Cable stretching test device and method thereof

Abstract

The invention discloses a cable stretching testing device and method, and belongs to the technical field of cable stretching testing, and the cable stretching testing device comprises a stretching mechanism which applies a pulling force to a cable so as to stretch the cable; the detection mechanism is used for acquiring a real-time tension value and a real-time elongation when the cable is stretched; the processing mechanism is used for processing and generating a cable tensile fracture analysis result according to the real-time tension value and the real-time elongation when the cable is stretched; and the control mechanism determines whether a fracture early warning prompt is generated or not according to the cable tensile fracture analysis result. According to the invention, the abnormal stretching state of the cable can be found in time, and accidental breakage of the cable in the testing process is effectively prevented, so that equipment damage and personnel safety risks caused by sudden breakage of the cable are avoided.

Description

Technical Field

[0001] The present invention relates to the technical field of cable tensile testing, and more specifically, to a cable tensile testing device and method thereof. Background Art

[0002] With the continuous expansion of power transmission and communication networks, cables, as key transmission media, have a direct impact on the stability and safety of the system due to their quality and performance. In order to ensure that cable products can meet specific technical requirements in practical applications, it is particularly important to conduct various performance tests on cables. Among them, tensile testing is one of the important means to evaluate the mechanical strength and elastic recovery ability of cables.

[0003] For example, the invention patent with publication number CN116735362A discloses a cable tensile test device, which can simultaneously drive two connected racks to move in opposite directions through the rotation of the central gear, and realize the opposite movement of two bearing frames under the guidance of the guide block, and transmit power to the bearing frames through a series of mechanical linkage structures, causing the cable to be subjected to tensile force. In this process, the displacement is recorded using the scale line, and the actual tensile force on the cable can be monitored and recorded through an additional pressure sensor or other form of force measuring element.

[0004] However, although the existing cable tensile test device can provide basic tensile test functions, it still has certain limitations in practical applications. The cable tensile test device lacks a real-time monitoring and early warning mechanism for the potential risk of cable breakage during the tensile test. During the tensile test, the cable may suddenly break due to material defects, manufacturing defects or excessive stretching, which will not only cause damage to the test equipment, but also pose a safety hazard to the testers, while increasing unnecessary test losses. Summary of the invention

[0005] Based on this, the present invention provides a cable tensile test device and method thereof, aiming to partially or completely solve the above technical problems, timely discover the abnormal tensile state of the cable, prevent the accidental breakage of the cable during the test, and avoid equipment damage and personnel safety risks caused by sudden cable breakage. The present invention is achieved through the following technical solutions: In a first aspect, a cable stretching test device comprises: a stretching mechanism, applying tension to a cable to stretch the cable; a detection mechanism, obtaining a real-time tension value and a real-time elongation of the cable when stretched; a processing mechanism, processing and generating a cable stretch fracture analysis result according to the real-time tension value and the real-time elongation of the cable when stretched; a control mechanism, determining whether to generate a fracture warning prompt according to the cable stretch fracture analysis result; the processing mechanism comprises: a cable stretching state monitoring module, obtaining a time queue of the real-time tension value and a time queue of the real-time elongation of the cable according to the real-time tension value and the real-time elongation of the cable when stretched time queue; a cable tensile parameter time series encoding module, which performs time series encoding on the time queue of real-time tension value and the time queue of real-time elongation respectively to obtain the time series associated implicit feature vector of real-time tension value and the time series associated implicit feature vector of real-time elongation; an information interaction and fusion module, which performs principal component matching interaction on the time series associated implicit feature vector of real-time tension value and the time series associated implicit feature vector of real-time elongation to obtain the time series significant interaction coupling feature vector of tension-elongation; a fracture analysis module, which obtains the cable tensile fracture analysis result based on the time series significant interaction coupling feature vector of tension-elongation.

[0006] Optionally, the information interaction fusion module includes: a principal component analysis unit, which performs principal component analysis on the real-time tension value time series associated implicit feature vector and the real-time elongation time series associated implicit feature vector respectively to obtain a set of real-time tension value time series principal component feature components and a set of real-time elongation time series principal component feature components; an optimal pairing interactive coupling unit, which performs optimal pairing multi-scale interactive coupling on the set of real-time tension value time series principal component feature components and the set of real-time elongation time series principal component feature components to obtain a tension-elongation time series significant interactive coupling feature vector.

[0007] Optionally, the principal component analysis unit calculates the covariance matrix of the implicit eigenvectors associated with the real-time tension value time series to obtain the real-time tension value time series feature covariance matrix; performs eigenvalue decomposition on the real-time tension value time series feature covariance matrix to obtain a set of real-time tension value time series principal component eigenvalues ​​and a set of corresponding real-time tension value time series principal component feature components; calculates the covariance matrix of the implicit eigenvectors associated with the real-time elongation time series to obtain the real-time elongation time series feature covariance matrix; performs eigenvalue decomposition on the real-time elongation time series feature covariance matrix to obtain a set of real-time elongation time series principal component eigenvalues ​​and a set of corresponding real-time elongation time series principal component feature components.

[0008] Optionally, the best pairing interactive coupling unit includes: a best matching screening subunit, which uses each real-time tension value time series principal component feature component in the set of real-time tension value time series principal component feature components as a query vector, and uses the set of real-time elongation time series principal component feature components as a query library, and matches the real-time elongation time series principal component feature components that best match each query vector from the query library to obtain a set of best matching pairs of real-time tension value time series principal component feature components and real-time elongation time series principal component feature components; a multi-scale interactive fusion subunit, which performs multi-scale interactive fusion on the set of best matching pairs of real-time tension value time series principal component feature components and real-time elongation time series principal component feature components to obtain a tension-elongation time series significant interactive coupling feature vector.

[0009] Optionally, the best matching screening subunit calculates the Mahalanobis distance between the query vector and each real-time elongation time series principal component feature component in the query library to obtain a set of tension-elongation matching difference coefficients; selects the real-time elongation time series principal component feature component corresponding to the minimum value in the set of tension-elongation matching difference coefficients as the optimal matching result of the query vector to obtain the best matching pair of the real-time tension value time series principal component feature component and the real-time elongation time series principal component feature component.

[0010] Optionally, the multi-scale interactive fusion sub-unit includes: a best matching pair interactive coupling secondary sub-unit, which inputs each best matching pair of real-time tension value time series principal component feature component and real-time elongation time series principal component feature component in the set of best matching pairs of real-time tension value time series principal component feature components and real-time elongation time series principal component feature components into the multi-scale interactive response coupling module to obtain a set of multi-scale interactive coupling representation vectors of tension-elongation time series feature best matching pairs; and a feature cascade secondary sub-unit, which cascades the set of multi-scale interactive coupling representation vectors of tension-elongation time series feature best matching pairs to obtain a tension-elongation time series significant interactive coupling feature vector.

[0011] In a second aspect, a cable tensile test method is provided, using a cable tensile test device as described in any one of the first aspects, comprising the following steps: Step S100: applying a pulling force to the cable to stretch the cable; Step S200: obtaining the real-time tension value and real-time elongation of the cable when it is stretched; Step S300: generating a cable tensile fracture analysis result according to the real-time tensile force value and the real-time elongation value when the cable is stretched; Step S400: Determine whether to generate a fracture warning prompt based on the cable tensile fracture analysis result.

