Fault positioning method and device, computer device and storage medium

Abstract

The application relates to a fault positioning method and device, computer equipment, a storage medium and a computer program product. The method comprises the following steps: acquiring a multi-channel sound signal obtained by a microphone array collecting sound of a target object, the microphone array is an array formed by a plurality of concentric rings, and any three microphones in the array are coplanar but not collinear; solving signal characteristic values corresponding to each channel sound signal according to the multi-channel sound signal, and acquiring a target channel with a signal characteristic value exceeding a signal characteristic threshold; determining a plurality of scanning points in a scanning plane, determining sound source power corresponding to each scanning point according to the channel sound signal corresponding to the target channel; obtaining a sound field distribution map according to the sound source power of each scanning point in the scanning plane; acquiring a monitoring picture obtained by image acquisition of the target object, and positioning a fault source according to the sound field distribution map and the monitoring picture. The method can accurately position the fault source.

Description

Technical Field

[0001] This application relates to the field of fault diagnosis technology, and in particular to a fault location method, apparatus, computer equipment, and storage medium. Background Technology

[0002] With the development of sound source localization technology, the use of microphone arrays to process sound signals has become a hot topic. Its basic principle is to use multiple microphones arranged in different shapes to process sound signals from different directions in space in a time-space manner, thereby achieving sound source localization. In the field of fault diagnosis, fault location can be achieved through sound source localization.

[0003] In traditional technologies, microphone arrays of a single shape are often used for fault location, such as cross-shaped microphone arrays or rectangular microphone arrays. However, cross-shaped arrays have a simple layout, a narrow main lobe, and a large side lobe, which can easily cause spatial aliasing. Rectangular arrays have a wide main lobe and low positioning resolution. This results in low accuracy of fault location using microphone arrays.

[0004] Therefore, how to accurately locate faults using microphone arrays is a problem that urgently needs to be solved. Summary of the Invention

[0005] Therefore, it is necessary to provide a fault location method, apparatus, computer equipment, computer-readable storage medium, and computer program product that can accurately locate the source of the fault in order to address the above-mentioned technical problems.

[0006] Firstly, this application provides a fault location method. The method includes:

[0007] The method involves acquiring multi-channel acoustic signals obtained by a microphone array from the sound of a target object. The microphone array is an array composed of multiple concentric rings, and any three microphones in the array are coplanar but not collinear.

[0008] Based on the multi-channel acoustic signals, the signal feature values ​​corresponding to each channel acoustic signal are calculated, and the target channel whose signal feature value exceeds the signal feature threshold is obtained;

[0009] Multiple scanning points in the scanning plane are determined, and the sound source power corresponding to each scanning point is determined based on the channel acoustic signal corresponding to the target channel.

[0010] The sound field distribution map is obtained based on the sound source power at each scanning point in the scanning plane.

[0011] The monitoring screen obtained by image acquisition of the target object is acquired, and the fault source is located based on the sound field distribution map and the monitoring screen.

[0012] In one embodiment, the step of solving for the signal feature values ​​corresponding to each channel acoustic signal based on the multi-channel acoustic signal includes:

[0013] Based on the multi-channel acoustic signals, the range, variance, and kurtosis of each channel acoustic signal are calculated.

[0014] Based on the range, variance, and kurtosis of each channel's acoustic signal, the corresponding signal characteristic values ​​for each channel's acoustic signal are calculated.

[0015] In one embodiment, the signal characteristic threshold characterizes the extreme value of signal characteristics under normal operating conditions, and the step of determining the signal characteristic threshold includes:

[0016] Multiple sets of reference acoustic signals are acquired by a microphone array to collect sound from a preset object; wherein the preset object is an object under normal operating conditions.

[0017] Multiple reference signal feature values ​​are obtained by solving based on the multiple sets of reference acoustic information;

[0018] A signal feature threshold is determined based on the plurality of reference signal feature values; the signal feature threshold is greater than any of the reference signal feature values.

[0019] In one embodiment, determining the plurality of scan points in the scan plane includes:

[0020] Determine the scanning range based on the target object;

[0021] The scanning range is scanned horizontally and vertically with a preset step size to obtain a scanning plane; the intersection of the scanning line obtained by horizontal scanning and the scanning line obtained by vertical scanning in the scanning plane is the scanning point.

[0022] In one embodiment, determining the sound source power corresponding to each scanning point based on the channel acoustic signal corresponding to the target channel includes:

[0023] The cross-spectrum matrix is ​​determined based on the channel signal corresponding to the target channel;

[0024] The sound source power of each scanning point is determined based on the coordinate vector of each target channel, the turning vector of each scanning point, and the cross-spectral matrix.

[0025] In one embodiment, the fault source localization based on the sound field distribution map and the monitoring screen includes:

[0026] Determine the scanning point with the highest sound source power in the sound field distribution map;

[0027] The sound field distribution map and the monitoring screen are superimposed, and the target position of the scanning point with the highest power of the sound source in the monitoring screen is determined. The target position is then identified as the fault source.

[0028] Secondly, this application also provides a fault location device. The device includes:

[0029] The sound signal acquisition module is used to acquire multi-channel sound signals obtained by the microphone array from the sound collection of the target object. The microphone array is an array composed of multiple concentric rings, and any three microphones in the array are coplanar but not collinear.

[0030] The target channel acquisition module is used to solve the signal feature values ​​corresponding to each channel of the multi-channel acoustic signal, and to acquire the target channel whose signal feature values ​​exceed the signal feature threshold.

[0031] The sound source power determination module is used to determine multiple scanning points in the scanning plane and determine the sound source power corresponding to each scanning point based on the channel acoustic signal corresponding to the target channel.

[0032] The sound field distribution map determination module is used to obtain the sound field distribution map based on the sound source power of each scanning point in the scanning plane.

[0033] The fault source localization module is used to acquire the monitoring screen obtained by image acquisition of the target object, and to locate the fault source based on the sound field distribution map and the monitoring screen.

