Abnormal working condition monitoring positioning method and system, electronic device, and storage medium

Abstract

The application discloses an abnormal working condition monitoring and positioning method and system, and the method comprises the following steps: A, respectively calibrating the space of the installed multiple acoustic cameras, and forming the corresponding relationship between the two-dimensional plane picture of the acoustic camera and the real three-dimensional space; B, fusing the three-dimensional model of the monitoring target into the coordinate system of the real three-dimensional space according to the real size; C, according to the division of the components and / or parts of the monitoring target, acquiring the space coordinate range of the components and / or parts; D, acquiring the space coordinate value of the monitored abnormal noise source in the coordinate system of the real three-dimensional space through calculation, and comparing the space coordinate value with the space coordinate range of the components and / or parts to obtain the position of the noise source; E, monitoring the abnormal working condition according to the position of the noise source and the collected noise signal characteristics.

Description

Technical Field

[0001] This invention relates to the fields of noise source localization, leakage detection, and online monitoring of equipment operating status in industrial equipment, and particularly to a method, system, electronic device, and storage medium for monitoring and locating abnormal operating conditions. Background Technology

[0002] With the continuous advancement of signal processing technology, sound source localization technology has become increasingly mature. Current sound source localization technology mainly uses multiple sound sensors placed at different spatial locations to collect multiple audio signals, analyzes the characteristics of the multiple audio signals, uses time delay algorithms to obtain the distance from the sound source to the multiple sound sensors, and then uses solid geometric calculation methods to obtain the spatial location of the sound source.

[0003] An acoustic camera, also known as a sound field imager, can simultaneously capture sound field distribution images from a microphone array and visible light video from a camera. After internal processing, the sound field images and video images are superimposed to visually display the sound field information of the actual object surface in the video image. However, both the sound field distribution image and the visible light video are two-dimensional images. The actual location of the sound source can be any point on a ray originating from the microphone array. Considering that the monitored object may have complex structures such as multiple layers of pipelines, a single acoustic camera cannot locate it in three-dimensional space, and therefore cannot accurately achieve functions such as noise source identification and leak detection.

[0004] Chinese invention patent application CN109254266A discloses a method and apparatus for sound source localization based on a microphone array. This prior art method first establishes a corresponding subarray coordinate system for each microphone subarray and a common coordinate system during the localization process. Then, the SRP-PHAT algorithm is used to calculate the direction vector of the sound source in each subarray coordinate system. Finally, each direction vector is normalized to the common coordinate system to calculate the position coordinates of the sound source in the common coordinate system. This method performs secondary processing on the sound signal to achieve sound source localization. The first processing obtains the subarray coordinates of the sound source, and the second processing obtains the common coordinates of the sound source. The secondary processing may have significant errors. Furthermore, in practical applications, taking petrochemical plants as an example, the monitored objects have complex structures such as multiple overlapping layers, and sound signals are prone to interference, diffraction, and reflection. The secondary processing relies on high-precision calculations, which may lead to significant errors in sound source localization.

[0005] Therefore, there is an urgent need for a method and system for monitoring and locating abnormal operating conditions of industrial equipment. Based on acoustic cameras, sound field distribution information and visible light video images are mapped into three-dimensional space and then fused with the three-dimensional spatial structure of the monitored object. This can accurately locate the spatial position of the noise source and, combined with the information of the monitored object, determine the abnormal operating conditions causing the noise.

[0006] The information disclosed in this background section is intended only to enhance the understanding of the overall background of the invention and should not be construed as an admission or in any way implying that the information constitutes prior art known to those skilled in the art. Summary of the Invention

[0007] The purpose of this invention is to provide a method and system for monitoring and locating abnormal operating conditions. Based on an acoustic camera, its two-dimensional information is mapped to three-dimensional space and then fused with the three-dimensional spatial structure of the monitored object. This can accurately locate the spatial position of the noise source and, combined with the information of the monitored target, determine the abnormal operating conditions causing the noise.

