Wind turbine vibration fault analysis method, system, device and electronic equipment

By analyzing the sensor data and curve characteristics of the wind turbine and generating fault diagnosis information, the problem of vibration fault detection of wind turbines is solved, and the operation stability and power generation efficiency of the equipment are improved.

CN118391199BActive Publication Date: 2024-11-15STATE POWER INVESTMENT CORPORATION RESEARCH INSTITUTE
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202410464447.8
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2024-04-17
Publication Date
2024-11-15
Estimated Expiration
2044-04-17

AI Technical Summary

Technical Problem

Vibration failures of wind turbines are difficult to effectively detect and analyze, resulting in a decrease in power generation efficiency and mechanical failures, affecting the safe and stable operation of the equipment.

Method used

By obtaining the sensor data of the wind turbine, determining it is in a dangerous state, analyzing the vibration characteristic curve and fault characteristic curve, generating fault diagnosis information, providing vibration fault analysis reports, and improving the comprehensiveness and accuracy of the analysis.

Benefits of technology

Accurate detection and analysis of vibration faults of wind turbines is achieved, the operation stability and safety of equipment are improved, and the power generation efficiency is improved.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN118391199B_ABST
    Figure CN118391199B_ABST
Patent Text Reader

Abstract

The present invention provides a method, system, device and electronic equipment for analyzing vibration faults of a wind turbine, and relates to the technical field of wind power generation. The specific implementation scheme is as follows: obtaining sensor data of the wind turbine in a first evaluation period; determining that the wind turbine is in a dangerous state according to the first evaluation period and the sensor data; determining a vibration characteristic curve of the wind turbine according to the sensor data; determining a vibration trend curve and a fault characteristic curve of the wind turbine according to the vibration characteristic curve; performing fault analysis on the wind turbine according to the fault characteristic curve and the vibration trend curve, and generating fault diagnosis information of the wind turbine; in this way, the problem of vibration faults of the wind turbine can be reflected intuitively and accurately, and the comprehensiveness and accuracy of vibration fault analysis of the wind turbine can be improved, so that users can conveniently and timely obtain effective information on vibration faults of the wind turbine.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present disclosure relates to the technical field of wind power generation, and in particular to a method, system, device and electronic equipment for analyzing vibration faults of a wind turbine. Background Art

[0002] With the rapid development of new energy technologies, wind energy has become a crucial component of the energy mix. As key equipment for wind energy utilization, the stable operation of wind turbines is crucial. Vibration failures in wind turbines can lead to reduced power generation efficiency and even mechanical failure, compromising the safe and stable operation of wind turbines. Summary of the Invention

[0003] The present disclosure provides a method, system, device and electronic equipment for analyzing vibration faults of a wind turbine.

[0004] According to a first aspect of the present disclosure, a method for analyzing vibration faults of a wind turbine is provided, comprising:

[0005] Acquire sensor data of the wind turbine during a first evaluation period;

[0006] Determining, based on the first evaluation cycle and sensor data, that the wind turbine is in a dangerous state;

[0007] Determine the vibration characteristic curve of the wind turbine based on the sensor data;

[0008] According to the vibration characteristic curve, determine the vibration trend curve and fault characteristic curve of the wind turbine;

[0009] Perform fault analysis on the wind turbine based on the fault characteristic curve and vibration trend curve to generate fault diagnosis information for the wind turbine;

[0010] Generate a vibration fault analysis report of the wind turbine based on the fault diagnosis information.

[0011] According to a second aspect of the present disclosure, a wind turbine vibration fault analysis system is provided, comprising:

[0012] A data acquisition unit, used to collect sensor data of the wind turbine;

[0013] A service management unit, the service management unit is connected to the data acquisition unit; wherein the service management unit is used to receive sensor data sent by the data acquisition unit;

[0014] A vibration fault analysis unit is connected to the service management unit and is configured to execute the wind turbine vibration fault analysis method described in the first aspect.

[0015] According to a third aspect of the present disclosure, a wind turbine vibration fault analysis device is provided, comprising:

[0016] An acquisition module, configured to acquire sensor data of the wind turbine during a first evaluation period;

[0017] a first determining module, configured to determine, based on a first evaluation period and sensor data, that the wind turbine is in a dangerous state;

[0018] a second determining module, configured to determine a vibration characteristic curve of the wind turbine based on the sensor data;

[0019] a third determining module, configured to determine a vibration trend curve and a fault characteristic curve of the wind turbine generator based on the vibration characteristic curve;

[0020] The fault analysis module is used to perform fault analysis on the wind turbine according to the fault characteristic curve and the vibration trend curve, and generate fault diagnosis information of the wind turbine, so that the report unit can generate a vibration fault analysis report according to the fault diagnosis information of the wind turbine.

[0021] In some embodiments of the present disclosure, the vibration characteristic curve in the third determination module includes a vibration information time domain curve. The third determination module is further configured to perform trend analysis on the vibration information time domain curve to determine a peak value index, a peak-to-peak value index, a kurtosis index, a pulse value index, and a margin value index of the vibration information time domain curve; the vibration information time domain curve refers to a curve whose horizontal axis represents time information and whose vertical axis represents vibration acceleration information or vibration velocity information; based on the peak value index, peak-to-peak value index, kurtosis index, pulse value index, and margin value index of the vibration information time domain curve, a vibration trend curve of the wind turbine is determined; wherein the vibration trend curve refers to a curve whose horizontal axis represents time information and whose vertical axis represents a peak value index, peak-to-peak value index, kurtosis index, pulse value index, or margin value index.

[0022] In some embodiments of the present disclosure, the vibration characteristic curve in the third determination module includes a vibration information frequency domain curve. The third determination module is further configured to obtain fault frequency information of the wind turbine; mark the vibration information frequency domain curve based on the fault frequency information to determine the fault characteristic curve of the wind turbine; wherein the vibration information frequency domain curve refers to a curve with frequency information on the horizontal axis and vibration acceleration information, vibration velocity information, marginal spectrum amplitude information, or envelope spectrum amplitude information on the vertical axis.

[0023] In some embodiments of the present disclosure, the third determination module is further used to determine the three-sideband information and the five-fold frequency information based on the fault frequency information; wherein the three-sideband information includes the vibration velocity information and the vibration acceleration information corresponding to the single-fold sideband, double-fold sideband and triple-fold sideband of the fault frequency information respectively; the five-fold frequency information includes the vibration velocity information and the vibration acceleration information corresponding to the single-fold frequency information, double-fold frequency information, triple-fold frequency information, quadruple-fold frequency information and five-fold frequency information of the wind turbine's rotation frequency information respectively; the vibration information frequency domain curve is marked according to the three-sideband information and the five-fold frequency information to obtain the fault characteristic curve of the wind turbine; wherein the fault characteristic curve refers to the vibration information frequency domain curve of the five-fold frequency information and the three-sideband information marked with the fault frequency information.

[0024] In some embodiments of the present disclosure, the first determination module is further used to divide the first evaluation cycle into at least one second evaluation cycle; determine the vibration velocity evaluation value based on the first evaluation cycle, at least one second evaluation cycle and the vibration velocity information; determine the vibration acceleration evaluation value based on the first evaluation cycle, at least one second evaluation cycle and the vibration acceleration information; and determine that the wind turbine is in a dangerous state based on the vibration velocity evaluation value and the vibration acceleration evaluation value.

[0025] In some embodiments of the present disclosure, the first determination module is further configured to determine that the wind turbine is in a dangerous state when the vibration velocity evaluation value is greater than or equal to a first threshold and / or the vibration acceleration evaluation value is greater than or equal to a second threshold.

[0026] According to a fourth aspect of the present disclosure, there is provided an electronic device, including:

[0027] at least one processor; and

[0028] a memory communicatively connected to at least one processor; wherein,

[0029] The memory stores instructions that can be executed by at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to perform the method of the first aspect mentioned above.

