Fault detection method and device for transmission chain of wind turbine generator

Abstract

The invention provides a wind turbine generator transmission chain fault detection method and device, and relates to the technical field of fault detection.The wind turbine generator transmission chain fault detection method comprises the steps that time sequence operation data and state waveform data of a wind turbine generator transmission chain are obtained; determining an abnormal characteristic index of the transmission chain of the wind turbine generator according to whether the time sequence operation data meets a preset target rule or not; according to the state waveform data, determining a time domain characteristic index and a frequency domain characteristic index of a transmission chain of the wind turbine generator; and based on the abnormal feature index, the time domain feature index and the frequency domain feature index, determining fusion features, and determining a fault detection result of the wind turbine generator transmission chain according to the fusion features, thereby solving the technical problems of incomplete data feature mining and low fault detection accuracy in the prior art.

Description

Technical Field

[0001] The present application relates to the technical field of fault detection, and in particular to a method and device for detecting a fault in a transmission chain of a wind turbine generator set. Background Art

[0002] The wind turbine transmission chain system is a key object for condition monitoring and fault diagnosis. Fault prediction and health management of the transmission chain are important guarantees for the efficient operation of wind power equipment. Real-time monitoring of the operating status of the wind turbine transmission chain and early warning and positioning before serious faults occur are conducive to extending the service life of major components of the transmission chain system and reducing power generation losses and operation and maintenance costs.

[0003] At present, most wind turbines are equipped with Supervisory Control And Data Acquisition (SCADA) systems and Condition Monitoring Systems (CMS) to collect various operating parameters of wind turbines in different modes, such as speed, temperature, vibration, etc. Most of the fault warnings of wind turbine transmission chain systems are based on a single signal source, SCADA data or CMS data. However, when a transmission chain system fails, there is obvious interference and coupling between the fault characteristics, and there is obvious correlation between different components in the transmission chain system. Therefore, when analyzing based on a single signal source, feature mining is not comprehensive enough, and the accuracy of fault detection and warning is not high. Summary of the invention

[0004] The present application aims to solve one of the technical problems in the related art at least to some extent.

[0005] To this end, the first objective of the present application is to propose a wind turbine transmission chain fault detection method to achieve accurate fault detection.

[0006] The second objective of the present application is to provide a wind turbine transmission chain fault detection device.

[0007] The third objective of the present application is to provide an electronic device.

[0008] A fourth objective of the present application is to provide a computer-readable storage medium.

[0009] A fifth object of the present application is to provide a computer program product.

[0010] To achieve the above-mentioned purpose, the first embodiment of the present application proposes a method for detecting a wind turbine transmission chain fault, comprising:

[0011] Obtaining the timing operation data and state waveform data of the wind turbine transmission chain;

[0012] Determining abnormal characteristic indicators of the wind turbine transmission chain according to whether the time series operation data meets a preset target rule;

[0013] Determining the time domain characteristic index and the frequency domain characteristic index of the wind turbine transmission chain according to the state waveform data;

[0014] Based on the abnormal characteristic index, the time domain characteristic index and the frequency domain characteristic index, a fusion feature is determined, and a fault detection result of the wind turbine transmission chain is determined according to the fusion feature.

[0015] To achieve the above-mentioned purpose, the second embodiment of the present application proposes a wind turbine transmission chain fault detection device, comprising:

[0016] The first acquisition module is used to acquire the timing operation data and state waveform data of the wind turbine transmission chain;

[0017] A second acquisition module is used to determine the abnormal characteristic index of the transmission chain of the wind turbine generator set according to whether the time series operation data meets the preset target rules;

[0018] A third acquisition module is used to determine the time domain characteristic index and the frequency domain characteristic index of the wind turbine transmission chain according to the state waveform data;

[0019] The fault detection module is used to determine a fusion feature based on the abnormal feature index, the time domain feature index and the frequency domain feature index, and determine a fault detection result of the wind turbine transmission chain according to the fusion feature.

[0020] To achieve the above-mentioned purpose, the third aspect of the present application provides an electronic device, including: a processor, and a memory communicatively connected to the processor;

[0021] The memory stores computer-executable instructions;

[0022] The processor executes the computer-executable instructions stored in the memory to implement the method as described in the embodiment of the first aspect.

[0023] To achieve the above-mentioned purpose, the fourth aspect embodiment of the present application proposes a computer-readable storage medium, in which computer execution instructions are stored. When the computer execution instructions are executed by a processor, they are used to implement the method described in the first aspect embodiment.

[0024] To achieve the above-mentioned purpose, the fifth aspect of the present application proposes a computer program product, including a computer program, which implements the method described in the first aspect when executed by a processor.

[0025] The wind turbine transmission chain fault detection method and device provided in the present application obtain the time-series operation data and state waveform data of the wind turbine transmission chain, match and judge based on the time domain operation data and the abnormal rules in the target rules, so as to determine the abnormal characteristic indicators of the wind turbine transmission chain, obtain the time domain characteristic indicators and frequency domain characteristic indicators based on the state waveform data, fully mine the features in the state waveform data, fuse the abnormal characteristic indicators, time domain characteristic indicators and frequency domain characteristic indicators to obtain the fused features for fault detection, thus solving the problem that the current feature mining is not comprehensive enough and the fault detection and early warning accuracy is not high.

[0026] Additional aspects and advantages of the present application will be given in part in the description below, and in part will become apparent from the description below, or will be learned through the practice of the present application. BRIEF DESCRIPTION OF THE DRAWINGS

[0027] The above and / or additional aspects and advantages of the present application will become apparent and easily understood from the following description of the embodiments in conjunction with the accompanying drawings, in which:

[0028] Figure 1 A schematic flow chart of a wind turbine transmission chain fault detection method provided in an embodiment of the present application;

[0029] Figure 2 A schematic diagram of a process for obtaining abnormal characteristic indicators provided in an embodiment of the present application;

[0030] Figure 3 A schematic diagram of a process for obtaining characteristic indicators and frequency domain characteristic indicators provided in an embodiment of the present application;

[0031] Figure 4 A schematic diagram of a process for obtaining a fault detection result provided in an embodiment of the present application;

[0032] Figure 5 A schematic flow chart of another wind turbine transmission chain fault detection method provided in an embodiment of the present application;

[0033] Figure 6 A logical schematic diagram of a wind turbine transmission chain fault detection method provided in an embodiment of the present application;

[0034] Figure 7 A schematic structural diagram of a wind turbine transmission chain fault detection device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0035] Embodiments of the present application are described in detail below, and examples of the embodiments are shown in the accompanying drawings, wherein the same or similar reference numerals throughout represent the same or similar elements or elements having the same or similar functions. The embodiments described below with reference to the accompanying drawings are exemplary and are intended to be used to explain the present application, and should not be construed as limiting the present application.

[0036] The wind turbine transmission chain fault detection method and device according to the embodiment of the present application are described below with reference to the accompanying drawings.

[0037] Figure 1 The following is a flow chart of a method for detecting a wind turbine transmission chain fault provided by an embodiment of the present application. Figure 1 As shown, the method comprises the following steps:

[0038] S101, acquiring the timing operation data and state waveform data of the wind turbine transmission chain.

[0039] In some implementations, the sequential operation data of the wind turbine transmission chain can be monitored by the SCADA system, which may include wind turbine operation-related parameters such as temperature, power, and speed; optionally, this embodiment can collect data at intervals of 1 second to obtain sequential operation data within a day.

[0040] In some implementations, the state waveform data of the wind turbine transmission chain can be monitored by the CMS system, which may include vibration signal waveform data of various important components such as the gearbox, generator and main shaft; optionally, this embodiment can collect data at a time interval of every 2 hours to obtain the state waveform data within a day.

[0041] Optionally, the timing operation data and the status waveform data may be data collected when the wind turbine was operating the previous day. The relevant data generated when the wind turbine is operating is stored on the big data platform. After a day's operation is completed, the data of the previous day is read from the big data platform in the early morning to obtain the timing operation data and the status waveform data for subsequent analysis. In other embodiments, half a day or longer may be used as an analysis cycle, that is, the timing operation data and the status waveform data within half a day or longer are obtained for fault detection, which is not described in detail here.

[0042] In some implementations, data preprocessing can also be performed on SCADA data and CMS data separately. For SCADA data, the temperature of the temperature measurement point at the current moment is greatly affected by the temperature at the previous moment, and is less affected by the short-term fluctuations of characteristic parameters such as wind speed and power. Therefore, abnormal data with large short-term fluctuations can be eliminated, and missing data can be supplemented; for CMS data, due to failure of the sensor or collector channel, the collected vibration data may be distorted. In the data preprocessing stage, it is necessary to eliminate failed data, such as asymmetric signal waveforms, waveforms with very small signal amplitudes, clipping, abnormal shocks, and waveforms with oversaturated shocks.

