A real-time displacement monitoring method and system for ground wire horizontal force tension test

Abstract

The present invention relates to a method and system for real-time displacement monitoring during a ground conductor's horizontal force and tension test, belonging to the field of intelligent testing technology. The method comprises: acquiring a sequence of adjacent grain images; obtaining an adjacent grain enhancement image based on the adjacent grain image sequence using a three-dimensional fusion preprocessing model; obtaining a multidimensional grain image based on the adjacent grain enhancement image using a grain reconstruction model; obtaining grain variation characteristics based on the multidimensional grain image using a grain analysis model; and obtaining actual force and displacement based on the grain variation characteristics through displacement calculation; and outputting a ground conductor performance evaluation result based on the actual force and displacement using a performance evaluation model. This method achieves real-time displacement monitoring during a ground conductor's horizontal force and tension test.

Description

Technical Field

[0001] The present invention belongs to the field of intelligent testing technology, and in particular relates to a real-time displacement monitoring method and system for a ground wire lying force tension test. Background Art

[0002] In modern electronic equipment and power systems, the stability of ground cables and their connectors directly impacts the safety and reliability of the equipment. Ground cables are subject to external forces during operation. In particular, when subjected to overload tension, the connector connection may experience slight displacement or even gradually loosen, affecting the accuracy of parameter calculations. Therefore, tensile testing of ground cables typically employs real-time monitoring using force sensors or displacement transducers to assess their stress state and stability.

[0003] However, traditional displacement measurement methods have limitations during actual testing. First, the minute displacements of the connection under tension are often difficult for conventional sensors to accurately capture in real time, leading to data lag and measurement errors. Second, connector displacement in the direction of loosening can interfere with the measurement system, causing the displacement recorded by the sensor to deviate from the actual force applied, affecting test accuracy. This error can lead to erroneous test results, making it difficult to accurately assess the stress state of the ground conductor, and thus impacting the design and construction of power transmission lines. The current method involves marking the ground conductor connection, with the operator monitoring the displacement by observing the changes in the mark's position. Measurements are then taken after the test is complete. However, since tension testing involves dynamically increasing the load, the inability to measure changes in load and displacement in a timely manner makes it difficult to obtain effective data. Therefore, it is crucial to effectively distinguish the true displacement of the connector under excessive tension from the interfering displacement in the direction of loosening, improve the real-time and accurate measurement, and ensure the long-term stability and reliability of the ground conductor connection. Summary of the Invention

[0004] In order to solve the above problems existing in the prior art, the present invention provides a method and system for real-time displacement monitoring of a ground wire during horizontal tension test.

[0005] The purpose of the present invention can be achieved through the following technical solutions:

[0006] A method for real-time displacement monitoring of a ground wire during a lying tension test, comprising:

[0007] S1: Acquire an adjacent texture image sequence, and obtain an adjacent texture enhanced image according to the adjacent texture image sequence through a three-dimensional fusion preprocessing model;

[0008] S2: Obtaining a multi-dimensional texture image through a texture reconstruction model according to the adjacent texture enhancement image;

[0009] S3: Obtaining a texture change feature through a texture analysis model according to the multi-dimensional texture image, and obtaining an actual tensile displacement through displacement calculation according to the texture change feature;

[0010] S4: Outputting a ground wire performance evaluation result through a performance evaluation model according to the actual tension displacement.

[0011] Preferably, the three-dimensional fusion preprocessing model includes:

[0012] S101: Obtaining an adjacent texture reference image sequence by filtering according to the adjacent texture image sequence;

[0013] S102: removing the adjacent texture reference image sequence from the adjacent texture image sequence to obtain a high-frequency component;

[0014] S103: Obtaining the adjacent texture enhanced image by using a strain-depth joint enhancement model according to the high-frequency component and the adjacent texture reference image sequence;

[0015] The calculation expression of the strain-depth joint enhancement model is:

[0016] ,

[0017] in, I enhanced Enhance the image for the adjacent textures, I smooth is the adjacent texture reference image sequence, I high is the high frequency component, l 1 、l 2 、c is the weight parameter, ▽ 2 is the second-order Laplace operator, tanh represents the hyperbolic tangent function, is the modulus of the three-dimensional gradient vector, Tr(e) For traces.

