Cable type identification method and device, storage medium and electronic equipment

Abstract

The invention discloses a cable type identification method and device, a storage medium and electronic equipment, and the method is applied to the field of electric power engineering, and comprises the steps: collecting a first scattering parameter of a cable; processing noise in the first scattering parameter to obtain a second scattering parameter; performing feature extraction on the second scattering parameter, and performing dimension reduction processing on the extracted feature information to obtain target feature information; and inputting the target feature information into a target identification model, and identifying the cable type of the cable. Through the cable type identification method and device, the problem that cable types are difficult to accurately identify due to the fact that cable type identification depends on simple signal feature extraction or artificial experience judgment in the prior art is solved.

Description

Technical Field

[0001] The present application relates to the field of communication cables, and in particular, to a method, device, storage medium and electronic device for identifying cable types. Background Art

[0002] Cable identification is an important step before installation. However, in practice, tags may become unreliable due to remote location, damage or aging. At the same time, data sheets for relevant cables are not always readily available, and multiple cables may have similar geometries and outer jacket colors, increasing the difficulty of differentiation. To address this problem, electrical properties can be modeled, such as characteristic impedance, propagation constant, and scattering parameters (S parameters) to extract parameters such as resistance R, inductance L, conductance G, and capacitance C per unit length. Previous studies have shown that these parameters can be used for fault location and cable identification.

[0003] Currently, two methods calculate RLCG parameters by using measured S-parameters. One method emphasizes the possibility of using scattering parameters to identify connection discontinuities and phase shifts on the measurement plane, while the other method eliminates the resonance effects at high frequencies through de-embedding techniques to obtain accurate S-parameters. However, these methods mainly focus on extracting characteristic parameters of the cable and characterizing certain fault sources rather than identifying the cable type.

[0004] Regarding the problem that the cable type identification in the related technology relies on simple signal feature extraction or manual experience judgment, which makes it difficult to accurately identify the cable type, and no effective solution has been proposed so far. Summary of the invention

[0005] The main purpose of the present application is to provide a cable type identification method, device, storage medium and electronic device to solve the problem that when identifying the cable type in the related art, it depends on simple signal feature extraction or manual experience judgment, which makes it difficult to accurately identify the cable type.

[0006] In order to achieve the above-mentioned purpose, according to one aspect of the present application, a method for identifying a cable type is provided, the method comprising: collecting a first scattering parameter of the cable, wherein the first scattering parameter is a parameter collected within a preset frequency band; processing the noise in the first scattering parameter to obtain a second scattering parameter; performing feature extraction on the second scattering parameter, and performing dimensionality reduction processing on the extracted feature information to obtain target feature information; inputting the target feature information into a target recognition model to identify the cable type of the cable, wherein the target recognition model is a model obtained by training a preset support vector machine model using a training set.

[0007] Furthermore, feature extraction is performed on the second scattering parameter, and dimension reduction processing is performed on the extracted feature information to obtain target feature information, including: extracting frequency domain features of the second scattering parameter and time domain features of the second scattering parameter respectively; calculating the wave propagation features of the second scattering parameter at a preset frequency; and using a preset algorithm to perform dimension reduction processing on the wave propagation features, the frequency domain features, and the time domain features respectively to obtain the target feature information.

[0008] Furthermore, the wave propagation characteristics of the second scattering parameter at a preset frequency are calculated, including: calculating a third scattering parameter based on a preset algorithm according to the preset frequency, the cable length of the cable, the second scattering parameter and the impedance wave of the cable; and calculating the wave propagation characteristics according to the third scattering parameter and the incident voltage wave of the cable.

[0009] Furthermore, a preset algorithm is used to perform dimensionality reduction processing on the wave propagation characteristics, the frequency domain characteristics and the time domain characteristics respectively to obtain the target feature information, including: constructing a first matrix corresponding to the wave propagation characteristics, a first matrix corresponding to the frequency domain characteristics and a first matrix corresponding to the time domain characteristics respectively to obtain multiple first matrices; for each first matrix in the multiple first matrices, calculating the covariance matrix of the first matrix; performing eigenvalue decomposition on the covariance matrix to obtain multiple eigenvalues ​​corresponding to each first matrix and an eigenvector corresponding to each eigenvalue in the multiple eigenvalues; sorting the multiple eigenvalues ​​corresponding to each first matrix according to the numerical size, and determining the feature information of each first matrix after dimensionality reduction with the eigenvectors corresponding to the first N eigenvalues ​​after sorting; and determining the target feature information based on the feature information of each first matrix after dimensionality reduction in the multiple first matrices.

[0010] Furthermore, the target recognition model is trained by the following steps: obtaining historical scattering parameters of any cable and extracting historical feature information of the historical scattering parameters; using the historical feature information to train the preset support vector machine model to obtain a first recognition model, wherein the preset support vector machine model is a linear support vector machine using a target kernel function; and using a cross-validation algorithm and an iterative optimization algorithm to optimize the first recognition model to obtain the target recognition model.

[0011] Further, the noise in the first scattering parameter is processed to obtain a second scattering parameter, including: denoising the first scattering parameter to obtain a fourth scattering parameter; filtering the fourth scattering parameter to obtain a fifth scattering parameter; and normalizing the fifth scattering parameter to obtain the second scattering parameter.

[0012] Furthermore, collecting the first scattering parameter of the cable includes: configuring equipment parameters of a test device and connecting the test device to the cable; collecting the first scattering parameter through the test device connected to the cable; after collecting the first scattering parameter of the cable, the method also includes: storing the first scattering parameter in a target database.

[0013] In order to achieve the above-mentioned purpose, according to another aspect of the present application, a cable type identification device is provided, which includes: an acquisition unit, used to acquire a first scattering parameter of the cable, wherein the first scattering parameter is a parameter collected within a preset frequency band; a processing unit, used to process the noise in the first scattering parameter to obtain a second scattering parameter; an extraction unit, used to perform feature extraction on the second scattering parameter, and perform dimensionality reduction processing on the extracted feature information to obtain target feature information; and an identification unit, used to input the target feature information into a target identification model to identify the cable type of the cable, wherein the target identification model is a model obtained by training a preset support vector machine model using a training set.

[0014] Furthermore, the extraction unit includes: an extraction subunit, used to respectively extract the frequency domain characteristics of the second scattering parameter and the time domain characteristics of the second scattering parameter; a calculation subunit, used to calculate the wave propagation characteristics of the second scattering parameter at a preset frequency; and a first processing subunit, used to respectively perform dimensionality reduction processing on the wave propagation characteristics, the frequency domain characteristics and the time domain characteristics using a preset algorithm to obtain the target feature information.

[0015] Furthermore, the calculation subunit includes: a first calculation module, used to calculate a third scattering parameter based on a preset algorithm according to the preset frequency, the cable length of the cable, the second scattering parameter and the impedance wave of the cable; and a second calculation module, used to calculate the wave propagation characteristics based on the third scattering parameter and the incident voltage wave of the cable.