[0043] S102, determining abnormal characteristic indicators of the wind turbine transmission chain according to whether the time series operation data meets a preset target rule.

[0044] Optionally, the preset target rules may be rules for determining whether there are abnormal conditions, such as the abnormal condition of rapid temperature rise in a short period of time, the rule for abnormal temperature of the engine drive end bearing, the rule for abnormal temperature of the engine non-drive end bearing, and the rule for gearbox-related temperature abnormalities, etc.; based on the temperature data in the timing operation data, determine whether any of the preset target rules is met, and if any of the abnormal rules is met, it indicates that there is an abnormality in the current timing operation data.

[0045] Optionally, this embodiment can set the exception values ​​to 0 and 1, and perform a match judgment on each of the preset target rules based on the timing operation data. In response to the timing operation data satisfying the corresponding rule, that is, when the abnormal situation is met, the corresponding exception value is 1; in response to the timing operation data not satisfying the corresponding rule, that is, when it is in a normal situation, the corresponding exception value is 0.

[0046] It can be understood that a match is made to each of the preset target rules based on the time series operation data, and the abnormal value corresponding to the time series operation data under each rule is determined, so as to obtain the same number of abnormal values ​​as the rules, and all the abnormal values ​​are combined to obtain abnormal feature indicators, for example, all the abnormal values ​​are used to form a feature vector, and the feature vector is used as the abnormal feature indicator.

[0047] S103, determining a time domain characteristic index and a frequency domain characteristic index of a wind turbine transmission chain according to the state waveform data.

[0048] In some implementations, the state waveform data is collected time domain waveform data, and the time domain waveform data can be converted to obtain corresponding frequency domain waveform data, and the frequency domain characteristic index can be calculated based on the frequency domain waveform data.

[0049] Optionally, the time domain characteristic index may include an effective value, a variance, a square root amplitude, a peak value, a time domain entropy, and other indexes that characterize the time domain waveform characteristics.

[0050] Optionally, the frequency domain characteristic indicators may include frequency domain entropy, envelope spectrum entropy, envelope spectrum peak factor, and different levels of meshing sideband energy, among which envelope spectrum entropy and envelope spectrum peak factor may be indicators calculated by extracting the upper envelope of the frequency domain waveform data from the upper envelope.

[0051] In some implementations, a wind turbine may include different key components such as bearings and gearboxes. The bearings include inner and outer ring balls, and the gearboxes include planetary gears and sun gears, etc. Therefore, different frequency domain indicators can be calculated separately through the frequency domain waveforms of the bearings and gearboxes. For example, the frequency domain characteristic indicators of the bearings include the inner ring envelope spectrum peak factor, the outer ring envelope spectrum peak factor, and the rolling element envelope spectrum peak factor, etc.; the frequency domain characteristic indicators of the gearbox include the first-level meshing low-speed sideband energy, the first-level meshing high-speed sideband energy, the second-level meshing low-speed sideband energy, etc.

[0052] S104, determining fusion features based on the abnormal feature index, the time domain feature index, and the frequency domain feature index, and determining a fault detection result of the wind turbine transmission chain according to the fusion features.

[0053] Optionally, the abnormal feature indicators, time domain feature indicators and frequency domain feature indicators can be spliced ​​together to obtain fused features. In some implementations, basic information and operating parameters of the wind turbine can also be obtained, such as additional feature information such as rated speed, wind speed, generator speed, etc., and fused features can be obtained by fusing the additional feature information with the abnormal feature indicators, time domain feature indicators and frequency domain feature indicators.

[0054] The fused features are input into the pre-trained fault identification model to obtain the fault detection result of whether there is a fault in the wind turbine transmission chain, thereby improving the accuracy of fault detection.

[0055] In this embodiment, by acquiring the timing operation data and state waveform data of the wind turbine transmission chain, matching and judging are performed based on the time domain operation data and the abnormal rules in the target rules, so as to determine the abnormal characteristic indicators of the wind turbine transmission chain, and acquiring the time domain characteristic indicators and frequency domain characteristic indicators based on the state waveform data, fully mining the features in the state waveform data, and fusion the abnormal characteristic indicators, time domain characteristic indicators and frequency domain characteristic indicators to obtain fusion features, and performing fault detection with more comprehensive and rich fusion features to obtain more accurate and reliable fault detection results, thereby improving the accuracy of fault analysis.

[0056] On the basis of the above embodiment, the process of obtaining the abnormal characteristic index is described. In this embodiment, the time series operation data includes at least one of the generator active power, the fan wind speed, the generator speed, the main shaft speed, the unit operation status, the generator drive end bearing temperature, the generator non-drive end bearing temperature, the gearbox oil temperature, the inverter power, the gearbox drive end bearing temperature and the gearbox non-drive end bearing temperature; Figure 2 A schematic diagram of a process for obtaining abnormal characteristic indicators provided in an embodiment of the present application. Figure 2 As shown, the method includes:

[0057] S201, in response to the unit operating state being the grid-connected state, at the same moment, based on the generator active power and the generator non-drive end bearing temperature, determine whether the generator non-drive end bearing temperature abnormality rule is met to obtain a first abnormal value.

[0058] Optionally, the unit operation status may include a grid-connected state, a standby state, a shutdown state, and a maintenance state, etc. This embodiment analyzes the unit operation status when it is a grid-connected state.

[0059] Optionally, the wind farm units can be divided into power intervals according to the active power of the generator to obtain the first power interval and the second power interval. For example, for a 0.85MW unit, the first power interval based on the active power of the generator is [600,∞), and the second power interval is [0,600); for a 1.25MW unit, the first power interval based on the active power of the generator is [1000,∞), and the second power interval is [0,1000); for the current moment, the unit is determined to be in the first power interval or the second power interval according to the interval into which the active power of the generator of the unit falls.

[0060] In some implementations, the time interval of the time series operation data can be processed. In this embodiment, the data with a sampling interval of 1 second is averaged and converted into time series operation data with an interval of 1 minute, that is, the data within 1 minute is averaged as the data within the 1 minute, thereby obtaining time series operation data with an interval of 1 minute; in this embodiment, the same moment is at the moment of every minute, and the first abnormal value is obtained.

[0061] For the first power interval, it can be determined that the non-drive end bearing temperature of the generator of the unit is at least higher than the first continuous time for which the drive end bearing temperature of the generator is a fixed value; this embodiment can perform a box plot analysis on the non-drive end bearing temperature of the generator to determine that the non-drive end bearing temperature of the generator is at least higher than the drive end bearing temperature of the generator for the first continuous time for which the fixed value is higher. For example, if the fixed value is 20 degrees, it is determined that the non-drive end bearing temperature of the generator is at least 20 degrees higher than the drive end bearing temperature of the generator for the first continuous time.

[0062] In response to the first continuous duration being greater than the preset time length, the first abnormal value of the unit is determined to be 1; optionally, assuming that the preset time length is 10 minutes, when the first continuous duration is greater than 10 minutes, it is determined that the non-drive end bearing temperature of the generator of the unit is abnormal, and the corresponding first abnormal value is 1; otherwise, there is no abnormality in the non-drive end bearing temperature of the generator of the unit, and the first abnormal value is 0.

[0063] For the second power range, it can be determined whether the non-drive end bearing temperature of the generator of the unit is greater than the second preset temperature; in response to the non-drive end bearing temperature of the generator of the unit being greater than the second preset temperature, the first abnormal value of the unit is determined to be 1; otherwise, the first abnormal value of the unit is determined to be 0; the second preset temperature can be 70 degrees.

[0064] S202, in response to the unit operating state being the grid-connected state, at the same moment, based on the generator active power and the generator drive end bearing temperature, determine whether the generator drive end bearing temperature abnormality rule is met to obtain a second abnormal value.

[0065] For the first power interval, it can be determined that the generator drive end bearing temperature of the unit is at least higher than the generator non-drive end bearing temperature for a second continuous period of time which is a fixed value; this embodiment can perform a box plot analysis on the generator drive end bearing temperature to determine that the generator drive end bearing temperature is at least higher than the generator non-drive end bearing temperature for a second continuous period of time which is a fixed value. For example, if the fixed value is 20 degrees, it is determined that the generator drive end bearing temperature is at least 20 degrees higher than the generator non-drive end bearing temperature for a second continuous period of time.

[0066] In response to the second continuous duration being greater than the preset time length, the first abnormal value of the unit is determined to be 1; optionally, the preset time length is 10 minutes, then when the second continuous duration is greater than 10 minutes, it is determined that the generator drive end bearing temperature of the unit is abnormal, and the corresponding first abnormal value is 1; otherwise, there is no abnormality in the generator drive end bearing temperature of the unit, and the first abnormal value is 0.

