appears as a temperature difference amplitude;

and determining the first statistical value and the second statistical value based on the temperature difference amplitude.

3. The abnormality detection method according to claim 2, characterized in that before determining the average value of the difference amounts as a temperature difference amplitude, the abnormality detection method further includes:

and deleting the maximum value and the minimum value in the difference amounts corresponding to all the moments when the fan power occurs.

4. The anomaly detection method of claim 2, wherein the first statistic comprises a first average value and the second statistic comprises a second average value,

Wherein the first average value is determined by:

determining the average value of the temperature difference amplitude values of the unit to be detected under all fan powers as the first average value,

wherein the second average value is determined by:

averaging the temperature difference amplitude of at least one first reference unit in the plurality of wind turbines to obtain an amplitude average value;

averaging the average values of the amplitude values under all fan powers to obtain the second average value,

the at least one first reference unit is the plurality of wind turbine generators, or is a wind turbine generator unit except the unit to be detected in the plurality of wind turbine generator units.

5. The abnormality detection method according to claim 4, characterized in that the step of determining whether or not the electronic device mounted in the unit to be detected is abnormal includes:

and determining that the electronic device in the unit to be detected is abnormal under the condition that the ratio of the second average value to the first average value is larger than a first preset value.

6. The anomaly detection method of claim 4 wherein the first statistic further comprises a third average value, the second statistic further comprises a fourth average value,

Wherein the third average value is determined by:

determining an average value of the temperature difference average values of the unit to be detected under all fan powers as the third average value;

wherein the fourth average value is determined by:

averaging the temperature difference average value of each second reference unit under all fan powers aiming at least one second reference unit in the plurality of wind turbines to obtain an average value;

averaging the average values of all the average values of the second reference units to obtain a fourth average value,

the second reference unit is a wind turbine except the unit to be detected in the plurality of wind turbine.

7. The abnormality detection method according to claim 6, characterized in that before averaging the average values of all second reference units to obtain the fourth average value, the abnormality detection method further includes:

and deleting the maximum value and the minimum value in the average value of the mean values of all the second reference units.

8. The abnormality detection method according to claim 6, characterized in that the step of determining whether or not the electronic device mounted in the unit to be detected is abnormal includes:

And determining that the electronic device in the unit to be detected is abnormal under the condition that the ratio of the second average value to the first average value is larger than a first preset value and the difference between the fourth average value and the third average value is larger than a second preset value.

9. The abnormality detection method according to claim 1, characterized in that before determining the temperature difference average value, the abnormality detection method further comprises:

and determining the occurrence frequency of each fan power in the plurality of fan powers in the operation data, and deleting the data corresponding to the fan powers with occurrence frequency smaller than a frequency threshold value from the operation data.

10. The abnormality detection method according to claim 1, characterized in that before determining the temperature difference average value, the abnormality detection method further comprises: and deleting the operation data of which the fan power is smaller than a power threshold value from the operation data.

11. The abnormality detection method according to claim 1, characterized in that the electronic device is a Du/Dt-filter.

12. An abnormality detection apparatus for an electronic device, characterized by comprising:

the system comprises an acquisition unit, a control unit and a control unit, wherein the acquisition unit is configured to acquire operation data of each wind turbine in a plurality of wind turbines in a wind power plant, and the operation data comprise a first temperature of a space in which an electronic device is installed in the wind turbine, a second temperature of an environment in which the wind turbine is located and fan power;

The temperature difference average value determining unit is configured to determine a temperature difference average value between the first temperature and the second temperature of each wind turbine generator set under different fan powers, wherein the temperature difference average value refers to: an average value of the temperature differences between the first temperature and the second temperature corresponding to all times when the same fan power occurs;

a statistic determining unit configured to determine a first statistic and a second statistic of the temperature difference average, wherein the first statistic represents a statistic of the temperature difference average of a unit to be detected in the plurality of wind turbines, and the second statistic represents a statistic of the temperature difference average of some or all wind turbines in the wind farm;

and an abnormality detection unit configured to determine whether or not an electronic device mounted in the unit to be detected is abnormal by comparing the first statistical value and the second statistical value.

13. An electronic device, the electronic device comprising:

a processor;

a memory storing computer-executable instructions,

wherein the computer executable instructions, when executed by the processor, cause the processor to perform the anomaly detection method of an electronic device as claimed in any one of claims 1 to 11.

14. A computer readable storage medium, characterized in that instructions in the computer readable storage medium, when executed by a processor, cause the processor to perform the anomaly detection method of an electronic device according to any one of claims 1-11.

15. A wind farm, characterized in that it comprises an abnormality detection device of an electronic device according to claim 12, or an electronic apparatus according to claim 13.