A fan installation fault detection method, system, device and storage medium

Abstract

The application discloses a fan installation fault detection method, system, device and storage medium, and the method comprises the steps of: acquiring a vibration signal of a fan air duct, and extracting a vibration feature according to the vibration signal; constructing a reference space matrix based on the vibration signal and the vibration feature; performing feature optimization based on the reference space matrix to obtain a target space matrix; and performing fan installation fault judgment based on the target space matrix and a first set fault threshold. The method can avoid misjudgment caused by subjective factors, and efficiently and accurately detect fan installation faults by optimizing the reference space of the vibration feature affecting the fan installation.

Description

Technical Field

[0001] This invention relates to the field of electrical technology, and specifically to a method, system, device, and storage medium for detecting installation faults in wind turbines. Background Technology

[0002] Currently, the only way to detect installation faults in wind turbines is through market and user feedback; there is no efficient and automatic method for detecting wind turbine installation faults. Summary of the Invention

[0003] The main objective of this invention is to provide a method, system, device, and storage medium for detecting wind turbine installation faults, which can avoid misjudgments caused by human subjective factors and efficiently and accurately detect wind turbine installation faults by optimizing the reference space that affects the vibration characteristics of wind turbine installation.

[0004] To achieve the above objectives, according to a first aspect of the embodiments of this application, a method for detecting wind turbine installation faults is provided, the method comprising:

[0005] The vibration signal of the fan duct is acquired, and the vibration characteristics are extracted based on the vibration signal;

[0006] A reference space matrix is ​​constructed based on the vibration signal of the fan duct and the vibration characteristics.

[0007] Based on the aforementioned baseline space matrix, feature optimization is performed to obtain the target space matrix;

[0008] Wind turbine installation faults are determined based on the target space matrix and a first set fault threshold.

[0009] Optionally, constructing a reference space matrix based on the fan duct vibration signal and the vibration characteristics includes:

[0010] An initial reference space matrix for all vibration signals is constructed based on all fan duct vibration signals and the vibration characteristics of each vibration signal.

[0011] The initial reference space matrix is ​​standardized to obtain the reference space matrix.

[0012] Optionally, the step of performing feature optimization based on the reference space matrix to obtain the target space matrix includes:

[0013] Calculate the Mahalanobis distance in each row of the reference space matrix based on the reference space matrix and the covariance inverse matrix of the reference space matrix;

[0014] The signal-to-noise ratio is calculated using the corresponding Mahalanobis distance in the reference space matrix;

[0015] Feature optimization is performed based on the signal-to-noise ratio of each row of the reference space matrix to select target features that affect the vibration signal;

[0016] The reference space matrix is ​​reconstructed based on the target features to obtain the target space matrix.

[0017] Optionally, feature optimization is performed based on the signal-to-noise ratio of each row of the reference space matrix to filter out target features affecting the vibration signal, including:

[0018] Remove each of the vibration features one by one, and construct a new reference space matrix after removing the vibration feature. Obtain the signal-to-noise ratio of the new reference space matrix and the signal-to-noise ratio of the original reference space matrix before removing the vibration feature.

[0019] If the signal-to-noise ratio (SNR) of the new reference space matrix is ​​less than or equal to that of the original reference space matrix, the vibration feature is retained; if the SNR of the new reference space matrix is ​​greater than that of the original reference space matrix, the vibration feature is removed.

[0020] All retained vibration features are identified as target features affecting the vibration signal.

[0021] Optionally, the step of determining wind turbine installation faults based on the target space matrix and a first set fault threshold includes:

[0022] Calculate the wind turbine performance coefficient based on the Mahalanobis distance corresponding to the target space matrix;

[0023] If the fan performance coefficient is less than or equal to the first set fault threshold, it is determined that there is a fault in the fan installation.

[0024] If the fan performance coefficient is greater than the first set fault threshold, the fan installation is determined to be normal.

[0025] Optionally, before extracting vibration features based on the vibration signal, the method further includes:

[0026] Obtain the fan linear velocity; if the fan linear velocity is within a set high speed range, determine the fan installation fault based on the root mean square difference of the vibration signal; if the fan linear velocity is within a set low speed range, continue with the step of extracting vibration features based on the vibration signal.

[0027] Optionally, the step of determining the fan installation fault based on the root mean square difference of the vibration signal includes:

[0028] Calculate the root mean square difference of the vibration signal of the fan duct;

[0029] If the root mean square difference is greater than or equal to the second set fault threshold, it is determined that there is a fault in the installation of the fan.

