Cable tensile testing device and method thereof

Abstract

The present invention discloses a cable stretching test device and method thereof, belonging to the technical field of cable stretching test. The cable stretching test device comprises: a stretching mechanism, applying tension to the cable to stretch the cable; a detection mechanism, obtaining the real-time tension value and real-time elongation of the cable when stretched; a processing mechanism, processing and generating a cable stretching fracture analysis result according to the real-time tension value and real-time elongation of the cable when stretched; and a control mechanism, determining whether to generate a fracture warning prompt according to the cable stretching fracture analysis result. The present invention 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.

Description

Technical Field

[0001] The present invention application 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, as a key transmission medium, the quality and performance of cables directly affect the stability and security of the system. In order to ensure that cable products can meet specific technical requirements in actual 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 the publication number CN116735362A discloses a cable tensile testing device, which can drive two connecting racks to move in opposite directions simultaneously by the rotation of a central gear. Under the guiding action of a guiding block, the two bearing frames move away from each other, and the power is transmitted to the bearing frames through a series of mechanical linkage structures, causing the cable to be subjected to a tensile force. During this process, the displacement is recorded using scale lines, and at the same time, the actual tensile force borne by the cable can be monitored and recorded through an additional pressure sensor or other forms of force measuring elements.

[0004] However, although the existing cable tensile testing devices can provide basic tensile testing functions, there are still certain limitations in actual applications. The cable tensile testing device lacks a real-time monitoring and early warning mechanism for potential fracture risks during the cable tensile process. During the tensile testing process, the cable may suddenly break due to material defects, manufacturing flaws, or excessive stretching, etc., which will not only cause damage to the testing equipment, but also pose a safety hazard to the testing personnel, and at the same time increase unnecessary testing losses. Summary of the Invention

[0005] Based on this, the present invention application provides a cable tensile testing device and method thereof, aiming to partially or completely solve the above technical problems, timely detect the abnormal tensile state of the cable, prevent accidental fracture of the cable during the testing process, and avoid equipment damage and personnel safety risks caused by sudden cable fracture. The present invention application is realized through the following technical solutions:

[0006] In a first aspect, a cable tensile test device includes: a stretching mechanism that applies a tensile force to the cable to stretch the cable; a detection mechanism that acquires real-time tensile force values and real-time elongation amounts when the cable is stretched; a processing mechanism that processes and generates a cable tensile fracture analysis result based on the real-time tensile force values and real-time elongation amounts when the cable is stretched; and a control mechanism that determines whether to generate a fracture warning prompt based on the cable tensile fracture analysis result. The processing mechanism includes: a cable tensile state monitoring module that acquires a time queue of the real-time tensile force values and a time queue of the real-time elongation amounts of the cable based on the real-time tensile force values and real-time elongation amounts when the cable is stretched; a cable tensile parameter time series encoding module that performs time series encoding on the time queue of the real-time tensile force values and the time queue of the real-time elongation amounts respectively to obtain a real-time tensile force value time series correlation implicit feature vector and a real-time elongation amount time series correlation implicit feature vector; an information interaction and fusion module that performs principal component matching interaction on the real-time tensile force value time series correlation implicit feature vector and the real-time elongation amount time series correlation implicit feature vector to obtain a tensile force-elongation amount time series significant interaction coupling feature vector; and a fracture analysis module that obtains a cable tensile fracture analysis result based on the tensile force-elongation amount time series significant interaction coupling feature vector.

[0007] Optionally, the information interaction and fusion module includes: a principal component analysis unit that performs principal component analysis on the real-time tensile force value time series correlation implicit feature vector and the real-time elongation amount time series correlation implicit feature vector respectively to obtain a set of real-time tensile force value time series principal component feature components and a set of real-time elongation amount time series principal component feature components; and an optimal pairing interaction coupling unit that performs optimal pairing multi-scale interaction coupling on the set of real-time tensile force value time series principal component feature components and the set of real-time elongation amount time series principal component feature components to obtain a tensile force-elongation amount time series significant interaction coupling feature vector.

[0008] Optionally, the principal component analysis unit calculates the covariance matrix of the real-time tensile force value time series correlation implicit feature vector to obtain a real-time tensile force value time series feature covariance matrix; performs eigenvalue decomposition on the real-time tensile force value time series feature covariance matrix to obtain a set of real-time tensile force value time series principal component eigenvalues and a corresponding set of real-time tensile force value time series principal component feature components; calculates the covariance matrix of the real-time elongation amount time series correlation implicit feature vector to obtain a real-time elongation amount time series feature covariance matrix; and performs eigenvalue decomposition on the real-time elongation amount time series feature covariance matrix to obtain a set of real-time elongation amount time series principal component eigenvalues and a corresponding set of real-time elongation amount time series principal component feature components.

[0009] Optionally, the optimal pairing interaction coupling unit includes: an optimal matching screening subunit, which uses each real-time tensile force value time-series principal component feature component in the set of real-time tensile force value time-series principal component feature components as a query vector, and uses the set of real-time elongation amount time-series principal component feature components as a query library, and matches the real-time elongation amount time-series principal component feature component that optimally matches each query vector from the query library to obtain a set of optimal matching pairs of real-time tensile force value time-series principal component feature components and real-time elongation amount time-series principal component feature components; a multi-scale interaction fusion subunit, which performs multi-scale interaction fusion on the set of optimal matching pairs of real-time tensile force value time-series principal component feature components and real-time elongation amount time-series principal component feature components to obtain a tensile-elongation amount time-series significant interaction coupling feature vector.

[0010] Optionally, the optimal matching screening subunit calculates the Mahalanobis distance between the query vector and each real-time elongation amount time-series principal component feature component in the query library to obtain a set of tensile-elongation amount matching difference coefficients; and selects the real-time elongation amount time-series principal component feature component corresponding to the minimum value in the set of tensile-elongation amount matching difference coefficients as the optimal matching result of the query vector to obtain a set of optimal matching pairs of real-time tensile force value time-series principal component feature components and real-time elongation amount time-series principal component feature components.

[0011] Optionally, the multi-scale interaction fusion subunit includes: an optimal matching pair interaction coupling secondary subunit, which inputs each optimal matching pair of real-time tensile force value time-series principal component feature components and real-time elongation amount time-series principal component feature components in the set of optimal matching pairs of real-time tensile force value time-series principal component feature components and real-time elongation amount time-series principal component feature components into a multi-scale interaction response coupling module respectively to obtain a set of multi-scale interaction coupling representation vectors of tensile-elongation amount time-series feature optimal matching pairs; a feature concatenation secondary subunit, which concatenates the set of multi-scale interaction coupling representation vectors of tensile-elongation amount time-series feature optimal matching pairs to obtain a tensile-elongation amount time-series significant interaction coupling feature vector.

