A cable quality testing method, device, and medium

Abstract

This application relates to the field of neural networks and discloses a cable quality inspection method, apparatus, and medium, comprising: acquiring cable quality inspection information of the cable to be inspected, wherein the cable quality inspection information includes dielectric loss information and dielectric loss information of the cable; processing the cable quality inspection information by calling a cable aging assessment model to obtain the aging factor of the cable to be inspected based on the dielectric loss information and dielectric loss information, thereby determining the quality of the cable to be inspected; the cable aging assessment model is a backpropagation network determined based on historical inspection data of cables with different degrees of aging; and determining whether the cable quality is qualified based on the aging factor. This application obtains the aging factor of the cable to be inspected by processing the dielectric loss information and dielectric loss information of the cable to be inspected. Obtaining the dielectric loss information and dielectric loss information does not require electrical processing of the cable, reducing damage to the cable during the inspection process.

Description

Technical Field

[0001] This application relates to the field of neural networks, and in particular to a method, apparatus, and medium for cable quality testing. Background Technology

[0002] Rubber cables are electrical wires with rubber as both insulation and sheath. Due to the excellent chemical resistance, electrical insulation properties, impact elasticity, low-temperature performance, low density, high filler capacity, and resistance to hot water and water vapor, rubber cables can significantly improve circuit safety. For example, a large number of ethylene propylene rubber cables are used in the onboard cables of high-speed railway trains.

[0003] During the operation of rubber cables, the cable core carries a large load current for an extended period, generating a significant amount of heat and causing thermal aging of the rubber insulation layer. As the service life of the rubber cable continues, the degree of thermal aging becomes increasingly severe, significantly impacting the safe operation of high-speed trains. Currently, the degree of thermal aging is mainly detected through partial discharge testing of the cable. Statistical analysis of the electrical and non-electrical quantities measured during partial discharge is used to determine the extent of thermal aging. However, partial discharge testing requires a strictly shielded environment, resulting in low detection efficiency. Applying local voltage to the cable accelerates insulation degradation and aging, affecting the cable's normal operation.

[0004] Therefore, it is evident that providing a new cable quality inspection method that can achieve real-time and rapid quality inspection of cables without damaging them is a problem that urgently needs to be solved by those skilled in the art. Summary of the Invention

[0005] The purpose of this application is to provide a cable quality testing method, device, and medium to achieve real-time and rapid cable quality testing without damaging the cable, thereby reducing the waste of manpower and resources in cable testing and improving testing efficiency.

[0006] To address the aforementioned technical problems, this application provides a cable quality inspection method, comprising:

[0007] Obtain cable quality inspection information of the cable to be inspected, wherein the cable quality inspection information includes the dielectric loss information and dielectric loss information of the cable;

[0008] The cable aging assessment model is invoked to process the cable quality inspection information to obtain the aging factor; wherein, the cable aging assessment model is a backpropagation network determined based on historical inspection data of cables with different degrees of aging.

[0009] The aging factor is used to determine whether the cable under test is qualified.

[0010] Preferably, obtaining cable quality inspection information includes:

[0011] A broadband dielectric spectrum test is performed on the cable under test to obtain the dielectric loss information and dielectric loss information of the cable under test at the operating frequency.

[0012] Preferably, the step of calling the cable aging assessment model to process the cable quality inspection information includes:

[0013] The dielectric loss tangent and relative permittivity are determined based on the dielectric loss information and the dielectric loss information; wherein, the relative permittivity is the ratio of the real part of the dielectric loss to the imaginary part of the dielectric loss.

[0014] The cable aging assessment model is invoked to process the dielectric loss tangent and the relative permittivity.

[0015] Preferably, determining the cable aging assessment model based on historical testing data of cables with different degrees of aging includes:

[0016] Obtain the parameter information of the cable aging assessment model, including the number of input layer nodes, the number of hidden layer nodes, the number of output layer nodes, and weight information;

[0017] A backpropagation network is created based on the parameter information, and the learning function of the backpropagation network is a nonlinear least squares algorithm;

[0018] The backpropagation network is trained using the historical detection data to obtain the cable aging assessment model.