[0016] Furthermore, the processing subunit includes: a construction module, which is used to respectively construct a first matrix corresponding to the wave propagation characteristics, a first matrix corresponding to the frequency domain characteristics, and a first matrix corresponding to the time domain characteristics to obtain multiple first matrices; a third calculation module, which is used to calculate the covariance matrix of the first matrix for each of the multiple first matrices; a decomposition module, which is used to perform eigenvalue decomposition on the covariance matrix to obtain multiple eigenvalues ​​corresponding to each first matrix and an eigenvector corresponding to each eigenvalue in the multiple eigenvalues; a first determination module, which is used to sort the multiple eigenvalues ​​corresponding to each first matrix according to the numerical size, and determine the characteristic information of each first matrix after dimensionality reduction with the eigenvectors corresponding to the first N eigenvalues ​​after sorting; a second determination module, which is used to determine the target characteristic information based on the characteristic information of each first matrix after dimensionality reduction in the multiple first matrices.

[0017] Furthermore, the device also includes: an acquisition unit, used to acquire historical scattering parameters of any cable and extract historical feature information of the historical scattering parameters; a training unit, used to train the preset support vector machine model using the historical feature information to obtain a first recognition model, wherein the preset support vector machine model is a linear support vector machine using a target kernel function; an optimization unit, used to optimize the first recognition model using a cross-validation algorithm and an iterative optimization algorithm to obtain the target recognition model.

[0018] Further, the processing unit includes: a second processing subunit, used to perform denoising processing on the first scattering parameter to obtain a fourth scattering parameter; a third processing subunit, used to perform filtering processing on the fourth scattering parameter to obtain a fifth scattering parameter; and a fourth processing subunit, used to perform normalization processing on the fifth scattering parameter to obtain the second scattering parameter.

[0019] Furthermore, the acquisition unit includes: a configuration subunit, used to configure equipment parameters of a test device and connect the test device to the cable; an acquisition subunit, used to acquire the first scattering parameter through the test device connected to the cable; the device also includes: a storage unit, used to store the first scattering parameter in a target database after acquiring the first scattering parameter of the cable.

[0020] In order to achieve the above-mentioned purpose, according to one aspect of the present application, a computer program product is provided, including a computer program, which, when executed by a processor, implements any of the above-mentioned methods for identifying the cable type, and which, when executed by a processor, implements the steps of the method for identifying the cable type described in each embodiment of the present application.

[0021] In order to achieve the above-mentioned purpose, according to one aspect of the present application, a computer-readable storage medium is provided, wherein the computer-readable storage medium includes stored computer instructions, wherein when the computer instructions are executed by a processor, any one of the above-mentioned cable type identification methods is implemented.

[0022] In order to achieve the above-mentioned purpose, according to one aspect of the present application, an electronic device is provided, including one or more processors and a memory, the memory being used to store one or more programs, wherein when the one or more programs are executed by one or more processors, the one or more processors implement any one of the above-mentioned cable type identification methods.

[0023] Through the present application, the following steps are adopted: collecting a first scattering parameter of a cable, wherein the first scattering parameter is a parameter collected within a preset frequency band; processing the noise in the first scattering parameter to obtain a second scattering parameter; performing feature extraction on the second scattering parameter, and performing dimensionality reduction processing on the extracted feature information to obtain target feature information; inputting the target feature information into a target recognition model to identify the cable type of the cable, wherein the target recognition model is a model obtained by training a preset support vector machine model with a training set, which solves the problem in the related art that when identifying the cable type, it depends on simple signal feature extraction or manual experience judgment, which makes it difficult to accurately identify the cable type. By collecting the first scattering parameter of the cable to be identified and performing noise processing on the first scattering parameter, comprehensive information about the cable characteristics can be provided, and environmental noise and instrument errors introduced in the measurement process can be effectively removed, thereby improving the accuracy of identifying the cable type. At the same time, through feature extraction and dimensionality reduction processing, the second scattering parameter is converted into target feature information containing key information, which can significantly reduce the amount of calculation in the subsequent classification process, while maintaining a high recognition accuracy and speeding up the recognition speed. By adopting a target recognition model based on a support vector machine algorithm to identify the cable type, the cable type of the cable to be identified can be accurately identified, and at the same time, it has a strong generalization ability, thereby achieving the effect of improving the adaptability and reliability of identifying the cable type. BRIEF DESCRIPTION OF THE DRAWINGS

[0024] The drawings constituting a part of the present application are used to provide a further understanding of the present application. The illustrative embodiments and descriptions of the present application are used to explain the present application and do not constitute an improper limitation on the present application. In the drawings:

[0025] Figure 1 is a flow chart of a method for identifying a cable type according to Embodiment 1 of the present application;

[0026] Figure 2 is a schematic diagram of scattering parameters of an optional communication cable provided according to Embodiment 1 of the present application;

[0027] Figure 3 is a schematic diagram of an optional cable type identification process provided according to Embodiment 1 of the present application;

[0028] Figure 4 is a schematic diagram of a cable type identification device provided according to Embodiment 2 of the present application;

[0029] Figure 5 It is a schematic diagram of an electronic device for identifying cable types provided according to Embodiment 5 of the present application. DETAILED DESCRIPTION

[0030] It should be noted that, in the absence of conflict, the embodiments and features in the embodiments of the present application can be combined with each other. The present application will be described in detail below with reference to the accompanying drawings and in combination with the embodiments.

[0031] It should be noted that the user information (including but not limited to user device information, user personal information, collected data, used data, generated data, processed data, etc.) and data (including but not limited to data used for analysis, stored data, displayed data, collected information, used information, generated information, processed information, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, storage, use, processing, transmission, provision, disclosure and application of relevant data are in compliance with the relevant laws, regulations and standards of relevant countries and regions, necessary confidentiality measures are taken, and public order and good morals are not violated, and corresponding operation portals are provided for users to choose to authorize or refuse. For example, an interface is set between this system and relevant users or organizations. Before obtaining relevant information, it is necessary to send an acquisition request to the aforementioned user or organization through the interface, and obtain relevant information after receiving the consent information fed back by the aforementioned user or organization.

[0032] It should be noted that this application provides users with corresponding operation entrances for them to choose to agree or reject the automated decision-making results; if the user chooses to reject, the expert decision-making process will be entered.

[0033] In order to enable those skilled in the art to better understand the solution of the present application, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work should fall within the scope of protection of the present application.

[0034] It should be noted that the terms "first", "second", etc. in the specification and claims of the present application and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequential order. It should be understood that the data used in this way can be interchanged where appropriate, so that the embodiments of the present application described here. In addition, the terms "including" and "having" and any of their variations are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device comprising a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0035] Embodiment 1

[0036] The present invention is described below in conjunction with preferred implementation steps. Figure 1 is a flow chart of a method for identifying a cable type according to the first embodiment of the present application. Figure 1 As shown, the method comprises the following steps:

[0037] Step S101 : collecting a first scattering parameter of a cable, wherein the first scattering parameter is a parameter collected within a preset frequency band.

[0038] In the first embodiment of the present invention, it is necessary to use a specific measuring device (for example, a network analyzer) to measure the cable and obtain the scattering parameters (S parameters, i.e., the first scattering parameters mentioned above) of the cable to be identified. The S parameters are a set of parameters that describe the reflection characteristics and transmission characteristics of the input port and output port of the cable at different frequencies. The first scattering parameters collected, i.e., the S parameters, may include S11 (reflection coefficient of the input port), S12 (transmission coefficient from the output port to the input port), S21 (transmission coefficient from the input port to the output port), and S22 (reflection coefficient of the output port), etc. The S parameters provide detailed information about the impedance matching, signal transmission, and reflection behavior of the cable over the entire frequency band of the cable. By measuring these parameters over a wide frequency band, the electrical characteristics of the cable can be more accurately characterized, which is beneficial to improving the accuracy and robustness of cable identification.