[0030] According to a fifth aspect of the present disclosure, a non-transitory computer-readable storage medium storing computer instructions is provided, wherein the computer instructions are used to enable a computer to execute the method of the first aspect.

[0031] According to a sixth aspect of the present disclosure, a computer program product is provided, comprising a computer program, which implements the steps of the method described in the first aspect when executed by a processor.

[0032] The technical solution disclosed herein obtains sensor data of a wind turbine within a first evaluation period; determines that the wind turbine is in a dangerous state based on the first evaluation period and the sensor data; determines a vibration characteristic curve of the wind turbine based on the sensor data; determines a vibration trend curve and a fault characteristic curve of the wind turbine based on the vibration characteristic curve; performs a fault analysis on the wind turbine based on the fault characteristic curve and the vibration trend curve, and generates fault diagnosis information for the wind turbine; this can intuitively and accurately reflect the problem of wind turbine vibration faults, improve the comprehensiveness and accuracy of wind turbine vibration fault analysis, and facilitate users to conveniently and timely obtain effective information on wind turbine vibration faults.

[0033] It should be understood that the contents described in this section are not intended to identify the key or important features of the embodiments of the present disclosure, nor are they intended to limit the scope of the present disclosure. Other features of the present disclosure will become readily understood through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0034] The accompanying drawings are provided to facilitate a better understanding of the present invention and do not constitute a limitation of the present disclosure.

[0035] Figure 1 is a flow chart of a method for analyzing vibration faults of a wind turbine generator according to an embodiment of the present disclosure;

[0036] Figure 2 is a flow chart of a method for analyzing vibration faults of a wind turbine generator according to an embodiment of the present disclosure;

[0037] Figure 3 is a flow chart of a method for analyzing vibration faults of a wind turbine generator according to an embodiment of the present disclosure;

[0038] Figure 4 is a flow chart of a method for analyzing vibration faults of a wind turbine generator according to an embodiment of the present disclosure;

[0039] Figure 5 is a block diagram of a wind turbine vibration fault analysis system provided according to an embodiment of the present disclosure;

[0040] Figure 6 is a block diagram of a wind turbine vibration fault analysis device provided according to an embodiment of the present disclosure;

[0041] Figure 7 is a block diagram of an electronic device provided according to an embodiment of the present disclosure. DETAILED DESCRIPTION

[0042] The following description of exemplary embodiments of the present disclosure is made in conjunction with the accompanying drawings, including various details of the embodiments of the present disclosure to facilitate understanding. These details should be considered as merely exemplary. Therefore, those skilled in the art will recognize that various changes and modifications may be made to the embodiments described herein without departing from the scope and spirit of the present disclosure. Similarly, for the sake of clarity and conciseness, descriptions of well-known functions and structures are omitted in the following description.

[0043] It should be noted that the collection, storage, use, processing, transmission, provision and disclosure of user personal information involved in the technical solution of this disclosure are in compliance with the provisions of relevant laws and regulations and do not violate public order and good morals.

[0044] In the description of the present disclosure, unless otherwise specified, “ / ” means or, for example, A / B can mean A or B; “and / or” in this article is merely a way to describe the association relationship of associated objects, indicating that there can be three relationships, for example, A and / or B can mean: A exists alone, A and B exist at the same time, and B exists alone.

[0045] Figure 1 This is a flow chart of a method for analyzing vibration failure of a wind turbine according to an embodiment of the present disclosure. Figure 1 As shown, the wind turbine vibration fault analysis method includes but is not limited to the following steps:

[0046] In step S101 , sensor data of a wind turbine in a first evaluation period is acquired.

[0047] It should be noted that sensor data includes, but is not limited to, sensor location information, measurement direction information, and frequency range information. Optionally, in some embodiments, the first evaluation period is determined based on the sensor location information, measurement direction information, and frequency range information. For example, the range of values ​​for the first evaluation period can be obtained from Table 1.

[0048] Table 1

[0049]

[0050] For example, the location information of the sensor is the cabin, the measurement direction information is the axial direction, the frequency range information of the sensor is 0.1 Hz-100 Hz, and the first evaluation period may be 15 minutes.

[0051] It should be noted that Table 1 is illustrative only and is only provided for those skilled in the art to understand the embodiments of the present disclosure, and the present disclosure does not make any specific limitations thereto.

[0052] It should be noted that vibration velocity is primarily used for vibration assessment of medium-speed rotating machinery to reflect the magnitude of vibration energy, while vibration acceleration is primarily used for vibration assessment of high-speed rotating machinery to reflect the magnitude of vibration impact force. Optionally, in some embodiments, the sensor data also includes vibration velocity information and vibration acceleration information.

[0053] In step S102 , it is determined that the wind turbine is in a dangerous state based on the first evaluation cycle and sensor data.

[0054] Optionally, in some embodiments, a vibration velocity evaluation value and a vibration acceleration evaluation value are determined based on the first evaluation period and sensor data; and based on the vibration velocity evaluation value and the vibration acceleration evaluation value, it is determined that the wind turbine is in a dangerous state.

[0055] In step S103 , a vibration characteristic curve of the wind turbine is determined based on the sensor data.

[0056] Optionally, in some embodiments, the vibration characteristic curve of the wind turbine includes but is not limited to a vibration information time domain curve and a vibration information frequency domain curve.

[0057] It should be noted that time-domain analysis refers to an analysis method that performs signal filtering, amplification, statistical feature calculation, and correlation analysis within the time domain. It is used to provide effective information for dynamic analysis and fault diagnosis of mechanical systems. For example, a vibration information time-domain curve is a curve with time information on the horizontal axis and wind turbine vibration information on the vertical axis. It is used to perform time-domain analysis of wind turbine sensor data.

[0058] It should be noted that spectrum analysis refers to an analysis method that analyzes the amplitude and phase information of each characteristic frequency of a signal to determine the operating status of the device. For example, a vibration information frequency domain curve is a curve with frequency information on the horizontal axis and wind turbine vibration information on the vertical axis. It is used to perform spectrum analysis on wind turbine sensor data.

[0059] In step S104, a vibration trend curve and a fault characteristic curve of the wind turbine are determined according to the vibration characteristic curve.

[0060] It should be noted that, in some embodiments, the vibration characteristic curve includes but is not limited to a vibration information time domain curve. In some embodiments, a vibration trend curve refers to a curve whose horizontal axis represents time information and whose vertical axis represents a vibration trend index. Optionally, in some embodiments, a trend analysis is performed on the vibration information time domain curve to determine the vibration trend curve of the wind turbine. Exemplarily, a trend analysis is performed on the vibration information time domain curve to determine the vibration trend index of the wind turbine; and based on the vibration trend index, the vibration trend curve of the wind turbine is determined.

[0061] It should be noted that, in some embodiments, the vibration characteristic curve includes but is not limited to the vibration information frequency domain curve. Optionally, in some embodiments, the vibration information frequency domain curve is marked to determine the fault characteristic curve of the wind turbine.

[0062] In step S105 , a fault analysis is performed on the wind turbine generator according to the fault characteristic curve and / or the vibration trend curve to generate fault diagnosis information of the wind turbine generator.

[0063] Optionally, in some embodiments, a fault analysis of the wind turbine is performed based on the fault characteristic curve and / or the vibration trend curve to determine a wind turbine vibration fault analysis result; and fault diagnosis information of the wind turbine is generated based on the wind turbine vibration fault analysis result.

[0064] It should be noted that in some embodiments, when a gear in a gearbox of a wind turbine fails, the vibration trend curve may exhibit an impact signal having a period of the gear's rotational period. Exemplarily, a determination is made as to whether the vibration trend curve exhibits an impact signal having a period of the gear's rotational period; if it is determined that the vibration trend curve exhibits an impact signal having a period of the gear's rotational period, a wind turbine vibration fault analysis result is determined; and based on the wind turbine vibration fault analysis result, wind turbine fault diagnosis information is generated.

