Fan gear box early fault warning method, device, equipment, medium and product

Abstract

The present application relates to the technical field of fault detection, and discloses a fan gear box early fault warning method, device, equipment, medium and product, the method comprising: respectively performing envelope spectrum analysis on the first vibration signal and the second vibration signal to obtain the first envelope feature of the first measuring point in multiple sub-periods and the second envelope feature of the second measuring point in multiple sub-periods, the first measuring point being the input bearing radial measuring point of the fan gear box, and the second measuring point being the first-stage inner ring gear radial measuring point; respectively performing impact feature extraction on the first vibration signal and the second vibration signal to obtain the first impact feature of the first measuring point in multiple sub-periods and the second impact feature of the second measuring point in multiple sub-periods; determining the health index value of the corresponding sub-period based on the first envelope feature, the second envelope feature, the first impact feature and the second impact feature of each sub-period; and performing early fault warning on the fan gear box based on the health index values of multiple sub-periods and a preset warning threshold.

Description

Technical Field

[0001] This invention relates to the field of fault detection technology, specifically to early warning methods, devices, equipment, media, and products for wind turbine gearboxes. Background Technology

[0002] The installed capacity of new energy sources, primarily wind and solar power, is rapidly expanding. Wind turbines are often deployed in harsh environments such as high mountains, deserts, and the sea, leading to frequent component failures. Due to the remote locations of these turbines, maintenance personnel often struggle to obtain timely fault information, which can easily worsen the problem. This can result in economic losses or even serious shutdowns and damage to the turbines. Therefore, early fault warning for wind turbines has become a core requirement for ensuring their efficient and stable operation.

[0003] From the perspective of failure evolution mechanism, gearbox failures mostly develop gradually from early damage such as bearing pitting, micro-pitting on gear tooth surfaces, and early cracks at the tooth root. In related technologies, gearbox anomalies are generally identified by monitoring the effective value or fixed threshold of vibration at the gearbox as a whole or at a single measuring point. However, in the early stages of a failure, the vibration signal energy is weak, and the characteristic frequency is easily masked by background noise and operating condition fluctuations, causing the failure to be discovered only in the middle and late stages, often delaying the best time for maintenance. Summary of the Invention

[0004] This invention provides a method, device, equipment, medium, and product for early warning of early faults in wind turbine gearboxes, in order to solve the problem that in related technologies, the identification of gearbox anomalies by monitoring the effective value or fixed threshold of vibration of the entire gearbox or a single measuring point cannot accurately identify early gearbox anomalies.

[0005] In a first aspect, the present invention provides an early fault warning method for a wind turbine gearbox. The method includes: acquiring a first vibration signal from a first measuring point and a second vibration signal from a second measuring point within a preset time period, wherein the first measuring point is a radial measuring point of the input bearing of the wind turbine gearbox, and the second measuring point is a radial measuring point of the first-stage internal gear ring; the preset time period includes multiple sub-time periods; performing envelope spectrum analysis on the first and second vibration signals respectively to obtain the first envelope features of the first measuring point and the second envelope features of the second measuring point in the multiple sub-time periods; extracting impact features from the first and second vibration signals respectively to obtain the first impact features of the first measuring point and the second impact features of the second measuring point in the multiple sub-time periods; determining the health index value of the corresponding sub-time period based on the first envelope features, second envelope features, first impact features, and second impact features of each sub-time period; and providing an early fault warning for the wind turbine gearbox based on the health index values ​​determined in the multiple sub-time periods and a preset warning threshold.

[0006] The wind turbine gearbox early fault warning method provided by this invention selects two core measurement points close to the fault source: the radial direction of the input bearing and the radial direction of the first-stage internal gear ring. This allows for targeted acquisition of sensitive vibration signals related to early faults. Compared to single-point or overall monitoring, this method can more accurately capture weak vibration characteristics caused by early damage such as bearing pitting and tooth surface micro-pitting. Simultaneously, it extracts modulation-type fault features through envelope spectrum analysis and combines impact features to capture non-Gaussian impact characteristics in the signal, achieving multi-dimensional fault feature fusion. This effectively reduces the interference of background noise and operating condition fluctuations on early fault identification, overcoming the limitations of related technologies that rely solely on effective vibration values ​​or single features. Furthermore, based on the feature fusion of multiple sub-time periods, a health index value is constructed, and combined with a preset warning threshold, it provides early warning. This dynamically reflects the evolution trend of the gearbox's health status. Compared to fixed threshold monitoring, it is more adaptable to the complex and variable operating conditions of wind turbine units, enabling timely identification of anomalies in the early stages of fault development, locking in the optimal maintenance window in advance, and preventing further deterioration of the fault from leading to prolonged unit shutdowns or major safety accidents. This improves the sensitivity and reliability of early fault warning for wind turbine gearboxes.

[0007] In one optional implementation, the step of acquiring a first vibration signal at a first measuring point and a second vibration signal at a second measuring point within a preset time period includes: acquiring a first original vibration signal at the first measuring point and a second original vibration signal at the second measuring point; preprocessing the first original vibration signal and the second original vibration signal respectively to obtain processed first original vibration signal and second original vibration signal; segmenting the first original vibration signal using a preset time window to obtain a first vibration signal; and segmenting the second original vibration signal using a preset time window to obtain a second vibration signal.

[0008] The method provided in this optional implementation can effectively remove noise, baseline drift and other interference from the original vibration signal by preprocessing it, thereby improving the purity of the vibration signal. By using a preset time window to segment the signal, the continuous vibration signal can be normalized into standardized segmented signals, ensuring the stability and consistency of subsequent envelope feature and impact feature extraction, and providing high-quality data support for accurate calculation of health indicators and reliable early warning.

[0009] In one optional implementation, the step of performing envelope spectrum analysis on the first vibration signal and the second vibration signal respectively to obtain the first envelope features of the first measuring point in multiple sub-time periods and the second envelope features of the second measuring point in multiple sub-time periods includes: performing Hilbert transform on the first vibration signal and the second vibration signal respectively to obtain a first analytic signal of the first vibration signal and a second analytic signal of the second vibration signal; determining the first envelope signal based on the first analytic signal and determining the second envelope signal based on the second analytic signal; extracting features from the first envelope signal to obtain the first envelope features, and extracting the second envelope features to obtain the second envelope features.

