Connection structure state identification method, system, equipment and medium
By processing acoustic and vibration signals using generalized variational mode decomposition and symmetric point image transformation algorithms, the problem of information redundancy in traditional methods is solved, and efficient identification of the state of connected structures is achieved.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2025-12-10
- Publication Date
- 2026-04-07
AI Technical Summary
Traditional SDP methods exhibit identical characteristics across different mirror planes, leading to information redundancy in acoustic and vibration signal processing and making it difficult to effectively identify the state of connected structures.
The acoustic vibration response signal is decomposed using a generalized variational mode decomposition algorithm to obtain multiple time-domain signals of different frequencies. These signals are then converted into two-dimensional images in polar coordinates using a symmetry point image transformation algorithm, generating distinct symmetry point images for connecting structural state identification.
It effectively reflects the characteristic information of the connection structure under different states, improves the accuracy and effectiveness of state recognition, and reduces information redundancy.
Smart Images
Figure CN121808304A_ABST
Abstract
Description
Technical Field
[0001] This invention relates to the field of complex structure state identification, and more specifically, to a method, system, device, and medium for identifying the state of a connection structure. Background Technology
[0002] The structural condition of equipment connections directly affects the reliability and safety of the entire equipment system. However, for some major and complex equipment, direct health monitoring is often not feasible. To understand the structural condition of critical internal connections, diagnosis must rely on indirect monitoring information such as sound and vibration. Vibration and sound information is rich, including not only responses related to the target structure's condition but also the complex responses of the overall structure. To extract information related to the target structure from indirect monitoring quantities such as vibration and sound, sensitive information analysis and feature extraction must be conducted in conjunction with the target structure's response characteristics.
[0003] Existing structural state diagnosis methods based on acoustic and vibration signals generally include time-domain analysis, frequency-domain analysis, time-frequency analysis, and machine learning. Among these, time-frequency analysis is currently one of the most commonly used methods in the field of signal processing. The SDP method is a novel image processing technique that maps a one-dimensional time-domain waveform to radius and angle values in polar coordinates, thus forming a symmetrical image in polar coordinate space. This method only processes time-domain signals, thereby bypassing complex time-frequency analysis. However, traditional SDP methods exhibit identical features across different mirror planes, leading to redundancy in overall information. Summary of the Invention
[0004] The purpose of this invention is to provide a connection structure state identification method, system, device and medium, which solves the problem that the features of the traditional SDP method are the same on different mirror planes, resulting in redundancy in the overall information of the two-dimensional image.
[0005] The above-mentioned technical objective of the present invention is achieved through the following technical solution:
[0006] A first aspect of the present invention provides a method for identifying the state of a connection structure, the method comprising:
[0007] The acoustic and vibration response signals of the connection structure are decomposed using a generalized variational mode decomposition algorithm to obtain n time-domain signals of different frequencies, where n is a positive integer;
[0008] Configure the parameters of the symmetric point image transformation algorithm, and convert each time domain signal of different frequencies into a two-dimensional image in polar coordinates according to the configured parameters to obtain a symmetric point image formed by the combination of n different frequency signals;
[0009] The state of different connection structures is identified by using symmetrical point images formed by combinations of n different frequency signals.
[0010] In one implementation, the parameters include the number of mirror-symmetric images, the angle magnification factor, and the time lag factor.
[0011] In one implementation, each time-domain signal of different frequencies is converted into a two-dimensional image in polar coordinates according to configured parameters, resulting in a symmetrical point image formed by the combination of n different frequency signals, including:
[0012] Calculate the polar radius of each time-domain signal at the i-th sampling point;
[0013] Calculate the clockwise and counterclockwise rotation angles corresponding to the polar coordinate radius of the i-th sampling point;
[0014] Based on the polar coordinate radius, clockwise rotation angle, and counterclockwise rotation angle, the polar coordinates of each time-domain signal are generated, and a symmetrical point image formed by the combination of n different frequency signals is drawn along the polar coordinates.
[0015] In one implementation, the polar radius is calculated as follows: ,in, Let i be the i-th sampling point of the m-th time-domain signal. Let be the minimum value of the m-th time-domain signal. Let m be the maximum value of the m-th time-domain signal, where m ranges from 1 to n.