[0065] In step S106, a vibration fault analysis report of the wind turbine is generated according to the fault diagnosis information.

[0066] Optionally, in some embodiments, a vibration fault analysis report of the wind turbine is generated based on the fault characteristic curve, the vibration trend curve, and the fault diagnosis information. Exemplarily, the vibration fault analysis report of the wind turbine includes the fault characteristic curve, the vibration trend curve, and the corresponding fault diagnosis information.

[0067] In an embodiment of the present disclosure, sensor data of a wind turbine within a first evaluation period is obtained; based on the first evaluation period and the sensor data, it is determined that the wind turbine is in a dangerous state; based on the sensor data, a vibration characteristic curve of the wind turbine is determined; based on the vibration characteristic curve, a vibration trend curve and a fault characteristic curve of the wind turbine are determined; a fault analysis of the wind turbine is performed based on the fault characteristic curve and the vibration trend curve, and fault diagnosis information of the wind turbine is generated; this can intuitively and accurately reflect the problem of wind turbine vibration fault, improve the comprehensiveness and accuracy of wind turbine vibration fault analysis, and facilitate users to conveniently and timely obtain effective information on wind turbine vibration faults.

[0068] Figure 2 This is a flow chart of a method for analyzing vibration failure of a wind turbine according to an embodiment of the present disclosure. Figure 2As shown, the wind turbine vibration fault analysis method includes but is not limited to the following steps:

[0069] In step S201 , sensor data of a wind turbine in a first evaluation period is acquired.

[0070] In the embodiment of the present disclosure, step S201 can be implemented in any of the ways in the embodiments of the present disclosure, which is not limited in the embodiment of the present disclosure and will not be described in detail.

[0071] In step S202 , it is determined that the wind turbine is in a dangerous state based on the first evaluation cycle and sensor data.

[0072] In the embodiment of the present disclosure, step S202 can be implemented in any of the ways in the embodiments of the present disclosure, which is not limited in the embodiment of the present disclosure and will not be described in detail.

[0073] In step S203 , a vibration characteristic curve of the wind turbine is determined based on the sensor data.

[0074] It should be noted that, in some embodiments, the vibration characteristic curve includes but is not limited to a vibration information time domain curve. The vibration information time domain curve refers to a curve with time information on the horizontal axis and vibration velocity information or vibration acceleration information on the vertical axis.

[0075] It should be noted that, in some embodiments, a vibration acceleration time-domain curve refers to a curve with time information on the horizontal axis and vibration acceleration information on the vertical axis; a vibration velocity time-domain curve refers to a curve with time information on the horizontal axis and vibration velocity information on the vertical axis. Optionally, in some embodiments, vibration information time-domain curves include but are not limited to vibration acceleration time-domain curves and vibration velocity time-domain curves.

[0076] In step S204 , a trend analysis is performed on the vibration information time domain curve to determine the peak index, peak-to-peak index, kurtosis index, pulse index, and margin index of the vibration information time domain curve.

[0077] It should be noted that, in some embodiments, vibration information includes but is not limited to vibration velocity information and vibration acceleration information.

[0078] Optionally, in some embodiments, the time domain sequence of the vibration information is determined based on the time domain curve of the vibration information; and the peak index, peak-to-peak index, kurtosis index, pulse index and margin index of the time domain curve of the vibration information are determined based on the time domain sequence of the vibration information.

[0079] For example, the peak index of the vibration information time domain curve can be calculated using the following formula (1):

[0080]

[0081] Among them, x p It refers to the peak index of the vibration information time domain curve; x(n) refers to the time domain sequence of vibration information in the vibration information time domain curve, and the vibration information includes but is not limited to vibration acceleration information and vibration velocity information; n refers to the index of the sample in the time domain sequence; N refers to the number of samples in the time domain sequence; MAX refers to the maximum value function, which is used to calculate the maximum value of the samples in the time domain sequence.

[0082] For example, the peak-to-peak value index of the vibration information time domain curve can be calculated using the following formula (2):

[0083] x pp =MAX(x(n))-MIN(x(n)) (2)

[0084] Among them, x pp It refers to the peak-to-peak value indicator of the vibration information time domain curve; MAX refers to the maximum value function, which is used to calculate the maximum value of samples in the time domain sequence; MIN refers to the minimum value function, which is used to calculate the minimum value of samples in the time domain sequence.

[0085] Exemplarily, based on the vibration information time domain curve, the time domain sequence of the vibration information is determined; the mean information and standard deviation information of the time domain sequence are determined; and based on the time domain sequence, the mean information and the standard deviation information, the kurtosis index of the vibration information time domain curve is determined.

[0086] For example, the mean information of the time domain series can be calculated using the following formula (3):

[0087]

[0088] in, refers to the mean information of the time domain sequence; x(n) refers to the time domain sequence of vibration information in the vibration information time domain curve; n refers to the index of the sample in the time domain sequence; N refers to the number of samples in the time domain sequence.

[0089] For example, the standard deviation information of the time domain series can be calculated using the following formula (4):

[0090]

[0091] Among them, σ x Refers to the standard deviation information of the time domain series; refers to the mean information of the time domain sequence; x(n) refers to the time domain sequence of vibration information in the vibration information time domain curve; n refers to the index of the sample in the time domain sequence; N refers to the number of samples in the time domain sequence.

[0092] For example, the kurtosis index of the vibration information time domain curve can be calculated using the following formula (5):

[0093]

[0094] Among them, K refers to the kurtosis index of the vibration information time domain curve; Refers to the mean information of the time domain series; σ x Refers to the standard deviation information of the time domain series.

[0095] For example, the pulse index of the vibration information time domain curve can be calculated by the following formula (6):

[0096]

[0097] Where I refers to the pulse index of the vibration information time domain curve; Refers to the mean information of the time domain series; MAX refers to the maximum value function, which is used to calculate the maximum value of samples in the time domain series.

[0098] For example, the time domain sequence of the vibration information is determined based on the time domain curve of the vibration information; the square root amplitude information of the time domain sequence is determined; and the margin index of the time domain curve of the vibration information is determined based on the square root amplitude information and the time domain sequence. For example, the square root amplitude information of the time domain sequence can be calculated using the following formula (7):

[0099]

[0100] Among them, x t refers to the square root amplitude information of the time domain sequence; x(n) refers to the time domain sequence of vibration information in the vibration information time domain curve; n refers to the index of the sample in the time domain sequence; N refers to the number of samples in the time domain sequence.

[0101] For example, the margin index of the vibration information time domain curve can be calculated using the following formula (8):

[0102]

[0103] Among them, L refers to the margin index of the vibration information time domain curve; x t Refers to the square root amplitude information of the time domain series; MAX refers to the maximum value function, which is used to calculate the maximum value of samples in the time domain series.

[0104] In step S205 , a vibration trend curve of the wind turbine is determined according to the peak index, peak-to-peak index, kurtosis index, pulse index and margin index of the vibration information time domain curve.

[0105] It should be noted that in some embodiments, a vibration trend curve refers to a curve with time information on the horizontal axis and a peak index, peak-to-peak index, kurtosis index, pulse index, or margin index on the vertical axis. A peak index curve refers to a curve with time information on the horizontal axis and a peak index on the vertical axis; a peak-to-peak index curve refers to a curve with time information on the horizontal axis and a peak-to-peak index on the vertical axis; a kurtosis index curve refers to a curve with time information on the horizontal axis and a kurtosis index on the vertical axis; and a margin index curve refers to a curve with time information on the horizontal axis and a margin index on the vertical axis.

[0106] Optionally, in some embodiments, the vibration trend curve includes but is not limited to a peak index curve, a peak-to-peak index curve, a kurtosis index curve, and a margin index curve.

