Hydraulic support abnormality detection method, device, electronic equipment and storage medium

Abstract

The present disclosure proposes a method, device, electronic device and storage medium for detecting anomalies of a hydraulic support, including: collecting initial sound data through a sound mobile collection device; offsetting the initial sound data to generate multiple covariance matrices; determining a target collection direction; adjusting to the target collection direction, collecting target sound data, and processing the target sound data to determine whether it is abnormal. By setting a movable sound mobile collection device to collect the sound data of the hydraulic support to determine whether the hydraulic support is abnormal, compared with the current technology of collecting hydraulic support data through fixed underground sensors, the impact of complex underground environments on the collected data can be reduced. At the same time, by calibrating and changing the sound collection direction of the sound mobile collection device, the quality of sound data collection can be further improved, so that a more accurate hydraulic support status can be obtained, and the cost is lower than the data collection solution in the current technology.

Description

Technical Field

[0001] The present invention relates to the technical field of equipment monitoring for fully mechanized coal mining working faces, and in particular to a method, device, electronic equipment and storage medium for detecting abnormalities in hydraulic supports. Background Art

[0002] With the continuous development of coal mining technology, intelligence, informationization and high efficiency are the main development directions of modern large-scale coal mines. As one of the important equipment for underground fully mechanized mining working faces in coal mines, hydraulic supports have a harsh operating environment and complex working conditions. During the long-term operation and production process, their mechanical properties and equipment stability continue to decline, resulting in frequent failures. Once a hydraulic support fails, it will not only affect the progress of coal mining, but may even cause irreparable losses such as casualties. Summary of the invention

[0003] The present disclosure aims to solve one of the technical problems in the related art at least to some extent.

[0004] To this end, an object of the present disclosure is to provide a method for detecting abnormalities in a hydraulic support.

[0005] The second objective of the present disclosure is to provide a hydraulic support abnormality detection device.

[0006] A third objective of the present disclosure is to provide an electronic device.

[0007] A fourth object of the present disclosure is to provide a non-transitory computer-readable storage medium.

[0008] A fifth object of the present disclosure is to provide a computer program product.

[0009] To achieve the above-mentioned purpose, the first aspect of the present disclosure proposes a method for detecting an abnormality of a hydraulic support, comprising: in response to a sound mobile collection device moving to a target collection position, collecting initial sound data of the hydraulic support in a sound collection direction that is an initial sound collection direction by the sound mobile collection device; offsetting the initial sound data to generate multiple covariance matrices; determining a target collection direction of the sound mobile collection device at the target collection position based on the covariance matrix; adjusting the sound collection direction of the sound mobile collection device from the initial sound collection direction to the target collection direction, collecting the target sound data of the hydraulic support by the sound mobile collection device, and processing the target sound data by a hydraulic support abnormality detection model to determine whether the hydraulic support corresponding to the target collection position is abnormal.

[0010] According to one embodiment of the present disclosure, the offsetting of the initial sound data to generate multiple covariance matrices includes: obtaining an offset distance and establishing an initial sound matrix based on the initial sound data; and translating the initial sound matrix multiple times according to the offset distance to obtain multiple covariance matrices.

[0011] According to one embodiment of the present disclosure, determining the target collection direction of the sound mobile collection device at the target collection position based on the covariance matrix includes: determining a judgment matrix based on all the covariance matrices; calculating the eigenvectors and eigenvalues ​​of the judgment matrix; generating a spatial spectrum based on the eigenvectors and the eigenvalues, and determining the target collection direction through the spatial spectrum.

[0012] According to an embodiment of the present disclosure, generating the spatial spectrum based on the eigenvector and the eigenvalue includes: performing eigendecomposition on the eigenvector to obtain a signal subspace and a noise subspace; and generating the spatial spectrum based on the signal subspace and the noise subspace.

[0013] According to an embodiment of the present disclosure, determining the target acquisition direction through the spatial spectrum includes: searching the spatial spectrum, and taking the direction corresponding to the searched maximum value as the target acquisition direction.

[0014] According to one embodiment of the present disclosure, before the target sound data is processed by the hydraulic support abnormality detection model, it also includes: preprocessing the target sound data; extracting sound features from the preprocessed target sound data to obtain target sound features of the target sound data, and using the target sound features as data for subsequent input into the hydraulic support abnormality detection model for processing.

[0015] According to one embodiment of the present disclosure, the hydraulic support anomaly detection model is generated by constructing an autoencoder.