[0019] Preferably, the number of input layer nodes is 3;

[0020] The input layer node includes: the dielectric loss tangent, the relative permittivity, and the maximum dielectric loss deviation.

[0021] Preferably, determining whether the cable to be tested is qualified based on the aging factor includes:

[0022] If the aging factor is greater than the first threshold, the cable under test is determined to be severely thermally aged.

[0023] If the aging factor is greater than the second threshold and not greater than the first threshold, then the cable under test is determined to have moderate thermal aging.

[0024] If the aging factor is greater than 0 and not greater than the second threshold, then the cable under test is determined to have mild thermal aging.

[0025] Preferably, after the step of determining whether the cable to be tested is qualified based on the aging factor, the method further includes:

[0026] If the cable under test shows severe thermal aging, an alarm message will be sent to the management personnel.

[0027] To address the aforementioned technical problems, this application also provides a cable quality testing device, comprising:

[0028] The acquisition module is used to acquire cable quality inspection information of the cable to be inspected, wherein the cable quality inspection information includes the cable's dielectric loss information and dielectric loss information.

[0029] The processing module is used to call the cable aging assessment model to process the cable quality inspection information in order to obtain the aging factor; wherein, the cable aging assessment model is a backpropagation network determined based on historical inspection data of cables with different degrees of aging;

[0030] The judgment module is used to determine whether the cable to be tested is qualified based on the aging factor.

[0031] To address the aforementioned technical problems, this application also provides a cable quality testing device, including a memory for storing a computer program;

[0032] A processor is used to implement the steps of the cable quality testing method when executing the computer program.

[0033] To address the aforementioned technical problems, this application also provides a computer-readable storage medium storing a computer program, which, when executed by a processor, implements the steps of the cable quality testing method.

[0034] This application provides a cable quality inspection method, comprising: acquiring cable quality inspection information of the cable to be inspected, wherein the cable quality inspection information includes dielectric loss information and dielectric loss information of the cable; processing the cable quality inspection information by calling a cable aging assessment model to obtain the aging factor of the cable to be inspected based on the dielectric loss information and dielectric loss information, thereby determining the quality of the cable to be inspected; wherein the cable aging assessment model is a backpropagation network determined based on historical inspection data of cables with different degrees of aging; and determining whether the cable quality is qualified based on the aging factor. Therefore, the technical solution provided by this application, by processing the dielectric loss information and dielectric loss information of the cable to be inspected to obtain the aging factor of the cable to be inspected, accurately and quickly determines whether the cable is qualified. The process of acquiring the dielectric loss information and dielectric loss information does not require electrical treatment of the cable, reducing damage to the cable during the inspection process.

[0035] In addition, to solve the above-mentioned technical problems, this application also provides a cable quality testing device and medium, which correspond to the above method and have the same effect. Attached Figure Description

[0036] To more clearly illustrate the embodiments of this application, the accompanying drawings used in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0037] Figure 1 A flowchart illustrating a cable quality inspection method provided in this application embodiment;

[0038] Figure 2 This is a structural diagram of a cable quality testing device provided in an embodiment of this application;

[0039] Figure 3 This is a structural diagram of another cable quality testing device provided in an embodiment of this application. Detailed Implementation

[0040] The technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, and not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those of ordinary skill in the art without creative effort are within the protection scope of this application.

[0041] The core of this application is to provide a cable quality testing method, device, and medium to achieve real-time and rapid cable quality testing without damaging the cable, thereby reducing the waste of manpower and resources in cable testing and improving testing efficiency.

[0042] To enable those skilled in the art to better understand the present application, the present application will be further described in detail below with reference to the accompanying drawings and specific embodiments.