[0008] To achieve the above objectives, according to a first aspect of the present invention, the present invention provides a method for monitoring and locating abnormal operating conditions, comprising the following steps: A. Spatially calibrating multiple installed acoustic cameras to establish a correspondence between the two-dimensional planar images of the acoustic cameras and the real three-dimensional space; B. Merging the three-dimensional model of the monitored target into the coordinate system of the real three-dimensional space according to its actual size; C. Obtaining the spatial coordinate range of the components and / or parts according to the division of the monitored target components and / or parts; D. Calculating the spatial coordinate values ​​of the detected abnormal noise sources in the coordinate system of the real three-dimensional space and comparing them with the spatial coordinate range of the components and / or parts to obtain the location of the noise sources; E. Monitoring the abnormal operating conditions based on the location of the noise sources and the characteristics of the collected noise signals.

[0009] Furthermore, in the above technical solution, the acoustic camera may include a first acoustic camera and a second acoustic camera, which are set on opposite sides of the monitoring target.

[0010] Furthermore, in the above technical solution, the spatial calibration of the acoustic camera can be performed using the following specific steps:

[0011] First, record the position of the acoustic camera as point A in the two-dimensional plane image; then select a point B0 in the real three-dimensional space, placing it at the exact center of the two-dimensional plane image. The direction of the acoustic camera is then the direction vector from point A to point B0. Select another point B1 in the real three-dimensional space and make it visible in the two-dimensional plane image;

[0012] Secondly, in the coordinate system of real three-dimensional space, the coordinates of measurement points A, B0, and B1 are A(x0, y0, z0), B0(x0, y0, z0), and B1, respectively. B0 ,y B0 ,z B0 B1(x) B1 ,y B1 ,z B1 );

[0013] Next, let the coordinates of point B`1 be (x... B1 ,y B1 ,z B0 ), calculate the direction vector With direction vector The included angle β1; simultaneously calculate the direction vector. The angle θ1 between the point B1 and the x-axis; Using the two-dimensional plane image of the acoustic camera, obtain the mapping point B of point B1 and point B0 in the image. 11 With point B 01 Measure direction vector The angle α1 between the horizontal line and the horizontal line;

[0014] Finally, in the two-dimensional plane image, with the aforementioned mapping point B 01 Establish a planar coordinate system x1B with the origin as the origin. 01 y1, let Let the length of the projection onto the x1 axis be L1, and the length of the projection onto the y1 axis be L2. Calculate the mapping coefficients. Record the mapping coefficients to complete the spatial calibration of the acoustic camera.

[0015] Furthermore, in the above technical solution, step D, which involves calculating the spatial coordinates of the detected abnormal noise source in the real three-dimensional space coordinate system, can specifically include the following steps:

[0016] D1. When an abnormal noise source appears in the two-dimensional plane image, the center point of the noise source is located in the plane coordinate system x1B. 01 In y1, it is represented as M1(x 1M1 ,y 1M1 ), calculate the distance L from point M1 to the x1 and y1 axes of the coordinate system. 1M1 With L 2M1 ;

[0017] D2. Calculate cosβ M1 =Φ1·L 1M1 ;

[0018] D3, Pass The direction vector is used to obtain the first acoustic camera. The point-line form of the equation of the straight line is as follows:

[0019]

[0020] D4. Repeat steps D1 to D3 to obtain the second acoustic camera. The point-line form of the equation of the straight line is as follows:

[0021]

[0022] D5. Calculate the intersection of equation (1) and equation (2). The coordinates of the intersection are the coordinates of the real three-dimensional space of the abnormal noise source.

[0023] Furthermore, in the above technical solution, step E can be specifically described as follows: comparing the location of the noise source and the characteristics of the collected noise signal with the abnormal operating condition data in the fault database to determine the possible fault type and degree and issue a warning message.

[0024] Furthermore, in the above technical solution, barrel distortion and pincushion distortion can be eliminated from the two-dimensional planar image of the acoustic camera before spatial calibration.