[0034] Thirdly, this application also provides a computer device. The computer device includes a memory and a processor, the memory storing a computer program, and the processor executing the computer program to perform the following steps:

[0035] The method involves acquiring multi-channel acoustic signals obtained by a microphone array from the sound of a target object. The microphone array is an array composed of multiple concentric rings, and any three microphones in the array are coplanar but not collinear.

[0036] Based on the multi-channel acoustic signals, the signal feature values ​​corresponding to each channel acoustic signal are calculated, and the target channel whose signal feature value exceeds the signal feature threshold is obtained;

[0037] Multiple scanning points in the scanning plane are determined, and the sound source power corresponding to each scanning point is determined based on the channel acoustic signal corresponding to the target channel.

[0038] The sound field distribution map is obtained based on the sound source power at each scanning point in the scanning plane.

[0039] The monitoring screen obtained by image acquisition of the target object is acquired, and the fault source is located based on the sound field distribution map and the monitoring screen.

[0040] Fourthly, this application also provides a computer-readable storage medium. The computer-readable storage medium stores a computer program thereon, which, when executed by a processor, performs the following steps:

[0041] The method involves acquiring multi-channel acoustic signals obtained by a microphone array from the sound of a target object. The microphone array is an array composed of multiple concentric rings, and any three microphones in the array are coplanar but not collinear.

[0042] Based on the multi-channel acoustic signals, the signal feature values ​​corresponding to each channel acoustic signal are calculated, and the target channel whose signal feature value exceeds the signal feature threshold is obtained;

[0043] Multiple scanning points in the scanning plane are determined, and the sound source power corresponding to each scanning point is determined based on the channel acoustic signal corresponding to the target channel.

[0044] The sound field distribution map is obtained based on the sound source power at each scanning point in the scanning plane.

[0045] The monitoring screen obtained by image acquisition of the target object is acquired, and the fault source is located based on the sound field distribution map and the monitoring screen.

[0046] Fifthly, this application also provides a computer program product. The computer program product includes a computer program that, when executed by a processor, performs the following steps:

[0047] The method involves acquiring multi-channel acoustic signals obtained by a microphone array from the sound of a target object. The microphone array is an array composed of multiple concentric rings, and any three microphones in the array are coplanar but not collinear.

[0048] Based on the multi-channel acoustic signals, the signal feature values ​​corresponding to each channel acoustic signal are calculated, and the target channel whose signal feature value exceeds the signal feature threshold is obtained;

[0049] Multiple scanning points in the scanning plane are determined, and the sound source power corresponding to each scanning point is determined based on the channel acoustic signal corresponding to the target channel.

[0050] The sound field distribution map is obtained based on the sound source power at each scanning point in the scanning plane.

[0051] The monitoring screen obtained by image acquisition of the target object is acquired, and the fault source is located based on the sound field distribution map and the monitoring screen.

[0052] The aforementioned fault location method, apparatus, computer equipment, storage medium, and computer program product acquire multi-channel acoustic signals from a microphone array that collects sound from a target object. The microphone array is composed of multiple concentric rings, with any three microphones in the array being coplanar but not collinear. Then, the signal characteristic values ​​corresponding to each channel's acoustic signal are calculated based on the multi-channel acoustic signals, and target channels whose signal characteristic values ​​exceed a signal characteristic threshold are identified. Next, multiple scanning points in the scanning plane are determined, and the sound source power corresponding to each scanning point is determined based on the channel acoustic signal corresponding to the target channel. A sound field distribution map is then obtained based on the sound source power of each scanning point in the scanning plane. Finally, a monitoring image obtained by acquiring an image of the target object is acquired, and the fault source is located based on the sound field distribution map and the monitoring image. Thus, by using an optimized microphone array to collect fault acoustic signals and obtaining a sound field distribution map based on the filtered fault acoustic signals, the robustness of sound source location can be improved, thereby achieving accurate fault source location. Attached Figure Description

[0053] Figure 1 This is a diagram illustrating the application environment of a fault location method in one embodiment.

[0054] Figure 2 This is a flowchart illustrating a fault location method in one embodiment;

[0055] Figure 3 This is a flowchart illustrating a fault location method in another embodiment;

[0056] Figure 4 This is a schematic diagram of the microphone array layout in one embodiment;

[0057] Figure 5 This is a structural block diagram of a fault location device in one embodiment;

[0058] Figure 6 This is an internal structural diagram of a computer device in one embodiment. Detailed Implementation

[0059] To make the objectives, technical solutions, and advantages of this application clearer, the following detailed description is provided in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative and not intended to limit the scope of this application.

[0060] It should be noted that the terms "comprising," "including," "having," and any variations thereof, as used in this application, are intended to cover non-exclusive inclusion. For example, a process, method, product, or apparatus that includes a series of steps or means is not necessarily limited to the steps that are clearly listed, but may also include other steps or means that are not clearly listed or that are inherent to such process, method, product, or apparatus. The term "and / or" as used in this application includes any and all combinations of one or more of the associated listed items.

[0061] The fault location method provided in this application embodiment can be applied to, for example, Figure 1 In the application environment shown, microphone array 104 communicates with computer device 102 via a network, and camera 106 communicates with computer device 102 via a network, with camera 106 mounted in the middle of microphone array 104. A data storage system can store the data that computer device 102 needs to process. The data storage system can be integrated into computer device 102 or placed in the cloud or on other network servers. Computer device 102 acquires multi-channel sound signals by acquiring sound from the target object through microphone array 104, and sends the acquired multi-channel sound signals to computer device 102. Computer device 102 acquires the multi-channel sound signals obtained by microphone array 104 acquiring sound from the target object. Microphone array 104 is an array composed of multiple concentric rings, and any three microphones in the array are coplanar but not collinear. Then, computer device 102 calculates the signal characteristic values ​​corresponding to each channel of the sound signal based on the multi-channel sound signals and identifies the target channel whose signal characteristic value exceeds the signal characteristic threshold. Then, computer device 102 determines multiple scanning points in the scanning plane through camera 106, and then determines the sound source power corresponding to each scanning point based on the channel acoustic signal corresponding to the target channel. Next, computer device 102 obtains a sound field distribution map based on the sound source power of each scanning point in the scanning plane; finally, it acquires the monitoring image obtained by image acquisition of the target object through camera 106, and locates the fault source based on the sound field distribution map and the monitoring image. Computer device 102 can be a terminal or a server. The terminal can be, but is not limited to, various personal computers, laptops, smartphones, tablets, IoT devices, and portable wearable devices. IoT devices can be smart TVs, smart in-vehicle devices, etc. Portable wearable devices can be smartwatches, smart bracelets, head-mounted devices, etc. The server can be implemented using a standalone server or a cluster of multiple servers.