[0012] In a second aspect, a cable stretching test method uses any one of the cable stretching test devices described in the first aspect above, and includes the following steps:

[0013] Step S100: Apply a tensile force to the cable to stretch the cable;

[0014] Step S200: Obtain the real-time tensile force value and the real-time elongation amount when the cable is stretched;

[0015] Step S300: Process and generate a cable stretching fracture analysis result according to the real-time tensile force value and the real-time elongation amount when the cable is stretched;

[0016] Step S400: Determine whether to generate a fracture warning prompt according to the cable stretching fracture analysis result.

[0017] Optionally, step S300 includes the following steps:

[0018] Step S301: Obtain the time queue of the real-time tensile force value and the time queue of the real-time elongation of the cable according to the real-time tensile force value and the real-time elongation amount when the cable is stretched;

[0019] Step S302: Perform temporal encoding on the time queue of the real-time tensile force value and the time queue of the real-time elongation amount respectively to obtain the real-time tensile force value temporal correlation implicit feature vector and the real-time elongation amount temporal correlation implicit feature vector;

[0020] Step S303: Perform principal component matching interaction on the real-time tensile force value temporal correlation implicit feature vector and the real-time elongation amount temporal correlation implicit feature vector to obtain the tensile-elongation amount temporal significant interaction coupling feature vector;

[0021] Step S304: Obtain the cable stretching fracture analysis result based on the tensile-elongation amount temporal significant interaction coupling feature vector.

[0022] Optionally, step S303 includes:

[0023] Step S3031: Perform principal component analysis on the real-time tensile force value temporal correlation implicit feature vector and the real-time elongation amount temporal correlation implicit feature vector respectively to obtain the set of real-time tensile force value temporal principal component feature components and the set of real-time elongation amount temporal principal component feature components;

[0024] Step S3032: Perform optimal pairing multi-scale interaction coupling on the set of real-time tensile force value temporal principal component feature components and the set of real-time elongation amount temporal principal component feature components to obtain the tensile-elongation amount temporal significant interaction coupling feature vector.

[0025] Optionally, step S3031 includes:

[0026] Step S30311: Calculate the covariance matrix of the real-time tensile force value temporal correlation implicit feature vector to obtain the real-time tensile force value temporal feature covariance matrix; perform eigenvalue decomposition on the real-time tensile force value temporal feature covariance matrix to obtain the set of real-time tensile force value temporal principal component eigenvalues and the corresponding set of real-time tensile force value temporal principal component feature components;

[0027] Step S30312: Calculate the covariance matrix of the real-time elongation amount temporal correlation implicit feature vector to obtain the real-time elongation amount temporal feature covariance matrix; perform eigenvalue decomposition on the real-time elongation amount temporal feature covariance matrix to obtain the set of real-time elongation amount temporal principal component eigenvalues and the corresponding set of real-time elongation amount temporal principal component feature components.

[0028] Compared with the prior art, the beneficial effects of the present invention application are as follows:

[0029] In the present invention application, the tensile force value and elongation of the cable are monitored in real time and data analyzed. The time-series dynamic change characteristics of the tensile force value and elongation are respectively extracted, and through fine-grained matching and interaction between the two, the interaction response pattern between the tensile force and elongation of the cable is captured. Furthermore, the potential fracture risk of the cable during the stretching process is intelligently identified, and a corresponding fracture warning prompt is generated, which can timely detect the abnormal stretching state of the cable, effectively prevent accidental fracture of the cable during the test, and thus avoid equipment damage and personnel safety risks caused by sudden fracture of the cable.

[0030] In the present invention application, while performing feature clustering on the significant interaction coupling feature vector of the tensile force-elongation time series, for the interactive description of the key feature information of the significant interaction coupling feature vector of the tensile force-elongation time series during the clustering process, a geometric equivariant topology of the feature is constructed through feature low-rank harmonic modulation based on the equivariance of the clustering feature and the overall feature of the significant interaction coupling feature vector of the tensile force-elongation time series, so as to obtain the translational and rotational symmetry of the schematic distribution of the clustering feature of the significant interaction coupling feature vector of the tensile force-elongation time series relative to the overall feature. Thus, on the basis of introducing geometric message passing in the feature expression of the significant interaction coupling feature vector of the tensile force-elongation time series, the clustering mapping symmetry of the significant interaction coupling feature vector of the tensile force-elongation time series is realized through the manipulation of irreducible low-rank order coefficients, improving the consistency of the clustering-based feature representation of the significant interaction coupling feature vector of the tensile force-elongation time series, and thereby improving the accuracy of the fracture analysis result obtained by inputting the significant interaction coupling feature vector of the tensile force-elongation time series into the fracture warning engine based on a classifier. Brief Description of the Drawings

[0031] By describing the embodiments of the present invention application in more detail in conjunction with the drawings, the above and other objects, features, and advantages of the present invention application will become more obvious. The drawings are used to provide a further understanding of the embodiments of the present invention application, and constitute a part of the specification. Together with the embodiments of the present invention application, they are used to explain the present invention application and do not constitute a limitation to the present invention application. In the drawings, the same reference numerals generally represent the same components or steps.

[0032] Figure 1 It is a schematic structural diagram of a cable stretching test device for the present invention application.

[0033] Figure 2 It is a schematic diagram of the working principle of the processing mechanism for the present invention application.

[0034] Figure 3 It is a schematic diagram of the composition of the information interaction and fusion module for the present invention application.

[0035] Figure 4 This is a schematic flowchart of a cable tensile test method for this invention application.

[0036] 100 - Cable tensile test device, 110 - Tensile mechanism, 120 - Detection mechanism, 130 - Processing mechanism, 140 - Control mechanism, 1300 - Information interaction and fusion module, 1301 - Principal component analysis unit, 1302 - Optimal pairing interactive coupling unit. Detailed implementation manners

[0037] In order to make the objectives, technical solutions and advantages of the embodiments of this disclosure clearer, the following further describes the embodiments of this disclosure in detail with reference to the accompanying drawings and embodiments; it should be understood that the specific embodiments described herein are only used to explain the embodiments of this disclosure, and are not used to limit the embodiments of this disclosure;

[0038] The structures, proportions, sizes, etc. shown in the drawings of this specification are only used to cooperate with the content disclosed in the specification for those skilled in this technology to understand and read, and are not used to limit the limiting conditions under which this invention application can be implemented. Therefore, they do not have technical essential significance. Any modification of the structure, change of the proportional relationship or adjustment of the size, without affecting the effects that this invention application can produce and the objectives that can be achieved, should still fall within the scope that the technical content disclosed in this invention application can cover; at the same time, terms such as "and" and "or" cited in this specification are only for the convenience of clear narration, and are not used to limit the scope that can be implemented. The change or adjustment of their relative relationships, without substantial change of the technical content, should also be regarded as the scope that this invention application can be implemented; in addition, the various embodiments of this invention application are not independent of each other, but can be combined;

[0039] As shown in this invention application and the claims, unless the context clearly indicates an exceptional situation, words such as "a", "an", "one" and / or "the" are not specifically singular, but may also include plural. Generally speaking, the terms "comprising" and "including" 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. The method or device may also include other steps or elements.