[0107] It should be noted that a vibration fault in a wind turbine can affect the speed information and output power information of the wind turbine. Optionally, in some embodiments, the vibration trend curve further includes a curve with the speed information on the horizontal axis and the peak index, peak-to-peak index, kurtosis index, pulse index, or margin index on the vertical axis, and a curve with the output power information on the horizontal axis and the peak index, peak-to-peak index, kurtosis index, pulse index, or margin index on the vertical axis.

[0108] In step S206, fault analysis is performed on the wind turbine generator according to the fault characteristic curve and the vibration trend curve to generate fault diagnosis information of the wind turbine generator.

[0109] In the embodiment of the present disclosure, step S206 can be implemented in any of the ways in the embodiments of the present disclosure, which is not limited in the embodiment of the present disclosure and will not be described in detail.

[0110] In step S207, a vibration fault analysis report of the wind turbine is generated according to the fault diagnosis information.

[0111] In the embodiment of the present disclosure, step S207 can be implemented in any of the ways in the embodiments of the present disclosure, which is not limited in the embodiment of the present disclosure and will not be described in detail.

[0112] In an embodiment of the present disclosure, a time-domain curve of the vibration information of a wind turbine is determined based on sensor data. A trend analysis is performed on the time-domain curve of the vibration information to determine the peak index, peak-to-peak index, kurtosis index, pulse index, and margin index of the time-domain curve of the vibration information. Based on the peak index, peak-to-peak index, kurtosis index, pulse index, and margin index of the time-domain curve of the vibration information, a vibration trend curve of the wind turbine is determined. In this way, vibration fault analysis of the wind turbine can be performed based on the time-domain characteristics and indicators of the vibration information, intuitively reflecting the problem of wind turbine vibration fault from a time-domain perspective, further improving the comprehensiveness and accuracy of wind turbine vibration fault analysis.

[0113] Figure 3 This is a flow chart of a method for analyzing vibration failure of a wind turbine according to an embodiment of the present disclosure. Figure 3 As shown, the wind turbine vibration fault analysis method includes but is not limited to the following steps:

[0114] In step S301 , sensor data of a wind turbine in a first evaluation period is acquired.

[0115] In the embodiment of the present disclosure, step S301 can be implemented in any of the ways in the embodiments of the present disclosure, which is not limited in the embodiment of the present disclosure and will not be described in detail.

[0116] In step S302 , it is determined that the wind turbine is in a dangerous state based on the first evaluation cycle and sensor data.

[0117] In the embodiment of the present disclosure, step S302 can be implemented in any of the ways in the embodiments of the present disclosure, which is not limited in the embodiment of the present disclosure and will not be described in detail.

[0118] In step S303 , a vibration characteristic curve of the wind turbine is determined based on the sensor data.

[0119] It should be noted that, in some embodiments, the vibration characteristic curve includes but is not limited to a vibration information frequency domain curve.

[0120] It should be noted that, in some embodiments, a vibration information frequency domain curve refers to a curve with frequency information on the horizontal axis and vibration acceleration information, vibration velocity information, marginal spectrum amplitude information, or envelope spectrum amplitude information on the vertical axis. A vibration acceleration frequency domain curve refers to a curve with frequency information on the horizontal axis and vibration acceleration information on the vertical axis; a vibration velocity frequency domain curve refers to a curve with frequency information on the horizontal axis and vibration velocity information on the vertical axis; a marginal spectrum curve refers to a curve with frequency information on the horizontal axis and marginal spectrum amplitude information on the vertical axis; and an envelope spectrum curve refers to a curve with frequency information on the horizontal axis and envelope spectrum amplitude information on the vertical axis.

[0121] It should be noted that different fault types generate different fault frequency information. The envelope spectrum curve reflects the severity of the vibration fault by extracting the characteristic frequency and amplitude of the periodic impact information in the vibration information. By comparing the envelope spectrum curve with the known fault frequency information, the fault type and fault location can be determined. Optionally, in some embodiments, periodic impact information is obtained from the sensor data; the periodic impact information is enveloped to obtain an envelope curve; and the envelope curve is fast Fourier transformed to generate an envelope spectrum curve.

[0122] It should be noted that the marginal spectrum curve is a technology used in the fields of signal processing and vibration analysis to extract periodic impact information or transient event characteristics. The marginal spectrum curve displays the energy distribution of each frequency component in the vibration information by analyzing the time domain and frequency domain characteristics of the vibration information. The marginal spectrum curve and other fault diagnosis techniques can be used to analyze the operating status of the wind turbine, and perform fault diagnosis and evaluation. Optionally, in some embodiments, the Hilbert time-frequency spectrum of the wind turbine is determined based on the sensor data; the Hilbert time-frequency spectrum is integrated to obtain the marginal spectrum curve.

[0123] Optionally, in some embodiments, the vibration information frequency domain curve includes but is not limited to a vibration acceleration frequency domain curve, a vibration velocity frequency domain curve, a marginal spectrum curve, and an envelope spectrum curve.

[0124] It should be noted that the speed information of the wind turbine may fluctuate or have errors during actual operation, which will affect the spectrum analysis of the vibration information frequency domain curve. The frequency information is corrected based on the known wind turbine operating speed data, so that the frequency information corresponding to each component of the wind turbine can be accurately identified and located in the vibration information frequency domain curve, so as to obtain more accurate analysis results. Optionally, in some embodiments, the frequency information of the wind turbine is adjusted to an effective frequency that matches the operating state of the wind turbine; and the vibration information frequency domain curve is determined based on the adjusted frequency information.

[0125] In step S304, the fault frequency information of the wind turbine is obtained.

[0126] It should be noted that, in some embodiments, a wind turbine includes, but is not limited to, rotor blades, a gearbox, a generator, and a tower. The fault frequency information of the wind turbine includes fault frequency information of each component of the wind turbine. The fault frequency information of each component of the wind turbine refers to the vibration frequency information of the component when in a faulty state. Optionally, in some embodiments, the fault frequency information of the wind turbine includes, but is not limited to, fault frequency information of the gearbox, rotor blades, and generator.

[0127] It should be noted that, in some embodiments, the fault frequency information of the wind turbine can be obtained from the manufacturer of the wind turbine, and the fault frequency information of the wind turbine can also be calculated based on the factory parameters of the wind turbine. This disclosure does not make specific limitations on this and will not elaborate on it.

[0128] In step S305 , the vibration information frequency domain curve is marked according to the fault frequency information to determine the fault characteristic curve of the wind turbine.

[0129] It should be noted that, in some embodiments, the vibration information frequency domain curve refers to a curve with the horizontal axis being frequency information and the vertical axis being vibration acceleration information, vibration velocity information, marginal spectrum amplitude information, or envelope spectrum amplitude information. The vibration acceleration frequency domain curve refers to a curve with the horizontal axis being frequency information and the vertical axis being vibration acceleration information; the vibration velocity frequency domain curve refers to a curve with the horizontal axis being frequency information and the vertical axis being vibration velocity information; the marginal spectrum curve refers to a curve with the horizontal axis being frequency information and the vertical axis being marginal spectrum amplitude information; and the envelope spectrum curve refers to a curve with the horizontal axis being frequency information and the vertical axis being envelope spectrum amplitude information. Optionally, in some embodiments, the vibration information frequency domain curve includes but is not limited to the vibration acceleration frequency domain curve, the vibration velocity frequency domain curve, the marginal spectrum curve, and the envelope spectrum curve.

[0130] It should be noted that, in some embodiments, the gearbox fault frequency information is specific frequency information generated by the faulty gearbox. Optionally, in some embodiments, the gearbox fault frequency information includes but is not limited to gear shaft rotation frequency information and gear meshing frequency information.