[0030] If the root mean square difference is less than the second set fault threshold, the fan installation is determined to be normal.

[0031] According to a second aspect of the embodiments of this application, a wind turbine installation fault detection system is provided, the system comprising:

[0032] The feature extraction module is used to acquire the vibration signal of the fan duct and extract vibration features based on the vibration signal;

[0033] The reference space matrix module is used to construct a reference space matrix based on the fan duct vibration signal and the vibration characteristics.

[0034] The baseline space optimization module is used to perform feature optimization based on the baseline space matrix to obtain the target space matrix.

[0035] The fault diagnosis module is used to diagnose wind turbine installation faults based on the target space matrix and a first set fault threshold.

[0036] According to a third aspect of the present application, an electronic device is provided, comprising: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the method described in the first aspect above.

[0037] According to a fourth aspect of the embodiments of this application, a computer-readable storage medium is provided having computer-readable instructions stored thereon, the computer-readable instructions being executable by a processor to implement the method described in the first aspect above.

[0038] This invention provides a method, system, device, and storage medium for detecting wind turbine installation faults. It acquires vibration signals from the wind turbine duct and extracts vibration features from these signals. A reference space matrix is ​​constructed based on the vibration signals and the vibration features. Feature optimization is performed on the reference space matrix to obtain a target space matrix. Wind turbine installation faults are then determined based on the target space matrix and a first preset fault threshold. This method avoids misjudgments caused by subjective human factors and efficiently and accurately detects wind turbine installation faults by optimizing the reference space of vibration features affecting wind turbine installation. Attached Figure Description

[0039] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on the structures shown in these drawings without creative effort.

[0040] Figure 1 This is a schematic diagram of a method for detecting installation faults in wind turbines provided by the present invention;

[0041] Figure 2 This is a schematic diagram of the noise diagnosis method provided by the present invention;

[0042] Figure 3 A block diagram of a wind turbine installation fault detection system provided by the present invention;

[0043] Figure 4 A schematic diagram of the structure of an electronic device provided by the present invention;

[0044] Figure 5 This invention provides a schematic diagram of a computer-readable storage medium.

[0045] The realization of the objective, functional features and advantages of the present invention will be further explained in conjunction with the embodiments and with reference to the accompanying drawings. Detailed Implementation

[0046] 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 a part of the embodiments of the present invention, and not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative effort are within the scope of protection of the present invention.

[0047] It should be noted that all directional indications (such as up, down, left, right, front, back, etc.) in the embodiments of the present invention are only used to explain the relative positional relationship and movement of each component in a certain specific posture (as shown in the figure). If the specific posture changes, the directional indication will also change accordingly.

[0048] Furthermore, in this invention, descriptions involving "first," "second," etc., are for descriptive purposes only and should not be construed as indicating or implying their relative importance or implicitly specifying the number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include at least one of that feature. In the description of this invention, "a plurality of" means at least two, such as two, three, etc., unless otherwise explicitly specified.

[0049] In this invention, unless otherwise explicitly specified and limited, the terms "connection," "fixed," etc., should be interpreted broadly. For example, "fixed" can mean a fixed connection, a detachable connection, or an integral part; it can mean a mechanical connection or an electrical connection; it can mean a direct connection or an indirect connection through an intermediate medium; it can mean the internal communication of two components or the interaction between two components, unless otherwise explicitly limited. Those skilled in the art can understand the specific meaning of the above terms in this invention according to the specific circumstances.

[0050] Furthermore, the technical solutions of the various embodiments of the present invention can be combined with each other, but only if they are feasible for those skilled in the art. If the combination of technical solutions is contradictory or cannot be implemented, it should be considered that such combination of technical solutions does not exist and is not within the scope of protection claimed by the present invention.

[0051] This invention addresses installation obstacles encountered during fan installation by starting from the production line end. It solves the problem of background noise on the production line by focusing on vibration signals, without affecting production speed. Based on the principle that fan installation faults occur in the frequency range below 2400Hz, vibration signals collected by sensors can be used to diagnose fan installation faults. The preferred installation location for the sensors is the front panel of the air duct, mainly because the transmission path is short at the front panel, resulting in a more noticeable vibration signal.