[0016] To achieve the above-mentioned purpose, the second aspect of the present disclosure proposes a hydraulic support abnormality detection device, including: a collection module, which is used to respond to the sound mobile collection device moving to the target collection position, and collect the initial sound data of the hydraulic support in the sound collection direction as the initial sound collection direction through the sound mobile collection device; a generation module, which is used to offset the initial sound data to generate multiple covariance matrices; a determination module, which is used to determine the target collection direction of the sound mobile collection device at the target collection position based on the covariance matrix; a processing module, which is used to adjust the sound collection direction of the sound mobile collection device from the initial sound collection direction to the target collection direction, collect the target sound data of the hydraulic support through the sound mobile collection device, and process the target sound data through the hydraulic support abnormality detection model to determine whether the hydraulic support corresponding to the target collection position is abnormal.

[0017] To achieve the above-mentioned purpose, the third aspect embodiment of the present disclosure proposes an electronic device, comprising: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor to implement the hydraulic support abnormality detection method as described in the first aspect embodiment of the present disclosure.

[0018] To achieve the above-mentioned purpose, the fourth aspect of the present disclosure proposes a non-transitory computer-readable storage medium storing computer instructions, wherein the computer instructions are used to implement the hydraulic support abnormality detection method as described in the first aspect of the present disclosure.

[0019] To achieve the above-mentioned purpose, the fifth embodiment of the present disclosure proposes a computer program product, including a computer program, which, when executed by a processor, is used to implement the hydraulic support abnormality detection method as described in the first embodiment of the present disclosure.

[0020] By setting up a movable sound collection device to collect the sound data of the hydraulic support to determine whether the hydraulic support is abnormal, compared with the current technology of collecting hydraulic support data through fixed underground sensors, the impact of the complex underground environment on the collected data can be reduced. At the same time, by calibrating and changing the sound collection direction of the sound collection device, the quality of sound data collection can be further improved, so that a more accurate hydraulic support status can be obtained, and the cost is lower than the data collection solution in the current technology. BRIEF DESCRIPTION OF THE DRAWINGS

[0021] Figure 1 is a schematic diagram of a method for detecting abnormality of a hydraulic support according to an embodiment of the present disclosure;

[0022] Figure 2 is a schematic diagram of another method for detecting abnormality of a hydraulic support according to an embodiment of the present disclosure;

[0023] Figure 3 is a schematic diagram of another method for detecting abnormality of a hydraulic support according to an embodiment of the present disclosure;

[0024] Figure 4 is a schematic diagram of another method for detecting abnormality of a hydraulic support according to an embodiment of the present disclosure;

[0025] Figure 5 is a schematic diagram of a hydraulic support abnormality detection device according to one embodiment of the present disclosure;

[0026] Figure 6 is a schematic diagram of an electronic device according to an embodiment of the present disclosure. DETAILED DESCRIPTION

[0027] Embodiments of the present disclosure 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 intended to be used to explain the present disclosure, and should not be construed as limiting the present disclosure.

[0028] The acquisition, storage, use, and processing of data in the technical solution disclosed in this disclosure are in compliance with the relevant provisions of relevant laws and regulations.

[0029] Figure 1 is a schematic diagram of a method for detecting abnormality of a hydraulic support according to an embodiment of the present disclosure, such as Figure 1 As shown, the hydraulic support abnormality detection method includes the following steps:

[0030] S101, in response to the sound mobile collection device moving to the target collection position, the sound mobile collection device collects initial sound data of the hydraulic support in a sound collection direction that is an initial sound collection direction.

[0031] The hydraulic support anomaly detection method of the embodiment of the present application can be applied to the scenario of underground hydraulic support monitoring. The executor of the hydraulic support anomaly detection of the embodiment of the present application can be the hydraulic support anomaly detection device of the embodiment of the present application, and the hydraulic support anomaly detection device can be set on an electronic device.

[0032] In current technology, sensors are set underground to collect sound signals or other signals to determine whether the state of the hydraulic support is abnormal. However, due to the complex underground environment and the constant changes in the state of the hydraulic support, it is very challenging for traditional sensors to collect data, and it will affect the accuracy of the final collected data. At the same time, in order to ensure the accuracy of the final prediction or processing results, it is necessary to set up multiple sensors at different locations for sound collection, which is very costly.

[0033] In order to solve the above problems, the inventor of the present disclosure proposes a mobile sound collection device, which is arranged above the well or underground, and is used to collect sound data at different points by moving.

[0034] When the mobile sound collection device is set up underground, a slide rail can be installed at the bottom of the top beam of the central hydraulic support of each hydraulic support group, and the microphone array can be installed on the inspection cart. The inspection cart slides on the slide rail to collect sound signals when passing through each collection position.