[0043] Figure 1 A flowchart of a cable quality inspection method provided in this application embodiment is shown below. Figure 1 As shown, the method includes:

[0044] S10: Obtain cable quality inspection information of the cable to be tested, including the cable's dielectric loss information and dielectric loss information.

[0045] This application evaluates the aging state of cables using various electrical performance test data. Dielectric loss information can be represented by the relative permittivity, primarily indicating the polarization phenomenon of the cable under the influence of an electric field, including lossless and lossy polarization. Dielectric loss information is expressed as the dielectric loss tangent, representing the loss characteristics of the cable due to the electric field during long-term service. By using both dielectric loss (relative permittivity) and the dielectric loss tangent, the thermal aging degree of the cable can be evaluated in multiple dimensions, thereby determining whether the cable quality is up to standard.

[0046] S11: The cable aging assessment model is invoked to process the cable quality inspection information to obtain the aging factor. The cable aging assessment model is a backpropagation network determined based on historical inspection data of cables at different aging levels. In actual working conditions, field experts conduct numerous insulation characteristic tests on cables to determine their aging state. This provides a large data source for our backpropagation (BP) network. The dielectric properties and dielectric loss parameters of these field-measured data at different aging states are used as the training dataset for the BP neural network.

[0047] In using the BP neural network algorithm, the parameters that need to be determined include the number of input layer nodes, the number of hidden layer nodes, the number of output layer nodes, the weights between each node, the number of iterations, the training function, the training accuracy, and the learning rate.

[0048] The parameter setting statements for a BP neural network are as follows:

[0049] net = newff(inputn, label_train, 2, {'tansig", 'purelin'}, 'trainlm'); (Sets the number of hidden layer nodes to 2, and uses the Levenberg-Marquardt algorithm as the learning function)

[0050] net.trainParam.epochs=1000: (Sets the maximum number of training iterations to 1000)

[0051] net.trainParam.1r = 0.1; (Sets the learning rate to 0.1)

[0052] net.trainParam.goal = 0.0001 (sets the training objective error to 0.0001)

[0053] The above statements describe the key parameters of the BP neural network used in the paper. Among them, the `newff` statement is crucial. The `newff` statement in MATLAB is used as follows:

[0054] net=newff(P,T,[S1 S2...S(Nl)],{TF1 TF2...TFN},BTF,BLF,PF,IPF,OPF,

[0055] DDF);

[0056] Where P and T represent the training matrix and training matrix labels; Si represents the number of hidden layers; TFi represents the transfer function of the i-th layer (the hidden layer transfer function is set to "tansig", and the output layer transfer function defaults to "purelin"); BTF represents the backpropagation network training function (set to "trainlm"); BLF represents the backpropagation weight / bias learning function (set to "learngdm"). The latter parameters generally do not need to be set during use.

[0057] By conducting the training process using the above settings, the optimized calculation method for the multi-dimensional aging factor τ can be obtained.

[0058] The number of input layer nodes in a BP neural network is related to the number of features. In this patent, there are three types of features, therefore the number of input layer nodes is three. The number of output layer nodes is also three, corresponding to the three aging states actually evaluated. The input layer nodes include: dielectric loss tangent, relative permittivity, and maximum dielectric loss deviation.

[0059] The real part of the dielectric loss at any frequency collected during the testing of the target vehicle-mounted EPDM cable is denoted as ε′. (m，n) The imaginary part of dielectric loss is denoted as Where m represents the m-th broadband dielectric spectrum test (m = {1, 2, ..., 10}), and n represents the n-th frequency point of any arbitrary acquisition of discrete broadband dielectric loss tangent data (n = {1, 2, ..., 10}). The dielectric loss tangent data of the cable under test is denoted as tanδ. m .