[0039] Exemplarily, 101 data points may be acquired within a frequency band range of 10 to 900 MHz (ie, the above-mentioned preset frequency band range) to ensure that changes in electrical characteristics of the cable at different frequencies can be fully and accurately captured.

[0040] Step S102: Process the noise in the first scattering parameter to obtain a second scattering parameter.

[0041] When measuring the scattering parameters of a communication cable, due to the complexity of the production environment, the limitations of the test equipment or the characteristics of the cable itself, the obtained original scattering parameters (i.e., the first scattering parameters mentioned above) may contain various types of noise, such as background noise, equipment noise, measurement errors, etc. These noises may affect the accuracy of subsequent feature extraction and cable type identification.

[0042] In the first embodiment, in order to remove or reduce the influence of noise from the first scattering parameter, it is necessary to perform a preprocessing operation on the first scattering parameter to remove the noise in the first scattering parameter and obtain the above-mentioned second scattering parameter. Exemplarily, steps such as data smoothing and normalization can be adopted, or different denoising algorithms can be adopted, such as low-pass filtering, median filtering, wavelet denoising or statistical-based methods. These methods can identify and eliminate random fluctuations and outliers in the data, thereby retaining the useful information of the cable scattering parameters.

[0043] Step S103: extract features from the second scattering parameters, and perform dimensionality reduction processing on the extracted feature information to obtain target feature information.

[0044] In the first embodiment, in order to improve the efficiency and accuracy of the cable type identification result, it is necessary to screen the feature information reflecting the cable characteristics from the second scattering parameter (i.e., the above-mentioned feature extraction of the second scattering parameter). After the feature extraction, in order to avoid the extracted high-dimensional data affecting the training and recognition performance of the target recognition model, it is necessary to perform dimensionality reduction processing on the extracted feature information to obtain the above-mentioned target feature information. By mapping the high-dimensional feature space to the low-dimensional space, the distinguishing ability of the original data can be retained as much as possible, thereby reducing the data dimension, thereby reducing the computational complexity and improving the recognition efficiency.

[0045] Step S104, inputting the target feature information into a target recognition model to identify the cable type of the cable, wherein the target recognition model is a model obtained by training a preset support vector machine model using a training set.

[0046] In the first embodiment of the present invention, in order to identify the cable type of the cable to be identified, the target feature information needs to be input into the trained support vector machine model (i.e., the above-mentioned target recognition model). The target recognition model will classify the input target feature information based on the learned decision boundary, thereby outputting the cable type recognition result.

[0047] In an optional embodiment, a preset support vector machine model can be trained using a training set to obtain the above-mentioned target recognition model. Support vector machine (SVM) is a supervised learning algorithm used as a classification model to distinguish different types of cables. During the training process, the support vector machine finds an optimal decision boundary (hyperplane) in the feature space based on the scattering parameters of any cable in the training set and the cable type corresponding to the cable, separates different types of cables, and obtains the cable type of the cable to be identified.

[0048] In summary, the cable type identification method provided in the first embodiment of the present application collects a first scattering parameter of the cable, wherein the first scattering parameter is a parameter collected within a preset frequency band; processes the noise in the first scattering parameter to obtain a second scattering parameter; performs feature extraction on the second scattering parameter, and performs dimensionality reduction processing on the extracted feature information to obtain target feature information; inputs the target feature information into a target recognition model to identify the cable type of the cable, wherein the target recognition model is a model obtained by training a preset support vector machine model with a training set, which solves the problem in the related art that when identifying the cable type, it relies on simple signal feature extraction or manual experience judgment, which makes it difficult to accurately identify the cable type. By collecting the first scattering parameter of the cable to be identified and performing noise processing on the first scattering parameter, comprehensive information about the cable characteristics can be provided, and environmental noise and instrument errors introduced in the measurement process can be effectively removed, thereby improving the accuracy of identifying the cable type. At the same time, through feature extraction and dimensionality reduction processing, the second scattering parameter is converted into target feature information containing key information, which can significantly reduce the amount of calculation in the subsequent classification process, while maintaining a high recognition accuracy and speeding up the recognition speed. By adopting a target recognition model based on a support vector machine algorithm to identify the cable type, the cable type of the cable to be identified can be accurately identified, and at the same time, it has a strong generalization ability, thereby achieving the effect of improving the adaptability and reliability of identifying the cable type.

[0049] Optionally, in the cable type identification method provided in Example 1 of the present application, feature extraction is performed on the second scattering parameter, and the extracted feature information is subjected to dimensionality reduction processing to obtain target feature information, including: respectively extracting frequency domain features of the second scattering parameter and time domain features of the second scattering parameter; calculating the wave propagation features of the second scattering parameter at a preset frequency; and using a preset algorithm to respectively perform dimensionality reduction processing on the wave propagation features, frequency domain features, and time domain features to obtain target feature information.

[0050] In the first embodiment of the present invention, in order to overcome the problems of high data processing complexity, slow recognition speed and low accuracy in the prior art and realize accurate recognition of the type of communication cable, the characteristics of the cable in the frequency domain and time domain can be comprehensively analyzed, combined with the wave propagation characteristics, and an efficient dimensionality reduction algorithm can be used to ensure that rich and refined feature information is extracted from the scattering parameters, thereby providing high-quality input for the target recognition model.

[0051] The scattering parameters of the communication cable will have different performances at different frequencies. Therefore, in an optional embodiment, the second scattering parameter can be subjected to frequency domain analysis to extract frequency domain features such as peak frequency, spectrum mean, and spectrum variance. These frequency domain features can reflect the characteristics of the cable for signal reflection and transmission at different frequencies. In addition to frequency domain features, the second scattering parameter can also be subjected to time domain analysis to extract time domain features such as waveform, amplitude, and phase of the signal. These time domain features can reflect the response characteristics of the cable in the time dimension, which helps to distinguish different types of cables.

[0052] Then, the wave propagation characteristics of the second scattering parameter at the preset frequency can be calculated, such as reflection coefficient, transmission coefficient, etc. By calculating the wave propagation characteristics, the signal transmission capability of the cable can be deeply understood, and key properties such as impedance matching and signal loss of the cable can be further revealed.

[0053] Finally, the extracted frequency domain features, time domain features, and wave propagation features can be subjected to dimensionality reduction processing respectively, retaining the most relevant and effective feature information for identifying the cable type in the feature information, reducing the dimension of the data, and reducing the computational complexity of subsequent processing. Exemplarily, principal component analysis (PCA, i.e., the above-mentioned preset algorithm) can be used to perform dimensionality reduction processing on the extracted frequency domain features, time domain features, and wave propagation features respectively, and screen out the target feature information, thereby facilitating the understanding and calculation of the target recognition model, and helping to improve the performance and accuracy of identifying the cable type.

[0054] Optionally, in the cable type identification method provided in Example 1 of the present application, the wave propagation characteristics of the second scattering parameter at a preset frequency are calculated, including: calculating a third scattering parameter based on a preset algorithm according to the preset frequency, the cable length of the cable, the second scattering parameter and the impedance of the cable; and calculating the wave propagation characteristics based on the third scattering parameter and the incident voltage wave of the cable.