[0012] Optionally, the step S300 includes the following steps: Step S301, obtaining a time queue of the real-time tension value and a time queue of the real-time elongation of the cable according to the real-time tension value and the real-time elongation of the cable when the cable is stretched; Step S302, performing time series coding on the time series of the real-time tension value and the time series of the real-time elongation respectively to obtain a time series associated implicit feature vector of the real-time tension value and a time series associated implicit feature vector of the real-time elongation; Step S303, performing principal component matching interaction on the real-time tension value time series associated implicit feature vector and the real-time elongation time series associated implicit feature vector to obtain a tension-elongation time series significant interaction coupling feature vector; Step S304, obtaining the cable tensile fracture analysis result based on the tension-elongation time series significant interactive coupling eigenvector.

[0013] Optionally, the step S303 includes: Step S3031: performing principal component analysis on the real-time tension value time series associated implicit feature vector and the real-time elongation time series associated implicit feature vector respectively to obtain a set of real-time tension value time series principal component feature components and a set of real-time elongation time series principal component feature components; Step S3032: optimally pair the set of principal component characteristic components of the real-time tension value time series and the set of principal component characteristic components of the real-time elongation time series by multi-scale interactive coupling to obtain a tension-elongation time series significant interactive coupling characteristic vector.

[0014] Optionally, the step S3031 includes: Step S30311: Calculate the covariance matrix of the real-time tension value time series associated implicit eigenvectors to obtain the real-time tension value time series feature covariance matrix; perform eigenvalue decomposition on the real-time tension value time series feature covariance matrix to obtain a set of real-time tension value time series principal component eigenvalues ​​and a set of corresponding real-time tension value time series principal component feature components; Step S30312: Calculate the covariance matrix of the implicit eigenvector associated with the real-time elongation time series to obtain the real-time elongation time series feature covariance matrix; perform eigenvalue decomposition on the real-time elongation time series feature covariance matrix to obtain a set of real-time elongation time series principal component eigenvalues ​​and a corresponding set of real-time elongation time series principal component feature components.

[0015] Compared with the prior art, the present invention has the following beneficial effects: (1) In the present invention, the tension and elongation of the cable are monitored and analyzed in real time, and the time series dynamic change characteristics of the tension and elongation are extracted respectively. The interactive response pattern between the tension and elongation of the cable is captured by fine-grained matching interaction between the two, so as to intelligently identify the potential risk of cable breakage during the stretching process and generate corresponding fracture warning prompts, so as to timely detect the abnormal stretching state of the cable and effectively prevent the accidental breakage of the cable during the test, thereby avoiding equipment damage and personnel safety risks caused by sudden cable breakage.

[0016] (2) In the present invention, while clustering the feature vectors of the tension-elongation time series significant interactive coupling, the interaction of the key feature information of the tension-elongation time series significant interactive coupling feature vectors in the clustering process is described, and the geometric equivariant topology of the feature is constructed by low-rank harmonic modulation of the clustering features of the tension-elongation time series significant interactive coupling feature vectors and the equivariance of the feature as a whole, so as to obtain the graphical distribution translation and rotation symmetry of the clustering features of the tension-elongation time series significant interactive coupling feature vectors relative to the feature as a whole, thereby introducing geometric message passing into the feature expression of the tension-elongation time series significant interactive coupling feature vectors and realizing the cluster mapping symmetry of the tension-elongation time series significant interactive coupling feature vectors through manipulation of irreducible low-rank order coefficients, thereby improving the consistency of the clustering-based feature representation of the tension-elongation time series significant interactive coupling feature vectors, thereby improving the accuracy of the fracture analysis result obtained by inputting the tension-elongation time series significant interactive coupling feature vectors into the classifier-based fracture warning engine. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] The above and other purposes, features and advantages of the present invention will become more apparent by describing the embodiments of the present invention in more detail in conjunction with the accompanying drawings. The accompanying drawings are used to provide a further understanding of the embodiments of the present invention and constitute a part of the specification. Together with the embodiments of the present invention, they are used to explain the present invention and do not constitute a limitation on the present invention. In the accompanying drawings, the same reference numerals generally represent the same components or steps.

[0018] Figure 1 This is a schematic structural diagram of a cable tensile testing device applied for in the present invention.

[0019] Figure 2 This is a schematic diagram of the working principle of the processing mechanism applied for in the present invention.

[0020] Figure 3 This is a schematic diagram of the composition of the information interaction and fusion module applied for in the present invention.

[0021] Figure 4A schematic flow chart of a cable tensile testing method applied for in the present invention.

[0022] 100 - cable tensile testing device, 110 - tensile mechanism, 120 - detection mechanism, 130 - processing mechanism, 140 - processing mechanism, 1300 - information interaction fusion module, 1301 - principal component analysis unit, 1302 - optimal pairing interaction coupling unit. DETAILED DESCRIPTION

[0023] In order to make the purpose, technical solution and advantages of the embodiments of the present disclosure more clear, the embodiments of the present disclosure are further described in detail below in conjunction with the accompanying drawings and embodiments; it should be understood that the specific embodiments described herein are only used to explain the embodiments of the present disclosure and are not used to limit the embodiments of the present disclosure; The structures, proportions, sizes, etc. illustrated in the drawings of this specification are only used to match the contents disclosed in the specification for people familiar with this technology to understand and read, and are not used to limit the limiting conditions for the implementation of the present invention, so they have no substantial technical significance. Any structural modification, change in proportion relationship or adjustment in size, without affecting the effects and purposes that can be produced by the present invention, should still fall within the scope of the technical contents disclosed by the present invention; at the same time, the terms such as "and" and "or" quoted in this specification are only for the convenience of description, and are not used to limit the scope of implementation. The change or adjustment of their relative relationship should also be regarded as the scope of implementation of the present invention without substantially changing the technical contents; in addition, the various embodiments of the present invention are not independent of each other, but can be combined; As shown in the present application and claims, unless the context clearly indicates an exception, the words "a", "an", "an" and / or "the" do not refer to the singular, but also include the plural. Generally speaking, the terms "include" and "comprise" only indicate the inclusion of the steps and elements that have been clearly identified, and these steps and elements do not constitute an exclusive list, and the method or device may also include other steps or elements.

[0024] Below, the exemplary embodiments of the present invention will be described in detail with reference to the accompanying drawings. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all the embodiments of the present invention, and it should be understood that the present invention is not limited to the exemplary embodiments described here.

[0025] In the existing cable technology field, cable tensile testing equipment can usually be used to evaluate the physical properties of cables under tensile conditions. Physical properties can usually include evaluation parameters such as tensile strength, elongation at break, yield strength, and elastic modulus. Tensile strength refers to the maximum tensile force that a cable can withstand before being pulled apart, and is an important indicator for evaluating the mechanical strength of a cable; elongation at break refers to the percentage of the elongation of the gauge length to the original gauge length when the cable breaks due to tension, reflecting the plastic deformation capacity of the cable; yield strength refers to the stress value when obvious plastic deformation occurs during the stretching process of the cable, and is an important indicator for evaluating the cable's ability to resist deformation; elastic modulus refers to the ratio of stress to strain during the elastic deformation stage of the cable, reflecting the cable's ability to resist elastic deformation. Generally speaking, these evaluation parameters are important bases for evaluating the mechanical properties of cables.

