Automatic positioning fan fault detection method and related device

Abstract

The invention discloses an automatic positioning fan fault detection method and a related device, and the method comprises the steps: obtaining a wave recording graph of wind power generation equipment, and carrying out the preprocessing of the wave recording graph of the wind power generation equipment; performing feature extraction on the preprocessed recording graph to obtain extracted features; inputting the extracted features into the trained intelligent diagnosis model to judge whether the fan has a fault or not; when the draught fan breaks down, the fault position is positioned, the method and the related device can automatically judge whether the draught fan breaks down or not, and meanwhile the fault is positioned.

Description

TECHNICAL FIELD

[0001] The application belongs to the technical field of wind power generation equipment fault diagnosis, and relates to an automatic positioning wind turbine fault detection method and a related device. BACKGROUND

[0002] The wind turbine fault recording automatic positioning fault technology is mainly realized through a fault recording device.

[0003] During the operation of the wind turbine, if a fault occurs, the recording device automatically and accurately records the changes of various electrical quantities before and after the fault, such as voltage, current, phase, power and the like. The system current, voltage and derived quantities caused by short-circuit fault, system oscillation, frequency collapse, voltage collapse and other large disturbances, such as active power, reactive power and system frequency, can also be recorded. The full-process change phenomena and waveform data of the system frequency are recorded.

[0004] Through analysis and comparison of these electrical quantities, the fault cause and fault location can be determined, and the nature and severity of the fault can be understood, thereby providing a reference and guidance for subsequent maintenance work.

[0005] However, the existing technology has the following problems:

[0006] The traditional recording analysis relies on manual experience, and is low in efficiency and strong in subjectivity.

[0007] A single feature analysis method is difficult to cope with multiple types of concurrent faults under complex working conditions.

[0008] The fault positioning accuracy is significantly affected by high-frequency noise and signal distortion. SUMMARY

[0009] The application aims to overcome the above-mentioned shortcomings of the prior art, and provides an automatic positioning wind turbine fault detection method and a related device. The method and the related device can automatically determine whether the wind turbine has a fault, and simultaneously position the fault.

[0010] To achieve the above-mentioned purpose, the application discloses an automatic positioning wind turbine fault detection method, which comprises the following steps:

[0011] Obtaining a recording graph of a wind power generation equipment, and pre-processing the recording graph of the wind power generation equipment;

[0012] Extracting features from the pre-processed recording graph to obtain extracted features;

[0013] Inputting the extracted features into a trained intelligent diagnosis model to determine whether the wind turbine has a fault;

[0014] When the wind turbine has a fault, the fault position is positioned.

[0015] The automatic positioning fan fault detection method further improves in that:

[0016] Further, the process of pre-processing the recording waveform of the wind power generation equipment is:

[0017] The recording waveform is subjected to frequency noise suppression and power frequency interference elimination.

[0018] Further, the process of extracting features from the processed recording waveform is:

[0019] The processed recording waveform is subjected to feature extraction to obtain time domain features, frequency domain features and sequence component features, i.e., nonlinear features.

[0020] Further, the intelligent diagnosis model is constructed based on a hybrid neural network architecture and an improved dynamic time warping.

[0021] Further, the process of positioning the fault location is:

[0022] The fault location is positioned by using a traveling wave positioning mode or an impedance trajectory positioning mode.

[0023] The application discloses an automatic positioning fan fault detection system, comprising:

[0024] An acquisition module is configured to acquire a recording waveform of a wind power generation equipment and pre-process the recording waveform of the wind power generation equipment.

[0025] An extraction module is configured to extract features from the pre-processed recording waveform.

[0026] A judgment module is configured to input the extracted features into a trained intelligent diagnosis model to determine whether a fan has a fault.

[0027] A positioning module is configured to position a fault location when the fan has a fault.

[0028] The automatic positioning fan fault detection system further improves in that:

[0029] Further, the process of pre-processing the recording waveform of the wind power generation equipment is:

[0030] The recording waveform is subjected to frequency noise suppression and power frequency interference elimination.

[0031] Further, the process of extracting features from the processed recording waveform is:

[0032] The processed recording waveform is subjected to feature extraction to obtain time domain features, frequency domain features and sequence component features, i.e., nonlinear features.

