Method and device for monitoring cracks in wind turbine pitch bearings based on acoustic emission technology

Abstract

The embodiments of the present application provide a method, device, equipment and computer-readable storage medium for monitoring cracks in wind turbine pitch bearings based on acoustic emission technology. The method includes acquiring an acoustic emission signal of a pitch bearing; analyzing the acoustic emission signal to determine crack trend parameters of the pitch bearing; comparing the crack trend parameters with the crack opening state threshold determined by the acoustic emission signal; and determining the current state of the pitch bearing based on the comparison result. In this way, the problems of low reliability and low efficiency of existing crack monitoring methods are solved, and the monitoring accuracy of pitch bearing cracks is greatly improved.

Description

Technical Field

[0001] Embodiments of the present application relate to the field of wind turbine pitch bearing crack monitoring, and in particular, to a method, device, equipment, and computer-readable storage medium for monitoring wind turbine pitch bearing cracks based on acoustic emission technology. Background Art

[0002] As the core component of wind turbines, pitch bearings are the key to achieve pitch action. They have harsh working environment, frequent start and stop, large torque transmission and high transmission ratio. Since the common working rotation range of pitch bearings is 0-90°, the rolling element does not roll along the entire raceway, but moves in a certain area. Therefore, the bearing range of its ring is relatively fixed and prone to overload. Therefore, ring cracking failure is prone to occur in the bearing area of ​​the pitch bearing.

[0003] Most existing methods for monitoring pitch bearing faults are video detection methods. However, due to environmental factors, the video monitoring area is often blocked by oil and dirt, and the pitch bearing cannot be directly monitored on wind turbines with reinforcement rings, so the reliability of the monitoring results is not high. In addition, existing monitoring technologies such as video, tin foil, and conductive paint can only detect cracks after they extend to the surface of the pitch bearing, which is inefficient. Summary of the invention

[0004] According to an embodiment of the present application, a solution for monitoring cracks in wind turbine pitch bearings based on acoustic emission technology is provided, which can solve the problems of low reliability and low efficiency of existing crack monitoring methods and greatly improve the monitoring accuracy of pitch bearing cracks.

[0005] In a first aspect of the present application, a method for monitoring cracks in a wind turbine pitch bearing based on acoustic emission technology is provided. The method comprises:

[0006] Obtain the acoustic emission signal of the pitch bearing;

[0007] Analyzing the acoustic emission signal to determine crack trend parameters of the pitch bearing;

[0008] Comparing the crack trend parameter with a crack opening state threshold determined by the acoustic emission signal;

[0009] According to the comparison results, the current state of the pitch bearing is determined.

[0010] Furthermore, it also includes:

[0011] The acoustic emission signal is cleaned to obtain a clean acoustic emission signal.

[0012] Furthermore, the cleaning of the acoustic emission signal to obtain a clean acoustic emission signal includes:

[0013] The acoustic emission signal is subjected to time domain impact parameter filtering to obtain a clean acoustic emission signal.

[0014] Furthermore, the step of cleaning the acoustic emission signal to obtain a clean acoustic emission signal further comprises:

[0015] The acoustic emission signal is filtered by a preset threshold function to obtain a clean acoustic emission signal; the threshold function includes a soft threshold function and a hard threshold function;

[0016] Wherein, the soft threshold function is:

[0017]

[0018] The hard threshold function is:

[0019]

[0020] Among them, x j (i) is the i-th coefficient of the j-th layer wavelet decomposition component;

[0021] x′ j (i) is the i-th coefficient of the j-th layer wavelet decomposition component after denoising;

[0022] thr(j) is the threshold estimate value obtained by the threshold determination criterion at the jth layer.

[0023] Further, analyzing the impact signal to determine the crack trend parameter of the pitch bearing includes:

[0024] Extracting features of the acoustic emission signal; the features include rise time, count, energy, duration, amplitude, ASL, RMS, absolute energy, etc. and frequency domain spectrum shape and / or frequency band energy;

[0025] Combine the extracted features to obtain a feature vector;

[0026] Performing standardization on the feature vector;

[0027] Cluster analysis is performed on the standardized eigenvectors to obtain the crack trend parameters of the pitch bearing.