[0062] In one embodiment, such as Figure 2 As shown, a fault location method is provided, which can be applied to... Figure 1 Taking a computer device as an example, the explanation includes the following steps:

[0063] Step 202: Obtain the multi-channel acoustic signal obtained by the microphone array from the target object. The microphone array is an array composed of multiple concentric rings, and any three microphones in the array are coplanar but not collinear.

[0064] A microphone array is a system that samples the spatial characteristics of a sound field by arranging a certain number of acoustic sensors in a specific manner. In this embodiment, the microphone array used is an array composed of multiple concentric rings, where any three microphones in the array are coplanar but not collinear. The target object is the object for which fault location needs to be performed. The target object can be a rotating machine, such as a rolling bearing.

[0065] Specifically, each microphone in the microphone array corresponds to one channel, and each microphone can obtain one channel of sound signal by capturing sound from the target object. The microphone array contains multiple microphones (e.g., 36), therefore, it can obtain multi-channel sound signals by capturing sound from the target object. After obtaining multi-channel sound signals by capturing sound from the target object, the microphone array sends these signals to a computer device. The computer device then acquires the multi-channel sound signals obtained by the microphone array from capturing sound from the target object, where each channel of sound signal includes multiple sound signal data.

[0066] Step 204: Solve for the signal feature values ​​corresponding to each channel of the multi-channel acoustic signal, and obtain the target channel whose signal feature values ​​exceed the signal feature threshold.

[0067] Among them, the signal characteristic value is a numerical value that comprehensively reflects the fluctuation degree, dispersion degree, and impact characteristics of the acquired acoustic signal. The signal characteristic threshold characterizes the extreme value of the signal characteristics under normal operating conditions. The target channel is the channel obtained after screening.

[0068] Specifically, after acquiring multi-channel acoustic signals from a microphone array that captures sound from a target object, the computer equipment processes these signals to calculate the signal feature values ​​corresponding to each channel. After obtaining the signal feature values ​​for each channel, the computer equipment compares these values ​​with a signal feature threshold. If a signal feature value exceeds the threshold, the channel corresponding to that value is retained; otherwise, it is discarded. This allows the computer equipment to identify target channels whose signal feature values ​​exceed the threshold.

[0069] In one embodiment, the process of solving for the signal feature values ​​corresponding to each channel acoustic signal based on the multi-channel acoustic signal includes: solving for the range, variance, and kurtosis corresponding to each channel acoustic signal based on the multi-channel acoustic signal; and calculating the signal feature values ​​corresponding to each channel acoustic signal based on the range, variance, and kurtosis corresponding to each channel acoustic signal.

[0070] Among them, the range reflects the fluctuation of each channel signal; the variance reflects the dispersion of each channel signal; and the kurtosis reflects the impulse characteristics of each channel signal.

[0071] Specifically, after the computer device acquires the multi-channel sound signal obtained by the microphone array from the target object, for each channel of the acquired multi-channel sound signal, the maximum, minimum, and average values ​​of the multiple sound signal data in each channel are obtained. The maximum value of the multiple sound signal data in each channel is subtracted from the minimum value to obtain the range of the sound signal in each channel. The squares of the differences between each sound signal data and the average value in each channel are summed and then divided by the number of sound signal data in each channel to obtain the variance of the sound signal in each channel. The fourth central moment of each sound signal data in each channel is divided by the fourth power of the standard deviation to obtain the kurtosis of the sound signal in each channel. Furthermore, the computer device can calculate the range, variance, and kurtosis corresponding to each channel sound signal according to equation (1) to obtain the signal characteristic values ​​corresponding to each channel sound signal:

[0072]

[0073] Where P is the range, V is the variance, K is the kurtosis, and PVK is the signal eigenvalue.

[0074] Step 206: Determine multiple scanning points in the scanning plane, and determine the sound source power corresponding to each scanning point based on the channel acoustic signal corresponding to the target channel.

[0075] The scanning plane is the plane obtained by the camera scanning the target object, and it contains multiple scanning points. Sound source power is the sound energy radiated outward by the sound source per unit time.

[0076] Specifically, a camera is installed in the center of the microphone array. The camera scans the target object to obtain a scanning plane, which contains multiple scanning points. The camera sends the scanning plane to a computer. After receiving the scanning plane from the camera, the computer can determine the multiple scanning points in the scanning plane, and then process the channel acoustic signal corresponding to the target channel to determine the sound source power corresponding to each scanning point.

[0077] In one embodiment, determining the sound source power corresponding to each scanning point based on the channel acoustic signal corresponding to the target channel includes: determining the cross-spectrum matrix based on the channel signal corresponding to the target channel; and determining the sound source power of each scanning point based on the coordinate vector of each target channel, the turning vector of each scanning point, and the cross-spectrum matrix.

[0078] The cross-spectral matrix is ​​a matrix that describes the statistical correlation between two signals in the frequency domain. The coordinate vector is a vector used to determine the position of the target channel on the scanning plane. The steering vector is a vector used to perform steering transformations at each scanning point.