[0033] The application discloses a computer device, comprising a memory, a processor and a computer program stored in the memory and executable on the processor, wherein the processor implements the steps of the automatic positioning fan fault detection method when executing the computer program.

[0034] The application discloses a computer readable storage medium, which stores a computer program, wherein the computer program implements the steps of the automatic positioning fan fault detection method when executed by a processor.

[0035] The application has the following beneficial effects:

[0036] The automatic positioning fan fault detection method and related device have the following advantages: the preprocessed recording waveforms are subjected to feature extraction to obtain extracted features, the extracted features are input into a trained intelligent diagnosis model to determine whether the fan has a fault, various problems caused by manual determination are avoided, the accuracy and efficiency of determination are improved, in addition, multiple features are used as input to cope with multiple concurrent faults under complex working conditions, and in addition, the fault position is positioned when the fan has a fault, and the device has high practicability. BRIEF DESCRIPTION OF DRAWINGS

[0037] The accompanying drawings, which form a part of this application, are included to provide a further understanding of the application and are incorporated in and constitute a part of this application. The embodiments of these drawings illustrate the embodiments of the present application and, together with the description, serve to explain the principles of the present application. In the drawings:

[0038] Figure 1 The accompanying drawings, which form a part of this application, are included to provide a further understanding of the application and are incorporated in and constitute a part of this application. The embodiments of these drawings illustrate the embodiments of the present application and, together with the description, serve to explain the principles of the present application. In the drawings: DETAILED DESCRIPTION

[0039] The technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application. Obviously, the described embodiments are only a part of the embodiments of the present application, but not all the embodiments of the present application. Based on the embodiments in the present application, all other embodiments obtained by a person of ordinary skill in the art without creative work fall within the protection scope of the present application.

[0040] In the description of the present application, it should be understood that the terms "comprise" and "include" indicate the presence of described features, whole, steps, operations, elements and / or components, but do not exclude the presence or addition of one or more other features, whole, steps, operations, elements, components and / or sets thereof.

[0041] It should also be understood that the terms used in the specification and the following claims are for the purpose of describing particular embodiments of the application and are not intended to limit the application. As used in the specification and the appended claims, the singular forms "a," "an" and "the" are intended to include the plural forms as well, unless the context clearly indicates otherwise.

[0042] It should further be understood that the term "and / or" as used in the specification and the following claims, refers to any combination of one or more of the associated listed items, and all possible combinations, including singular combinations, of the associated listed items, for example, A and / or B, can mean A alone, A and B together, or B alone. In addition, the character " / " in the present application generally represents an "or" relationship between the front and rear associated objects.

[0043] It should be understood that, although the terms first, second, third, etc. can be used in the embodiments of the present application to describe a certain range, etc., these ranges should not be limited to these terms. These terms are only used to distinguish the ranges from each other. For example, the first range can also be referred to as the second range, and similarly, the second range can also be referred to as the first range, without departing from the scope of the embodiments of the present application.

[0044] Depending on the context, the word "if" as used herein can be interpreted to mean "when" or "while" or "in response to determining" or "in response to detecting." Similarly, the phrase "if it is determined" or "if a stated condition or event occurs" can be interpreted to mean "when it is determined" or "in response to determining" or "when a stated condition or event occurs" or "in response to detecting a stated condition or event."

[0045] In order to make the purposes, technical solutions and advantages of the embodiments of the present application clearer, the technical solutions in the embodiments of the present application will be described clearly and completely below with reference to the drawings in the embodiments of the present application. Obviously, the described embodiments are some of the embodiments of the present application, rather than all the embodiments of the present application. The components of the embodiments of the present application described and shown in the drawings herein can be arranged and designed in various different configurations. Therefore, the following detailed description of the embodiments of the present application provided in the drawings is not intended to limit the scope of the claimed present application, but only represents selected embodiments of the present application. Based on the embodiments in the present application, all other embodiments obtained by those of ordinary skill in the art without creative efforts fall within the scope of the present application.

[0046] Various structural diagrams according to the disclosed embodiments of the present application are shown in the drawings. These diagrams are not drawn to scale, in which certain details are exaggerated for clarity and others omitted. The shapes and relative sizes of the various regions, layers, and their relative positions are shown in the drawings for exemplary purposes only, and may deviate in actual implementation due to manufacturing tolerances or technical limitations, and regions / layers with different shapes, sizes, and relative positions can be additionally designed by those skilled in the art according to actual needs.