[0025] According to a second aspect of the present invention, an abnormal operating condition monitoring and positioning system is provided, comprising: a spatial calibration unit for spatially calibrating multiple installed acoustic cameras respectively, establishing a correspondence between the two-dimensional planar images of the acoustic cameras and the real three-dimensional space; a target fusion unit for fusing the three-dimensional model of the monitored target into the coordinate system of the real three-dimensional space according to its actual size; a target segmentation unit for obtaining the spatial coordinate range of the components and / or parts according to the segmentation of the monitored target components and / or parts; a noise location acquisition unit for calculating the spatial coordinate values ​​of the detected abnormal noise sources in the coordinate system of the real three-dimensional space and comparing them with the spatial coordinate range of the components and / or parts to obtain the location of the noise sources; and an abnormal operating condition monitoring unit for monitoring abnormal operating conditions based on the location of the noise sources and the characteristics of the acquired noise signals.

[0026] Furthermore, in the above technical solution, the abnormal operating condition monitoring unit may specifically include: a data comparison subunit, used to compare the location of the noise source and the characteristics of the collected noise signal with the abnormal operating condition data in the fault database; and a fault judgment subunit, used to judge the possible fault type and degree and issue early warning information.

[0027] Furthermore, in the above technical solution, the system may also include an image preprocessing unit, which is used to eliminate barrel distortion and pincushion distortion of the two-dimensional planar image of the acoustic camera before spatial calibration.

[0028] According to a third aspect of the present invention, an electronic device is provided, 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, the instructions being executed by the at least one processor to cause the at least one processor to perform the method described in any of the preceding claims.

[0029] According to a fourth aspect of the present invention, a non-transitory computer-readable storage medium is provided, the non-transitory computer-readable storage medium storing computer-executable instructions for causing the computer to perform the method as described in any of the preceding claims.

[0030] Compared with the prior art, the present invention has one or more of the following beneficial effects:

[0031] 1) This invention integrates the three-dimensional spatial structure, two-dimensional video image, sound field distribution information and sound source localization information of the monitoring target, which can realize rapid identification and localization of anomalies based on hearing and vision, and is highly intuitive. It can promptly feed back the visual monitoring and identification results to the operation and maintenance personnel, and can be applied to fields such as industrial noise monitoring, leakage monitoring, and equipment status monitoring.

[0032] 2) This invention only requires processing the audio signal once to generate sound field coordinates in each array sub-coordinate system; then, the sound field coordinates are superimposed on the planar image to obtain the sound source image sub-coordinate system coordinates; finally, the coordinates of two or more sets of two-dimensional planar images are mapped to three-dimensional space to obtain the coordinates of the noise source in three-dimensional space, thereby determining its true location. The sound signal is processed only once, avoiding the amplification of errors;

[0033] 3) After obtaining the three-dimensional spatial coordinates of the noise source, the present invention can compare the coordinate values ​​with the three-dimensional model of the monitoring target and locate the target by combining the structural characteristics of the monitoring target, which can reduce the positioning error caused by the complexity of the structure.

[0034] 4) Based on the use of multiple acoustic cameras, this invention maps two-dimensional information into three-dimensional space, and then superimposes it with the three-dimensional spatial structure of the monitored object to locate the location of abnormal noise. Then, it compares the audio characteristics of the abnormal noise, the location of the sound source, and the parts of the sound source with the fault database of the monitored target to comprehensively judge the possible fault type and degree, and issues early warning or alarm information to the operation and maintenance personnel.

[0035] The above description is merely an overview of the technical solution of the present invention. In order to better understand the technical means of the present invention and to implement it according to the contents of the specification, and to make the above and other objects, technical features and advantages of the present invention easier to understand, one or more preferred embodiments are listed below and described in detail with reference to the accompanying drawings. Attached Figure Description

[0036] Figure 1 This is a schematic diagram of the acoustic camera arrangement in the abnormal working condition monitoring and positioning method of Embodiment 1 of the present invention.

[0037] Figure 2 This is a flowchart illustrating the abnormal operating condition monitoring and location method of Embodiment 1 of the present invention.