[0016] In one implementation, the formula for calculating the clockwise rotation angle is: Where T represents the time lag factor and A represents the angle magnification factor;
[0017] The formula for calculating the counterclockwise rotation angle is: .
[0018] A second aspect of the present invention provides a connection structure state identification system, the system comprising:
[0019] The signal decomposition module is used to decompose the acoustic and vibration response signal of the connection structure using the generalized variational mode decomposition algorithm to obtain n time-domain signals of different frequencies, where n is a positive integer;
[0020] The transformation module is used to configure the parameters of the symmetric point image transformation algorithm. Based on the configured parameters, it converts each time-domain signal of different frequencies into a two-dimensional image in polar coordinates, and obtains a symmetric point image formed by the combination of n different frequency signals.
[0021] The identification module is used to identify the state of different connection structures based on a symmetrical point image formed by a combination of n different frequency signals.
[0022] In one implementation, the parameters include the number of mirror-symmetric images, the angle magnification factor, and the time lag factor.
[0023] In one implementation, the transformation module is specifically used for:
[0024] Calculate the polar radius of each time-domain signal at the i-th sampling point;
[0025] Calculate the clockwise and counterclockwise rotation angles corresponding to the polar coordinate radius of the i-th sampling point;
[0026] Based on the polar coordinate radius, clockwise rotation angle, and counterclockwise rotation angle, the polar coordinates of each time-domain signal are generated, and a symmetrical point image formed by the combination of n different frequency signals is drawn along the polar coordinates.
[0027] A third aspect of the present invention provides an electronic device, including a memory and a processor;
[0028] A memory for storing computer programs, the computer programs including program instructions;
[0029] A processor is configured to execute the program instructions to cause the electronic device to perform the steps of a connection structure state identification method as provided in the first aspect of the present invention.
[0030] A fourth aspect of the present invention provides a computer-readable storage medium comprising a computer program that, when executed by one or more processors, implements a connection structure state identification method as provided in the first aspect of the present invention.
[0031] Compared with the prior art, the present invention has the following beneficial effects:
[0032] This invention employs a generalized variational mode decomposition algorithm to decompose the acoustic and vibration response signals of the connection structure, obtaining n independent time-domain signals of different frequencies. Then, the n independent time-domain signals of different frequencies are individually analyzed by SDP, and a symmetrical point image formed by the combination of the n different frequency signals is plotted. The feature dispersion of each image is different, which can effectively reflect the feature information of the connection structure under different states, thereby effectively supporting the state identification of the connection structure. Attached Figure Description
[0033] The accompanying drawings, which are included to provide a further understanding of embodiments of the invention and form part of this application, do not constitute a limitation thereof. In the drawings:
[0034] Figure 1 A flowchart illustrating a connection structure state identification method provided in an embodiment of the present invention;
[0035] Figure 2 This is a schematic diagram of the decomposition of acoustic vibration response signal provided in an embodiment of the present invention;
[0036] Figure 3 A schematic diagram of the features of symmetrical point images of different pre-tightened wedge ring states provided in an embodiment of the present invention;
[0037] Figure 4 This is a schematic diagram of a connection structure state identification system provided in an embodiment of the present invention. Detailed Implementation
[0038] To make the objectives, technical solutions, and advantages of this invention clearer, the invention will be further described in detail below with reference to the embodiments and accompanying drawings. The illustrative embodiments and descriptions of this invention are only for explaining this invention and are not intended to limit this invention.
[0039] It should be noted that the terms "comprising" or "may include" used in the various embodiments of this application indicate the presence of the claimed function, operation, or element, and do not limit the addition of one or more functions, operations, or elements. Furthermore, as used in the various embodiments of this application, the terms "comprising," "having," and their cognates are intended only to indicate a specific feature, number, step, operation, element, component, or combination of the foregoing, and should not be construed as primarily excluding the presence of one or more other features, numbers, steps, operations, elements, components, or combinations of the foregoing, or adding one or more combinations of the foregoing.
[0040] It should be understood that terms such as "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of technical features indicated. Therefore, a feature defined as "first" or "second" may explicitly or implicitly include one or more of that feature. In the description of this invention, "a plurality of" means two or more, unless otherwise explicitly specified.