[0067] For the second power range, it can be determined whether the generator drive end bearing temperature of the unit is greater than the second preset temperature; in response to the generator drive end bearing temperature of the unit being greater than the second preset temperature, the first abnormal value of the unit is determined to be 1; otherwise, the first abnormal value of the unit is determined to be 0; the second preset temperature can be 70 degrees.

[0068] S203, in response to the unit operating state being the grid-connected state, at the same moment, based on the generator active power and the gearbox oil temperature, determine whether the gearbox oil temperature abnormality rule is met to obtain a third abnormal value.

[0069] For the first power range, the third continuous duration that the gearbox oil temperature of the unit is higher than the first preset temperature can be determined; this embodiment can perform a box diagram analysis on the gearbox oil temperature to determine the third continuous duration that the gearbox oil temperature is higher than the first preset temperature. For example, the first preset temperature is the sum of the average value of the gearbox temperature and a fixed value, and the fixed value is 20 degrees. Then, it is determined that the gearbox temperature is continuously higher than the average temperature value + 20 degrees for the third continuous duration.

[0070] In response to the third continuous duration being greater than the preset time length, the first abnormal value of the unit is determined to be 1; optionally, the preset time length is 10 minutes, then when the third continuous duration is greater than 10 minutes, it is determined that the gearbox oil temperature of the unit is abnormal, and the corresponding first abnormal value is 1; otherwise, there is no abnormality in the gearbox oil temperature of the unit, and the first abnormal value is 0.

[0071] For the second power range, it can be determined whether the gearbox oil temperature of the unit is greater than the second preset temperature; in response to the gearbox oil temperature of the unit being greater than the second preset temperature, the first abnormal value of the unit is determined to be 1; otherwise, the first abnormal value of the unit is determined to be 0; the second preset temperature can be 70 degrees.

[0072] S204, determining whether a gearbox drive end bearing temperature abnormality rule is met based on the inverter power and the gearbox drive end bearing temperature, and obtaining a fourth abnormal value.

[0073] The inverter power collected every second is obtained, and whether the inverter power of the unit is greater than the preset power is determined according to the inverter power; optionally, the preset power may be 2000kW, that is, whether the inverter power is greater than 2000kW is determined.

[0074] In response to the inverter power being greater than the preset power, it is determined that the gearbox drive end bearing temperature is greater than the third preset temperature for the fourth continuous time; in this embodiment, the third preset temperature may be 67.5 degrees, that is, when the inverter power is greater than 2000kW, it is determined that the gearbox drive end bearing temperature is greater than 67.5 degrees for the fourth continuous time.

[0075] In response to the fourth continuous duration being greater than the preset time length, the fourth abnormal value of the unit is determined to be 1; in this embodiment, the preset time length is 10 minutes, that is, when the fourth continuous duration is greater than 10 minutes, it is determined that the gearbox drive end bearing temperature of the unit is abnormal, and the fourth abnormal value is 1; otherwise, it is determined that there is no abnormality in the gearbox drive end bearing temperature of the unit, and the fourth abnormal value is 0.

[0076] S205, determining whether a gear box non-drive end bearing temperature abnormality rule is met according to the inverter power and the gear box non-drive end bearing temperature, and obtaining a fifth abnormal value.

[0077] The inverter power collected every second is obtained, and whether the inverter power of the unit is greater than the preset power is determined according to the inverter power at the second level; optionally, the preset power can be 2000kW, that is, whether the inverter power is greater than 2000kW is determined.

[0078] In response to the inverter power being greater than the preset power, it is determined that the gear box non-drive end bearing temperature is greater than the third preset temperature for the fifth consecutive time; in this embodiment, the third preset temperature may be 67.5 degrees, that is, when the inverter power is greater than 2000kW, it is determined that the gear box non-drive end bearing temperature is greater than 67.5 degrees for the fifth consecutive time.

[0079] In response to the fifth continuous duration being greater than the preset time length, the fifth abnormal value of the unit is determined to be 1; in this embodiment, the preset time length is 10 minutes, that is, when the fifth continuous duration is greater than 10 minutes, it is determined that the temperature of the non-drive end bearing of the gearbox of the unit is abnormal, and the fifth abnormal value is 1; otherwise, it is determined that there is no abnormality in the temperature of the non-drive end bearing of the gearbox of the unit, and the fifth abnormal value is 0.

[0080] S206, obtaining the startup time of the wind turbine generator set, and determining whether the abnormal rule of the generator drive end bearing temperature rising too fast is met according to the startup time and the degree of change of the generator drive end bearing temperature, and obtaining a sixth abnormal value.

[0081] Optionally, the unit can be divided into an initial startup stage and a normal operation stage according to the startup time; in this embodiment, the time period from the startup of the unit to the grid-connected operation for 1 hour is divided into the initial startup stage; the power generation state of the grid-connected operation for 1 hour and thereafter is divided into the normal operation stage.

[0082] For the unit in the initial stage of startup, the first change value of the generator drive end bearing temperature within a fixed time period is determined. In response to the first change value of two consecutive fixed time periods being greater than the first preset change value, the sixth abnormal value of the unit is determined to be 1; assuming that the fixed time period is 30 seconds, the temperature rise value of the generator drive end bearing temperature within 30 seconds is obtained as the first change value; if the first change value within 30 seconds is greater than the first preset change value twice in a row, the unit is determined to be abnormal. For example, if the first preset change value is 0.5 degrees, then the first change value within 30 seconds is greater than 0.5 degrees in a row, and it is determined that the generator drive end bearing temperature of the unit rises too fast, and the sixth abnormal value is 1; otherwise, it is determined that the generator drive end bearing temperature of the unit does not rise too fast, and the sixth abnormal value is 0.

[0083] For the unit in the normal operating stage, the third change value of the generator drive end bearing temperature within the fixed time period is determined. In response to the third change value of two consecutive fixed time periods being greater than the second preset change value, the sixth abnormal value of the unit is determined to be 1; optionally, the fixed time period can be 30 seconds, and the second preset change value is 0.3 degrees. If the temperature rise value (third change value) within two consecutive 30 seconds is greater than 0.3 degrees, it is determined that the unit has an abnormal situation where the generator drive end bearing temperature rises too quickly, and the sixth abnormal value is 1; otherwise, it is determined that the unit does not have an abnormal situation where the generator drive end bearing temperature rises too quickly, and the sixth abnormal value is 0.

[0084] S207, determining whether the abnormal rule of excessively rapid rise in the non-drive end bearing temperature of the generator is satisfied according to the startup time and the degree of change in the non-drive end bearing temperature of the generator, and obtaining a seventh abnormal value.

[0085] For the unit in the initial stage of startup, the second change value of the generator non-drive end bearing temperature within a fixed time period is determined. In response to the second change value of two consecutive fixed time periods being greater than the first preset change value, the seventh abnormal value of the unit is determined to be 1; optionally, the fixed time period can be 30 seconds, and the first preset change value is 0.5 degrees. If the temperature rise value (second change value) within two consecutive 30 seconds is greater than 0.5 degrees, it is determined that the unit has an abnormal situation that the generator non-drive end bearing temperature rises too quickly, and the seventh abnormal value is 1; otherwise, it is determined that the unit does not have an abnormal situation that the generator non-drive end bearing temperature rises too quickly, and the seventh abnormal value is 0.

[0086] For the unit in the normal operating stage, the fourth change value of the generator non-drive end bearing temperature within a fixed time period is determined. In response to the fourth change value of two consecutive fixed time periods being greater than the second preset change value, the seventh abnormal value of the unit is determined to be 1; optionally, the fixed time period can be 30 seconds, and the second preset change value is 0.3 degrees. If the temperature rise value (fourth change value) within two consecutive 30 seconds is greater than 0.3 degrees, it is determined that the unit has an abnormal situation that the generator non-drive end bearing temperature rises too quickly, and the seventh abnormal value is 1; otherwise, it is determined that the unit does not have an abnormal situation that the generator non-drive end bearing temperature rises too quickly, and the seventh abnormal value is 0.

[0087] S208: Determine an abnormal characteristic index of the wind turbine transmission chain based on the first abnormal value to the seventh abnormal value.

[0088] It can be understood that the execution order of steps S201-S207 in this embodiment can be changed or executed simultaneously. This embodiment is only an example and the specific execution order is not limited. The value of each abnormal value is 0 or 1, and the abnormal characteristic index of the wind turbine transmission chain is determined based on the results of 7 abnormal values ​​from the first abnormal value to the seventh abnormal value.

