Evaluation method, device and detection system for insulation aging state of cable

Abstract

The invention provides a cable insulation aging state evaluation method and device and a detection system. The method comprises the following steps: acquiring near-infrared spectrum data which is a light intensity value of a cable for absorbing near-infrared light; according to the near infrared spectrum data, the crystallinity of the cable is determined, and the crystallinity is the proportion of the volume of a crystallization area of a polymer material of the cable to the material volume of the whole cable; according to the crystallinity and a first preset mapping relation, the aging index of the cable is determined, and the first preset mapping relation is the mapping relation between the crystallinity and the aging index; and when the aging index is greater than a first preset index threshold, controlling the alarm device to give an alarm. The method solves the problem that the aging state of the cable cannot be accurately evaluated in the prior art.

Description

Technical Field

[0001] The present application relates to the field of cable detection technology, and in particular to a method for evaluating the aging state of cable insulation, an evaluation device for the aging state of cable insulation, a computer program product, and a detection system. Background Art

[0002] The power system is a crucial pillar supporting the high-quality development of my country's modernization drive. With the gradual advancement of social development, the nation's annual electricity consumption has grown rapidly, driving a corresponding increase in demand for power cables. The development of green, low-carbon insulation materials, such as polypropylene (PP), has become a trend in the cable industry. Furthermore, cable insulation materials inevitably develop defects or age during manufacturing, installation, and operation, leading to irreversible damage to their physical and chemical structure and insulation properties, impacting the reliability and service life of cable lines.

[0003] Currently, methods for testing the aging status of high-voltage cable insulation primarily include broadband impedance spectroscopy, DC leakage current testing, ultra-low frequency dielectric loss testing, and partial discharge testing. While these methods can be used to detect aging in high-voltage cable insulation, they have numerous limitations, such as restrictions on installation environments and operating conditions, lengthy testing cycles, and high testing costs. Other testing methods rely on slicing and sampling cable insulation, but these methods cannot accurately assess the aging status of cables. Summary of the Invention

[0004] The main purpose of this application is to provide a method for evaluating the aging state of cable insulation, an evaluation device for the aging state of cable insulation, a computer program product and a detection system, so as to at least solve the problem in the prior art that the aging state of the cable cannot be accurately evaluated.

[0005] In order to achieve the above-mentioned purpose, according to one aspect of the present application, a method for evaluating the aging status of cable insulation is provided, comprising: obtaining near-infrared spectral data, wherein the near-infrared spectral data is the light intensity value of the cable's absorption of near-infrared light; determining the crystallinity of the cable based on the near-infrared spectral data, wherein the crystallinity is the ratio of the volume of the crystalline region of the polymer material of the cable to the material volume of the entire cable; determining the aging index of the cable based on the crystallinity and a first preset mapping relationship, wherein the first preset mapping relationship is the mapping relationship between the crystallinity and the aging index; and controlling an alarm device to sound an alarm when the aging index is greater than a first preset index threshold.

[0006] Optionally, determining the crystallinity of the cable according to the near-infrared spectral data includes: preprocessing the near-infrared spectral data to obtain the preprocessed near-infrared spectral data, wherein the preprocessing method includes one or more of data smoothing, denoising, CARS algorithm optimization, derivative method, and wavelet transformation; and testing and obtaining the corresponding crystallinity of the cable according to the preprocessed near-infrared spectral data.

[0007] Optionally, based on the preprocessed near-infrared spectral data, the corresponding crystallinity of the cable is tested, including: obtaining a first recognition model, wherein the first recognition model is one of a PLS model, an MLR model, and an SVM model; historical near-infrared spectral data and corresponding crystallinity labels are combined into a first training set, and the first training set is used to train the first recognition model to obtain a crystallization recognition model, wherein the crystallinity label is the crystallinity index of the cable in the first training set; the preprocessed near-infrared spectral data is input into the crystallization recognition model to obtain the crystallinity corresponding to the preprocessed near-infrared spectral data.

[0008] Optionally, after determining the crystallinity of the cable based on the near-infrared spectral data, the method further includes: obtaining a second recognition model, wherein the second recognition model is one of an ANN model, a random forest model, and a CNN model; forming historical crystallinity and corresponding aging status labels into a second training set, and using the second training set to train the second recognition model to obtain an aging recognition model, wherein the aging status label is the aging status index of the cable in the second training set; and inputting the crystallinity into the aging recognition model to obtain the aging index corresponding to the crystallinity.

[0009] Optionally, after determining the aging index of the cable based on the crystallinity, the method further includes: determining the maximum historical temperature based on all historical temperatures of the cable, the historical temperature being the temperature of the cable measured at a historical moment; determining the damage index of the cable based on the maximum historical temperature of the cable and a second preset mapping relationship, wherein the second preset mapping relationship is a mapping relationship between the temperature of the cable and the damage index; determining the comprehensive aging index of the cable based on the crystallinity and the damage index; and controlling the alarm device to alarm when the comprehensive aging index is greater than a second preset index threshold.

[0010] Optionally, before determining the maximum historical temperature based on all historical temperatures of the cable, the method further includes: obtaining a third recognition model, wherein the third recognition model is one of an LSTM model, a PCA model, and a KNN model; forming historical Raman spectral data and corresponding temperature labels into a third training set, and using the third training set to train the third recognition model to obtain a temperature recognition model, wherein the temperature label is the temperature index of the cable in the third training set; and inputting Raman spectral data into the temperature recognition model to obtain the temperature corresponding to the Raman spectral data.

[0011] Optionally, the comprehensive aging index of the cable is determined based on the crystallinity and the damage index, including: obtaining a first weight coefficient, wherein the first weight coefficient is a preset weight coefficient of the crystallinity; obtaining a second weight coefficient, wherein the second weight coefficient is a preset weight coefficient of the damage index; obtaining the first preset mapping relationship, wherein the first preset mapping relationship is the relationship between the crystallinity and the aging index; obtaining a third preset mapping relationship, wherein the third preset mapping relationship is the relationship between the damage index and the aging index; according to the first preset mapping relationship, determining the aging index corresponding to the crystallinity as a first target aging index; according to the third preset mapping relationship, determining the aging index corresponding to the damage index as a second target aging index; calculating the weighted average of the first weight coefficient, the second weight coefficient, the first target aging index and the second target aging index to obtain the comprehensive aging index.

[0012] According to another aspect of the present application, a device for evaluating the aging status of cable insulation is provided, comprising: a first acquisition unit for acquiring near-infrared spectral data, wherein the near-infrared spectral data is the light intensity value of the near-infrared light absorbed by the cable; a first determination unit for determining the crystallinity of the cable based on the near-infrared spectral data, wherein the crystallinity is the ratio of the volume of the crystalline region of the polymer material of the cable to the material volume of the entire cable; a second determination unit for determining the aging index of the cable based on the crystallinity and a first preset mapping relationship, wherein the first preset mapping relationship is the mapping relationship between the crystallinity and the aging index; and a first control unit for controlling an alarm device to sound an alarm when the aging index is greater than a first preset index threshold.

[0013] According to another aspect of the present application, a computer program product is provided, comprising a computer program, wherein when the computer program is executed by a processor, the computer program implements the steps of any one of the methods for evaluating the aging state of cable insulation.

[0014] According to another aspect of the present application, a detection system is provided, comprising: a cable; a near-infrared spectrometer; a Raman spectrometer; and a control device, which is communicatively connected to the near-infrared spectrometer and the Raman spectrometer, respectively, and the control device is used to execute any one of the methods for evaluating the aging status of cable insulation.