[0035] When the sound collection device is set up on the well, sound collection can be carried out when arriving at the collection location by a mobile sound collection vehicle, a sound collection drone, etc.

[0036] In the embodiment of the present disclosure, multiple collection locations may be included. The multiple collection locations are set in advance and can be changed according to actual monitoring needs. No limitation is made here.

[0037] In actual operation, due to the complex underground environment and the constant change of the state of the hydraulic support, the sound data collected in different sound collection directions are very different, which will cause deviations in the final data processing results. At the same time, different climatic conditions and the direction of the sound mobile collection device will affect the optimal sound collection direction.

[0038] It should be noted that the initial sound collection direction can be a direction that is actually good in advance, or a random collection direction, and no limitation is made here. The initial sound collection direction can be the best sound data collection direction, or it may not be the best sound data collection direction, which needs to be verified later.

[0039] S102, offsetting the initial sound data to generate a plurality of covariance matrices.

[0040] In the embodiments of the present disclosure, there may be many methods for generating multiple covariance matrices, which are not limited here.

[0041] In one possible implementation, the initial sound data can be input into a covariance matrix generation model to achieve the purpose of offsetting the initial sound data and generating a covariance matrix. The covariance matrix generation model is trained in advance and stored in the storage space of the electronic device for easy retrieval when needed.

[0042] In another possible implementation, a sound matrix may be first generated based on initial sound data, and then the sound matrix may be shifted to generate a plurality of covariance matrices.

[0043] S103: Determine a target collection direction of the sound mobile collection device at the target collection position based on the covariance matrix.

[0044] It should be noted that the target collection direction is the optimal direction for the mobile sound collection device to collect sound at the target collection position this time.

[0045] In the embodiment of the present disclosure, after the covariance matrix is ​​obtained, the target acquisition direction can be determined by processing the covariance matrix. There are many processing methods, which are not limited here.

[0046] In one possible implementation, the collected sound signal may be compared with the covariance matrix, and the covariance matrix that best matches the sound signal may be determined based on the comparison result, and the direction corresponding to the covariance matrix may be defined as the target collection direction.

[0047] S104, adjusting the sound collection direction of the mobile sound collection device from the initial sound collection direction to the target collection direction, collecting target sound data of the hydraulic support through the mobile sound collection device, and processing the target sound data through the hydraulic support anomaly detection model to determine whether the hydraulic support corresponding to the target collection position is abnormal.

[0048] In the embodiment of the present disclosure, first, in response to the sound mobile collection device moving to the target collection position, the sound mobile collection device collects the initial sound data of the hydraulic support in the sound collection direction that is the initial sound collection direction, and then the initial sound data is offset to generate multiple covariance matrices, and then the target collection direction of the sound mobile collection device at the target collection position is determined based on the covariance matrix, and finally the sound collection direction of the sound mobile collection device is adjusted from the initial sound collection direction to the target collection direction, and the target sound data of the hydraulic support is collected by the sound mobile collection device, and the target sound data is processed by the hydraulic support abnormality detection model to determine whether the hydraulic support corresponding to the target collection position is abnormal. Therefore, by setting a movable sound mobile collection device to collect the sound data of the hydraulic support to determine whether the hydraulic support is abnormal, compared with the method of collecting hydraulic support data through fixed underground sensors in the current technology, the influence of the complex underground environment on the collected data can be reduced, and at the same time, by calibrating and changing the sound collection direction of the sound mobile collection device, the quality of sound data collection can be further improved, so that a more accurate hydraulic support state can be obtained, and the cost of the data collection scheme is lower than that in the current technology.

[0049] In the above embodiment, the initial sound data is offset to generate multiple covariance matrices, and the covariance matrix can also be obtained by Figure 2 Explaining further, the method includes:

[0050] S201, obtaining an offset distance, and establishing an initial sound matrix based on initial sound data.

[0051] In the embodiment of the present disclosure, the offset distance is designed in advance and can be changed according to actual design requirements, and is not limited here.

[0052] S202, performing multiple translations on the initial sound matrix according to the offset distance to obtain multiple covariance matrices.

[0053] It should be noted that the number of translations is designed in advance and can be changed according to actual design needs, and is not limited here.