[0052] Figure 1 This application illustrates a method for detecting installation faults in wind turbines, comprising:

[0053] Step 101: Obtain the vibration signal of the fan duct and extract vibration features based on the vibration signal;

[0054] Step 102: Construct a reference space matrix based on the fan duct vibration signal and the vibration characteristics;

[0055] Step 103: Perform feature optimization based on the reference space matrix to obtain the target space matrix;

[0056] Step 104: Determine the installation fault of the wind turbine based on the target space matrix and the first set fault threshold.

[0057] In a preferred embodiment of the present invention, before constructing the feature vector based on the vibration signal in step 101, the method further includes:

[0058] Obtain the fan linear velocity; if the fan linear velocity is within a set high speed range, determine the fan installation fault based on the root mean square difference of the vibration signal; if the fan linear velocity is within a set low speed range, continue with the step of constructing a feature vector based on the vibration signal.

[0059] In a preferred embodiment of the present invention, step 102, the construction of a reference space matrix based on the fan duct vibration signal and the vibration characteristics, includes:

[0060] An initial reference space matrix for all vibration signals is constructed based on all fan duct vibration signals and the vibration characteristics of each vibration signal; the initial reference space matrix is ​​then standardized to obtain the reference space matrix.

[0061] In a preferred embodiment of the present invention, step 103, which involves performing feature optimization based on the reference space matrix to obtain the target space matrix, includes:

[0062] The Mahalanobis distance in each row of the reference space matrix is ​​calculated based on the reference space matrix and its covariance inverse matrix. The corresponding signal-to-noise ratio is calculated using the Mahalanobis distance in the reference space matrix. Feature optimization is performed based on the signal-to-noise ratio of each row of the reference space matrix to select target features that affect the vibration signal. The reference space matrix is ​​reconstructed based on the target features to obtain the target space matrix.

[0063] It should be noted that, in the embodiments of this application, features can also be filtered by clustering to achieve the purpose of feature optimization.

[0064] Furthermore, feature optimization is performed based on the signal-to-noise ratio of each row of the reference space matrix to screen out target features affecting the vibration signal, including:

[0065] Each of several vibration features is removed one by one, and a new reference space matrix is ​​constructed after removing the vibration feature. The signal-to-noise ratio (SNR) of the new reference space matrix and the SNR of the original reference space matrix before removing the vibration feature are obtained. If the SNR of the new reference space matrix is ​​less than or equal to the SNR of the original reference space matrix, the vibration feature is retained. If the SNR of the new reference space matrix is ​​greater than the SNR of the original reference space matrix, the vibration feature is removed. All retained vibration features are identified as target features affecting the vibration signal.

[0066] Furthermore, the step of determining wind turbine installation faults based on the target space matrix and a first set fault threshold includes:

[0067] The wind turbine performance coefficient is calculated based on the Mahalanobis distance corresponding to the target space matrix; if the wind turbine performance coefficient is less than or equal to the first set fault threshold, it is determined that the wind turbine installation is faulty; if the wind turbine performance coefficient is greater than the first set fault threshold, it is determined that the wind turbine installation is normal.

[0068] In a preferred embodiment of the present invention, step 104, which involves determining the installation fault of the wind turbine based on the root mean square difference of the vibration signal, includes:

[0069] Calculate the root mean square difference of the fan duct vibration signal; if the root mean square difference is greater than or equal to a second set fault threshold, it is determined that there is a fault in the fan installation; if the root mean square difference is less than the second set fault threshold, it is determined that the fan installation is normal.

[0070] The method provided in the embodiments of this application will be described in detail below with reference to the accompanying drawings.

[0071] Figure 2 This diagram illustrates a method for diagnosing installation faults in wind turbines, which includes the following steps:

[0072] Step 1: Use a vibration sensor to acquire the vibration signal x(i) of the front panel of the line fan; the preferred installation position of the vibration sensor is the front panel of the air duct, which has a short transmission path and acquires a clear vibration signal characteristic.

[0073] The fault detection method can be selected based on the wind turbine linear speed. If the speed is in the set high speed range, proceed to step 2; if the speed is in the set low speed range, proceed to step 3. Alternatively, the specific method can be selected based on the actual situation, and is not limited to judging based on the wind turbine linear speed.

[0074] Step 2 includes:

[0075] Step 2-1: Calculate the root mean square difference e of the fan duct vibration signal x(i) according to the following formula;

[0076]

[0077] Where i takes values ​​from 1 to N, and N is the number of samples.