[0060] Based on the collected data of dielectric loss tangent, real part, and imaginary part at multiple frequencies of the target cable, the aging degree of the cable is jointly assessed from two dimensions: loss and polarization. The multi-dimensional aging factor τ of the target vehicle-mounted EPDM rubber cable is calculated using the following formula:

[0061]

[0062] Looking at the elements of the middle matrix row by row, the first element in the first row is the real part of the dielectric loss ε′ at the first recorded frequency point in the first broadband dielectric spectrum test. (1，1) Divide by the imaginary part of dielectric loss ε″ (1，1)The first element in the second row is the real part of the dielectric loss ε′ at the first recorded frequency point in the second broadband dielectric spectrum test. (2，1) Divide by the imaginary part of dielectric loss ε″ (2，1) And so on; looking at the elements of the intermediate matrix from the columns, the first element of the first column is the real part of the dielectric loss ε′ at the first recorded frequency point in the first broadband dielectric spectrum test. (1，1) Divide by the imaginary part of dielectric loss ε″ (1，1) The first element in the second row is the real part of the dielectric loss ε′ at the second recorded frequency point in the first broadband dielectric spectrum test. (1，2) Divide by the imaginary part of dielectric loss ε″ (1，2) And so on;

[0063] The rightmost matrix element is divided into two parts. The left part is the imaginary part of the dielectric loss ε″ in the m-th test. (m，n) The maximum value of the arctangent divided by the real part of the dielectric loss ε′ (m，n) The goal of this step is to obtain the minimum value of the dielectric loss tangent. The test result with the largest deviation between the real and imaginary parts of the dielectric loss, i.e. the most severely aged part, is used as one of the parameters for judging the degree of cable aging. Then, it is multiplied by the dielectric loss tangent value data at the power frequency corresponding to each test.

[0064] The reason for using this type of matrix is ​​that the data from multiple broadband dielectric spectrum tests may differ, and it is necessary to comprehensively consider the results of each test, as well as the possible cumulative effects on cable insulation.

[0065] It should be noted that this embodiment uses 10 broadband dielectric spectrum test data as an example to limit the quality inspection process of the cable under test. However, in the actual test process, the amount of test data can be more than 10 sets or less. There is no limitation here. It should be noted that when the amount of test data is more, the test results are more accurate and reliable, but the test time is also longer.

[0066] S12: Determine whether the cable under test is qualified based on the aging factor.

[0067] Ten broadband dielectric spectral tests were performed on the cable under test, yielding a total of ten dielectric loss tangent values ​​(tan δ). m And 100 real part data points of dielectric loss ε′ (m，n) 100 imaginary parts of dielectric loss ε″ (m，n) Substitute the three matrices into the formula above; the leftmost matrix is ​​a 1-row, 10-column matrix, the middle matrix is ​​a 10-row, 10-column matrix, and the rightmost matrix is ​​a 10-row, 1-column matrix. Multiply the left and middle matrices by the dot product to get a 1-row, 10-column matrix, and then multiply it by the right matrix by the dot product to get a value, which is the multidimensional aging factor τ.

[0068] This embodiment provides a cable quality inspection method, including: acquiring cable quality inspection information of the cable to be inspected, wherein the cable quality inspection information includes dielectric loss information and dielectric loss information of the cable; processing the cable quality inspection information by calling a cable aging assessment model to obtain the aging factor of the cable to be inspected based on the dielectric loss information and dielectric loss information, thereby determining the quality of the cable to be inspected; wherein the cable aging assessment model is a backpropagation network determined based on historical inspection data of cables with different degrees of aging; and determining whether the cable quality is qualified based on the aging factor. Therefore, the technical solution provided in this application, by processing the dielectric loss information and dielectric loss information of the cable to be inspected to obtain the aging factor of the cable to be inspected, accurately and quickly determines whether the cable is qualified. The process of acquiring the dielectric loss information and dielectric loss information does not require electrical processing of the cable, reducing damage to the cable during the inspection process.

[0069] In practice, the quality inspection information of the cable under test is obtained by performing a broadband dielectric spectrum test at the working frequency.