[0054] In the embodiment of the present disclosure, the directions of the multiple translations are in the same direction. For example, the covariance matrix can be expressed by the following formula:

[0055] R k =AD (k-1) R s (D (k-1) ) H A H +σ 2 I

[0056] Among them, R kis the covariance matrix of the virtual array receiving signal after K times translation, which is an M×M matrix, k=1,2,3…M, M is the number of array elements. A is the amplitude of the received signal. D represents the spacing of the array, that is, the distance between adjacent array elements in the array. R s is the covariance matrix of the transmitted signal s(t), which is an N×N matrix, where N is the dimension of the signal. H represents the conjugate transpose operator, σ 2 represents the variance of the noise, and I represents the identity matrix.

[0057] x k (t) = AD (k-1) s(t)+n k (t)

[0058] Among them, x k (t) is the signal received by the virtual array after the Kth translation, which is an M-dimensional vector, k = 1, 2, 3 ... ... M, M is the number of array elements. A is the amplitude of the received signal. D represents the spacing of the array, that is, the distance between adjacent array elements in the array. s(t) represents the transmitted signal, which is an N-dimensional vector containing N narrowband signals. n k (t) is the noise signal received by the virtual array after the k-th translation, which is usually assumed to be Gaussian white noise, and t represents time.

[0059] In the above embodiment, the target collection direction of the sound mobile collection device at the target collection position is determined based on the covariance matrix, and the target collection direction of the sound mobile collection device at the target collection position can also be determined by Figure 3 Explaining further, the method includes:

[0060] S301, determining a judgment matrix based on all covariance matrices.

[0061] In the embodiment of the present disclosure, the judgment matrix may be calculated and generated by averaging all covariance matrices.

[0062] In the embodiment of the present disclosure, the calculation can be performed by the following formula:

[0063]

[0064] Among them, R is the judgment matrix, L is the number of judgment matrices, R k is the Kth covariance matrix.

[0065] S302, calculating the eigenvectors and eigenvalues ​​of the judgment matrix.

[0066] In the embodiments of the present disclosure, eigenvalues ​​and eigenvectors are important concepts in linear algebra, and are usually related to matrix operations. It should be noted that there are many methods for calculating the eigenvectors and eigenvalues ​​of the judgment matrix, which are not limited here.

[0067] For example, given a square matrix (A), its eigenvalue (Eigenvalue) and the corresponding eigenvector (Eigenvector) satisfy the following relationship:

[0068] For eigenvalues ​​(\lambda) and corresponding non-zero eigenvectors (v), we have: [Av = \lambda v] To calculate all eigenvalues ​​and eigenvectors of a matrix, follow these steps:

[0069] Calculate eigenvalues: construct a matrix (A-\lambda I), where (I) is the identity matrix of the same order as (A).

[0070] Solve the characteristic polynomial equation whose determinant (|A - \lambda I|) about (\lambda) is equal to 0.

[0071] The roots of the characteristic polynomial are the eigenvalues ​​of the matrix (A). 2. Calculate the eigenvectors corresponding to the eigenvalues:

[0072] Select an eigenvalue (\lambda) and construct the matrix ((A-\lambda I)).

[0073] Find a non-zero solution vector (v) such that ((A-\lambda I)v=0).

[0074] Each such non-zero vector (v) is the eigenvector of the corresponding eigenvalue (\lambda). In actual calculations, numerical methods (such as QR decomposition, power method, or Jacobi iteration method, etc.) can usually be used to solve eigenvalues ​​and eigenvectors. Modern mathematical software (such as MATLAB, Python's NumPy library, etc.) provides functions for directly calculating eigenvalues ​​and eigenvectors, and users do not need to perform complex calculations manually.

[0075] S303: Generate a spatial spectrum based on the eigenvector and the eigenvalue, and determine the target acquisition direction through the spatial spectrum.

[0076] In signal processing, especially in array signal processing and DOA estimation in radar, sonar and other fields, spatial spectrum is a method used to estimate the direction of arrival of the signal source. Among them, algorithms such as MUSIC (Multiple Signal Classification) and ESPRIT (Estimation of Signal Parameters via Rotational Invariance Techniques) are based on subspace decomposition methods.

[0077] In the embodiment of the present disclosure, the signal subspace and the noise subspace may be obtained by performing eigendecomposition on the eigenvector, and then a spatial spectrum may be generated based on the signal subspace and the noise subspace.

[0078] For example, an array composed of multiple antennas receives signals from different directions and there is background noise. The collected data can form a received data matrix, and the covariance matrix (R) or correlation matrix is ​​constructed by this data matrix.

[0079] Eigenvalue decomposition of the covariance matrix: First, perform eigenvalue decomposition on the covariance matrix (R) to obtain (R = U\Sigma U^H), where (U) is a matrix containing all eigenvectors and (\Sigma) is a diagonal matrix with eigenvalues ​​on the diagonal.

