Wind turbine bearing state evaluation method and system based on sound energy flow deviation index

Abstract

The invention provides a fan bearing state evaluation method and system based on a sound energy flow deviation index. The method comprises the following steps: acquiring a plurality of sound signals under the stable operation of a normal fan bearing as reference samples; acquiring a sound signal under the stable operation of the current fan bearing as an evaluation sample; calculating the wavelet packet energy flow of each reference sample and the wavelet packet energy flow of each evaluation sample; calculating a wavelet packet energy flow deviation degree reference value of the wavelet packet energy flow of each reference sample in pairs, and selecting a maximum reference value of the wavelet packet energy flow deviation degree; calculating the wavelet packet energy flow deviation degree between the wavelet packet energy flow of the evaluation sample and the wavelet packet energy flow of any reference sample; if the wavelet packet energy flow deviation degree is larger than the maximum reference value of the wavelet packet energy flow deviation degree, the fan bearing is abnormal, and otherwise, the fan bearing is normal. The method has the characteristics of high evaluation speed and high accuracy.

Description

Technical Field

[0001] The invention relates to the field of civil engineering, and in particular to a method and system for evaluating the state of a fan bearing based on a sound energy flow deviation index. Background Art

[0002] Fans are one of the most common equipment in industrial production, and their failure may have a serious impact on production efficiency and safety. Common types of fan failures include bearing wear, blade damage, motor failure, fan imbalance, etc. These failures may cause vibration, increased noise, increased energy consumption, etc. during fan operation. In severe cases, they may cause equipment shutdown, damage to peripheral equipment, or personal injury. Therefore, timely detection and prevention of fan failures are crucial to ensure the normal operation of production equipment.

[0003] At present, the safety management of fans mainly relies on regular maintenance. The use of fans is judged by inspecting and repairing various parts of the fans, which is prone to blind maintenance and waste of resources. The fan bearing is the heart of the fan, and its normal operation is the guarantee of the entire production safety and production efficiency. According to relevant statistics: up to 40% of fan failures are caused by bearings. Therefore, the evaluation of the fan bearing status is conducive to the prediction of fan failures. Among them, the more commonly used fan bearing status evaluation is mainly to use vibration signals for fault diagnosis. However, the traditional vibration signal fault diagnosis method has the disadvantage that the vibration signal is limited by the measurement method, and sometimes it is impossible to extract effective information, so it is impossible to accurately evaluate the fan bearing status. Summary of the invention

[0004] In order to overcome the defects existing in the above-mentioned prior art, the purpose of the present invention is to provide a method and system for evaluating the state of a fan bearing based on a sound energy flow deviation index.

[0005] In order to achieve the above-mentioned object of the present invention, the present invention provides a method for evaluating the state of a fan bearing based on a sound energy flow deviation index, characterized in that it comprises the following steps:

[0006] Obtain multiple sound signals of normal fan bearings in stable operation as reference samples;

[0007] Acquire the sound signal of the current fan bearing under stable operation as an evaluation sample;

[0008] Calculate the wavelet packet energy flow of each reference sample and the wavelet packet energy flow of the evaluation sample;

[0009] The wavelet packet energy flow deviation reference values ​​of each reference sample are calculated pairwise, and the maximum reference value of the wavelet packet energy flow deviation is selected;

[0010] Calculate the wavelet packet energy flow deviation between the wavelet packet energy flow of the evaluation sample and the wavelet packet energy flow of any reference sample;

[0011] If the wavelet packet energy flow deviation is greater than the maximum reference value of the wavelet packet energy flow deviation, the fan bearing is abnormal, otherwise the fan bearing is normal.

[0012] This method extracts the wavelet packet energy flow characteristics of the fan bearing sound signal and analyzes its energy flow deviation, thereby realizing the state assessment of the fan bearing, which has the characteristics of high assessment speed and accuracy.

[0013] In an optional solution of the method for evaluating the state of a fan bearing based on a sound energy flow deviation index, an original array signal of the sound of the fan bearing under stable operation is obtained, and the original array signal is beamformed to obtain the sound signal.

[0014] Since the fan bearing sound signal is collected in a closed laboratory, the original array signal contains severe reverberation and echo. This optional solution can effectively remove the reverberation and echo to obtain a purer and more accurate fan bearing sound signal, providing more accurate data support for fan bearing abnormality judgment.