[0018] Preferably, the texture reconstruction model includes:

[0019] S201: obtaining local texture features and global texture features by feature extraction according to the adjacent texture enhancement image;

[0020] S202: Obtaining a local texture enhancement feature by adjusting the adaptability according to the local texture feature;

[0021] S203: Obtaining a multi-dimensional texture basic image through a reconstruction function according to the local texture enhancement feature and the global texture feature;

[0022] The reconstruction function expression is:

[0023] ,

[0024] in, I r represents the multi-dimensional texture basic image, i represents the i-th local texture, N Indicates the number of local textures, β i 、 c is the weight coefficient of local and global feature fusion, For the local texture enhancement feature, T g is the global texture feature;

[0025] S204: Obtain the multidimensional texture image according to the multidimensional texture basic image through a texture enhancement model.

[0026] Preferably, the texture enhancement model is expressed as:

[0027] ,

[0028] in, L represents the texture enhancement model, l 1 、 l 2 is the balance coefficient, I r represents the multi-dimensional texture basic image, I represents the adjacent texture enhanced image, represents the pixel difference between the multi-dimensional texture base image and the adjacent texture enhanced image, is a constraint function used to constrain the consistency of local texture features and global texture features.

[0029] Preferably, the texture analysis model includes:

[0030] S301: Obtaining multi-dimensional texture local features by feature extraction according to the multi-dimensional texture image;

[0031] S302: Extracting features from the multi-dimensional texture image using a multi-head attention mechanism to obtain a multi-dimensional texture global feature;

[0032] S303: Obtaining a multidimensional texture comprehensive feature by feature fusion based on the multidimensional texture local feature and the multidimensional texture global feature;

[0033] S304: Obtaining a multi-dimensional texture comprehensive time series feature by adding a timestamp according to the multi-dimensional texture comprehensive feature;

[0034] S305: Obtaining the texture change feature through texture change calculation according to the multi-dimensional texture comprehensive time series feature.

[0035] Preferably, the displacement calculation expression is:

[0036] ,

[0037] in, d r is the actual tensile displacement, W d is the weight coefficient, Dt is the texture change feature, b d For bias.

[0038] Preferably, the performance evaluation model includes:

[0039] S401: Obtaining a ground conductor performance score through performance score calculation according to the actual tension displacement;

[0040] The performance score calculation expression is:

[0041] ,

[0042] in, P Score the performance of the ground conductor, s is the activation function, W p is the weight coefficient, d r is the actual tensile displacement, b p is bias;

[0043] S402: Preset a performance threshold, and output a ground wire performance evaluation result through performance judgment based on the performance threshold and the ground wire performance score;

[0044] The expression for the performance judgment is:

[0045] ,

[0046] Wherein, S represents the performance evaluation result of the ground wire, P is the performance score of the ground wire, and Pth1 and Pth2 are the performance thresholds.

[0047] A real-time displacement monitoring system for a ground wire horizontal tension test includes an image processing module, a texture reconstruction module, a displacement calculation module, and a performance evaluation module, including:

[0048] The image processing module is used to obtain an adjacent texture image sequence, and obtain an adjacent texture enhanced image based on the adjacent texture image sequence through a three-dimensional fusion preprocessing model;

[0049] The texture reconstruction module is used to obtain a multi-dimensional texture image through a texture reconstruction model according to the adjacent texture enhancement image;

[0050] The displacement calculation module is used to obtain the texture change characteristics through the texture analysis model according to the multi-dimensional texture image, and obtain the actual tension displacement through displacement calculation according to the texture change characteristics;

[0051] The performance evaluation module is used to output a ground wire performance evaluation result through a performance evaluation model according to the actual tension displacement.

[0052] An electronic device comprises a memory, a processor and a computer program stored in the memory and capable of running on the processor. When the processor executes the program, the above-mentioned method for real-time displacement monitoring of a ground wire lying force and tension test is realized.

[0053] A storage medium containing computer executable instructions, wherein the computer executable instructions are used to execute the above-mentioned ground wire lying force tension test real-time displacement monitoring method when executed by a computer processor.