[0131] It should be noted that in some embodiments, sidebands refer to specific frequency components surrounding the gear meshing frequency information. Faults in the gear meshing process can cause sidebands to appear. A single sideband is the frequency corresponding to the gear meshing frequency information plus or minus the gear shaft rotational frequency information; a double sideband is the frequency corresponding to the gear meshing frequency information plus or minus twice the gear shaft rotational frequency information; a triple sideband is the frequency corresponding to the gear meshing frequency information plus or minus three times the gear shaft rotational frequency information, and so on.

[0132] It should be noted that by analyzing the triple-sideband information and harmonic components in the vibration information, vibration faults can be identified and located. Optionally, in some embodiments, the triple-sideband information includes vibration velocity information and vibration acceleration information corresponding to the single, double, and triple sidebands of the fault frequency information, respectively.

[0133] It should be noted that frequency multiplication refers to the frequency information corresponding to an integer multiple of the wind turbine's rotational frequency information. Single-frequency information refers to the wind turbine's rotational frequency information; double-frequency information refers to twice the wind turbine's rotational frequency information, and so on. For example, for a wind turbine with a rotational frequency of 30 Hz, the five-frequency information of the wind turbine is 150 Hz.

[0134] It should be noted that if a wind turbine has local damage or cracks, the frequency-multiplication data of the rotational frequency information may be abnormal. This abnormal frequency-multiplication data is compared with normal data to accurately determine the nature and severity of the wind turbine vibration fault. The quintuple frequency information includes the vibration velocity and vibration acceleration information corresponding to the single, double, triple, quadruple, and quintuple frequency information of the wind turbine's rotational frequency information, respectively.

[0135] It should be noted that in some embodiments, the fault characteristic curve refers to a vibration information frequency domain curve that labels the quintuplicate frequency information and tri-sideband information of the fault frequency information. Alternatively, in some embodiments, the tri-sideband information and quintuplicate frequency information are determined based on the fault frequency information; the vibration information frequency domain curve is labeled based on the tri-sideband information and the quintuplicate frequency information to obtain the fault characteristic curve of the wind turbine.

[0136] In step S306, fault analysis is performed on the wind turbine generator according to the fault characteristic curve and the vibration trend curve to generate fault diagnosis information of the wind turbine generator.

[0137] Optionally, in some embodiments, a fault analysis is performed on the wind turbine based on the fault characteristic curve and the vibration trend curve to determine the fault analysis result; and fault diagnosis information of the wind turbine is generated based on the fault analysis result, the fault characteristic curve and the vibration trend curve.

[0138] It should be noted that, in some embodiments, when there is a broken tooth during the gear meshing process, sidebands will appear in the vibration acceleration frequency domain curve. For example, the gear meshing frequency information is 100Hz, the gear shaft rotation frequency information is 2Hz, the single sidebands are 98Hz and 102Hz, and the double sidebands are 96Hz and 104Hz. When there is a broken tooth during the gear meshing process, a single sideband with abnormal amplitude will appear around the gear meshing frequency information in the vibration acceleration frequency domain curve; when there are two broken teeth during the gear meshing process, a double sideband with abnormal amplitude will appear around the gear meshing frequency information in the vibration acceleration frequency domain curve.

[0139] Optionally, in some embodiments, it is determined that there is a double sideband with abnormal amplitude around the gear meshing frequency information in the vibration acceleration frequency domain curve; it is determined that the fault analysis result is that there is a broken tooth in the gearbox of the wind turbine; and fault diagnosis information of the wind turbine is generated based on the fault analysis results, the fault characteristic curve and the vibration trend curve.

[0140] In step S307, a vibration fault analysis report of the wind turbine is generated according to the fault diagnosis information.

[0141] In the embodiment of the present disclosure, step S307 can be implemented in any of the ways in the embodiments of the present disclosure, which is not limited in the embodiment of the present disclosure and will not be described in detail.

[0142] In an embodiment of the present disclosure, a frequency domain curve of wind turbine vibration information is determined based on sensor data. Fault frequency information of the wind turbine is obtained. The frequency domain curve of the vibration information is labeled based on the fault frequency information to determine the fault characteristic curve of the wind turbine. This allows for spectral analysis of the fault characteristic curve of the wind turbine, intuitively reflecting the vibration fault of the wind turbine from a frequency domain perspective, further improving the comprehensiveness and accuracy of wind turbine vibration fault analysis.

[0143] Figure 4 This is a flow chart of a method for analyzing vibration failure of a wind turbine according to an embodiment of the present disclosure. Figure 4 As shown, the wind turbine vibration fault analysis method includes but is not limited to the following steps:

[0144] In step S401 , sensor data of a wind turbine in a first evaluation period is acquired.

[0145] It should be noted that, in some embodiments, the sensor data includes sensor position information, measurement direction information, sensor frequency range information, vibration acceleration information, and vibration velocity information.

[0146] In step S402 , the first evaluation period is divided into at least one second evaluation period.

[0147] Exemplarily, the first evaluation cycle includes at least one second evaluation cycle. For example, the relationship between the first evaluation cycle and the second evaluation cycle can be expressed by the following formula (9).

[0148]

[0149] Among them, T0 refers to the first evaluation cycle; T e refers to the e-th second evaluation cycle in the first evaluation cycle; n refers to the number of at least one second evaluation cycle.

[0150] In step S403 , a vibration velocity evaluation value is determined according to the first evaluation period, at least one second evaluation period, and the vibration velocity information.

[0151] Optionally, in some embodiments, for each second evaluation period in at least one second evaluation period, a segmented vibration velocity evaluation value within the second evaluation period is determined based on the second evaluation period and the vibration velocity information. Exemplarily, the segmented vibration velocity evaluation value within the second evaluation period can be calculated using the following formula (10):

[0152]

[0153] Among them, v rmswe Refers to the vibration speed segmented evaluation value within the second evaluation period; T e Refers to the second evaluation cycle; v w It refers to the vibration velocity information after frequency filtering after eliminating temperature drift and impact instability trend items.

[0154] Optionally, in some embodiments, the vibration velocity evaluation value is determined based on the first evaluation period, the at least one second evaluation period, and the vibration velocity segment evaluation value corresponding to each second evaluation period in the at least one second evaluation period. Exemplarily, the vibration velocity evaluation value can be calculated using the following formula (11):

[0155]

[0156] Among them, v rmsw0 Refers to the vibration velocity assessment value; v rmswe Refers to the vibration speed segmented evaluation value in the e-th second evaluation cycle; T0 refers to the first evaluation cycle; T e refers to the e-th second evaluation cycle in the first evaluation cycle; n refers to the number of at least one second evaluation cycle.

[0157] In step S404 , a vibration acceleration evaluation value is determined according to the first evaluation period, at least one second evaluation period, and the vibration acceleration information.

[0158] Optionally, in some embodiments, for each second evaluation period in at least one second evaluation period, a segmented vibration acceleration evaluation value within the second evaluation period is determined based on the second evaluation period and the vibration acceleration information. Exemplarily, the segmented vibration acceleration evaluation value within the second evaluation period can be calculated using the following formula (12):

[0159]

[0160] Among them, among them, α rmswe Refers to the vibration acceleration segment evaluation value in the second evaluation cycle; T e Refers to the second evaluation cycle; α w It refers to the vibration acceleration information after frequency filtering after eliminating temperature drift and impact instability trend items.

[0161] Optionally, in some embodiments, the vibration acceleration evaluation value is determined based on the first evaluation period, the at least one second evaluation period, and the vibration acceleration segment evaluation value corresponding to each second evaluation period in the at least one second evaluation period. Exemplarily, the vibration acceleration evaluation value can be calculated using the following formula (13):

[0162]

[0163] Among them, among them, α rmsw0 Refers to the vibration acceleration evaluation value; α rmswe Refers to the vibration acceleration segment evaluation value in the e-th second evaluation cycle; T0 refers to the first evaluation cycle; T e refers to the e-th second evaluation cycle in the first evaluation cycle; n refers to the number of at least one second evaluation cycle.