[0080] Signal subspace and noise subspace division: Eigenvalues ​​are sorted by size. Usually, the larger eigenvalues ​​correspond to signal components, while the smaller eigenvalues ​​correspond to noise components. The signal subspace is composed of eigenvectors corresponding to the larger eigenvalues, while the noise subspace is composed of eigenvectors corresponding to the remaining small eigenvalues ​​corresponding to the noise contribution.

[0081] By using the orthogonality of the signal subspace and the noise subspace, a high-resolution spatial spectrum can be obtained. By searching the spatial spectrum, the direction corresponding to the maximum value found is used as the target acquisition direction.

[0082] In the above embodiment, before the target sound data is processed by the hydraulic support anomaly detection model, Figure 4 Explaining further, the method includes:

[0083] S401, pre-processing the target sound data.

[0084] In the embodiments of the present disclosure, there may be multiple methods for preprocessing the target sound data, which are not limited herein.

[0085] In one possible implementation, channel fusion may be performed first.

[0086] For example, if the sound mobile acquisition device uses a 6-channel uniform microphone array, the sound sequence corresponding to each channel is X1(t), X2(t), ..., X6(t). The sound signals of the 6-channel uniform circular array are fused and averaged:

[0087]

[0088] Then perform pre-emphasis:

[0089] High-frequency signals decay quickly, so the energy of the high-frequency part of the collected sound signal is lower than that of the low-frequency part, resulting in information loss. The sound signal is pre-emphasized through a first-order digital high-pass filter.

[0090] Then perform frame processing:

[0091] When the hydraulic support is in abnormal operation, the sound signal has the characteristics of time non-stationarity. It often appears in a very short time and changes greatly. It is difficult to effectively analyze it in a longer and complete sound signal. Generally, the sound signal with a shorter time is defined as steady state. Therefore, the collected sound signal can be divided into multiple small parts, and the duration of each small part is usually 10ms to 30ms. In order to maintain the relative continuity of the smooth transition between frames, when dividing the next frame, part of the content in the previous frame is generally retained.

[0092] Finally, perform windowing:

[0093] After the sound signal is processed by framing, there is always a sudden change from 0 to 1 or from 1 to 0 at both ends. Directly performing Fourier transform on it is likely to cause spectrum leakage and noise in the spectrum. Therefore, these components need to be removed during the windowing process.

[0094] Using the Hamming window function, a frame signal x(n) can be expressed as:

[0095] H=W(n)·x(n), first define the indices variable, which generates the index of the sample corresponding to each frame. The np.tile function can expand the array from rows or columns. Then define frames, which corresponds to the value of the signal in each frame. Frames has 1999 rows and 1102 columns, corresponding to a total of 1999 frames and 1102 samples per frame. Directly multiply the obtained frames and the hamming window to obtain the pre-processed target sound data.

[0096] S402, extracting sound features from the preprocessed target sound data to obtain target sound features of the target sound data, and using the target sound features as data subsequently input into a hydraulic support anomaly detection model for processing.

[0097] It should be noted that there are many methods for extracting sound features from the preprocessed target sound data, which are not limited here. In one possible implementation, the target sound data can be feature extracted using a sound feature extraction model to obtain the target sound features. The sound feature extraction model can be trained in advance and stored in the storage space of the electronic device to facilitate retrieval and use when needed.

[0098] In the embodiment of the present disclosure, the hydraulic support anomaly detection model is generated by constructing an autoencoder. For example, the hydraulic support sound data can be regarded as input data x. Assuming that the sound data is a time series, it can be represented as a vector x = [x 1 ,x 2 ,…,x n ], where x i Represents the sound data at the i-th time point. In the autoencoder, it is desirable to compress this sound data into a low-dimensional latent space representation h, and then decode it back to the original data.

[0099] 1. Coding process:

[0100] In the encoder, a neural network can be used to map the input data x to the latent space representation h. The encoder used is a fully connected neural network with 128 neurons in the first layer and 64 neurons in the second layer, and the activation function is ReLU. Then the encoding process can be expressed as:

[0101] h=f(W 1 *f(W 2 *x+b 2 )+b 1 )

[0102] Among them, W 1 and W 2 is the weight matrix, b 1 and b 2 is the bias term, and f is the ReLU activation function.

[0103] 2. Decoding process:

[0104] In the decoder, another neural network is used to decode the latent space representation h into the reconstructed data The decoder is also a fully connected neural network with 64 neurons in the first layer and 128 neurons in the second layer, and the activation function is ReLU. Then the decoding process can be expressed as:

[0105]

[0106] Among them, W′ 1 and W′ 2 is the weight matrix of the decoder, b′ 1 and b′ 2 is the bias term of the decoder, and g is the output layer of the decoder.