[0028] Furthermore, the crack trend parameters of the pitch bearing obtained by clustering the standardized feature vectors include:

[0029] The crack trend parameters of the pitch bearing are obtained by analyzing the standardized eigenvectors in the following way:

[0030]

[0031] Among them, S is the silhouette coefficient, and its value range is [-1,1];

[0032] a i It represents the average distance between a sample i and other cluster samples;

[0033] b i Represents the average distance between a sample i and other samples in its cluster;

[0034] N is the total number of samples; and / or

[0035]

[0036] Among them, k represents the number of clusters;

[0037] C i represents the i-th cluster;

[0038] μ i represents the i-th cluster center;

[0039] x represents a data point.

[0040] Furthermore, the crack opening state threshold is determined by:

[0041] The acoustic emission signal is processed by the principal component analysis method in SPSS to obtain the weight of the primary index;

[0042] Based on the weight of the first-level indicator, the weight of the second-level indicator is calculated by the entropy method;

[0043] Based on the weight of the primary index and the weight of the secondary index, a crack opening state threshold is determined.

[0044] In a second aspect of the present application, a device for monitoring cracks in a wind turbine pitch bearing based on acoustic emission technology is provided. The device comprises:

[0045] An acquisition module, used for acquiring an acoustic emission signal of a pitch bearing;

[0046] A determination module, used to analyze the acoustic emission signal to determine crack trend parameters of the pitch bearing;

[0047] A comparison module, used for comparing the crack trend parameter with a crack opening state threshold determined by the acoustic emission signal;

[0048] The monitoring module is used to determine the current state of the variable pitch bearing according to the comparison result.

[0049] In a third aspect of the present application, an electronic device is provided, which includes a memory and a processor, wherein a computer program is stored in the memory, and when the processor executes the program, the method described above is implemented.

[0050] In a fourth aspect of the present application, a computer-readable storage medium is provided, on which a computer program is stored, and when the program is executed by a processor, the method according to the first aspect of the present application is implemented.

[0051] The method for monitoring cracks in a wind turbine pitch bearing based on acoustic emission technology provided in an embodiment of the present application obtains an acoustic emission signal of the pitch bearing; analyzes the impact signal to determine crack trend parameters of the pitch bearing; compares the crack trend parameters with a crack opening state threshold determined by the acoustic emission signal; and determines the current state of the pitch bearing based on the comparison result, thereby solving the problems of low reliability and low efficiency of existing crack monitoring methods and greatly improving the monitoring accuracy of pitch bearing cracks.

[0052] It should be understood that the contents described in the Summary of the Invention are not intended to limit the key or important features of the embodiments of the present application, nor are they intended to limit the scope of the present application. Other features of the present application will become easily understood through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0053] The above and other features, advantages and aspects of the embodiments of the present application will become more apparent with reference to the following detailed description in conjunction with the accompanying drawings. In the accompanying drawings, the same or similar reference numerals represent the same or similar elements, wherein:

[0054] Figure 1 It is a flow chart of a method for monitoring cracks in a wind turbine pitch bearing based on acoustic emission technology according to an embodiment of the present application;

[0055] Figure 2 is a flow chart of cluster analysis according to an embodiment of the present application;

[0056] Figure 3 A block diagram of a device for monitoring cracks in a wind turbine pitch bearing based on acoustic emission technology according to an embodiment of the present application;

[0057] Figure 4 It is a schematic diagram of the structure of a terminal device or a server suitable for implementing the embodiments of the present application. DETAILED DESCRIPTION

[0058] In order to make the purpose, technical solution and advantages of the embodiments of the present disclosure clearer, the technical solution in the embodiments of the present disclosure will be clearly and completely described below in conjunction with the drawings in the embodiments of the present disclosure. Obviously, the described embodiments are part of the embodiments of the present disclosure, not all of the embodiments. Based on the embodiments in the present disclosure, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present disclosure.

[0059] In addition, the term "and / or" in this article is only a description of the association relationship between the associated objects, indicating that there can 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. In addition, the character " / " in this article generally indicates that the associated objects before and after are in an "or" relationship.