[0054] The beneficial effects of the present invention are:

[0055] (1) Adjacent texture images are enhanced by a three-dimensional fusion preprocessing model. The high-frequency components and the reference image sequence are jointly enhanced to achieve refined processing of adjacent textures and improve the recognizability of texture features.

[0056] (2) Feature extraction and fusion are performed through a multi-dimensional texture reconstruction model, and the adaptation of local and global texture features is adjusted to achieve accurate reconstruction of complex texture structures, thereby improving the integrity and accuracy of texture information.

[0057] (3) The texture change is calculated through the multi-head attention mechanism and time series feature analysis. The fusion of local and global features and time series analysis are used to accurately capture the texture change trend and improve the calculation accuracy of the actual tension displacement. BRIEF DESCRIPTION OF THE DRAWINGS

[0058] To facilitate understanding by those skilled in the art, the present invention is further described below with reference to the accompanying drawings.

[0059] Figure 1 The present invention is a flow chart of a method for real-time displacement monitoring of a ground wire tensile test under lying force. DETAILED DESCRIPTION

[0060] In order to further illustrate the technical means and effects adopted by the present invention to achieve the predetermined purpose of the invention, the specific implementation methods, structures, features and effects of the present invention are described in detail below in conjunction with the accompanying drawings and preferred embodiments.

[0061] See also Figure 1 A method for real-time displacement monitoring of a ground wire during a horizontal tension test, comprising:

[0062] S1: Acquire an adjacent texture image sequence, and obtain an adjacent texture enhanced image according to the adjacent texture image sequence through a three-dimensional fusion preprocessing model;

[0063] S2: Obtaining a multi-dimensional texture image through a texture reconstruction model according to the adjacent texture enhancement image;

[0064] S3: Obtaining a texture change feature through a texture analysis model according to the multi-dimensional texture image, and obtaining an actual tensile displacement through displacement calculation according to the texture change feature;

[0065] S4: Outputting a ground wire performance evaluation result through a performance evaluation model according to the actual tension displacement.

[0066] Specifically, the adjacent pattern image sequence is obtained by real-time monitoring and photographing the ground wire patterns in the adjacent area of ​​the connector from the x-axis, y-axis, and z-axis directions.

[0067] Specifically, in step S1, the 3D fusion preprocessing model includes:

[0068] S101: Obtaining an adjacent texture reference image sequence by filtering according to the adjacent texture image sequence;

[0069] S102: removing the adjacent texture reference image sequence from the adjacent texture image sequence to obtain a high-frequency component;

[0070] S103: Obtaining the adjacent texture enhanced image by using a strain-depth joint enhancement model according to the high-frequency component and the adjacent texture reference image sequence;

[0071] The calculation expression of the strain-depth joint enhancement model is:

[0072] ,

[0073] in, I enhanced Enhance the image for the adjacent textures, Ismooth is the adjacent texture reference image sequence, I high is the high frequency component, l 1 、l 2 、c is the weight parameter, ▽ 2 is the second-order Laplace operator, tanh represents the hyperbolic tangent function, is the modulus of the three-dimensional gradient vector, Tr(e) For traces.

[0074] Specifically, in step S2, the texture reconstruction model includes:

[0075] S201: obtaining local texture features and global texture features by feature extraction according to the adjacent texture enhancement image;

[0076] S202: Obtaining a local texture enhancement feature by adjusting the adaptability according to the local texture feature;

[0077] The adaptation adjustment is expressed as:

[0078] ,

[0079] in, For the local texture enhancement feature, α is the weight parameter, T l is the local texture feature, W(T g , T l ) Represents the local and global texture interaction mapping function;

[0080] S203: Obtaining a multi-dimensional texture basic image through a reconstruction function according to the local texture enhancement feature and the global texture feature;

[0081] The reconstruction function expression is:

[0082] ,

[0083] in, I r represents the multi-dimensional texture basic image, i represents the i-th local texture, N Indicates the number of local textures, β i 、 c is the weight coefficient of local and global feature fusion, For the local texture enhancement feature, T g is the global texture feature;

[0084] S204: Obtaining the multidimensional texture image through a texture enhancement model according to the multidimensional texture basic image;

[0085] The texture enhancement model is expressed as:

[0086] ,

[0087] in, L represents the texture enhancement model, l 1 、 l 2 is the balance coefficient, I r represents the multi-dimensional texture basic image, I represents the adjacent texture enhanced image, represents the pixel difference between the multi-dimensional texture base image and the adjacent texture enhanced image, is a constraint function used to constrain the consistency of local texture features and global texture features.