[0015] The technical solution of the present application is applied, and near-infrared spectroscopy technology is used to detect the light intensity value of the cable's near-infrared light absorption, and near-infrared spectral data is obtained. Near-infrared spectroscopy technology does not have high requirements on environmental conditions and is suitable for on-site detection. It is no longer limited by the environment. As the cable ages, the polymer material will degrade, oxidize, crack, and other phenomena, resulting in changes in the crystallinity of the material. The size of the crystalline region of the polymer will directly affect the change in absorbance. These changes will be directly reflected in the near-infrared spectral data, forming spectral characteristics. Therefore, the changes in the crystallinity of the material can be accurately captured through near-infrared spectral data. The aging index is a quantitative indicator used to express the aging status of the cable. There is a mapping relationship between the crystallinity and the aging index. Different crystallinity corresponds to different aging states. Through this embodiment, when detecting the cable on-site, there is no need to conduct experiments, and it is not restricted by the environment. The limitations of traditional detection methods are overcome, and the aging status of the cable can be accurately evaluated. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] The drawings that constitute part of this application are used to provide a further understanding of this application. The illustrative embodiments of this application and their descriptions are used to explain this application and do not constitute an improper limitation on this application. In the drawings:

[0017] Figure 1 A hardware structure block diagram of a mobile terminal for performing a method for evaluating cable insulation aging status provided in an embodiment of the present application is shown;

[0018] Figure 2 A schematic flow chart of a method for evaluating the aging state of cable insulation provided in accordance with an embodiment of the present application is shown;

[0019] Figure 3 A schematic flow chart showing another method for evaluating the aging state of cable insulation is provided;

[0020] Figure 4 A schematic diagram showing the trend of crystallinity of the target sample with aging time;

[0021] Figure 5 A schematic diagram showing the number of iterations of the near-infrared spectrum of the target sample based on the CARS algorithm;

[0022] Figure 6A schematic diagram showing the near-infrared spectrum of the target sample based on the CARS algorithm is shown;

[0023] Figure 7 A schematic diagram showing the correlation curve between the crystallinity of the target sample during the aging process and the near-infrared spectrum after optimization;

[0024] Figure 8 A schematic diagram showing the predicted values ​​and errors of the predicted sample crystallinity;

[0025] Figure 9 A schematic diagram showing the predicted trends of sample crystallinity, elongation at break, and breakdown field strength with aging time;

[0026] Figure 10 A structural block diagram of a device for evaluating the aging state of cable insulation provided according to an embodiment of the present application is shown.

[0027] The above drawings include the following reference numerals:

[0028] 102. Processor; 104. Memory; 106. Transmission device; 108. Input / output device. DETAILED DESCRIPTION

[0029] It should be noted that, in the absence of conflict, the embodiments and features of the embodiments in this 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.

[0030] In order to enable those skilled in the art to better understand the present invention, the following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments in the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts should fall within the scope of protection of this application.

[0031] 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 herein. 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 that includes 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.

[0032] As introduced in the background technology, the existing technology cannot accurately evaluate the aging status of the cable. To solve the above problem, the embodiments of the present application provide a method for evaluating the aging status of cable insulation, an evaluation device for the aging status of cable insulation, a computer program product and a detection system.

[0033] The technical solutions in the embodiments of the present invention will be described clearly and completely below with reference to the accompanying drawings in the embodiments of the present invention.

[0034] The method embodiments provided in the embodiments of the present application can be executed in a mobile terminal, a computer terminal or a similar computing device. Taking running on a mobile terminal as an example, Figure 1 FIG. 1 is a hardware structure block diagram of a mobile terminal for a method for evaluating cable insulation aging status according to an embodiment of the present invention. Figure 1 As shown, the mobile terminal may include one or more ( Figure 1 Only one is shown) a processor 102 (the processor 102 may include but is not limited to a microprocessor MCU or a programmable logic device FPGA and other processing devices) and a memory 104 for storing data, wherein the mobile terminal may also include a transmission device 106 and an input and output device 108 for communication functions. It will be understood by those skilled in the art that Figure 1 The structure shown is only for illustration and does not limit the structure of the mobile terminal. Figure 1 More or fewer components than shown, or with Figure 1 Different configurations shown.

[0035] The memory 104 can be used to store computer programs, such as software programs and modules of application software, such as the computer program corresponding to the device information display method in the embodiment of the present invention. The processor 102 executes various functional applications and data processing by running the computer program stored in the memory 104, that is, implementing the above-mentioned method. The memory 104 may include a high-speed random access memory and may also include a non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memory. In some examples, the memory 104 may further include a memory remotely located relative to the processor 102, and these remote memories can be connected to the mobile terminal via a network. Examples of the above-mentioned networks include but are not limited to the Internet, corporate intranets, local area networks, mobile communication networks, and combinations thereof. The transmission device 106 is used to receive or send data via a network. Specific examples of the above-mentioned network may include a wireless network provided by the mobile terminal's communication provider. In one example, the transmission device 106 includes a network adapter (Network Interface Controller, abbreviated as NIC), which can be connected to other network devices via a base station to communicate with the Internet. In one example, the transmission device 106 may be a radio frequency (RF) module, which is used to communicate with the Internet wirelessly.

[0036] In this embodiment, a method for evaluating the aging state of cable insulation running on a mobile terminal, a computer terminal or a similar computing device is provided. It should be noted that the steps shown in the flowchart of the accompanying drawings can be executed in a computer system such as a set of computer executable instructions, and although a logical order is shown in the flowchart, in some cases, the steps shown or described can be executed in an order different from that shown here.

[0037] Figure 2 FIG. 1 is a flow chart of a method for evaluating the aging state of cable insulation according to an embodiment of the present application. Figure 2 As shown, the method includes the following steps:

[0038] Step S201, obtaining near-infrared spectrum data, wherein the near-infrared spectrum data is the light intensity value of the near-infrared light absorbed by the cable;

[0039] Specifically, near-infrared spectral data is obtained using a near-infrared spectrometer. Using a near-infrared spectrometer, spectral information of cable polymer materials is obtained. This information can reflect the cable material's absorption characteristics of near-infrared light, thereby capturing the material's microstructural changes during aging. The near-infrared spectrum covers the spectral region where the material's molecules vibrate and rotate, and can accurately depict the state of the chemical bonds within the polymer material. The chemical composition and structure of cable polymer materials (such as polypropylene (PP) and polyethylene (PE)) change during aging, and these changes manifest as changes in the intensity or positional shifts of specific absorption peaks in the near-infrared spectrum.

[0040] Step S202, determining the crystallinity of the cable based on the near-infrared spectrum data, wherein the crystallinity is the ratio of the volume of the crystalline region of the polymer material of the cable to the volume of the entire material of the cable;

[0041] The polymer material includes one or more of polypropylene, polyethylene, cross-linked polyethylene, and rubber, and the crystalline region is a region where the polymer material forms crystals on the surface of the cable.

[0042] Chemometric analysis of near-infrared spectral data allows us to determine the crystallinity of cable polymer materials. This ratio reflects the distribution of crystalline and amorphous regions within the material and is a key parameter for assessing cable aging. Crystallinity is a crucial material property that directly impacts the strength, ductility, and electrical insulation properties of cables. As polymer materials age, their crystallinity changes, resulting in characteristic absorption peaks in the near-infrared spectrum.

[0043] Step S203, determining the aging index of the cable according to the crystallinity and a first preset mapping relationship, wherein the first preset mapping relationship is a mapping relationship between the crystallinity and the aging index;

[0044] Specifically, by comparing the crystallinity determined above with a pre-set aging index mapping table, this embodiment can calculate a comprehensive aging index for the cable. This index comprehensively considers the impact of the crystallinity of the cable's polymer material on its aging state. The aging index is established based on extensive experimental data and statistical analysis. It correlates the crystallinity of the cable with the degree of aging, forming a quantitative assessment standard. This mapping relationship may have been pre-established through experimental research and machine learning techniques, ensuring that the conversion between crystallinity and aging index is both accurate and reliable, reflecting the true condition of cable aging.

[0045] Step S204: When the aging index is greater than a first preset index threshold, the alarm device is controlled to sound an alarm.

[0046] Specifically, when the calculated aging index exceeds a preset warning threshold, this embodiment automatically activates the alarm system, promptly notifies the power system maintenance personnel of the health risks that the cable may face, and promotes immediate maintenance or replacement decisions. The first preset index threshold is set based on the performance limit of the cable polymer material and the power system operation safety standard. It represents that the degree of cable aging has reached a critical point that may pose a threat to the system operation. By real-time monitoring of the aging index, once its value exceeds the threshold, the alarm device is immediately activated and a warning signal is issued, prompting maintenance personnel to intervene quickly to inspect and perform necessary maintenance on the cable. This embodiment can issue an early warning when the aging degree of the cable approaches this threshold. For example, if the first preset index threshold is set to 0.65 (it can also be any other feasible value), it means that once the aging index exceeds this value, it will be considered that the aging degree of the cable may affect its normal function.

