Fan fault diagnosis method and system, electronic equipment and storage medium
The characteristics of the vibration signal and speed signal of the wind turbine transmission chain are extracted through the CEEMDAN treatment method and fused to solve the problem of low accuracy in fan fault diagnosis, improving the diagnostic accuracy and adaptability to variable working conditions.
Patent Information
- Application Number
- CN202411272097.1
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-09-11
- Publication Date
- 2025-02-18
AI Technical Summary
In the prior art, the accuracy of the fan fault diagnosis is low, especially in variable operating conditions, and it is difficult to effectively analyze the vibration signals and velocity signals of the transmission chain of the wind turbine, resulting in low monitoring accuracy and susceptibility to interference.
By obtaining the vibration signal data and velocity signal data of the wind turbine transmission chain, the CEEMDAN processing method is used to extract the frequency domain and time domain features and fuse them into fusion features to identify wind turbine faults and provide early warnings.
It improves the accuracy of fan fault diagnosis, avoids the problem of incomplete signal description of single-domain feature extraction, and enhances the fault diagnosis capability of wind turbine transmission chain under variable operating conditions.
Smart Images
Figure CN119475205A_ABST
Abstract
Description
Technical Field
[0001] The present application relates to the field of fault diagnosis, and in particular to a method, system, electronic device and storage medium for diagnosing fan faults. Background Art
[0002] Wind turbines are the main device for wind power generation and the core of wind power technology. Since wind turbines are installed in high mountains, wilderness, beaches, islands and other wind outlets, they are subject to irregular wind forces of changing direction and load, as well as the impact of strong gusts, and are subject to extreme heat and cold and extreme temperature differences all year round, which causes frequent failures of wind turbines.
[0003] In the related art, wind turbine fault warning is carried out by analyzing the vibration signal of the wind turbine transmission chain. At present, the method of extracting the feature of the vibration signal of the wind turbine transmission chain is based on the vibration signal of the transmission chain with a constant speed, which can only judge the vibration fault information of the current wind turbine transmission chain, and cannot effectively analyze the vibration signal and speed signal of the wind turbine transmission chain under variable working conditions, resulting in low monitoring accuracy and easy interference.
[0004] Currently, no effective solution has been proposed for the problem of low accuracy in fan fault diagnosis in related technologies. Summary of the invention
[0005] The embodiments of the present application provide a fan fault diagnosis method, system, electronic device and storage medium to at least solve the problem of low accuracy of fan fault diagnosis in the related art.
[0006] In a first aspect, an embodiment of the present application provides a method for diagnosing a fan fault, the method comprising:
[0007] Acquire vibration signal data and speed signal data of the wind turbine transmission chain;
[0008] Performing CEEMDAN processing on the vibration signal data to obtain a first modal component, and extracting frequency domain features of the vibration signal data based on a low-frequency signal in the first modal component;
[0009] Performing CEEMDAN processing on the speed signal data to obtain a second modal component, and extracting time domain features of the speed signal data based on a low-frequency signal in the second modal component;
[0010] The frequency domain feature and the time domain feature are fused to obtain a fused feature, and wind turbine faults are identified and an early warning is issued based on the fused feature.
[0011] In some embodiments, the first modal component includes an IMF component and a residual signal; and performing CEEMDAN processing on the vibration signal data to obtain the first modal component includes:
[0012] Adding Gaussian white noise with a mean value of 0 to the vibration signal data multiple times to obtain multiple vibration noise signals;
[0013] Perform EMD decomposition on the multiple vibration noise signals respectively to obtain multiple IMF components and one residual signal.