[0040] Next, exemplary embodiments according to this invention application will be described in detail with reference to the drawings. Obviously, the described embodiments are only a part of the embodiments of this invention application, rather than all the embodiments of this invention application. It should be understood that this invention application is not limited by the exemplary embodiments described here.

[0041] In the field of existing cable technology, cable tensile testing equipment is usually used to evaluate the physical properties of cables under tensile conditions. The physical properties 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 broken, and it is an important indicator for evaluating the mechanical strength of the cable; elongation at break is the percentage of the elongation of the gauge length to the original gauge length when the cable is stretched and broken, which reflects the plastic deformation ability of the cable; yield strength refers to the stress value when obvious plastic deformation occurs during the stretching process of the cable, and it is an important indicator for evaluating the anti-deformation ability of the cable; elastic modulus refers to the ratio of stress to strain in the elastic deformation stage of the cable, which reflects the ability of the cable to resist elastic deformation. Generally speaking, these evaluation parameters are important bases for evaluating the mechanical properties of cables.

[0042] Cable tensile testing equipment usually includes: a tensile mechanism for clamping the cable and applying a tensile force to stretch the cable at a certain speed. The tensile mechanism usually includes a motor, a reducer, a transmission structure, a fixture, etc.; a detection mechanism for measuring cable tensile data (such as parameters like tensile force, displacement, etc.) during the stretching process of the cable and outputting them to the processing mechanism. The detection mechanism usually includes a tensile force sensor, a displacement sensor, etc.; a processing mechanism for performing real-time processing and accurate analysis on the cable tensile data (such as parameters like tensile force, displacement, etc.) during the cable testing process and outputting them to the control mechanism; a control mechanism for controlling and real-time monitoring the cable tensile testing process and displaying the cable tensile data during the cable tensile testing process. The control mechanism usually consists of a computer, a controller, a data acquisition card, etc. The tensile mechanism, the detection mechanism, the processing mechanism, and the control mechanism cooperate with each other during the testing process, operate strictly in accordance with relevant standards and specifications, and jointly ensure the accuracy, stability, and reliability during the cable tensile testing process to complete a comprehensive evaluation of the physical properties of the cable under tensile conditions. All these are common technical knowledge in the field of existing cable technology.

[0043] However, considering that during the cable tensile testing process, the cable may suddenly break due to material defects, manufacturing flaws, or excessive stretching, etc., which will not only cause damage to the cable testing equipment, but also pose a safety hazard to the testers, and at the same time increase unnecessary testing costs. Therefore, in order to avoid unnecessary testing costs and improve the safety of cable testing, this invention application proposes a cable tensile testing device and its method.

[0044] As Figures 1 to 3As shown, in a first aspect, the present invention application provides a cable tensile test device 100, including: a tensile mechanism 110 that applies a tensile force to the cable to stretch the cable; a detection mechanism 120 that obtains the real-time tensile force value and the real-time elongation amount when the cable is stretched; a processing mechanism 130 that processes and generates a cable tensile fracture analysis result according to the real-time tensile force value and the real-time elongation amount when the cable is stretched; and a control mechanism 140 that determines whether to generate a fracture warning prompt according to the cable tensile fracture analysis result.

[0045] Based on the common technical knowledge in the above-mentioned existing cable technology field, it should be understandable that during the tensile test of the cable, 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 application, by real-time monitoring the magnitude of the tensile force received by the cable and the real-time elongation amount generated by the tensile force received by the cable, it can be used to evaluate the physical properties of the cable, and at the same time, it can also timely detect abnormal data changes during the cable tensile test, so as to early warn of potential fracture risks.

[0046] Optionally, the processing mechanism includes: a cable tensile state monitoring module that obtains the time queue of the real-time tensile force value and the time queue of the real-time elongation amount of the cable according to the real-time tensile force value and the real-time elongation amount when the cable is stretched; a cable tensile parameter time series encoding module that performs time series encoding on the time queue of the real-time tensile force value and the time queue of the real-time elongation amount respectively to obtain a real-time tensile force value time series correlation implicit feature vector and a real-time elongation amount time series correlation implicit feature vector; an information interaction and fusion module 1300 that performs principal component matching interaction on the real-time tensile force value time series correlation implicit feature vector and the real-time elongation amount time series correlation implicit feature vector to obtain a tensile force-elongation amount time series significant interaction coupling feature vector; and a fracture analysis module that obtains a cable tensile fracture analysis result based on the tensile force-elongation amount time series significant interaction coupling feature vector.

[0047] In some embodiments, the cable tensile state monitoring module can complete obtaining the time queue of the real-time tensile force value and the time queue of the real-time elongation amount of the cable.

[0048] Exemplarily, the detection mechanism may include a force sensor and a displacement sensor. The force sensor and the displacement sensor can respectively monitor and acquire the real-time tensile force value and the real-time elongation amount when the cable is stretched. The real-time tensile force value and the real-time elongation amount can change over time. The cable stretching state monitoring module can obtain the real-time tensile force value and the real-time elongation amount of the cable collected by the force sensor and the displacement sensor. Moreover, as time gradually elapses during the cable stretching test, multiple real-time tensile force values at different times can at least form a time queue of real-time tensile force values, and multiple real-time elongation amounts at different times can at least form a time queue of real-time elongation amounts. Furthermore, the cable stretching state monitoring module can complete obtaining the time queue of the real-time tensile force value and the time queue of the real-time elongation amount of the cable.

[0049] In some embodiments, the cable stretching parameter time series encoding module inputs the time queue of the real-time tensile force value and the time queue of the real-time elongation amount into a sequence encoder based on a forward long short-term memory (LSTM) model respectively to obtain a real-time tensile force value time series associated hidden feature vector and a real-time elongation amount time series associated hidden feature vector.