[0107] 3. Loss function:

[0108] The loss function of the autoencoder is usually the sum of the input data x and the output of the decoder The mean square error (MSE) between:

[0109]

[0110] Where n is the number of samples, x i is the i-th element of the input data, is the i-th element of the decoder output.

[0111] By training the autoencoder, an effective representation of sound data can be learned, which can be used for tasks such as dimensionality reduction or feature extraction of sound data.

[0112] After the hydraulic support anomaly detection model is generated by the autoencoder, the hydraulic support anomaly detection model can also be trained. It can be understood that the training of the model is an iterative process, which is trained by continuously adjusting the network parameters of the model until the overall loss function value of the model is less than the preset value, or the overall loss function value of the model no longer changes or changes slowly, the model converges, and a trained model is obtained. The loss function can be designed in advance and can be changed according to actual design needs, without any limitation here.

[0113] Corresponding to the hydraulic support abnormality detection methods provided in the above-mentioned embodiments, an embodiment of the present disclosure also provides a hydraulic support abnormality detection device. Since the hydraulic support abnormality detection device provided in the embodiment of the present disclosure corresponds to the hydraulic support abnormality detection methods provided in the above-mentioned embodiments, the implementation method of the above-mentioned hydraulic support abnormality detection method is also applicable to the hydraulic support abnormality detection device provided in the embodiment of the present disclosure, and will not be described in detail in the following embodiments.

[0114] Figure 5 is a schematic diagram of a hydraulic support abnormality detection device according to one embodiment of the present disclosure, such as Figure 5 As shown, the hydraulic support abnormality detection device 500 includes: a collection module 510, a generation module 520, a determination module 530 and a processing module 540.

[0115] The collection module 510 is used to collect initial sound data of the hydraulic support in an initial sound collection direction by using the sound collection device in response to the sound collection device moving to a target collection position.

[0116] The generating module 520 is used to shift the initial sound data to generate a plurality of covariance matrices.

[0117] The determination module 530 is used to determine the target collection direction of the sound mobile collection device at the target collection position based on the covariance matrix.

[0118] The processing module 540 is used to adjust the sound collection direction of the sound mobile collection device from the initial sound collection direction to the target collection direction, collect the target sound data of the hydraulic support through the sound mobile collection device, and process the target sound data through the hydraulic support abnormality detection model to determine whether the hydraulic support corresponding to the target collection position is abnormal.

[0119] In a possible implementation, the generation module 520 is further used to: obtain an offset distance, and establish an initial sound matrix based on the initial sound data; and perform multiple translations on the initial sound matrix according to the offset distance to obtain multiple covariance matrices.

[0120] In a possible implementation, the determination module 530 is further used to: determine a judgment matrix based on all covariance matrices; calculate eigenvectors and eigenvalues ​​of the judgment matrix; generate a spatial spectrum based on the eigenvectors and eigenvalues, and determine the target acquisition direction through the spatial spectrum.

[0121] In a possible implementation, the determination module 530 is further configured to: perform eigendecomposition on the eigenvector to obtain a signal subspace and a noise subspace; and generate a spatial spectrum based on the signal subspace and the noise subspace.

[0122] In a possible implementation, the determination module 530 is further configured to: search the spatial spectrum, and use the direction corresponding to the searched maximum value as the target acquisition direction.

[0123] In one possible implementation, the processing module 540 is also used to: pre-process the target sound data; extract sound features from the pre-processed target sound data to obtain target sound features of the target sound data, and use the target sound features as data for subsequent input into the hydraulic support anomaly detection model for processing.

[0124] In one possible implementation, the hydraulic support anomaly detection model is generated by constructing an autoencoder.

[0125] By setting up a movable sound collection device to collect the sound data of the hydraulic support to determine whether the hydraulic support is abnormal, compared with the current technology of collecting hydraulic support data through fixed underground sensors, the impact of the complex underground environment on the collected data can be reduced. At the same time, by calibrating and changing the sound collection direction of the sound collection device, the quality of sound data collection can be further improved, so that a more accurate hydraulic support status can be obtained, and the cost is lower than the data collection solution in the current technology.