[0014] In some embodiments, performing EMD decomposition on the plurality of vibration noise signals respectively to obtain the plurality of IMF components and one residual signal comprises:
[0015] Performing EMD decomposition on the vibration noise signal to obtain a new vibration signal;
[0016] When the new vibration signal satisfies a preset IMF condition, using the new vibration signal as the IMF component;
[0017] In the case that the new vibration signal does not satisfy the preset IMF condition, re-performing EMD decomposition on the vibration noise signal until the newly generated vibration signal satisfies the preset IMF condition, and taking the newly generated vibration sound signal as the IMF component;
[0018] The vibration noise signal is subtracted from all the IMF components to obtain the residual signal.
[0019] In some embodiments, performing EMD decomposition on the vibration noise signal to obtain a new vibration signal includes:
[0020] Acquire all local extreme value points of a single vibration noise signal;
[0021] Based on cubic spline interpolation, construct an upper envelope and a lower envelope according to the local extreme value points, and obtain an average envelope according to the upper envelope and the lower envelope;
[0022] The average envelope is subtracted from the vibration noise signal to obtain the new vibration signal.
[0023] In some embodiments, obtaining all local extreme points of a single vibration noise signal includes:
[0024] The local extreme value points are analyzed, outliers in the local extreme value points are removed, and missing values in the local extreme value points are corrected.
[0025] In some embodiments, subtracting all the IMF components from the vibration noise signal to obtain the residual signal comprises:
[0026] Subtract all the IMF components from the vibration noise signal to obtain the residual signal;
[0027] It is determined whether the residual signal satisfies a preset residual condition. If not, the vibration noise signal is re-decomposed by EMD until the generated residual signal satisfies the preset residual condition.
[0028] In some embodiments, identifying wind turbine faults based on the fusion features and issuing warnings includes:
[0029] Normalizing the fused features to obtain feature vectors with the same scale, and generating a training set and a test set according to the feature vectors;
[0030] Training an evaluation model based on the training set, and adjusting parameters of the evaluation model through cross-validation;
[0031] The test set is input into the trained evaluation model to obtain the fan fault identification result and issue an early warning.
[0032] In a second aspect, an embodiment of the present application provides a wind turbine fault diagnosis system, the system comprising: a collection device and a monitoring center, wherein:
[0033] The acquisition device includes a vibration sensor and a speed sensor, wherein the vibration sensor is used to acquire vibration signal data of the wind turbine transmission chain, and the speed sensor is used to acquire speed signal data of the wind turbine transmission chain;
[0034] The monitoring center is connected to the acquisition device in communication, and includes a database module and a monitoring and maintenance integration module.
[0035] The monitoring and maintenance integrated module is used to execute the wind turbine fault diagnosis method described in the first aspect,
[0036] The database module is used to store the wind turbine data collected by the collection device and the identification results of the monitoring and maintenance integration module.
[0037] In a third aspect, an embodiment of the present application provides a computer device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the computer program, the fan fault diagnosis method as described in the first aspect above is implemented.
[0038] In a fourth aspect, an embodiment of the present application provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the fan fault diagnosis method as described in the first aspect above.
[0039] Compared with the related art, the wind turbine fault diagnosis method provided in the embodiment of the present application obtains the vibration signal data and speed signal data of the wind turbine transmission chain, performs CEEMDAN processing on the vibration signal data to obtain the first modal component, extracts the frequency domain features of the vibration signal data based on the low-frequency signal in the first modal component, performs CEEMDAN processing on the speed signal data to obtain the second modal component, extracts the time domain features of the speed signal data based on the low-frequency signal in the second modal component, fuses the frequency domain features and the time domain features to obtain the fusion features, identifies the wind turbine fault based on the fusion features and issues an early warning, and solves the problem of low accuracy in wind turbine fault diagnosis. The speed time domain features and the vibration frequency domain features of the wind turbine transmission chain signal are fused to avoid the incomplete description of the signal by the single domain feature extraction, and improves the accuracy of wind turbine fault diagnosis. BRIEF DESCRIPTION OF THE DRAWINGS
[0040] The drawings described herein are used to provide a further understanding of the present application and constitute a part of the present application. The illustrative embodiments of the present application and their descriptions are used to explain the present application and do not constitute an improper limitation on the present application. In the drawings:
[0041] Figure 1 is a schematic diagram of an application environment of a fan fault diagnosis method according to an embodiment of the present application;
[0042] Figure 2 is a flow chart of a fan fault diagnosis method according to an embodiment of the present application;
[0043] Figure 3 is a flow chart of a CEEMDAN signal processing method according to an embodiment of the present application;
[0044] Figure 4 is a flow chart of a wind turbine fault identification method according to an embodiment of the present application;
[0045] Figure 5 is a structural block diagram of a fan fault diagnosis system according to an embodiment of the present application;
[0046] Figure 6 It is a schematic diagram of the internal structure of an electronic device according to an embodiment of the present application. DETAILED DESCRIPTION
[0047] In order to make the purpose, technical solutions and advantages of the present application clearer, the present application is described and illustrated below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not intended to limit the present application. Based on the embodiments provided in the present application, all other embodiments obtained by ordinary technicians in the field without making creative work are within the scope of protection of the present application.