[0041] As described in the background section, existing structural state diagnosis methods based on acoustic and vibration signals generally include time-domain analysis, frequency-domain analysis, time-frequency analysis, and machine learning. Among these, time-frequency analysis is currently one of the most commonly used methods in the field of signal processing. The SDP method is a novel image processing technique that maps a one-dimensional time-domain waveform to radius and angle values in polar coordinates, thus forming a symmetrical image in polar coordinate space. This method processes only time-domain signals, thereby bypassing complex time-frequency analysis. However, traditional SDP methods exhibit identical features across different mirror planes, leading to redundancy in the overall information.
[0042] To this end, this invention provides a method for identifying the state of a connection structure. The method uses a generalized variational mode decomposition algorithm to decompose the acoustic and vibration response signal of the connection structure to obtain n independent time-domain signals of different frequencies. Then, the n independent time-domain signals of different frequencies are analyzed separately using SDP and a symmetrical point image formed by the combination of the n different frequency signals is plotted. The feature dispersion of each image is different, which can effectively reflect the feature information of the connection structure under different states, thereby effectively supporting the state identification of the connection structure.
[0043] The following will provide a detailed description of the connection structure state identification method provided in this embodiment, with reference to specific implementation schemes, such as... Figure 1 As shown, the method includes:
[0044] S101, the generalized variational mode decomposition algorithm is used to decompose the acoustic and vibration response signal of the connection structure to obtain n time-domain signals of different frequencies, where n is a positive integer.
[0045] Specifically, Generalized Variational Mode Decomposition (GVMD) is a signal processing algorithm that, as an extension of traditional Variational Mode Decomposition (VMD), aims to overcome the limitations of VMD in terms of flexibility in adjusting frequency scale and spectral position. GVMD has multi-scale and fixed-frequency decomposition capabilities, and can decompose a signal into multiple narrowband modes or a combination of narrowband and wideband modes.
[0046] For example, such as Figure 2 As shown, GVMD decomposition is performed on the acoustic-vibration response signal x of the wedge-shaped ring connection structure. With n=6 decomposition modes, six independent time-domain signals of different frequencies are obtained. , , ..., Each signal has a time domain length of 2000.
[0047] S102, Configure the parameters of the symmetric point image transformation algorithm, and convert each time domain signal of different frequencies into a two-dimensional image in polar coordinates according to the configured parameters, so as to obtain a symmetric point image formed by the combination of n different frequency signals.
[0048] In this embodiment, the parameters include the number of mirror-symmetric images, the angle magnification factor, and the time lag factor. It should be noted that the number of mirror-symmetric images must be consistent with the number of decomposition modes in the generalized variational mode decomposition, which is 6; the angle magnification factor is set to 40; and the time lag factor is set to 200.
[0049] Specifically, after configuring the parameters, the six time-domain signals of different frequencies are transformed into two-dimensional images in polar coordinates using a symmetric point image transformation algorithm, resulting in n GVMD-SDP images, which are the symmetric point images formed by the combination of n different frequency signals provided in this embodiment. The transformation process is as follows:
[0050] First, calculate the polar radius of each time-domain signal at the i-th sampling point; where the formula for calculating the polar radius is: ,in, Let i be the i-th sampling point of the m-th time-domain signal. Let be the minimum value of the m-th time-domain signal. Let m be the maximum value of the m-th time-domain signal, where m ranges from 1 to n.
[0051] Next, calculate the clockwise and counterclockwise rotation angles corresponding to the polar coordinate radius of the i-th sampling point; where the formula for calculating the clockwise rotation angle is: Where T represents the time lag factor and A represents the angle magnification factor; the formula for calculating the counterclockwise rotation angle is: ;
[0052] Finally, based on the polar coordinate radius, clockwise rotation angle, and counterclockwise rotation angle, the polar coordinates of each time-domain signal are generated, and a symmetrical point image formed by the combination of n different frequency signals is drawn along the polar coordinates.
[0053] Calculate the polar coordinate radii of six independent time-domain signals. The expression is as follows: In the formula, i represents the independent component signal. The i-th point, where m ranges from 1 to 6 and i ranges from 1 to 2000.
[0054] Calculate the polar coordinate radii of six independent time-domain signals. The corresponding angle is expressed as follows:
[0055] ×40; ×40, where m ranges from 1 to 6.