[0026] Cable tensile testing equipment usually includes: a stretching mechanism, which is used to clamp the cable and apply a tensile force to the cable to stretch the cable at a certain speed. The stretching mechanism usually includes a motor, a reducer, a transmission structure, a clamp, etc.; a detection mechanism, which measures the cable stretching data (such as tension, displacement and other parameters) during the stretching process and outputs it to the processing mechanism. The detection mechanism usually includes a tension sensor, a displacement sensor, etc.; a processing mechanism, which processes and accurately analyzes the cable stretching data (such as tension, displacement and other parameters) during the cable testing process in real time, and outputs it to the control mechanism; a control mechanism, which is used to control and monitor the cable stretching test process in real time, and display the cable stretching data during the cable stretching test process. The control mechanism usually includes a computer, a controller, a data acquisition card, etc.; the stretching mechanism, the detection mechanism, the processing mechanism and the control mechanism cooperate with each other during the test process, operate in strict accordance with relevant standards and specifications, and jointly ensure the accuracy, stability and reliability of the cable stretching test process to complete a comprehensive evaluation of the physical properties of the cable under stretching conditions. These are all common technical knowledge in the existing cable technology field.

[0027] However, considering that during the cable tensile test, the cable may suddenly break due to material defects, manufacturing defects or over-stretching, it will not only damage the cable testing equipment, but also pose a safety hazard to the tester, while increasing unnecessary testing costs. Therefore, in order to avoid unnecessary testing costs and improve the safety of cable testing, the present invention proposes a cable tensile testing device and method.

[0028] like Figures 1 to 3As shown, in the first aspect, the present invention provides a cable stretching test device 100, including: a stretching mechanism 110, applying tension to the cable to stretch the cable; a detection mechanism 120, obtaining the real-time tension value and the real-time elongation of the cable when stretched; a processing mechanism 130, processing and generating a cable stretching fracture analysis result according to the real-time tension value and the real-time elongation of the cable when stretched; a control mechanism 140, determining whether to generate a fracture warning prompt according to the cable stretching fracture analysis result.

[0029] Based on the common technical knowledge in the above-mentioned existing cable technology field, it should be understood that during the cable tensile test, the force and deformation of the cable are key indicators reflecting the physical properties of the cable and the tensile state of the cable tensile test. Therefore, in the technical solution of the present invention, by real-time monitoring of the magnitude of the tensile force on the cable and the real-time elongation of the cable under the tensile force, it can be used to evaluate the physical properties of the cable, and at the same time, it can also timely discover abnormal data changes during the cable tensile test, so as to warn of potential breakage risks in advance.

[0030] Optionally, the processing mechanism includes: a cable tension state monitoring module, which obtains the time queue of the real-time tension value and the time queue of the real-time elongation of the cable according to the real-time tension value and the real-time elongation when the cable is stretched; a cable tension parameter timing encoding module, which performs timing encoding on the time queue of the real-time tension value and the time queue of the real-time elongation respectively to obtain the real-time tension value time series associated implicit feature vector and the real-time elongation time series associated implicit feature vector; an information interaction fusion module 1300, which performs principal component matching interaction on the real-time tension value time series associated implicit feature vector and the real-time elongation time series associated implicit feature vector to obtain the tension-elongation time series significant interactive coupling feature vector; a fracture analysis module, which obtains the cable tension fracture analysis result based on the tension-elongation time series significant interactive coupling feature vector.

[0031] In some embodiments, the cable tension state monitoring module can complete a time queue for obtaining a real-time tension value and a time queue for obtaining a real-time elongation value of the cable.

[0032] Exemplarily, the detection mechanism may include a force sensor and a displacement sensor, which may respectively monitor and collect the real-time tension value and real-time elongation of the cable when it is stretched, and the real-time tension value and real-time elongation may change with time; the cable stretching state monitoring module may obtain the real-time tension value and real-time elongation of the cable based on the force sensor and the displacement sensor, and as time gradually passes during the stretching test of the cable, multiple real-time tension values ​​that are sequentially spaced in time may at least form a time queue of real-time tension values, and multiple real-time elongations that are sequentially spaced in time may at least form a time queue of real-time elongations, and thus the cable stretching state monitoring module may complete the acquisition of the time queue of the real-time tension value and the time queue of the real-time elongation of the cable.

[0033] In some embodiments, the cable tensile parameter timing encoding module inputs the time queue of real-time tension values ​​and the time queue of real-time elongation into a sequence encoder based on a forward long short-term memory network (LSTM) model to obtain a real-time tension value timing-associated implicit feature vector and a real-time elongation timing-associated implicit feature vector.

[0034] Exemplarily, considering that the stress and deformation of the cable during the stretching process is a continuous and dynamically changing process, in order to fully and accurately capture the dynamic change characteristics of the cable tension value and elongation, the present invention application adopts a forward long short-term memory network (LSTM) to process the time queue of the real-time tension value and the time queue of the real-time elongation respectively. The forward long short-term memory network (LSTM) is a special recurrent neural network architecture, which performs well in processing sequence data, especially time series data analysis. It can make full use of the gating mechanism inside the forward long short-term memory network (LSTM), effectively capture the long-term dependencies in the time series data, learn the complex patterns of tension value and elongation changing with time, and obtain the real-time tension value time series associated implicit feature vector and the real-time elongation time series associated implicit feature vector, thereby providing useful data support for subsequent fracture warning identification.

[0035] In some embodiments, the information interaction fusion module performs principal component matching interaction on the real-time tension value time series associated implicit feature vector and the real-time elongation time series associated implicit feature vector to obtain the tension-elongation time series significant interaction coupling feature vector.

[0036] For example, during the tensile test of the cable, there is a certain interaction between the force and deformation, that is, the increase in the tensile force value of the cable is usually accompanied by an increase in the elongation. However, when the cable approaches the breaking point, since the material begins to undergo plastic deformation when approaching the ultimate strength and no longer follows linear elastic behavior, this interaction will show an abnormal pattern. For example, the rate of increase in elongation is much greater than the rate of increase in the tensile force value. Accordingly, the interactive response pattern between the real-time tensile force value and the real-time elongation of the cable can be analyzed to identify the potential risk of cable breakage.

[0037] Accordingly, in order to effectively extract and enhance the key interaction features between tension values ​​and elongation, the present invention application proposes an optimal matching interaction method based on feature principal components, which uses principal component analysis and feature optimal matching technology to screen out the most representative feature interaction combinations between tension values ​​and elongation, thereby better understanding and modeling the subtle and nonlinear interaction response patterns between the two, thereby improving the distinction between the two.

[0038] like Figure 3 As shown, the information interaction fusion module 1300 includes: a principal component analysis unit 1301, which performs principal component analysis on the real-time tension value time series associated implicit feature vector and the real-time elongation time series associated implicit feature vector respectively to obtain a set of real-time tension value time series principal component feature components and a set of real-time elongation time series principal component feature components; an optimal pairing interactive coupling unit 1302, which performs optimal pairing multi-scale interactive coupling on the set of real-time tension value time series principal component feature components and the set of real-time elongation time series principal component feature components to obtain a tension-elongation time series significant interactive coupling feature vector.