[0050] Exemplarily, considering that the force and deformation of the cable during stretching are a continuous and dynamically changing process, therefore, in order to fully and accurately capture the dynamic change characteristics of the tensile force value and the elongation amount of the cable, the present invention application uses a forward long short-term memory (LSTM) network to process the time queue of the real-time tensile force value and the time queue of the real-time elongation amount respectively. The forward long short-term memory (LSTM) network 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 (LSTM) network to effectively capture the long-term dependencies in the time series data, learn the complex patterns of the tensile force value and the elongation amount changing over time, and obtain a real-time tensile force value time series associated hidden feature vector and a real-time elongation amount time series associated hidden feature vector, thereby providing useful data support for subsequent fracture warning identification.

[0051] In some embodiments, the information interaction and fusion module performs principal component matching interaction on the real-time tensile force value time series associated hidden feature vector and the real-time elongation amount time series associated hidden feature vector to obtain a tensile force-elongation amount time series significantly interacting coupling feature vector.

[0052] Exemplarily, during the tensile test of a cable, there is a certain interaction between the force and deformation, that is, an 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 exhibit 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 potential breaking risk of the cable can be identified by analyzing the interaction response pattern between the real-time tensile force value and the real-time elongation of the cable.

[0053] Accordingly, in order to effectively extract and strengthen the key interaction features between the tensile force value and the 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 combination between the tensile force value and the elongation, so as to better understand and model the subtle and non-linear interaction response pattern between the two, and improve the discrimination between the two.

[0054] As Figure 3 shown, the information interaction fusion module 1300 includes: a principal component analysis unit 1301, which performs principal component analysis on the real-time tensile force 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 tensile force value time-series principal component feature components and a set of real-time elongation time-series principal component feature components; a best-pairing interaction coupling unit 1302, which performs best-pairing multi-scale interaction coupling on the set of real-time tensile force value time-series principal component feature components and the set of real-time elongation time-series principal component feature components to obtain a tensile-elongation time-series significant interaction coupling feature vector.

[0055] Optionally, the principal component analysis unit 1301 calculates the covariance matrix of the real-time tensile force value time-series associated implicit feature vector to obtain the real-time tensile force value time-series feature covariance matrix; performs eigenvalue decomposition on the real-time tensile force value time-series feature covariance matrix to obtain a set of real-time tensile force value time-series principal component eigenvalues and a corresponding set of real-time tensile force value time-series principal component feature components; calculates 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; 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 corresponding set of real-time elongation time-series principal component feature components.

[0056] In some embodiments, Principal Components Analysis (PCA) is a widely used linear dimensionality reduction technique for reducing the dimensionality of a dataset while preserving as much important information of the original data as possible. It transforms potentially correlated variables into a set of linearly uncorrelated variables through orthogonal transformation. Correspondingly, the PCA technique can be used to process the real-time tensile value time-series associated implicit feature vectors and the real-time elongation time-series associated implicit feature vectors, thereby reducing the complexity of the tensile value and elongation data and extracting the main features in the tensile value and elongation data, focusing on the key dynamic changes in the cable tensile test to obtain a set of real-time tensile value time-series principal component feature components and a set of real-time elongation time-series principal component feature components.

[0057] Optionally, the optimal pairing interaction coupling unit 1302 includes: an optimal matching screening subunit, which uses each real-time tensile value time-series principal component feature component in the set of real-time tensile 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 component that best matches each query vector from the query library to obtain a set of best matching pairs of real-time tensile value time-series principal component feature components and real-time elongation time-series principal component feature components; a multi-scale interaction fusion subunit, which performs multi-scale interaction fusion on the set of best matching pairs of real-time tensile value time-series principal component feature components and real-time elongation time-series principal component feature components to obtain a tensile-elongation time-series significant interaction coupling feature vector.

[0058] Optionally, the optimal 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 tensile-elongation matching difference coefficients; selects the real-time elongation time-series principal component feature component corresponding to the minimum value in the set of tensile-elongation matching difference coefficients as the optimal matching result of the query vector to obtain a best matching pair of real-time tensile value time-series principal component feature components and real-time elongation time-series principal component feature components.

[0059] In some embodiments, an optimal matching algorithm can be used to perform feature query matching on the two sets of principal component feature components, use the Mahalanobis distance as a measurement method to query the most relevant feature pairs, and establish a one-to-one correspondence between the real-time tensile value time-series principal component feature components and the real-time elongation time-series principal component feature components, so as to achieve an accurate matching of the strong correlation interaction response mode between the tensile force and the elongation.

[0060] Optionally, the multi-scale interaction fusion subunit includes: an optimal matching pair interaction coupling secondary subunit that inputs each real-time tensile force value time-series principal component feature component and real-time elongation amount time-series principal component feature component optimal matching pair in the set of real-time tensile force value time-series principal component feature component and real-time elongation amount time-series principal component feature component optimal matching pairs into a multi-scale interaction response coupling module to obtain a set of tensile force-elongation amount time-series feature optimal matching pair multi-scale interaction coupling representation vectors; a feature concatenation secondary subunit that concatenates the set of tensile force-elongation amount time-series feature optimal matching pair multi-scale interaction coupling representation vectors to obtain the tensile force-elongation amount time-series significant interaction coupling feature vector.

[0061] In some embodiments, each optimal matching pair can be input into the multi-scale interaction response coupling module for interaction response analysis of the optimal paired features. The multi-scale interaction response coupling module performs multi-level feature interaction and deep learning on the real-time tensile force value time-series principal component feature component and the real-time elongation amount time-series principal component feature component in the optimal matching pair, can effectively capture the interaction patterns of the tensile force value and the elongation amount at different abstraction levels, automatically learn and generate the interaction feature representation of each optimal matching pair. Finally, by performing a concatenation operation on the interaction feature representations of the optimal matching pairs to synthesize global information, a tensile force-elongation amount time-series significant interaction coupling feature vector during the cable stretching test is obtained, so as to comprehensively reflect the interaction response pattern between the tensile force and the elongation amount during the cable stretching process, thereby providing a more comprehensive and in-depth analysis basis for the fracture warning analysis and evaluation of the cable.