[0089] Based on the above-mentioned method for obtaining the first to seventh abnormal values, a table corresponding to the target rule can be constructed, which includes abnormal temperature judgment rules for abnormal bearing temperature at the non-drive end of the generator, abnormal temperature at the drive end of the generator, abnormal temperature of the gearbox oil, abnormal temperature of the drive end bearing of the gearbox, abnormal temperature of the non-drive end bearing of the gearbox, too fast rise in the temperature of the drive end bearing of the generator, and too fast rise in the temperature of the non-drive end bearing of the generator, as shown in the following table:

[0090] Table 1

[0091]

[0092] Further, after determining the abnormal index characteristics such as the first abnormal value to the seventh abnormal value, the abnormal characteristic indicators can be presented in a table, as shown in the following table:

[0093] Table 2

[0094] Exception Type Fields Outliers Abnormal bearing temperature at the non-drive end of the generator GNDEBTA 0 / 1 Abnormal bearing temperature at the generator drive end GDEBTA 0 / 1 Abnormal gearbox oil temperature GOTA 0 / 1 Abnormal temperature of gearbox front bearing GFBTA 0 / 1 Abnormal temperature of the rear bearing of the gearbox GRBTA 0 / 1 The bearing temperature at the drive end of the generator rises too fast GDEBTRTF 0 / 1 The temperature of the non-drive end bearing of the generator rises too fast GNDEBTRTF 0 / 1

[0095] In this embodiment, a judgment is made based on data such as the generator active power, unit operating status, generator drive-end bearing temperature, generator non-drive-end bearing temperature, gearbox oil temperature, inverter power, gearbox drive-end bearing temperature and gearbox non-drive-end bearing temperature in the time series operation data to determine whether the judgment rules corresponding to the corresponding abnormal situation are met, and the abnormal situation is judged according to the preset target rules in advance to improve the efficiency and accuracy of abnormality identification, and abnormal feature indicators are obtained according to various abnormal situations to fully explore the abnormal features in the time series operation data and improve the accuracy of subsequent analysis.

[0096] On the basis of the above embodiment, the process of obtaining the time domain characteristic index and the frequency domain characteristic index is described, and the state waveform data includes: the time domain waveform of the radial acceleration of the main shaft impeller side bearing, the time domain waveform of the radial acceleration of the main shaft motor side bearing, the time domain waveform of the radial acceleration of the first-stage inner gear ring of the gearbox, the time domain waveform of the radial acceleration of the low-speed shaft of the gearbox, the time domain waveform of the radial acceleration of the high-speed shaft of the gearbox, the time domain waveform of the radial acceleration of the generator drive end, and at least one of the time domain waveform of the radial acceleration of the non-drive end of the generator; Figure 3 A schematic diagram of a process for obtaining characteristic indicators and frequency domain characteristic indicators provided in an embodiment of the present application. Figure 3 As shown, the method includes:

[0097] S301, for any time domain waveform in the state waveform data, obtain the effective value, variance, root amplitude, skewness index, kurtosis index, kurtosis factor, waveform index, peak index, margin index, peak value, peak-to-peak value and time domain entropy of the time domain waveform as time domain feature indicators.

[0098] It can be understood that the state waveform data is data collected within a day at a time interval of 2 hours. The corresponding time domain waveform is generated based on the data at each time of the day. The time domain waveform can be expressed as [x(1), x(2), ... x(N)]. In some implementations, the time domain waveform can be encrypted and compressed and stored in the big data platform. Therefore, when the time domain waveform is read from the big data platform for analysis, the time domain waveform is pre-processed such as decompression and decryption to ensure that the time domain waveform is visualized and editable.

[0099] As an example, the calculation of mean, variance, kurtosis and skewness can be expressed as:

[0100]

[0101]

[0102] in, is the mean; X std is the variance; X kf is the kurtosis; 1 is the skewness; N is the number of all data in the time domain waveform; x(i) is the data at the i-th moment in the time domain waveform.

[0103] Furthermore, based on the time domain waveform, calculations are performed on indicators such as effective value, square root amplitude, kurtosis factor, waveform index, peak index, peak value, peak-to-peak value and time domain entropy. The effective value reflects the average power or energy of the waveform in one period; the square root amplitude is the arithmetic square root of the average value of the sum of squares of data in the time domain waveform; the kurtosis factor is an indicator indicating the smoothness of the waveform, which is used to describe the distribution of variables; the waveform index can be the ratio of the effective value to the overall average value; the peak index usually refers to the maximum value of the signal within a time interval; the peak value refers to the maximum value of a single peak in the time domain waveform; the peak-to-peak value refers to the difference between the maximum and minimum values ​​of the signal within the time interval, that is, the range between the highest and lowest values ​​of the signal; the time domain entropy is a parameter that describes the complexity of the signal; it indicates the randomness and uncertainty of the signal in the time domain; the calculation and acquisition of the above indicators can be achieved according to the existing technical solutions, which are not limited to this and will not be repeated here.

[0104] S302, converting the time domain waveform into a frequency domain waveform, and determining the frequency domain entropy, upper envelope and corresponding unit components of the frequency domain waveform, and determining the envelope spectrum entropy according to the upper envelope.

[0105] Optionally, a Fourier transform may be used to convert a time domain waveform into a frequency domain waveform; in some implementations, window features may be calculated before Fourier transform, including rectangular window, Blackman window, Hanning window, triangular window, Gaussian window, Hamming window, etc., to prevent frequency leakage during Fourier transform.

[0106] In some implementations, frequency domain entropy is determined based on the frequency domain waveform. Frequency domain entropy is an indicator used to measure the degree of confusion of the frequency domain signal. It can be calculated by the Fast Fourier Transform (FFT) coefficients of the frequency domain waveform. The FFT coefficients can be obtained by fast Fourier transforming the frequency domain waveform.

[0107] In some implementations, the frequency domain waveform can be de-averaged and normalized, and the peak value of each waveform period can be extracted and connected to obtain the upper envelope of the frequency domain waveform. The envelope spectral entropy is calculated based on the upper envelope. The envelope spectral entropy is a feature extraction method for evaluating signal complexity, which is mainly used to analyze the complexity and changing trend of the signal. The specific calculation method is not described in detail.

[0108] Optionally, the unit components include bearings and gearboxes, the bearings include an inner ring, an outer ring and a ball, and the gearbox includes a planetary gear and a sun gear. Therefore, when the frequency domain waveforms belong to different unit components, the calculated frequency domain characteristic indicators are different; it can be understood that all frequency domain characteristic indicators in this embodiment can be calculated based on the existing technology, and this is not limited here and will not be repeated.

[0109] S303, in response to the frequency domain waveform belonging to the bearing, the inner ring envelope spectrum peak factor, the outer ring envelope spectrum peak factor, the rolling element envelope spectrum peak factor and the cage envelope spectrum peak factor are obtained based on the upper envelope line, and the envelope spectrum entropy and the frequency domain entropy are combined to form a frequency domain characteristic index.

[0110] Based on the calculation of the time domain characteristic index and frequency domain characteristic index of the bearing, all the time domain characteristic index and frequency domain characteristic index corresponding to the bearing are obtained, as shown in the following table:

[0111] Table 3 Time domain characteristic index and frequency domain characteristic index of bearing

[0112]

[0113] S304, in response to the frequency domain waveform belonging to the gearbox, obtain the first-level meshing low-speed sideband energy, the first-level meshing high-speed sideband energy, the second-level meshing low-speed sideband energy, the second-level meshing high-speed sideband energy, the third-level meshing low-speed sideband energy and the third-level meshing high-speed sideband energy of the frequency domain waveform, and combine the envelope spectrum entropy and the frequency domain entropy to form a frequency domain characteristic index.

[0114] Based on the calculation of the time domain characteristic index and frequency domain characteristic index of the gearbox, all the time domain characteristic index and frequency domain characteristic index corresponding to the gearbox are obtained, as shown in the following table:

[0115] Table 4 Time domain characteristic index and frequency domain characteristic index of gearbox

[0116]

[0117] In this embodiment, comprehensive time domain feature indicators are extracted from each time domain waveform in the state waveform data, and the time domain waveform is further converted into the frequency domain to obtain the corresponding frequency domain waveform. The features in the frequency domain waveform are mined to obtain the frequency domain indicator characteristics corresponding to the gearbox and the bearing respectively, thereby extracting the complete time domain feature indicators and frequency domain feature indicators in the CMS data to improve the accuracy of subsequent fault detection.

[0118] Based on the above embodiment, the process of obtaining the fault detection result is described. Figure 4 A schematic diagram of a process for obtaining a fault detection result provided in an embodiment of the present application. Figure 4 As shown, the method includes:

[0119] S401, concatenating the abnormal feature index, the time domain feature index and the frequency domain feature index to obtain a fusion feature.

[0120] S402, inputting the fusion features into a pre-trained fault detection model to obtain a fault detection result output by the fault detection model.