[0038] Figure 3 This is a first schematic diagram of the spatial calibration calculation process in the abnormal working condition monitoring and positioning method of Embodiment 1 of the present invention.

[0039] Figure 4 This is a second schematic diagram of the spatial calibration calculation process in the abnormal working condition monitoring and positioning method of Embodiment 1 of the present invention.

[0040] Figure 5 This is a schematic diagram of the abnormal working condition monitoring and positioning system of Embodiment 2 of the present invention.

[0041] Figure 6 This is a schematic diagram of the abnormal working condition monitoring and positioning electronic device of Embodiment 5 of the present invention. Detailed Implementation

[0042] The specific embodiments of the present invention will now be described in detail with reference to the accompanying drawings, but it should be understood that the scope of protection of the present invention is not limited to the specific embodiments.

[0043] Unless otherwise expressly stated, throughout the specification and claims, the term "comprising" or its variations such as "including" or "comprising" shall be understood to include the stated elements or components without excluding other elements or other components.

[0044] In this document, for ease of description, spatial relative terms such as “below,” “under,” “down,” “above,” “above,” “up,” etc., are used to describe the relationship of one element or feature to another element or feature in the accompanying drawings. It should be understood that spatial relative terms are intended to encompass different orientations of an object in use or operation, in addition to those depicted in the figures. For example, if an object in the figure is flipped, an element described as “below” or “under” another element or feature would be oriented “above” that element or feature. Thus, the exemplary term “below” can encompass both the downward and upward orientations. An object may also have other orientations (rotated 90 degrees or other orientations), and the spatial relative terms used herein should be interpreted accordingly.

[0045] In this document, the terms "first," "second," etc., are used to distinguish two different elements or parts, and are not used to define specific positions or relative relationships. In other words, in some embodiments, the terms "first," "second," etc., can also be used interchangeably.

[0046] The methods, systems, electronic devices, and storage media of the present invention are described in more detail below by way of specific embodiments. It should be understood that the embodiments are merely exemplary and the present invention is not limited thereto.

[0047] like Figure 1As shown, this invention relates to a method and system for monitoring and locating abnormal operating conditions of industrial equipment based on acoustic cameras. The abnormal operating condition monitoring and location system consists of a first acoustic camera 1, a second acoustic camera 2, a data processing system 3, and other supporting components, used for monitoring and locating abnormal operating conditions of target 4. Abnormal operating conditions refer to the abnormal working state of industrial equipment and devices that can emit abnormal sounds. The method and system of this invention can be flexibly deployed according to usage requirements, comprehensively covering the monitoring of petrochemical plants. It can accurately locate the three-dimensional spatial position of abnormal sound sources and combine it with the two-dimensional video images and three-dimensional models of the monitored target device to make the location of abnormal sound sources more intuitive. This method and system only use the audio signal for location processing and calculation once, which can reduce the location error of abnormal sound sources.

[0048] Example 1

[0049] like Figure 2 As shown, the abnormal operating condition monitoring and location method of the present invention includes the following steps:

[0050] Step 101: Spatial calibration is performed on the multiple installed acoustic cameras to establish a correspondence between the two-dimensional planar images of the acoustic cameras and the actual three-dimensional space. This invention uses at least two acoustic cameras; this embodiment uses two acoustic cameras as an example (i.e., the first acoustic camera 1 and the second acoustic camera 2). The first acoustic camera 1 and the second acoustic camera 2 are placed on opposite sides of the monitoring target 4. To avoid signal interference, when there are two acoustic cameras, they cannot be placed on opposite sides. The acoustic cameras are connected to the data processing system 3 via wired or wireless means. Preferably, but not limitingly, before spatial calibration, distortion correction is performed on the two-dimensional video images of the acoustic cameras to eliminate barrel and pincushion distortion in the video images.

[0051] Further as Figure 3 , 4 As shown, the spatial calibration of the acoustic camera in this embodiment can be performed using the following specific steps:

[0052] First, adjust the orientation of the first acoustic camera 1 to meet the requirements of the monitoring target 4, adjust the lower edge of the two-dimensional video image to be horizontal with the ground, and record the position of the first acoustic camera 1 as point A.