[0047] Near-infrared spectroscopy technology identifies the structural characteristics of a sample by detecting the sample's absorption characteristics of near-infrared light. In this solution, near-infrared spectroscopy technology is used to detect the light intensity value of the cable's absorption of near-infrared light, and near-infrared spectral data is obtained. Near-infrared spectroscopy technology has low requirements for environmental conditions and is suitable for on-site detection. It is no longer limited by the environment. As the cable ages, the polymer material will degrade, oxidize, crack, and other phenomena will occur, resulting in changes in the crystallinity of the material. The size of the crystalline region of the polymer will directly affect the change in absorbance. These changes will be directly reflected in the near-infrared spectral data, forming spectral characteristics. Therefore, the changes in the crystallinity of the material can be accurately captured through near-infrared spectral data. The aging index is a quantitative indicator used to express the aging status of the cable. There is a mapping relationship between crystallinity and aging index. Different crystallinity corresponds to different aging states. Through this embodiment, when detecting the cable on-site, there is no need to conduct tests and it is not restricted by the environment. It overcomes the limitations of traditional detection methods, and thus the aging status of the cable can be accurately evaluated.

[0048] Specifically, currently available methods for testing the insulation quality and monitoring the aging status of high-voltage cables primarily include broadband impedance spectroscopy, DC leakage current testing, ultra-low frequency dielectric loss testing, partial discharge testing, and AC withstand voltage testing. These methods are currently primarily used to detect the aging status of XLPE high-voltage cable insulation and suffer from numerous limitations, such as restrictions on installation and operating conditions, lengthy testing cycles, and high testing costs. Further optimization is needed for the testing of PP high-voltage cable insulation, and research is urgently needed on alternative testing methods to enable rapid, efficient, and accurate testing of polypropylene cable insulation. Current methods are time-consuming and labor-intensive when testing damaged power cables, and lack intelligent testing applications.

[0049] Near-infrared spectroscopy has obvious advantages in testing the performance of polyolefin polymers. Compared with traditional testing methods, this method is fast, efficient, low-cost and highly accurate. In addition, the decline in the insulation performance of PP during damage or aging is mainly attributed to irreversible changes in the physical and chemical composition and structure, and the key information of chemical components related to the PP structure (such as alkyl groups) is also distributed throughout the near-infrared spectrum. Therefore, the microstructural changes of PP can be reflected through the near-infrared spectrum. Changes in microstructure regulate changes in macroscopic properties. Crystallinity is closely related to various insulating properties of PP insulation. This example shows the correlation between crystallinity and the elongation at break and AC breakdown field strength of PP insulation. After normalization, the change trends are basically the same. The degree of degradation of macroscopic performance can be judged based on the value of crystallinity, and the macroscopic performance can vividly characterize the aging state of cable insulation. Therefore, this method can evaluate the aging state of insulation.

[0050] Near-infrared spectroscopy technology can reflect changes in the microscopic molecular structure of polyolefin polymer materials (such as functional groups, molecular configurations, etc.) and establish correlations with macroscopic properties (such as electrical properties, etc.), making it suitable for material performance prediction and evaluation. Near-infrared spectroscopy analysis is fast, non-destructive, does not require complex pre-processing, and is applicable to a variety of working environments. When combined with modern chemometric methods, it can achieve high-precision and sensitive quantitative and qualitative analysis. During damage or aging, PP cables undergo irreversible changes in their physical and chemical composition and structure, and the key information of these structurally related chemical components (such as alkyl groups) is distributed throughout the wavelength range of the near-infrared spectrum. The absorption peak intensity of the characteristic band in the near-infrared spectrum will change with changes in the structure. Using structural changes as a bridge, the correlation between the near-infrared spectrum and crystallinity is constructed to achieve performance prediction based on near-infrared spectroscopy. Therefore, it is reasonable and feasible to predict the crystallinity of PP insulation by near-infrared spectroscopy.

[0051] Specifically, near-infrared spectroscopy technology can reflect the changes in the microscopic molecular structure of polyolefin polymer materials (such as functional groups, molecular configurations, etc.), and establish correlations with macroscopic properties (such as electrical properties, etc.), which is suitable for material performance prediction and evaluation. Near-infrared spectroscopy analysis is fast, non-destructive, does not require complex pre-processing, and is applicable to a variety of working environments. When combined with modern chemometric methods, it can achieve high-precision and sensitive quantitative and qualitative analysis. During damage or aging, the physicochemical composition and structure of PP cables undergo irreversible changes, and the key information of these structurally related chemical components (such as alkyl groups) is distributed throughout the wavelength range of the near-infrared spectrum. The absorption peak intensity of the characteristic band in the near-infrared spectrum will change with changes in the structure. Using structural changes as a bridge, the correlation between the near-infrared spectrum and crystallinity is constructed to achieve performance prediction based on near-infrared spectroscopy.

[0052] Specifically, the above-mentioned solution of the present application establishes a correlation database between the near-infrared spectrum and crystallinity of PP cable insulation materials, and uses the near-infrared spectrum data obtained by cross-sectional scanning to predict the crystallinity, thereby evaluating the insulation aging status.

[0053] In the specific implementation process, the crystallinity of the above-mentioned cable is determined according to the above-mentioned near-infrared spectral data, which can be achieved by the following steps: preprocessing the above-mentioned near-infrared spectral data to obtain the preprocessed near-infrared spectral data, wherein the above-mentioned preprocessing method includes one or more of data smoothing, denoising, CARS algorithm optimization, derivative method, and wavelet transformation; based on the above-mentioned preprocessed near-infrared spectral data, testing to obtain the above-mentioned crystallinity of the corresponding above-mentioned cable.

[0054] In this scheme, by preprocessing the near-infrared spectral data, noise interference can be reduced and data quality can be improved, so that the crystallinity of the cable can be determined more accurately.

[0055] Specifically, the object of application of this solution can be the insulation layer (XLPE material) of the cable, of course, it can also be other layers of the cable. The insulation material can be polypropylene (PP) insulation material, or any other feasible material.

[0056] Specifically, the preprocessing steps include data smoothing to remove random fluctuations at short wavelengths, denoising to reduce random errors in spectral data, the CARS algorithm to optimize key wavelengths to enhance model prediction capabilities, the derivative method to improve spectral resolution, and wavelet transform to decompose spectral signals. These steps collectively ensure the accuracy and reliability of crystallinity information extracted from spectral data. Each preprocessing method targets different issues in near-infrared spectral data. For example, smoothing and denoising reduce random noise in the data and improve the signal-to-noise ratio of the spectrum; the CARS algorithm optimizes wavelengths to eliminate interference from irrelevant information and focus on wavelengths closely related to crystallinity changes; the derivative method and wavelet transform increase data resolution, helping to more accurately capture subtle changes in the spectrum.

[0057] In some embodiments, the crystallinity of the corresponding cable is obtained by testing based on the preprocessed near-infrared spectral data, which can be specifically achieved by the following steps: obtaining a first recognition model, wherein the first recognition model is one of a PLS model, an MLR model, and an SVM model; combining historical near-infrared spectral data and corresponding crystallinity labels into a first training set, and using the first training set to train the first recognition model to obtain a crystallization recognition model, wherein the crystallinity label is the crystallinity index of the cable in the first training set; inputting the preprocessed near-infrared spectral data into the crystallization recognition model to obtain the crystallinity corresponding to the preprocessed near-infrared spectral data.

[0058] In this solution, a suitable first recognition model is selected, and a crystallization recognition model is obtained by training with the help of the first training set. Different models have different data prediction accuracies. By using a large amount of actual data for model training, the model can learn the characteristics related to crystallinity changes in the spectral data, so that when facing unknown samples, the crystallinity of the cable can be determined more accurately.

[0059] Specifically, a suitable first recognition model is selected, such as one of PLS ​​(partial least squares regression), MLR (multivariate linear regression), and SVM (support vector machine) to establish a crystallization recognition model. In this embodiment, model selection depends on the complexity of historical data, the requirements for prediction accuracy, and the availability of computing resources. For example, when there is multicollinearity in the data, the PLS model is a better choice; when the data is linearly separable and a simple model is sought, MLR may be more suitable; and for nonlinear problems, SVM can provide a satisfactory solution. Selecting the appropriate model type is an important prerequisite for ensuring model generalization ability and prediction accuracy.

[0060] A large number of cable samples with known crystallinity were subjected to near-infrared spectroscopy testing, and the corresponding spectral data and true crystallinity values ​​(crystallization labels) were recorded. These data were then input into the first recognition model as a training set. Through the learning algorithm, the model was allowed to autonomously learn the intrinsic relationship between the data and crystallinity, and finally a crystallization recognition model was established that could predict crystallinity from new spectral data.