[0039] Optionally, the principal component analysis unit 1301 calculates the covariance matrix of the implicit eigenvectors associated with the real-time tension value time series to obtain the real-time tension value time series feature covariance matrix; performs eigenvalue decomposition on the real-time tension value time series feature covariance matrix to obtain a set of real-time tension value time series principal component eigenvalues ​​and a set of corresponding real-time tension value time series principal component feature components; calculates the covariance matrix of the implicit eigenvectors associated with the real-time elongation time series to obtain the real-time elongation time series feature covariance matrix; performs eigenvalue decomposition on the real-time elongation time series feature covariance matrix to obtain a set of real-time elongation time series principal component eigenvalues ​​and a set of corresponding real-time elongation time series principal component feature components.

[0040] In some embodiments, principal component analysis (PCA) is a widely used linear dimensionality reduction technique for reducing the dimension of a data set while retaining important information of the original data as much as possible. It converts possibly correlated variables into a set of linearly uncorrelated variables through orthogonal transformation. Accordingly, principal component analysis (PCA) technology can be used to process the real-time tension value time series associated implicit eigenvectors and the real-time elongation time series associated implicit eigenvectors, thereby reducing the complexity of the tension value and elongation data and extracting the main features in the tension value and elongation data, focusing on the key dynamic changes in the cable tensile test, thereby obtaining a set of real-time tension value time series principal component feature components and a set of real-time elongation time series principal component feature components.

[0041] Optionally, the best pairing interactive coupling unit 1302 includes: a best matching screening subunit, which uses each real-time tension value time series principal component feature component in the set of real-time tension value time series principal component feature components as a query vector, and uses the set of real-time elongation time series principal component feature components as a query library, and matches the real-time elongation time series principal component feature components that best match each query vector from the query library to obtain a set of best matching pairs of real-time tension value time series principal component feature components and real-time elongation time series principal component feature components; a multi-scale interactive fusion subunit, which performs multi-scale interactive fusion on the set of best matching pairs of real-time tension value time series principal component feature components and real-time elongation time series principal component feature components to obtain a tension-elongation time series significant interactive coupling feature vector.

[0042] Optionally, the best matching screening subunit calculates the Mahalanobis distance between the query vector and each real-time elongation time series principal component feature component in the query library to obtain a set of tension-elongation matching difference coefficients; selects the real-time elongation time series principal component feature component corresponding to the minimum value in the set of tension-elongation matching difference coefficients as the optimal matching result of the query vector to obtain the best matching pair of the real-time tension value time series principal component feature component and the real-time elongation time series principal component feature component.

[0043] In some embodiments, an optimal matching algorithm can be used to perform feature query matching on a set of two principal component feature components, and the most relevant feature pairs can be queried using the Mahalanobis distance as a metric to establish a one-to-one correspondence between the real-time tension value time series principal component feature components and the real-time elongation time series principal component feature components, thereby achieving accurate matching of the strongly correlated interactive response pattern between tension and elongation.

[0044] Optionally, the multi-scale interactive fusion sub-unit includes: a best matching pair interactive coupling secondary sub-unit, which inputs each best matching pair of real-time tension value time series principal component feature component and real-time elongation time series principal component feature component in the set of best matching pairs of real-time tension value time series principal component feature components and real-time elongation time series principal component feature components into the multi-scale interactive response coupling module to obtain a set of multi-scale interactive coupling representation vectors of tension-elongation time series feature best matching pairs; and a feature cascade secondary sub-unit, which cascades the set of multi-scale interactive coupling representation vectors of tension-elongation time series feature best matching pairs to obtain the tension-elongation time series significant interactive coupling feature vector.

[0045] In some embodiments, each best matching pair can be input into a multi-scale interactive response coupling module for interactive response analysis of the best pairing features. The multi-scale interactive response coupling module performs multi-level feature interaction and deep learning on the real-time tension value time series principal component feature components and the real-time elongation time series principal component feature components in the best matching pair, which can effectively capture the interaction mode of tension value and elongation at different abstract levels, and automatically learn and generate the interactive feature representation of each best matching pair. Finally, by performing a cascade operation on the interactive feature representation of the best matching pair to integrate global information, the tension-elongation time series significant interactive coupling feature vector in the cable tensile test process is obtained, so as to comprehensively reflect the interactive response mode between tension and elongation of the cable during the tensile process, thereby providing a more comprehensive and in-depth analysis basis for the cable fracture warning analysis and evaluation.

[0046] Optionally, the best matching pair of interactively coupled secondary subunits comprises: Respectively calculate the best matching pairs of the real-time tension value time series principal component characteristic components and the real-time elongation time series principal component characteristic components by position point addition, position point subtraction and position point multiplication between the real-time tension value time series principal component characteristic components and the real-time elongation time series principal component characteristic components to obtain the best matching interaction representation vector of the first tension-elongation time series principal component component, the best matching interaction representation vector of the second tension-elongation time series principal component component and the best matching interaction representation vector of the third tension-elongation time series principal component component; The first tension-elongation time series principal component best matching interaction representation vector, the second tension-elongation time series principal component best matching interaction representation vector and the third tension-elongation time series principal component best matching interaction representation vector are cascaded and fused, and then input into a one-dimensional convolutional layer including a maximum pooling layer to obtain a tension-elongation time series principal component best matching multi-scale interaction representation vector; The second norm of the real-time tension value time series principal component characteristic component, the second norm of the real-time elongation time series principal component characteristic component and the maximum value of the preset scale adjustment parameter are selected as the scale scaling factor, and each eigenvalue in the best matching multi-scale interaction representation vector of the tension-elongation time series principal component component is divided by the scale scaling factor to obtain the multi-scale interaction coupling representation vector of the best matching pair of tension-elongation time series characteristics.

[0047] Optionally, the information interaction fusion module uses a principal component matching interaction fusion formula to process the real-time tension value time series associated implicit feature vector and the real-time elongation time series associated implicit feature vector to obtain a tension-elongation time series significant interaction coupling feature vector, and the principal component matching interaction fusion formula includes: Wherein, C1 and C2 represent the covariance matrices of the real-time tension value time series associated implicit eigenvector and the real-time elongation time series associated implicit eigenvector, respectively. Λ1 is the diagonal matrix composed of the set of real-time tension value time series principal component eigenvalues ​​obtained by eigenvalue decomposition of the real-time tension value time series feature covariance matrix. λ 11 and λ 1m They respectively represent the first and mth real-time tension value time series principal component eigenvalues ​​in the set of real-time tension value time series principal component eigenvalues, wherein m is the number of real-time tension value time series principal component eigenvalues, U1 is a matrix composed of the set of real-time tension value time series principal component eigenvalues, and v 11 、v 12 、v 1i and v 1m They represent the first, second, i-th and m-th real-time tension value time series principal component characteristic components in the set of real-time tension value time series principal component characteristic components, respectively, (•) T represents the transpose of the matrix, Λ2 is the diagonal matrix composed of the set of principal component eigenvalues ​​of the real-time elongation time series obtained by eigenvalue decomposition of the real-time elongation time series feature covariance matrix, λ 21 and λ 2m respectively represent the first and mth real-time stretch time series principal component eigenvalues ​​in the set of real-time stretch time series principal component eigenvalues, U2 is a matrix composed of the set of real-time stretch time series principal component eigenvalues, v 21 、v 22 、v 2i 、v 2k and v 2m They represent the first, second, jth, kth and mth real-time stretch time series principal component characteristic components in the set of real-time stretch time series principal component characteristic components, S -1represents the inverse matrix of the covariance matrix between the i-th real-time tension value time series principal component feature component and the j-th real-time elongation time series principal component feature component, argmin represents the index corresponding to the minimum value, k represents the index of the real-time elongation time series principal component feature component with the smallest semantic difference from the i-th real-time tension value time series principal component feature component, represents dot product, Indicates point addition, represents point subtraction, conv1D represents a one-dimensional convolution operation, and MaxPool represents a maximum pooling operation. represents the bi-norm of the feature vector, ε is the preset scale adjustment parameter, max(•) is the maximum value function, and v p1 、v p2 、v pi and v pm They represent the multi-scale interaction coupling representation vectors of the first, second, i-th and m-th tensile-elongation time series characteristics’ best matches, respectively. represents the cascade operation, and V represents the significant interactive coupling eigenvector of the tension-elongation time series.