[0060] Figure 1 A flow chart of a method for monitoring cracks in a wind turbine pitch bearing based on acoustic emission technology according to an embodiment of the present disclosure is shown. The method comprises:

[0061] S110, acquiring an acoustic emission signal of a pitch bearing.

[0062] In some embodiments, the pitch bearing may be monitored and data collected by pre-configured acoustic emission sensors and equipment to obtain acoustic emission signals;

[0063] Furthermore, the acquired acoustic emission signal includes an impact signal and a continuous waveform signal of the pitch bearing, that is, the acoustic emission signal contains time domain and frequency domain information.

[0064] Specifically,

[0065] 1. Prepare sensors and data acquisition systems: Select appropriate sensors and data acquisition systems to obtain acoustic emission signals. Piezoelectric sensors can be used as sensors.

[0066] 2. Install the sensor: Install the sensor on the object to be measured. The location and number of sensors can be pre-set according to the actual application scenario to ensure that accurate acoustic emission signals can be obtained.

[0067] 3. Calibrate the sensor: Calibrate the sensor to ensure that its measurement results are accurate and reliable. The calibration process includes sensitivity calibration, frequency response calibration, etc.

[0068] 4. Set up the data acquisition system: Set up the data acquisition system as needed, including sampling rate, filter and other parameters. The selection of the above parameters will depend on the characteristics of the object being measured and the required signal resolution.

[0069] 5. Start data acquisition: Start the data acquisition system and begin collecting acoustic emission signals and continuous waveform data.

[0070] 6. Data recording and storage: The collected data should be recorded and properly stored and backed up. That is, the data can be stored on a computer, data collector or other storage medium for subsequent analysis and processing.

[0071] S120, analyzing the impact signal to determine crack trend parameters of the pitch bearing.

[0072] In some embodiments, due to the diversity and complexity of environmental factors, the acoustic emission signal obtained by step S110 usually has a lot of interference. Therefore, in the disclosure, for the accuracy of the result, the acoustic emission signal obtained by step S110 needs to be cleaned (pre-processed) to remove the attenuation and refraction signals in the signal and obtain a signal that meets the preset standard, that is, to obtain a clean acoustic emission signal.

[0073] Specifically, the collected acoustic emission signals may be processed using signal filtering technology.

[0074] In the time domain, filtering methods of time domain impact parameters can be used, such as using sliding windows and thresholds to exclude interference signals not caused by cracks.

[0075] In the frequency domain, the following method can be used to remove the interference signal in the signal:

[0076] Select appropriate wavelet basis and wavelet decomposition layers to perform wavelet decomposition on the signal. The number of decomposition layers is generally 3-5;

[0077] A threshold is set for the coefficients of each layer after decomposition, and the coefficients greater than and less than the threshold are processed respectively by the threshold function, and finally the original signal is reconstructed using the processed wavelet coefficients to obtain a denoised signal; the threshold function includes a soft threshold function and a hard threshold function;

[0078] Wherein, the soft threshold function is:

[0079]

[0080] The hard threshold function is:

[0081]

[0082] Among them, x j (i) is the i-th coefficient of the j-th layer wavelet decomposition component;

[0083] x′ j (i) is the i-th coefficient of the j-th layer wavelet decomposition component after denoising;

[0084] thr(j) is the threshold estimation value obtained by the threshold determination criteria of the jth layer. The threshold determination criteria include fixed Stein unbiased estimation, adaptive Stein unbiased estimation, maximum and minimum criteria, and fixed threshold criteria;

[0085] The threshold value may be determined in the following manner:

[0086] The selection of threshold plays a decisive role in the above-mentioned noise reduction process. When the wavelet coefficient after wavelet decomposition is less than the preset threshold, it is considered that the wavelet coefficient is mainly caused by noise and should be set to zero; when the wavelet coefficient is greater than the preset threshold, it is considered that the wavelet coefficient is mainly caused by the signal. The following methods can usually be used to select the threshold: soft threshold estimation of unbiased likelihood estimation, universal threshold, heuristic threshold, minimum maximum variance threshold, etc.

[0087] In summary, by filtering the time domain and frequency domain signals of the acoustic emission signal, the interference and noise can be effectively removed and the characteristics of the crack signal can be highlighted.