[0061] In a specific application, a large power company is responsible for maintaining thousands of kilometers of high-voltage cables in the city's power grid. During routine inspections, staff use advanced near-infrared spectrometers to conduct on-site inspections of cables and collect near-infrared spectral data of the cables. Subsequently, through preprocessing steps such as data smoothing, denoising, and CARS optimized wavelength, key band data related to crystallinity are screened out from the original spectrum. Next, the staff selected a rigorously trained PLS model as a crystallization recognition model. This model is based on the near-infrared spectral data of cables collected in the past few years and the corresponding experimental crystallinity data. It is trained and can accurately predict the crystallinity of cables. The preprocessed spectral data is input into the PLS model, and the model quickly outputs the current crystallinity value of the cable.

[0062] Specifically, if Figure 3As shown, near-infrared spectral data and crystallinity of a target sample are obtained. Based on these data and crystallinity, a database of near-infrared spectral data points is generated and a partial least squares regression model is established. This partial least squares regression model is used to predict the crystallinity of an unknown sample, evaluate electrical insulation performance, and determine the aging state. Based on the predicted sample crystallinity, macroscopic performance degradation is studied and the aging state is assessed. The target sample is a uniform, sheet-like PP sample with a thickness of approximately 1 mm.

[0063] In the specific implementation process, after determining the crystallinity of the above-mentioned cable based on the above-mentioned near-infrared spectral data, the above-mentioned method also includes the following steps: obtaining a second recognition model, wherein the above-mentioned second recognition model is one of the ANN model, the random forest model, and the CNN model; forming the historical crystallinity and the corresponding aging status label into a second training set, and using the above-mentioned second training set to train the above-mentioned second recognition model to obtain an aging recognition model, wherein the above-mentioned aging status label is the aging status index of the above-mentioned cable in the above-mentioned second training set; inputting the above-mentioned crystallinity into the above-mentioned aging recognition model to obtain the above-mentioned aging index corresponding to the above-mentioned crystallinity.

[0064] In this approach, a second recognition model is selected from predefined artificial neural network (ANN), random forest, and convolutional neural network (CNN) models. This model has strong nonlinear mapping capabilities and can learn and predict the complex relationship between crystallinity and cable aging status. A second training set is then constructed, containing historical crystallinity data and corresponding cable aging status labels. By training the second recognition model, it learns the correlation between crystallinity and aging status index, ultimately obtaining a highly accurate aging recognition model. By inputting the crystallinity of the cable to be evaluated into this model, a more accurate comprehensive aging index for the cable can be obtained, reflecting its current degree of aging.

[0065] In a specific application, in a large-scale power transmission network, cables are laid in various harsh and complex environments, including underground tunnels, open-air areas, high temperature or extremely cold areas. In order to ensure the continuity and safety of power transmission, the operator adopts the aging identification model in this embodiment to regularly evaluate the aging status of the cable. First, the spectral data of the cable is obtained by near-infrared spectroscopy technology to calculate the crystallinity. Then, these crystallinity data and previous cable aging status labels are used as part of the second training set to train the selected AI model (for example, a random forest model). The aging status label includes the performance evaluation results of the cable at different aging stages, such as elongation at break, AC breakdown field strength, etc. Through training with a large amount of historical data, the AI ​​model can accurately identify the nonlinear relationship between crystallinity and cable aging status. Finally, the latest measured crystallinity data is input into the trained aging identification model to obtain the comprehensive aging index of the cable.

[0066] Specifically, the detection steps of this scheme include the following:

[0067] 1) Sample preparation: Polypropylene cable insulation material was processed into sheet samples with uniform thickness. The samples were subjected to a 48-day accelerated thermal oxidative aging test at 135°C and divided into a modeling set and a prediction set.

[0068] 2) Near-Infrared Spectroscopy: The UV-3600 near-infrared / visible / ultraviolet spectrophotometer was used to measure the near-infrared spectrum of the PP aged samples in the wavelength range of 1600-1900 nm. Specifically, the UV-3600 near-infrared / visible / ultraviolet spectrophotometer was used to measure the background spectrum without any sample placed in the sample, followed by measuring the near-infrared spectrum of the PP sample in the wavelength range of 1600-1900 nm.

[0069] 3) Near-infrared spectrum preprocessing: The near-infrared spectrum of the measured PP aged sample is smoothed, normalized and preprocessed by the second-order derivative to eliminate the influence of noise, miscellaneous peaks and baseline drift, and highlight the absorption peak at the characteristic wavelength.

[0070] 4) Crystallinity Test: 5-10 mg of sample was weighed using an AG135 photoelectric balance and conducted using a Mettler DSC 822e differential scanning calorimeter. The test procedure was as follows: The experiment was conducted in a nitrogen atmosphere at a flow rate of 50 mL / min. The test temperature range was 25°C to 200°C, and the heating rate was 10°C / min. The total crystallinity of the sample was calculated according to the following formula.

[0071]

[0072] X C Indicates crystallinity, ΔH mCalculated from the integrated area of ​​the DSC curve, the unit is / J·g-1; The enthalpy of complete crystallization of polypropylene α crystals is 209 J / g.

[0073] 5) Wavelength optimization of near-infrared spectral data: The wavelengths of the preprocessed near-infrared spectra were optimized using the CARS algorithm, and wavelengths that were strongly correlated with the change in crystallinity during the aging process of the PP samples were selected. 13 wavelengths that were strongly correlated with the crystallinity of the PP samples were selected.

[0074] 6) Establishing a partial least squares regression model: Using the partial least squares algorithm, the spectral data optimized by the CARS algorithm and the crystallinity of PP during aging are combined to construct a PP crystallinity prediction regression model based on near-infrared spectroscopy;

[0075] Detection of crystallinity of unknown samples: Collect the near-infrared spectrum of the PP sample in the prediction set, pre-process the spectral data, and input it into the prediction model to obtain the crystallinity of the prediction set;

[0076] Evaluate the aging state of PP insulation: Based on the predicted value of crystallinity, the relevant macro-performance indicators are obtained to evaluate the aging state of PP insulation.

[0077] Specifically, a 48-day aging test at 135°C can be performed on sheet PP samples of uniform thickness. The aged samples are used as research subjects, and near-infrared spectroscopy is performed on the aged PP samples using a UV-3600 near-infrared / visible / ultraviolet spectrophotometer. The changes in crystallinity with aging time and the changes in the absorption peak of the characteristic wavelength of the near-infrared spectrum with aging are analyzed. Using the CARS algorithm to optimize wavelengths, a comprehensive database containing the near-infrared spectral characteristics and crystallinity of samples with different degrees of aging is constructed. The correlation characteristics between the near-infrared characteristic spectrum and crystallinity are studied, and a correlation model between the two is determined. A matrix relationship between the near-infrared spectrum and crystallinity is established, thereby achieving the goal of rapidly detecting the crystallinity of PP samples during aging based on near-infrared spectroscopy, achieving the purpose of indirectly evaluating the parameter indicators of various macroscopic properties, and completing the aging status assessment of PP cable insulation.

[0078] In some embodiments, after determining the aging index of the cable according to the crystallinity, the method further includes the following steps: determining the maximum historical temperature according to all historical temperatures of the cable, the historical temperature being the temperature of the cable measured at a historical moment; determining the damage index of the cable according to the maximum historical temperature of the cable and a second preset mapping relationship, wherein the second preset mapping relationship is a mapping relationship between the temperature of the cable and the damage index; determining the comprehensive aging index of the cable according to the crystallinity and the damage index; and controlling the alarm device to alarm when the comprehensive aging index is greater than the second preset index threshold.

[0079] In this solution, the cable will face temperature fluctuations during actual operation. Extreme temperature conditions (whether overheating or overcooling) will have an adverse effect on the insulation material of the cable and accelerate its aging process. In order to more comprehensively evaluate the aging status of the cable, it is also possible to collect the historical temperature data of the cable to determine the highest temperature at a historical moment, that is, the maximum historical temperature. According to the characteristics of the cable material, a second preset mapping relationship is established, which reflects the relationship between the temperature and the degree of damage of the cable. Through this mapping relationship, the damage index that may accumulate in the cable under extreme temperatures can be determined. Combining the damage index with the crystallinity, a calculation method for the comprehensive aging index is formed, which provides a more comprehensive perspective for the evaluation of the aging status of the cable.