[0088] In this embodiment, in the adaptation adjustment, the weight α=0.6, the global feature interaction function W(T g ,T l ) uses cosine similarity mapping. When the local texture feature T l With the global feature T g When the difference exceeds 30%, α is adaptively reduced to 0.4 to avoid overfitting. In the reconstruction function, β i The local feature saliency (calculated by the Sobel operator) is set to γ ​​= 0.3. With the above settings, the texture reconstruction effect is good.

[0089] Specifically, in step S3, the texture analysis model includes:

[0090] S301: Obtaining multi-dimensional texture local features by feature extraction according to the multi-dimensional texture image;

[0091] S302: Extracting features from the multi-dimensional texture image using a multi-head attention mechanism to obtain a multi-dimensional texture global feature;

[0092] S303: Obtaining a multidimensional texture comprehensive feature by feature fusion based on the multidimensional texture local feature and the multidimensional texture global feature;

[0093] S304: Obtaining a multi-dimensional texture comprehensive time series feature by adding a timestamp according to the multi-dimensional texture comprehensive feature;

[0094] S305: Obtaining the texture change feature by texture change calculation according to the multi-dimensional texture comprehensive time series feature;

[0095] The calculation expression of the texture change is:

[0096] ,

[0097] in, Dt is the texture change feature, FC(h t ) Indicates that the texture change features are calculated through the fully connected layer. h t is the hidden state at the current moment, T n is the comprehensive temporal feature of the multi-dimensional texture, h t-1 is the hidden state at the previous moment, LSTM Long short-term memory network.

[0098] Specifically, the displacement calculation expression is:

[0099] ,

[0100] in, d r is the actual tensile displacement, W d is the weight coefficient, Dt is the texture change feature, b d For bias.

[0101] In this example, an LSTM network (hidden layer dimension 128) is used to process the comprehensive temporal features of multi-dimensional textures. The time window is set to 10 frames (Δt = 0.5s), and the fully connected layer output dimension is 3 (corresponding to the x, y, and z axis displacements).

[0102] Specifically, in step S4, the performance evaluation model includes:

[0103] S401: Obtaining a ground conductor performance score through performance score calculation according to the actual tension displacement;

[0104] The performance score calculation expression is:

[0105] ,

[0106] in, P Score the performance of the ground conductor, s is the activation function, Wp is the weight coefficient, d r is the actual tensile displacement, b p is bias;

[0107] S402: Preset a performance threshold, and output a ground wire performance evaluation result through performance judgment based on the performance threshold and the ground wire performance score;

[0108] The expression for performance judgment is:

[0109] ,

[0110] Wherein, S represents the performance evaluation result of the ground wire, P is the performance score of the ground wire, and Pth1 and Pth2 are the performance thresholds.

[0111] A real-time displacement monitoring system for a ground wire horizontal tension test includes an image processing module, a texture reconstruction module, a displacement calculation module, and a performance evaluation module, including:

[0112] The image processing module is used to obtain an adjacent texture image sequence, and obtain an adjacent texture enhanced image based on the adjacent texture image sequence through a three-dimensional fusion preprocessing model;

[0113] The texture reconstruction module is used to obtain a multi-dimensional texture image through a texture reconstruction model according to the adjacent texture enhancement image;

[0114] The displacement calculation module is used to obtain the texture change characteristics through the texture analysis model according to the multi-dimensional texture image, and obtain the actual tension displacement through displacement calculation according to the texture change characteristics;

[0115] The performance evaluation module is used to output a ground wire performance evaluation result through a performance evaluation model according to the actual tension displacement.