[0078] Step 2-2: If the root mean square difference is greater than or equal to the set fault threshold u1, a fault is determined to exist in the fan installation, and an alarm is output; if the root mean square difference is less than the set fault threshold u1, the fan installation is determined to be normal. Here, the fault threshold u1 is a threshold for obtaining the root mean square difference of various faults in advance.

[0079] Step 3 includes:

[0080] Step 3-1: Calculate the characteristic parameters of each fan and duct based on the fan and duct vibration signal x(i). The characteristic parameters of the fan and duct may include: average value, peak value, crest factor, margin factor, impulse coefficient, shape coefficient, root mean square, skewness, kurtosis, variance, etc., and construct the feature vector.

[0081] Step 3-2: Construct the initial reference space matrix under all feature parameters based on the feature parameters. The specific steps are as follows:

[0082] Step 3-2-1: Construct an initial reference space matrix for all vibration signals based on all fan and duct vibration signals and the vibration characteristics of each signal:

[0083] Given n samples of fan duct vibration signals, each sample has m feature variables. Let Xij be the j-th feature parameter of the i-th sample data. Then, the initial reference space matrix X formed by the n samples is X = (Xj - ...). ij ) n×m (i = 1, 2, ..., n; j = 1, 2, ..., m); represented as

[0084] Step 3-2-2: Standardize the initial reference space matrix to obtain the reference space matrix;

[0085] Characteristic variables Z of standardized sample Z i =[Z i1 Z i2 ,...,Z im ] T i = 1, 2, ..., n;

[0086]

[0087] in, and s p Let represent the mean and standard deviation of the characteristic corresponding to the p-th sample, respectively. The calculation formulas are as follows:

[0088]

[0089]

[0090] Step 3-3: Perform feature optimization based on the baseline space matrix to obtain the target space matrix.

[0091] Because this application embodiment has 10 feature parameters, the Martin system in this application embodiment has 10 feature variables, the sampling period is set to twice, and the orthogonal array is represented as L. 11 (2 10 ).

[0092] The specific optimization steps for the target space matrix are as follows:

[0093] Step 3-3-1: Calculate the Mahalanobis distance for each row of the reference space matrix based on the reference space matrix and its covariance inverse:

[0094]

[0095] Among them, S -1 The covariance inverse matrix of the standardized reference space is given by the Mahalanobis distance t, which is positively correlated with the number of eigenparameters m.

[0096] Step 3-3-2: Calculate the corresponding signal-to-noise ratio R using the Mahalanobis distance in the reference space matrix:

[0097]

[0098] Step 3-3-3: Perform feature optimization based on the signal-to-noise ratio of each row of the reference space matrix to select target features that affect the vibration signal;

[0099] Specifically, each of the several vibration features is removed one by one, and a new reference space matrix is ​​constructed after removing the vibration feature. The signal-to-noise ratio (SNR) of the new reference space matrix is ​​compared with that of the original reference space matrix. If the SNR of the new reference space matrix is ​​less than or equal to that of the original reference space matrix, the vibration feature is retained. If the SNR of the new reference space matrix is ​​greater than that of the original reference space matrix, the vibration feature is removed. All retained vibration features are determined as the optimal features affecting the vibration signal.

[0100] Step 3-3-4: Reconstruct the reference space matrix based on the target features to obtain the target space matrix;

[0101] The selected vibration features are the optimal features affecting this type of signal. Therefore, the reference space is reconstructed based on the optimal features to obtain the optimal reference space, which is the target space matrix.

[0102] Steps 3-4: Determine wind turbine installation faults based on the target space matrix and the first set fault threshold;

[0103] Step 3-4-1: Calculate the wind turbine performance coefficient based on the Mahalanobis distance corresponding to the target space matrix;

[0104] Specifically, the Mahalanobis distance is converted into the wind turbine performance coefficient HS according to the following formula, and then HS is used to determine whether there is a fault:

[0105] HS = 1 - tanh(α*MD) w )

[0106]

[0107]

[0108] α is the health coefficient, MD slightIt is the average of all Mahalanobis distances under minor fault conditions (the average Mahalanobis distance under normal conditions is taken); the HSo value is between 0.8 and 0.9 to indicate the health performance of the fan.

[0109] Step 3-4-2: If the fan performance coefficient is less than or equal to the set fault threshold u2, a fault is determined to exist in the fan installation, and an alarm is output; if the fan performance coefficient is greater than the set fault threshold u2, the fan installation is determined to be normal. u2 is the threshold obtained by performing the above operations on a certain number of fault samples.