[0048] However, when the real-time tension value temporal association implicit feature vector and the real-time elongation temporal association implicit feature vector respectively represent the forward short-range-long-range temporal association features of the real-time tension value and the real-time elongation, when the interactive response coupling based on the best matching of the feature principal component granularity is performed on them, the tension-elongation temporal significant interactive coupling feature vector will also cause the interactive response difference value based on the best matching due to the difference in the temporal pattern of the feature principal component granularity, affecting the consistency of the classification mapping iteration and reducing the accuracy of the classification result. Therefore, it is expected to improve the semantically consistent aggregation expression effect of the tension-elongation temporal significant interactive coupling feature vector.

[0049] Optionally, inputting the tension-elongation time series significant interactive coupling feature vector into a classifier-based fracture warning engine to obtain a fracture analysis result includes: The feature set of the tension-elongation time series significant interactive coupling feature vector is clustered to obtain a tension-elongation time series significant interactive coupling in-class feature set and a tension-elongation time series significant interactive coupling out-class feature set, that is: Among them, C represents the intra-class feature set of significant interaction coupling of tension-elongation time series, and f 1i represents the i-th eigenvalue of the feature set within the class of significant interaction coupling of tension-elongation time series, f 2j It represents the jth eigenvalue of the out-of-class feature set of the tension-elongation time series significant interactive coupling, where i and j are both positive integers; The ratio of the number of eigenvalues ​​in the feature set of the tension-elongation time series significant interactive coupling class to the number of eigenvalues ​​in the feature set of the tension-elongation time series significant interactive coupling feature vector is calculated, that is: Wherein, k represents the number of eigenvalues ​​in the feature set of the tension-elongation time series significant interactive coupling class, n represents the number of eigenvalues ​​in the feature set of the tension-elongation time series significant interactive coupling feature vector, and λ represents the ratio; The ratio of the λ-th power of the sum of the absolute values ​​of all eigenvalues ​​in the feature set of the tension-elongation time series significant interactive coupling class to the λ-th power of the sum of the absolute values ​​of all eigenvalues ​​in the feature set of the tension-elongation time series significant interactive coupling eigenvector is calculated to obtain the tension-elongation time series significant interactive coupling modulation weight, that is: Among them, f p represents each eigenvalue in the feature set of the tension-elongation time series significant interactive coupling eigenvector, w1 represents the tension-elongation time series significant interactive coupling modulation weight; The ratio of the λ / 2 power of the sum of squares of all eigenvalues ​​in the feature set of the tension-elongation time series significant interactive coupling class to the λ / 2 power of the sum of squares of all eigenvalues ​​in the feature set of the tension-elongation time series significant interactive coupling eigenvector is calculated to obtain the tension-elongation time series significant interactive coupling harmonic weight, that is: Where w2 represents the harmonic weight of the significant interaction coupling of the tension-elongation time series; For each eigenvalue in the feature set of the tension-elongation time series significant interactive coupling class, the product of the eigenvalue and the tension-elongation time series significant interactive coupling harmonic weight is calculated, and then the product of the eigenvalue and the tension-elongation time series significant interactive coupling modulation weight is added to obtain the optimized eigenvalue, that is: Among them, f' 1i represents the i-th optimized eigenvalue of the feature set within the class of significant interactive coupling based on the tension-elongation time series; For each eigenvalue in the tension-elongation time series significant interactive coupling out-of-class feature set, the product of the eigenvalue and the tension-elongation time series significant interactive coupling modulation weight is calculated to obtain the optimized eigenvalue, that is: Among them, f' 2j represents the jth optimized eigenvalue of the out-of-class feature set based on the tension-elongation time series significant interactive coupling; The optimized tension-elongation time series significant interactive coupling feature vector based on the optimized feature values ​​of the tension-elongation time series significant interactive coupling within-class feature set and the tension-elongation time series significant interactive coupling outside-class feature set is input into the classifier-based fracture warning engine to obtain the fracture analysis result.

[0050] In some embodiments, the fracture analysis module can input the optimized tension-elongation time series significant interactive coupling feature vector into the fracture warning engine based on the classifier to obtain the fracture analysis result. For example, the optimized tension-elongation time series significant interactive coupling feature vector can be judged by the classifier model, and the classifier can deeply learn the interactive change pattern between tension and elongation contained in the tension-elongation time series significant interactive coupling feature vector, and then accurately distinguish the normal tension state and potential abnormal state of the cable, and output the corresponding fracture analysis result, so as to provide real-time fracture warning prompts for operators, so as to realize real-time monitoring of the cable tension state and fracture warning.

[0051] Therefore, while the tension-elongation time series significant interactive coupling feature vector is subjected to feature clustering, the interaction of the key feature information of the tension-elongation time series significant interactive coupling feature vector in the clustering process is described, and the geometric equivariant topology of the feature is constructed by low-rank harmonic modulation of the clustering features of the tension-elongation time series significant interactive coupling feature vector and the equivariance of the feature as a whole, so as to obtain the graphical distribution translation and rotational symmetry of the clustering features of the tension-elongation time series significant interactive coupling feature vector relative to the feature as a whole, thereby introducing geometric message passing into the feature expression of the tension-elongation time series significant interactive coupling feature vector and realizing the cluster mapping symmetry of the tension-elongation time series significant interactive coupling feature vector through manipulation of irreducible low-rank order coefficients, thereby improving the consistency of the clustering-based feature representation of the tension-elongation time series significant interactive coupling feature vector, thereby improving the accuracy of the fracture analysis result obtained by inputting the tension-elongation time series significant interactive coupling feature vector into the classifier-based fracture warning engine.

[0052] In some embodiments, determining whether to generate a fracture warning prompt includes: the control mechanism determines that there is a risk of tensile fracture according to the cable tensile fracture analysis result, and generates a fracture warning prompt; the control mechanism determines that there is no risk of tensile fracture according to the cable tensile fracture analysis result, and does not generate a fracture warning prompt. Exemplarily, the fracture warning prompt can be prompted by a display module (such as a display screen, etc.) and / or an audible and visual alarm module.