[0080] Specifically, this embodiment further considers the impact of the cable's historical temperature data on the aging state, and forms a comprehensive aging index through damage index evaluation combined with crystallinity to more comprehensively evaluate the degree of cable aging. First, the temperature records of the cable at different historical moments are summarized, and the maximum historical temperature is screened out as the basis for temperature impact analysis. Then, the damage index of the cable is calculated based on a preset second mapping relationship (established based on experimental data and theoretical analysis). This index reflects the additional damage that the cable may suffer when experiencing high or low temperature conditions. Finally, the crystallinity measurement results and the damage index are comprehensively considered, and a comprehensive aging index is calculated through a mathematical model (such as weighted average, composite function, etc.) to comprehensively reflect the aging state of the cable. This process ensures that the aging assessment covers the dual influence of the inherent aging trend of the cable material and external environmental factors (such as temperature), thereby improving the comprehensiveness and accuracy of the assessment.

[0081] By combining crystallinity and damage indices, a more comprehensive cable aging condition assessment system has been constructed, improving the accuracy and reliability of the assessment and helping to prevent power system failures caused by aging or damage. The calculation of the comprehensive aging index fully considers the inherent aging of cable materials and the accumulation of damage caused by temperature changes, resulting in a more comprehensive assessment result that more accurately reflects the actual operating condition of the cable.

[0082] In a specific application, in a large-scale power transmission project, cables are deployed in a variety of environments, including high-temperature desert areas and cold mountainous areas. In order to ensure the healthy operation of the cables, the project operator adopted the comprehensive aging index evaluation method in this embodiment. First, the temperature data of the cable at different historical moments are collected through a built-in or external temperature sensor, and the maximum historical temperature is determined to be 85°C (the highest temperature recorded when operating in the desert area). Next, based on the second preset mapping relationship (such as the functional relationship curve between temperature and damage index), the cable damage index at the maximum historical temperature is calculated to be 0.15. Then, combined with the crystallinity measurement results (assuming it is 30%), the final comprehensive aging index is 0.45 through the comprehensive aging index calculation model. Finally, the second preset index threshold is set to 0.5 (it can also be any other feasible value). When it is detected that the comprehensive aging index is close to or exceeds this threshold, the alarm mechanism is automatically activated to notify the maintenance team to conduct a detailed inspection or replace the cable to ensure the continuity and safety of the power supply.

[0083] During the specific implementation process, before determining the maximum historical temperature based on all the historical temperatures of the above-mentioned cable, the above-mentioned method also includes the following steps: obtaining a third recognition model, wherein the above-mentioned third recognition model is one of an LSTM model, a PCA model, and a KNN model; forming the historical Raman spectral data and the corresponding temperature labels into a third training set, and using the above-mentioned third training set to train the above-mentioned third recognition model to obtain a temperature recognition model, wherein the above-mentioned temperature label is the temperature index of the above-mentioned cable in the above-mentioned third training set; inputting the Raman spectral data into the above-mentioned temperature recognition model to obtain the above-mentioned temperature corresponding to the above-mentioned Raman spectral data.

[0084] In this solution, the temperature status of the cable is one of the key parameters for assessing its health status and preventing failures, but direct measurement in some cases may be subject to environmental restrictions or cost considerations. Therefore, this solution is based on a third recognition model that can extract temperature information from the Raman spectrum. Samples are collected from historical Raman spectral data, which contain spectral information of the cable under different temperature conditions. Subsequently, these spectral data and corresponding temperature labels are combined into a training set, and by training a third recognition model (such as an LSTM, PCA or KNN model), a temperature recognition model that can convert spectral data into temperature data is obtained. In the absence of a temperature sensor or sensor failure, the current Raman spectral data of the cable can be input into the temperature recognition model to obtain an accurate temperature estimate of the cable for subsequent aging status assessment and maintenance decisions.

[0085] Specifically, the Raman spectrum data is the light intensity value of light scattered by the cable detected by a Raman spectrum analyzer.

[0086] Specifically, before determining the maximum historical temperature, this embodiment uses Raman spectral data to predict the temperature of the cable by constructing a temperature recognition model to supplement or replace direct temperature measurement. This process first involves selecting a suitable third recognition model from LSTM (long short-term memory network), PCA (principal component analysis), or KNN (k-nearest neighbor algorithm). Subsequently, a third training set is formed by collecting historical records containing Raman spectral data of cables at different temperatures, as well as the temperature labels corresponding to these records. The selected model is trained using this training set to obtain a temperature recognition model that can predict the temperature state of the cable from the spectral data. Finally, the Raman spectral data of the current cable is input into the temperature recognition model to obtain its temperature estimate, which provides the necessary temperature information for subsequent aging index calculation and damage assessment.

[0087] In a specific application, considering the use of power cables in deep sea or underground pipelines, these environmental conditions may make direct temperature measurement very difficult or costly. Therefore, the temperature recognition model in this embodiment is used to predict cable temperature using Raman spectral data. Assume that a large amount of Raman spectral data and corresponding temperature labels were collected in the year before the cable was laid. This data constitutes the third training set. Next, the LSTM model is selected as the third recognition model because the LSTM model excels at processing time series data and can consider the time-dependent characteristics of spectral data, thereby more accurately predicting temperature. Through training, a temperature recognition model is obtained that can predict temperature from Raman spectral data. In actual operation, once the cable is laid in an environment where direct temperature measurement is impossible, its Raman spectral data can be obtained in real time and input into the temperature recognition model to obtain a temperature estimate of the cable. For example, suppose the temperature recognition model predicts the cable temperature to be 80°C. This temperature information is crucial for subsequent aging status assessment. Finally, the comprehensive aging index of the cable is calculated by combining the temperature prediction results and crystallinity data. When the comprehensive aging index exceeds the second preset index threshold (such as 0.6), an automatic alarm is triggered, ensuring that the aging status of the cable can be evaluated promptly and accurately even in extreme environments, providing a guarantee for the safe operation of the power system.

[0088] In some embodiments, the comprehensive aging index of the cable is determined based on the crystallinity and the damage index, which can be specifically achieved through the following steps: obtaining a first weight coefficient, wherein the first weight coefficient is a preset weight coefficient of the crystallinity; obtaining a second weight coefficient, wherein the second weight coefficient is a preset weight coefficient of the damage index; obtaining the first preset mapping relationship, wherein the first preset mapping relationship is the relationship between the crystallinity and the aging index; obtaining a third preset mapping relationship, wherein the third preset mapping relationship is the relationship between the damage index and the aging index; according to the first preset mapping relationship, determining the aging index corresponding to the crystallinity as the first target aging index; according to the third preset mapping relationship, determining the aging index corresponding to the damage index as the second target aging index; calculating the weighted average of the first weight coefficient, the second weight coefficient, the first target aging index and the second target aging index to obtain the comprehensive aging index.

[0089] In this solution, the crystallinity and damage index are converted into aging indices through the first preset mapping relationship and the third preset mapping relationship respectively, and then weighted averaged according to their respective weight coefficients to obtain the final comprehensive aging index, which can more comprehensively reflect the aging status of the cable.

[0090] In addition, the solution of the present application also includes the following contents: using terahertz spectroscopy technology to collect terahertz spectral data of cable insulation materials; analyzing the above terahertz spectral data to identify molecular dynamic change information related to cable aging, including but not limited to moisture content and molecular vibration characteristics; using artificial intelligence models to conduct in-depth analysis of the above molecular dynamic change information to generate early warning signals of cable aging status; based on the above early warning signals, taking maintenance measures in advance to prevent power system failures.

[0091] Terahertz spectrometers are used to collect data at different locations along the cable, covering the entire length of the cable to ensure comprehensive and representative data. Terahertz spectrometers can penetrate the outer layer of the cable and directly obtain spectral information from within the insulation material without causing any physical damage to the cable.

[0092] The collected terahertz spectral data is preprocessed, including smoothing, normalization, and background correction, to eliminate the influence of noise and nonspecific signals. Subsequently, feature extraction algorithms (such as PCA and CARS) are used to identify molecular dynamic changes associated with cable aging, such as increased internal moisture content, changes in molecular structure, and shifts in vibration frequency.

[0093] The identified molecular dynamics are fed into a pre-trained artificial intelligence model (such as a deep neural network or support vector machine). By learning from a large amount of historical cable aging data and aging patterns, the model can extract features related to cable aging from the terahertz spectrum and perform quantitative predictions of the aging degree. The model is trained on a historical database containing terahertz spectral data for cables in various aging states, ensuring its generalizability and accuracy.