[0053] Secondly, taking the first acoustic camera 1 as the calibration object, select a point B0 in the real three-dimensional space, placing it at the exact center of the two-dimensional video frame. Then, the pointing direction of the first acoustic camera 1 is the direction vector from point A to point B0. In the real three-dimensional space, select another point B1 and make it visible in the two-dimensional video image.

[0054] Next, a coordinate system xoyz is established in the real three-dimensional space. In this coordinate system, the coordinates of measurement points A, B0, and B1 are A(x0, y0, z0), B0(x0, y0, z0), and B1(x0, y0, z0), respectively. B0 ,y B0 ,z B0 B1(x) B1 ,y B1 ,z B1 ).

[0055] Then, let the coordinates of point B`1 be (x B1 ,y B1 ,z B0 ), then we have Parallel to the horizontal plane Parallel to the horizontal plane. The direction vector is calculated using a plane geometry algorithm. With direction vector The included angle β1; simultaneously, the direction vector is calculated using a plane geometry algorithm. The angle θ1 between the point B1 and the x-axis; Using the two-dimensional video image from the acoustic camera, obtain the mapping point B of point B1 and point B0 in the image. 11 With point B 01 Measure direction vector The angle α1 between the horizontal line and the horizontal line.

[0056] Finally, in the two-dimensional video image, with mapping point B... 01 Establish a planar coordinate system x1B with the origin as the origin. 01 y1, let Let the length of the projection onto the x1 axis be L1, and the length of the projection onto the y1 axis be L2. Calculate the mapping coefficients. Record these two mapping coefficients to complete the spatial calibration of the first acoustic camera 1.

[0057] The spatial calibration of the second acoustic camera 2 can be completed using the same method described above. By calibrating the first acoustic camera 1 and the second acoustic camera 2 respectively, a correspondence can be established between the two-dimensional video images of the two acoustic cameras and the real three-dimensional space.

[0058] Step S102 involves fusing the 3D model of the monitored target into a coordinate system of real 3D space according to its actual dimensions. This means representing the 3D model of the monitored target in the xoyz coordinate system according to its actual dimensions. This step allows the abnormal noise sources to be located in the same model as their actual locations on-site, making identification and localization more intuitive.

[0059] Step S103: Based on the division of the monitored target components and / or parts, obtain the spatial coordinate range of the components and / or parts. Considering the different structural characteristics of the monitored target, components and parts can be divided into components A, B, C, D... and the spatial coordinate range of each component and / or part can be obtained.

[0060] Step S104: The spatial coordinates of the detected abnormal noise source in the coordinate system of the real three-dimensional space are obtained by calculation, and compared with the spatial coordinate range of the component and / or part to obtain the location of the noise source.

[0061] The step of "obtaining the spatial coordinates of the detected abnormal noise sources in the real three-dimensional space coordinate system through calculation" specifically includes the following steps:

[0062] First, when the abnormal noise source appears in the two-dimensional video frame of the first acoustic camera 1, the center position of the noise source is determined, that is, the center point of the noise source is located in the plane coordinate system x1B. 01 In y1, it is represented as M1(x 1M1 ,y 1M1 ), calculate the distance L from point M1 to the x1 and y1 axes of the coordinate system. 1M1 With L 2M1 ;

[0063] Secondly, based on the calculations in step S101 above,

[0064] Calculate cosβ M1 =Φ1·L 1M1 ;

[0065] Again, by β M1 α M1 θ M1 The three angle values ​​can be calculated. Direction vector (cosβ M1 ,cosα M1 cosθ M1 Then, the first acoustic camera 1 can be obtained. The point-line form of the equation of the straight line is as follows:

[0066]

[0067] Then, repeat the calculation method described above in this step to obtain the second acoustic camera 2. The point-line form of the equation of the straight line is as follows:

[0068]

[0069] Finally, the intersection of the two straight line equations (1) and (2) is calculated, and the coordinates of the intersection are the coordinates of the true three-dimensional space of the abnormal noise source.