[0047] Embodiment one

[0048] With reference to Figure 1 The automatic positioning fan fault detection method described in the present application comprises the following steps:

[0049] 1) Obtain a recording waveform of a wind power generation device, and pre-process the recording waveform of the wind power generation device;

[0050] The specific operation of step 1) is as follows:

[0051] 11) Perform frequency noise suppression on the recording waveform;

[0052] Perform 6-layer decomposition using dual-tree complex wavelet transform (DTCWT), i.e.:

[0053] Wj,k = ∫s(t)ψj,k*(t)dt

[0054] Where ψ is the dual-tree complex wavelet basis function.

[0055] Threshold processing, i.e.:

[0056] W~j,k = sign(Wj,k)·max(|Wj,k|-Tj,0)

[0057] Where Tj = σj√(2lnN), and σj is the standard deviation of the jth layer of detail coefficients.

[0058] 12) Perform power frequency interference elimination on the recording waveform;

[0059] Design the notch filter transfer function as:

[0060] H(z) = (1-2z^{-1}cosω0+z^{-2}) / (1-2rz^{-1}cosω0+r 2 z^{-2})

[0061] Where ω0 = 2π×50Hz, and r = 0.99.

[0062] 2) Perform feature extraction on the processed recording waveform, and construct a multi-dimensional feature library based on the extracted features, as shown in Table 1:

[0063] Table 1

[0064]

[0065] 3) constructing an intelligent diagnosis model;

[0066] constructing the intelligent diagnosis model in a hybrid neural network architecture;

[0067] 4) training the intelligent diagnosis model;

[0068] During the training process, data augmentation is performed on the training samples, wherein data augmentation is performed by adding Gaussian noise, time stretching, and channel loss;

[0069] The loss function during the training process is:

[0070] FL(p_t) = -a(1-p_t)^y log(p_t)

[0071] wherein y = 2, a = 0.25.

[0072] 5) fault location: 51) traveling wave positioning mode:

[0073] The Teager-Kaiser energy operator is used to detect the wave head arrival time TEO(n) as:

[0074] TEO(n) = x 2 (n)-x(n-1)x(n+1)

[0075] When TEO(n) > 3σ_TEO, the wave head marker is triggered.

[0076] Ranging formula based on cable wave speed:

[0077] L = (t2-t1) x v x 0.98 / 2 + D_correction

[0078] wherein v = 1.6 x 10^8 m / s (cross-linked polyethylene cable).

[0079] 52) impedance trajectory positioning mode:

[0080] The dynamic calculation of the fault loop impedance Z is:

[0081] Z = (V_pre-V_fault) / (I_fault-I_pre)

[0082] The trajectory determination rule is:

[0083] IF |Z| < Z_set AND arg(Z) e [θ_min, θ_max], trigger region localization. The localization result fusion strategy is:

[0084] IF |L_wave - L_impedance| < 50 m, output the weighted average position.

[0085] ELSE start time-frequency analysis (WVD distribution peak tracking) for arbitration.

[0086] Embodiment Two

[0087] The specific process of the embodiment is:

[0088] 1) Data acquisition;

[0089] Vibration signal: impact pulse value (SPM) reaches 35 dBm / ℃.

[0090] Current signal: the sideband amplitude of the characteristic frequency 125 Hz increases by 15 dB.

[0091] 2) Feature extraction;

[0092] The wavelet packet decomposition of the 4th layer details accounts for 62% (normal working condition <40%) of the energy.

[0093] The current Park vector trajectory presents an elliptical distortion (the ratio of major axis to minor axis is 1:2.3).

[0094] 3) Intelligent diagnosis;

[0095] The CNN-LSTM model outputs the bearing outer ring fault probability of 92.7%.

[0096] Time-frequency analysis shows that the fault characteristic frequency is:

[0097] f_fault = f_rotor x (N_balls + 1) / 2 = 17.5 Hz x (9 + 1) / 2 = 87.5 Hz

[0098] 4) Localization output;

[0099] Traveling wave localization: 83.6 m away from the measurement point (corresponding to the input shaft position of the gearbox).

[0100] Maintenance suggestion: replace the SKF NU216ECP bearing and check the lubrication system.