[0056] Based on the angle, obtain the polar coordinates of different independent components. [ , ]and [ , ], and plotted GVMD-SDP images of six independent time-domain signals along polar coordinates, such as Figure 3 As shown, the GVMD-SDP images under different states show significant differences, and the six petal features are scattered differently under different states, which can effectively reflect the characteristic information of the wedge ring connection structure under different pre-tightening states.
[0057] S103 identifies the state of different connection structures based on a symmetrical point image formed by a combination of n different frequency signals.
[0058] Specifically, the GVMD-SDP image obtained based on the SDP transformation mentioned above can effectively reflect the characteristic information of different pre-tightening states of the wedge ring, thereby effectively supporting state identification.
[0059] like Figure 4 As shown, this embodiment also provides a connection structure state identification system, the system including:
[0060] The signal decomposition module 410 is used to decompose the acoustic and vibration response signal of the connection structure using the generalized variational mode decomposition algorithm to obtain n time-domain signals of different frequencies, where n is a positive integer;
[0061] The transformation module 420 is used to configure the parameters of the symmetric point image transformation algorithm. Based on the configured parameters, it converts each time-domain signal of different frequencies into a two-dimensional image in polar coordinates to obtain a symmetric point image formed by the combination of n different frequency signals.
[0062] The identification module 430 is used to identify the state of different connection structures based on a symmetrical point image formed by a combination of n different frequency signals.
[0063] In one embodiment, the parameters include the number of mirror-symmetric images, the angle magnification factor, and the time lag factor.
[0064] In one embodiment, the transformation module 420 is specifically used for:
[0065] Calculate the polar radius of each time-domain signal at the i-th sampling point;
[0066] Calculate the clockwise and counterclockwise rotation angles corresponding to the polar coordinate radius of the i-th sampling point;
[0067] Based on the polar coordinate radius, clockwise rotation angle, and counterclockwise rotation angle, the polar coordinates of each time-domain signal are generated, and a symmetrical point image formed by the combination of n different frequency signals is drawn along the polar coordinates.
[0068] This application provides a connection structure state identification system, which is similar to the one described above. Figure 1 The connection structure state identification method shown is a technical solution based on the same inventive concept. Through the detailed description of the connection structure state identification method provided in the above embodiments, those skilled in the art can clearly understand the implementation process of the connection structure state identification system in this embodiment. Therefore, for the sake of brevity, it will not be described again here.
[0069] This invention also provides an electronic device. The electronic device includes a processor, a memory, a communication interface, and at least one communication bus for connecting the processor, the memory, and the communication interface. The memory includes, but is not limited to, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (PROM), or portable read-only memory (CD-ROM), and is used for related instructions and data.
[0070] The communication interface is used to receive and send data. The processor can be one or more CPUs; if it is a single CPU, it can be a single-core or multi-core CPU. The processor in the electronic device reads one or more programs stored in memory and performs the following operations: decomposes the acoustic and vibration response signals of the connection structure using a generalized variational mode decomposition algorithm to obtain n time-domain signals of different frequencies, where n is a positive integer; configures the parameters of the symmetry point image transformation algorithm, and converts each time-domain signal of different frequencies into a two-dimensional image in polar coordinates based on the configured parameters, obtaining a symmetry point image formed by the combination of n different frequency signals; and identifies the state of different connection structures based on the symmetry point image formed by the combination of n different frequency signals.
[0071] It should be noted that the specific implementation of each operation can be described above. Figure 1 The corresponding description of the method embodiments shown indicates that the electronic device can be used to execute a connection structure state identification method of the above method embodiments of this application, which will not be described in detail here.
[0072] This invention also provides a computer-readable storage medium, which is a memory device in a computer device for storing programs and data. It is understood that the computer-readable storage medium here can include both the built-in storage medium in the computer device and extended storage media supported by the computer device. The computer-readable storage medium provides storage space that stores the operating system of the terminal. Furthermore, the storage space also stores one or more instructions suitable for loading and execution by a processor. These instructions can be one or more computer programs (including program code). It should be noted that the computer-readable storage medium here can be high-speed RAM or non-volatile memory, such as at least one disk storage device. The processor can load and execute one or more instructions stored in the computer-readable storage medium to implement the corresponding steps of the connection structure state identification method in the above embodiments. Those skilled in the art should understand that embodiments of the present invention can be provided as methods, systems, or computer program products. Therefore, the present invention can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the present invention can take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.