[0070] Step S105: Based on the location of the noise source obtained in step S104 and the characteristics of the collected noise signal, monitor the abnormal operating conditions. Specifically, compare the spatial coordinates of the abnormal noise source with the spatial coordinate range of each component and / or part to obtain the name of the component and / or part where the abnormal noise source is located. Then, based on the characteristics of the collected abnormal sound signal, determine the possible abnormal operating conditions and issue an alarm to the maintenance personnel, such as prompting "Component X is abnormal, and condition X may occur".

[0071] Example 2

[0072] Combination Figure 5 As shown, the abnormal operating condition monitoring and positioning system of this embodiment includes a spatial calibration unit 201, a target fusion unit 202, a target segmentation unit 203, a noise location acquisition unit 204, and an abnormal operating condition monitoring unit 205. The spatial calibration unit 201 is used to perform spatial calibration on multiple installed acoustic cameras, establishing a correspondence between the two-dimensional planar images of the acoustic cameras and the real three-dimensional space. The target fusion unit 202 is used to fuse the three-dimensional model of the monitored target into the coordinate system of the real three-dimensional space according to its actual size. The target segmentation unit 203 is used to obtain the spatial coordinate range of the components and / or parts according to the segmentation of the monitored target components and / or parts. The noise location acquisition unit 204 is used to calculate the spatial coordinate values ​​of the detected abnormal noise sources in the coordinate system of the real three-dimensional space and compare them with the spatial coordinate range of the components and / or parts to obtain the location of the noise source. The abnormal operating condition monitoring unit 205 is used to monitor abnormal operating conditions based on the location of the noise source and the characteristics of the collected noise signal. Preferably, but not limitingly, the abnormal working condition monitoring and positioning system may also include an image preprocessing unit 206 for eliminating barrel distortion and pincushion distortion in the two-dimensional planar image of the acoustic camera before spatial calibration.

[0073] Further as Figure 5 As shown, the abnormal operating condition monitoring unit 205 may specifically include: a data comparison subunit and a fault judgment subunit. The data comparison subunit can be used to compare the location of the noise source and the characteristics of the collected noise signal with the abnormal operating condition data in the fault database; the fault judgment subunit can be used to determine the possible fault type and degree and issue early warning information.

[0074] Example 3

[0075] This embodiment provides a non-transient (non-volatile) computer storage medium that stores computer-executable instructions. These computer-executable instructions can execute the abnormal operating condition monitoring and location method in any of the above method embodiments and achieve the same technical effect.

[0076] Example 4

[0077] This embodiment provides a computer program product, which includes a computer program stored on a non-transitory computer-readable storage medium. The computer program includes program instructions, which, when executed by a computer, cause the computer to perform the abnormal operating condition monitoring and location method described in the above aspects and achieve the same technical effect.

[0078] Example 5

[0079] Figure 6 This is a schematic diagram of the hardware structure of the abnormal operating condition monitoring and positioning electronic device of this embodiment. The device includes one or more processors 610 and a memory 620. Taking one processor 610 as an example, the device may also include an input device 630 and an output device 640.

[0080] The processor 610, memory 620, input device 630 and output device 640 can be connected by a bus or other means.

[0081] The memory 620, as a non-transitory computer-readable storage medium, can be used to store non-transitory software programs, non-transitory computer-executable programs, and modules. The processor 610 executes various functional applications and data processing of the electronic device by running the non-transitory software programs, instructions, and modules stored in the memory 620, thereby implementing the processing method of the above-described method embodiments.

[0082] The memory 620 may include a program storage area and a data storage area, wherein the program storage area may store the operating system and applications required for at least one function; the data storage area may store data, etc. Furthermore, the memory 620 may include high-speed random access memory, and may also include non-transitory memory, such as at least one disk storage device, flash memory device, or other non-transitory solid-state storage device. In some embodiments, the memory 620 may optionally include memory remotely located relative to the processor 610, and these remote memories may be connected to the processing device via a network. Examples of such networks include, but are not limited to, the Internet, corporate intranets, local area networks, mobile communication networks, and combinations thereof.