[0088] In some embodiments, feature extraction and classification are performed on the filtered signal (clean acoustic emission signal) to determine crack trend parameters of the pitch bearing.

[0089] Specifically, features are extracted from the filtered impact signal to describe the change pattern of the signal. Common features include rise time, count, energy, duration, amplitude, ASL, RMS, absolute energy, etc., and frequency domain spectrum shape, band energy, etc. These features are combined into a feature vector, each of which represents a sample. The above parameters provide information about the intensity, persistence and shape of the acoustic emission signal.

[0090] Furthermore, the feature vectors are standardized. Standardization can make different features have the same scale and importance, and avoid some features from having too much influence on the principal component dimensionality reduction and clustering results. The steps are as follows:

[0091] Calculate the mean and standard deviation of each feature;

[0092] For each feature, subtract the mean from the original value and then divide it by the standard deviation to get the standardized value;

[0093] The standardized values ​​will have zero mean and unit variance, as shown below:

[0094]

[0095] Furthermore, cluster analysis is performed to group similar data points into clusters to facilitate data classification and analysis. Figure 2As shown in the figure, the K-Means clustering algorithm can be used to cluster the acoustic emission signals generated in the process, so as to find the change law of the variable pitch bearing in the acoustic emission characteristic parameter data set. The K-Means clustering algorithm is the most commonly used algorithm based on the partitioning method proposed by Mac Queen, which has the advantages of fast calculation speed, strong scalability, simple ideas and high efficiency.

[0096] Furthermore, the optimal number of categories can be determined by using the Silhouette coefficient and / or the Elbow Method;

[0097] Among them, the silhouette coefficient is an evaluation index based on the distance within and between clusters, which aims to measure the compactness and separation of clustering results. Its calculation formula is as follows:

[0098]

[0099] Among them, S is the silhouette coefficient, and its value range is [-1,1]. The closer it is to 1, the better the clustering effect is, and the closer it is to -1, the worse the clustering effect is.

[0100] a i It represents the average distance between a sample i and other cluster samples;

[0101] b i Represents the average distance between a sample i and other samples in its cluster;

[0102] N represents the total number of samples.

[0103] The basic idea of ​​the elbow criterion is to calculate the corresponding sum of squares of clustering errors SSE for different cluster numbers k, and use SSE as an evaluation indicator. The SSE calculation formula is as follows:

[0104]

[0105] Among them, k represents the number of clusters;

[0106] C i represents the i-th cluster;

[0107] μ i represents the i-th cluster center;

[0108] x represents a data point;

[0109] Through the above formula, the point where the "elbow bend" appears on the SSE curve is found, and the number of clusters corresponding to this point is the optimal number of clusters, that is, the crack trend parameter of the variable pitch bearing.

[0110] S130, comparing the crack trend parameter with a crack opening state threshold determined by the acoustic emission signal.

[0111] In some embodiments, the crack initiation state threshold may be determined as follows:

[0112] The acoustic emission signal (clean acoustic emission signal) is processed by the principal component analysis method in SPSS to obtain the weight of the primary index;

[0113] Based on the weight of the first-level indicator, the weight of the second-level indicator is calculated by the entropy method;

[0114] Based on the weight of the primary index and the weight of the secondary index, a crack opening state threshold is determined.

[0115] Specifically, the SPSS principal component analysis process includes:

[0116] Step 1: Determine whether to conduct principal component analysis (PCA); the judgment standard is that the KMO value is greater than 0.6.

[0117] Step 2: Determine the corresponding relationship between the principal component and the analysis item:

[0118] Assume that there are 3 principal components and 10 analysis items. The intersection of the principal components and the analysis items gives a total of 30 numbers, which are called "load coefficients" (the load coefficient value indicates the degree of correlation between the analysis item and the principal component). For each principal component, there are 10 "load coefficients" and for each analysis item, there are 3 "load coefficient values" (such as 0.765, -0.066, 0.093). Select 3 numbers with an absolute value greater than 0.4 (0.765). If it corresponds to principal component 1, it means that this analysis item should be classified under principal component 1.