[0094] Once the AI ​​model analysis results indicate that the aging index of a part of the cable reaches or exceeds the preset threshold (such as the aging degree exceeds 80%), the system will automatically generate an early warning signal and transmit it to the monitoring center in real time through the wireless communication network. At the same time, the alarm mechanism will be activated to remind maintenance personnel to pay attention to inspection and take necessary maintenance measures.

[0095] Depending on the severity of the early warning signal, the monitoring center will dispatch maintenance personnel to conduct on-site inspections of the cables, or initiate preventive maintenance procedures through remote control systems, such as local heating to drive out moisture and automatic spraying of chemical coatings, to slow down or prevent further development of the aging process.

[0096] Through in-depth analysis using terahertz spectroscopy technology and AI models, early warning signals can be issued for cable aging with high accuracy. Terahertz spectroscopy can penetrate the outer layer of the cable, reaching deep into the insulation material and capturing dynamic changes at the molecular level, such as abnormal increases in moisture content and spectral shifts in molecular vibrations, which are important indicators of early cable aging. Through deep learning of these molecular dynamic changes, the AI ​​model can identify complex cable aging patterns, predict aging trends, and issue timely warning signals when aging indicators reach warning thresholds. This approach effectively prevents sudden failures in the power system caused by cable aging, improving system safety and operational efficiency.

[0097] In order to enable those skilled in the art to more clearly understand the technical solution of the present application, the implementation process of the method for evaluating the aging status of cable insulation of the present application will be described in detail below with reference to specific embodiments.

[0098] This embodiment relates to a specific method for evaluating the aging state of cable insulation. Taking a commercial 110kV polypropylene cable insulation as an example, the insulation is processed into sheet specimens with uniform thickness and subjected to a 48-day accelerated thermal oxidative aging test at 135°C. The near-infrared spectra of the specimens are measured as follows:

[0099] The UV-3600 near-infrared / visible / ultraviolet spectrophotometer used in this example placed the target sample in the sample chamber and used the transmission mode with a resolution of 0.1 nm. Specifically, the following steps were included:

[0100] 1) Prepare the sample: Process the polypropylene cable insulation material into a sheet sample with a width of about 60mm and a uniform thickness of about 1mm. Perform an accelerated thermal oxidative aging test at 135℃ for 48 days. Figure 4 As shown, it is divided into a modeling set and a prediction set as target samples.

[0101] 2) Detection of near-infrared spectrum: Use a UV-3600 near-infrared / visible / ultraviolet spectrophotometer to detect the background spectrum when no sample is placed, and then test the near-infrared spectrum of the PP sample in the wavelength range of 1600nm-1900nm.

[0102] 3) Preprocessing of the near-infrared spectrum: Smoothing, standardization and second-order derivative processing are performed on the measured near-infrared spectrum to eliminate the influence of noise, miscellaneous peaks and baseline drift.

[0103] 4) Crystallinity Test: 5-10 mg of sample was weighed using an AG135 photoelectric balance and conducted using a Mettler DSC 822e differential scanning calorimeter. The test procedure was as follows: The experiment was conducted in a nitrogen atmosphere at a flow rate of 50 mL / min. The test temperature range was 25°C to 200°C, and the heating rate was 10°C / min. The total crystallinity of the sample was calculated.

[0104] 5) Wavelength optimization of near-infrared spectral data: The wavelength of the pre-processed spectral data was optimized by the CARS algorithm, and 13 wavelength points that were strongly correlated with the crystallinity of the PP sample were selected. The results of wavelength optimization are as follows: Figure 5 and Figure 6 shown.

[0105] 6) Establish a partial least squares regression model: Based on the near-infrared spectrum data and measured crystallinity of the optimized model set samples, a partial least squares regression model is established to obtain a regression model of near-infrared spectrum and crystallinity. The prediction model results are as follows: Figure 7 shown.

[0106] 7) Predicting the crystallinity of unknown samples: Collect the near-infrared spectrum of the prediction set PP sample, pre-process the spectral data, and input it into the prediction model to obtain the crystallinity of the prediction set. The prediction results are as follows: Figure 8 As shown in Table 1.

[0107] Table 1

[0108] Prediction set samples Predicted value (%) Error range (%) Measured value R1 33.53 0.73％ 33.28 R2 31.81 0.93％ 32.11 R3 32.55 0.30％ 32.45 R4 31.84 0.22％ 31.91

[0109] Evaluation of the aging state of PP insulation: Based on the predicted value of crystallinity, the relevant macro-performance indicators are obtained to evaluate the aging state of PP insulation, such as Figure 9 shown.

[0110] PP sheet samples of uniform thickness were cut from commercial PP cable insulation and used as target samples. The target samples were divided into a modeling set and a prediction set. The near-infrared spectra of the PP samples were measured using a UV-3600 near-infrared / visible / ultraviolet spectrophotometer, and the spectral data were preprocessed to eliminate the effects of noise, stray peaks, and baseline drift. The crystallinity of the PP samples was measured using a Mettler DSC 822e differential scanning calorimeter to obtain microscopic parameters reflecting the macroscopic properties of the PP samples. The preprocessed near-infrared spectra were optimized using the CARS algorithm, and a partial least squares regression model was established using the optimized near-infrared spectral data from the modeling set and the measured crystallinity. Near-infrared spectra of unknown samples were collected and, after processing, input into the established crystallinity prediction model system to obtain the crystallinity of the prediction set samples. Based on the obtained crystallinity, relevant macroscopic performance indicators were derived to evaluate the aging state of the PP insulation.

[0111] The embodiment of the present application also provides an evaluation device for the aging state of cable insulation. It should be noted that the evaluation device for the aging state of cable insulation in the embodiment of the present application can be used to execute the evaluation method for the aging state of cable insulation provided in the embodiment of the present application. The device is used to implement the above-mentioned embodiments and preferred implementation methods, and the details that have been explained will not be repeated here. As used below, the term "module" can implement a combination of software and / or hardware for a predetermined function. Although the device described in the following embodiments is preferably implemented in software, implementation in hardware, or a combination of software and hardware, is also possible and conceivable.

[0112] The following introduces the device for evaluating the aging status of cable insulation provided in an embodiment of the present application.

[0113] Figure 10 This is a structural block diagram of a device for evaluating the aging state of cable insulation according to an embodiment of the present application. Figure 10 As shown, the device includes:

[0114] A first acquiring unit 10 is configured to acquire near-infrared spectrum data, wherein the near-infrared spectrum data is a light intensity value of near-infrared light absorbed by the cable;

[0115] A first determining unit 20 is configured to determine the crystallinity of the cable based on the near-infrared spectrum data, wherein the crystallinity is the ratio of the volume of the crystalline region of the polymer material of the cable to the volume of the entire cable material;

[0116] a second determining unit 30, configured to determine an aging index of the cable according to the crystallinity and a first preset mapping relationship, wherein the first preset mapping relationship is a mapping relationship between the crystallinity and the aging index;

[0117] The first control unit 40 is configured to control the alarm device to sound an alarm when the aging index is greater than a first preset index threshold.

[0118] Near-infrared spectroscopy technology identifies the structural characteristics of a sample by detecting the sample's absorption characteristics of near-infrared light. In this solution, near-infrared spectroscopy technology is used to detect the light intensity value of the cable's absorption of near-infrared light, and near-infrared spectral data is obtained. Near-infrared spectroscopy technology has low requirements for environmental conditions and is suitable for on-site detection. It is no longer limited by the environment. As the cable ages, the polymer material will degrade, oxidize, crack, and other phenomena will occur, resulting in changes in the crystallinity of the material. The size of the crystalline region of the polymer will directly affect the change in absorbance. These changes will be directly reflected in the near-infrared spectral data, forming spectral characteristics. Therefore, the changes in the crystallinity of the material can be accurately captured through near-infrared spectral data. The aging index is a quantitative indicator used to express the aging status of the cable. There is a mapping relationship between crystallinity and aging index. Different crystallinity corresponds to different aging states. Through this embodiment, when detecting the cable on-site, there is no need to conduct tests and it is not restricted by the environment. It overcomes the limitations of traditional detection methods, and thus the aging status of the cable can be accurately evaluated.

[0119] During the specific implementation process, the first determination unit includes a preprocessing module and a first determination module. The preprocessing module is used to preprocess the above-mentioned near-infrared spectral data to obtain the preprocessed near-infrared spectral data, wherein the above-mentioned preprocessing method includes one or more of data smoothing, denoising, CARS algorithm optimization, derivative method, and wavelet transformation; the first determination module is used to test and obtain the above-mentioned crystallinity of the corresponding above-mentioned cable based on the above-mentioned preprocessed near-infrared spectral data.