[0121] In some implementations, basic information and operating parameters of the generator set can also be obtained. The basic information includes one or more of the power plant data, wind turbines, measuring points, rated speed, global encoding of vibration waveform, number of sampling points and time; the operating parameters include one or more of generator speed, wind speed, active power and main shaft speed.

[0122] In some implementations, in order to better adapt to the actual operating status of the unit and real-time data collection, external input parameters such as power plant related data, rated speed, and gearbox speed ratio can be determined before analyzing the wind turbine unit; the failure frequency of major components of the wind turbine transmission chain can also be obtained in advance and stored in the database. The wind turbine failure frequency may include but is not limited to: inner ring failure frequency, outer ring failure frequency, rolling element failure frequency, cage failure frequency, input shaft, first-stage planetary gear, first-stage sun gear shaft, second-stage planetary gear, second-stage sun gear shaft, high-speed shaft, first-stage planetary-level meshing, second-stage planetary-level meshing, and high-speed-level meshing; the main shaft parameters corresponding to the unit can also be obtained, including the outer ring diameter, inner ring diameter, rolling element diameter, pitch circle diameter, and the number of rolling elements, and the gearbox related parameters can also be obtained, such as the first-stage parameters of the gearbox, the second-stage parameters of the gearbox, and the third-stage parameters of the gearbox, so as to calculate the relevant rotational frequency, meshing frequency, and failure frequency and store them in the database.

[0123] Optionally, the rotational frequency can be calculated based on the rotational speed, and the rotational frequency is equal to the rotational speed divided by 60; the waveform time length can be calculated according to the number of sampling points and the sampling frequency, and the waveform time length is equal to the number of sampling points divided by the sampling frequency, so as to match data such as wind speed and generator power at corresponding time points. The operating parameter values ​​such as wind speed and generator power can be the values ​​at the most recent moment within 5 minutes of the corresponding waveform time length.

[0124] Furthermore, basic information, public parameters and fused features can be input into a pre-trained fault detection model to obtain fault detection results for the wind turbine transmission chain, that is, feature extraction is performed on various data of the wind turbine operation on the previous day to obtain fused features, and the fused features are analyzed to obtain fault detection results, thereby improving the accuracy of fault detection for the wind turbine; the fault detection results include: main bearing damage, generator bearing damage, gearbox tooth surface damage, gearbox parallel stage bearing damage, poor alignment and no faults.

[0125] Optionally, the fault detection model can adopt an extreme gradient boosting (EXtreme Gradient Boosting, XGBoost) model. Compared with other learning algorithms in the prior art, the advantage of the XGBoost model is that the XGBoost model performs a second-order Taylor expansion on the loss function, combines the prediction term and the regularization term, and optimizes computing resources by simplifying the objective function to balance the decrease of the loss function and the complexity of the model and obtain the optimal solution; at the same time, XGBoost automatically performs parallel computing to ensure the optimal computing speed.

[0126] It can be understood that in the training stage of the fault prediction model, a relatively balanced normal sample data set and a fault sample data set can be constructed. For example, the sample data set is constructed based on the data of the past year, and the model is trained based on the normal sample data set and the fault sample data set. The fault types are marked as 0 to 5, a total of 6 types, corresponding to main bearing damage, generator bearing damage, gearbox tooth surface damage, gearbox parallel stage bearing damage, poor alignment and normal; 70% of the samples in the data set are used as the training set, 10% as the validation set, and 20% of the samples as the test set. The XGBoost model is input for training to obtain the fault prediction model. In order to select a better fault prediction model, this embodiment adopts grid search cross validation (Grid Search Cross-Validation, GridSearchCV) method is used to tune the main parameters of the model; by extracting abnormal feature indicators, time domain feature indicators, frequency domain feature indicators, basic information and operating condition parameters in the sample data, fusion features are constructed, and then input into the fault prediction model for classification training to achieve full and efficient use of information from different sources. The three evaluation indicators of accuracy, recall rate and F1-score can also be used to evaluate the training effect of the wind turbine transmission chain system state classification model to ensure the fault identification effect.

[0127] In this embodiment, the abnormal feature indicators extracted from the SCADA data and the time domain feature indicators and frequency domain feature indicators extracted from the CMS data are spliced ​​to obtain fused features, and the basic information and operating parameters of the unit can also be obtained to better adapt to the actual operating status and real-time data of the unit. The fused features and the basic information and operating parameters are input into the pre-trained fault identification model, and the fault identification model outputs specific fault identification results, that is, main bearing damage, generator bearing damage, gearbox tooth surface damage, gearbox parallel stage bearing damage, poor alignment or no fault results, thereby improving fault identification efficiency and accuracy.

[0128] Based on the above embodiments, Figure 5 A schematic flow chart of another wind turbine transmission chain fault detection method provided in an embodiment of the present application; Figure 5 As shown, the method comprises the following steps:

[0129] S501, acquiring the timing operation data and state waveform data of the wind turbine transmission chain.

[0130] S502, in response to the unit operating state being the grid-connected state, at the same moment, based on the generator active power and the generator non-drive end bearing temperature, determine whether the generator non-drive end bearing temperature abnormality rule is met to obtain a first abnormal value.

[0131] S503, in response to the unit operating state being the grid-connected state, at the same moment, based on the generator active power and the generator drive end bearing temperature, determine whether the generator drive end bearing temperature abnormality rule is met to obtain a second abnormal value.

[0132] S504, in response to the unit operating state being the grid-connected state, at the same moment, based on the generator active power and the gearbox oil temperature, determine whether the gearbox oil temperature abnormality rule is met to obtain a third abnormal value.

[0133] S505, determining whether a gearbox drive end bearing temperature abnormality rule is met according to the inverter power and the gearbox drive end bearing temperature, and obtaining a fourth abnormal value.

[0134] S506, determining whether a gear box non-drive end bearing temperature abnormality rule is met according to the inverter power and the gear box non-drive end bearing temperature, and obtaining a fifth abnormal value.

[0135] S507, obtaining the startup time of the wind turbine generator set, and determining whether the abnormal rule of too fast rise in the generator drive end bearing temperature is met according to the startup time and the degree of change in the generator drive end bearing temperature, to obtain a sixth abnormal value.

[0136] S508, determining whether the abnormal rule of excessively rapid rise in the non-drive-end bearing temperature of the generator is satisfied according to the startup time and the degree of change in the non-drive-end bearing temperature of the generator, and obtaining a seventh abnormal value.

[0137] S509: Determine an abnormal characteristic index of the wind turbine transmission chain based on the first abnormal value to the seventh abnormal value.

[0138] S510, for any time domain waveform in the state waveform data, obtain the effective value, variance, root amplitude, skewness index, kurtosis index, kurtosis factor, waveform index, peak index, margin index, peak value, peak-to-peak value and time domain entropy of the time domain waveform as time domain feature indicators.

[0139] S511, converting the time domain waveform into a frequency domain waveform, and determining the frequency domain entropy, upper envelope and corresponding unit components of the frequency domain waveform, and determining the envelope spectrum entropy according to the upper envelope.

[0140] S512, in response to the frequency domain waveform belonging to the bearing, the inner ring envelope spectrum peak factor, the outer ring envelope spectrum peak factor, the rolling element envelope spectrum peak factor and the cage envelope spectrum peak factor are obtained based on the upper envelope line, and the envelope spectrum entropy and the frequency domain entropy are combined to form a frequency domain characteristic index.

[0141] S513, in response to the frequency domain waveform belonging to the gearbox, obtain the first-level meshing low-speed sideband energy, the first-level meshing high-speed sideband energy, the second-level meshing low-speed sideband energy, the second-level meshing high-speed sideband energy, the third-level meshing low-speed sideband energy and the third-level meshing high-speed sideband energy of the frequency domain waveform, and combine the envelope spectrum entropy and the frequency domain entropy to form a frequency domain characteristic index.

[0142] S514, concatenating the abnormal feature index, the time domain feature index, and the frequency domain feature index to obtain a fusion feature.

[0143] S515, inputting the fusion features into a pre-trained fault detection model to obtain a fault detection result output by the fault detection model.

[0144] In the embodiment of the present application, the implementation method of step S501 to step S515 can be implemented in any way in the embodiments of the present disclosure, which is not limited here and will not be repeated.