[0083] Input device 630 can receive input digital or character information and generate signal input. Output device 640 may include display devices such as a display screen.

[0084] The one or more modules are stored in the memory 620, and when executed by the one or more processors 610, the following steps are performed:

[0085] Step A: Spatial calibration is performed on the multiple acoustic cameras after installation to establish a correspondence between the two-dimensional planar images of the acoustic cameras and the real three-dimensional space;

[0086] Step B: Fuse the 3D model of the monitored target into the coordinate system of the real 3D space according to its actual size;

[0087] Step C: Based on the division of the monitored target components and / or parts, obtain the spatial coordinate range of the components and / or parts;

[0088] Step D: Calculate the spatial coordinates of the detected abnormal noise source in the coordinate system of the real three-dimensional space, and compare them with the spatial coordinate range of the component and / or part to obtain the location of the noise source;

[0089] Step E: Monitor abnormal operating conditions based on the location of the noise source and the characteristics of the collected noise signals.

[0090] The above-described product can execute the methods provided in the embodiments of the present invention, and has the corresponding functional modules and beneficial effects for executing the methods. Technical details not described in detail in this embodiment can be found in the methods provided in other embodiments of the present invention.

[0091] The device embodiments described above are merely illustrative. The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the modules can be selected to achieve the purpose of this embodiment according to actual needs.

[0092] Through the above description of the embodiments, those skilled in the art can clearly understand that each embodiment can be implemented using software plus a general-purpose hardware platform, or of course, using hardware. Based on this understanding, the above technical solutions, in essence or the parts that contribute to the related technology, can be embodied in the form of a software product. This computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, magnetic disk, optical disk, etc., and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute the methods described in the various embodiments or some parts of the embodiments.

[0093] The foregoing description of specific exemplary embodiments of the present invention is for illustrative and explanatory purposes. These descriptions are not intended to limit the invention to the precise forms disclosed, and it will be apparent that many changes and variations can be made in accordance with the foregoing teachings. The exemplary embodiments were chosen and described in order to explain the specific principles of the invention and its practical application, thereby enabling those skilled in the art to implement and utilize various different exemplary embodiments of the invention, as well as various different choices and variations. Any simple modifications, equivalent changes, and alterations made to the foregoing exemplary embodiments should fall within the scope of protection of the present invention.