[0079] Specifically, the computer device performs a Fourier transform on the acoustic signals of the selected target channels to obtain their spectral characteristic matrix, and then performs cross-spectral calculation to determine the cross-spectral matrix of the acquired acoustic signals of the target channels. Furthermore, based on the coordinate vector of each target channel, the turning vector of each scanning point, and the cross-spectral matrix of the acoustic signals of the target channels, the computer device determines the sound source power of each scanning point.

[0080] In this embodiment, the cross-spectrum matrix is ​​determined based on the channel signal corresponding to the target channel; then, the sound source power of each scanning point is determined based on the coordinate vector of each target channel, the turning vector of each scanning point, and the cross-spectrum matrix. This enables the sound field distribution map to be obtained based on the screened fault sound signal, improving the robustness of sound source localization and achieving accurate localization of the fault source.

[0081] Step 208: Obtain the sound field distribution map based on the sound source power at each scanning point in the scanning plane.

[0082] Among them, the sound field distribution map is a distribution map of the areas where sound waves exist.

[0083] Specifically, after the computer equipment determines the sound source power corresponding to each scanning point in the scanning plane, it processes the sound source power corresponding to each scanning point in the scanning plane to obtain a sound field distribution map.

[0084] Step 210: Obtain the monitoring screen obtained by image acquisition of the target object, and locate the fault source based on the sound field distribution map and the monitoring screen.

[0085] The fault source is the location in the target object where a fault occurs.

[0086] Specifically, after obtaining the sound field distribution map, the computer equipment acquires a monitoring image of the target object from the camera. It can be understood that the scanning points in the sound field distribution map showing abnormal sound source power are highly likely to be the location of the fault. Furthermore, the sound field distribution map and the acquired monitoring image of the target object can be overlaid to find the specific location in the monitoring image corresponding to the scanning points in the sound field distribution map showing abnormal sound source power. This specific location is then determined as the location of the fault within the target object.

[0087] The aforementioned fault location method acquires multi-channel acoustic signals from a microphone array that collects sound from a target object. The microphone array consists of multiple concentric rings, with any three microphones in the array being coplanar but not collinear. Then, it calculates the signal characteristic values ​​corresponding to each channel's acoustic signal and identifies target channels whose signal characteristic values ​​exceed a threshold. Next, it determines multiple scanning points in a scanning plane and, based on the acoustic signals corresponding to the target channels, determines the sound source power corresponding to each scanning point. This results in a sound field distribution map obtained from the sound source power at each scanning point in the scanning plane. Finally, it acquires a monitoring image of the target object and uses the sound field distribution map and the monitoring image to locate the fault source. By using an optimized microphone array to collect fault acoustic signals and obtaining a sound field distribution map from the filtered fault acoustic signals, the robustness of sound source location is improved, thus achieving accurate fault source localization.

[0088] In one embodiment, the step of determining the signal feature threshold includes: acquiring multiple sets of reference acoustic signals obtained by the microphone array collecting sound from a preset object; solving for multiple reference signal feature values ​​based on the multiple sets of reference acoustic information; determining the signal feature threshold based on the multiple reference signal feature values; and ensuring that the signal feature threshold is greater than any of the reference signal feature values.

[0089] The preset object is an object under normal operating conditions.

[0090] Specifically, the microphone array collects sound from an object under normal operating conditions, obtaining multiple sets (e.g., 60 sets) of reference sound signals. These signals are then sent to a computer. The computer processes these signals to obtain the range, variance, and kurtosis for each set. Based on equation (1), the range, variance, and kurtosis are calculated to obtain multiple (e.g., 60) reference signal feature values. The computer then selects the signal feature extremum greater than any of the reference signal feature values ​​as the signal feature threshold.

[0091] In this embodiment, multiple sets of reference acoustic signals are obtained by acquiring sound from a preset object using a microphone array. The preset object is an object under normal operating conditions. Multiple reference signal feature values ​​are obtained based on the multiple sets of reference acoustic information. Then, the extreme value of the signal feature greater than any of the reference signal feature values ​​is selected as the signal feature threshold. In this way, by determining the signal feature threshold using multiple sets of reference signal feature values ​​under normal operating conditions, and then filtering the channel using the signal feature threshold, the robustness of sound source localization can be improved, thereby achieving accurate location of the fault source.

[0092] In one embodiment, determining multiple scanning points in the scanning plane includes: determining a scanning range based on the target object; scanning the scanning range from the horizontal and vertical directions with a preset step size to obtain a scanning plane; and the intersection of the scanning line obtained by the horizontal scanning and the scanning line obtained by the vertical scanning in the scanning plane is the scanning point.

[0093] The preset step size is the scan step size that is pre-set in the computer device.

[0094] Specifically, the computer equipment determines the size of the test platform based on the structural dimensions of the target object, and then determines the scanning plane range based on the test platform size. The computer equipment then sends a preset step size and the determined scanning plane range to the camera. The camera scans horizontally and vertically within the determined scanning plane range according to the preset step size to obtain the scanning plane. It should be noted that the camera scans horizontally according to the preset step size to obtain multiple horizontal scan lines spaced at preset step sizes, and the camera scans vertically according to the preset step size to obtain multiple vertical scan lines spaced at preset step sizes. The intersection points of the horizontal and vertical scan lines are the scan points. Multiple horizontal and vertical scan lines have multiple intersection points, thus allowing multiple scan points to be determined on the scanning plane.

[0095] In this embodiment, a scanning plane is obtained by determining the scanning range based on the target object and scanning the range horizontally and vertically with a preset step size. The intersection of the scanning lines obtained by the horizontal scan and the scanning lines obtained by the vertical scan on the scanning plane is then identified as scanning points. In this way, by confirming the scanning plane through the target object, and subsequently confirming multiple scanning points on the scanning plane, a relationship between the target object and the scanning points can be established, thereby achieving precise location of the fault source.

[0096] In one embodiment, fault source localization is performed based on the sound field distribution map and the monitoring screen, including: determining the scanning point with the highest sound source power in the sound field distribution map; superimposing the sound field distribution map and the monitoring screen, and determining the target location in the monitoring screen that is the same as the scanning point with the highest sound source power, and identifying the target location as the fault source.