[0070] In practice, the cable under test undergoes multiple broadband dielectric spectrum tests. During each test, the dielectric loss tangent data at the operating frequency, the real part of the dielectric loss at any frequency, and the imaginary part of the dielectric loss are collected. The dielectric loss tangent data at the operating frequency collected during the testing of the cable under test is denoted as tanδ. m , where m represents the m-th broadband dielectric spectrum test, m={1,2,...,10}.

[0071] As a preferred embodiment, determining the cable aging assessment model based on historical testing data of cables with different degrees of aging includes: obtaining parameter information of the cable aging assessment model, including the number of input layer nodes, the number of hidden layer nodes, the number of output layer nodes, and weight information; creating a backpropagation network based on the parameter information, wherein the learning function of the backpropagation network is a nonlinear least squares algorithm; and training the backpropagation network using historical testing data to obtain the cable aging assessment model.

[0072] Accordingly, the cable aging assessment model is called to process the cable quality inspection information, including: determining the dielectric loss tangent and relative permittivity based on the dielectric loss information and dielectric loss information; wherein, the relative permittivity is the ratio of the real part of the dielectric loss data to the imaginary part of the dielectric loss data; and the cable aging assessment model is called to process the dielectric loss tangent and relative permittivity.

[0073] In a preferred embodiment, determining the cable quality based on the aging factor includes: if the aging factor is greater than a first threshold, the cable under test is determined to have undergone severe thermal aging; if the aging factor is greater than a second threshold but not greater than the first threshold, the cable under test is determined to have undergone moderate thermal aging; if the aging factor is greater than 0 but not greater than the second threshold, the cable under test is determined to have undergone mild thermal aging. It is understood that the first threshold is greater than the second threshold and the second threshold is greater than 0. Typically, the first threshold is taken as 524.37 and the second threshold as 61.82. If τ≤61.82, it indicates that the insulation of the target vehicle-mounted EPDM cable has undergone mild thermal aging; if 61.82<τ≤524.37, it indicates that the insulation of the target vehicle-mounted EPDM cable has undergone moderate thermal aging; if τ≥524.37, it indicates that the insulation of the target vehicle-mounted EPDM cable has undergone severe thermal aging. It should be noted that, to ensure circuit safety, when severe thermal aging of the cable is detected, an alarm message should be promptly sent to the management personnel to facilitate timely cable replacement or maintenance.

[0074] The cable quality testing method has been described in detail in the above embodiments. This application also provides embodiments corresponding to the cable quality testing device. It should be noted that this application describes the embodiments of the device from two perspectives: one is based on the functional modules, and the other is based on the hardware.

[0075] Figure 2 A structural diagram of a cable quality testing device provided in this application embodiment includes:

[0076] The acquisition module 10 is used to acquire the cable quality inspection information of the cable to be inspected, wherein the cable quality inspection information includes the dielectric loss information and dielectric loss information of the cable.

[0077] Processing module 11 is used to call the cable aging assessment model to process the cable quality inspection information in order to obtain the aging factor; wherein, the cable aging assessment model is a back propagation network determined based on historical inspection data of cables with different degrees of aging.

[0078] The judgment module 12 is used to determine whether the cable under test is qualified based on the aging factor.

[0079] Since the embodiments of the apparatus and the embodiments of the method correspond to each other, please refer to the description of the embodiments of the method for the embodiments of the apparatus, which will not be repeated here.

[0080] This embodiment provides a cable quality testing device, comprising: acquiring cable quality testing information of a cable to be tested, so as to facilitate the testing of the cable quality, wherein the cable quality testing information includes dielectric loss information and dielectric loss information of the cable; processing the cable quality testing information by calling a cable aging assessment model to obtain the aging factor of the cable to be tested based on the dielectric loss information and dielectric loss information, thereby determining the quality of the cable to be tested; wherein the cable aging assessment model is a backpropagation network determined based on historical testing data of cables with different degrees of aging; and determining whether the cable quality is qualified based on the aging factor. Therefore, the technical solution provided in this application, by processing the dielectric loss information and dielectric loss information of the cable to be tested to obtain the aging factor of the cable to be tested, accurately and quickly determines whether the cable is qualified. The process of acquiring the dielectric loss information and dielectric loss information does not require electrical processing of the cable, reducing damage to the cable during the testing process.