[0048] Obviously, the drawings described below are only some examples or embodiments of the present application. For ordinary technicians in this field, the present application can also be applied to other similar scenarios based on these drawings without creative work. In addition, it can also be understood that although the efforts made in this development process may be complicated and lengthy, for ordinary technicians in this field related to the content disclosed in this application, some changes in design, manufacturing or production based on the technical content disclosed in this application are just conventional technical means, and should not be understood as the content disclosed in this application is insufficient.
[0049] Reference to "embodiments" in this application means that a particular feature, structure, or characteristic described in conjunction with the embodiments may be included in at least one embodiment of the present application. The appearance of the phrase in various locations in the specification does not necessarily refer to the same embodiment, nor is it an independent or alternative embodiment that is mutually exclusive with other embodiments. It is explicitly and implicitly understood by those of ordinary skill in the art that the embodiments described in this application may be combined with other embodiments without conflict.
[0050] Unless otherwise defined, the technical terms or scientific terms involved in this application should be understood by people with ordinary skills in the technical field to which this application belongs. The words "one", "a", "a", "the" and the like involved in this application do not indicate a quantitative limitation, and may represent the singular or plural. The terms "include", "comprise", "have" and any of their variations involved in this application are intended to cover non-exclusive inclusions; for example, a process, method, system, product or device that includes a series of steps or modules (units) is not limited to the listed steps or units, but may also include steps or units that are not listed, or may also include other steps or units inherent to these processes, methods, products or devices. The words "connect", "connected", "coupled" and the like involved in this application are not limited to physical or mechanical connections, but may include electrical connections, whether direct or indirect. The "multiple" involved in this application refers to two or more. "And / or" describes the association relationship of associated objects, indicating that there may be three relationships, for example, "A and / or B" can represent: A exists alone, A and B exist at the same time, and B exists alone. The character " / " generally indicates that the objects before and after are in an "or" relationship. The terms "first", "second", "third", etc. involved in this application are only used to distinguish similar objects and do not represent a specific ordering of the objects.
[0051] Figure 1 FIG. 1 is a schematic diagram of an application environment of a fan fault diagnosis method according to an embodiment of the present application. The fan fault diagnosis method provided by the present application can be applied to Figure 1 In the application environment shown. Figure 1 As shown, the acquisition device 101 communicates with the monitoring center 102 through the network. The acquisition device 101 acquires wind turbine data and sends the wind turbine data to the monitoring center 102. The wind turbine data includes vibration signal data and speed signal data of the wind turbine transmission chain; the monitoring center 102 performs fault analysis and early warning based on the wind turbine data, and stores the wind turbine data and analysis results.
[0052] This embodiment provides a method for diagnosing fan faults. Figure 2 is a flow chart of a fan fault diagnosis method according to an embodiment of the present application, such as Figure 2 As shown, the process includes the following steps:
[0053] Step S201, obtaining vibration signal data and speed signal data of a wind turbine transmission chain.