[0073] This invention also provides a computer program product containing program instructions. The computer program product may be software or program products containing program instructions, capable of running on a computing device or stored on any usable medium. When the computer program product runs on at least one electronic device, it causes the at least one electronic device to execute a connection structure state identification method.
[0074] The specific embodiments described above further illustrate the purpose, technical solution, and beneficial effects of the present invention. It should be understood that the above description is only a specific embodiment of the present invention and is not intended to limit the scope of protection of the present invention. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the present invention should be included within the scope of protection of the present invention.
Claims
1. A method for identifying the state of a connection structure, characterized in that, The methods include: The acoustic and vibration response signals of the connection structure are decomposed using a generalized variational mode decomposition algorithm to obtain n time-domain signals of different frequencies, where n is a positive integer; Configure the parameters of the symmetric point image transformation algorithm, and convert each time domain signal of different frequencies into a two-dimensional image in polar coordinates according to the configured parameters to obtain a symmetric point image formed by the combination of n different frequency signals; The state of different connection structures is identified by using symmetrical point images formed by combinations of n different frequency signals.
2. The method according to claim 1, characterized in that, The parameters include the number of mirror-symmetric images, the angle magnification factor, and the time lag factor.
3. The method according to claim 1, characterized in that, Based on the configured parameters, each time-domain signal of different frequencies is converted into a two-dimensional image in polar coordinates, resulting in a symmetrical point image formed by the combination of n different frequency signals, including: Calculate the polar radius of each time-domain signal at the i-th sampling point; Calculate the clockwise and counterclockwise rotation angles corresponding to the polar coordinate radius of the i-th sampling point; Based on the polar coordinate radius, clockwise rotation angle, and counterclockwise rotation angle, the polar coordinates of each time-domain signal are generated, and a symmetrical point image formed by the combination of n different frequency signals is drawn along the polar coordinates.
4. The method according to claim 3, characterized in that, The formula for calculating the polar radius is: ,in, Let i be the i-th sampling point of the m-th time-domain signal. Let be the minimum value of the m-th time-domain signal. Let m be the maximum value of the m-th time-domain signal, where m ranges from 1 to n.
5. The method according to claim 4, characterized in that, The formula for calculating the clockwise rotation angle is: Where T represents the time lag factor and A represents the angle magnification factor; The formula for calculating the counterclockwise rotation angle is: .
6. A connection structure state identification system, characterized in that, The system includes: The signal decomposition module is used to decompose the acoustic and vibration response signal of the connection structure using the generalized variational mode decomposition algorithm to obtain n time-domain signals of different frequencies, where n is a positive integer; The transformation module is used to configure the parameters of the symmetric point image transformation algorithm. Based on the configured parameters, it converts each time-domain signal of different frequencies into a two-dimensional image in polar coordinates, and obtains a symmetric point image formed by the combination of n different frequency signals. The identification module is used to identify the state of different connection structures based on a symmetrical point image formed by a combination of n different frequency signals.
7. The system according to claim 6, characterized in that, The parameters include the number of mirror-symmetric images, the angle magnification factor, and the time lag factor.
8. The system according to claim 6, characterized in that, The transformation module is specifically used for: Calculate the polar radius of each time-domain signal at the i-th sampling point; Calculate the clockwise and counterclockwise rotation angles corresponding to the polar coordinate radius of the i-th sampling point; Based on the polar coordinate radius, clockwise rotation angle, and counterclockwise rotation angle, the polar coordinates of each time-domain signal are generated, and a symmetrical point image formed by the combination of n different frequency signals is drawn along the polar coordinates.
9. An electronic device, characterized in that, Including memory and processor; A memory for storing computer programs, the computer programs including program instructions; A processor is configured to execute the program instructions to cause the electronic device to perform the steps of a connection structure state identification method as described in any one of claims 1 to 5.
10. A computer-readable storage medium, characterized in that, The computer-readable storage medium includes a computer program that, when executed by one or more processors, implements a connection structure state identification method as described in any one of claims 1 to 5.