[0145] In this embodiment, by acquiring the timing operation data and state waveform data of the wind turbine transmission chain, judging whether the judgment rules corresponding to the corresponding abnormal situation are met based on the timing operation data, judging the abnormal situation according to the preset target rules, improving the efficiency and accuracy of abnormal identification, and fully mining the abnormal features in the timing operation data; extracting comprehensive time domain feature indicators from each time domain waveform in the state waveform data, further performing frequency domain conversion on the time domain waveform to obtain the corresponding frequency domain waveform, mining the features in the frequency domain waveform, and obtaining the frequency domain indicator features corresponding to the gearbox and the bearing respectively; splicing the abnormal feature indicators extracted from the SCADA data and the time domain feature indicators and frequency domain feature indicators extracted from the CMS data to obtain fused features, and also obtaining the basic information and operating parameters of the unit to better adapt to the actual operating status and real-time data of the unit, and inputting the fused features together with the basic information and operating parameters into the pre-trained fault identification model, and the fault identification model outputs a specific fault identification result, thereby improving the efficiency and accuracy of fault identification.

[0146] Figure 6 A logical schematic diagram of a wind turbine transmission chain fault detection method provided in an embodiment of the present application; SCADA data and CMS data are obtained respectively, and pre-processing operations such as data cleaning are performed on the SCADA data and the CMS data to improve data analysis accuracy, abnormality judgment is performed based on the SCADA data and preset target rules to obtain abnormal feature indicators, time domain feature extraction and frequency domain feature extraction are performed based on the CMS data, and finally the abnormal feature indicators, time domain feature indicators and frequency domain feature indicators are fused to obtain fused features, and the fused features are input into a pre-trained fault detection model to output fault detection results, fully mine the relevant data features of the wind turbine, and improve the accuracy of fault identification.

[0147] In order to implement the above embodiment, the present application also proposes a wind turbine transmission chain fault detection device.

[0148] Figure 7 The structure diagram of a wind turbine transmission chain fault detection device provided in the embodiment of the present application is shown in FIG. Figure 7 As shown, the wind turbine transmission chain fault detection device 700 includes:

[0149] The first acquisition module 701 is used to acquire the timing operation data and state waveform data of the wind turbine transmission chain;

[0150] The second acquisition module 702 is used to determine the abnormal characteristic index of the wind turbine transmission chain according to whether the time series operation data meets the preset target rules;

[0151] The third acquisition module 703 is used to determine the time domain characteristic index and frequency domain characteristic index of the wind turbine transmission chain according to the state waveform data;

[0152] The fault detection module 704 is used to determine the fusion feature based on the abnormal feature index, the time domain feature index and the frequency domain feature index, and determine the fault detection result of the wind turbine transmission chain according to the fusion feature.

[0153] Furthermore, in a possible implementation of an embodiment of the present application, the timing operation data includes: generator active power, fan wind speed, generator speed, main shaft speed, unit operating status, generator drive end bearing temperature, generator non-drive end bearing temperature, gearbox oil temperature, inverter power, gearbox drive end bearing temperature and gearbox non-drive end bearing temperature. At least one of the bearing temperature.

[0154] Furthermore, in a possible implementation of the embodiment of the present application, the second acquisition module 702 includes:

[0155] In response to the unit operating state being a grid-connected state, at the same time, based on the generator active power and the generator non-drive end bearing temperature, determining whether the generator non-drive end bearing temperature abnormality rule is met, and obtaining a first abnormal value;

[0156] In response to the unit operating state being the grid-connected state, at the same time, based on the generator active power and the generator drive end bearing temperature, determining whether the generator drive end bearing temperature abnormality rule is met, and obtaining a second abnormal value;

[0157] In response to the unit operating state being a grid-connected state, at the same time, based on the generator active power and the gearbox oil temperature, determining whether the gearbox oil temperature abnormality rule is satisfied, and obtaining a third abnormal value;

[0158] According to the inverter power and the gearbox drive end bearing temperature, determine whether the gearbox drive end bearing temperature abnormality rule is met to obtain a fourth abnormal value;

[0159] According to the inverter power and the gearbox non-drive end bearing temperature, determine whether the gearbox non-drive end bearing temperature abnormality rule is met to obtain a fifth abnormal value;

[0160] Obtain the start-up time of the wind turbine generator set, and determine whether the abnormal rule of too fast rise of the generator drive end bearing temperature is met according to the start-up time and the degree of change of the generator drive end bearing temperature, and obtain the sixth abnormal value;

[0161] According to the startup time and the degree of change of the temperature of the non-drive end bearing of the generator, it is determined whether the abnormal rule of the excessively rapid rise of the non-drive end bearing temperature of the generator is met, and the seventh abnormal value is obtained;

[0162] Based on the first abnormal value to the seventh abnormal value, an abnormal characteristic index of the wind turbine transmission chain is determined.

[0163] Furthermore, in a possible implementation of the embodiment of the present application, the second acquisition module 702 includes:

[0164] Dividing the wind farm units into power intervals according to the active power of the generators to obtain a first power interval and a second power interval;

[0165] For the first power interval, determine a first continuous time duration that the generator non-drive end bearing temperature of the unit is at least higher than a fixed value of the generator drive end bearing temperature, a second continuous time duration that the generator drive end bearing of the unit is at least higher than a fixed value of the generator non-drive end bearing temperature, and a third continuous time duration that the gearbox oil temperature of the unit is higher than a first preset temperature;

[0166] In response to the first continuous time being longer than the preset time length, the first abnormal value of the unit is determined to be 1; in response to the second continuous time being longer than the preset time length, the second abnormal value of the unit is determined to be 1; in response to the third continuous time being longer than the preset time length, the third abnormal value of the unit is determined to be 1;

[0167] For the second power range, in response to the generator non-drive end bearing temperature of the unit being greater than the second preset temperature, the first abnormal value of the unit is determined to be 1; in response to the generator drive end bearing temperature of the unit being greater than the second preset temperature, the second abnormal value of the unit is determined to be 1; in response to the gearbox oil temperature of the unit being greater than the second preset temperature, the third abnormal value of the unit is determined to be 1;

[0168] Determine whether the inverter power of the unit is greater than a preset power according to the inverter power, and in response to the inverter power being greater than the preset power, respectively determine a fourth continuous time that the gearbox drive end bearing temperature is greater than a third preset temperature, and a fifth continuous time that the gearbox non-drive end bearing temperature is greater than the third preset temperature;

[0169] In response to the fourth continuous time being longer than the preset time, determining that the fourth abnormal value of the unit is 1; in response to the fifth continuous time being longer than the preset time, determining that the fifth abnormal value of the unit is 1;

[0170] The unit is divided into the initial startup stage and the normal operation stage according to the startup time;

[0171] For the unit in the initial stage of startup, determine the first change value of the generator drive end bearing temperature within a fixed time period, and the second change value of the generator non-drive end bearing temperature within a fixed time period; in response to the first change value of two consecutive fixed time periods being greater than the first preset change value, determine the sixth abnormal value of the unit to be 1; in response to the second change value of two consecutive fixed time periods being greater than the first preset change value, determine the seventh abnormal value of the unit to be 1;

[0172] For the unit in the normal operating stage, the third change value of the generator drive end bearing temperature within a fixed time period and the fourth change value of the generator non-drive end bearing temperature within a fixed time period are determined; in response to the third change value of two consecutive fixed time periods being greater than the second preset change value, the sixth abnormal value of the unit is determined to be 1; in response to the fourth change value of two consecutive fixed time periods being greater than the second preset change value, the seventh abnormal value of the unit is determined to be 1.

[0173] Furthermore, in a possible implementation of an embodiment of the present application, the state waveform data includes: a time-domain waveform of radial acceleration of a main shaft impeller side bearing, a time-domain waveform of radial acceleration of a main shaft motor side bearing, a time-domain waveform of radial acceleration of a first-stage inner gear ring of a gearbox, a time-domain waveform of radial acceleration of a low-speed shaft of a gearbox, a time-domain waveform of radial acceleration of a high-speed shaft of a gearbox, a time-domain waveform of radial acceleration of a drive end of a generator, and at least one of a time-domain waveform of radial acceleration of a non-drive end of a generator.

[0174] Furthermore, in a possible implementation of the embodiment of the present application, the third acquisition module 703 includes:

[0175] For any time domain waveform in the state waveform data, obtain the effective value, variance, root amplitude, skewness index, kurtosis index, kurtosis factor, waveform index, peak index, margin index, peak value, peak-to-peak value and time domain entropy of the time domain waveform as time domain feature indicators;

[0176] Converting the time domain waveform into a frequency domain waveform, and determining the frequency domain entropy, upper envelope and corresponding unit components of the frequency domain waveform, the unit components including bearings and gear boxes;

[0177] Determine the envelope spectrum entropy based on the upper envelope;

[0178] In response to the frequency domain waveform belonging to the bearing, the inner ring envelope spectrum peak factor, the outer ring envelope spectrum peak factor, the rolling element envelope spectrum peak factor and the cage envelope spectrum peak factor are obtained based on the upper envelope line, and the envelope spectrum entropy and the frequency domain entropy are combined to form a frequency domain characteristic index;

[0179] In response to the frequency domain waveform belonging to the gearbox, the first-order meshing low-speed sideband energy, the first-order meshing high-speed sideband energy, the second-order meshing low-speed sideband energy, the second-order meshing high-speed sideband energy, the third-order meshing low-speed sideband energy and the third-order meshing high-speed sideband energy of the frequency domain waveform are obtained, and the envelope spectrum entropy and the frequency domain entropy are combined to form a frequency domain characteristic index.