[0055] In an optional embodiment, the S-matrix algorithm (ie, the above-mentioned preset algorithm) can be used to calculate the power consumption of the cable according to the preset frequency, the cable length, the impedance Z of the cable, and the power consumption of the cable. C The third scattering parameter is calculated by using the preprocessed second scattering parameter. r The calculation formula can be shown as formula 6,

[0056]

[0057] Among them, v p is the cable phase velocity, 1 is the cable length, and n is the number of resonant frequencies (also called modes). The process of calculating the third scattering parameter can be shown in Formulas 2 to 5,

[0058]

[0059]

[0060] Where [S] represents the third scattering parameter mentioned above, S 11 , S 12 , S 21 and S 22 is the second scattering parameter after preprocessing, Z0 represents a known impedance, for example, it can be set to 50 ohms (in an actual production environment, the value of Z0 can be flexibly adjusted, which is not specifically limited in this embodiment 1), Z C is the impedance value determined according to the cable material characteristics, and 1 is the cable length. Then, the wave propagation characteristics are calculated based on the third scattering parameter and the incident voltage wave of the cable. The process of calculating the wave propagation characteristics (including b1 and b2) can be shown in Formulas 6 to 10,

[0061]

[0062] Among them, a1 is the incident voltage wave at cable port 1, a2 is the incident voltage wave at cable port 2, b1 is the reflected voltage wave at cable port 1, b2 is the reflected voltage wave at cable port 2, V1 and V2 are the voltages at both ends of the cable to be identified, I1 and I2 are the terminal currents at the interfaces at both ends of the cable to be identified, It represents the voltage of V1 split in the positive direction of the horizontal plane. It represents the voltage of V1 split in the negative direction of the horizontal plane. and Similarly, Z0 represents a known impedance, for example, it can be set to 50 ohms (in an actual production environment, the value of Z0 can be flexibly adjusted and is not specifically limited in this first embodiment).

[0063] Optionally, in the cable type identification method provided in Example 1 of the present application, a preset algorithm is used to perform dimensionality reduction processing on the wave propagation characteristics, frequency domain characteristics and time domain characteristics respectively to obtain target feature information, including: constructing a first matrix corresponding to the wave propagation characteristics, a first matrix corresponding to the frequency domain characteristics and a first matrix corresponding to the time domain characteristics respectively to obtain multiple first matrices; for each first matrix in the multiple first matrices, calculating the covariance matrix of the first matrix; performing eigenvalue decomposition on the covariance matrix to obtain multiple eigenvalues ​​corresponding to each first matrix and an eigenvector corresponding to each eigenvalue in the multiple eigenvalues; sorting the multiple eigenvalues ​​corresponding to each first matrix according to the numerical size, and determining the feature information of each first matrix after dimensionality reduction with the eigenvectors corresponding to the first N eigenvalues ​​after sorting; and determining the target feature information based on the feature information of each first matrix after dimensionality reduction in the multiple first matrices.

[0064] In an optional embodiment, a first matrix of each characteristic information can be constructed, wherein each row represents a characteristic vector of a sample and each column represents a feature. For each constructed first matrix (i.e., the first matrix corresponding to the wave propagation feature, the first matrix corresponding to the frequency domain feature, and the first matrix corresponding to the time domain feature), the covariance matrix of each first matrix is ​​calculated. The covariance matrix is ​​a matrix that describes the linear dependency between different variables, so that the features extracted from different angles reveal the characteristic information with strong correlation.

[0065] Then, each calculated covariance matrix is ​​subjected to eigenvalue decomposition. Eigenvalue decomposition is used to decompose a matrix into the product of an eigenvalue and an eigenvector. The direction of the eigenvector represents the main direction of change of the data, and the size of the eigenvalue represents the degree of change in this direction, which helps to identify the characteristic information of significant changes, and then serves as an inherent structure to characterize the characteristic information. The eigenvalues ​​of each covariance matrix are sorted according to the numerical value to obtain the eigenvalue queue corresponding to each covariance matrix. The size of the eigenvalue reflects the importance of the eigenvector corresponding to the eigenvalue in the data change. Generally, the eigenvector corresponding to the top eigenvalue corresponds to the principal component of the data, which contains a lot of information about the data. According to each sorted eigenvalue queue, the eigenvectors corresponding to the first N eigenvalues ​​in each eigenvalue queue can be selected, and these N eigenvectors will be used to represent different types of characteristic information after dimensionality reduction (i.e., wave propagation characteristics, frequency domain characteristics, and time domain characteristics), and obtain the characteristic information after dimensionality reduction of each first matrix. It should be noted that the selection of N is usually based on the required degree of data compression and the trade-off between the amount of information that needs to be retained. Exemplarily, N can be a positive integer such as 3, 5, 10, etc., or can be determined based on a percentage of the total data volume. For example, the value of N is equal to the value obtained by multiplying the total data volume by a percentage value such as 90%, 80%, or 20%.

[0066] Finally, after obtaining the feature information of each first matrix after dimensionality reduction, these feature information are integrated to form the above-mentioned target feature information. The target feature information is the dimensionality reduction result that integrates the wave propagation, frequency domain and time domain features. It contains the most important information for cable identification, while reducing the dimension of the original data, improving the calculation efficiency and the training speed of the model, and also improving the accuracy and efficiency of identification.

[0067] Optionally, in the cable type identification method provided in Example 1 of the present application, the above-mentioned target identification model is trained by the following steps: obtaining historical scattering parameters of any cable, and extracting historical feature information of the historical scattering parameters; using the historical feature information to train a preset support vector machine model to obtain a first identification model, wherein the preset support vector machine model is a linear support vector machine using a target kernel function; and using a cross-validation algorithm and an iterative optimization algorithm to optimize the first identification model to obtain a target identification model.

[0068] In an optional embodiment, historical data of scattering parameters of different types of cables at different frequencies, i.e., the above-mentioned historical scattering parameters, may be collected. These historical scattering parameters need to cover a wide range of cable types, including coaxial cables of different lengths, sizes, and connectors, to ensure the generalization ability of the model.

[0069] Then, after the historical scattering parameters are collected, the historical scattering parameters need to be preprocessed, feature extracted, and feature dimension reduced, so as to select the most beneficial historical feature information for cable type identification from the original historical scattering parameters. In the process of processing the historical scattering parameters, the historical scattering parameters can be processed accordingly according to the preprocessing, feature extraction, and feature dimension reduction steps for the cable to be identified.

[0070] Secondly, a data set is constructed using the extracted historical feature information, and the data set is used to train a preset support vector machine model, wherein the preset support vector machine is a support vector machine model using a specific kernel function (e.g., a linear kernel function). The linear kernel function is suitable for the case where the data is linearly separable in the feature space, and can directly process the linear relationship of the scattering parameters, and therefore, is suitable for the identification problem of the cable type. The training process of the preset support vector machine model includes multiple iterations, and the model parameters are adjusted in each iteration to find a hyperplane that can maximize the classification interval or minimize the classification error.