[0015] In an optional solution of the wind turbine bearing condition assessment method based on the sound energy flow deviation index, the step of calculating the wavelet packet energy flow of the sound signal is:

[0016] Perform wavelet packet decomposition on the sound signal to obtain wavelet packet decomposition coefficients;

[0017] Reconstruct the wavelet packet energy feature vector with the same length as the sound signal based on the wavelet packet decomposition coefficients;

[0018] The wavelet packet energy eigenvector is transformed into a new wavelet packet phase space to obtain the wavelet packet energy flow of the sound signal. During the transformation, the time delay is equal to the embedding dimension.

[0019] In an optional solution of the wind turbine bearing state assessment method based on the sound energy flow deviation index, the wavelet packet energy eigenvector is in Refers to the nth reconstruction coefficient of the pth wavelet packet node in the i-th layer, n refers to the ordinal number of the reconstruction coefficient of the pth wavelet packet node in the i-th layer, and N is the length of the sound signal;

[0020] The wavelet packet energy flow of the sound signal is

[0021] In an optional solution of the fan bearing state assessment method based on the sound energy flow deviation index, the calculation formula of the wavelet packet energy flow deviation is:

[0022]

[0023] Among them, WPI A is the wavelet packet energy flow of a sound signal, WPI B is the wavelet packet energy flow of another sound signal.

[0024] The present invention also proposes a fan bearing state assessment system, comprising a processing module, a storage module and an array sensing module for acquiring a fan bearing sound signal;

[0025] The array sensing module is communicatively connected to the processing module and sends the acquired fan bearing sound signal to the processing module. The processing module is communicatively connected to the storage module, and the storage module is used to store at least one executable instruction. The executable instruction enables the processing module to perform operations corresponding to the above-mentioned fan bearing state assessment method based on the sound energy flow deviation index according to the fan bearing sound signal, so as to assess the fan bearing state.

[0026] Optionally, the array sensing module includes a microphone array placed near the fan for receiving the fan bearing sound signal, the fan bearing sound obtained is a multi-channel signal, and the microphone array also buffers, amplifies, low-pass filters and A / D converts the received fan bearing sound signal;

[0027] It also includes a signal synchronization set device composed of an array driver board and a development board for synchronously receiving multi-channel signals; the signal synchronization set device is communicatively connected to the processing module to send multi-channel fan bearing sound signals to the processing module.

[0028] Optionally, the processing module performs beamforming on the multi-channel fan bearing sound signal to obtain a single-channel fan bearing sound signal, and the processing module evaluates the fan bearing state based on the single-channel fan bearing sound signal.

[0029] The beneficial effects of the present invention are:

[0030] The present invention uses array sound signals, which have a certain effect of noise reduction and reverberation removal, and the signal obtained after wavelet packet reconstruction can also achieve filtering and noise reduction, so that the signal-to-noise ratio of the sound signal is increased, providing a reliable data source for the subsequent construction of wavelet packet energy flow; by analyzing the deviation of wavelet packet energy flow, the fan state is recognized.

[0031] This invention makes up for the shortcomings of traditional vibration signal fault diagnosis methods. Combined with the non-contact detection of acoustic signals, it has the advantages of easy signal collection and easy detection of early faults.

[0032] Additional aspects and advantages of the present invention will be given in part in the following description and in part will be obvious from the following description, or will be learned through practice of the present invention. BRIEF DESCRIPTION OF THE DRAWINGS

[0033] The above and / or additional aspects and advantages of the present invention will become apparent and easily understood from the description of the embodiments in conjunction with the following drawings, in which:

[0034] Figure 1 It is a schematic diagram of the process of embodiment 1;

[0035] Figure 2 It is a schematic diagram of a binary decomposition tree;

[0036] Figure 3 This is a schematic diagram of the principle structure of the array sensing module. DETAILED DESCRIPTION

[0037] Embodiments of the present invention are described in detail below, examples of which are shown in the accompanying drawings, wherein the same or similar reference numerals throughout represent the same or similar elements or elements having the same or similar functions. The embodiments described below with reference to the accompanying drawings are exemplary and are only used to explain the present invention, and cannot be understood as limiting the present invention.

[0038] In the description of the present invention, unless otherwise specified and limited, it should be noted that the terms "installed", "connected" and "connected" should be understood in a broad sense. For example, it can be a mechanical connection or an electrical connection, or it can be the internal connection between two components. It can be a direct connection or an indirect connection through an intermediate medium. For ordinary technicians in this field, the specific meanings of the above terms can be understood according to the specific circumstances.