[0053] In summary, the cable tensile test device based on the present invention application is explained, which uses deep learning-based data analysis technology to perform real-time monitoring and data analysis on the tension and elongation of the cable, extracts the time series dynamic change characteristics of the tension and elongation respectively, and captures the interactive response pattern between the tension and elongation of the cable by fine-grained matching interaction between the two, so as to intelligently identify the potential risk of cable breakage during the stretching process and generate corresponding breakage warning prompts. In this way, the abnormal stretching state of the cable can be discovered in time, and the accidental breakage of the cable during the test can be effectively prevented, thereby avoiding equipment damage and personnel safety risks caused by sudden cable breakage.

[0054] like Figure 4 As shown, in a second aspect, the present invention provides a cable testing method, using a cable testing device as described in any one of the first aspects above, comprising the following steps: It should be noted that a cable testing method applied for in the present invention adopts a cable testing device described in any one of the first aspects above, and accordingly includes: all the technical problems, technical solutions and technical effects recorded in a cable testing device described in any one of the first aspects, which will not be repeated in the present application.

[0055] Step S100: applying a pulling force to the cable to stretch the cable; Step S200: obtaining the real-time tension value and real-time elongation of the cable when it is stretched; Step S300: generating a cable tensile fracture analysis result according to the real-time tensile force value and the real-time elongation value when the cable is stretched; Step S400: Determine whether to generate a fracture warning prompt based on the cable tensile fracture analysis result.

[0056] In a cable testing method applied for in the present invention, first, a tensile force is applied to the cable to stretch the cable, and the real-time tensile force value and the real-time elongation of the cable when stretched are obtained; then, according to the real-time tensile force value and the real-time elongation of the cable when stretched, the cable stretching fracture analysis result is processed and generated; then, according to the cable stretching fracture analysis result, it is determined whether to generate a fracture warning prompt, thereby realizing real-time monitoring and data analysis of the tensile force value and elongation of the cable, respectively extracting the time series dynamic change characteristics of the tensile force value and the elongation, intelligently identifying the potential fracture risk of the cable during the stretching process, and generating corresponding fracture warning prompts, which can timely detect the abnormal stretching state of the cable, effectively prevent the accidental fracture of the cable during the test, thereby avoiding equipment damage and personnel safety risks caused by sudden cable fracture.

[0057] Optionally, step S300 includes the following steps: Step S301, obtaining a time queue of the real-time tension value and a time queue of the real-time elongation of the cable according to the real-time tension value and the real-time elongation of the cable when the cable is stretched; Step S302, performing time series coding on the time series of the real-time tension value and the time series of the real-time elongation respectively to obtain a time series associated implicit feature vector of the real-time tension value and a time series associated implicit feature vector of the real-time elongation; Step S303, performing principal component matching interaction on the real-time tension value time series associated implicit feature vector and the real-time elongation time series associated implicit feature vector to obtain a tension-elongation time series significant interaction coupling feature vector; Step S304, obtaining the cable tensile fracture analysis result based on the tension-elongation time series significant interactive coupling eigenvector.

[0058] Optionally, step S303 includes: Step S3031: performing principal component analysis on the real-time tension value time series associated implicit feature vector and the real-time elongation time series associated implicit feature vector respectively to obtain a set of real-time tension value time series principal component feature components and a set of real-time elongation time series principal component feature components; Specifically, step S3031 includes: Step S30311: Calculate the covariance matrix of the real-time tension value time series associated implicit eigenvectors to obtain the real-time tension value time series feature covariance matrix; perform eigenvalue decomposition on the real-time tension value time series feature covariance matrix to obtain a set of real-time tension value time series principal component eigenvalues ​​and a set of corresponding real-time tension value time series principal component feature components; Step S30312: Calculate the covariance matrix of the real-time elongation time series associated implicit eigenvector to obtain the real-time elongation time series feature covariance matrix; perform eigenvalue decomposition on the real-time elongation time series feature covariance matrix to obtain a set of real-time elongation time series principal component eigenvalues ​​and a set of corresponding real-time elongation time series principal component feature components; Step S3032: Perform optimal pairing multi-scale interactive coupling on the set of real-time tension value time series principal component characteristic components and the set of real-time elongation time series principal component characteristic components to obtain a tension-elongation time series significant interactive coupling characteristic vector.

[0059] Specifically, step S3032 includes: Step S30321: using each real-time tension value time series principal component characteristic component in the set of real-time tension value time series principal component characteristic components as a query vector, and using the set of real-time elongation time series principal component characteristic components as a query library, matching the real-time elongation time series principal component characteristic components that best match each query vector from the query library to obtain a set of best matching pairs of real-time tension value time series principal component characteristic components and real-time elongation time series principal component characteristic components; Step S30322: Perform multi-scale interactive fusion on the set of the best matching pairs of the real-time tension value time series principal component feature components and the real-time elongation time series principal component feature components to obtain a tension-elongation time series significant interactive coupling feature vector.

[0060] Optionally, in step S300, the real-time tension value time series associated implicit feature vector and the real-time elongation time series associated implicit feature vector are processed using a principal component matching interactive fusion formula to obtain a tension-elongation time series significant interactive coupling feature vector, wherein the principal component matching interactive fusion formula includes: Wherein, C1 and C2 represent the covariance matrix of the real-time tension value time series associated implicit eigenvector and the real-time elongation time series associated implicit eigenvector, respectively, Λ1 is a diagonal matrix composed of the set of real-time tension value time series principal component eigenvalues ​​obtained by eigenvalue decomposition of the real-time tension value time series feature covariance matrix, λ 11 and λ 1m They respectively represent the first and mth real-time tension value time series principal component eigenvalues ​​in the set of real-time tension value time series principal component eigenvalues, wherein m is the number of real-time tension value time series principal component eigenvalues, U1 is a matrix composed of the set of real-time tension value time series principal component eigenvalues, and v 11 、v 12 、v 1i and v 1m They represent the first, second, i-th and m-th real-time tension value time series principal component characteristic components in the set of real-time tension value time series principal component characteristic components, respectively, (•) T represents the transpose of the matrix, Λ2 is the diagonal matrix composed of the set of principal component eigenvalues ​​of the real-time elongation time series obtained by eigenvalue decomposition of the real-time elongation time series feature covariance matrix, λ 21 and λ 2m respectively represent the first and mth real-time stretch time series principal component eigenvalues ​​in the set of real-time stretch time series principal component eigenvalues, U2 is a matrix composed of the set of real-time stretch time series principal component eigenvalues, v 21 、v 22 、v 2i 、v 2k and v 2m They represent the first, second, jth, kth and mth real-time stretch time series principal component characteristic components in the set of real-time stretch time series principal component characteristic components, S -1represents the inverse matrix of the covariance matrix between the i-th real-time tension value time series principal component feature component and the j-th real-time elongation time series principal component feature component, argmin represents the index corresponding to the minimum value, k represents the index of the real-time elongation time series principal component feature component with the smallest semantic difference from the i-th real-time tension value time series principal component feature component, represents dot product, Indicates point addition, represents point subtraction, conv1D represents a one-dimensional convolution operation, and MaxPool represents a maximum pooling operation. represents the bi-norm of the feature vector, ε is the preset scale adjustment parameter, max(•) is the maximum value function, and v p1 、v p2 、v pi and v pm They represent the multi-scale interaction coupling representation vectors of the first, second, i-th and m-th tensile-elongation time series characteristics’ best matches, respectively. represents the cascade operation, and V represents the significant interactive coupling eigenvector of the tension-elongation time series.