[0097] Specifically, after the computer equipment obtains the sound field distribution map, it searches for the scanning point with the highest sound source power based on the peak value in the sound field distribution map. Then, it overlays the sound field distribution map with the acquired monitoring screen of the target object and determines the target location in the monitoring screen that corresponds to the scanning point with the highest sound source power in the sound field distribution map. The target location is then identified as the source of the fault.

[0098] In this embodiment, by determining the scanning point with the highest sound source power in the sound field distribution map and superimposing the sound field distribution map and the monitoring screen, the target position of the scanning point with the highest sound source power in the monitoring screen is determined. The target position is identified as the fault source, which can visualize the location of the fault source and thus achieve accurate positioning of the fault source.

[0099] The following is for reference. Figure 3 The fault diagnosis method of this application will be described in detail with a specific embodiment:

[0100] In this embodiment, the following is adopted: Figure 4 The 36-channel microphone array shown collects sound signals to simulate a real far-field model. The microphone array is ring-shaped, with an inner ring diameter of 192.93 mm containing 8 microphones, a second ring diameter of 148.05 mm containing 12 microphones, and an outer ring diameter of 84.85 mm containing 16 microphones. The microphone layout incorporates structures such as spiral and circular arrays, combining the advantages of various array types. Any three (or more) microphones in the array are on the same plane but not collinear.

[0101] After the 36-channel microphone array collects sound from the faulty rolling bearing and obtains multi-channel sound signals, it sends the collected multi-channel sound signals to a computer device. Then, the computer device calculates the signal characteristic value (PVK value) corresponding to each channel sound signal according to equation (1):

[0102]

[0103] Where P is the range, reflecting the degree of signal fluctuation; V is the variance, reflecting the degree of signal dispersion; K is the kurtosis, reflecting the impulse characteristics of the signal; and PVK is the signal eigenvalue.

[0104] It should be noted that the 36-channel microphone array also needs to collect sound from 60 sets of rolling bearings under normal operating conditions to obtain 60 sets of reference sound signals, and send the 60 sets of reference sound signals to the computer equipment. The computer equipment processes the 60 sets of reference sound signals according to equation (1) to obtain 60 sets of reference signal feature values ​​(PVK values). It can be seen from the processing of the 60 sets of reference signal feature values ​​(PVK values) that the maximum value of the 60 sets of reference signal feature values ​​(PVK values) is less than 100. Therefore, the signal feature threshold (PVK1) is set to 100. Then, the computer equipment compares the signal feature values ​​(PVK values) of the multi-channel sound signals with the signal feature threshold (PVK1) respectively. If the signal feature value (PVK value) of a specific channel sound signal is greater than the signal feature threshold (PVK1), the channel is retained. If the signal feature value (PVK value) of a specific channel sound signal is less than the signal feature threshold (PVK1), the channel is discarded. Then, the channel selection is completed, and the channels with signal feature values ​​(PVK values) greater than 100 are used as inputs for calculating the sound field distribution.

[0105] After the computer equipment completes channel selection, based on the test bench dimensions of the rolling bearing, the scanning range x∈[-1.25,0.25]m and z∈[-0.99,0.01]m are set. Furthermore, to ensure positioning accuracy, the scanning step size is set to 0.01m, thereby determining the scanning plane and constructing a coordinate system on it. Then, the sound source power at each scanning point within the scanning plane is calculated using the Least Mean Square Distortionless Response (MVDR) algorithm. By traversing the entire scanning plane, a sound field distribution map of the scanning plane is obtained (e.g., a three-dimensional beam power map of a bearing outer ring fault).

[0106] After the computer equipment obtains the sound field distribution map of the scanning plane, it searches for the coordinates (0.19, -0.40)m corresponding to the maximum sound source power based on the peak size in the sound field distribution map. This coordinate is the location of the fault source. The coordinate system of the sound field distribution map is superimposed with the coordinate system of the camera monitoring screen to obtain a visualization map of the fault source location. It is found that the map is close to the actual location (0.14, -0.44)m where the rolling bearing fault occurred, thus realizing the location of the fault in the outer ring of the rolling bearing.

[0107] In this embodiment, multi-channel acoustic signals are acquired by using a microphone array to collect sound from a target object. The microphone array consists of multiple concentric rings, with any three microphones in the array being coplanar but not collinear. Then, the signal characteristic values ​​corresponding to each channel are calculated based on the multi-channel acoustic signals, and target channels whose signal characteristic values ​​exceed a signal characteristic threshold are identified. Next, multiple scanning points in the scanning plane are determined, and the sound source power corresponding to each scanning point is determined based on the channel acoustic signal corresponding to the target channel. A sound field distribution map is then obtained based on the sound source power of each scanning point in the scanning plane. Finally, a monitoring image of the target object is acquired, and the fault source is located based on the sound field distribution map and the monitoring image. Thus, by using an optimized microphone array to collect fault acoustic signals and obtaining a sound field distribution map based on the filtered fault acoustic signals, the robustness of sound source localization is improved, thereby achieving accurate fault source localization.

[0108] It should be understood that although the steps in the flowcharts of the embodiments described above are shown sequentially according to the arrows, these steps are not necessarily executed in the order indicated by the arrows. Unless explicitly stated herein, there is no strict order restriction on the execution of these steps, and they can be executed in other orders. Moreover, at least some steps in the flowcharts of the embodiments described above may include multiple steps or multiple stages. These steps or stages are not necessarily completed at the same time, but can be executed at different times. The execution order of these steps or stages is not necessarily sequential, but can be performed alternately or in turn with other steps or at least some of the steps or stages of other steps.

[0109] In one embodiment, such as Figure 5 As shown, based on the same inventive concept, this application also provides a fault location device 500, including: an acoustic signal acquisition module 501, a target channel acquisition module 502, an acoustic source power determination module 503, an acoustic field distribution map determination module 504, and a fault source location module 505, wherein:

[0110] The sound signal acquisition module is used to acquire multi-channel sound signals obtained by the microphone array from the sound collection of the target object. The microphone array is an array composed of multiple concentric rings, and any three microphones in the array are coplanar but not collinear.