[0039] Embodiment 1

[0040] like Figure 1 As shown, the present invention provides a method for evaluating the state of a fan bearing based on a sound energy flow deviation index, comprising the following steps:

[0041] Acquire multiple sound signals under normal stable operation of fan bearings as reference samples. The reference samples can be obtained from the database or directly collected. When directly collected, the same acquisition method as the evaluation sample can be used. Assume that there are λ reference samples, namely Data-1~Data-λ, and each reference sample contains m data points, for example: Data-λ=(x1,x2,……,xm), xm refers to the mth data point.

[0042] The sound signal of the current fan bearing under stable operation is obtained as an evaluation sample, which is recorded as Data-r and includes m data points. In this embodiment, the evaluation sample is obtained by setting an array sensing module. Specifically, Figure 3 As shown, the array sensing module includes a microphone array, an array driver board and a development board. The microphone array includes a microphone module and an array base plate. The microphone array is placed next to the fan on one side of the motor to receive the fan bearing sound signal, and at the same time, the received signal is buffered, amplified, low-pass filtered and A / D converted. The received signal is pre-processed; the array driver board and the development board together constitute a signal synchronization device, which is used to synchronously receive multi-channel signals to ensure the accuracy of the phase of each channel, and transmit the data to the host computer or processing module through the network cable to provide raw array data for data processing and fault diagnosis.

[0043] Since the fan bearing sound signal is collected in a closed laboratory, the original array signal contains severe reverberation and echo. Therefore, in this embodiment, beamforming is performed on the original array data to obtain the output sound signal y(t). The output sound signal y(t) is the weighted sum of multiple channels after processing. The number of microphones on the microphone array is the number of channels. In this embodiment, the output sound signal y(t) is the weighted sum of 8 channels after processing.

[0044] Calculate the wavelet packet energy flow WPI-1~WPI-λ of each reference sample and the wavelet packet energy flow WPI-r of the evaluation sample.

[0045] The wavelet packet energy flow of the reference sample and the evaluation sample is calculated using the same method.

[0046] First, use low-pass filter h(k) and high-pass filter g(k) to iteratively decompose the sound signal y(t) in the reference sample or evaluation sample to obtain the wavelet packet decomposition coefficients:

[0047]

[0048] in, is the wavelet decomposition coefficient of the p-th node in the i-th layer, and Represents the wavelet decomposition coefficients of the 2pth and 2p+1th nodes in the i+1th layer, corresponding to the approximate coefficients and detail coefficients respectively. The approximate coefficients reflect the overall characteristics of the signal, and the detail coefficients reflect the local details of the signal. In the wavelet transform, the approximate coefficients contain the low-frequency components of the signal, and the detail coefficients contain the high-frequency components of the signal. In the binary decomposition tree, 2^i nodes (frequency bands) can be obtained in the i-th layer and the nodes can be numbered as (i, p) (p = 0, 1, 2, ... 2^i-1), such as Figure 2 shown.

[0049] Then, the wavelet packet energy feature vector with the same length as the sound signal is reconstructed based on the wavelet packet decomposition coefficients. In contrast to the recursive splitting operation of equation (1), the reconstruction process can be expressed based on the wavelet decomposition coefficients as follows:

[0050]

[0051] in represents the reconstructed wavelet packet coefficient of the p-th node in the i-th layer, It means inserting a zero next to each d point (corresponding to the downsampling operation in the decomposition process), that is, when performing wavelet packet reconstruction, zero is filled between every two wavelet decomposition coefficients, and a 2-fold upsampling operation is performed; H(k-2τ) and G(k-2τ) refer to low-pass filter and high-pass filter respectively. Compared with the previous h(k) and g(k), they only differ in time reversal. k refers to the kth wavelet packet coefficient. Except for the node (i, p), all wavelet packet node coefficients of the i-th layer are set to zero, that is, when reconstructing the p-th wavelet packet node coefficient of the i-th layer, the wavelet packet node coefficients of the remaining groups are set to 0. Therefore, 2^i signals with the same length as the original signal y(t) can be reconstructed, in which the frequency information of the reconstructed node is retained. Due to the different states of the wind turbine, its frequency information is also different, and the distribution characteristics of the obtained reconstruction coefficients are also different, which gives the state recognition a theoretical basis. The frequency information of the reconstructed nodes retained here provides data support for state recognition.