[0054] Optionally, a vibration signal of the wind turbine transmission chain is acquired through a vibration sensor, and a speed signal of the wind turbine transmission chain is acquired through a speed sensor.
[0055] Step S202: Perform CEEMDAN processing on the vibration signal data to obtain a first modal component, and extract frequency domain features of the vibration signal data based on a low-frequency signal in the first modal component.
[0056] Step S203, performing CEEMDAN processing on the speed signal data to obtain a second modal component, and extracting the time domain features of the speed signal data based on the low-frequency signal in the second modal component.
[0057] The vibration signal data and speed signal data of the wind turbine transmission chain are processed by CEEMDAN respectively to obtain modal components of different frequencies, decompose the low-frequency signal, extract the frequency domain characteristics of the vibration signal data and the time domain characteristics of the speed signal data, and perform frequency domain characteristics and time domain characteristics.
[0058] It should be noted that the vibration signal is composed of the following:
[0059] F=A 1 +n 1
[0060] Among them, F is the complete vibration signal, A 1 is the original vibration signal, n 1 is a noise signal.
[0061] The vibration signal sequence is decomposed by wavelet packets, and the new wavelet signal calculation formula is as follows:
[0062] x c1 =B(u c ,f c )F×v
[0063] Among them, x c1 is the wavelet signal after the vibration signal is decomposed, B is the wavelet function, u c is the mapping feature in the dimensionality reduction process, f c The number of decomposition layers of the vibration signal.
[0064] The speed signal is composed as follows:
[0065] S=A 2 +n 2
[0066] Among them, S is the complete speed signal, A 2 is the original speed signal, n 2 is a noise signal.
[0067] The velocity signal sequence is decomposed by wavelet packets, and the new wavelet signal calculation formula is as follows:
[0068] x c2 =B(u c ,sc )S×v
[0069] Among them, x c2 is the wavelet signal after the velocity signal is decomposed, B is the wavelet function, u c is the mapping feature in the dimensionality reduction process, s c is the number of decomposition layers of the velocity signal.
[0070] The changing rules of wind turbine transmission chain vibration and speed are obtained, and time-frequency analysis is performed using wavelet packet decomposition to extract the time-domain speed characteristics and vibration frequency-domain characteristics of the wind turbine transmission chain.
[0071] The CEEMDAN processing process for vibration signal data and velocity signal data is the same. Taking the processing of vibration signal data as an example, the CEEMDAN processing process is explained.
[0072] In some embodiments, the first modal component includes an IMF component and a residual signal; in step S202, the vibration signal data is processed by CEEMDAN to obtain the first modal component including:
[0073] Step S2021, adding Gaussian white noise with a mean value of 0 to the vibration signal data multiple times to obtain multiple vibration noise signals.
[0074] Step S2022: Perform EMD decomposition on the multiple vibration noise signals respectively to obtain multiple IMF components and a residual signal.
[0075] The IMF components obtained by decomposing all the noise-added signals are integrated, and the final IMF components are obtained by averaging the IMF components of the same order obtained by each decomposition. EMD (Empirical Mode Decomposition) decomposition is an adaptive decomposition method used in signal processing and data analysis. It decomposes complex signals into several intrinsic mode functions (IMFs) and a residual term.
[0076] In some embodiments, step S2022 specifically includes:
[0077] Step S301, performing EMD decomposition on the vibration noise signal to obtain a new vibration signal.
[0078] In some embodiments, step S301 specifically includes:
[0079] Step S3011, obtaining all local extreme value points of a single vibration noise signal.
[0080] Get all local maximum and local minimum points of the vibration noise signal.
[0081] In the EMD analysis process, since there may be non-extreme points at both ends of the signal, endpoint effects will occur, affecting the accuracy of the decomposition results.
[0082] In some of the embodiments, in order to alleviate the endpoint effect, step S3011 further includes: analyzing the local extreme points, removing outliers in the local extreme points, and correcting missing values in the local extreme points.