[0010] The method provided in this optional implementation obtains the analytical signal and extracts the envelope signal through Hilbert transform, which can effectively demodulate the fault modulation component in the vibration signal, accurately highlight the low-frequency characteristic frequency of the early fault, solve the problem that the characteristics of the vibration signal of the early fault are easily masked by noise and operating condition fluctuations, and can stably extract sensitive and reliable envelope features, providing accurate feature basis for subsequent health index calculation and fault early warning.

[0011] In one alternative implementation, the first impact feature includes a first kurtosis, a first spectral kurtosis, and a first impact factor, and the second impact feature includes a second kurtosis, a second spectral kurtosis, and a second impact factor.

[0012] The method provided by this optional implementation uses kurtosis, spectral kurtosis and impact factor as impact features, which can accurately capture the weak impact characteristics of early faults from multiple dimensions such as time domain statistics, frequency domain distribution and amplitude intensity. It avoids the problem of single feature being disturbed by operating condition fluctuations, greatly improves the sensitivity and stability of fault feature extraction, and provides reliable feature support for health indicator calculation and early warning.

[0013] In one optional implementation, the step of providing early fault warning for the wind turbine gearbox based on health indicator values ​​determined by multiple sub-time periods and a preset warning threshold includes: comparing the health indicator values ​​of each sub-time period with the preset warning threshold to obtain a first comparison result; if, based on the first comparison result, it is determined that there are consecutive target number of sub-time periods with health indicator values ​​greater than the preset warning threshold, providing early fault warning for the wind turbine gearbox.

[0014] The method provided by this optional implementation adopts the judgment logic of health indicators exceeding the limit in multiple consecutive sub-time periods, which can effectively filter out transient noise and instantaneous abnormal interference caused by sudden changes in operating conditions, avoid false alarms caused by single-point instantaneous exceedance, and greatly improve the reliability and accuracy of the early warning results while ensuring the sensitivity of early fault identification.

[0015] In one optional implementation, if, based on the first comparison result, it is determined that the health indicator value of a consecutive target number of sub-time periods exceeds a preset warning threshold, an early fault warning is issued for the wind turbine gearbox. This includes: acquiring the third vibration signal of a third measuring point and the fourth vibration signal of a fourth measuring point within a preset time period, wherein the third measuring point is a radial measuring point of the secondary internal gear ring and the fourth measuring point is a radial measuring point of the high-speed shaft; determining the third vibration characteristic time series of the third measuring point based on the third vibration signal; determining the fourth vibration characteristic time series of the fourth measuring point based on the fourth vibration signal; comparing the first vibration characteristic time series, the second vibration characteristic time series with the third vibration characteristic time series, and the fourth vibration characteristic time series to obtain a second comparison result; if, based on the second comparison result, it is determined that the characteristic trends of the first measuring point, the second measuring point, the third measuring point, and the third measuring point are consistent, and based on the first comparison result, it is determined that the health indicator value of a consecutive target number of sub-time periods exceeds a preset warning threshold, an early fault warning is issued for the wind turbine gearbox.

[0016] The method provided in this optional implementation introduces radial and high-speed shaft radial measurement points of the secondary internal gear ring to construct a vibration characteristic time series and conducts a multi-measurement point characteristic trend consistency comparison. By combining the synchronous verification of multi-measurement point characteristic trends with the continuous over-limit judgment of health indicators, it can effectively filter out non-fault interference such as operating condition fluctuations and instantaneous noise, avoid false warnings caused by single measurement points or instantaneous anomalies, and significantly improve the accuracy, stability and reliability of early fault warning of wind turbine gearbox while ensuring the sensitivity of early fault identification. This makes the warning results more consistent with the actual fault evolution law of the gearbox and adapts to the engineering application needs of wind turbine units under complex operating conditions.

[0017] Secondly, the present invention provides an early fault warning device for a wind turbine gearbox. The device includes: an acquisition module for acquiring a first vibration signal from a first measuring point and a second vibration signal from a second measuring point within a preset time period, wherein the first measuring point is a radial measuring point of the input bearing of the wind turbine gearbox, and the second measuring point is a radial measuring point of the first-stage internal gear ring; the preset time period includes multiple sub-time periods; an analysis module for performing envelope spectrum analysis on the first and second vibration signals respectively to obtain the first envelope features of the first measuring point and the second envelope features of the second measuring point in the multiple sub-time periods; an extraction module for extracting impact features from the first and second vibration signals respectively to obtain the first impact features of the first measuring point in the multiple sub-time periods and the second impact features of the second measuring point in the multiple time periods; a determination module for determining the health indicator value of the corresponding sub-time period based on the first envelope features, second envelope features, first impact features, and second impact features of each sub-time period; and an early warning module for providing early fault warning for the wind turbine gearbox based on the health indicator values ​​determined in the multiple sub-time periods and a preset early warning threshold.

[0018] Thirdly, the present invention provides an electronic device, comprising: a memory and a processor, wherein the memory and the processor are communicatively connected to each other, the memory stores computer instructions, and the processor executes the computer instructions to perform the wind turbine gearbox early fault warning method described in the first aspect or any corresponding embodiment.

[0019] Fourthly, the present invention provides a computer-readable storage medium storing computer instructions for causing a computer to execute the wind turbine gearbox early fault warning method described in the first aspect or any corresponding embodiment thereof.

[0020] Fifthly, the present invention provides a computer program product, including computer instructions for causing a computer to execute the wind turbine gearbox early fault warning method described in the first aspect or any corresponding embodiment thereof. Attached Figure Description

[0021] To more clearly illustrate the specific embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the specific embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of the present invention. For those skilled in the art, other drawings can be obtained from these drawings without creative effort.