[0071] Finally, the first recognition model is optimized using a cross-validation algorithm and an iterative optimization algorithm to obtain a target recognition model. The cross-validation algorithm is used to evaluate the generalization ability of the model after each iteration. The data set is usually divided into a training set and a validation set. Training and validation on different data subsets are performed to avoid overfitting and ensure the performance of the model on unknown data. The iterative optimization algorithm is used to continuously adjust the model parameters during the training process to optimize the performance of the model, such as the gradient descent method, sequential minimum optimization (SMO), etc.

[0072] By collecting historical scattering parameters and extracting features from them, a data set can be constructed to ensure the performance and practicality of the identification system. The support vector machine model is then trained and optimized through the data set to improve the accuracy, robustness and generalization ability of the cable type identification model. This allows a target recognition model to be constructed to identify the type of communication cables, and the target recognition model can then be used to more accurately distinguish different types of communication cables.

[0073] Optionally, in the cable type identification method provided in Example 1 of the present application, the noise in the first scattering parameter is processed to obtain the second scattering parameter, including: denoising the first scattering parameter to obtain a fourth scattering parameter; filtering the fourth scattering parameter to obtain a fifth scattering parameter; and normalizing the fifth scattering parameter to obtain the second scattering parameter.

[0074] In the first embodiment, in order to eliminate random noise in the data and improve the accuracy of subsequent analysis, the first scattering parameter can be denoised to obtain the second scattering parameter. Here, the first scattering parameter refers to the original scattering parameter measured by the test equipment (for example, a network analyzer).

[0075] Then, in order to further smooth the signal, remove some unnecessary high-frequency noise or signal fluctuations, and obtain more concise scattering parameters, filtering processing can be performed after denoising, that is, the fourth scattering parameter is normalized to obtain the above-mentioned fifth scattering parameter.

[0076] Finally, in order to avoid the negative impact of certain features on the results due to their large magnitude, different features or different measurement data are within the same range. Scale adjustment can be performed, that is, the fifth scattering parameter is normalized to obtain the above-mentioned second scattering parameter, which is helpful for subsequent analysis and algorithm processing to achieve accurate identification of the type of communication cable.

[0077] Optionally, in the cable type identification method provided in Example 1 of the present application, collecting the first scattering parameter of the cable includes: configuring device parameters of a test device and connecting the test device to the cable; collecting the first scattering parameter through the test device connected to the cable; after collecting the first scattering parameter of the cable, the above method also includes: storing the first scattering parameter in a target database.

[0078] In the first embodiment, in order to ensure that the test equipment (e.g., network analyzer) can accurately measure the scattering parameters of the cable, the parameters of the test equipment need to be set, including but not limited to: frequency band range, number of sampling points, resolution bandwidth, average times, etc., wherein the frequency band range should cover 10MHz to 900MHz to ensure that the characteristics of the cable in a wide frequency band can be obtained, the number of sampling points is configured as 101 frequency points to ensure the comprehensiveness of the data, and the selection of resolution bandwidth depends on the minimum characteristic frequency that needs to be resolved. By adjusting these parameters, the test equipment can accurately collect the scattering parameters of the cable, thereby providing high-quality data input for subsequent cable type identification.

[0079] Then, connect the test equipment to the cable to be identified, usually using a standard test interface or connector, such as SMA (Screw-Mounted Aperture) or N-type connector, to ensure the stability of the connection and low insertion loss to avoid signal reflection or attenuation, which will affect the accuracy of the measurement. After the cable to be identified is correctly connected to the test equipment, the test equipment will send a series of signals of different frequencies to the cable and measure its reflected and transmitted signals to obtain the scattering parameters. The scattering parameters reflect the impedance matching of the cable at different frequencies, including S11 (input port reflection), S21 (input to output transmission), S12 (reverse transmission) and S22 (output port reflection). The scattering parameters can provide information about the internal structure of the cable, length, connector type, etc., which helps to identify the cable type.

[0080] Finally, after collecting the first scattering parameters of the cable, the first scattering parameters can be stored in a target database for subsequent data analysis and feature extraction. The target database can be a local storage system, a cloud database, or a specially designed data storage software for organizing and managing measurement data from different cables. At the same time, the target database should have certain security, accessibility, and scalability to ensure that the scattering parameters of a large number of cables can be efficiently stored and retrieved. When storing the first scattering parameters of the cable to be identified, the first scattering parameters should be recorded together with other relevant information of the cable (such as type, length, connector type, etc.) so that they can be associated and compared in subsequent analysis.

[0081] The above steps ensure that comprehensive and accurate cable scattering parameters are collected, which helps the subsequent feature extraction, data processing and machine learning classification of cable types, thereby achieving efficient and accurate identification of communication cables.

[0082] Optionally, in this embodiment 1, Figure 2 It is a schematic diagram of the scattering parameters of an optional communication cable provided according to the first embodiment of the present application. Figure 2 The parameters of the coaxial cable as a two-port network are shown in Figure 1, including parameters such as S11 (reflection coefficient of the input port), S12 (transmission coefficient from the output port to the input port), S21 (transmission coefficient from the input port to the output port), and S22 (reflection coefficient of the output port). These parameters describe the performance of the cable at different frequencies, including reflection, transmission, and energy distribution between ports. The S parameters of the cable to be identified are measured within a preset frequency band, that is, the frequency range of 10 to 900 MHz. This frequency range covers the common operating frequency bands of communication cables, ensuring that the measurement data can fully reflect the characteristics of the cable. The measurement can be performed using a vector network analyzer (VNA), which provides accurate and reliable measurement results with its high precision and wide bandwidth characteristics. Through port 1 and port 2, the VNA sends signals to the cable and receives reflected and transmitted signals, thereby calculating the scattering parameters. a1 is the incident voltage wave at port 1, a2 is the incident voltage wave at port 2, b1 is the reflected voltage wave at port 1, and b2 is the reflected voltage wave at port 2.

[0083] Optionally, in this embodiment 1, Figure 3 It is a schematic diagram of an optional cable type identification process provided according to the first embodiment of the present application. Figure 3 The overall process of communication cable type identification is depicted. At the beginning, the scattering parameters of the cable to be identified are measured. The measurement results (i.e., the first scattering parameters mentioned above) are denoised, filtered, and normalized to improve data quality. Exemplarily, denoising can use wavelet denoising, filtering uses a bandpass filter consistent with a preset frequency range to ensure the validity and integrity of the data, and normalization can use a maximum-minimum normalization method to standardize the scattering parameters to a range of 0 to 1 to eliminate dimensional effects and improve the accuracy of subsequent feature analysis.

[0084] Then, the preprocessed data is subsequently used to extract wave propagation features, frequency domain features, and time domain features, and dimensionality reduction processing is performed respectively, from which key features are selected to obtain the above-mentioned target feature information. Exemplarily, the number of target feature information is set to 5 to maintain a balance between recognition accuracy and processing speed. Principal component analysis can effectively reduce redundant information in the data set and extract the most important features for cable type recognition, thereby improving system recognition efficiency and reducing computational complexity.

[0085] Secondly, the target feature information is input into the target recognition model for recognition, and the cable type recognition result is output. Among them, the target recognition model is a model trained based on the linear support vector machine (SVM) model. For example, the performance of the classifier can be optimized by adjusting the kernel function parameters, regularization parameters and penalty coefficients to ensure that the model can accurately classify different types of cables. Parameter optimization is a key step to improve the generalization ability of the model, especially the selection of the penalty coefficient, which directly affects the model's tolerance to misclassification and its adaptability to new data.