[0052] It can be predicted that there is a wealth of class information in the reconstruction coefficients obtained from the wavelet packet nodes. When a fault occurs, the coefficients of some nodes will change significantly. As an intuitive feature, energy is first calculated from the wavelet packet reconstruction coefficients. This paper reconstructs the energy features distributed on the wavelet packet nodes and explores new energy images between different wavelet packet nodes.

[0053] In order to distinguish that what is needed in this application is the reconstruction coefficient, according to equations (1) and (2), the reconstruction coefficient of the p-th wavelet packet node (i, p) of the i-th layer is Expressed as n refers to the ordinal number of the reconstruction coefficient of the pth wavelet packet node in the i-th layer, that is, Refers to the nth reconstruction coefficient of the pth wavelet packet node in the i-th layer, and the corresponding wavelet packet energy feature is calculated as:

[0054]

[0055] Where N is the length of the sound signal.

[0056] Finally, the wavelet packet energy eigenvector is transformed into a new wavelet packet phase space to obtain the wavelet packet energy flow of the sound signal. The number of energy eigenvectors is 2 i The energy eigenvector is transformed into a new wavelet packet phase space, so that the dynamic structure of the frequency distribution can be reconstructed in the wavelet packet energy flow. The jth phase vector in the m-dimensional phase space is set to In this patent, the time delay τ is set equal to the embedding dimension m. Therefore, the wavelet packet energy flow can be redefined and mathematically defined as follows:

[0057]

[0058] Where i is the decomposition level, q is the dimension of wavelet packet energy flow, which is the dimension of wavelet packet energy flow obtained after determining the embedding dimension. In this application, q = m, which is 2 i / 2 ×2 i / 2 In this multidimensional data construction process, the dynamic structure of WPI can reflect the discrimination information of different fault categories, which is beneficial to the performance evaluation of wind turbine bearings.

[0059] The wavelet packet energy flow WPI-1 to WPI-n of each reference sample and the wavelet packet energy flow WPI-r of the evaluation sample are obtained by the above steps.

[0060] Then, the wavelet packet energy flow WPI-1~WPI-n of each reference sample are used to calculate the wavelet packet energy flow deviation reference value SWPI respectively, and the calculation formula is as follows:

[0061]

[0062] Among them, WPI A is the wavelet packet energy flow of a sound signal involved in the calculation, WPI B is the wavelet packet energy flow of another sound signal involved in the calculation.

[0063] Select the maximum reference value of wavelet packet energy flow deviation SWPI from all reference values ​​of wavelet packet energy flow deviation. max :

[0064] SWPI| max =max(SWPI1…SWPI (n-1)！ ) (6)

[0065] And calculate the wavelet packet energy flow deviation SWPI between the wavelet packet energy flow WPI-r of the evaluation sample and the wavelet packet energy flow of any reference sample r , the calculation formula refers to formula (5).

[0066] Comparison of wavelet packet energy flow deviation SWPI r and the maximum reference value of the deviation of wavelet packet energy flow SWPI| max If the wavelet packet energy flow deviation SWPI r Not greater than the maximum reference value of wavelet packet energy flow deviation SWPI| max , then the fan bearing is normal; if the wavelet packet energy flow deviation SWPI rGreater than the maximum reference value of wavelet packet energy flow deviation SWPI| max , then the fan bearing is abnormal.

[0067] Embodiment 2

[0068] This embodiment also provides a fan bearing state assessment system, which includes a processing module, a storage module, and an array sensing module for acquiring fan bearing sound signals.

[0069] The array sensing module is connected in communication with the processing module, and sends the acquired fan bearing sound signal to the processing module. Specifically, the array sensing module includes a microphone array placed near the fan for receiving the fan bearing sound signal, and the obtained fan bearing sound is a multi-channel signal. The microphone array also buffers, amplifies, low-pass filters and A / D converts the received fan bearing sound signal; it also includes a signal synchronization set device composed of an array driver board and a development board for synchronously receiving multi-channel signals; the signal synchronization set device is connected in communication with the processing module, and sends the multi-channel fan bearing sound signal to the processing module, and the processing module beamforms the multi-channel fan bearing sound signal to obtain a single-channel fan bearing sound signal.

[0070] The processing module and the storage module are communicatively connected to each other. The storage module is used to store at least one executable instruction. The executable instruction enables the processing module to perform operations corresponding to the fan bearing state assessment method based on the sound energy flow deviation index of Example 1 according to the single-channel fan bearing sound signal, so as to assess the fan bearing state.