[0022] Figure 1 This is a schematic diagram of an application scenario according to an embodiment of the present invention; Figure 2 This is a schematic flowchart of the first method for early fault warning of wind turbine gearbox according to an embodiment of the present invention; Figure 3 This is a schematic diagram of the second process of the early fault warning method for wind turbine gearbox according to an embodiment of the present invention; Figure 4 This is a schematic diagram of the third process of the early fault warning method for wind turbine gearbox according to an embodiment of the present invention; Figure 5 This is a structural block diagram of a wind turbine gearbox early fault warning device according to an embodiment of the present invention; Figure 6 This is a schematic diagram of the hardware structure of an electronic device according to an embodiment of the present invention. Detailed Implementation

[0023] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0024] It is understood that before using the technical solutions disclosed in the various embodiments of the present invention, users should be informed of the types, scope of use, and usage scenarios of the personal information involved in the present invention and their authorization should be obtained in accordance with relevant laws and regulations through appropriate means.

[0025] The terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include one or more of that feature. In the description of this invention, "a plurality of" means two or more, unless otherwise explicitly specified.

[0026] As an optional application scenario of this invention, the specific application environment architecture or specific hardware architecture on which the early fault warning method for wind turbine gearboxes depends is described here. For example... Figure 1 As shown, the architecture system may include at least one terminal device and at least one server. Figure 1 The system is illustrated in the example, which includes a computer 101, a mobile terminal 102, and a server 103, and the terminal devices such as the computer 101 and the mobile terminal 102 are connected to the server 103 through a network 110.

[0027] Specifically, the terminal device can be a smartphone, tablet, laptop, PDA, desktop computer, game console, smart TV, smart wearable device, in-vehicle terminal, VR (Virtual Reality) device, AR (Augmented Reality) device, etc. Server 103 can be a standalone physical server, a server cluster, a distributed system, or a cloud server providing cloud services. Network 110 can be a wired or wireless network, examples of which include, but are not limited to, the Internet, corporate intranet, local area network, wide area network, mobile communication network, and combinations thereof.

[0028] In related technologies, gearbox anomalies are generally identified by monitoring the effective value or fixed threshold of vibration of the gearbox as a whole or a single measuring point. However, in the early stage of a fault, the vibration signal energy is weak and the characteristic frequency is easily masked by background noise and operating condition fluctuations, causing the fault to be discovered only in the middle and late stages, often delaying the best time for maintenance.

[0029] In view of this, embodiments of this application provide a method for early fault warning of wind turbine gearboxes, which can be applied to a server to realize early fault warning of wind turbine gearboxes. The method provided in this application selects two core measurement points near the fault source—the radial direction of the input bearing and the radial direction of the first-stage internal gear ring—to collect early fault-sensitive vibration signals. Compared to single measurement point or overall monitoring, this method can more accurately capture weak vibration characteristics caused by early damage such as bearing pitting and tooth surface micro-pitting. Simultaneously, it extracts modulation-type fault features through envelope spectrum analysis and combines impact features to capture non-Gaussian impact characteristics in the signal, achieving multi-dimensional fault feature fusion. This effectively reduces the interference of background noise and operating condition fluctuations on early fault identification, overcoming the limitations of related technologies that rely solely on effective vibration values ​​or single features. Furthermore, based on the feature fusion of multiple sub-time periods, a health index value is constructed, and a preset warning threshold is used for early warning. This dynamically reflects the evolution trend of the gearbox's health status. Compared to fixed threshold monitoring, it is more adaptable to the complex and variable operating conditions of wind turbine units, enabling timely identification of anomalies in the early stages of fault development, locking in the optimal maintenance window in advance, and preventing further deterioration of the fault from leading to prolonged unit shutdown or major safety accidents. This improves the sensitivity and reliability of early fault warning for wind turbine gearboxes.

[0030] According to an embodiment of the present invention, an embodiment of a method for early fault warning of wind turbine gearbox is provided. It should be noted that the steps shown in the flowchart in the accompanying drawings can be executed in a computer system such as a set of computer-executable instructions. Furthermore, although a logical order is shown in the flowchart, in some cases, the steps shown or described may be executed in a different order than that shown here.

[0031] This embodiment provides a method for early fault warning of a wind turbine gearbox, which can be used in the aforementioned server. Figure 2 This is a flowchart of an early fault warning method for wind turbine gearboxes according to an embodiment of the present invention, such as... Figure 2 As shown, the process includes the following steps: Step S201: Obtain the first vibration signal of the first measuring point and the second vibration signal of the second measuring point within a preset time period. The first measuring point is the radial measuring point of the input bearing of the wind turbine gearbox, and the second measuring point is the radial measuring point of the first-stage internal gear ring. The preset time period includes multiple sub-time periods.

[0032] For example, the preset time period is the period during which early fault warning of the wind turbine gearbox is required. It can be determined according to actual needs. In this embodiment, the preset time period is the overall time range for uniformly collecting gearbox vibration data. The first measuring point is a vibration acquisition point set radially at the input bearing of the wind turbine gearbox. It is close to the fault source at the input end, which facilitates the capture of weak vibration information caused by early bearing damage. The second measuring point is a vibration acquisition point set radially at the first-stage internal gear ring of the wind turbine gearbox. It can accurately collect early fault vibration signals generated by the first-stage gear transmission part. The first vibration signal is the actual operating vibration signal of the gearbox collected at the radial measuring point of the input bearing, and the second vibration signal is the actual operating vibration signal of the gearbox collected at the radial measuring point of the first-stage internal gear ring.

[0033] Step S202: Perform envelope spectrum analysis on the first vibration signal and the second vibration signal respectively to obtain the first envelope features of the first measuring point in multiple sub-time periods and the second envelope features of the second measuring point in multiple sub-time periods.

[0034] For example, envelope spectrum analysis is performed on the first vibration signal and the second vibration signal in sequence, and the signals are processed according to the predefined sub-time periods. The envelope features corresponding to the first measuring point in each sub-time period are extracted from the first vibration signal, and the envelope features corresponding to the second measuring point in each sub-time period are extracted from the second vibration signal.

[0035] Step S203: Extract impact features from the first vibration signal and the second vibration signal respectively to obtain the first impact features of the first measuring point in multiple sub-time periods and the second impact features of the second measuring point in multiple time periods.