[0101] The present application has the following characteristics:

[0102] Multi-level hybrid noise reduction algorithm: adaptive wavelet threshold denoising and Kalman filter cascade processing technology are proposed.

[0103] Fault feature dynamic weight distribution: multi-dimensional feature fusion strategy based on improved entropy weight method (voltage mutation rate, spectral entropy, sequence component difference degree).

[0104] Spacetime joint positioning model: hybrid positioning framework combining convolutional neural network (CNN) and improved dynamic time warping (DTW).

[0105] Traveling wave-impedance dual-mode verification mechanism: simultaneous use of traveling wave head precise calibration and impedance trajectory boundary determination to realize dual verification.

[0106] Example three

[0107] The automatic positioning fan fault detection system provided by the application comprises:

[0108] An acquisition module is configured to acquire a recording waveform of a wind power generation device and pre-process the recording waveform of the wind power generation device.

[0109] An extraction module is configured to extract features from the pre-processed recording waveform.

[0110] A judgment module is configured to input the extracted features into a trained intelligent diagnosis model to determine whether a fan has a fault.

[0111] A positioning module is configured to locate a fault position when the fan has a fault.

[0112] In this embodiment, the pre-processing of the recording waveform of the wind power generation device comprises:

[0113] The recording waveform is subjected to frequency noise suppression and power frequency interference elimination.

[0114] In this embodiment, the feature extraction from the processed recording waveform comprises:

[0115] The processed recording waveform is subjected to feature extraction to obtain time domain features, frequency domain features and sequence component features, i.e., nonlinear features.

[0116] The division of the modules in the embodiments of the application is illustrative, and is merely a logical function division, and another division mode can be used in actual implementation, and each functional module in each embodiment of the application can be integrated in one processor, or can be physically separated, or two or more modules can be integrated in one module.

[0117] Example four

[0118] The computer device comprises a memory, a processor, and a computer program stored in the memory and executable on the processor, and the processor implements the steps of the method for generating and uploading the trusted state alarm information when executing the computer program, for example, comprising: obtaining a recording waveform of a wind power generation device, and preprocessing the recording waveform of the wind power generation device; performing feature extraction on the preprocessed recording waveform to obtain extracted features; inputting the extracted features into a trained intelligent diagnosis model to determine whether the wind turbine has a fault; and when the wind turbine has a fault, positioning the fault position, the preprocessing process of the recording waveform of the wind power generation device comprises: performing frequency noise suppression and power frequency interference elimination on the recording waveform, and the feature extraction process of the preprocessed recording waveform to obtain the extracted features comprises: performing feature extraction on the preprocessed recording waveform to obtain time domain features, frequency domain features, and sequence component features, i.e., nonlinear features. The memory can include an internal memory, such as a high-speed random memory, and can also include a non-volatile memory, such as at least one disk memory. The processor, network interface, and memory are connected to each other through an internal bus, which can be an industry standard architecture bus, a peripheral component interconnect standard bus, an extended industry standard structure bus, etc. The bus can be divided into an address bus, a data bus, a control bus, etc. The memory is used to store programs, specifically, the programs can include program codes, and the program codes include computer operation instructions. The memory can include an internal memory and a non-volatile memory, and provide instructions and data to the processor.

[0119] Example five

[0120] The computer readable storage medium stores a computer program, and the computer program is executed by a processor to implement steps of the method for generating and uploading the trusted state alarm information, for example, including: obtaining a recording waveform of a wind power generation device, and preprocessing the recording waveform of the wind power generation device; performing feature extraction on the preprocessed recording waveform to obtain extracted features; inputting the extracted features into a trained intelligent diagnosis model to determine whether the wind turbine has a fault; and when the wind turbine has a fault, positioning the fault position. The preprocessing process of the recording waveform of the wind power generation device includes frequency noise suppression and power frequency interference elimination. The feature extraction process of the preprocessed recording waveform includes feature extraction on the preprocessed recording waveform to obtain time domain features, frequency domain features, and sequence component features, i.e., nonlinear features. Specifically, the computer readable storage medium includes but is not limited to, for example, volatile memory and / or non-volatile memory. The volatile memory can include random access memory (RAM) and / or cache memory, etc. The non-volatile memory can include read-only memory (ROM), hard disk, flash memory, optical disc, magnetic disc, etc.