[0071] In the description of this specification, the description with reference to the terms "one embodiment", "some embodiments", "examples", "specific examples", or "some examples" means that the specific features, structures, materials or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present invention. In this specification, the schematic representation of the above terms does not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described may be combined in any one or more embodiments or examples in a suitable manner.

[0072] Although the embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that various changes, modifications, substitutions and variations may be made to the embodiments without departing from the principles and spirit of the present invention, and that the scope of the present invention is defined by the claims and their equivalents.

Claims

1. A method for evaluating the condition of a fan bearing based on a sound energy flow deviation index, characterized in that: The following steps are involved: Obtain multiple sound signals of normal fan bearings in stable operation as reference samples; Acquire the sound signal of the current fan bearing under stable operation as an evaluation sample; Calculate the wavelet packet energy flow of each reference sample and the wavelet packet energy flow of the evaluation sample; The wavelet packet energy flow deviation reference values ​​of each reference sample are calculated pairwise, and the maximum reference value of the wavelet packet energy flow deviation is selected; Calculate the wavelet packet energy flow deviation between the wavelet packet energy flow of the evaluation sample and the wavelet packet energy flow of any reference sample; If the wavelet packet energy flow deviation is greater than the maximum reference value of the wavelet packet energy flow deviation, the fan bearing is abnormal, otherwise the fan bearing is normal.

2. The method for evaluating the condition of a fan bearing based on the sound energy flow deviation index according to claim 1 is characterized in that: The steps to calculate the wavelet packet energy flow of the sound signal are: Perform wavelet packet decomposition on the sound signal to obtain wavelet packet decomposition coefficients; Reconstruct the wavelet packet energy feature vector with the same length as the sound signal based on the wavelet packet decomposition coefficients; The wavelet packet energy eigenvector is transformed into a new wavelet packet phase space to obtain the wavelet packet energy flow of the sound signal. During the transformation, the time delay is equal to the embedding dimension.

3. The method for evaluating the condition of a fan bearing based on the sound energy flow deviation index according to claim 2 is characterized in that: The wavelet packet energy eigenvector is in Refers to the nth reconstruction coefficient of the pth wavelet packet node in the i-th layer, n refers to the ordinal number of the reconstruction coefficient of the pth wavelet packet node in the i-th layer, and N is the length of the sound signal; The wavelet packet energy flow of the sound signal is 4. The method for evaluating the condition of a fan bearing based on a sound energy flow deviation index according to claim 1, characterized in that: The calculation formula of the wavelet packet energy flow deviation is: Among them, WPI A is the wavelet packet energy flow of a sound signal, WPI B is the wavelet packet energy flow of another sound signal.

5. The method for evaluating the condition of a fan bearing based on the sound energy flow deviation index according to claim 1 is characterized in that: An original array signal of the sound of the fan bearing in stable operation is obtained, and the original array signal is beamformed to obtain the sound signal.

6. A fan bearing condition assessment system, characterized in that: It includes a processing module, a storage module and an array sensing module for acquiring the sound signal of the fan bearing; The array sensing module is communicatively connected to the processing module and sends the acquired fan bearing sound signal to the processing module. The processing module is communicatively connected to the storage module, and the storage module is used to store at least one executable instruction. The executable instruction enables the processing module to perform an operation corresponding to the fan bearing state assessment method based on the sound energy flow deviation index as described in any one of claims 1 to 5 according to the fan bearing sound signal, so as to assess the fan bearing state.

7. The wind turbine bearing condition assessment system according to claim 6, characterized in that: The array sensing module includes a microphone array placed near the fan for receiving the fan bearing sound signal. The fan bearing sound obtained is a multi-channel signal. The microphone array also buffers, amplifies, low-pass filters and performs A / D conversion on the received fan bearing sound signal. It also includes a signal synchronization set device composed of an array driver board and a development board for synchronously receiving multi-channel signals; the signal synchronization set device is communicatively connected to the processing module to send multi-channel fan bearing sound signals to the processing module.

8. The wind turbine bearing condition assessment system according to claim 7, characterized in that: The processing module performs beamforming on the multi-channel fan bearing sound signal to obtain a single-channel fan bearing sound signal, and the processing module evaluates the fan bearing state based on the single-channel fan bearing sound signal.

Images