[0111] The target channel acquisition module is used to solve the signal feature values ​​corresponding to each channel of the multi-channel acoustic signal, and to acquire the target channel whose signal feature values ​​exceed the signal feature threshold.

[0112] The sound source power determination module is used to determine multiple scanning points in the scanning plane and determine the sound source power corresponding to each scanning point based on the channel acoustic signal corresponding to the target channel.

[0113] The sound field distribution map determination module is used to obtain the sound field distribution map based on the sound source power of each scanning point in the scanning plane.

[0114] The fault source localization module is used to acquire monitoring images obtained from image acquisition of the target object, and to locate the fault source based on the sound field distribution map and the monitoring images.

[0115] In one embodiment, the target channel acquisition module is further configured to solve for the range, variance, and kurtosis of each channel acoustic signal based on the multi-channel acoustic signal; and to calculate the signal feature values ​​corresponding to each channel acoustic signal based on the range, variance, and kurtosis of each channel acoustic signal.

[0116] In one embodiment, the target channel acquisition module is further configured to acquire multiple sets of reference acoustic signals obtained by the microphone array collecting sound from a preset object; wherein the preset object is an object under normal operating conditions; multiple reference signal feature values ​​are obtained by solving based on the multiple sets of reference acoustic information; a signal feature threshold is determined based on the multiple reference signal feature values; and the signal feature threshold is greater than any reference signal feature value.

[0117] In one embodiment, the sound source power determination module is further configured to determine the scanning range based on the target object; scan the scanning range from the horizontal and vertical directions with a preset step size to obtain a scanning plane; the intersection of the scanning line obtained by the horizontal scanning and the scanning line obtained by the vertical scanning in the scanning plane is the scanning point.

[0118] In one embodiment, the sound source power determination module is further configured to determine the cross-spectrum matrix based on the channel signal corresponding to the target channel; and to determine the sound source power of each scanning point based on the coordinate vector of each target channel, the turning vector of each scanning point, and the cross-spectrum matrix.

[0119] In one embodiment, the fault source location module is further configured to determine the scanning point with the highest sound source power in the sound field distribution map; superimpose the sound field distribution map and the monitoring screen, and determine the target location in the monitoring screen that is the scanning point with the highest sound source power, and identify the target location as the fault source.

[0120] Each module in the aforementioned fault location device can be implemented entirely or partially through software, hardware, or a combination thereof. These modules can be embedded in the processor of a computer device in hardware form or independent of it, or stored in the memory of a computer device in software form, so that the processor can call and execute the corresponding operations of each module.

[0121] In one embodiment, a computer device is provided, which may be a terminal, and its internal structure diagram may be as follows: Figure 6 As shown, the computer device includes a processor, memory, input / output interfaces, a communication interface, a display unit, and an input device. The processor, memory, and input / output interfaces are connected via a system bus, and the communication interface, display unit, and input device are also connected to the system bus via the input / output interfaces. The processor provides computational and control capabilities. The memory includes non-volatile storage media and internal memory. The non-volatile storage media stores the operating system and computer programs. The internal memory provides an environment for the operation of the operating system and computer programs stored in the non-volatile storage media. The input / output interfaces are used for exchanging information between the processor and external devices. The communication interface is used for wired or wireless communication with external terminals; wireless communication can be achieved through Wi-Fi, mobile cellular networks, NFC (Near Field Communication), or other technologies. When the computer program is executed by the processor, it implements a fault location method. The display unit is used to form a visually visible image and can be a display screen, a projection device, or a virtual reality imaging device. The display screen can be an LCD screen or an e-ink screen. The input device of the computer device can be a touch layer covering the display screen, or buttons, trackballs, or touchpads set on the casing of the computer device, or external keyboards, touchpads, or mice, etc.

[0122] Those skilled in the art will understand that Figure 6 The structure shown is merely a block diagram of a portion of the structure related to the present application and does not constitute a limitation on the computer device to which the present application is applied. Specific computer devices may include more or fewer components than those shown in the figure, or combine certain components, or have different component arrangements.

[0123] In one embodiment, a computer device is provided, including a memory and a processor. The memory stores a computer program, and the processor executes the computer program to perform the following steps: acquiring multi-channel acoustic signals obtained by a microphone array collecting sound from a target object, wherein the microphone array is an array composed of multiple concentric rings, and any three microphones in the array are coplanar but not collinear; solving for the signal feature values ​​corresponding to each channel acoustic signal based on the multi-channel acoustic signals, and acquiring the target channel whose signal feature values ​​exceed the signal feature threshold; determining multiple scanning points in a scanning plane, and determining the sound source power corresponding to each scanning point based on the channel acoustic signal corresponding to the target channel; obtaining a sound field distribution map based on the sound source power of each scanning point in the scanning plane; acquiring a monitoring image obtained by image acquisition of the target object, and locating the fault source based on the sound field distribution map and the monitoring image.

[0124] In one embodiment, when the processor executes the computer program, it further performs the following steps: solving for the range, variance, and kurtosis of each channel acoustic signal based on the multi-channel acoustic signal; and calculating the signal feature values ​​corresponding to each channel acoustic signal based on the range, variance, and kurtosis of each channel acoustic signal.

[0125] In one embodiment, when the processor executes the computer program, it further performs the following steps: acquiring multiple sets of reference acoustic signals obtained by the microphone array collecting sound from a preset object; wherein the preset object is an object under normal operating conditions; solving for multiple reference signal feature values ​​based on the multiple sets of reference acoustic information; determining a signal feature threshold based on the multiple reference signal feature values; the signal feature threshold is greater than any reference signal feature value.

[0126] In one embodiment, when the processor executes the computer program, it further performs the following steps: determining the scanning range based on the target object; scanning the scanning range from the horizontal and vertical directions with a preset step size to obtain a scanning plane; and the intersection of the scanning line obtained by the horizontal scanning and the scanning line obtained by the vertical scanning in the scanning plane is the scanning point.