[0120] In this scheme, by preprocessing the near-infrared spectral data, noise interference can be reduced and data quality can be improved, so that the crystallinity of the cable can be determined more accurately.

[0121] In some embodiments, the first determination module includes an acquisition submodule, a training submodule and a processing submodule, the acquisition submodule is used to acquire a first recognition model, wherein the above-mentioned first recognition model is one of a PLS model, an MLR model, and an SVM model; the training submodule is used to combine historical near-infrared spectral data and corresponding crystallinity labels into a first training set, and use the above-mentioned first training set to train the above-mentioned first recognition model to obtain a crystallization recognition model, wherein the above-mentioned crystallinity label is the crystallinity index of the above-mentioned cable in the above-mentioned first training set; the processing submodule is used to input the above-mentioned preprocessed near-infrared spectral data into the above-mentioned crystallization recognition model to obtain the above-mentioned crystallinity corresponding to the above-mentioned preprocessed near-infrared spectral data.

[0122] In this solution, a suitable first recognition model is selected, and a crystallization recognition model is obtained by training with the help of the first training set. Different models have different data prediction accuracies. By using a large amount of actual data for model training, the model can learn the characteristics related to crystallinity changes in the spectral data, so that when facing unknown samples, the crystallinity of the cable can be determined more accurately.

[0123] During the specific implementation process, the above-mentioned device also includes a second acquisition unit, a first training unit and a first processing unit. The second acquisition unit is used to obtain a second recognition model after determining the crystallinity of the above-mentioned cable based on the above-mentioned near-infrared spectral data, wherein the above-mentioned second recognition model is one of the ANN model, the random forest model, and the CNN model; the first training unit is used to form the historical crystallinity and the corresponding aging status label into a second training set, and use the above-mentioned second training set to train the above-mentioned second recognition model to obtain an aging recognition model, wherein the above-mentioned aging status label is the aging status index of the above-mentioned cable in the above-mentioned second training set; the first processing unit is used to input the above-mentioned crystallinity into the above-mentioned aging recognition model to obtain the above-mentioned aging index corresponding to the above-mentioned crystallinity.

[0124] In this approach, a second recognition model is selected from predefined artificial neural network (ANN), random forest, and convolutional neural network (CNN) models. This model has strong nonlinear mapping capabilities and can learn and predict the complex relationship between crystallinity and cable aging status. A second training set is then constructed, containing historical crystallinity data and corresponding cable aging status labels. By training the second recognition model, it learns the correlation between crystallinity and aging status index, ultimately obtaining a highly accurate aging recognition model. By inputting the crystallinity of the cable to be evaluated into this model, a more accurate comprehensive aging index for the cable can be obtained, reflecting its current degree of aging.

[0125] In some embodiments, the above-mentioned device also includes a third determination unit, a fourth determination unit, a fifth determination unit and a second control unit. The third determination unit is used to determine the maximum historical temperature based on all historical temperatures of the above-mentioned cable after determining the aging index of the above-mentioned cable according to the above-mentioned crystallinity, and the above-mentioned historical temperature is the temperature of the above-mentioned cable measured at a historical moment; the fourth determination unit is used to determine the damage index of the above-mentioned cable according to the above-mentioned maximum historical temperature of the above-mentioned cable and a second preset mapping relationship, wherein the above-mentioned second preset mapping relationship is a mapping relationship between the temperature of the above-mentioned cable and the above-mentioned damage index; the fifth determination unit is used to determine the comprehensive aging index of the above-mentioned cable according to the above-mentioned crystallinity and the above-mentioned damage index; the second control unit is used to control the above-mentioned alarm device to alarm when the above-mentioned comprehensive aging index is greater than the second preset index threshold.

[0126] In this solution, the cable will face temperature fluctuations during actual operation. Extreme temperature conditions (whether overheating or overcooling) will have an adverse effect on the insulation material of the cable and accelerate its aging process. In order to more comprehensively evaluate the aging status of the cable, it is also possible to collect the historical temperature data of the cable to determine the highest temperature at a historical moment, that is, the maximum historical temperature. According to the characteristics of the cable material, a second preset mapping relationship is established, which reflects the relationship between the temperature and the degree of damage of the cable. Through this mapping relationship, the damage index that may accumulate in the cable under extreme temperatures can be determined. Combining the damage index with the crystallinity, a calculation method for the comprehensive aging index is formed, which provides a more comprehensive perspective for the evaluation of the aging status of the cable.

[0127] During the specific implementation process, the above-mentioned device also includes a third acquisition unit, a second training unit and a second processing unit. The third acquisition unit is used to obtain a third recognition model before determining the maximum historical temperature based on all the historical temperatures of the above-mentioned cable, wherein the above-mentioned third recognition model is one of the LSTM model, the PCA model, and the KNN model; the second training unit is used to combine the historical Raman spectral data and the corresponding temperature labels into a third training set, and use the above-mentioned third training set to train the above-mentioned third recognition model to obtain a temperature recognition model, wherein the above-mentioned temperature label is the temperature index of the above-mentioned cable in the above-mentioned third training set; the second processing unit is used to input the Raman spectral data into the above-mentioned temperature recognition model to obtain the above-mentioned temperature corresponding to the above-mentioned Raman spectral data.

[0128] In this solution, the temperature status of the cable is one of the key parameters for assessing its health status and preventing failures, but direct measurement in some cases may be subject to environmental restrictions or cost considerations. Therefore, this solution is based on a third recognition model that can extract temperature information from the Raman spectrum. Samples are collected from historical Raman spectral data, which contain spectral information of the cable under different temperature conditions. Subsequently, these spectral data and corresponding temperature labels are combined into a training set, and by training a third recognition model (such as an LSTM, PCA or KNN model), a temperature recognition model that can convert spectral data into temperature data is obtained. In the absence of a temperature sensor or sensor failure, the current Raman spectral data of the cable can be input into the temperature recognition model to obtain an accurate temperature estimate of the cable for subsequent aging status assessment and maintenance decisions.

[0129] In some embodiments, the fifth determination unit includes a first acquisition module, a second acquisition module, a third acquisition module, a fourth acquisition module, a second determination module, a third determination module and a calculation module, wherein the first acquisition module is used to acquire a first weight coefficient, wherein the first weight coefficient is a preset weight coefficient of the above-mentioned crystallinity; the second acquisition module is used to acquire a second weight coefficient, wherein the second weight coefficient is a preset weight coefficient of the above-mentioned damage index; the third acquisition module is used to acquire the above-mentioned first preset mapping relationship, wherein the above-mentioned first preset mapping relationship is the relationship between the above-mentioned crystallinity and the above-mentioned aging index; the fourth acquisition module is used to acquire a third preset mapping relationship, wherein the above-mentioned third preset mapping relationship is the relationship between the above-mentioned damage index and the above-mentioned aging index; the second determination module is used to determine the above-mentioned aging index corresponding to the above-mentioned crystallinity as the first target aging index according to the above-mentioned first preset mapping relationship; the third determination module is used to determine the above-mentioned aging index corresponding to the above-mentioned damage index as the second target aging index according to the above-mentioned third preset mapping relationship; and the calculation module is used to calculate the weighted average of the above-mentioned first weight coefficient, the above-mentioned second weight coefficient, the above-mentioned first target aging index and the above-mentioned second target aging index to obtain the above-mentioned comprehensive aging index.

[0130] In this solution, the crystallinity and damage index are converted into aging indices through the first preset mapping relationship and the third preset mapping relationship respectively, and then weighted averaged according to their respective weight coefficients to obtain the final comprehensive aging index, which can more comprehensively reflect the aging status of the cable.

[0131] The device for assessing the aging state of cable insulation includes a processor and a memory. The first acquisition unit, first determination unit, second determination unit, and first control unit are all stored as program units in the memory. The processor executes the program units stored in the memory to implement the corresponding functions. All of the modules are located in the same processor; alternatively, the modules can be located in different processors in any combination.

[0132] The processor includes a core, which retrieves the corresponding program unit from the memory. One or more cores can be set, and the problem of the inability to accurately assess the aging status of the cable in the existing technology can be solved by adjusting the core parameters.

[0133] 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 RAM, and the memory includes at least one memory chip.

[0134] An embodiment of the present invention provides a computer-readable storage medium, which includes a stored program. When the program is run, the device where the computer-readable storage medium is located is controlled to execute the cable insulation aging status evaluation method.