[0086] Figure 3 The flowchart in the figure shows in detail the entire process from measurement to identification, including scattering parameter measurement, data preprocessing, feature extraction, principal component analysis, support vector machine model construction, and cable type identification. Data is transferred and processed between each step, ensuring the consistency and accuracy from the original measurement data to the final identification result. The system design takes into account the purity and stability of the data and the accuracy of feature extraction. Through the high-precision measurement of the vector network analyzer, the comprehensive optimization of data preprocessing, and the efficient classification of the support vector machine model, the communication cable type can be quickly and accurately identified. The technical effect is reflected in improving the efficiency of network maintenance, reducing troubleshooting time, and ensuring communication quality. This identification method and system has significant benefits for the management of cables in communication networks, especially in application scenarios that require a large number of cable types to be quickly identified.

[0087] It should be noted that the steps shown in the flowcharts of the accompanying drawings can be executed in a computer system such as a set of computer executable instructions, and that, although a logical order is shown in the flowcharts, in some cases, the steps shown or described can be executed in an order different from that shown here.

[0088] Embodiment 2

[0089] The second embodiment of the present application also provides a device for identifying the type of a cable. It should be noted that the device for identifying the type of a cable in the second embodiment of the present application can be used to execute the method for identifying the type of a cable provided in the first embodiment of the present application. The device for identifying the type of a cable provided in the second embodiment of the present application is introduced below.

[0090] Figure 4 Schematic diagram of a cable type identification device according to Embodiment 2 of the present application. Figure 4 As shown, the device includes: a collection unit 401, a processing unit 402, an extraction unit 403 and a recognition unit 404.

[0091] Specifically, the collecting unit 401 is used to collect a first scattering parameter of the cable, wherein the first scattering parameter is a parameter collected within a preset frequency band.

[0092] The processing unit 402 is configured to process the noise in the first scattering parameter to obtain a second scattering parameter.

[0093] The extraction unit 403 is used to perform feature extraction on the second scattering parameter and perform dimensionality reduction processing on the extracted feature information to obtain target feature information.

[0094] The identification unit 404 is used to input the target feature information into the target identification model to identify the cable type of the cable, wherein the target identification model is a model obtained by training a preset support vector machine model using a training set.

[0095] The cable type identification device provided in the second embodiment of the present application collects the first scattering parameter of the cable through the collection unit 401, wherein the first scattering parameter is a parameter collected within a preset frequency band; the processing unit 402 processes the noise in the first scattering parameter to obtain the second scattering parameter; the extraction unit 403 extracts features from the second scattering parameter, and performs dimensionality reduction processing on the extracted feature information to obtain target feature information; the identification unit 404 inputs the target feature information into the target recognition model to identify the cable type of the cable, wherein the target recognition model is a model obtained by training a preset support vector machine model with a training set, which solves the problem in the related art that when identifying the cable type, it depends on simple signal feature extraction or manual experience judgment, which makes it difficult to accurately identify the cable type. By collecting the first scattering parameter of the cable to be identified and performing noise processing on the first scattering parameter, comprehensive information about the cable characteristics can be provided, and environmental noise and instrument errors introduced in the measurement process can be effectively removed, thereby improving the accuracy of identifying the cable type. At the same time, through feature extraction and dimensionality reduction processing, the second scattering parameter is converted into target feature information containing key information, which can significantly reduce the amount of calculation in the subsequent classification process, while maintaining a high recognition accuracy and speeding up the recognition speed. By adopting a target recognition model based on a support vector machine algorithm to identify the cable type, the cable type of the cable to be identified can be accurately identified, and at the same time, it has a strong generalization ability, thereby achieving the effect of improving the adaptability and reliability of identifying the cable type.

[0096] Optionally, in the cable type identification device provided in Example 2 of the present application, the above-mentioned extraction unit 403 includes: an extraction subunit, used to extract the frequency domain characteristics of the second scattering parameter and the time domain characteristics of the second scattering parameter respectively; a calculation subunit, used to calculate the wave propagation characteristics of the second scattering parameter at a preset frequency; a first processing subunit, used to use a preset algorithm to perform dimensionality reduction processing on the wave propagation characteristics, frequency domain characteristics and time domain characteristics respectively to obtain target feature information.

[0097] Optionally, in the cable type identification device provided in Example 2 of the present application, the above-mentioned calculation subunit includes: a first calculation module, used to calculate a third scattering parameter based on a preset algorithm according to a preset frequency, the cable length of the cable, a second scattering parameter and the impedance wave of the cable; a second calculation module, used to calculate the wave propagation characteristics based on the third scattering parameter and the incident voltage wave of the cable.

[0098] Optionally, in the cable type identification device provided in Example 2 of the present application, the above-mentioned processing sub-unit includes: a construction module, which is used to respectively construct a first matrix corresponding to the wave propagation characteristics, a first matrix corresponding to the frequency domain characteristics, and a first matrix corresponding to the time domain characteristics to obtain multiple first matrices; a third calculation module, which is used to calculate the covariance matrix of the first matrix for each first matrix in the multiple first matrices; a decomposition module, which is used to perform eigenvalue decomposition on the covariance matrix to obtain multiple eigenvalues ​​corresponding to each first matrix and an eigenvector corresponding to each eigenvalue in the multiple eigenvalues; a first determination module, which is used to sort the multiple eigenvalues ​​corresponding to each first matrix according to the numerical size, and determine the characteristic information of each first matrix after dimensionality reduction with the eigenvectors corresponding to the first N eigenvalues ​​after sorting; a second determination module, which is used to determine the target characteristic information based on the characteristic information of each first matrix after dimensionality reduction in the multiple first matrices.

[0099] Optionally, in the cable type identification device provided in Example 2 of the present application, the above-mentioned device also includes: an acquisition unit, used to obtain historical scattering parameters of any cable and extract historical feature information of the historical scattering parameters; a training unit, used to use the historical feature information to train a preset support vector machine model to obtain a first identification model, wherein the preset support vector machine model is a linear support vector machine using a target kernel function; an optimization unit, used to optimize the first identification model using a cross-validation algorithm and an iterative optimization algorithm to obtain a target identification model.

[0100] Optionally, in the cable type identification device provided in Example 2 of the present application, the above-mentioned processing unit 402 includes: a second processing sub-unit, used to perform denoising processing on the first scattering parameter to obtain a fourth scattering parameter; a third processing sub-unit, used to perform filtering processing on the fourth scattering parameter to obtain a fifth scattering parameter; and a fourth processing sub-unit, used to perform normalization processing on the fifth scattering parameter to obtain a second scattering parameter.

[0101] Optionally, in the cable type identification device provided in Example 2 of the present application, the above-mentioned acquisition unit 401 includes: a configuration subunit, used to configure equipment parameters of a test device and connect the test device to the cable; a collection subunit, used to collect first scattering parameters through the test device connected to the cable; the above-mentioned device also includes: a storage unit, used to store the first scattering parameters in a target database after collecting the first scattering parameters of the cable.

[0102] The cable type identification device includes a processor and a memory. The above-mentioned acquisition unit 401, processing unit 402, extraction unit 403 and identification unit 404 are all stored in the memory as program units, and the processor executes the above-mentioned program units stored in the memory to realize corresponding functions.