[0081] Figure 3 This is a structural diagram of another cable quality testing device provided in an embodiment of this application, as shown below. Figure 3 As shown, the cable quality testing device includes: a memory 20 for storing computer programs;

[0082] The processor 21 is used to execute a computer program to implement the steps of the cable quality inspection method as described in the above embodiment.

[0083] The cable quality testing device provided in this embodiment may include, but is not limited to, smartphones, tablets, laptops, or desktop computers.

[0084] The processor 21 may include one or more processing cores, such as a quad-core processor or an octa-core processor. The processor 21 may be implemented using at least one of the following hardware forms: Digital Signal Processor (DSP), Field-Programmable Gate Array (FPGA), or Programmable Logic Array (PLA). The processor 21 may also include a main processor and a coprocessor. The main processor, also known as the Central Processing Unit (CPU), is used to process data in the wake-up state; the coprocessor is a low-power processor used to process data in the standby state. In some embodiments, the processor 21 may integrate a Graphics Processing Unit (GPU), which is responsible for rendering and drawing the content to be displayed on the screen. In some embodiments, the processor 21 may also include an Artificial Intelligence (AI) processor, which is used to handle computational operations related to machine learning.

[0085] The memory 20 may include one or more computer-readable storage media, which may be non-transitory. The memory 20 may also include high-speed random access memory and non-volatile memory, such as one or more disk storage devices or flash memory devices. In this embodiment, the memory 20 is used to store at least the following computer program 201, which, after being loaded and executed by the processor 21, is capable of implementing the relevant steps of the cable quality inspection method disclosed in any of the foregoing embodiments. In addition, the resources stored in the memory 20 may also include an operating system 202 and data 203, and the storage method may be temporary or permanent storage. The operating system 202 may include Windows, Unix, Linux, etc. The data 203 may include, but is not limited to, cable quality inspection information.

[0086] In some embodiments, the cable quality testing device may further include a display screen 22, an input / output interface 23, a communication interface 24, a power supply 25, and a communication bus 26.

[0087] Those skilled in the art will understand that Figure 3 The structure shown does not constitute a limitation on the cable quality testing device and may include more or fewer components than shown.

[0088] The cable quality testing device provided in this application includes a memory and a processor. When the processor executes the program stored in the memory, it can implement the following method:

[0089] Obtain cable quality inspection information of the cable to be inspected, including cable dielectric loss information and dielectric loss information;

[0090] The cable aging assessment model is called to process the cable quality inspection information to obtain the aging factor; the cable aging assessment model is a backpropagation network determined based on historical inspection data of cables with different degrees of aging.

[0091] The aging factor is used to determine whether the cable under test is qualified.

[0092] Finally, this application also provides an embodiment corresponding to a computer-readable storage medium. The computer-readable storage medium stores a computer program, which, when executed by a processor, implements the steps described in the above method embodiments.

[0093] It is understood that if the methods in the above embodiments are implemented as software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, or all or part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and executes all or part of the steps of the methods described in the various embodiments of this application. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0094] The cable quality testing method, apparatus, and medium provided in this application have been described in detail above. The various embodiments in the specification are described in a progressive manner, with each embodiment focusing on its differences from other embodiments. Similar or identical parts between embodiments can be referred to interchangeably. For the apparatus disclosed in the embodiments, since it corresponds to the method disclosed in the embodiments, the description is relatively simple; relevant parts can be referred to in the method section. It should be noted that those skilled in the art can make several improvements and modifications to this application without departing from the principles of this application, and these improvements and modifications also fall within the protection scope of the claims of this application.