[0083] Step S3012: Based on cubic spline interpolation, an upper envelope and a lower envelope are constructed according to local extreme points, and an average envelope is obtained according to the upper envelope and the lower envelope.
[0084] Specifically, the local maximum points are interpolated (using cubic spline interpolation) to obtain the upper envelope, and the local minimum points are interpolated to obtain the lower envelope. The two smooth upper and lower envelopes generated are located above and below the signal, respectively.
[0085] The average envelope is obtained by calculating the average value of the upper and lower envelopes, that is, adding the values of the upper and lower envelopes at each corresponding point and dividing by 2.
[0086] Step S3013, subtract the average envelope from the vibration noise signal to obtain a new vibration signal.
[0087] After subtracting the average envelope, a new signal is obtained.
[0088] After obtaining a new vibration signal through step S301, continue to step S302.
[0089] Step S302: When the new vibration signal meets the preset IMF condition, the new vibration signal is used as the IMF component.
[0090] Step S303: When the new vibration signal does not meet the preset IMF condition, the vibration noise signal is re-decomposed by EMD until the newly generated vibration signal meets the preset IMF condition, and the newly generated vibration signal is used as the IMF component.
[0091] Determine whether the new vibration signal meets the preset IMF condition. If the new signal meets the preset IMF condition, it is regarded as an IMF component. If not, repeat step S301 until the newly generated vibration signal meets the condition. The new signal that meets the preset IMF condition is regarded as an IMF component.
[0092] Perform RMD decomposition on each vibration noise signal to obtain a series of IMF components that meet the preset IMF conditions. Each component is a signal component with specific frequency and amplitude changes.
[0093] Step S304: subtract all IMF components from the vibration noise signal to obtain a residual signal.
[0094] In some embodiments, step S304 specifically includes:
[0095] Step S3041: subtract all IMF components from the vibration noise signal to obtain a residual signal.
[0096] Step S3042, determining whether the residual signal meets a preset residual condition, if not, re-performing EMD decomposition on the vibration noise signal until the generated residual signal meets the preset residual condition.
[0097] Subtract all extracted IMF components from the vibration noise signal one by one to obtain a residual signal. Determine whether the residual signal meets the stopping condition. The stopping condition can be that the residual signal becomes a monotonic function, or that the preset number of iterations (for example, 10 times) is reached. If the stopping condition is not met, it is considered that the residual signal still contains useful information. The EMD decomposition process can be repeated to continuously extract IMF components and residual signals until both the IMF components and the residual signal meet the conditions. The obtained residual signal contains low-frequency trend terms or noise components in the original signal.
[0098] In this embodiment, the vibration noise signal is decomposed by EMD. EMD is an adaptive decomposition method that does not rely on preset basis functions (such as sine and cosine functions in Fourier transform) and can automatically adjust the decomposition process according to the characteristics of the signal itself. EMD can provide time-varying frequency information, analyze the changes of the signal on different time scales through the different frequency components of the IMF component, and at the same time, it is sensitive to the local characteristics of the signal and can effectively capture the local oscillations and mutations in the signal.
[0099] Figure 3 It is a flow chart of a CEEMDAN signal processing method according to an embodiment of the present application. The speed signal data is processed by CEEMDAN by the same method to obtain multiple IMF components and a second modal component of a residual signal. It includes: adding Gaussian white noise with a mean of 0 to the speed signal data multiple times to obtain multiple speed noise signals, and performing EMD decomposition on the multiple speed noise signals respectively to obtain multiple IMF components and a residual signal.
[0100] Continue to refer to Figure 2 After obtaining the vibration frequency domain characteristics and the velocity time domain characteristics, execute step S204.
[0101] Step S204: The frequency domain features and the time domain features are fused to obtain fused features, and the wind turbine fault is identified based on the fused features and an early warning is issued.