[0110] Fan installation faults can be broadly categorized into two types: strong faults and weak faults. Weak faults involve interference between the fan blades and the conveyor belt, resulting in relatively high-frequency noise. Because the vibration is relatively small, its characteristics are subtle and difficult to diagnose using the methods described above. Therefore, in addition to... Figure 2 The two wind turbine installation fault detection methods involved in the study also include, in practical applications, using human judgment of high-frequency sounds to determine installation faults. Combining the threshold judgment method and the manual judgment method provides multiple layers of protection against wind turbine installation faults.

[0111] This invention provides a method for detecting wind turbine installation faults. The method involves acquiring vibration signals from the wind turbine duct and extracting vibration features from these signals; constructing a reference space matrix based on the vibration signals and the vibration features; optimizing the reference space matrix to obtain a target space matrix; and determining wind turbine installation faults based on the target space matrix and a first predetermined fault threshold. This method avoids misjudgments caused by subjective human factors and efficiently and accurately detects wind turbine installation faults by optimizing the reference space of vibration features affecting wind turbine installation.

[0112] Based on the same technical concept, embodiments of this application also provide a wind turbine installation fault detection system, such as... Figure 3 As shown, the system includes:

[0113] The feature extraction module 301 is used to acquire the vibration signal of the fan duct and extract vibration features based on the vibration signal;

[0114] The reference space matrix module 302 is used to construct a reference space matrix based on the fan duct vibration signal and the vibration characteristics.

[0115] The baseline space optimization module 303 is used to perform feature optimization based on the baseline space matrix to obtain the target space matrix;

[0116] The fault diagnosis module 304 is used to diagnose wind turbine installation faults based on the target space matrix and a first set fault threshold.

[0117] This application also provides an electronic device corresponding to the method provided in the foregoing embodiments. Please refer to... Figure 4 The diagram illustrates an electronic device provided by some embodiments of this application. The electronic device 20 may include: a processor 200, a memory 201, a bus 202, and a communication interface 203, wherein the processor 200, the communication interface 203, and the memory 201 are connected via the bus 202; the memory 201 stores a computer program that can run on the processor 200, and when the processor 200 runs the computer program, it executes the method provided by any of the foregoing embodiments of this application.

[0118] The memory 201 may include high-speed random access memory (RAM) or non-volatile memory, such as at least one disk storage device. Communication between this system network element and at least one other network element is achieved through at least one physical port 203 (which can be wired or wireless), such as the Internet, wide area network, local area network, or metropolitan area network.

[0119] Bus 202 can be an ISA bus, PCI bus, or EISA bus, etc. The bus can be divided into an address bus, a data bus, a control bus, etc. The memory 201 is used to store programs. After receiving an execution instruction, the processor 200 executes the program. The method disclosed in any of the foregoing embodiments of this application can be applied to the processor 200, or implemented by the processor 200.

[0120] The processor 200 may be an integrated circuit chip with signal processing capabilities. In implementation, each step of the above method can be completed by the integrated logic circuitry in the hardware of the processor 200 or by instructions in software form. The processor 200 may be a general-purpose processor, including a central processing unit (CPU), a network processor (NP), etc.; it may also be a digital signal processor (DSP), an application-specific integrated circuit (ASIC), an off-the-shelf programmable gate array (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, or discrete hardware components. It can implement or execute the methods, steps, and logic block diagrams disclosed in the embodiments of this application. The general-purpose processor may be a microprocessor or any conventional processor. The steps of the methods disclosed in the embodiments of this application can be directly embodied in the execution of a hardware decoding processor, or executed by a combination of hardware and software modules in the decoding processor. The software modules may reside in random access memory, flash memory, read-only memory, programmable read-only memory, electrically erasable programmable memory, registers, or other mature storage media in the art. The storage medium is located in memory 201. The processor 200 reads the information in memory 201 and, in conjunction with its hardware, completes the steps of the above method.

[0121] The electronic devices and methods provided in the embodiments of this application are based on the same inventive concept and have the same beneficial effects as the methods they employ, operate, or implement.

[0122] This application also provides a computer-readable storage medium corresponding to the method provided in the foregoing embodiments. Please refer to... Figure 5 The computer-readable storage medium shown is an optical disc 30, on which a computer program (i.e., a program product) is stored, which, when run by a processor, executes the methods provided in any of the foregoing embodiments.