[0095] It should also be noted that, in this specification, relational terms such as "first" and "second" are used only to distinguish one entity or operation from another, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Furthermore, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitations, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes said element.

Claims

1. A method of detecting the quality of a cable, characterized by, The method comprises the following steps: performing broadband dielectric spectrum test on the cable to be detected to obtain dielectric loss information and dielectric loss information of the cable to be detected at working frequency; determining a dielectric loss tangent value and a relative dielectric constant according to the dielectric loss information and the dielectric loss information; wherein the relative dielectric constant is the ratio of dielectric loss real part data to dielectric loss imaginary part data; calling a cable aging evaluation model to process the dielectric loss tangent value and the relative dielectric constant to obtain an aging factor; judging whether the cable to be detected is qualified according to the aging factor; wherein the cable aging evaluation model is a back propagation network determined according to historical detection data of cables of different degrees of aging; the determination of the cable aging evaluation model according to the historical detection data of cables of different degrees of aging comprises: obtaining parameter information of the cable aging evaluation model, the parameter information comprising input layer node number, hidden layer node number, output layer node number and weight information; wherein the input layer node number is 3; the input layer nodes comprise the dielectric loss tangent value, the relative dielectric constant and a dielectric loss maximum deviation value; creating a back propagation network according to the parameter information, the learning function of the back propagation network being a nonlinear least square algorithm; training the back propagation network using the historical detection data to obtain the cable aging evaluation model.

2. The method of claim 1, wherein, The judgment of whether the cable to be detected is qualified according to the aging factor comprises: if the aging factor is greater than a first threshold value, determining that the cable to be detected is severely heat aged; if the aging factor is greater than a second threshold value and not greater than the first threshold value, determining that the cable to be detected is moderately heat aged; if the aging factor is greater than 0 and not greater than the second threshold value, determining that the cable to be detected is slightly heat aged.

3. The method of claim 2, wherein, After the step of judging whether the cable to be detected is qualified according to the aging factor, the method further comprises the following steps: if the cable to be detected is severely heat aged, sending alarm information to a manager.

4. A cable quality detection device characterized by comprising: The method comprises the following steps: obtaining a module for performing broadband dielectric spectrum test on the cable to be detected to obtain dielectric loss information and dielectric loss information of the cable to be detected at working frequency; The processing module is configured to determine a dielectric loss tangent value and a relative dielectric constant according to the dielectric loss information and the dielectric loss information, wherein the relative dielectric constant is a ratio of a dielectric loss real part data to a dielectric loss imaginary part data; and call a cable aging evaluation model to process the dielectric loss tangent value and the relative dielectric constant to obtain an aging factor, wherein the cable aging evaluation model is a back propagation network determined according to historical detection data of cables with different degrees of aging; the determination of the cable aging evaluation model according to the historical detection data of cables with different degrees of aging comprises: obtaining parameter information of the cable aging evaluation model, wherein the parameter information comprises an input layer node number, a hidden layer node number, an output layer node number and weight information; the input layer node number is 3; the input layer nodes comprise the dielectric loss tangent value, the relative dielectric constant and a dielectric loss maximum deviation value; creating a back propagation network according to the parameter information, wherein a learning function of the back propagation network is a nonlinear least square algorithm; and training the back propagation network by using the historical detection data to obtain the cable aging evaluation model. The judging module is configured to judge whether the to-be-detected cable is qualified according to the aging factor.

5. A cable quality detection device characterized by comprising: The computer readable storage medium stores a computer program. The processor is configured to execute the computer program to implement the steps of the cable quality detection method according to any one of claims 1 to 3.

6. A computer-readable storage medium, characterized in that, The computer readable storage medium stores a computer program, and the computer program is executed by the processor to implement the steps of the cable quality detection method according to any one of claims 1 to 3.

Images