[0119] Deleting unreasonable analysis items usually includes the following three situations:

[0120] Category 1: If the commonality (common factor variance) value of the analysis item is less than 0.4, the corresponding analysis item should be deleted;

[0121] Category 2: If the absolute values ​​of the "load coefficient" corresponding to a certain analysis item are all less than 0.4, then delete this analysis item;

[0122] Category 3: If there is a serious deviation between the correspondence between an analysis item and the principal component (often referred to as "putting the wrong hat on the head"), the analysis item will be deleted.

[0123] Step 3: Principal component naming

[0124] In the second step, after deleting unreasonable analysis items and confirming that the correspondence between the principal component and the analysis item is good, the principal component can be named based on the correspondence between the principal component and the analysis item.

[0125] SPSS entropy analysis process:

[0126] The information carried by entropy is used to calculate the weight. Combined with the degree of variation of each indicator, the information entropy tool is used to calculate the weight of each indicator, providing a basis for the comprehensive evaluation of multiple indicators.

[0127] Step 1: The acoustic emission signal can be processed in a positive, negative, or inverse manner as needed.

[0128] Step 2: Analyze the processed data using entropy method.

[0129] In the present disclosure, the above two methods (SPSS principal component analysis and SPSS entropy analysis) can be used in combination. Since the data is divided into two working conditions, faulty and non-faulty, the two working conditions are analyzed separately:

[0130] First, SPSS principal component analysis is used to classify the data into one dimension, and the KMO and Bartlett values ​​are analyzed to confirm whether principal component analysis is suitable. Then, the weight of the classification factor is obtained based on the variance explanation rate column in the variance explanation rate table and the last accumulated value.

[0131] Then, the factors obtained after principal component analysis are analyzed separately using the SPSS entropy method. Each factor will get a summary table of entropy method weight calculation results, in which the weight coefficient is the weight corresponding to the sub-factors contained in a factor. The above operation is performed on each factor to obtain the weights of all required sub-factors.

[0132] Finally, the one-dimensional index (factor) and the two-dimensional index (sub-factor) are weighted:

[0133]

[0134] Get the value range of the crack opening state threshold (the upper and lower limits of the data domain value).

[0135] Furthermore, the crack trend parameter of the pitch bearing is compared with the crack opening state threshold.

[0136] S140: Determine the current state of the pitch bearing according to the comparison result.

[0137] In some embodiments, the state of the current variable pitch bearing is determined based on the comparison result. If the crack trend parameter of the variable pitch bearing is not in the crack opening state threshold interval, the current state of the variable pitch bearing can be determined to be "dangerous", that is, maintenance is required, and the current variable pitch bearing has cracks; otherwise, the current state of the variable pitch bearing can be determined to be "normal".

[0138] According to the embodiments of the present disclosure, the following technical effects are achieved:

[0139] The problem of low reliability and low efficiency of existing crack monitoring methods is solved, and the monitoring accuracy of pitch bearing cracks is greatly improved.

[0140] It should be noted that, for the aforementioned method embodiments, for the sake of simplicity, they are all expressed as a series of action combinations, but those skilled in the art should be aware that the present application is not limited by the described order of actions, because according to the present application, certain steps can be performed in other orders or simultaneously. Secondly, those skilled in the art should also be aware that the embodiments described in the specification are all optional embodiments, and the actions and modules involved are not necessarily required by the present application.

[0141] The above is an introduction to the method embodiment. The following is a further explanation of the scheme described in this application through an apparatus embodiment.

[0142] Figure 3 FIG. 3 shows a device 300 for monitoring cracks in a wind turbine pitch bearing based on acoustic emission technology according to an embodiment of the present application, as shown in FIG. Figure 3 Shown include:

[0143] An acquisition module 310 is used to acquire an acoustic emission signal of a pitch bearing;

[0144] A determination module 320 is used to analyze the acoustic emission signal to determine crack trend parameters of the pitch bearing;

[0145] A comparison module 330, for comparing the crack trend parameter with a crack opening state threshold determined by an acoustic emission signal;

[0146] The monitoring module 340 is used to determine the current state of the variable pitch bearing according to the comparison result.

[0147] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working process of the described module can refer to the corresponding process in the aforementioned method embodiment, and will not be repeated here.