[0036] For example, the first impact feature includes a first kurtosis, a first spectral kurtosis, and a first impact factor, and the second impact feature includes a second kurtosis, a second spectral kurtosis, and a second impact factor. In this embodiment, kurtosis is used to describe the peaking of the signal amplitude distribution and is highly sensitive to transient impact components. It can be calculated using the following formula:

[0037] in, K Indicates kurtosis, E Expressing expectations, This represents the mean value of the vibration signal.

[0038] Spectral kurtosis is an extension of kurtosis characteristics in the frequency domain. It can be used to identify the optimal frequency band for impact energy concentration and can be calculated using the following formula:

[0039] in, Spectral kurtosis is a frequency. The function represents the frequency The spectral kurtosis value at a given point is used to identify the optimal frequency band for impact energy concentration. The time-frequency representation of a vibration signal, that is, the signal at a frequency... ,time The complex value (or amplitude) at a given frequency reflects the energy distribution of the signal at that frequency and time. This indicates a time averaging operation, averaging the quantities within the parentheses over time to eliminate fluctuations in the time dimension and obtain the frequency. The corresponding statistics; Representation of time and frequency The absolute value of the fourth power is used to reflect the fourth-order moment correlation of the signal energy at that frequency and time point, highlighting the non-Gaussian nature of the impact component.

[0040] The crest factor (CF) measures the change in transient impact amplitude relative to the overall energy level in a vibration signal, and can be calculated using the following formula:

[0041] in, CF Indicates the impact factor. x max This represents the maximum amplitude of the signal. x rms This is the root mean square value of the signal.

[0042] Step S204: Determine the health indicator value for the corresponding sub-period based on the first envelope feature, second envelope feature, first impact feature, and second impact feature of each sub-period.

[0043] For example, in this embodiment of the application, regarding the early fault characteristics of the radial vibration signals of the input bearing and the first-stage internal gear ring, a single indicator is easily affected by noise and operating condition fluctuations, making it difficult to comprehensively reflect the fault state. Therefore, multiple indicators such as envelope spectrum, kurtosis, spectral kurtosis, and impact factor are normalized and weighted to achieve sensitive monitoring of early, subtle faults. The normalization operation is achieved through the following formula:

[0044] in, F i ( k ) indicates the first i The first indicator in the k The raw data for each sub-period, This is represented as the normalized index value; the meanings of the other variables will not be elaborated further.

[0045] Health indicator values ​​can be calculated using the following formula:

[0046] in, HI ( k ) indicates the first k Health indicator values ​​for each sub-period. ω i For the first i The weighting coefficients of each indicator n This represents the total number of selected indicators; the meanings of the other variables will not be elaborated further.

[0047] Step S205: Based on the health indicator values ​​determined by multiple sub-time periods and the preset early warning threshold, early fault warning is given for the wind turbine gearbox.

[0048] For example, in this embodiment of the application, the preset warning threshold can be determined by the following formula:

[0049] in, T ( k ) indicates the first k The adaptive warning threshold corresponding to each discrete sub-period is the warning judgment boundary that is dynamically updated over time. μ HI and ζ HI These represent the mean and standard deviation of health indicators under normal historical operating conditions. λ It is an adjustable sensitivity coefficient used to control the sensitivity of the early warning system.

[0050] The health indicator values ​​of each sub-period are compared with the preset warning threshold one by one. Based on the comparison results of multiple sub-periods, it is determined whether there are consecutive target number of sub-periods where the health indicator values ​​exceed the threshold. If the threshold is met, an early fault warning for the wind turbine gearbox is triggered. If the threshold is not met, it is determined to be normal operation or instantaneous interference.

[0051] The early fault warning method for wind turbine gearboxes provided in this embodiment selects two core measurement points close to the fault source: the radial direction of the input bearing and the radial direction of the first-stage internal gear ring. This allows for targeted acquisition of sensitive vibration signals related to early faults. Compared to single-point or overall monitoring, this method can more accurately capture weak vibration characteristics caused by early damage such as bearing pitting and tooth surface micro-pitting. Simultaneously, it extracts modulation-type fault features through envelope spectrum analysis and combines impact features to capture non-Gaussian impact characteristics in the signal, achieving multi-dimensional fault feature fusion. This effectively reduces the interference of background noise and operating condition fluctuations on early fault identification, overcoming the limitations of related technologies that rely solely on effective vibration values ​​or single features. Furthermore, based on the feature fusion of multiple sub-time periods, a health index value is constructed, and combined with a preset warning threshold, it provides early warning. This dynamically reflects the evolution trend of the gearbox's health status. Compared to fixed threshold monitoring, it is more adaptable to the complex and variable operating conditions of wind turbine units, enabling timely identification of anomalies in the early stages of fault development, locking in the optimal maintenance window in advance, and preventing further deterioration of the fault from leading to prolonged downtime or safety accidents. This improves the sensitivity and reliability of early fault warning for wind turbine gearboxes.

[0052] This embodiment provides a method for early fault warning of a wind turbine gearbox, which can be used in the aforementioned server. Figure 3 This is a flowchart of an early fault warning method for wind turbine gearboxes according to an embodiment of the present invention, such as... Figure 3 As shown, the process includes the following steps: Step S301: Obtain the first vibration signal from the first measuring point and the second vibration signal from the second measuring point within a preset time period. The first measuring point is the radial measuring point of the input bearing of the wind turbine gearbox, and the second measuring point is the radial measuring point of the first-stage internal gear ring. The preset time period includes multiple sub-time periods. For details, please refer to... Figure 2 Step S201 of the illustrated embodiment will not be described again here.

[0053] Step S302: Perform envelope spectrum analysis on the first vibration signal and the second vibration signal respectively to obtain the first envelope features of the first measuring point in multiple sub-time periods and the second envelope features of the second measuring point in multiple sub-time periods.

[0054] Specifically, step S302 includes: Step S3021: Perform Hilbert transform on the first vibration signal and the second vibration signal respectively to obtain the first analytical signal of the first vibration signal and the second analytical signal of the second vibration signal.

[0055] For example, in an embodiment of this application, the parsed signal can be determined by the following formula:

[0056] in, x ( t() represents a vibration signal; j H is the imaginary unit; x ( t )}for x ( t The Hilbert transform of the signal is used to construct the imaginary part that is orthogonal to the original signal.