[0062] Optionally, the optimal matching pair interaction coupling secondary subunit includes:

[0063] Calculate respectively the element-wise addition, element-wise subtraction, and element-wise multiplication between the real-time tensile force value time-series principal component feature component and the real-time elongation amount time-series principal component feature component in the real-time tensile force value time-series principal component feature component and real-time elongation amount time-series principal component feature component optimal matching pair to obtain a first tensile force-elongation amount time-series principal component component optimal matching interaction representation vector, a second tensile force-elongation amount time-series principal component component optimal matching interaction representation vector, and a third tensile force-elongation amount time-series principal component component optimal matching interaction representation vector;

[0064] After concatenating and fusing the first tensile force-elongation amount time-series principal component component optimal matching interaction representation vector, the second tensile force-elongation amount time-series principal component component optimal matching interaction representation vector, and the third tensile force-elongation amount time-series principal component component optimal matching interaction representation vector, input them into a one-dimensional convolutional layer including a max pooling layer to obtain a tensile force-elongation amount time-series principal component component optimal matching multi-scale interaction representation vector;

[0065] Select the maximum value among the two-norm of the principal component feature component of the real-time tensile force value time series, the two-norm of the principal component feature component of the real-time elongation amount time series, and the preset scale adjustment parameter as the scale scaling factor, and divide each eigenvalue in the best-matched multi-scale interaction representation vector of the tensile force-elongation amount time series principal component component by the scale scaling factor to obtain the best-matched multi-scale interaction coupling representation vector of the tensile force-elongation amount time series feature.

[0066] Optionally, the information interaction fusion module processes the real-time tensile force value time series correlation implicit feature vector and the real-time elongation amount time series correlation implicit feature vector using the principal component matching interaction fusion formula to obtain the tensile force-elongation amount time series significant interaction coupling feature vector. The principal component matching interaction fusion formula includes:

[0067]

[0068] where C 1 and C 2 represent the covariance matrices of the real-time tensile force value time series correlation implicit feature vector and the real-time elongation amount time series correlation implicit feature vector respectively, Λ 1 is a diagonal matrix composed of the set of principal component eigenvalues of the real-time tensile force value time series obtained by eigenvalue decomposition of the real-time tensile force value time series feature covariance matrix, λ 11 and λ 1m represent the first and the m-th principal component eigenvalues of the real-time tensile force value time series in the set of the principal component eigenvalues of the real-time tensile force value time series respectively, where m is the number of principal component eigenvalues of the real-time tensile force value time series, U 1 is a matrix composed of the set of principal component feature components of the real-time tensile force value time series, v 11 , v 12 , v 1i and v 1m represent the first, the second, the i-th, and the m-th principal component feature components of the real-time tensile force value time series in the set of the principal component feature components of the real-time tensile force value time series respectively, (·) T represents the transpose of the matrix, Λ 2 is a diagonal matrix composed of the set of principal component eigenvalues of the real-time elongation amount time series obtained by eigenvalue decomposition of the real-time elongation amount time series feature covariance matrix, λ 21 and λ 2m represent the first and the m-th principal component eigenvalues of the real-time elongation amount time series in the set of the principal component eigenvalues of the real-time elongation amount time series respectively, U 2 is a matrix composed of the set of principal component feature components of the real-time elongation amount time series, v 21 , v 22 , v 2i , v 2k and v 2mrespectively represent the 1st, 2nd, jth, kth, and mth real-time elongation time-series principal component feature components in the set of real-time elongation time-series principal component feature components, S -1 represents the inverse matrix of the covariance matrix between the ith real-time tensile force value time-series principal component feature component and the jth 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 ith real-time tensile force value time-series principal component feature component, ⊙ represents dot product, and ⊕ represents dot addition represents point subtraction, conv1D represents a one-dimensional convolution operation, MaxPool represents a maximum pooling operation, ||·|| 2 represents the two-norm of the feature vector, ε is a preset scale adjustment parameter, max(·) is the maximum value function, v p1 、v p2 、v pi and v pm respectively represent the 1st, 2nd, ith, and mth tensile-elongation time-series feature best matching pair multi-scale interaction coupling representation vectors, [·;·;·] represents a concatenation operation, and V represents the tensile-elongation time-series significant interaction coupling feature vector

[0069] However, in the case where the real-time tensile force value time-series associated implicit feature vector and the real-time elongation time-series associated implicit feature vector respectively represent the forward short-range-long-range time-series association features of the real-time tensile force value and the real-time elongation, when performing interactive response coupling based on the best match of the feature principal component granularity, the tensile-elongation time-series significant interaction coupling feature vector will also have an interactive response difference value based on the best match due to the difference in the time-series pattern of the feature principal component granularity, affecting the classification mapping iteration consistency and reducing the accuracy of the classification result. Therefore, it is expected to improve the semantic consistent aggregation expression effect of the tensile-elongation time-series significant interaction coupling feature vector

[0070] Optionally, inputting the tensile-elongation time-series significant interaction coupling feature vector into a classifier-based fracture warning engine to obtain a fracture analysis result includes:

[0071] Performing feature clustering on the feature set of the tensile-elongation time-series significant interaction coupling feature vector to obtain a tensile-elongation time-series significant interaction coupling intra-class feature set and a tensile-elongation time-series significant interaction coupling out-of-class feature set, that is:

[0072] where C represents the tensile-elongation time-series significant interaction coupling intra-class feature set, f 1i represents the ith eigenvalue of the tensile-elongation time-series significant interaction coupling intra-class feature set, f 2jrepresents the j-th eigenvalue of the set of external features of the significant interaction coupling of the tensile force-elongation amount time series, where both i and j are positive integers;

[0073] Calculate the ratio of the number of eigenvalues in the set of internal features of the significant interaction coupling of the tensile force-elongation amount time series to the number of eigenvalues in the set of features of the significant interaction coupling eigenvector of the tensile force-elongation amount time series, that is:

[0074] where k represents the number of eigenvalues in the set of internal features of the significant interaction coupling of the tensile force-elongation amount time series, n represents the number of eigenvalues in the set of features of the significant interaction coupling eigenvector of the tensile force-elongation amount time series, and λ represents the ratio;

[0075] Calculate the ratio of the λ-th power of the sum of the absolute values of all eigenvalues in the set of internal features of the significant interaction coupling of the tensile force-elongation amount time series to the λ-th power of the sum of the absolute values of all eigenvalues in the set of features of the significant interaction coupling eigenvector of the tensile force-elongation amount time series to obtain the modulation weight of the significant interaction coupling of the tensile force-elongation amount time series, that is:

[0076] where f p represents each eigenvalue in the set of features of the significant interaction coupling eigenvector of the tensile force-elongation amount time series, and w 1 represents the modulation weight of the significant interaction coupling of the tensile force-elongation amount time series;

[0077] Calculate the ratio of the (λ / 2)-th power of the sum of the squares of all eigenvalues in the set of internal features of the significant interaction coupling of the tensile force-elongation amount time series to the (λ / 2)-th power of the sum of the squares of all eigenvalues in the set of features of the significant interaction coupling eigenvector of the tensile force-elongation amount time series to obtain the harmonic weight of the significant interaction coupling of the tensile force-elongation amount time series, that is:

[0078] where w 2 represents the harmonic weight of the significant interaction coupling of the tensile force-elongation amount time series;