[0116] The computer storage medium of the embodiment of the present invention may adopt any combination of one or more computer-readable media. The computer-readable medium may be a computer-readable signal medium or a computer-readable storage medium. The computer-readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or component, or any combination thereof. More specific examples (a non-exhaustive list) of computer-readable storage media include: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination thereof. In this document, a computer-readable storage medium may be any tangible medium containing or storing a program that can be used by or in combination with an instruction execution system, device or device.

[0117] A computer-readable signal medium may include a data signal propagated in baseband or as part of a carrier wave, which carries computer-readable program code. Such propagated data signals may take various forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination thereof. A computer-readable signal medium may also be any computer-readable medium other than a computer-readable storage medium that can transmit, propagate, or transport a program for use by or in conjunction with an instruction execution system, apparatus, or device.

[0118] The program code included in the computer-readable medium can be transmitted with any appropriate medium, including but not limited to wireless, electric wire, optical cable, RF or the like, or any suitable combination thereof. The computer program code for performing the operation of the present invention can be written in one or more programming languages ​​or a combination thereof, and the programming language includes an object-oriented programming language such as Java, Smalltalk, C++, and also includes a conventional procedural programming language such as "C" language or similar programming language. The program code can be executed completely on the user's computer, partially on the user's computer, as an independent software package, partially on the user's computer and partially on a remote computer, or completely on a remote computer or server. In the case of a remote computer, the remote computer can be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or can be connected to an external computer (for example, utilizing an Internet service provider to connect through the Internet).

[0119] The above description is merely a preferred embodiment of the present invention and does not constitute any form of limitation to the present invention. Although the present invention has been disclosed as a preferred embodiment as above, it is not intended to limit the present invention. Any person skilled in the art can make some changes or modifications to equivalent embodiments using the technical contents disclosed above without departing from the scope of the technical solution of the present invention. However, any simple modifications, equivalent changes and modifications made to the above embodiments based on the technical essence of the present invention without departing from the content of the technical solution of the present invention are still within the scope of the technical solution of the present invention.

Claims

1. A method for real-time displacement monitoring of a ground wire during a horizontal tension test, characterized in that: The following steps are involved: S1: Acquire an adjacent texture image sequence, and obtain an adjacent texture enhanced image according to the adjacent texture image sequence through a three-dimensional fusion preprocessing model; S2: Obtaining a multi-dimensional texture image through a texture reconstruction model according to the adjacent texture enhancement image; The texture reconstruction model includes: S201: obtaining local texture features and global texture features by feature extraction according to the adjacent texture enhancement image; S202: Obtaining a local texture enhancement feature by adjusting the adaptability according to the local texture feature; S203: Obtaining a multi-dimensional texture basic image through a reconstruction function according to the local texture enhancement feature and the global texture feature; The reconstruction function expression is: ， in, I r represents the multi-dimensional texture basic image, i represents the i-th local texture, N Indicates the number of local textures, β i 、 γ is the weight coefficient of local and global feature fusion, For the local texture enhancement feature, T g is the global texture feature; S204: Obtaining the multidimensional texture image through a texture enhancement model according to the multidimensional texture basic image; S3: Obtaining a texture change feature through a texture analysis model according to the multi-dimensional texture image, and obtaining an actual tensile displacement through displacement calculation according to the texture change feature; S4: Outputting a ground wire performance evaluation result through a performance evaluation model according to the actual tension displacement.

2. The method for real-time displacement monitoring of a ground wire tensile test according to claim 1, characterized in that: The three-dimensional fusion preprocessing model includes: S101: Obtaining an adjacent texture reference image sequence by filtering according to the adjacent texture image sequence; S102: removing the adjacent texture reference image sequence from the adjacent texture image sequence to obtain a high-frequency component; S103: Obtaining the adjacent texture enhanced image by using a strain-depth joint enhancement model according to the high-frequency component and the adjacent texture reference image sequence; The calculation expression of the strain-depth joint enhancement model is: ， in, I enhanced Enhance the image for the adjacent textures, I smooth is the adjacent texture reference image sequence, I high is the high frequency component, λ 1 ,λ 2 , γ is the weight parameter, ▽ 2 is the second-order Laplace operator, tanh represents the hyperbolic tangent function, is the modulus of the three-dimensional gradient vector, Tr(ε) For traces.