[0057] Step S3022: Determine the first envelope signal based on the first analytical signal, and determine the second envelope signal based on the second analytical signal.

[0058] For example, in an embodiment of this application, the envelope signal is shown in the following formula:

[0059] in, e ( t () represents the instantaneous envelope of the vibration signal, used to describe the variation of the high-frequency carrier amplitude over time.

[0060] Step S3023: Extract features from the first envelope signal to obtain the first envelope features, and extract the second envelope features to obtain the second envelope features.

[0061] For example, in the embodiments of this application, feature extraction operations are performed on the first envelope signal and the second envelope signal respectively, and feature quantities that can reflect the fault modulation characteristics are extracted from the envelope signal, thereby obtaining the first envelope feature and the second envelope feature of the corresponding measurement point.

[0062] Step S303 involves extracting impact features from the first vibration signal and the second vibration signal, respectively, to obtain the first impact features of the first measuring point over multiple sub-time periods and the second impact features of the second measuring point over multiple time periods. For details, please refer to [link to relevant documentation]. Figure 2 Step S203 of the illustrated embodiment will not be described again here.

[0063] Step S304: Determine the health indicator value for each sub-time period based on the first envelope feature, second envelope feature, first impact feature, and second impact feature. For details, please refer to [link to relevant documentation]. Figure 2 Step S204 of the illustrated embodiment will not be described again here.

[0064] Step S305: Based on the health indicator values ​​determined by multiple sub-time periods and the preset early warning threshold, early fault warning is given for the wind turbine gearbox.

[0065] Specifically, step S305 includes: Step S3051: Compare the health indicator values ​​of each sub-time period with the preset warning threshold to obtain the first comparison result.

[0066] For example, in this embodiment of the application, the health indicator value corresponding to each sub-time period is compared with the preset warning threshold in turn, the judgment result of whether the health indicator value of each sub-time period exceeds the warning threshold is recorded, and the first comparison result is obtained by summarizing.

[0067] Step S3052: If, based on the first comparison result, it is determined that the health indicator value of a number of consecutive target sub-periods in multiple sub-periods is greater than the preset warning threshold, an early fault warning is issued for the wind turbine gearbox.

[0068] Exemplary, in the embodiments of this application, when HI ( k )> T ( k If the limit is exceeded for M consecutive sub-time periods, it can be determined as an early fault warning, as shown in the following formula:

[0069] The sampling points and sub-time periods correspond one-to-one, and the meanings of the other variables will not be elaborated further.

[0070] In some optional implementations, step S3052 above includes: Step a1: Obtain the third vibration signal of the third measuring point and the fourth vibration signal of the fourth measuring point within a preset time period. The third measuring point is the radial measuring point of the secondary internal gear ring, and the fourth measuring point is the radial measuring point of the high-speed shaft.

[0071] For example, a third vibration signal is acquired from a radial measuring point arranged on the secondary internal gear ring, and a fourth vibration signal is acquired from a radial measuring point arranged on the high-speed shaft to complete the vibration data acquisition at the specified position.

[0072] Step a2: Determine the third vibration characteristic time series of the third measuring point based on the third vibration signal.

[0073] For example, in this embodiment of the application, based on the third vibration signal of the radial direction of the secondary internal gear ring, kurtosis, spectral kurtosis, impact factor and envelope spectrum related features are extracted, arranged in chronological order, and the vibration feature time series corresponding to the measuring point is generated.

[0074] Step a3: Determine the fourth vibration characteristic time series of the fourth measuring point based on the fourth vibration signal.

[0075] For example, in this embodiment of the application, based on the fourth vibration signal of high-speed axial and radial direction, kurtosis, spectral kurtosis, impact factor and envelope spectrum features are extracted, arranged in time order, and the time series of the fourth vibration features corresponding to the measuring point is constructed.

[0076] Step a4: Compare the characteristic trend consistency of the first vibration characteristic time series, the second vibration characteristic time series, the third vibration characteristic time series, and the fourth vibration characteristic time series to obtain the second comparison result.

[0077] For example, the first vibration characteristic time series is the vibration characteristic sequence of the first measuring point during a preset time period, and the second vibration characteristic sequence is the vibration characteristic sequence of the second measuring point during the preset time period. In this embodiment, the vibration characteristic time series of the first and second measuring points are compared with the third and fourth vibration characteristic time series corresponding to the secondary internal gear ring and the high-speed shaft. The overall trend of the various vibration characteristics changing over time is compared to see if they are consistent. The corresponding second comparison result is obtained through trend matching analysis.

[0078] Step a5: If the characteristic trends of the first measuring point, the second measuring point, the third measuring point and the third measuring point are consistent based on the second comparison result, and the health index value of a number of consecutive target sub-periods is greater than the preset warning threshold based on the first comparison result, an early fault warning is issued for the wind turbine gearbox.

[0079] For example, first determine that the vibration characteristics of the four measuring points have the same trend, and then combine the first comparison results to confirm that there are a number of consecutive time periods in multiple segmented durations, and the health index values ​​exceed the preset warning standard. After both judgment conditions are met, an early fault warning can be issued to the wind turbine gearbox.

[0080] Furthermore, by combining the structural mechanism of the high-speed shaft of the wind turbine gearbox with the physical causes of axial vibration, such as axial movement, thrust bearing load, and coupling misalignment, characteristic analysis is carried out on the axial vibration signal of the high-speed shaft to verify whether the signal characteristics conform to the mechanism law of axial faults of the high-speed shaft, thereby assisting in the judgment of axial related faults of the high-speed shaft.

[0081] This embodiment provides a method for early fault warning of a wind turbine gearbox, which can be used in the aforementioned server. Figure 4 This is a flowchart of an early fault warning method for wind turbine gearboxes according to an embodiment of the present invention, such as... Figure 4 As shown, the process includes the following steps: Step S401: Obtain the first vibration signal of the first measuring point and the second vibration signal of the second measuring point within a preset time period. The first measuring point is the radial measuring point of the input bearing of the wind turbine gearbox, and the second measuring point is the radial measuring point of the first-stage internal gear ring. The preset time period includes multiple sub-time periods.