[0121] Those skilled in the art should understand that the embodiments of the present application can be provided as a method, a system, or a computer program product. Therefore, the present application can take the form of an entirely hardware embodiment, an entirely software embodiment, or an embodiment combining software and hardware aspects. Moreover, the present application can take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROMs, optical storage, etc.) containing computer-usable program code.

[0122] The present application is described with reference to flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of the present application. It should be understood that each flow and / or block in the flowcharts and / or block diagrams, and the combination of flows and / or blocks in the flowcharts and / or block diagrams can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing apparatus to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing apparatus produce a device that implements the functions specified in the flowcharts and / or block diagrams. Figure 1 The functions specified in one or more flows and / or blocks Figure 1 The device that implements the functions specified in one or more flows and / or blocks.

[0123] These computer program instructions can also be stored in a computer- readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instructions which implement the Figure 1 function specified in the flow or flows and / or blocks Figure 1 of the block or blocks.

[0124] These computer program instructions can also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the Figure 1 function specified in the flow or flows and / or blocks Figure 1 of the block or blocks.

[0125] Other embodiments of the application will be apparent to those skilled in the art from consideration of the specification and practice of the application disclosed herein. It is intended that the specification and examples be considered as exemplary only, with the true scope and spirit of the application being indicated by the following claims.

[0126] It is to be understood that the application is not limited to the precise construction described herein and as shown in the attached drawings, and that various modifications and changes can be made by those skilled in the art without departing from the scope of the application. The scope of the application is to be defined by the claims appended hereto.

[0127] The above description is only preferred embodiments of the present application, not any limitation thereto, any simple modification, change and equivalent structure change according to the technical essence of the present application to the above embodiments are still within the protection scope of the present application technical solution.

Claims

1. An automatic positioning wind turbine fault detection method, characterized in that, The method comprises the following steps: acquiring a recording waveform of a wind power generation device, and preprocessing the recording waveform of the wind power generation device; extracting features from the preprocessed recording waveform to obtain extracted features; inputting the extracted features into a trained intelligent diagnosis model to determine whether the wind turbine has a fault; locating a fault position when the wind turbine has a fault.

2. The automatic positioning fan fault detection method of claim 1, wherein, The preprocessing of the recording waveform of the wind power generation device comprises the following steps: frequency noise suppression and power frequency interference elimination are performed on the recording waveform.

3. The automatic positioning fan fault detection method of claim 1, wherein, The feature extraction from the preprocessed recording waveform to obtain the extracted features comprises the following steps: time domain features, frequency domain features, and sequence component features (i.e., nonlinear features) are extracted from the preprocessed recording waveform.

4. The automatic positioning fan fault detection method of claim 1, wherein, The intelligent diagnosis model is constructed based on a hybrid neural network architecture and an improved dynamic time warping.

5. The automatic positioning fan fault detection method of claim 1, wherein, The locating of the fault position comprises the following steps: a traveling wave positioning mode or an impedance trajectory positioning mode is used to locate the fault position.

6. An automatic positioning fan fault detection system characterized by, The method comprises the following steps: a recording waveform of a wind power generation device is acquired, and the recording waveform of the wind power generation device is preprocessed; features are extracted from the preprocessed recording waveform to obtain extracted features; the extracted features are input into a trained intelligent diagnosis model to determine whether the wind turbine has a fault; a fault position is located when the wind turbine has a fault.

7. The automatic positioning fan fault detection system of claim 6, wherein, The preprocessing of the recording waveform of the wind power generation device comprises the following steps: frequency noise suppression and power frequency interference elimination are performed on the recording waveform.

8. The automatic positioning fan fault detection system of claim 6, wherein, The feature extraction from the preprocessed recording waveform to obtain the extracted features comprises the following steps: time domain features, frequency domain features, and sequence component features (i.e., nonlinear features) are extracted from the preprocessed recording waveform.

9. A computer device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, The processor executes the computer program to implement the steps of the automatic wind turbine fault detection and positioning method according to any one of claims 1-5.

10. A computer-readable storage medium storing a computer program, the computer program comprising instructions that, when executed by a computer, cause the computer to perform the method of any one of claims 1 to 9. The computer program is executed by the processor to implement the steps of the automatic wind turbine fault detection and positioning method according to any one of claims 1-5.

Images