3. The real-time displacement monitoring method for a ground wire lying tension test according to claim 1, characterized in that: The texture enhancement model is expressed as: ， in, L represents the texture enhancement model, λ 1 、 λ 2 is the balance coefficient, I r represents the multi-dimensional texture basic image, I represents the adjacent texture enhanced image, represents the pixel difference between the multi-dimensional texture base image and the adjacent texture enhanced image, is a constraint function used to constrain the consistency of local texture features and global texture features.

4. The method for real-time displacement monitoring of a ground wire lying tension test according to claim 1, characterized in that: The texture analysis model includes: S301: Obtaining multi-dimensional texture local features by feature extraction according to the multi-dimensional texture image; S302: Extracting features from the multi-dimensional texture image using a multi-head attention mechanism to obtain a multi-dimensional texture global feature; S303: Obtaining a multidimensional texture comprehensive feature by feature fusion based on the multidimensional texture local feature and the multidimensional texture global feature; S304: Obtaining a multi-dimensional texture comprehensive time series feature by adding a timestamp according to the multi-dimensional texture comprehensive feature; S305: Obtaining the texture change feature through texture change calculation according to the multi-dimensional texture comprehensive time series feature.

5. The method for real-time displacement monitoring of a ground wire lying tension test according to claim 1, characterized in that: The displacement calculation expression is: ， in, d r is the actual tensile displacement, W d is the weight coefficient, τ is the texture change feature, b d For bias.

6. The method for real-time displacement monitoring of a ground wire under lying tension test according to claim 1, characterized in that: The performance evaluation model includes: S401: Obtaining a ground conductor performance score through performance score calculation according to the actual tension displacement; The performance score calculation expression is: ， in, P Score the performance of the ground conductor, σ is the activation function, W p is the weight coefficient, d r is the actual tensile displacement, b p is bias; S402: Preset a performance threshold, and output a ground wire performance evaluation result through performance judgment based on the performance threshold and the ground wire performance score; The expression for the performance judgment is: ， Wherein, S represents the performance evaluation result of the ground wire, P is the performance score of the ground wire, and Pth1 and Pth2 are the performance thresholds.

7. A real-time displacement monitoring system for a ground wire horizontal tension test, used to perform the method according to any one of claims 1 to 6, characterized in that: include: Image processing module, texture reconstruction module, displacement calculation module, performance evaluation module; The image processing module is used to obtain an adjacent texture image sequence, and obtain an adjacent texture enhanced image based on the adjacent texture image sequence through a three-dimensional fusion preprocessing model; The texture reconstruction module is used to obtain a multi-dimensional texture image through a texture reconstruction model based on the adjacent texture enhancement image; the texture reconstruction model includes: Obtaining local texture features and global texture features by feature extraction based on the adjacent texture enhancement image; Obtaining a local texture enhancement feature by adjusting the degree of adaptation according to the local texture feature; Obtaining a multi-dimensional texture basic image through a reconstruction function according to the local texture enhancement feature and the global texture feature; The reconstruction function expression is: ， Among them, I r represents the multidimensional texture basic image, i represents the i-th local texture, N represents the number of local textures, β i , γ is the weight coefficient of local and global feature fusion, is the local texture enhancement feature, T g is the global texture feature; Obtaining the multidimensional texture image through a texture enhancement model according to the multidimensional texture basic image; The displacement calculation module is used to obtain the texture change characteristics through the texture analysis model according to the multi-dimensional texture image, and obtain the actual tension displacement through displacement calculation according to the texture change characteristics; The performance evaluation module is used to output a ground wire performance evaluation result through a performance evaluation model according to the actual tension displacement.

8. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein: When the processor executes the program, the real-time displacement monitoring method for the ground wire lying force and tension test as described in any one of claims 1 to 6 is implemented.

9. A storage medium containing computer-executable instructions, characterized in that: When executed by a computer processor, the computer executable instructions are used to execute the real-time displacement monitoring method for a ground wire lying force and tension test as described in any one of claims 1 to 6.

Images