[0127] In one embodiment, when the processor executes the computer program, it further performs the following steps: determining the cross-spectrum matrix based on the channel signal corresponding to the target channel; and determining the sound source power of each scan point based on the coordinate vector of each target channel, the turning vector of each scan point, and the cross-spectrum matrix.

[0128] In one embodiment, when the processor executes the computer program, it further performs the following steps: determining the scanning point with the highest sound source power in the sound field distribution map; superimposing the sound field distribution map and the monitoring screen, and determining the target location in the monitoring screen that is the scanning point with the highest sound source power, and identifying the target location as the fault source.

[0129] In one embodiment, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, it performs the following steps: acquiring multi-channel acoustic signals obtained by a microphone array collecting sound from a target object, wherein the microphone array is an array composed of multiple concentric rings, and any three microphones in the array are coplanar but not collinear; solving for the signal feature values ​​corresponding to each channel acoustic signal based on the multi-channel acoustic signals, and acquiring the target channel whose signal feature values ​​exceed the signal feature threshold; determining multiple scanning points in a scanning plane, and determining the sound source power corresponding to each scanning point based on the channel acoustic signal corresponding to the target channel; obtaining a sound field distribution map based on the sound source power of each scanning point in the scanning plane; acquiring a monitoring image obtained by image acquisition of the target object, and locating the fault source based on the sound field distribution map and the monitoring image.

[0130] In one embodiment, when the computer program is executed by the processor, it further performs the following steps: solving for the range, variance, and kurtosis of each channel acoustic signal based on the multi-channel acoustic signal; and calculating the signal feature values ​​corresponding to each channel acoustic signal based on the range, variance, and kurtosis of each channel acoustic signal.

[0131] In one embodiment, when the computer program is executed by the processor, it further performs the following steps: acquiring multiple sets of reference acoustic signals obtained by the microphone array collecting sound from a preset object; wherein the preset object is an object under normal operating conditions; solving for multiple reference signal feature values ​​based on the multiple sets of reference acoustic information; determining a signal feature threshold based on the multiple reference signal feature values; the signal feature threshold is greater than any reference signal feature value.

[0132] In one embodiment, when the computer program is executed by the processor, it further performs the following steps: determining the scanning range according to the target object; scanning the scanning range from the horizontal and vertical directions with a preset step size to obtain a scanning plane; and the intersection of the scanning line obtained by the horizontal scanning and the scanning line obtained by the vertical scanning in the scanning plane is the scanning point.

[0133] In one embodiment, when the computer program is executed by the processor, it further performs the following steps: determining the cross-spectrum matrix based on the channel signal corresponding to the target channel; and determining the sound source power of each scan point based on the coordinate vector of each target channel, the turning vector of each scan point, and the cross-spectrum matrix.

[0134] In one embodiment, when the computer program is executed by the processor, it further performs the following steps: determining the scanning point with the highest sound source power in the sound field distribution map; superimposing the sound field distribution map and the monitoring screen, and determining the target location in the monitoring screen that is the scanning point with the highest sound source power, and identifying the target location as the fault source.

[0135] In one embodiment, a computer program product is provided, including a computer program that, when executed by a processor, performs the following steps: acquiring multi-channel acoustic signals obtained by a microphone array collecting sound from a target object, wherein the microphone array is an array composed of multiple concentric rings, and any three microphones in the array are coplanar but not collinear; solving for the signal feature values ​​corresponding to each channel acoustic signal based on the multi-channel acoustic signals, and acquiring the target channel whose signal feature values ​​exceed a signal feature threshold; determining multiple scanning points in a scanning plane, and determining the sound source power corresponding to each scanning point based on the channel acoustic signal corresponding to the target channel; and obtaining a sound field distribution map based on the sound source power of each scanning point in the scanning plane.

[0136] The system acquires monitoring images of the target object and locates the fault source based on the sound field distribution map and the monitoring images.

[0137] In one embodiment, when the computer program is executed by the processor, it further performs the following steps: solving for the range, variance, and kurtosis of each channel acoustic signal based on the multi-channel acoustic signal; and calculating the signal feature values ​​corresponding to each channel acoustic signal based on the range, variance, and kurtosis of each channel acoustic signal.

[0138] In one embodiment, when the computer program is executed by the processor, it further performs the following steps: acquiring multiple sets of reference acoustic signals obtained by the microphone array collecting sound from a preset object; wherein the preset object is an object under normal operating conditions; solving for multiple reference signal feature values ​​based on the multiple sets of reference acoustic information; determining a signal feature threshold based on the multiple reference signal feature values; the signal feature threshold is greater than any reference signal feature value.

[0139] In one embodiment, when the computer program is executed by the processor, it further performs the following steps: determining the scanning range according to the target object; scanning the scanning range from the horizontal and vertical directions with a preset step size to obtain a scanning plane; and the intersection of the scanning line obtained by the horizontal scanning and the scanning line obtained by the vertical scanning in the scanning plane is the scanning point.

[0140] In one embodiment, when the computer program is executed by the processor, it further performs the following steps: determining the cross-spectrum matrix based on the channel signal corresponding to the target channel; and determining the sound source power of each scan point based on the coordinate vector of each target channel, the turning vector of each scan point, and the cross-spectrum matrix.

[0141] In one embodiment, when the computer program is executed by the processor, it further performs the following steps: determining the scanning point with the highest sound source power in the sound field distribution map; superimposing the sound field distribution map and the monitoring screen, and determining the target location in the monitoring screen that is the scanning point with the highest sound source power, and identifying the target location as the fault source.