[0102] In some embodiments, identifying wind turbine faults based on fusion features and issuing warnings in step S204 includes:
[0103] Step S2041, normalize the fused features to obtain feature vectors with the same scale, and generate a training set and a test set based on the feature vectors.
[0104] Step S2042: train the evaluation model based on the training set, and adjust the parameters of the evaluation model through cross-validation.
[0105] Step S2043, input the test set into the trained evaluation model to obtain the fan fault identification result and issue an early warning.
[0106] Figure 4 is a flow chart of a method for identifying a wind turbine fault according to an embodiment of the present application. Figure 4 As shown in the figure, a fused feature vector is formed based on the frequency domain features and the time domain features, and the fused feature vector is scaled or normalized so that the features have the same scale. The fused feature vector and its corresponding fault state label are combined into a data set, and the data set is divided into a training set and a test set. After selecting the radial basis function kernel, the feature vector of the training set and the corresponding fault state label are used to train the evaluation model.
[0107] In this embodiment, before training the evaluation model, some key parameters are preset, such as the gamma parameter of the RBF kernel (controlling the range of influence of a single training sample) and the regularization parameter C (controlling the balance between the complexity and generalization ability of the model); during the model training process, the parameters of the evaluation model are adjusted through cross-validation.
[0108] The feature vector is input into the trained evaluation model to classify the samples, and the fault state or category of the wind turbine transmission chain is determined according to the output of the evaluation model.
[0109] It should be noted that a threshold needs to be set during classification to determine the confidence of the classification. If the maximum probability of the model output is lower than the threshold, it means that the classification result is uncertain or needs further inspection. The threshold setting is set according to the specific business needs of wind turbine transmission chain fault identification. For example, if the system has a low tolerance for false alarm rate, a higher threshold can be selected to reduce false alarms; if the system has a low tolerance for missed alarm rate, a lower threshold can be selected to increase the sensitivity of detection.
[0110] Through the above steps, the vibration signal data and speed signal data of the wind turbine transmission chain are obtained, the vibration signal data is processed by CEEMDAN to obtain the first modal component, the frequency domain features of the vibration signal data are extracted based on the low-frequency signal in the first modal component, the speed signal data is processed by CEEMDAN to obtain the second modal component, the time domain features of the speed signal data are extracted based on the low-frequency signal in the second modal component, the frequency domain features and the time domain features are fused to obtain fusion features, the wind turbine fault is identified and an early warning is issued based on the fusion features, and the problem of low accuracy in wind turbine fault diagnosis is solved. The speed time domain features and the vibration frequency domain features of the wind turbine transmission chain signal are fused to avoid the incomplete description of the signal by single-domain feature extraction, and the accuracy of wind turbine fault diagnosis is improved.
[0111] It should be noted that the steps shown in the above process or the flowchart in the accompanying drawings can be executed in a computer system such as a set of computer executable instructions, and although a logical order is shown in the flowchart, in some cases, the steps shown or described can be executed in an order different from that shown here.
[0112] This embodiment also provides a fan fault diagnosis system, which is used to implement the above embodiments and preferred implementations, and will not be repeated here. As used below, the terms "module", "unit", "subunit", etc. can be a combination of software and / or hardware that implements a predetermined function. Although the device described in the following embodiments is preferably implemented in software, it is also possible and conceivable to implement it in hardware, or in a combination of software and hardware.
[0113] Figure 5 is a structural block diagram of a fan fault diagnosis system according to an embodiment of the present application, such as Figure 5 As shown, the system includes: a collection device 51 and a monitoring center 52.
[0114] The acquisition device 51 includes a vibration sensor 511 and a speed sensor 512. The vibration sensor 511 is used to acquire vibration signal data of the wind turbine transmission chain, and the speed sensor 512 is used to acquire speed signal data of the wind turbine transmission chain.
[0115] The monitoring center 52 is in communication connection with the acquisition device 51 , and includes a monitoring and maintenance integration module 521 and a database module 522 .