[0103] The processor includes a kernel, which calls the corresponding program unit from the memory. One or more kernels can be set, and the accuracy of identifying the cable type can be improved by adjusting the kernel parameters.

[0104] The memory may include non-permanent memory in a computer-readable medium, random access memory (RAM) and / or non-volatile memory, such as read-only memory (ROM) or flash memory (nash RAM), and the memory includes at least one memory chip.

[0105] Embodiment 3 of the present invention provides a computer-readable storage medium on which a program is stored. When the program is executed by a processor, a method for identifying a cable type is implemented.

[0106] A fourth embodiment of the present invention provides a processor, which is used to run a program, wherein the program executes a method for identifying a cable type when the program is running.

[0107] like Figure 5As shown, embodiment 5 of the present invention provides an electronic device, the device includes a processor, a memory, and a program stored in the memory and executable on the processor, and the processor implements the following steps when executing the program: collecting a first scattering parameter of the cable, wherein the first scattering parameter is a parameter collected within a preset frequency band; processing the noise in the first scattering parameter to obtain a second scattering parameter; performing feature extraction on the second scattering parameter, and performing dimensionality reduction processing on the extracted feature information to obtain target feature information; inputting the target feature information into a target recognition model to identify the cable type of the cable, wherein the target recognition model is a model obtained by training a preset support vector machine model using a training set.

[0108] When the processor executes the program, the following steps are also implemented: feature extraction is performed on the second scattering parameter, and dimension reduction processing is performed on the extracted feature information to obtain target feature information, including: extracting frequency domain features of the second scattering parameter and time domain features of the second scattering parameter respectively; calculating the wave propagation features of the second scattering parameter at a preset frequency; and using a preset algorithm to perform dimension reduction processing on the wave propagation features, frequency domain features and time domain features respectively to obtain target feature information.

[0109] When the processor executes the program, the following steps are also implemented: calculating the wave propagation characteristics of the second scattering parameter at a preset frequency, including: calculating the third scattering parameter based on a preset algorithm according to the preset frequency, the cable length of the cable, the second scattering parameter and the impedance wave of the cable; calculating the wave propagation characteristics based on the third scattering parameter and the incident voltage wave of the cable.

[0110] When the processor executes the program, the following steps are also implemented: using a preset algorithm to perform dimensionality reduction processing on the wave propagation characteristics, frequency domain characteristics and time domain characteristics respectively to obtain target feature information, including: constructing a first matrix corresponding to the wave propagation characteristics, a first matrix corresponding to the frequency domain characteristics and a first matrix corresponding to the time domain characteristics respectively to obtain multiple first matrices; for each first matrix in the multiple first matrices, calculating the covariance matrix of the first matrix; performing eigenvalue decomposition on the covariance matrix to obtain multiple eigenvalues ​​corresponding to each first matrix and an eigenvector corresponding to each eigenvalue in the multiple eigenvalues; sorting the multiple eigenvalues ​​corresponding to each first matrix according to the numerical value, and determining the feature information of each first matrix after dimensionality reduction by the eigenvectors corresponding to the first N eigenvalues ​​after sorting; and determining the target feature information based on the feature information of each first matrix after dimensionality reduction in the multiple first matrices.

[0111] When the processor executes the program, the following steps are also implemented: the above-mentioned target recognition model is trained by the following steps: obtaining the historical scattering parameters of any cable, and extracting the historical feature information of the historical scattering parameters; using the historical feature information to train a preset support vector machine model to obtain a first recognition model, wherein the preset support vector machine model is a linear support vector machine using a target kernel function; using a cross-validation algorithm and an iterative optimization algorithm to optimize the first recognition model to obtain a target recognition model.

[0112] When the processor executes the program, the following steps are also implemented: processing the noise in the first scattering parameter to obtain the second scattering parameter, including: performing denoising processing on the first scattering parameter to obtain the fourth scattering parameter; performing filtering processing on the fourth scattering parameter to obtain the fifth scattering parameter; and performing normalization processing on the fifth scattering parameter to obtain the second scattering parameter.

[0113] When the processor executes the program, the following steps are also implemented: collecting the first scattering parameter of the cable, including: configuring the equipment parameters of the test equipment and connecting the test equipment to the cable; collecting the first scattering parameter through the test equipment connected to the cable; after collecting the first scattering parameter of the cable, the above method also includes: storing the first scattering parameter in a target database.

[0114] The devices in this article can be servers, PCs, PADs, mobile phones, etc.

[0115] The present application also provides a computer program product, which, when executed on a data processing device, is suitable for executing a program that is initialized with the following method steps: collecting a first scattering parameter of a cable, wherein the first scattering parameter is a parameter collected within a preset frequency band; processing the noise in the first scattering parameter to obtain a second scattering parameter; performing feature extraction on the second scattering parameter, and performing dimensionality reduction processing on the extracted feature information to obtain target feature information; inputting the target feature information into a target recognition model to identify the cable type of the cable, wherein the target recognition model is a model obtained by training a preset support vector machine model using a training set.

[0116] When executed on a data processing device, it is also suitable for executing an initialized program having the following method steps: extracting features of the second scattering parameter, and performing dimensionality reduction processing on the extracted feature information to obtain target feature information, including: extracting the frequency domain features and the time domain features of the second scattering parameter respectively; calculating the wave propagation features of the second scattering parameter at a preset frequency; and using a preset algorithm to perform dimensionality reduction processing on the wave propagation features, frequency domain features and time domain features respectively to obtain target feature information.

[0117] When executed on a data processing device, it is also suitable for executing an initialized program having the following method steps: calculating the wave propagation characteristics of the second scattering parameter at a preset frequency, including: calculating the third scattering parameter based on a preset algorithm according to the preset frequency, the cable length of the cable, the second scattering parameter and the impedance wave of the cable; calculating the wave propagation characteristics based on the third scattering parameter and the incident voltage wave of the cable.

[0118] When executed on a data processing device, it is also suitable for executing an initialized program having the following method steps: using a preset algorithm to perform dimensionality reduction processing on wave propagation characteristics, frequency domain characteristics and time domain characteristics respectively to obtain target feature information, including: constructing a first matrix corresponding to the wave propagation characteristics, a first matrix corresponding to the frequency domain characteristics and a first matrix corresponding to the time domain characteristics respectively to obtain multiple first matrices; for each first matrix in the multiple first matrices, calculating the covariance matrix of the first matrix; performing eigenvalue decomposition on the covariance matrix to obtain multiple eigenvalues ​​corresponding to each first matrix and an eigenvector corresponding to each eigenvalue in the multiple eigenvalues; sorting the multiple eigenvalues ​​corresponding to each first matrix according to the numerical size, and determining the feature information of each first matrix after dimensionality reduction by the eigenvectors corresponding to the first N eigenvalues ​​after sorting; determining the target feature information based on the feature information of each first matrix after dimensionality reduction in the multiple first matrices.

[0119] When executed on a data processing device, it is also suitable for executing a program initialized with the following method steps: the above-mentioned target recognition model is trained by the following steps: obtaining the historical scattering parameters of any cable, and extracting the historical feature information of the historical scattering parameters; using the historical feature information to train a preset support vector machine model to obtain a first recognition model, wherein the preset support vector machine model is a linear support vector machine using a target kernel function; using a cross-validation algorithm and an iterative optimization algorithm to optimize the first recognition model to obtain a target recognition model.