[0061] Optionally, in step S304, the tension-elongation time series significant interaction coupling feature vector is input into a classifier-based fracture warning engine to obtain a fracture analysis result.

[0062] Specifically, step S304 includes: Step S3041: performing feature clustering on the feature set of the tension-elongation time series significant interactive coupling feature vector to obtain a tension-elongation time series significant interactive coupling in-class feature set and a tension-elongation time series significant interactive coupling out-class feature set, namely: Among them, C represents the intra-class feature set of significant interaction coupling of tension-elongation time series, and f 1i represents the i-th eigenvalue of the feature set within the class of significant interaction coupling of tension-elongation time series, f 2j It represents the jth eigenvalue of the out-of-class feature set of the tension-elongation time series significant interactive coupling, where i and j are both positive integers; Step S3042: Calculate the ratio of the number of eigenvalues ​​in the feature set of the tension-elongation time series significant interactive coupling class to the number of eigenvalues ​​in the feature set of the tension-elongation time series significant interactive coupling feature vector, that is: Wherein, k represents the number of eigenvalues ​​in the feature set of the tension-elongation time series significant interactive coupling class, n represents the number of eigenvalues ​​in the feature set of the tension-elongation time series significant interactive coupling feature vector, and λ represents the ratio; Step S3043: Calculate the ratio of the λ-th power of the sum of the absolute values ​​of all eigenvalues ​​in the feature set of the tension-elongation time series significant interactive coupling class to the λ-th power of the sum of the absolute values ​​of all eigenvalues ​​in the feature set of the tension-elongation time series significant interactive coupling feature vector to obtain the tension-elongation time series significant interactive coupling modulation weight, that is: Among them, f p represents each eigenvalue in the feature set of the tension-elongation time series significant interactive coupling eigenvector, w1 represents the tension-elongation time series significant interactive coupling modulation weight; Step S3044: Calculate the ratio of the λ / 2 power of the sum of squares of all eigenvalues ​​in the feature set of the tension-elongation time series significant interactive coupling class to the λ / 2 power of the sum of squares of all eigenvalues ​​in the feature set of the tension-elongation time series significant interactive coupling eigenvector to obtain the tension-elongation time series significant interactive coupling harmonic weight, that is: Where w2 represents the harmonic weight of the significant interaction coupling of the tension-elongation time series; Step S3045: For each eigenvalue in the feature set of the tension-elongation time series significant interactive coupling class, calculate the product of the eigenvalue and the tension-elongation time series significant interactive coupling harmonic weight plus the tension-elongation time series significant interactive coupling modulation weight to obtain the optimized eigenvalue, that is: Among them, f' 1i represents the i-th optimized eigenvalue of the feature set within the class of significant interactive coupling based on the tension-elongation time series; Step S3046: For each eigenvalue in the tension-elongation time series significant interactive coupling out-of-class feature set, calculate the product of the eigenvalue and the tension-elongation time series significant interactive coupling modulation weight to obtain the optimized eigenvalue, that is: Among them, f' 2j represents the jth optimized eigenvalue of the out-of-class feature set based on the tension-elongation time series significant interactive coupling; Step S3047: Input the optimized tension-elongation time series significant interactive coupling feature vector based on the optimized feature values ​​of the tension-elongation time series significant interactive coupling within-class feature set and the tension-elongation time series significant interactive coupling outside-class feature set into the classifier-based fracture warning engine to obtain the fracture analysis result.

[0063] In step S400, determining whether to generate a fracture warning prompt according to the cable tensile fracture analysis result includes: the control mechanism determines that there is a tensile fracture risk according to the cable tensile fracture analysis result, and generates a fracture warning prompt; the control mechanism determines that there is no tensile fracture risk according to the cable tensile fracture analysis result, and does not generate a fracture warning prompt. Exemplarily, the fracture warning prompt can be prompted by a display module (such as a display screen, etc.) and / or an audio and visual alarm module.

[0064] In a cable testing method applied in the present invention, while the tension-extension time series significant interactive coupling feature vector is subjected to feature clustering, the interaction description of the key feature information of the tension-extension time series significant interactive coupling feature vector in the clustering process is carried out, and the geometric equivariant topology of the feature is constructed by characteristic low-rank harmonic modulation based on the clustering feature of the tension-extension time series significant interactive coupling feature vector and the equivariant basis of the feature as a whole, so as to obtain the schematic distribution translation and rotation symmetry of the clustering feature of the tension-extension time series significant interactive coupling feature vector relative to the feature as a whole, thereby introducing geometric elimination in the feature expression of the tension-extension time series significant interactive coupling feature vector. On the basis of information transmission, the cluster mapping symmetry of the tension-elongation time series significant interactive coupling feature vector is realized by manipulating irreducible low-rank coefficients, and the consistency of the clustering-based feature representation of the tension-elongation time series significant interactive coupling feature vector is improved, thereby improving the accuracy of the fracture analysis result obtained by the fracture warning engine based on the classifier input of the tension-elongation time series significant interactive coupling feature vector, intelligently identifying the potential fracture risk of the cable during the stretching process, and generating corresponding fracture warning prompts, which can timely discover the abnormal stretching state of the cable and effectively prevent the accidental fracture of the cable during the test, thereby avoiding equipment damage and personnel safety risks caused by sudden cable fracture.

[0065] The basic principle of the present invention is described above in conjunction with specific embodiments. However, it should be pointed out that the advantages, strengths, effects, etc. mentioned in the present invention are only examples and not limitations, and it cannot be considered that these advantages, strengths, effects, etc. must be possessed by each embodiment of the present invention. In addition, the specific details of the above embodiments are only for the purpose of illustration and facilitation of understanding, rather than limitation, and the above details do not limit the present invention to being implemented by adopting the above specific details.

[0066] It will be apparent to those skilled in the art that the invention is not limited to the details of the exemplary embodiments described above and that the invention can be implemented in other specific forms without departing from the spirit or essential features of the invention. Therefore, the embodiments should be considered exemplary and non-limiting in all respects, and the scope of the invention is defined by the appended claims rather than the foregoing description, and it is intended that all variations falling within the meaning and scope of the equivalent elements of the claims be included in the invention. Any reference to a figure in a claim should not be considered as limiting the claim to which it relates.

[0067] In the above embodiments, the description of each embodiment has its own emphasis. For the parts that are not described or recorded in detail in a certain embodiment, please refer to the relevant description of other embodiments. In the several embodiments provided by the present invention, it should be understood that the disclosed system and method can be implemented in other ways. For example, the system embodiment described above is only schematic. For example, the unit division is only a logical function division, and there may be other division methods in actual implementation. The unit described as a separate component may or may not be physically separated, and the component displayed as a unit may or may not be a physical unit, that is, it may be located in one place, or it may be distributed on multiple network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the scheme of this embodiment. In addition, it is obvious that the word "including" does not exclude other units or steps, and the singular does not exclude the plural. The multiple units stated in the system claim can also be implemented by one unit through software or hardware.

[0068] Finally, it should be noted that the above description has been given for the purpose of illustration and description. In addition, the above embodiments are only used to illustrate the technical solution of the present invention and are not intended to limit it. Although the present invention has been described in detail with reference to the preferred embodiments, it should be understood by those skilled in the art that the technical solution of the present invention can be modified or replaced by equivalents without departing from the spirit and scope of the technical solution of the present invention.