[0116] The monitoring and maintenance integrated module 521 is used to execute the above-mentioned fan fault diagnosis method.
[0117] The database module 522 is used to store the wind turbine data collected by the collection equipment and the identification results of the monitoring and maintenance integration module.
[0118] Through the above system, the speed time domain characteristics and vibration frequency domain characteristics of the wind turbine transmission chain signal are fused, avoiding the incomplete signal description of single-domain feature extraction, solving the problem of low accuracy of wind turbine fault diagnosis, and improving the accuracy of wind turbine fault diagnosis.
[0119] It should be noted that the above modules can be functional modules or program modules, and can be implemented by software or hardware. For modules implemented by hardware, the above modules can be located in the same processor; or the above modules can be located in different processors in any combination.
[0120] This embodiment further provides an electronic device, including a memory and a processor, wherein the memory stores a computer program, and the processor is configured to run the computer program to execute the steps in any one of the above method embodiments.
[0121] Optionally, the electronic device may further include a transmission device and an input / output device, wherein the transmission device is connected to the processor, and the input / output device is connected to the processor.
[0122] Optionally, in this embodiment, the processor may be configured to perform the following steps through a computer program:
[0123] S1, obtaining vibration signal data and speed signal data of the wind turbine transmission chain.
[0124] S2, performing CEEMDAN processing on the vibration signal data to obtain a first modal component, and extracting frequency domain features of the vibration signal data based on a low-frequency signal in the first modal component.
[0125] S3, performing CEEMDAN processing on the speed signal data to obtain a second modal component, and extracting time domain features of the speed signal data based on a low-frequency signal in the second modal component.
[0126] S4, the frequency domain features and the time domain features are fused to obtain fused features, and the wind turbine faults are identified and early warnings are issued based on the fused features.
[0127] It should be noted that the specific examples in this embodiment can refer to the examples described in the above embodiments and optional implementation modes, and this embodiment will not be described in detail here.
[0128] In one embodiment, Figure 6 is a schematic diagram of the internal structure of an electronic device according to an embodiment of the present application, such as Figure 6 As shown, an electronic device is provided, which may be a server, and its internal structure diagram may be as shown in Figure 6As shown. The electronic device includes a processor, a memory, a network interface and a database connected through a system bus. Among them, the processor of the electronic device is used to provide computing and control capabilities. The memory of the electronic device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program and a database. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The database of the electronic device is used to store data. The network interface of the electronic device is used to communicate with an external terminal through a network connection. When the computer program is executed by the processor, a fan fault diagnosis method is implemented.
[0129] Those skilled in the art will understand that Figure 6 The structure shown in the figure is merely a block diagram of a partial structure related to the scheme of the present application, and does not constitute a limitation on the electronic device to which the scheme of the present application is applied. The specific electronic device may include more or fewer components than shown in the figure, or combine certain components, or have a different arrangement of components.
[0130] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to memory, storage, database or other media used in the embodiments provided in this application can include non-volatile and / or volatile memory. Non-volatile memory may include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM) or flash memory. Volatile memory may include random access memory (RAM) or external cache memory. As an illustration and not limitation, RAM is available in many forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous link (Synchlink) DRAM (SLDRAM), memory bus (Rambus) direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM).
[0131] Those skilled in the art should understand that the various technical features of the above-described embodiments may be arbitrarily combined. To make the description concise, not all possible combinations of the various technical features in the above-described embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.
[0132] The above-mentioned embodiments only express several implementation methods of the present application, and the descriptions thereof are relatively specific and detailed, but they cannot be understood as limiting the scope of the invention patent. It should be pointed out that, for a person of ordinary skill in the art, several variations and improvements can be made without departing from the concept of the present application, and these all belong to the protection scope of the present application. Therefore, the protection scope of the patent of the present application shall be subject to the attached claims.