[0148] Figure 4 A schematic diagram of the structure of a terminal device or server suitable for implementing an embodiment of the present application is shown.

[0149] like Figure 4 As shown, the terminal device or server includes a central processing unit (CPU) 401, which can perform various appropriate actions and processes according to the program stored in the read-only memory (ROM) 402 or the program loaded from the storage part 408 to the random access memory (RAM) 403. In RAM403, various programs and data required for the operation of the terminal device or server are also stored. CPU401, ROM402 and RAM403 are connected to each other through a bus 404. An input / output (I / O) interface 405 is also connected to the bus 404.

[0150] The following components are connected to the I / O interface 405: an input section 406 including a keyboard, a mouse, etc.; an output section 407 including a cathode ray tube (CRT), a liquid crystal display (LCD), etc., and a speaker, etc.; a storage section 408 including a hard disk, etc.; and a communication section 409 including a network interface card such as a LAN card, a modem, etc. The communication section 409 performs communication processing via a network such as the Internet. A drive 410 is also connected to the I / O interface 405 as needed. A removable medium 411, such as a magnetic disk, an optical disk, a magneto-optical disk, a semiconductor memory, etc., is installed on the drive 410 as needed, so that a computer program read therefrom is installed into the storage section 408 as needed.

[0151] In particular, according to an embodiment of the present application, the above method flow steps can be implemented as a computer software program. For example, an embodiment of the present application includes a computer program product, which includes a computer program carried on a machine-readable medium, and the computer program includes a program code for executing the method shown in the flow chart. In such an embodiment, the computer program can be downloaded and installed from the network through the communication part 409, and / or installed from the removable medium 411. When the computer program is executed by the central processing unit (CPU) 401, the above-mentioned functions defined in the system of the present application are executed.

[0152] It should be noted that the computer-readable medium shown in the present application may be a computer-readable signal medium or a computer-readable storage medium or any combination of the above two. The computer-readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or device, or any combination of the above. More specific examples of computer-readable storage media may include, but are not limited to: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In the present application, a computer-readable storage medium may be any tangible medium containing or storing a program that can be used by or in combination with an instruction execution system, device or device. In the present application, a computer-readable signal medium may include a data signal propagated in a baseband or as part of a carrier wave, which carries a computer-readable program code. This propagated data signal may take a variety of forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the above. Computer-readable signal media may also be any computer-readable medium other than computer-readable storage media, which may send, propagate or transmit a program for use by or in conjunction with an instruction execution system, apparatus or device. The program code contained on the computer-readable medium may be transmitted using any appropriate medium, including but not limited to: wireless, wire, optical cable, RF, etc., or any suitable combination of the above.

[0153] The flow chart and block diagram in the accompanying drawings illustrate the possible architecture, function and operation of the system, method and computer program product according to various embodiments of the present application. In this regard, each box in the flow chart or block diagram can represent a module, a program segment or a part of the code, and the aforementioned module, program segment or a part of the code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the box can also occur in a different order from the order marked in the accompanying drawings. For example, two boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each box in the block diagram and / or flow chart, and the combination of the boxes in the block diagram and / or flow chart can be implemented with a dedicated hardware-based system that performs the specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions.

[0154] The units or modules involved in the embodiments described in the present application may be implemented by software or hardware. The units or modules described may also be arranged in a processor. The names of these units or modules do not, in some cases, constitute limitations on the units or modules themselves.

[0155] As another aspect, the present application further provides a computer-readable storage medium, which may be included in the electronic device described in the above embodiment; or may exist independently without being assembled into the electronic device. The above computer-readable storage medium stores one or more programs, and when the above programs are used by one or more processors to execute the method described in the present application.

[0156] The above description is only a preferred embodiment of the present application and an explanation of the technical principles used. Those skilled in the art should understand that the scope of application involved in the present application is not limited to the technical solution formed by a specific combination of the above technical features, but should also cover other technical solutions formed by any combination of the above technical features or their equivalent features without departing from the aforementioned application concept. For example, the above features are replaced with (but not limited to) technical features with similar functions applied in the present application.