[0079] For each eigenvalue in the set of internal features of the significant interaction coupling of the tensile force-elongation amount time series, calculate the product of it and the harmonic weight of the significant interaction coupling of the tensile force-elongation amount time series and then add the modulation weight of the significant interaction coupling of the tensile force-elongation amount time series to obtain the optimized eigenvalue, that is:

[0080] where f’ 1i represents the i-th optimized eigenvalue based on the set of internal features of the significant interaction coupling of the tensile force-elongation amount time series;

[0081] For each eigenvalue in the set of outlier features with significant interactive coupling of the tensile force - elongation amount time series, calculate the product of it and the modulation weight of the significant interactive coupling of the tensile force - elongation amount time series to obtain an optimized eigenvalue, that is:

[0082] where f 2j ’ represents the j - th optimized eigenvalue based on the set of outlier features with significant interactive coupling of the tensile force - elongation amount time series;

[0083] Input the optimized tensile force - elongation amount time series significant interactive coupling feature vector based on the set of inlier features and the set of outlier features of the tensile force - elongation amount time series significant interactive coupling into the classifier - based fracture warning engine to obtain the fracture analysis result.

[0084] In some embodiments, the fracture analysis module can input the optimized tensile force - elongation amount time series significant interactive coupling feature vector into the classifier - based fracture warning engine to obtain the fracture analysis result. Exemplarily, a classifier model can be used to judge the optimized tensile force - elongation amount time series significant interactive coupling feature vector. The classifier can deeply learn the interactive change pattern between the tensile force and the elongation amount contained in the tensile force - elongation amount time series significant interactive coupling feature vector, and then accurately distinguish the normal stretching state and the potential abnormal state of the cable, and output the corresponding fracture analysis result, so as to provide real - time fracture warning prompts for the operator to realize real - time monitoring and fracture warning of the cable stretching state.

[0085] Therefore, while clustering the tensile force - elongation amount time series significant interactive coupling feature vector, for the interactive description of the key feature information of the tensile force - elongation amount time series significant interactive coupling feature vector during the clustering process, by means of feature low - rank harmonic modulation on the basis of the equivariance of the clustering features and the whole features of the tensile force - elongation amount time series significant interactive coupling feature vector, construct the geometric equivariant topology of the features to obtain the translational and rotational symmetry of the schematic distribution of the clustering features of the tensile force - elongation amount time series significant interactive coupling feature vector relative to the whole features. Thus, on the basis of introducing geometric message passing in the feature expression of the tensile force - elongation amount time series significant interactive coupling feature vector, realize the clustering mapping symmetry of the tensile force - elongation amount time series significant interactive coupling feature vector through the manipulation of irreducible low - rank order coefficients, improve the consistency of the clustering - based feature representation of the tensile force - elongation amount time series significant interactive coupling feature vector, and thus improve the accuracy of the fracture analysis result obtained by inputting the tensile force - elongation amount time series significant interactive coupling feature vector into the classifier - based fracture warning engine.

[0086] In some embodiments, determining whether to generate a fracture warning prompt includes: a control mechanism that determines the existence of a tensile fracture risk based on the cable tensile fracture analysis result and generates a fracture warning prompt; a control mechanism that determines the non-existence of a tensile fracture risk based on the cable tensile fracture analysis result and does not generate a fracture warning prompt. Exemplarily, the fracture warning prompt can be prompted through a display module (such as a display screen, etc.) and / or an audible and visual alarm module.

[0087] In summary, the cable tensile testing device based on the present invention application is elucidated. It uses data analysis technology based on deep learning to monitor and analyze the tensile force value and elongation of the cable in real time, respectively extracts the temporal dynamic change characteristics of the tensile force value and elongation, and through fine-grained matching and interaction between the two, captures the interaction response mode between the tensile force and elongation of the cable, thereby intelligently identifying the potential fracture risk during the cable stretching process and generating corresponding fracture warning prompts. In this way, the abnormal stretching state of the cable can be detected in time, effectively preventing accidental fracture of the cable during the test, and thus avoiding equipment damage and personnel safety risks caused by sudden cable fracture.

[0088] As Figure 4 shown, in the second aspect, the present invention application provides a cable testing method, which uses any one of the cable testing devices described in the first aspect above, and includes the following steps:

[0089] It should be noted that a cable testing method of the present invention application, which uses any one of the cable testing devices described in the first aspect above, correspondingly also includes: all the technical problems, technical solutions, and technical effects described in any one of the cable testing devices in the first aspect. The present invention application will not repeat them here.

[0090] Step S100: Apply a tensile force to the cable to stretch the cable;

[0091] Step S200: Obtain the real-time tensile force value and real-time elongation of the cable during stretching;

[0092] Step S300: Process and generate a cable tensile fracture analysis result based on the real-time tensile force value and real-time elongation of the cable during stretching;

[0093] Step S400: Determine whether to generate a fracture warning prompt based on the cable tensile fracture analysis result.

[0094] In a cable testing method of the present invention application, 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 amount of the cable during stretching are obtained; then, according to the real-time tensile force value and the real-time elongation amount of the cable during stretching, a cable stretching fracture analysis result is processed and generated; then, according to the cable stretching fracture analysis result, it is determined whether a fracture warning prompt is generated, realizing real-time monitoring and data analysis of the tensile force value and the elongation amount received by the cable, respectively extracting the time-series dynamic change characteristics of the tensile force value and the elongation amount, intelligently identifying the potential fracture risk of the cable during stretching, and generating a corresponding fracture warning prompt, which can timely detect the abnormal stretching state of the cable, effectively prevent the accidental fracture of the cable during the test, and thus avoid equipment damage and personnel safety risks caused by the sudden fracture of the cable.

[0095] Optionally, step S300 includes the following steps:

[0096] Step S301, according to the real-time tensile force value and the real-time elongation amount of the cable during stretching, obtain the time queue of the real-time tensile force value of the cable and the time queue of the real-time elongation amount;

[0097] Step S302, perform time-series encoding on the time queue of the real-time tensile force value and the time queue of the real-time elongation amount respectively to obtain the real-time tensile force value time-series correlation implicit feature vector and the real-time elongation amount time-series correlation implicit feature vector;

[0098] Step S303, perform principal component matching interaction on the real-time tensile force value time-series correlation implicit feature vector and the real-time elongation amount time-series correlation implicit feature vector to obtain the tensile force-elongation amount time-series significant interaction coupling feature vector;

[0099] Step S304, based on the tensile force-elongation amount time-series significant interaction coupling feature vector, obtain the cable stretching fracture analysis result.