[0082] Specifically, step S401 includes: Step S4011: Obtain the first original vibration signal of the first measuring point and the second original vibration signal of the second measuring point.

[0083] For example, unprocessed raw vibration waveform data are collected at the first and second measuring points. In this embodiment, the raw vibration signal of the wind turbine gearbox is collected and processed by a digital wind turbine equipment structure vibration analyzer. This device has multi-channel, high-precision signal acquisition capabilities, supports 12 configurable frequency band settings, and can perform refined frequency band analysis of vibration signals according to different equipment structural characteristics and fault types, thereby improving the pertinence and accuracy of fault identification. The system has four built-in programmable independent alarm relays, all with set / reset functions, enabling real-time monitoring and hierarchical alarm control of equipment operating status; additionally, a system fault relay is provided to indicate abnormal operating status of the equipment itself. Each alarm relay supports independent alarm threshold setting and delay parameter configuration, which can be flexibly adjusted according to the vibration characteristics of different monitored objects, effectively avoiding false alarms and missed alarms.

[0084] Step S4012: Preprocess the first original vibration signal and the second original whole building signal respectively to obtain the processed first original vibration signal and the second original vibration signal.

[0085] For example, the two original vibration signals are sequentially subjected to preprocessing operations such as filtering and noise reduction and removal of clutter interference to optimize signal quality and obtain the processed vibration signal.

[0086] Step S4013: The first original vibration signal is segmented using a time window of a preset length to obtain the first vibration signal.

[0087] For example, a time window of a specified duration is used to perform time-series segmentation of the preprocessed first original vibration signal, and the processed signal is then used to obtain the first vibration signal.

[0088] Step S4014: The second original vibration signal is segmented using a time window of preset length to obtain the second vibration signal.

[0089] For example, a time window of a set duration is used to perform time-series segmentation on the preprocessed second original vibration signal to finally obtain the second vibration signal.

[0090] Step S402: Envelope spectrum analysis is performed on the first vibration signal and the second vibration signal respectively to obtain the first envelope characteristics of the first measuring point in multiple sub-time periods and the second envelope characteristics of the second measuring point in multiple sub-time periods. For details, please refer to [link to relevant documentation]. Figure 3 Step S302 of the illustrated embodiment will not be described again here.

[0091] Step S403 involves extracting impact features from the first vibration signal and the second vibration signal, respectively, to obtain the first impact features of the first measuring point over multiple sub-time periods and the second impact features of the second measuring point over multiple time periods. For details, please refer to [link to relevant documentation]. Figure 3 Step S303 of the illustrated embodiment will not be described again here.

[0092] Step S404: Determine the health indicator value for each sub-time period based on the first envelope feature, second envelope feature, first impact feature, and second impact feature. For details, please refer to [link to relevant documentation]. Figure 3 Step S304 of the illustrated embodiment will not be described again here.

[0093] Step S405: Early fault warning is issued for the wind turbine gearbox based on health indicator values ​​determined from multiple sub-time periods and preset warning thresholds. For details, please refer to [link to relevant documentation]. Figure 3 Step S305 of the illustrated embodiment will not be described again here.

[0094] The method provided in this application, through multi-index joint analysis of vibration signals from key measuring points such as the radial direction of the input bearing and the radial direction of the first-stage internal gear ring, can achieve early identification of faults when the impact characteristics are not yet obvious in the early stage. Compared with traditional single-index methods, it significantly improves the sensitivity of early fault detection, helps to avoid fault expansion, and ensures the safe and stable operation of the unit. By integrating multiple features such as envelope spectrum, kurtosis, spectral kurtosis, and impact factor, the equipment status is comprehensively characterized from multiple perspectives such as impact characteristics, modulation characteristics, and frequency band energy distribution. This effectively reduces misjudgments caused by the influence of single index on operating condition fluctuations and improves the accuracy and stability of fault identification. By constructing a multi-index fusion health index and adaptive threshold criteria, automatic analysis and anomaly identification of vibration data are realized, reducing the workload of manual point-by-point analysis, improving operation and maintenance efficiency, and enhancing the standardization and consistency of monitoring work. It does not rely on a large number of fault samples for training, has a clear model structure, and has strong parameter interpretability. It can be directly applied to existing vibration monitoring systems and is suitable for online monitoring and unified management of large-scale wind farm units.

[0095] This embodiment also provides an early fault warning device for a wind turbine gearbox. This device is used to implement the above embodiments and preferred embodiments, and details already described will not be repeated. As used below, the term "module" can refer to a combination of software and / or hardware that performs a predetermined function. Although the device described in the following embodiments is preferably implemented in software, hardware implementation, or a combination of software and hardware, is also possible and contemplated.

[0096] This embodiment provides an early fault warning device for wind turbine gearboxes, such as... Figure 5 As shown, it includes: The acquisition module 501 is used to acquire the first vibration signal of the first measuring point and the second vibration signal of the second measuring point within a preset time period. The first measuring point is the radial measuring point of the input bearing of the wind turbine gearbox, and the second measuring point is the radial measuring point of the first-stage internal gear ring. The preset time period includes multiple sub-time periods. Analysis module 502 is used to perform envelope spectrum analysis on the first vibration signal and the second vibration signal respectively, to obtain the first envelope features of the first measuring point in multiple sub-time periods and the second envelope features of the second measuring point in multiple sub-time periods; The extraction module 503 is used to extract the impact features of the first vibration signal and the second vibration signal respectively, so as to obtain the first impact features of the first measuring point in multiple sub-time periods and the second impact features of the second measuring point in multiple time periods. The determination module 504 is used to determine the health indicator value of the corresponding sub-period based on the first envelope feature, second envelope feature, first impact feature and second impact feature of each sub-period; The early warning module 505 is used to provide early fault warnings for wind turbine gearboxes based on health indicator values ​​determined by multiple sub-time periods and preset early warning thresholds.