Claims

1. A method for monitoring cracks in wind turbine pitch bearings based on acoustic emission technology, characterized in that: include: Obtain the acoustic emission signal of the pitch bearing; The acoustic emission signal is analyzed to determine crack trend parameters of the pitch bearing, including: Extracting features from the acoustic emission signal; the features include rise time, count, energy, duration, amplitude, ASL, RMS, absolute energy and frequency domain spectrum shape and / or frequency band energy; Combine the extracted features to obtain a feature vector; Performing standardization on the feature vector; Cluster analysis is performed on the standardized feature vectors to obtain the crack trend parameters of the pitch bearing, including: The crack trend parameters of the pitch bearing are obtained by clustering the standardized feature vectors in the following way: Among them, S is the silhouette coefficient, and its value range is [-1,1]; Represents the average distance between a sample i and other cluster samples; Represents the average distance between a sample i and other samples in its cluster; N is the total number of samples; and / or Among them, k represents the number of clusters; represents the i-th cluster; represents the i-th cluster center; Representing a data point; comparing the crack trend parameter with a crack opening state threshold determined by the acoustic emission signal; According to the comparison result, the current state of the variable pitch bearing is determined; The crack opening state threshold is determined in the following manner: The acoustic emission signal is processed by the principal component analysis method in SPSS to obtain the weight of the primary index; Based on the weight of the first-level indicator, the weight of the second-level indicator is calculated by the entropy method; Based on the weight of the primary index and the weight of the secondary index, a crack opening state threshold is determined.

2. The method according to claim 1, characterized in that Also includes: The acoustic emission signal is cleaned to obtain a clean acoustic emission signal.

3. The method according to claim 2, characterized in that The step of cleaning the acoustic emission signal to obtain a clean acoustic emission signal comprises: The acoustic emission signal is subjected to time domain impact parameter filtering to obtain a clean acoustic emission signal.

4. The method according to claim 3, characterized in that The step of cleaning the acoustic emission signal to obtain a clean acoustic emission signal further comprises: The acoustic emission signal is filtered by a preset threshold function to obtain a clean acoustic emission signal; the threshold function includes a soft threshold function and a hard threshold function; Wherein, the soft threshold function is: The hard threshold function is: in, The jth layer wavelet decomposition component is coefficients; After denoising, The wavelet decomposition component coefficients; For The threshold estimate resulting from the thresholding criterion.

5. A device for monitoring cracks in wind turbine pitch bearings based on acoustic emission technology, characterized in that: include: An acquisition module, used for acquiring an acoustic emission signal of a pitch bearing; A determination module is used to analyze the acoustic emission signal to determine the crack trend parameters of the pitch bearing, including: Extracting features from the acoustic emission signal; the features include rise time, count, energy, duration, amplitude, ASL, RMS, absolute energy and frequency domain spectrum shape and / or frequency band energy; Combine the extracted features to obtain a feature vector; Performing standardization on the feature vector; Cluster analysis is performed on the standardized feature vectors to obtain the crack trend parameters of the pitch bearing, including: The crack trend parameters of the pitch bearing are obtained by clustering the standardized feature vectors in the following way: Among them, S is the silhouette coefficient, and its value range is [-1,1]; Represents the average distance between a sample i and other cluster samples; Represents the average distance between a sample i and other samples in its cluster; N is the total number of samples; and / or Among them, k represents the number of clusters; represents the i-th cluster; represents the i-th cluster center; represents a data point; A comparison module, used for comparing the crack trend parameter with a crack opening state threshold determined by the acoustic emission signal; A monitoring module is used to determine the current state of the variable pitch bearing according to the comparison result; The crack opening state threshold is determined in the following manner: The acoustic emission signal is processed by the principal component analysis method in SPSS to obtain the weight of the primary index; Based on the weight of the first-level indicator, the weight of the second-level indicator is calculated by the entropy method; Based on the weight of the primary index and the weight of the secondary index, a crack opening state threshold is determined.

6. An electronic device comprising a memory and a processor, wherein a computer program is stored in the memory, wherein: When the processor executes the computer program, the method according to any one of claims 1 to 4 is implemented.

7. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the method according to any one of claims 1 to 4 is implemented.

Images