[0164] In step S405 , it is determined that the wind turbine is in a dangerous state based on the vibration velocity evaluation value and the vibration acceleration evaluation value.

[0165] Optionally, in some embodiments, when the vibration velocity evaluation value is greater than or equal to a first threshold, and / or the vibration acceleration evaluation value is greater than or equal to a second threshold, it is determined that the wind turbine is in a dangerous state.

[0166] Exemplarily, when the vibration speed evaluation value is greater than or equal to a first threshold, it is determined that the wind turbine is in a dangerous state.

[0167] Exemplarily, when the vibration acceleration evaluation value is greater than or equal to the second threshold, it is determined that the wind turbine is in a dangerous state.

[0168] Exemplarily, when the vibration velocity evaluation value is greater than or equal to a first threshold and the vibration acceleration evaluation value is greater than or equal to a second threshold, it is determined that the wind turbine is in a dangerous state.

[0169] In step S406 , a vibration characteristic curve of the wind turbine is determined based on the sensor data.

[0170] In the embodiment of the present disclosure, step S406 can be implemented in any of the ways in the embodiments of the present disclosure, which is not limited in the embodiment of the present disclosure and will not be described in detail.

[0171] In step S407 , the vibration trend curve and the fault characteristic curve of the wind turbine are determined according to the vibration characteristic curve.

[0172] In the embodiment of the present disclosure, step S407 can be implemented in any of the ways in the embodiments of the present disclosure, which is not limited in the embodiment of the present disclosure and will not be described in detail.

[0173] In step S408, fault analysis is performed on the wind turbine generator according to the fault characteristic curve and the vibration trend curve to generate fault diagnosis information of the wind turbine generator.

[0174] In the embodiment of the present disclosure, step S408 can be implemented in any of the ways in the embodiments of the present disclosure, which is not limited in the embodiment of the present disclosure and will not be described in detail.

[0175] In step S409, a vibration fault analysis report of the wind turbine is generated according to the fault diagnosis information.

[0176] In the embodiment of the present disclosure, step S409 can be implemented in any of the ways in the embodiments of the present disclosure, which is not limited in the embodiment of the present disclosure and will not be described in detail.

[0177] In an embodiment of the present disclosure, a first evaluation cycle is divided into at least one second evaluation cycle. A vibration velocity assessment value is determined based on the first evaluation cycle, the at least one second evaluation cycle, and the vibration velocity information. A vibration acceleration assessment value is determined based on the first evaluation cycle, the at least one second evaluation cycle, and the vibration acceleration information. Based on the vibration velocity assessment value and the vibration acceleration assessment value, it is determined that the wind turbine is in a dangerous state. This allows for accurate and timely detection of wind turbines in dangerous states, and allows for fault analysis of such wind turbines to ensure stable operation of the wind turbines.

[0178] Figure 5 FIG. 1 is a block diagram of a wind turbine vibration fault analysis system according to an embodiment of the present disclosure. Figure 5 As shown, the wind turbine vibration fault analysis system includes but is not limited to a data acquisition unit 501 , a service management unit 502 , and a vibration fault analysis unit 503 .

[0179] The data acquisition unit 501 is used to collect sensor data of the wind turbine;

[0180] The service management unit 502 is connected to the data acquisition unit 501; wherein the service management unit 502 is used to receive the sensor data sent by the data acquisition unit 501;

[0181] The vibration fault analysis unit 503 is connected to the service management unit 502 and is configured to execute the wind turbine vibration fault analysis method in the above method embodiment.

[0182] It should be noted that, in some embodiments, the wind turbine vibration fault analysis system only includes the data acquisition unit 501 and the vibration fault analysis unit 503. The data acquisition unit 501 and the vibration fault analysis unit 503 are deployed on the wind turbine, so that the wind turbine has the vibration fault analysis capability, that is, it can implement the wind turbine vibration fault analysis method in the above method embodiment.

[0183] It should be noted that, in some embodiments, the wind turbine vibration fault analysis system includes a data acquisition unit 501, a service management unit 502, and a vibration fault analysis unit 503. The data acquisition unit 501 is deployed on the wind turbine to collect sensor data from the wind turbine; the service management unit 502 and the vibration fault analysis unit 503 are deployed on a server in a data center to perform vibration fault analysis on the wind turbine based on the sensor data acquired by the data acquisition unit 501.

[0184] Optionally, in some embodiments, the service management unit 502 is further configured to determine that a communication failure has occurred in the wind turbine if the service management unit 502 does not receive sensor data sent by the data acquisition unit 501 within a first period of time. Exemplarily, the first period of time is 24 hours. If the service management unit 502 does not receive sensor data sent by the data acquisition unit 501 within 24 hours, the service management unit 502 determines that a communication failure has occurred in the wind turbine and issues a communication status fault alarm for the wind turbine.

[0185] Optionally, in some embodiments, the service management unit 502 is further configured to issue a danger alarm for the operation state of the wind turbine when it is determined that the wind turbine is in a dangerous state.

[0186] Optionally, in some embodiments, the vibration fault analysis unit 503 is further configured to manage the models and parameters of wind turbines. For example, the vibration fault analysis unit 503 maintains wind farm information, gearbox model information, number of teeth at each level, transmission ratio information, bearing model information, and bearing fault frequency parameter information for each type of wind turbine.

[0187] Optionally, in some embodiments, the vibration fault analysis unit 503 is further configured to display the warning status, sensor data, vibration characteristic curves, vibration trend curves, and fault characteristic curves of all wind turbines in each wind farm.

[0188] Figure 6 FIG. 1 is a block diagram of a wind turbine vibration fault analysis device according to an embodiment of the present disclosure. Figure 6 As shown, the wind turbine vibration fault analysis device includes but is not limited to an acquisition module 601 , a first determination module 602 , a second determination module 603 , a third determination module 604 and a fault analysis module 605 .

[0189] An acquisition module 601 is used to acquire sensor data of the wind turbine in a first evaluation period;

[0190] A first determining module 602 is configured to determine, based on a first evaluation period and sensor data, whether the wind turbine is in a dangerous state;

[0191] A second determining module 603 is configured to determine a vibration characteristic curve of the wind turbine based on the sensor data;

[0192] The third determining module 604 is configured to determine a vibration trend curve and a fault characteristic curve of the wind turbine generator based on the vibration characteristic curve;

[0193] The fault analysis module 605 is used to perform fault analysis on the wind turbine according to the fault characteristic curve and the vibration trend curve, and generate fault diagnosis information of the wind turbine, so that the report unit can generate a vibration fault analysis report according to the fault diagnosis information of the wind turbine.

[0194] As an example, the vibration characteristic curve in the third determination module 604 includes a vibration information time domain curve. The third determination module 604 is further configured to perform trend analysis on the vibration information time domain curve to determine a peak value index, a peak-to-peak value index, a kurtosis index, a pulse value index, and a margin value index of the vibration information time domain curve; a vibration information time domain curve is a curve whose horizontal axis represents time information and whose vertical axis represents vibration acceleration information or vibration velocity information; and a vibration trend curve of the wind turbine is determined based on the peak value index, peak-to-peak value index, kurtosis index, pulse value index, and margin value of the vibration information time domain curve; wherein a vibration trend curve is a curve whose horizontal axis represents time information and whose vertical axis represents a peak value index, peak-to-peak value index, kurtosis index, pulse value index, or margin value index.

[0195] As an example, the vibration characteristic curve in the third determination module 604 includes a vibration information frequency domain curve. The third determination module 604 is further configured to obtain fault frequency information of the wind turbine; mark the vibration information frequency domain curve based on the fault frequency information, and determine the fault characteristic curve of the wind turbine; wherein the vibration information frequency domain curve refers to a curve whose horizontal axis represents frequency information and whose vertical axis represents vibration acceleration information, vibration velocity information, marginal spectrum amplitude information, or envelope spectrum amplitude information.