Claims
1. A fan fault diagnosis method, characterized in that: The method comprises: Acquire vibration signal data and speed signal data of the wind turbine transmission chain; Performing CEEMDAN processing on the vibration signal data to obtain a first modal component, and extracting frequency domain features of the vibration signal data based on a low-frequency signal in the first modal component; Performing CEEMDAN processing on the speed signal data to obtain a second modal component, and extracting time domain features of the speed signal data based on a low-frequency signal in the second modal component; The frequency domain feature and the time domain feature are fused to obtain a fused feature, and wind turbine faults are identified and an early warning is issued based on the fused feature.
2. The method according to claim 1, characterized in that The first modal component includes an IMF component and a residual signal; the vibration signal data is processed by CEEMDAN to obtain the first modal component including: Adding Gaussian white noise with a mean value of 0 to the vibration signal data multiple times to obtain multiple vibration noise signals; Perform EMD decomposition on the multiple vibration noise signals respectively to obtain multiple IMF components and one residual signal.
3. The method according to claim 2, characterized in that The performing EMD decomposition on the plurality of vibration noise signals respectively to obtain the plurality of IMF components and one residual signal comprises: Performing EMD decomposition on the vibration noise signal to obtain a new vibration signal; When the new vibration signal satisfies a preset IMF condition, using the new vibration signal as the IMF component; In the case that the new vibration signal does not meet the preset IMF condition, re-performing EMD decomposition on the vibration noise signal until the newly generated vibration signal meets the preset IMF condition, and using the newly generated vibration signal as the IMF component; The vibration noise signal is subtracted from all the IMF components to obtain the residual signal.
4. The method according to claim 3, characterized in that The performing EMD decomposition on the vibration noise signal to obtain a new vibration signal comprises: Acquire all local extreme value points of a single vibration noise signal; Based on cubic spline interpolation, construct an upper envelope and a lower envelope according to the local extreme value points, and obtain an average envelope according to the upper envelope and the lower envelope; The average envelope is subtracted from the vibration noise signal to obtain the new vibration signal.
5. The method according to claim 4, characterized in that The obtaining of all local extreme value points of a single vibration noise signal comprises: The local extreme value points are analyzed, outliers in the local extreme value points are removed, and missing values in the local extreme value points are corrected.
6. The method according to claim 3, characterized in that Subtracting all the IMF components from the vibration noise signal to obtain the residual signal comprises: Subtract all the IMF components from the vibration noise signal to obtain the residual signal; It is determined whether the residual signal satisfies a preset residual condition. If not, the vibration noise signal is re-decomposed by EMD until the generated residual signal satisfies the preset residual condition.
7. The method according to claim 1, characterized in that The identifying of wind turbine faults based on the fusion features and issuing early warnings comprises: Normalizing the fused features to obtain feature vectors with the same scale, and generating a training set and a test set according to the feature vectors; Training an evaluation model based on the training set, and adjusting parameters of the evaluation model through cross-validation; The test set is input into the trained evaluation model to obtain the fan fault identification result and issue an early warning.
8. A fan fault diagnosis system, characterized in that: The system includes: a collection device and a monitoring center, wherein: The acquisition device includes a vibration sensor and a speed sensor, wherein the vibration sensor is used to acquire vibration signal data of the wind turbine transmission chain, and the speed sensor is used to acquire speed signal data of the wind turbine transmission chain; The monitoring center is connected to the acquisition device in communication, and includes a database module and a monitoring and maintenance integration module. The monitoring and maintenance integrated module is used to execute the fan fault diagnosis method according to any one of claims 1 to 7. The database module is used to store the wind turbine data collected by the collection device and the identification results of the monitoring and maintenance integration module.
9. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the computer program, the wind turbine fault diagnosis method according to any one of claims 1 to 7 is implemented.
10. A storage medium having a computer program stored thereon, characterized in that: When the program is executed by a processor, the fan fault diagnosis method according to any one of claims 1 to 7 is implemented.