[0123] It should be noted that examples of the computer-readable storage medium may also include, but are not limited to, phase-change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other optical and magnetic storage media, which will not be elaborated here.

[0124] The computer-readable storage medium provided in the above embodiments of this application and the method provided in the embodiments of this application are based on the same inventive concept and have the same beneficial effects as the methods adopted, run or implemented by the applications stored therein.

[0125] It should be noted that:

[0126] The algorithms and displays provided herein are not inherently related to any particular computer, virtual device, or other equipment. Various general-purpose devices can also be used in conjunction with the teachings herein. The required structure for constructing such devices is apparent from the above description. Furthermore, this application is not directed to any particular programming language. It should be understood that the content of this application described herein can be implemented using various programming languages, and the above description of specific languages ​​is for the purpose of disclosing the best mode of implementation of this application.

[0127] Numerous specific details are set forth in the specification provided herein. However, it will be understood that embodiments of this application may be practiced without these specific details. In some instances, well-known methods, structures, and techniques have not been shown in detail so as not to obscure the understanding of this specification.

[0128] Similarly, it should be understood that, in order to simplify this application and aid in understanding one or more of the various inventive aspects, in the above description of exemplary embodiments of this application, various features of this application are sometimes grouped together into a single embodiment, figure, or description thereof. However, this method of disclosure should not be construed as reflecting an intention that the claimed application requires more features than are expressly recited in each claim. Rather, as reflected in the following claims, inventive aspects lie in fewer than all features of a single foregoing disclosed embodiment. Therefore, the claims following the detailed description are hereby expressly incorporated into that detailed description, wherein each claim itself is a separate embodiment of this application.

[0129] Those skilled in the art will understand that modules in the device of the embodiments can be adaptively changed and placed in one or more devices different from that embodiment. Modules, units, or components in the embodiments can be combined into a single module, unit, or component, and further, they can be divided into multiple sub-modules, sub-units, or sub-components. Except where at least some of such features and / or processes or units are mutually exclusive, any combination can be used to combine all features disclosed in this specification (including the accompanying claims, abstract, and drawings) and all processes or units of any method or device so disclosed. Unless expressly stated otherwise, each feature disclosed in this specification (including the accompanying claims, abstract, and drawings) may be replaced by an alternative feature that serves the same, equivalent, or similar purpose.

[0130] Furthermore, those skilled in the art will understand that although some embodiments described herein include certain features but not others included in other embodiments, combinations of features from different embodiments are intended to be within the scope of this application and form different embodiments. For example, in the following claims, any of the claimed embodiments can be used in any combination.

[0131] The various component embodiments of this application can be implemented in hardware, or as software modules running on one or more processors, or a combination thereof. Those skilled in the art will understand that microprocessors or digital signal processors (DSPs) can be used in practice to implement some or all of the functions of some or all of the components in the virtual machine creation apparatus according to embodiments of this application. This application can also be implemented as a device or apparatus program (e.g., a computer program and computer program product) for performing part or all of the methods described herein. Such an implementation of this application can be stored on a computer-readable medium, or can be in the form of one or more signals. Such signals can be downloaded from an Internet website, provided on a carrier signal, or provided in any other form.

[0132] It should be noted that the above embodiments are illustrative of this application and not restrictive, and that those skilled in the art can devise alternative embodiments without departing from the scope of the appended claims. In the claims, any reference signs placed between parentheses should not be construed as limiting the claims. The word "comprising" does not exclude the presence of elements or steps not listed in the claims. The word "a" or "an" preceding an element does not exclude the presence of a plurality of such elements. This application can be implemented by means of hardware comprising several different elements and by means of a suitably programmed computer. In the unit claims enumerating several means, several of these means may be embodied by the same item of hardware. The use of the words first, second, and third, etc., does not indicate any order. These words can be interpreted as names.

[0133] The above description is only a preferred embodiment of the present invention and does not limit the patent scope of the present invention. All equivalent structural transformations made under the concept of the present invention using the contents of the present invention specification and drawings, or direct / indirect applications in other related technical fields, are included within the patent protection scope of the present invention.