[0196] As an example, the third determination module 604 is also used to determine the three-sideband information and the five-fold frequency information based on the fault frequency information; wherein the three-sideband information includes the vibration velocity information and vibration acceleration information corresponding to the single-fold sideband, double-fold sideband and triple-fold sideband of the fault frequency information respectively; the five-fold frequency information includes the vibration velocity information and vibration acceleration information corresponding to the single-fold frequency information, double-fold frequency information, triple-fold frequency information, quadruple-fold frequency information and five-fold frequency information of the wind turbine's rotation frequency information respectively; the vibration information frequency domain curve is marked according to the three-sideband information and the five-fold frequency information to obtain the fault characteristic curve of the wind turbine; wherein the fault characteristic curve refers to the vibration information frequency domain curve of the five-fold frequency information and the three-sideband information marked with the fault frequency information.

[0197] As an example, the first determination module 602 is also used to divide the first evaluation cycle into at least one second evaluation cycle; determine the vibration velocity evaluation value based on the first evaluation cycle, at least one second evaluation cycle and the vibration velocity information; determine the vibration acceleration evaluation value based on the first evaluation cycle, at least one second evaluation cycle and the vibration acceleration information; and determine that the wind turbine is in a dangerous state based on the vibration velocity evaluation value and the vibration acceleration evaluation value.

[0198] As an example, the first determining module 602 is further configured to determine that the wind turbine is in a dangerous state when the vibration velocity evaluation value is greater than or equal to a first threshold and / or the vibration acceleration evaluation value is greater than or equal to a second threshold.

[0199] Regarding the apparatus in the above embodiment, the specific manner in which each module performs operations has been described in detail in the embodiment of the method, and will not be elaborated here.

[0200] Optionally, in some embodiments, the present disclosure further provides an electronic device and a readable storage medium.

[0201] like Figure 7 As shown, Figure 7 is a block diagram of an electronic device provided according to an embodiment of the present disclosure. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device may also represent various forms of mobile devices, such as personal digital assistants, cellular phones, smartphones, wearable devices, and other similar computing devices. The components shown herein, their connections and relationships, and their functions are provided for example only and are not intended to limit the implementation of the present disclosure described and / or claimed herein.

[0202] like Figure 7 As shown, the electronic device includes: one or more processors 701, a memory 702, and interfaces for connecting various components, including high-speed interfaces and low-speed interfaces. The various components are connected to each other using different buses and can be installed on a common mainboard or installed in other ways as needed. The processor can process instructions executed in the electronic device, including instructions stored in or on the memory to display graphical information of a GUI on an external input / output device (such as a display device coupled to the interface). In other embodiments, if necessary, multiple processors and / or multiple buses can be used together with multiple memories and multiple memories. Similarly, multiple electronic devices can be connected, and each device provides some necessary operations (for example, as a server array, a group of blade servers, or a multi-processor system). Figure 7A processor 701 is taken as an example.

[0203] Memory 702 is a non-transitory computer-readable storage medium provided in the present disclosure. The memory stores instructions executable by at least one processor, causing the at least one processor to execute the wind turbine vibration fault analysis method provided in the present disclosure. The non-transitory computer-readable storage medium of the present disclosure stores computer instructions for causing a computer to execute the wind turbine vibration fault analysis method provided in the present disclosure.

[0204] The memory 702 is a non-transient computer-readable storage medium that can be used to store non-transient software programs, non-transient computer executable programs and modules, such as the program instructions / modules corresponding to the wind turbine vibration fault analysis method in the embodiment of the present disclosure (for example, the attached Figure 6 The processor 701 executes the non-transient software programs, instructions, and modules stored in the memory 702 to execute various functional applications and data processing of the server, thereby implementing the wind turbine vibration fault analysis method in the above method embodiment.

[0205] The memory 702 may include a program storage area and a data storage area, wherein the program storage area may store an operating system and applications required for at least one function; the data storage area may store data created based on the use of the electronic device, etc. In addition, the memory 702 may include a high-speed random access memory, and may also include a non-transient memory, such as at least one disk storage device, a flash memory device, or other non-transient solid-state storage device. In some embodiments, the memory 702 may optionally include a memory remotely located relative to the processor 701, and these remote memories may be connected to the electronic device via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.

[0206] The electronic device may further include: an input device 703 and an output device 704. The processor 701, the memory 702, the input device 703 and the output device 704 may be connected via a bus or other means. Figure 7 The bus connection is taken as an example.

[0207] The input device 703 can receive input digital or character information and generate key signal input related to user settings and function control of the electronic device, such as input devices such as a touch screen, a keypad, a mouse, a trackpad, a touch pad, an indicator stick, one or more mouse buttons, a trackball, and a joystick. The output device 704 may include a display device, an auxiliary lighting device (e.g., an LED), and a tactile feedback device (e.g., a vibration motor). The display device may include, but is not limited to, a liquid crystal display (LCD), a light emitting diode (LED) display, and a plasma display. In some embodiments, the display device may be a touch screen.

[0208] Optionally, in some embodiments, a computer program product is also provided, including a computer program. When the computer program is executed by one or more processors 701, it can implement the wind turbine vibration fault analysis method provided in the embodiment of the present disclosure.

[0209] Various implementations of the systems and techniques described herein can be realized in digital electronic circuit systems, integrated circuit systems, dedicated ASICs (application specific integrated circuits), computer hardware, firmware, software, and / or combinations thereof. These various implementations can include being implemented in one or more computer programs that can be executed and / or interpreted on a programmable system that includes at least one programmable processor, which can be a special purpose or general purpose programmable processor that can receive data and instructions from a storage system, at least one input device, and at least one output device, and transmit data and instructions to the storage system, the at least one input device, and the at least one output device.

[0210] These computer programs (also referred to as programs, software, software applications, or code) include machine instructions for a programmable processor and can be implemented using high-level procedural and / or object-oriented programming languages, and / or assembly / machine languages. As used herein, the terms "machine-readable medium" and "computer-readable medium" refer to any computer program product, apparatus, and / or device (e.g., a magnetic disk, an optical disk, a memory, a programmable logic device (PLD)) for providing machine instructions and / or data to a programmable processor, including a machine-readable medium that receives machine instructions as a machine-readable signal. The term "machine-readable signal" refers to any signal for providing machine instructions and / or data to a programmable processor.

[0211] To provide interaction with a user, the systems and techniques described herein can be implemented on a computer having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and pointing device (e.g., a mouse or trackball) through which the user can provide input to the computer. Other types of devices can also be used to provide interaction with the user; for example, the feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including acoustic input, voice input, or tactile input).

[0212] The systems and techniques described herein can be implemented in a computing system that includes back-end components (e.g., as a data server), or a computing system that includes middleware components (e.g., an application server), or a computing system that includes front-end components (e.g., a user computer with a graphical user interface or a web browser through which a user can interact with implementations of the systems and techniques described herein), or a computing system that includes any combination of such back-end components, middleware components, or front-end components. The components of the system can be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: a local area network (LAN), a wide area network (WAN), the Internet, and a blockchain network.

[0213] A computer system may include a client and a server. The client and server are generally remote from each other and typically interact via a communication network. This client-server relationship is established by computer programs running on the respective computers, establishing a client-server relationship. The server may be a cloud server, also known as a cloud computing server or cloud host, a host product within the cloud computing service ecosystem that addresses the management difficulties and limited scalability of traditional physical hosts and VPS services ("Virtual Private Servers" or simply "VPS"). The server may also be a server in a distributed system or a server integrated with blockchain.

[0214] It should be understood that the various forms of the processes shown above can be used to reorder, add, or delete steps. For example, the steps described in this disclosure can be performed in parallel, sequentially, or in a different order, as long as the desired results of the technical solutions disclosed in this disclosure can be achieved. This is not limited herein.