[0097] In some optional implementations, the acquisition module 501 includes: The acquisition submodule is used to acquire the first original vibration signal of the first measuring point and the second original vibration signal of the second measuring point; The first processing submodule is used to preprocess the first original vibration signal and the second original whole building signal respectively to obtain the processed first original vibration signal and the second original vibration signal. The second processing submodule is used to segment the first original vibration signal using a time window of preset length to obtain the first vibration signal. The third processing submodule is used to segment the second original vibration signal using a preset time window to obtain the second vibration signal.

[0098] In some alternative implementations, the analysis module 502 includes: The transformation submodule is used to perform Hilbert transformation on the first vibration signal and the second vibration signal respectively to obtain the first analytical signal of the first vibration signal and the second analytical signal of the second vibration signal. The determination submodule is used to determine the first envelope signal based on the first analyzed signal and to determine the second envelope signal based on the second analyzed signal. The extraction submodule is used to extract features from the first envelope signal to obtain the first envelope features, and to extract the second envelope features to obtain the second envelope features.

[0099] In some alternative implementations, the first impact feature includes a first kurtosis, a first spectral kurtosis, and a first impact factor, and the second impact feature includes a second kurtosis, a second spectral kurtosis, and a second impact factor.

[0100] In some alternative implementations, the warning module 505 includes: The comparison submodule is used to compare the health indicator values ​​of each sub-time period with the preset warning threshold to obtain the first comparison result; The early warning submodule is used to provide early fault warning for the wind turbine gearbox if, based on the first comparison result, it is determined that the health indicator value of a number of consecutive target sub-periods exceeds the preset early warning threshold.

[0101] In some optional implementations, the early warning submodule includes: The acquisition unit is used to acquire the third vibration signal of the third measuring point and the fourth vibration signal of the fourth measuring point within a preset time period. The first determining unit is used to determine the third vibration characteristic time series of the third measuring point based on the third vibration signal; The second determining unit is used to determine the fourth vibration characteristic time series of the fourth measuring point based on the fourth vibration signal; The comparison unit is used to compare the first vibration feature time series, the second vibration feature time series with the third vibration feature time series and the fourth vibration feature time series to obtain the second comparison result; The early warning unit is used to provide early fault warning for the wind turbine gearbox if, based on the second comparison result, it is determined that the characteristic trends of the first measuring point, the second measuring point, the third measuring point, and the third measuring point are consistent, and based on the first comparison result, it is determined that the health index values ​​of a number of consecutive target sub-periods are greater than the preset early warning threshold.

[0102] The wind turbine gearbox early fault warning device provided in this embodiment of the invention can execute the wind turbine gearbox early fault warning method provided in any embodiment of the invention, and has the corresponding functional modules and beneficial effects of the method. Further functional descriptions of the above modules and units are the same as in the corresponding embodiments described above, and will not be repeated here.

[0103] Figure 6 This is a schematic diagram of the structure of an electronic device provided in an embodiment of the present invention.

[0104] The following is a detailed reference. Figure 6This diagram illustrates a suitable structural design for implementing an electronic device according to embodiments of the present invention. The electronic device may include a processor (e.g., a central processing unit, graphics processor, etc.) 601, which can perform various appropriate actions and processes based on a program stored in read-only memory (ROM) 602 or a program loaded from memory 608 into random access memory (RAM) 603. RAM 603 also stores various programs and data required for the operation of the electronic device. The processor 601, ROM 602, and RAM 603 are interconnected via a bus 604. An input / output (I / O) interface 605 is also connected to the bus 604.

[0105] Typically, the following devices can be connected to I / O interface 605: input devices 606 including, for example, touchscreens, touchpads, keyboards, mice, cameras, microphones, accelerometers, gyroscopes, etc.; output devices 607 including, for example, liquid crystal displays (LCDs), speakers, vibrators, etc.; memory devices 608 including, for example, magnetic tapes, hard disks, etc.; and communication devices 609. Communication device 609 allows electronic devices to communicate wirelessly or wiredly with other devices to exchange data. Although Figure 6 Electronic devices with various devices are shown, but it should be understood that it is not required to implement or have all of the devices shown, and more or fewer devices may be implemented or have instead.

[0106] In particular, according to embodiments of the present invention, the processes described above with reference to the flowcharts can be implemented as computer software programs. For example, embodiments of the present invention include a computer program product comprising a computer program carried on a non-transitory computer-readable medium, the computer program containing program code for performing the methods shown in the flowcharts. In such embodiments, the computer program can be downloaded and installed from a network via a communication device 609, or installed from a memory 608, or installed from a ROM 602. When the computer program is executed by the processor 601, it performs the functions defined in the wind turbine gearbox early fault warning method of the embodiments of the present invention.

[0107] Figure 6 The electronic device shown is merely an example and should not be construed as limiting the functionality and scope of use of the embodiments of the present invention.

[0108] This invention also provides a computer-readable storage medium. The methods described above according to embodiments of the invention can be implemented in hardware or firmware, or implemented as computer code that can be recorded on a storage medium, or implemented as computer code downloaded via a network and originally stored on a remote storage medium or a non-transitory machine-readable storage medium and then stored on a local storage medium. Thus, the methods described herein can be processed by software stored on a storage medium using a general-purpose computer, a dedicated processor, or programmable or dedicated hardware. The storage medium can be a magnetic disk, optical disk, read-only memory, random access memory, flash memory, hard disk, or solid-state drive, etc.; further, the storage medium can also include combinations of the above types of memory. It is understood that computers, processors, microprocessor controllers, or programmable hardware include storage components capable of storing or receiving software or computer code. When the software or computer code is accessed and executed by the computer, processor, or hardware, the early fault warning method for wind turbine gearboxes shown in the above embodiments is implemented.

[0109] A portion of this invention can be applied as a computer program product, such as computer program instructions, which, when executed by a computer, can invoke or provide the methods and / or technical solutions according to the invention through the operation of the computer. Those skilled in the art will understand that the forms in which computer program instructions exist in a computer-readable medium include, but are not limited to, source files, executable files, installation package files, etc. Correspondingly, the ways in which computer program instructions are executed by a computer include, but are not limited to: the computer directly executing the instructions, or the computer compiling the instructions and then executing the corresponding compiled program, or the computer reading and executing the instructions, or the computer reading and installing the instructions and then executing the corresponding installed program. Here, the computer-readable medium can be any available computer-readable storage medium or communication medium accessible to a computer.