Claims

1. A method for detecting installation faults in wind turbines, characterized in that, The method includes: The vibration signal of the fan duct is acquired, and the vibration characteristics are extracted based on the vibration signal; A reference space matrix is ​​constructed based on the vibration signal and the vibration characteristics; Feature optimization is performed based on the aforementioned baseline space matrix to obtain the target space matrix; Wind turbine installation faults are determined based on the target space matrix and a first set fault threshold. The step of optimizing features based on the reference space matrix to obtain the target space matrix includes: calculating the Mahalanobis distance corresponding to each row of the reference space matrix according to the reference space matrix and its covariance inverse matrix; calculating the corresponding signal-to-noise ratio (SNR) using the Mahalanobis distance in the reference space matrix; optimizing features based on the SNR of each row of the reference space matrix to select target features affecting the vibration signal; reconstructing the reference space matrix based on the target features to obtain the target space matrix; the step of optimizing features based on the SNR of each row of the reference space matrix to select target features affecting the vibration signal includes: removing each of several vibration features one by one, constructing a new reference space matrix after removing the vibration feature, obtaining the SNR of the new reference space matrix and the SNR of the original reference space matrix before removing the vibration feature; retaining the vibration feature if the SNR of the new reference space matrix is ​​less than or equal to the SNR of the original reference space matrix; removing the vibration feature if the SNR of the new reference space matrix is ​​greater than the SNR of the original reference space matrix; and determining all retained vibration features as target features affecting the vibration signal.

2. The method as described in claim 1, characterized in that, The construction of the reference space matrix based on the vibration signal and the vibration characteristics includes: An initial reference space matrix for all vibration signals is constructed based on all vibration signals and the vibration characteristics of each vibration signal. The initial reference space matrix is ​​standardized to obtain the reference space matrix.

3. The method as described in claim 1, characterized in that, The method of determining wind turbine installation faults based on the target space matrix and a first set fault threshold includes: Calculate the wind turbine performance coefficient based on the Mahalanobis distance corresponding to the target space matrix; If the fan performance coefficient is less than or equal to the first set fault threshold, it is determined that there is a fault in the fan installation. If the fan performance coefficient is greater than the first set fault threshold, the fan installation is determined to be normal.

4. The method as described in claim 1, characterized in that, Before extracting vibration features based on the vibration signal, the method further includes: Obtain the fan linear velocity; if the fan linear velocity is within a set high speed range, determine the fan installation fault based on the root mean square difference of the vibration signal; if the fan linear velocity is within a set low speed range, continue with the step of extracting vibration features based on the vibration signal.

5. The method as described in claim 4, characterized in that, The step of determining fan installation faults based on the root mean square difference of the vibration signals includes: Calculate the root mean square difference of the vibration signal of the fan duct; If the root mean square difference is greater than or equal to the second set fault threshold, it is determined that there is a fault in the installation of the fan. If the root mean square difference is less than the second set fault threshold, the fan installation is determined to be normal.

6. A wind turbine installation fault detection system, characterized in that, The system includes: The feature extraction module is used to acquire the vibration signal of the fan duct and extract vibration features based on the vibration signal; The reference space matrix module is used to construct a reference space matrix based on the fan duct vibration signal and the vibration characteristics. The baseline space optimization module is used to perform feature optimization based on the baseline space matrix to obtain the target space matrix. The fault diagnosis module is used to diagnose wind turbine installation faults based on the target space matrix and a first set fault threshold. The reference space optimization module is specifically used for: calculating the Mahalanobis distance corresponding to each row of the reference space matrix based on the reference space matrix and the covariance inverse matrix of the reference space matrix; calculating the corresponding signal-to-noise ratio (SNR) using the Mahalanobis distance in the reference space matrix; performing feature optimization based on the SNR of each row of the reference space matrix to filter out target features affecting the vibration signal; reconstructing the reference space matrix based on the target features to obtain the target space matrix; the step of performing feature optimization based on the SNR of each row of the reference space matrix to filter out target features affecting the vibration signal includes: removing each of several vibration features one by one, constructing a new reference space matrix after removing the vibration feature, obtaining the SNR of the new reference space matrix and the SNR of the original reference space matrix before removing the vibration feature; retaining the vibration feature if the SNR of the new reference space matrix is ​​less than or equal to the SNR of the original reference space matrix; removing the vibration feature if the SNR of the new reference space matrix is ​​greater than the SNR of the original reference space matrix; and determining all retained vibration features as target features affecting the vibration signal.

7. An electronic 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 method as claimed in any one of claims 1-5.

8. A computer-readable storage medium, characterized in that, It stores computer-readable instructions that can be executed by a processor to implement the method as described in any one of claims 1-5.

Images