[0215] The above specific embodiments do not constitute a limitation on the scope of protection of this disclosure. Those skilled in the art will appreciate that various modifications, combinations, sub-combinations, and substitutions may be made based on design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of this disclosure shall be included within the scope of protection of this disclosure.

Claims

1. A method for analyzing vibration failure of a wind turbine generator, characterized in that: The following steps are involved: Acquire sensor data of the wind turbine, the sensor data including sensor position information, sensor measurement direction information and frequency range information, and determine a first evaluation period according to the sensor position information, the sensor measurement direction information and the frequency range information, wherein the sensor measurement direction information is axial, the frequency range information is 0.1 Hz-100 Hz, and the sensor data also includes vibration velocity information and vibration acceleration information; The first evaluation cycle is divided into at least one second evaluation cycle, a vibration velocity evaluation value is determined according to the first evaluation cycle, the at least one second evaluation cycle and the vibration velocity information, a vibration acceleration evaluation value is determined according to the first evaluation cycle, the at least one second evaluation cycle and the vibration acceleration information, and the wind turbine is determined to be in a dangerous state according to the vibration velocity evaluation value and the vibration acceleration evaluation value; wherein: The relationship between the first evaluation cycle and the second evaluation cycle is expressed by formula (9): Among them, T0 refers to the first evaluation cycle; T e refers to the e-th second evaluation cycle in the first evaluation cycle; n refers to the number of at least one second evaluation cycle; The vibration velocity evaluation value is determined by formula (11): Among them, v rmsw0 Refers to the vibration velocity assessment value; v rmswe It refers to the vibration speed segmented evaluation value in the e-th second evaluation cycle; The vibration acceleration evaluation value is determined by formula (13): Among them, α rmsw0 Refers to the vibration acceleration evaluation value; α rmswe It refers to the vibration acceleration segment evaluation value in the e-th second evaluation cycle; Determine a vibration characteristic curve of the wind turbine according to the sensor data, wherein the vibration characteristic curve includes a vibration information time domain curve and a vibration information frequency domain curve, wherein the vertical axis of the vibration information time domain curve is a curve of vibration acceleration information or vibration velocity information, and the vertical axis of the vibration information frequency domain curve is a curve of vibration acceleration information, vibration velocity information, marginal spectrum amplitude information, or envelope spectrum amplitude information; Performing trend analysis on the vibration information time domain curve to determine the peak index, peak-to-peak index, kurtosis index, pulse index and margin index of the vibration information time domain curve, and determining the vibration trend curve of the wind turbine according to the peak index, peak-to-peak index, kurtosis index, pulse index and margin index of the vibration information time domain curve; determining the three-sideband information and the five-fold frequency information according to the fault frequency information of the wind turbine, and marking the vibration information frequency domain curve according to the three-sideband information and the five-fold frequency information to obtain the fault characteristic curve of the wind turbine; Performing fault analysis on the wind turbine according to the fault characteristic curve and / or the vibration trend curve to generate fault diagnosis information of the wind turbine; A vibration fault analysis report of the wind turbine is generated according to the fault diagnosis information.

2. The method according to claim 1, characterized in that: The horizontal axis of the vibration information time domain curve is time information; the vibration trend curve refers to a curve whose horizontal axis is time information and whose vertical axis is peak index, peak-to-peak index, kurtosis index, pulse index or margin index.

3. The method according to claim 1, characterized in that The vibration information frequency domain curve means that the horizontal axis is frequency information.

4. The method according to claim 3, characterized in that The three-sideband information includes the vibration velocity information and vibration acceleration information corresponding to the single-time sideband, double-time sideband and triple-time sideband of the fault frequency information respectively; the five-time frequency information includes the vibration velocity information and vibration acceleration information corresponding to the single-time frequency information, double-time frequency information, triple-time frequency information, quadruple-time frequency information and five-time frequency information of the rotation frequency information of the wind turbine respectively.

5. The method according to claim 1, characterized in that The step of determining that the wind turbine generator is in a dangerous state according to the vibration velocity evaluation value and the vibration acceleration evaluation value includes: When the vibration velocity evaluation value is greater than or equal to a first threshold value, and / or the vibration acceleration evaluation value is greater than or equal to a second threshold value, it is determined that the wind turbine is in a dangerous state.

6. A wind turbine vibration fault analysis system, characterized in that: include: A data acquisition unit, used for collecting sensor data of the wind turbine; A vibration fault analysis unit, wherein the vibration fault analysis unit is configured to execute the wind turbine vibration fault analysis method according to any one of claims 1 to 4.

7. A wind turbine vibration fault analysis device, characterized in that: include: An acquisition module is used to acquire sensor data of the wind turbine, wherein the sensor data includes sensor position information, sensor measurement direction information and frequency range information, and a first evaluation period is determined according to the sensor position information, the sensor measurement direction information and the frequency range information, wherein the sensor measurement direction information is axial, the frequency range information is 0.1 Hz-100 Hz, and the sensor data also includes vibration velocity information and vibration acceleration information; a first determination module, configured to divide the first evaluation cycle into at least one second evaluation cycle, determine a vibration velocity evaluation value according to the first evaluation cycle, the at least one second evaluation cycle and the vibration velocity information, determine a vibration acceleration evaluation value according to the first evaluation cycle, the at least one second evaluation cycle and the vibration acceleration information, and determine that the wind turbine is in a dangerous state according to the vibration velocity evaluation value and the vibration acceleration evaluation value; wherein: The relationship between the first evaluation cycle and the second evaluation cycle is expressed by formula (9): Among them, T0 refers to the first evaluation cycle; T e refers to the e-th second evaluation cycle in the first evaluation cycle; n refers to the number of at least one second evaluation cycle; The vibration velocity evaluation value is determined by formula (11): Among them, v rmsw0 Refers to the vibration velocity assessment value; v rmswe It refers to the vibration speed segmented evaluation value in the e-th second evaluation cycle; The vibration acceleration evaluation value is determined by formula (13): Among them, α rmsw0 Refers to the vibration acceleration evaluation value; α rmswe It refers to the vibration acceleration segment evaluation value in the e-th second evaluation cycle; A second determination module is used to determine a vibration characteristic curve of the wind turbine according to the sensor data, wherein the vibration characteristic curve includes a vibration information time domain curve and a vibration information frequency domain curve, wherein the vertical axis of the vibration information time domain curve is a curve of vibration acceleration information or vibration velocity information, and the vertical axis of the vibration information frequency domain curve is a curve of vibration acceleration information, vibration velocity information, marginal spectrum amplitude information or envelope spectrum amplitude information; A third determination module is used to perform trend analysis on the vibration information time domain curve to determine the peak index, peak-to-peak index, kurtosis index, pulse index and margin index of the vibration information time domain curve, and determine the vibration trend curve of the wind turbine according to the peak index, peak-to-peak index, kurtosis index, pulse index and margin index of the vibration information time domain curve; determine the three-sideband information and the five-fold frequency information according to the fault frequency information of the wind turbine, and mark the vibration information frequency domain curve according to the three-sideband information and the five-fold frequency information to obtain the fault characteristic curve of the wind turbine; The fault analysis module is used to perform fault analysis on the wind turbine according to the fault characteristic curve and / or the vibration trend curve, and generate fault diagnosis information of the wind turbine, so that the report unit can generate a vibration fault analysis report according to the fault diagnosis information of the wind turbine.

8. An electronic device, characterized in that: include: at least one processor; as well as a memory communicatively connected to the at least one processor; wherein, The memory stores instructions that can be executed by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to perform the method according to any one of claims 1 to 5.

9. A non-transitory computer-readable storage medium storing computer instructions, characterized in that: The computer instructions are used to cause the computer to execute the method according to any one of claims 1 to 5.