[0110] Although embodiments of the invention have been described in conjunction with the accompanying drawings, those skilled in the art can make various modifications and variations without departing from the spirit and scope of the invention, and such modifications and variations all fall within the scope defined by the appended claims.

Claims

1. A method for early fault warning of a wind turbine gearbox, characterized in that, The method includes: The first vibration signal of the first measuring point and the second vibration signal of the second measuring point are acquired within a preset time period. The first measuring point is the radial measuring point of the input bearing of the wind turbine gearbox, and the second measuring point is the radial measuring point of the first-stage internal gear ring. The preset time period includes multiple sub-time periods. Envelope spectrum analysis was performed on the first vibration signal and the second vibration signal respectively to obtain the first envelope characteristics of the first measuring point in multiple sub-time periods and the second envelope characteristics of the second measuring point in multiple sub-time periods. Impact features are extracted from the first vibration signal and the second vibration signal respectively to obtain the first impact features of the first measuring point in multiple sub-time periods and the second impact features of the second measuring point in multiple time periods. The health indicator values ​​for each sub-period are determined based on the first envelope feature, second envelope feature, first impact feature, and second impact feature of each sub-period. Early fault warnings are issued for wind turbine gearboxes based on the health indicator values ​​determined by multiple sub-time periods and preset warning thresholds.

2. The method according to claim 1, characterized in that, The step of acquiring the first vibration signal of the first measuring point and the second vibration signal of the second measuring point within a preset time period includes: Acquire the first original vibration signal at the first measuring point and the second original vibration signal at the second measuring point; The first original vibration signal and the second original whole building signal are preprocessed respectively to obtain the processed first original vibration signal and the second original vibration signal. The first original vibration signal is segmented using a time window of preset length to obtain the first vibration signal; The second original vibration signal is segmented using a time window of preset length to obtain the second vibration signal.

3. The method according to claim 1 or 2, characterized in that, The steps of performing envelope spectrum analysis on the first vibration signal and the second vibration signal respectively to obtain the first envelope characteristics of the first measuring point in multiple sub-time periods and the second envelope characteristics of the second measuring point in multiple sub-time periods include: Perform Hilbert transforms on the first vibration signal and the second vibration signal respectively to obtain the first analytical signal of the first vibration signal and the second analytical signal of the second vibration signal; The first envelope signal is determined based on the first analytical signal, and the second envelope signal is determined based on the second analytical signal; Feature extraction is performed on the first envelope signal to obtain the first envelope feature, and the second envelope feature is extracted to obtain the second envelope feature.

4. The method according to claim 1 or 2, characterized in that, The first impact feature includes a first kurtosis, a first spectral kurtosis, and a first impact factor, and the second impact feature includes a second kurtosis, a second spectral kurtosis, and a second impact factor.

5. The method according to claim 1 or 2, characterized in that, The steps for providing early fault warnings for wind turbine gearboxes based on the health indicator values ​​determined across multiple sub-time periods and preset warning thresholds include: The health indicator values ​​for each sub-period are compared with the preset warning threshold to obtain the first comparison result; If, based on the first comparison result, it is determined that there are consecutive target number of sub-time periods with health index values ​​greater than the preset warning threshold, an early fault warning is issued for the wind turbine gearbox.

6. The method according to claim 5, characterized in that, If, based on the first comparison result, it is determined that there are consecutive target number of sub-time periods with health indicator values ​​greater than the preset warning threshold, an early fault warning is issued for the wind turbine gearbox, including: The third vibration signal of the third measuring point and the fourth vibration signal of the fourth measuring point are obtained within a preset time period. The third measuring point is the radial measuring point of the second-stage internal gear ring, and the fourth measuring point is the radial measuring point of the high-speed shaft. The third vibration characteristic time series of the third measuring point is determined based on the third vibration signal; Based on the fourth vibration signal, determine the fourth vibration characteristic time series of the fourth measuring point; The first vibration characteristic time series, the second vibration characteristic time series, the third vibration characteristic time series, and the fourth vibration characteristic time series are compared to obtain the second comparison result; If, based on the second comparison result, it is determined that the characteristic trends of the first measuring point, the second measuring point, the third measuring point, and the third measuring point are consistent, and based on the first comparison result, it is determined that the health index value of a number of consecutive target sub-periods in the multiple sub-periods is greater than the preset warning threshold, an early fault warning is issued for the wind turbine gearbox.

7. A wind turbine gearbox early fault warning device, characterized in that, The device includes: The acquisition module is used to acquire the first vibration signal of the first measuring point and the second vibration signal of the second measuring point within a preset time period. The first measuring point is the radial measuring point of the input bearing of the wind turbine gearbox, and the second measuring point is the radial measuring point of the first-stage internal gear ring. The preset time period includes multiple sub-time periods. The analysis module is used to perform envelope spectrum analysis on the first vibration signal and the second vibration signal respectively, to obtain the first envelope features of the first measuring point in multiple sub-time periods and the second envelope features of the second measuring point in multiple sub-time periods; The extraction module is used to extract the impact features of the first vibration signal and the second vibration signal respectively, so as to obtain the first impact features of the first measuring point in multiple sub-time periods and the second impact features of the second measuring point in multiple time periods. The determination module is used to determine the health indicator value of the corresponding sub-period based on the first envelope feature, second envelope feature, first impact feature and second impact feature of each sub-period; The early warning module is used to provide early fault warnings for the wind turbine gearbox based on the health indicator values ​​determined by multiple sub-time periods and preset early warning thresholds.

8. An electronic device, characterized in that, include: A memory and a processor are interconnected, the memory stores computer instructions, and the processor executes the computer instructions to perform the wind turbine gearbox early fault warning method according to any one of claims 1 to 6.

9. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer instructions for causing the computer to execute the wind turbine gearbox early fault warning method according to any one of claims 1 to 6.

10. A computer program product, characterized in that, It includes computer instructions for causing a computer to execute the wind turbine gearbox early fault warning method according to any one of claims 1 to 6.

Images