[0100] Optionally, step S303 includes:

[0101] Step S3031: Perform principal component analysis on the real-time tensile force value time-series correlation implicit feature vector and the real-time elongation amount time-series correlation implicit feature vector respectively to obtain the set of real-time tensile force value time-series principal component feature components and the set of real-time elongation amount time-series principal component feature components;

[0102] Specifically, step S3031 includes:

[0103] Step S30311: Calculate the covariance matrix of the real-time tensile force value time-series correlation implicit feature vector to obtain the real-time tensile force value time-series feature covariance matrix; perform eigenvalue decomposition on the real-time tensile force value time-series feature covariance matrix to obtain the set of real-time tensile force value time-series principal component eigenvalues and the corresponding set of real-time tensile force value time-series principal component feature components;

[0104] Step S30312: Calculate the covariance matrix of the real-time elongation time-series correlation implicit feature vectors 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 the set of real-time elongation time-series principal component eigenvalues and the corresponding set of real-time elongation time-series principal component eigenvectors;

[0105] Step S3032: Perform optimal pairing multi-scale interactive coupling on the set of real-time tensile force value time-series principal component eigenvectors and the set of real-time elongation time-series principal component eigenvectors to obtain the tensile force-elongation time-series significant interactive coupling feature vectors.

[0106] Specifically, step S3032 includes:

[0107] Step S30321: Use each real-time tensile force value time-series principal component eigenvector in the set of real-time tensile force value time-series principal component eigenvectors as a query vector, and use the set of real-time elongation time-series principal component eigenvectors as a query library to match the real-time elongation time-series principal component eigenvector that best matches each query vector from the query library to obtain the set of best matching pairs of real-time tensile force value time-series principal component eigenvectors and real-time elongation time-series principal component eigenvectors;

[0108] Step S30322: Perform multi-scale interactive fusion on the set of best matching pairs of real-time tensile force value time-series principal component eigenvectors and real-time elongation time-series principal component eigenvectors to obtain the tensile force-elongation time-series significant interactive coupling feature vectors.

[0109] Optionally, in step S300, use the principal component matching interactive fusion formula to process the real-time tensile force value time-series correlation implicit feature vectors and the real-time elongation time-series correlation implicit feature vectors to obtain the tensile force-elongation time-series significant interactive coupling feature vectors, where the principal component matching interactive fusion formula includes:

[0110]

[0111] where C 1 and C 2 respectively represent the covariance matrices of the real-time tensile force value time-series correlation implicit feature vectors and the real-time elongation time-series correlation implicit feature vectors, Λ 1 is the diagonal matrix composed of the set of real-time tensile force value time-series principal component eigenvalues obtained by performing eigenvalue decomposition on the real-time tensile force value time-series feature covariance matrix, λ 11 and λ 1m respectively represent the first and the m-th real-time tensile force value time-series principal component eigenvalues in the set of real-time tensile force value time-series principal component eigenvalues, where m is the number of real-time tensile force value time-series principal component eigenvalues, U 1is a matrix composed of a set of principal component feature components of the real-time tensile force value time series, v 11 and v 12 and v 1i and v 1m respectively represent the 1st, 2nd, ith, and mth principal component feature components of the real-time tensile force value time series in the set of principal component feature components of the real-time tensile force value time series, (·) T represents the transpose of the matrix, Λ 2 is a diagonal matrix composed of a set of principal component eigenvalues of the real-time elongation amount time series obtained by eigenvalue decomposition of the real-time elongation amount time series feature covariance matrix, λ 21 and λ 2m respectively represent the 1st and mth principal component eigenvalues of the real-time elongation amount time series in the set of principal component eigenvalues of the real-time elongation amount time series, U 2 is a matrix composed of a set of principal component feature components of the real-time elongation amount time series, v 21 and v 22 and v 2i and v 2k and v 2m respectively represent the 1st, 2nd, jth, kth, and mth principal component feature components of the real-time elongation amount time series in the set of principal component feature components of the real-time elongation amount time series, S -1 represents the inverse matrix of the covariance matrix between the ith principal component feature component of the real-time tensile force value time series and the jth principal component feature component of the real-time elongation amount time series, argmin represents the index corresponding to the minimum value, k represents the index of the principal component feature component of the real-time elongation amount time series with the smallest semantic difference from the ith principal component feature component of the real-time tensile force value time series, ⊙ represents dot multiplication, ⊕ represents dot addition, represents point subtraction, conv1D represents a one-dimensional convolution operation, MaxPool represents a maximum pooling operation, ||·|| 2 represents the two-norm of the feature vector, ε is a preset scale adjustment parameter, max(·) is a maximum value function, v p1 and v p2 and v pi and v pm respectively represent the 1st, 2nd, ith, and mth best matching pair multi-scale interaction coupling representation vectors of the tensile force-elongation amount time series features, [·;·;·] represents a concatenation operation, V represents the tensile force-elongation amount time series significant interaction coupling feature vector.

[0112] Optionally, in step S304, the tensile force-elongation amount time series significant interaction coupling feature vector is input into a classifier-based fracture warning engine to obtain a fracture analysis result.

[0113] Specifically, step S304 includes:

[0114] Step S3041: Perform feature clustering on the feature set of the significant interaction coupling eigenvectors of the tensile force - elongation amount time series to obtain the in - class feature set of the significant interaction coupling of the tensile force - elongation amount time series and the out - of - class feature set of the significant interaction coupling of the tensile force - elongation amount time series, that is:

[0115] where C represents the in - class feature set of the significant interaction coupling of the tensile force - elongation amount time series, f 1i represents the i - th eigenvalue of the in - class feature set of the significant interaction coupling of the tensile force - elongation amount time series, f 2j represents the j - th eigenvalue of the out - of - class feature set of the significant interaction coupling of the tensile force - elongation amount time series, and both i and j are positive integers;

[0116] Step S3042: Calculate the ratio of the number of eigenvalues in the in - class feature set of the significant interaction coupling of the tensile force - elongation amount time series to the number of eigenvalues in the feature set of the significant interaction coupling eigenvectors of the tensile force - elongation amount time series, that is:

[0117] where k represents the number of eigenvalues in the in - class feature set of the significant interaction coupling of the tensile force - elongation amount time series, n represents the number of eigenvalues in the feature set of the significant interaction coupling eigenvectors of the tensile force - elongation amount time series, and λ represents the ratio;

[0118] Step S3043: Calculate the ratio of the λ - th power of the sum of the absolute values of all eigenvalues in the in - class feature set of the significant interaction coupling of the tensile force - elongation amount time series to the λ - th power of the sum of the absolute values of all eigenvalues in the feature set of the significant interaction coupling eigenvectors of the tensile force - elongation amount time series to obtain the modulation weight of the significant interaction coupling of the tensile force - elongation amount time series, that is:

[0119] where f p represents each eigenvalue in the feature set of the significant interaction coupling eigenvectors of the tensile force - elongation amount time series, and w 1 represents the modulation weight of the significant interaction coupling of the tensile force - elongation amount time series;

[0120] Step S3044: Calculate the ratio of the (λ / 2) - th power of the sum of the squares of all eigenvalues in the in - class feature set of the significant interaction coupling of the tensile force - elongation amount time series to the (λ / 2) - th power of the sum of the squares of all eigenvalues in the feature set of the significant interaction coupling eigenvectors of the tensile force - elongation amount time series to obtain the harmonic weight of the significant interaction coupling of the tensile force - elongation amount time series, that is:

[0121] where w 2 represents the harmonic weight of the significant interaction coupling of the tensile force - elongation amount time series;

[0122] Step S3045: For each eigenvalue in the set of intra-class features with significant interaction coupling of tensile force-elongation amount time series, calculate the product of the eigenvalue and the significant interaction coupling harmonic weight of the tensile force-elongation amount time series, and then add the significant interaction coupling modulation weight of the tensile force-elongation amount time series to obtain an optimized eigenvalue, that is:

[0123] where f’ 1i represents the i-th optimized eigenvalue based on the set of intra-class features with significant interaction coupling of tensile force-elongation amount time series;

[0124] Step S3046: For each eigenvalue in the set of inter-class features with significant interaction coupling of tensile force-elongation amount time series, calculate the product of the eigenvalue and the significant interaction coupling modulation weight of the tensile force-elongation amount time series to obtain an optimized eigenvalue, that is:

[0125] where f 2j ’ represents the j-th optimized eigenvalue based on the set of inter-class features with significant interaction coupling of tensile force-elongation amount time series;

[0126] Step S3047: Input the optimized eigenvector of the tensile force-elongation amount time series with significant interaction coupling based on the set of intra-class features and the set of inter-class features of the tensile force-elongation amount time series with significant interaction coupling into the fracture warning engine based on a classifier to obtain the fracture analysis result.

[0127] 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 through a display module (such as a display screen, etc.) and / or an acoustic-optic alarm module.

[0128] In a cable testing method of the present invention application, while performing feature clustering on the significant interaction coupling eigenvector of the tensile force - elongation amount time series, for the interactive description of the key feature information of the significant interaction coupling eigenvector of the tensile force - elongation amount time series during the clustering process, a geometric equivariant topology of the feature is constructed through feature low - rank harmonic modulation based on the equivariance of the clustering features and the overall features of the significant interaction coupling eigenvector of the tensile force - elongation amount time series, so as to obtain the translational and rotational symmetry of the schematic distribution of the clustering features of the significant interaction coupling eigenvector of the tensile force - elongation amount time series relative to the overall features. Thus, on the basis of introducing geometric message passing in the feature expression of the significant interaction coupling eigenvector of the tensile force - elongation amount time series, the clustering mapping symmetry of the significant interaction coupling eigenvector of the tensile force - elongation amount time series is realized through the manipulation of irreducible low - rank order coefficients, improving the consistency of the clustering - based feature representation of the significant interaction coupling eigenvector of the tensile force - elongation amount time series, thereby improving the accuracy of the fracture analysis result obtained by inputting the significant interaction coupling eigenvector of the tensile force - elongation amount time series into a classifier - based fracture warning engine, 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 accidental fractures of the cable during the testing process, and thus avoid equipment damage and personnel safety risks caused by sudden cable fractures.

[0129] The basic principles of the present invention have been described above in conjunction with specific embodiments. However, it should be noted that the advantages, advantages, effects, etc. mentioned in the present invention are only examples and not limitations. It cannot be considered that these advantages, advantages, effects, etc. are essential for each embodiment of the present invention. In addition, the specific details of the above - mentioned embodiments are only for the purposes of illustration and easy understanding, rather than limitations. The above details do not limit the present invention to necessarily adopt the above - specific details for implementation.

[0130] For those skilled in the art, it is obvious that the present invention is not limited to the details of the above - mentioned exemplary embodiments, and can be implemented in other specific forms without departing from the spirit or basic characteristics of the present invention. Therefore, from any point of view, the embodiments should be regarded as exemplary and non - restrictive. The scope of the present invention is defined by the appended claims rather than the above description. Therefore, it is intended to encompass all changes falling within the meaning and scope of the equivalent elements of the claims in the present invention. Any associated drawing marks in the claims should not be regarded as limiting the claimed rights.

[0131] In the above embodiments, the descriptions of the various embodiments have their own emphases. For the parts not detailed or recorded in a certain embodiment, reference may be made to the relevant descriptions of other embodiments. In the several embodiments provided by the present invention, it should be understood that the disclosed systems and methods can be implemented in other ways. For example, the system embodiments described above are merely illustrative. For example, the unit division is only a logical function division, and there may be other division methods in actual implementation. The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed to multiple network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of this embodiment. In addition, obviously, 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 claims can also be implemented by one unit through software or hardware.

[0132] Finally, it should be noted that the above description has been given for purposes of illustration and description. In addition, the above embodiments are only used to illustrate the technical solutions of the present invention and not to limit them. Although the present invention has been described in detail with reference to the preferred embodiments, those of ordinary skill in the art should understand that the technical solutions of the present invention can be modified or equivalently replaced without departing from the spirit and scope of the technical solutions 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 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 time series encoding module, which performs time series encoding on the time queue of the real-time tension value and the time queue of the real-time elongation respectively to obtain the time series associated implicit feature vector of the real-time tension value and the time series associated implicit feature vector of the real-time elongation; an information interaction fusion module, which performs principal component matching interaction on the time series associated implicit feature vector of the real-time tension value and the time series associated implicit feature vector of the real-time elongation to obtain the time series significant interaction coupling feature vector of the tension-elongation; a fracture analysis module; a cable tension state monitoring module, which obtains the time series significant interaction coupling feature vector of the real-time tension value and the real-time elongation according to the real-time tension value ... 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 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; an optimal pairing interaction coupling unit, which performs optimal pairing multi-scale interaction 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 the tension-elongation time series significant interaction coupling feature vector.

2. A cable tensile testing device according to claim 1, 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.

3. A cable tensile testing device according to claim 2, 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.

4. A cable tensile testing device according to claim 3, 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.

5. A cable tensile testing device according to claim 4, 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.

6. A cable tensile testing method, using a cable tensile testing device according to any one of claims 1 to 5, 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.

7. A cable tensile testing method according to claim 6, 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.

8. A cable tensile testing method according to claim 7, 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.

9. A cable tensile testing method according to claim 8, 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