Claims

1. A method for monitoring and locating abnormal operating conditions, characterized in that, Includes the following steps: A. Spatial calibration is performed on the multiple acoustic cameras after installation to establish a correspondence between the two-dimensional planar images of the acoustic cameras and the real three-dimensional space; the acoustic cameras include a first acoustic camera and a second acoustic camera, which are set on opposite sides of the monitoring target. The spatial calibration of the acoustic camera involves the following specific steps: Record the position of the acoustic camera as a point on the two-dimensional plane image. A Select a point in the real three-dimensional space. B 0, so that it is located in the exact center of the two-dimensional plane image, then the pointing direction of the acoustic camera is from the point. A To the point B 0 direction vector ; Choose another point in the real three-dimensional space B 1. Make it visible in the two-dimensional plane image; measure the point in the coordinate system of the real three-dimensional space. A , B 0、 B The coordinates of 1 are respectively A ( x 0 , y 0 , z 0) B 0( x B0 , y B0 , z B0 ), B 1( x B1 , y B1 , z B1 ); Set points Coordinates are ( x B1 , y B1 , z B0 ), calculate the direction vector With the direction vector The included angle β 1; Simultaneously calculate the direction vector and x Angle between coordinate axes θ 1; The point is obtained through the two-dimensional planar image of the acoustic camera. B 1 and point B 0's mapping point in the image B 11 With point B 01 Measure direction vector Angle with the horizontal line α 1; In the two-dimensional plane image, with the mapping point B 01 Establish a planar coordinate system with the origin as the origin. x 1 B 01 y 1. Let the above be... Projected on x The length of axis 1 is L 1. Projected on y The length of axis 1 is L 2. Calculate the mapping coefficients , The spatial calibration of the acoustic camera is completed by recording the mapping coefficients. B. Merge the three-dimensional model of the monitored target into the coordinate system of the real three-dimensional space according to its actual size; C. Based on the division of the monitored target components and / or parts, obtain the spatial coordinate range of the components and / or parts; D. Calculate the spatial coordinates of the detected abnormal noise source in the coordinate system of the real three-dimensional space, and compare them with the spatial coordinate range of the component and / or part to obtain the location of the noise source; Calculating the spatial coordinates of the detected abnormal noise source in the coordinate system of the real three-dimensional space specifically includes the following steps: D1. When the abnormal noise source appears in the two-dimensional plane image, the center point of the noise source is located in the plane coordinate system. x 1 B 01 y 1 is represented as M 1( x 1M1 , y 1M1 ), calculation points M 1. Distance coordinate system x 1 axis and y Distance along axis 1 L 1M1 and L 2M1 ; D2, Calculation ; ; ; D3, Pass The direction vector of the first acoustic camera is used to obtain the direction vector. The point-line form of the equation of the straight line is as follows: Equation (1); D4. Repeat steps D1 to D3 to acquire the second acoustic camera. The point-line form of the equation of the straight line is as follows: Equation (2); D5. Calculate the intersection of equation (1) and equation (2). The coordinates of the intersection are the coordinates of the real three-dimensional space of the abnormal noise source. E. Monitor abnormal operating conditions based on the location of the noise source and the characteristics of the collected noise signals.

2. The abnormal operating condition monitoring and location method according to claim 1, characterized in that, Step E specifically involves comparing the location of the noise source and the characteristics of the collected noise signal with the abnormal operating condition data in the fault database to determine the possible fault type and severity and issue a warning message.

3. The abnormal operating condition monitoring and location method according to claim 1, characterized in that, Before the spatial calibration, barrel distortion and pincushion distortion elimination processing is performed on the two-dimensional planar image of the acoustic camera.

4. An abnormal operating condition monitoring and positioning system, characterized in that, The method described in any one of claims 1 to 3 includes: The spatial calibration unit is used to perform spatial calibration on multiple acoustic cameras after installation, and to establish a correspondence between the two-dimensional planar images of the acoustic cameras and the real three-dimensional space. The target fusion unit is used to fuse the three-dimensional model of the monitored target into the coordinate system of the real three-dimensional space according to its actual size; The target segmentation unit is used to obtain the spatial coordinate range of the monitored target components and / or parts based on the segmentation of the components and / or parts. The noise location acquisition unit is used to calculate the spatial coordinates of the detected abnormal noise source in the coordinate system of the real three-dimensional space, and compare them with the spatial coordinate range of the component and / or part to obtain the location of the noise source. An abnormal operating condition monitoring unit is used to monitor abnormal operating conditions based on the location of the noise source and the characteristics of the collected noise signals.

5. The abnormal operating condition monitoring and positioning system according to claim 4, characterized in that, The abnormal operating condition monitoring unit specifically includes: The data comparison subunit is used to compare the location of the noise source and the characteristics of the collected noise signal with the abnormal operating condition data in the fault database. The fault diagnosis subunit is used to determine the possible fault type and severity and issue early warning information.

6. The abnormal operating condition monitoring and positioning system according to claim 4, characterized in that, It also includes an image preprocessing unit, used to perform barrel distortion and pincushion distortion elimination processing on the two-dimensional planar image of the acoustic camera before the spatial calibration.

7. An electronic device, characterized in that, include: At least one processor; as well as A memory communicatively connected to the at least one processor; wherein, The memory stores instructions that can be executed by the at least one processor to cause the at least one processor to perform the method as described in any one of claims 1 to 3.

8. A non-transitory computer-readable storage medium, characterized in that, The non-transitory computer-readable storage medium stores computer-executable instructions for causing the computer to perform the method as described in any one of claims 1 to 3.

Images