Claims

1. A cable tensile testing device, characterized in that: include: A stretching mechanism applies a pulling force to the cable to stretch the cable; The detection mechanism obtains the real-time tension value and real-time elongation of the cable when it is stretched; The processing mechanism generates a cable tensile fracture analysis result according to the real-time tension value and real-time elongation of the cable when it is stretched; the control mechanism determines whether to generate a fracture warning prompt according to the cable tensile fracture analysis result; The processing mechanism includes: a cable stretching state monitoring module, which obtains a time queue of the real-time tension value and a time queue of the real-time elongation of the cable according to the real-time tension value and the real-time elongation of the cable when the cable is stretched; The cable tensile parameter timing encoding module performs timing encoding on the time queue of the real-time tension value and the time queue of the real-time elongation respectively to obtain the real-time tension value timing associated implicit feature vector and the real-time elongation timing associated implicit feature vector; the information interaction and fusion module performs principal component matching interaction on the real-time tension value timing associated implicit feature vector and the real-time elongation timing associated implicit feature vector to obtain the tension-elongation timing significant interactive coupling feature vector; the fracture analysis module obtains the cable tensile fracture analysis results based on the tension-elongation timing significant interactive coupling feature vector.

2. A cable tensile testing device according to claim 1, characterized in that: The information interaction fusion module includes: a principal component analysis unit, which performs principal component analysis on the implicit feature vector associated with the real-time tension value time series and the implicit feature vector associated with the real-time elongation time series to obtain a set of principal component feature components of the real-time tension value time series and a set of principal component feature components of the real-time elongation time series; an optimal pairing interactive coupling unit, which performs optimal pairing multi-scale interactive coupling on the set of principal component feature components of the real-time tension value time series and the set of principal component feature components of the real-time elongation time series to obtain a tension-elongation time series significant interactive coupling feature vector.

3. A cable tensile testing device according to claim 2, characterized in that: A principal component analysis unit calculates the covariance matrix of the real-time tension value time series associated implicit feature vector to obtain the real-time tension value time series feature covariance matrix; Performing eigenvalue decomposition on the real-time tension value time series feature covariance matrix to obtain a set of real-time tension value time series principal component eigenvalues ​​and a set of corresponding real-time tension value time series principal component feature components; Calculate the covariance matrix of the real-time elongation time series associated implicit feature vector to obtain the real-time elongation time series feature covariance matrix; The real-time elongation time series feature covariance matrix is ​​subjected to eigenvalue decomposition to obtain a set of real-time elongation time series principal component eigenvalues ​​and a set of corresponding real-time elongation time series principal component feature components.

4. A cable tensile testing device according to claim 3, characterized in that: The best pairing interactive coupling unit includes: a best matching screening subunit, which uses each real-time tension value time series principal component characteristic component in the set of real-time tension value time series principal component characteristic components as a query vector, and uses the set of real-time elongation time series principal component characteristic components as a query library, and matches the real-time elongation time series principal component characteristic components that best match each query vector from the query library to obtain a set of best matching pairs of real-time tension value time series principal component characteristic components and real-time elongation time series principal component characteristic components; a multi-scale interactive fusion subunit, which performs multi-scale interactive fusion on the set of best matching pairs of real-time tension value time series principal component characteristic components and real-time elongation time series principal component characteristic components to obtain a tension-elongation time series significant interactive coupling characteristic vector.

5. A cable tensile testing device according to claim 4, characterized in that: The best matching screening subunit calculates the Mahalanobis distance between the query vector and each real-time elongation time series principal component characteristic component in the query library to obtain a set of tension-elongation matching difference coefficients; selects the real-time elongation time series principal component characteristic component corresponding to the minimum value in the set of tension-elongation matching difference coefficients as the best matching result of the query vector to obtain the best matching pair of the real-time tension value time series principal component characteristic component and the real-time elongation time series principal component characteristic component.

6. A cable tensile testing device according to claim 5, characterized in that: The multi-scale interactive fusion sub-unit includes: a best matching pair interactive coupling secondary sub-unit, which inputs each best matching pair of real-time tension value time series principal component feature component and real-time elongation time series principal component feature component in the set of best matching pairs of real-time tension value time series principal component feature component and real-time elongation time series principal component feature component into the multi-scale interactive response coupling module to obtain a set of multi-scale interactive coupling representation vectors of tension-elongation time series feature best matching pairs; a feature cascade secondary sub-unit, which cascades the set of multi-scale interactive coupling representation vectors of tension-elongation time series feature best matching pairs to obtain a tension-elongation time series significant interactive coupling feature vector.

7. A cable tensile testing method, using a cable tensile testing device according to any one of claims 1 to 6, characterized in that: The following steps are involved: Step S100: applying a pulling force to the cable to stretch the cable; Step S200: obtaining the real-time tension value and real-time elongation of the cable when it is stretched; Step S300: generating a cable tensile fracture analysis result according to the real-time tensile force value and the real-time elongation value when the cable is stretched; Step S400: Determine whether to generate a fracture warning prompt based on the cable tensile fracture analysis result.

8. A cable tensile testing method according to claim 7, characterized in that: The step S300 includes the following steps: Step S301, obtaining a time queue of the real-time tension value and a time queue of the real-time elongation of the cable according to the real-time tension value and the real-time elongation of the cable when the cable is stretched; Step S302, performing time series coding on the time series of the real-time tension value and the time series of the real-time elongation respectively to obtain a time series associated implicit feature vector of the real-time tension value and a time series associated implicit feature vector of the real-time elongation; Step S303, performing principal component matching interaction on the real-time tension value time series associated implicit feature vector and the real-time elongation time series associated implicit feature vector to obtain a tension-elongation time series significant interaction coupling feature vector; Step S304, obtaining the cable tensile fracture analysis result based on the tension-elongation time series significant interactive coupling eigenvector.

9. A cable tensile testing method according to claim 8, characterized in that: The step S303 includes: Step S3031: performing principal component analysis on the real-time tension value time series associated implicit feature vector and the real-time elongation time series associated implicit feature vector respectively to obtain a set of real-time tension value time series principal component feature components and a set of real-time elongation time series principal component feature components; Step S3032: optimally pair the set of principal component characteristic components of the real-time tension value time series and the set of principal component characteristic components of the real-time elongation time series by multi-scale interactive coupling to obtain a tension-elongation time series significant interactive coupling characteristic vector.

10. A cable tensile testing method according to claim 9, characterized in that: The step S3031 includes: Step S30311: Calculate the covariance matrix of the real-time tension value time series associated implicit eigenvectors to obtain the real-time tension value time series feature covariance matrix; perform eigenvalue decomposition on the real-time tension value time series feature covariance matrix to obtain a set of real-time tension value time series principal component eigenvalues ​​and a set of corresponding real-time tension value time series principal component feature components; Step S30312: Calculate the covariance matrix of the implicit eigenvector associated with the real-time elongation time series to obtain the real-time elongation time series feature covariance matrix; perform eigenvalue decomposition on the real-time elongation time series feature covariance matrix to obtain a set of real-time elongation time series principal component eigenvalues ​​and a corresponding set of real-time elongation time series principal component feature components.

Images