[0126] In order to implement the above embodiment, the present disclosure further provides an electronic device 600, Figure 6 is a schematic diagram of an electronic device according to an embodiment of the present disclosure, such as Figure 6 As shown, the electronic device 600 includes: a processor 601 and a memory 602 that is communicatively connected to the processor, the memory 602 stores instructions that can be executed by at least one processor, and the instructions are executed by at least one processor 601 to implement the present disclosure. Figure 1-Figure 4 A method for detecting abnormality of a hydraulic support according to an embodiment.

[0127] In order to implement the above embodiments, the present disclosure also provides a non-transitory computer-readable storage medium storing computer instructions, wherein the computer instructions are used to enable the computer to implement the above embodiments. Figure 1-Figure 4 A method for detecting abnormality of a hydraulic support according to an embodiment.

[0128] In order to implement the above embodiments, the present disclosure also provides a computer program product, including a computer program. When the computer program is executed by a processor, the computer program implements the above embodiments. Figure 1-Figure 4 A method for detecting abnormality of a hydraulic support according to an embodiment.

[0129] It should be noted that personal information from users should be collected for legitimate and reasonable purposes and should not be shared or sold outside of these legitimate uses. In addition, such collection / sharing should be carried out after receiving the user's informed consent, including but not limited to notifying the user to read the user agreement / user notice and sign the agreement / authorization including authorization of relevant user information before the user uses the function. In addition, any necessary steps should be taken to protect and safeguard access to such personal information data and ensure that others who have access to personal information data comply with its privacy policy and procedures.

[0130] The present application is expected to provide an implementation scheme for users to selectively block the use or access of personal information data. That is, the present disclosure is expected to provide hardware and / or software to prevent or block access to such personal information data. Once the personal information data is no longer needed, the risk can be minimized by limiting data collection and deleting the data. In addition, when applicable, such personal information is de-identified to protect the privacy of the user.

[0131] In the description of the aforementioned embodiments, the description with reference to the terms "one embodiment", "some embodiments", "example", "specific example", or "some examples" etc. 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 application. In this specification, the schematic representations of the above terms do 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. In addition, those skilled in the art may combine and combine the different embodiments or examples described in this specification and the features of the different embodiments or examples, without contradiction.

[0132] In addition, the terms "first" and "second" are used for descriptive purposes only and should not be understood as indicating or implying relative importance or implicitly indicating the number of the indicated technical features. Therefore, the features defined as "first" and "second" may explicitly or implicitly include at least one of the features. In the description of this application, the meaning of "plurality" is at least two, such as two, three, etc., unless otherwise clearly and specifically defined.

[0133] Any process or method description in a flowchart or otherwise described herein may be understood to represent a module, fragment or portion of code comprising one or more executable instructions for implementing the steps of a custom logical function or process, and the scope of the preferred embodiments of the present application includes alternative implementations in which functions may not be performed in the order shown or discussed, including performing functions in a substantially simultaneous manner or in the reverse order depending on the functions involved, which should be understood by technicians in the technical field to which the embodiments of the present application belong.

[0134] The logic and / or steps represented in the flowchart or otherwise described herein, for example, can be considered as an ordered list of executable instructions for implementing logical functions, and can be embodied in any computer-readable medium for use by an instruction execution system, device or apparatus (such as a computer-based system, a system including a processor, or other system that can fetch instructions from an instruction execution system, device or apparatus and execute instructions), or in combination with these instruction execution systems, devices or apparatuses. For the purpose of this specification, "computer-readable medium" can be any device that contains, stores, communicates, propagates or transmits a program for use by an instruction execution system, device or apparatus, or in combination with these instruction execution systems, devices or apparatuses. More specific examples (non-exhaustive list) of computer-readable media include the following: an electrical connection with one or more wires (electronic device), a portable computer disk box (magnetic device), a random access memory (RAM), a read-only memory (ROM), an erasable and programmable read-only memory (EPROM or flash memory), a fiber optic device, and a portable compact disk read-only memory (CDROM). In addition, the computer-readable medium may even be paper or other suitable medium on which the program is printed, since the program may be obtained electronically, for example, by optically scanning the paper or other medium and then editing, interpreting or processing in other suitable ways if necessary, and then stored in a computer memory.

[0135] It should be understood that the various parts of the present application can be implemented by hardware, software, firmware or a combination thereof. In the above-mentioned embodiments, multiple steps or methods can be implemented by software or firmware stored in a memory and executed by a suitable instruction execution system. For example, if implemented by hardware, as in another embodiment, it can be implemented by any one of the following technologies known in the art or their combination: a discrete logic circuit having a logic gate circuit for implementing a logic function for a data signal, a dedicated integrated circuit having a suitable combination of logic gate circuits, a programmable gate array (PGA), a field programmable gate array (FPGA), etc.