[0180] Furthermore, in a possible implementation of the embodiment of the present application, the fault detection module 704 includes:

[0181] The abnormal feature indicators, time domain feature indicators and frequency domain feature indicators are spliced ​​to obtain fusion features.

[0182] Furthermore, in a possible implementation of the embodiment of the present application, the fault detection module 704 includes:

[0183] The fusion features are input into the pre-trained fault detection model to obtain the fault detection results output by the fault detection model. The fault detection results include: main bearing damage, generator bearing damage, gearbox tooth surface damage, gearbox parallel stage bearing damage, misalignment and no fault.

[0184] Furthermore, in a possible implementation of the embodiment of the present application, the apparatus 700 further includes:

[0185] Obtaining basic information and operating parameters of the generator set, the basic information including one or more of the power plant, wind turbine, measuring point, rated speed, global code of vibration waveform, number of sampling points and time; the operating parameters including one or more of generator speed, wind speed, active power and main shaft speed;

[0186] The basic information, public parameters and fusion features are input into the pre-trained fault detection model to obtain the fault detection results of the wind turbine transmission chain.

[0187] It should be noted that the above explanations of the embodiment of the method for detecting a transmission chain fault of a wind turbine generator set are also applicable to the device for detecting a transmission chain fault of a wind turbine generator set of this embodiment, and will not be described in detail here.

[0188] In an embodiment of the present application, by acquiring the timing operation data and state waveform data of the wind turbine transmission chain, judging whether the judgment rules corresponding to the corresponding abnormal situation are met based on the timing operation data, judging the abnormal situation according to the preset target rules, improving the efficiency and accuracy of abnormal identification, and fully mining the abnormal features in the timing operation data; extracting comprehensive time domain feature indicators from each time domain waveform in the state waveform data, further performing frequency domain conversion on the time domain waveform to obtain the corresponding frequency domain waveform, mining the features in the frequency domain waveform, and obtaining the frequency domain indicator features corresponding to the gearbox and the bearing respectively; splicing the abnormal feature indicators extracted from the SCADA data and the time domain feature indicators and frequency domain feature indicators extracted from the CMS data to obtain fused features, and also obtaining the basic information and operating parameters of the unit to better adapt to the actual operating status and real-time data of the unit, and inputting the fused features together with the basic information and operating parameters into the pre-trained fault identification model, and the fault identification model outputs a specific fault identification result, thereby improving the efficiency and accuracy of fault identification.

[0189] In order to implement the above embodiments, the present application also proposes an electronic device, comprising: a processor, and a memory communicatively connected to the processor; the memory stores computer-executable instructions; the processor executes the computer-executable instructions stored in the memory to implement the method provided by the above embodiments.

[0190] In order to implement the above embodiments, the present application also proposes a computer-readable storage medium, in which computer-executable instructions are stored. When the computer-executable instructions are executed by a processor, they are used to implement the methods provided by the above embodiments.

[0191] In order to implement the above embodiments, the present application also proposes a computer program product, including a computer program, which implements the methods provided by the above embodiments when executed by a processor.

[0192] The collection, storage, use, processing, transmission, provision and disclosure of user personal information involved in this application are in compliance with relevant laws and regulations and do not violate public order and good morals.

[0193] It should be noted that personal information from users should be collected for legitimate and reasonable purposes and should not be shared or sold outside of these legitimate uses. In addition, such collection / sharing should be carried out after receiving the user's informed consent, including but not limited to notifying the user to read the user agreement / user notice and sign the agreement / authorization including authorization of relevant user information before the user uses the function. In addition, any necessary steps should be taken to protect and safeguard access to such personal information data and ensure that others who have access to personal information data comply with its privacy policy and procedures.

[0194] The present application is expected to provide an implementation scheme for users to selectively block the use or access of personal information data. That is, the present disclosure is expected to provide hardware and / or software to prevent or block access to such personal information data. Once the personal information data is no longer needed, the risk can be minimized by limiting data collection and deleting the data. In addition, when applicable, such personal information is de-identified to protect the privacy of the user.

[0195] In the description of the aforementioned embodiments, the description with reference to the terms "one embodiment", "some embodiments", "example", "specific example", or "some examples" etc. means that the specific features, structures, materials or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present application. In this specification, the schematic representations of the above terms do not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described may be combined in any one or more embodiments or examples in a suitable manner. In addition, those skilled in the art may combine and combine the different embodiments or examples described in this specification and the features of the different embodiments or examples, without contradiction.

[0196] In addition, the terms "first" and "second" are used for descriptive purposes only and should not be understood as indicating or implying relative importance or implicitly indicating the number of the indicated technical features. Therefore, the features defined as "first" and "second" may explicitly or implicitly include at least one of the features. In the description of this application, the meaning of "plurality" is at least two, such as two, three, etc., unless otherwise clearly and specifically defined.

[0197] Any process or method description in a flowchart or otherwise described herein may be understood to represent a module, fragment or portion of code comprising one or more executable instructions for implementing the steps of a custom logical function or process, and the scope of the preferred embodiments of the present application includes alternative implementations in which functions may not be performed in the order shown or discussed, including performing functions in a substantially simultaneous manner or in the reverse order depending on the functions involved, which should be understood by technicians in the technical field to which the embodiments of the present application belong.

[0198] The logic and / or steps represented in the flowchart or otherwise described herein, for example, can be considered as an ordered list of executable instructions for implementing logical functions, and can be embodied in any computer-readable medium for use by an instruction execution system, device or apparatus (such as a computer-based system, a system including a processor, or other system that can fetch instructions from an instruction execution system, device or apparatus and execute the instructions), or in combination with these instruction execution systems, devices or apparatuses. For the purpose of this specification, "computer-readable medium" can be any device that can contain, store, communicate, propagate or transmit a program for use by an instruction execution system, device or apparatus, or in combination with these instruction execution systems, devices or apparatuses. More specific examples of computer-readable media (a non-exhaustive list) include the following: an electrical connection with one or more wires (electronic device), a portable computer disk box (magnetic device), a random access memory (RAM), a read-only memory (ROM), an erasable and programmable read-only memory (EPROM or flash memory), a fiber optic device, and a portable compact disk read-only memory (CDROM). In addition, the computer-readable medium may even be paper or other suitable medium on which the program is printed, since the program may be obtained electronically, for example, by optically scanning the paper or other medium and then editing, interpreting or processing in other suitable ways if necessary, and then stored in a computer memory.

[0199] It should be understood that the various parts of the present application can be implemented by hardware, software, firmware or a combination thereof. In the above-mentioned embodiments, multiple steps or methods can be implemented by software or firmware stored in a memory and executed by a suitable instruction execution system. For example, if implemented by hardware, as in another embodiment, it can be implemented by any one of the following technologies known in the art or their combination: a discrete logic circuit having a logic gate circuit for implementing a logic function for a data signal, a dedicated integrated circuit having a suitable combination of logic gate circuits, a programmable gate array (PGA), a field programmable gate array (FPGA), etc.

[0200] A person skilled in the art may understand that all or part of the steps in the method for implementing the above-mentioned embodiment may be completed by instructing related hardware through a program, and the program may be stored in a computer-readable storage medium, which, when executed, includes one or a combination of the steps of the method embodiment.

[0201] In addition, each functional unit in each embodiment of the present application may be integrated into a processing module, or each unit may exist physically separately, or two or more units may be integrated into one module. The above-mentioned integrated module may be implemented in the form of hardware or in the form of a software functional module. If the integrated module is implemented in the form of a software functional module and sold or used as an independent product, it may also be stored in a computer-readable storage medium.

[0202] The storage medium mentioned above may be a read-only memory, a magnetic disk or an optical disk, etc. Although the embodiments of the present application have been shown and described above, it can be understood that the above embodiments are exemplary and cannot be understood as limiting the present application. A person of ordinary skill in the art may change, modify, replace and modify the above embodiments within the scope of the present application.

Claims

1. A method for detecting a fault in a transmission chain of a wind turbine generator system, characterized in that: include: Obtaining the timing operation data and state waveform data of the wind turbine transmission chain; Determining abnormal characteristic indicators of the wind turbine transmission chain according to whether the time series operation data meets a preset target rule; Determining the time domain characteristic index and the frequency domain characteristic index of the wind turbine transmission chain according to the state waveform data; Based on the abnormal characteristic index, the time domain characteristic index and the frequency domain characteristic index, a fusion feature is determined, and a fault detection result of the wind turbine transmission chain is determined according to the fusion feature.