[0142] Those skilled in the art will understand that all or part of the processes in the methods of the above embodiments can be implemented by a computer program instructing related hardware. The computer program can be stored in a non-volatile computer-readable storage medium, and when executed, it can include the processes of the embodiments of the above methods. Any references to memory, databases, or other media used in the embodiments provided in this application can include at least one of non-volatile and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. By way of illustration and not limitation, RAM can take many forms, such as Static Random Access Memory (SRAM) or Dynamic Random Access Memory (DRAM). The databases involved in the embodiments provided in this application may include at least one type of relational database and non-relational database. Non-relational databases may include, but are not limited to, blockchain-based distributed databases. The processors involved in the embodiments provided in this application may be general-purpose processors, central processing units, graphics processing units, digital signal processors, programmable logic devices, quantum computing-based data processing logic devices, etc., and are not limited to these.

[0143] The technical features of the above embodiments can be combined in any way. For the sake of brevity, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0144] The embodiments described above are merely illustrative of several implementation methods of this application, and while the descriptions are specific and detailed, they should not be construed as limiting the scope of this patent application. It should be noted that those skilled in the art can make various modifications and improvements without departing from the concept of this application, and these all fall within the protection scope of this application. Therefore, the protection scope of this application should be determined by the appended claims.

Claims

1. A fault location method, characterized in that, The method includes: The method involves acquiring multi-channel acoustic signals obtained by a microphone array from the sound of a target object. The microphone array is an array composed of multiple concentric rings, and any three microphones in the array are coplanar but not collinear. The signal feature values ​​corresponding to each channel of the multi-channel acoustic signal are calculated, and the target channel whose signal feature value exceeds the signal feature threshold is obtained; the signal feature value is a numerical value that comprehensively reflects the fluctuation degree, dispersion degree and impact characteristics of the obtained acoustic signal. Multiple scanning points in the scanning plane are determined, and the sound source power corresponding to each scanning point is determined based on the channel acoustic signal corresponding to the target channel. The sound field distribution map is obtained based on the sound source power at each scanning point in the scanning plane. Acquire monitoring images obtained by image acquisition of the target object, and locate the fault source based on the sound field distribution map and the monitoring images; Wherein, the signal feature threshold characterizes the extreme value of signal characteristics under normal operating conditions, and the steps for determining the signal feature threshold include: Multiple sets of reference acoustic signals are acquired by a microphone array to collect sound from a preset object; wherein the preset object is an object under normal operating conditions. Multiple reference signal feature values ​​are obtained by solving based on the multiple sets of reference acoustic information; A signal feature threshold is determined based on the plurality of reference signal feature values; the signal feature threshold is greater than any of the reference signal feature values.

2. The method according to claim 1, characterized in that, The step of solving for the signal feature values ​​corresponding to each channel of the acoustic signal based on the multi-channel acoustic signal includes: Based on the multi-channel acoustic signals, the range, variance, and kurtosis of each channel acoustic signal are calculated. Based on the range, variance, and kurtosis of each channel's acoustic signal, the corresponding signal characteristic values ​​for each channel's acoustic signal are calculated.

3. The method according to claim 1, characterized in that, The determination of multiple scan points in the scan plane includes: Determine the scanning range based on the target object; The scanning range is scanned horizontally and vertically with a preset step size to obtain a scanning plane; the intersection of the scanning line obtained by horizontal scanning and the scanning line obtained by vertical scanning in the scanning plane is the scanning point.

4. The method according to claim 1, characterized in that, The step of determining the sound source power corresponding to each scanning point based on the channel acoustic signal corresponding to the target channel includes: The cross-spectrum matrix is ​​determined based on the channel signal corresponding to the target channel; The sound source power of each scanning point is determined based on the coordinate vector of each target channel, the turning vector of each scanning point, and the cross-spectral matrix.

5. The method according to claim 1, characterized in that, The step of locating the fault source based on the sound field distribution map and the monitoring screen includes: Determine the scanning point with the highest sound source power in the sound field distribution map; The sound field distribution map and the monitoring screen are superimposed, and the target position of the scanning point with the highest sound source power in the monitoring screen is determined. The target position is then identified as the fault source.

6. A fault location device, characterized in that, The device includes: The sound signal acquisition module is used to acquire multi-channel sound signals obtained by the microphone array from the sound collection of the target object. The microphone array is an array composed of multiple concentric rings, and any three microphones in the array are coplanar but not collinear. The target channel acquisition module is used to solve the signal feature values ​​corresponding to each channel of the multi-channel acoustic signal, and to acquire the target channel whose signal feature values ​​exceed the signal feature threshold; the signal feature values ​​are numerical values ​​that comprehensively reflect the fluctuation degree, dispersion degree and impact characteristics of the acquired acoustic signal. The sound source power determination module is used to determine multiple scanning points in the scanning plane and determine the sound source power corresponding to each scanning point based on the channel acoustic signal corresponding to the target channel. The sound field distribution map determination module is used to obtain the sound field distribution map based on the sound source power of each scanning point in the scanning plane. The fault source localization module is used to acquire the monitoring screen obtained by image acquisition of the target object, and to locate the fault source based on the sound field distribution map and the monitoring screen; The target channel acquisition module is also used to acquire multiple sets of reference acoustic signals obtained by the microphone array collecting sound from a preset object; wherein, the preset object is an object under normal operating conditions; multiple reference signal feature values ​​are obtained based on the multiple sets of reference acoustic information; a signal feature threshold is determined based on the multiple reference signal feature values; the signal feature threshold is greater than any reference signal feature value.

7. The apparatus according to claim 6, characterized in that, The target channel acquisition module is also used to solve the range, variance and kurtosis of each channel acoustic signal according to the multi-channel acoustic signal; and to calculate the signal feature value corresponding to each channel acoustic signal according to the range, variance and kurtosis of each channel acoustic signal.

8. A computer device comprising a memory and a processor, wherein the memory stores a computer program, characterized in that, When the processor executes the computer program, it implements the steps of the method according to any one of claims 1 to 5.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by a processor, it implements the steps of the method according to any one of claims 1 to 5.

10. A computer program product, comprising a computer program, characterized in that, When the computer program is executed by a processor, it implements the steps of the method according to any one of claims 1 to 5.

Images