[0120] When executed on a data processing device, the method is also suitable for executing a program that is initialized with the following method steps: processing the noise in the first scattering parameter to obtain the second scattering parameter, including: performing denoising processing on the first scattering parameter to obtain the fourth scattering parameter; performing filtering processing on the fourth scattering parameter to obtain the fifth scattering parameter; and performing normalization processing on the fifth scattering parameter to obtain the second scattering parameter.

[0121] When executed on a data processing device, the method is also suitable for executing a program that is initialized with the following method steps: collecting the first scattering parameter of the cable, including: configuring the device parameters of the test device, and connecting the test device to the cable; collecting the first scattering parameter through the test device connected to the cable; after collecting the first scattering parameter of the cable, the method further includes: storing the first scattering parameter in a target database.

[0122] Those skilled in the art will appreciate that the embodiments of the present application may be provided as methods, systems, or computer program products. Therefore, the present application may adopt the form of a complete hardware embodiment, a complete software embodiment, or an embodiment in combination with software and hardware. Moreover, the present application may adopt the form of a computer program product implemented in one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) that include computer-usable program code.

[0123] The present application is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of the present application. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0124] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0125] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0126] In a typical configuration, a computing device includes one or more processors (CPU), input / output interfaces, network interfaces, and memory.

[0127] The memory may include non-permanent memory in a computer-readable medium, random access memory (RAM) and / or non-volatile memory in the form of read-only memory (ROM) or flash RAM. The memory is an example of a computer-readable medium.

[0128] Computer readable media include permanent and non-permanent, removable and non-removable media that can be implemented by any method or technology to store information. Information can be computer readable instructions, data structures, program modules or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technology, compact disk read-only memory (CD-ROM), digital versatile disk (DVD) or other optical storage, magnetic cassettes, magnetic tape disk storage or other magnetic storage devices or any other non-transmission media that can be used to store information that can be accessed by a computing device. As defined herein, computer readable media does not include temporary computer readable media (transitory media), such as modulated data signals and carrier waves.

[0129] It should also be noted that the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, commodity or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, commodity or device. In the absence of more restrictions, the elements defined by the sentence "comprises a ..." do not exclude the existence of other identical elements in the process, method, commodity or device including the elements.

[0130] Those skilled in the art will appreciate that the embodiments of the present application may be provided as methods, systems or computer program products. Therefore, the present application may adopt the form of a complete hardware embodiment, a complete software embodiment or an embodiment in combination with software and hardware. Moreover, the present application may adopt the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) that contain computer-usable program code.

[0131] The above are only embodiments of the present application and are not intended to limit the present application. For those skilled in the art, the present application may have various changes and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application should be included within the scope of the claims of the present application.

Claims

1. A method for identifying cable types, characterized in that: include: Collecting a first scattering parameter of the cable, wherein the first scattering parameter is a parameter collected within a preset frequency band; Processing the noise in the first scattering parameter to obtain a second scattering parameter; Performing feature extraction on the second scattering parameter, and performing dimensionality reduction processing on the extracted feature information to obtain target feature information; The target feature information is input into a target recognition model to identify the cable type of the cable, wherein the target recognition model is a model obtained by training a preset support vector machine model using a training set.

2. The method according to claim 1, characterized in that Performing feature extraction on the second scattering parameter and performing dimensionality reduction processing on the extracted feature information to obtain target feature information includes: extracting frequency domain features of the second scattering parameter and time domain features of the second scattering parameter respectively; calculating a wave propagation characteristic of the second scattering parameter at a preset frequency; A preset algorithm is used to perform dimensionality reduction processing on the wave propagation characteristics, the frequency domain characteristics and the time domain characteristics respectively to obtain the target feature information.

3. The method according to claim 2, characterized in that Calculating the wave propagation characteristics of the second scattering parameter at a preset frequency includes: Calculating a fourth scattering parameter based on a preset algorithm according to the preset frequency, the cable length of the cable, the second scattering parameter, and the impedance wave of the cable; The wave propagation characteristic is calculated based on the fourth scattering parameter and an incident voltage wave of the cable.

4. The method according to claim 2, characterized in that: The wave propagation characteristics, the frequency domain characteristics and the time domain characteristics are respectively subjected to dimensionality reduction processing by using a preset algorithm to obtain the target characteristic information, including: Respectively constructing a first matrix corresponding to the wave propagation feature, a first matrix corresponding to the frequency domain feature, and a first matrix corresponding to the time domain feature to obtain a plurality of first matrices; For each first matrix among the plurality of first matrices, calculating a covariance matrix of the first matrix; Performing eigenvalue decomposition on the covariance matrix to obtain a plurality of eigenvalues ​​corresponding to each first matrix and an eigenvector corresponding to each eigenvalue in the plurality of eigenvalues; Sorting multiple eigenvalues ​​corresponding to each first matrix according to their numerical values, and determining the eigenvectors corresponding to the first N eigenvalues ​​after the sorting to determine the eigeninformation of each first matrix after dimensionality reduction; The target feature information is determined according to feature information of each first matrix in the multiple first matrices after dimension reduction.

5. The method according to claim 1, characterized in that: The target recognition model is trained by the following steps: Obtaining historical scattering parameters of any cable, and extracting historical characteristic information of the historical scattering parameters; The preset support vector machine model is trained using the historical feature information to obtain a first recognition model, wherein the preset support vector machine model is a linear support vector machine using a target kernel function; The first recognition model is optimized by using a cross-validation algorithm and an iterative optimization algorithm to obtain the target recognition model.

6. The method according to claim 1, characterized in that Processing the noise in the first scattering parameter to obtain a second scattering parameter includes: performing denoising processing on the first scattering parameter to obtain a fourth scattering parameter; performing filtering processing on the fourth scattering parameter to obtain a fifth scattering parameter; The fifth scattering parameter is normalized to obtain the second scattering parameter.

7. The method according to claim 1, characterized in that Collecting a first scattering parameter of the cable, comprising: configuring equipment parameters of a test device, and connecting the test device to the cable; collecting the first scattering parameter through the test device connected to the cable; After collecting the first scattering parameter of the cable, the method further includes: storing the first scattering parameter in a target database.

8. A cable type identification device, characterized in that: include: A collecting unit, used for collecting a first scattering parameter of the cable, wherein the first scattering parameter is a parameter collected within a preset frequency band; a processing unit, configured to process the noise in the first scattering parameter to obtain a second scattering parameter; An extraction unit, configured to perform feature extraction on the second scattering parameter, and perform dimensionality reduction processing on the extracted feature information to obtain target feature information; The identification unit is used to input the target feature information into a target identification model to identify the cable type of the cable, wherein the target identification model is a model obtained by training a preset support vector machine model using a training set.

9. A computer-readable storage medium, characterized in that: The computer-readable storage medium includes stored computer instructions, wherein when the computer instructions are executed by a processor, the cable type identification method according to any one of claims 1 to 7 is implemented.

10. An electronic device, characterized in that: It includes one or more processors and a memory, wherein the memory is used to store one or more programs, wherein when the one or more programs are executed by the one or more processors, the one or more processors implement the cable type identification method described in any one of claims 1 to 7.

Images