[0136] A person skilled in the art may understand that all or part of the steps in the method for implementing the above-mentioned embodiment may be completed by instructing related hardware through a program, and the program may be stored in a computer-readable storage medium, which, when executed, includes one or a combination of the steps of the method embodiment.

[0137] In addition, each functional unit in each embodiment of the present application may be integrated into a processing module, or each unit may exist physically separately, or two or more units may be integrated into one module. The above-mentioned integrated module may be implemented in the form of hardware or in the form of a software functional module. If the integrated module is implemented in the form of a software functional module and sold or used as an independent product, it may also be stored in a computer-readable storage medium.

[0138] The storage medium mentioned above may be a read-only memory, a magnetic disk or an optical disk, etc. Although the embodiments of the present application have been shown and described above, it can be understood that the above embodiments are exemplary and cannot be understood as limiting the present application. A person of ordinary skill in the art may change, modify, replace and modify the above embodiments within the scope of the present application.

Claims

1. A method for detecting abnormality of a hydraulic support, characterized in that: include: In response to the sound mobile collection device moving to the target collection position, the sound mobile collection device collects initial sound data of the hydraulic support in a sound collection direction that is an initial sound collection direction; offsetting the initial sound data to generate a plurality of covariance matrices; Determining a target collection direction of the sound mobile collection device at the target collection position based on the covariance matrix; The sound collection direction of the mobile sound collection device is adjusted from the initial sound collection direction to the target collection direction, the target sound data of the hydraulic support is collected by the mobile sound collection device, and the target sound data is processed by the hydraulic support abnormality detection model to determine whether the hydraulic support corresponding to the target collection position is abnormal; The initial sound data is shifted to generate a plurality of covariance matrices, including: Acquiring an offset distance, and establishing an initial sound matrix based on the initial sound data; The initial sound matrix is ​​translated multiple times according to the offset distance to obtain multiple covariance matrices, wherein the directions of the multiple translations are in the same direction.

2. The method according to claim 1, characterized in that The determining the target collection direction of the sound mobile collection device at the target collection position based on the covariance matrix includes: Based on all the covariance matrices, determining a judgment matrix; Calculating the eigenvectors and eigenvalues ​​of the judgment matrix; A spatial spectrum is generated based on the eigenvector and the eigenvalue, and the target acquisition direction is determined through the spatial spectrum.

3. The method according to claim 2, characterized in that The generating a spatial spectrum based on the eigenvector and the eigenvalue comprises: Performing eigendecomposition on the eigenvector to obtain a signal subspace and a noise subspace; The spatial spectrum is generated based on the signal subspace and the noise subspace.

4. The method according to claim 2 or 3, characterized in that: The determining the target acquisition direction by using the spatial spectrum includes: The spatial spectrum is searched, and the direction corresponding to the searched maximum value is used as the target acquisition direction.

5. The method according to claim 1, characterized in that Before the target sound data is processed by the hydraulic support anomaly detection model, the method further includes: Preprocessing the target sound data; The preprocessed target sound data is subjected to sound feature extraction to obtain the target sound feature of the target sound data, and the target sound feature is used as data subsequently input into the hydraulic support abnormality detection model for processing.

6. The method according to claim 1, characterized in that The hydraulic support anomaly detection model is generated by constructing an autoencoder.

7. A hydraulic support abnormality detection device, characterized in that: include: A collection module, configured to collect initial sound data of the hydraulic support in a sound collection direction that is an initial sound collection direction by means of the sound collection device in response to the sound mobile collection device moving to a target collection position; A generating module, configured to shift the initial sound data to generate a plurality of covariance matrices; A determination module, configured to determine a target collection direction of the sound mobile collection device at the target collection position based on the covariance matrix; A processing module, used for adjusting the sound collection direction of the sound mobile collection device from the initial sound collection direction to the target collection direction, collecting target sound data of the hydraulic support through the sound mobile collection device, and processing the target sound data through the hydraulic support abnormality detection model to determine whether the hydraulic support corresponding to the target collection position is abnormal; The generating module is further used to obtain an offset distance and establish an initial sound matrix based on the initial sound data; The initial sound matrix is ​​translated multiple times according to the offset distance to obtain multiple covariance matrices, wherein the directions of the multiple translations are in the same direction.

8. An electronic device, characterized in that: Including memory and processor; The processor runs a program corresponding to the executable program code by reading the executable program code stored in the memory, so as to implement the method according to any one of claims 1 to 6.

9. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer-executable instructions, which are used to implement the method according to any one of claims 1 to 6 when executed by a processor.

Images