2. The method according to claim 1, characterized in that The time series operation data includes: at least one of the active power of the generator, the wind speed of the fan, the generator speed, the main shaft speed, the unit operation status, the generator drive end bearing temperature, the generator non-drive end bearing temperature, the gearbox oil temperature, the inverter power, the gearbox drive end bearing temperature and the gearbox non-drive end bearing temperature.

3. The method according to claim 2, characterized in that The determining of the abnormal characteristic index of the wind turbine transmission chain according to whether the time series operation data meets a preset target rule includes: In response to the running state of the unit being a grid-connected state, at the same time, based on the active power of the generator and the non-drive end bearing temperature of the generator, determining whether the abnormal temperature rule of the non-drive end bearing of the generator is satisfied, and obtaining a first abnormal value; In response to the running state of the unit being a grid-connected state, at the same time, based on the active power of the generator and the bearing temperature of the driving end of the generator, determining whether the abnormal temperature rule of the bearing at the driving end of the generator is satisfied, and obtaining a second abnormal value; In response to the running state of the unit being a grid-connected state, at the same time, based on the active power of the generator and the gearbox oil temperature, determining whether a gearbox oil temperature abnormality rule is satisfied, and obtaining a third abnormal value; Determine whether a gearbox drive end bearing temperature abnormality rule is met according to the inverter power and the gearbox drive end bearing temperature, and obtain a fourth abnormal value; Determine whether a gearbox non-drive end bearing temperature abnormality rule is met according to the inverter power and the gearbox non-drive end bearing temperature, and obtain a fifth abnormal value; Obtaining the startup time of the wind turbine generator set, and determining whether the generator drive end bearing temperature rises too fast abnormal rule is met according to the startup time and the degree of change of the generator drive end bearing temperature, to obtain a sixth abnormal value; Determine whether the abnormal rule of excessively rapid rise in the temperature of the non-drive end bearing of the generator is met according to the startup time and the degree of change in the temperature of the non-drive end bearing of the generator, and obtain a seventh abnormal value; Based on the first to seventh abnormal values, an abnormal characteristic index of the wind turbine transmission chain is determined.

4. The method according to claim 3, characterized in that The method for obtaining the abnormal characteristic indicator includes: Dividing the wind farm units into power intervals according to the active power of the generator to obtain a first power interval and a second power interval; For the first power interval, determine a first continuous time duration that the generator non-drive end bearing temperature of the unit is at least higher than a fixed value of the generator drive end bearing temperature, a second continuous time duration that the generator drive end bearing of the unit is at least higher than a fixed value of the generator non-drive end bearing temperature, and a third continuous time duration that the gearbox oil temperature of the unit is higher than a first preset temperature; In response to the first continuous time being longer than the preset time length, the first abnormal value of the unit is determined to be 1; in response to the second continuous time being longer than the preset time length, the second abnormal value of the unit is determined to be 1; in response to the third continuous time being longer than the preset time length, the third abnormal value of the unit is determined to be 1; For the second power range, in response to the generator non-drive end bearing temperature of the unit being greater than the second preset temperature, the first abnormal value of the unit is determined to be 1; in response to the generator drive end bearing temperature of the unit being greater than the second preset temperature, the second abnormal value of the unit is determined to be 1; in response to the gearbox oil temperature of the unit being greater than the second preset temperature, the third abnormal value of the unit is determined to be 1; Determine whether the inverter power of the unit is greater than a preset power according to the inverter power, and in response to the inverter power being greater than the preset power, respectively determine a fourth continuous time length during which the gearbox drive end bearing temperature is greater than a third preset temperature, and a fifth continuous time length during which the gearbox non-drive end bearing temperature is greater than the third preset temperature; In response to the fourth continuous time being longer than the preset time, determining that the fourth abnormal value of the unit is 1; in response to the fifth continuous time being longer than the preset time, determining that the fifth abnormal value of the unit is 1; The unit is divided into an initial startup stage and a normal operation stage according to the startup time; For the unit in the initial startup stage, determine a first change value of the generator drive end bearing temperature within a fixed time period, and a second change value of the generator non-drive end bearing temperature within a fixed time period; in response to the first change value being greater than a first preset change value for two consecutive fixed time periods, determine that the sixth abnormal value of the unit is 1; in response to the second change value being greater than the first preset change value for two consecutive fixed time periods, determine that the seventh abnormal value of the unit is 1; For the unit in the normal operating stage, the third change value of the generator drive end bearing temperature within a fixed time period and the fourth change value of the generator non-drive end bearing temperature within a fixed time period are determined; in response to the third change value of two consecutive fixed time periods being greater than the second preset change value, the sixth abnormal value of the unit is determined to be 1; in response to the fourth change value of two consecutive fixed time periods being greater than the second preset change value, the seventh abnormal value of the unit is determined to be 1.

5. The method according to claim 1, characterized in that The state waveform data includes: a time-domain waveform of radial acceleration of a main shaft impeller side bearing, a time-domain waveform of radial acceleration of a main shaft motor side bearing, a time-domain waveform of radial acceleration of a first-stage inner gear ring of a gearbox, a time-domain waveform of radial acceleration of a low-speed shaft of a gearbox, a time-domain waveform of radial acceleration of a high-speed shaft of a gearbox, a time-domain waveform of radial acceleration of a driving end of a generator, and at least one of the time-domain waveforms of radial acceleration of a non-driving end of a generator.

6. The method according to claim 5, characterized in that Determining the time domain characteristic index and the frequency domain characteristic index of the wind turbine transmission chain according to the state waveform data includes: For any time domain waveform in the state waveform data, obtaining the effective value, variance, root amplitude, skewness index, kurtosis index, kurtosis factor, waveform index, peak index, margin index, peak value, peak-to-peak value and time domain entropy of the time domain waveform as time domain feature indicators; Converting the time domain waveform into a frequency domain waveform, and determining the frequency domain entropy, upper envelope and corresponding unit components of the frequency domain waveform, wherein the unit components include bearings and a gearbox; Determining envelope spectrum entropy according to the upper envelope; In response to the frequency domain waveform belonging to the bearing, the inner ring envelope spectrum peak factor, the outer ring envelope spectrum peak factor, the rolling element envelope spectrum peak factor and the cage envelope spectrum peak factor are obtained based on the upper envelope line, and the envelope spectrum entropy and the frequency domain entropy are combined to form a frequency domain characteristic index; In response to the frequency domain waveform belonging to a gearbox, the first-level meshing low-speed sideband energy, the first-level meshing high-speed sideband energy, the second-level meshing low-speed sideband energy, the second-level meshing high-speed sideband energy, the third-level meshing low-speed sideband energy and the third-level meshing high-speed sideband energy of the frequency domain waveform are obtained, and the envelope spectrum entropy and the frequency domain entropy are combined to form a frequency domain characteristic index.

7. The method according to claim 1, characterized in that The determining of the fusion feature based on the abnormal feature indicator, the time domain feature indicator and the frequency domain feature indicator includes: The abnormal feature index, the time domain feature index and the frequency domain feature index are spliced ​​to obtain the fusion feature.

8. The method according to claim 7, characterized in that The step of determining the fault detection result of the wind turbine transmission chain according to the fusion feature includes: The fusion features are input into a pre-trained fault detection model to obtain a fault detection result output by the fault detection model, wherein the fault detection result includes: main bearing damage, generator bearing damage, gearbox tooth surface damage, gearbox parallel stage bearing damage, misalignment and absence of fault.

9. The method according to claim 8, characterized in that The method further comprises: Obtaining basic information and operating parameters of the generator set, wherein the basic information includes one or more of the power plant, wind turbine, measuring point, rated speed, global coding of vibration waveform, number of sampling points and time; the operating parameters include one or more of generator speed, wind speed, active power and main shaft speed; The basic information, the public parameters and the fusion features are input into a pre-trained fault detection model to obtain a fault detection result of the wind turbine transmission chain.

10. A wind turbine transmission chain fault detection device, characterized in that: include: The first acquisition module is used to acquire the timing operation data and state waveform data of the wind turbine transmission chain; A second acquisition module is used to determine the abnormal characteristic index of the transmission chain of the wind turbine generator set according to whether the time series operation data meets the preset target rules; A third acquisition module is used to determine the time domain characteristic index and the frequency domain characteristic index of the wind turbine transmission chain according to the state waveform data; The fault detection module is used to determine a fusion feature based on the abnormal feature index, the time domain feature index and the frequency domain feature index, and determine a fault detection result of the wind turbine transmission chain according to the fusion feature.

Images