[0135] An embodiment of the present invention provides a processor, which is used to run a program, wherein the method for evaluating the cable insulation aging state is executed when the program is run.

[0136] An embodiment of the present invention provides a device comprising a processor, a memory, and a program stored in the memory and executable on the processor. When the processor executes the program, it implements at least the steps of a method for assessing the aging status of cable insulation. The device herein may be a server, a PC, a PAD, a mobile phone, or the like.

[0137] A computer program product includes a non-volatile computer-readable storage medium, wherein the non-volatile computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps of the cable insulation aging status evaluation method in each embodiment of the present application are implemented.

[0138] The present application also provides a detection system, including a cable; a near-infrared spectrometer; a Raman spectrometer; and a control device, which is respectively communicated with the above-mentioned near-infrared spectrometer and the above-mentioned Raman spectrometer, and the above-mentioned control device is used to execute any one of the above-mentioned cable insulation aging status evaluation methods.

[0139] Obviously, those skilled in the art will appreciate that the various modules or steps of the present invention described above can be implemented using a general-purpose computing device, can be centralized on a single computing device, or can be distributed across a network of multiple computing devices. They can be implemented using program code executable by the computing device, and thus, can be stored in a storage device and executed by the computing device. In some cases, the steps shown or described herein can be performed in a different order than that shown, or can be fabricated as separate integrated circuit modules, or multiple modules or steps can be fabricated as a single integrated circuit module. Thus, the present invention is not limited to any particular combination of hardware and software.

[0140] Those skilled in the art will appreciate that the embodiments of the present application can be provided as methods, systems, or computer program products. Therefore, the present application can 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 can adopt the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to magnetic disk storage, CD-ROM, optical storage, etc.) that contain computer-usable program code.

[0141] 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 produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the steps in the process. 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.

[0142] These computer program instructions may also be stored in a computer readable memory that can direct a computer or other programmable data processing device to work 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 The function specified in one or more boxes.

[0143] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operational steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing the instructions executed on the computer or other programmable device for implementing the process. Figure 1 a process or multiple processes and / or boxes Figure 1 A step that specifies a function in one or more boxes.

[0144] In a typical configuration, a computing device includes one or more processors (CPUs), input / output interfaces, network interfaces, and memory.

[0145] 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.

[0146] Computer-readable media includes permanent and non-permanent, removable and non-removable media that can be implemented by any method or technology to store information. The 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 disc read-only memory (CD-ROM), digital versatile disc (DVD) or other optical storage, magnetic cassettes, magnetic 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 transitory media such as modulated data signals and carrier waves.

[0147] It should also be noted that the terms "comprises," "includes," or any other variations thereof are intended to encompass non-exclusive inclusion, such that a process, method, commodity, or apparatus that includes a series of elements includes not only those elements but also other elements not explicitly listed, or includes elements inherent to such process, method, commodity, or apparatus. In the absence of further limitations, an element defined by the phrase "comprises a ..." does not exclude the presence of other identical elements in the process, method, commodity, or apparatus that includes the element.

[0148] The above description is merely a preferred embodiment of the present application and is not intended to limit the present application. Various modifications and variations are possible for those skilled in the art. Any modifications, equivalent substitutions, or improvements made within the spirit and principles of the present application shall be included within the scope of protection of the present application.

Claims

1. A method for evaluating the aging state of cable insulation, characterized in that: include: Acquiring near-infrared spectrum data, wherein the near-infrared spectrum data is a light intensity value of near-infrared light absorbed by the cable; Determining the crystallinity of the cable based on the near-infrared spectral data, wherein the crystallinity is the ratio of the volume of the crystalline region of the polymer material of the cable to the volume of the entire material of the cable; determining an aging index of the cable according to the crystallinity and a first preset mapping relationship, wherein the first preset mapping relationship is a mapping relationship between the crystallinity and the aging index; When the aging index is greater than a first preset index threshold, the alarm device is controlled to sound an alarm.

2. The method according to claim 1, characterized in that Determining the crystallinity of the cable according to the near-infrared spectrum data comprises: Preprocessing the near-infrared spectral data to obtain preprocessed near-infrared spectral data, wherein the preprocessing method includes one or more of data smoothing, denoising, CARS algorithm optimization, derivative method, and wavelet transformation; The crystallinity of the corresponding cable is obtained by testing based on the pre-processed near-infrared spectrum data.

3. The method according to claim 2, characterized in that The method of testing and obtaining the corresponding crystallinity of the cable according to the pre-processed near-infrared spectrum data comprises: Obtaining a first recognition model, wherein the first recognition model is one of a PLS model, an MLR model, and an SVM model; historical near-infrared spectral data and corresponding crystallinity labels are combined into a first training set, and the first recognition model is trained using the first training set to obtain a crystallization recognition model, wherein the crystallinity label is a crystallinity index of the cable in the first training set; The pre-processed near-infrared spectrum data is input into the crystallization recognition model to obtain the crystallinity corresponding to the pre-processed near-infrared spectrum data.

4. The method according to claim 1, wherein After determining the crystallinity of the cable according to the near-infrared spectrum data, the method further includes: Obtain a second recognition model, wherein the second recognition model is one of an ANN model, a random forest model, and a CNN model; The historical crystallinity and the corresponding aging state label are combined into a second training set, and the second recognition model is trained using the second training set to obtain an aging recognition model, wherein the aging state label is the aging state index of the cable in the second training set; The crystallinity is input into the aging recognition model to obtain the aging index corresponding to the crystallinity.

5. The method according to claim 1, wherein After determining the aging index of the cable according to the crystallinity, the method further includes: Determining a maximum historical temperature based on all historical temperatures of the cable, where the historical temperatures are temperatures of the cable measured at historical moments; determining a damage index of the cable according to the maximum historical temperature of the cable and a second preset mapping relationship, wherein the second preset mapping relationship is a mapping relationship between the temperature of the cable and the damage index; Determining a comprehensive aging index of the cable according to the crystallinity and the damage index; When the comprehensive aging index is greater than a second preset index threshold, the alarm device is controlled to sound an alarm.

6. The method according to claim 5, characterized in that Before determining the maximum historical temperature based on all historical temperatures of the cable, the method further includes: Obtain a third recognition model, wherein the third recognition model is one of an LSTM model, a PCA model, and a KNN model; historical Raman spectral data and corresponding temperature labels are combined into a third training set, and the third recognition model is trained using the third training set to obtain a temperature recognition model, wherein the temperature label is the temperature index of the cable in the third training set; The Raman spectrum data is input into the temperature recognition model to obtain the temperature corresponding to the Raman spectrum data.

7. The method according to claim 5, characterized in that Determining a comprehensive aging index of the cable according to the crystallinity and the damage index includes: Obtaining a first weight coefficient, wherein the first weight coefficient is a preset weight coefficient of the crystallinity; Obtaining a second weight coefficient, wherein the second weight coefficient is a preset weight coefficient of the damage index; Acquire the first preset mapping relationship, wherein the first preset mapping relationship is the relationship between the crystallinity and the aging index; Acquire a third preset mapping relationship, wherein the third preset mapping relationship is a relationship between the damage index and the aging index; determining, according to the first preset mapping relationship, the aging index corresponding to the crystallinity as a first target aging index; According to the third preset mapping relationship, determining the aging index corresponding to the damage index as a second target aging index; A weighted average of the first weight coefficient, the second weight coefficient, the first target aging index, and the second target aging index is calculated to obtain the comprehensive aging index.

8. A device for evaluating the aging state of cable insulation, characterized in that: include: A first acquiring unit is configured to acquire near-infrared spectrum data, wherein the near-infrared spectrum data is a light intensity value of near-infrared light absorbed by the cable; a first determining unit, configured to determine the crystallinity of the cable according to the near-infrared spectrum data, wherein the crystallinity is a ratio of the volume of a crystalline region of the polymer material of the cable to the volume of the entire material of the cable; a second determining unit, configured to determine an aging index of the cable according to the crystallinity and a first preset mapping relationship, wherein the first preset mapping relationship is a mapping relationship between the crystallinity and the aging index; The first control unit is configured to control the alarm device to sound an alarm when the aging index is greater than a first preset index threshold.

9. A computer program product comprising a computer program, characterized in that When the computer program is executed by a processor, the steps of the method for evaluating the cable insulation aging state according to any one of claims 1 to 7 are implemented.

10. A detection system, characterized in that: include: cable; Near-infrared spectrometer; Raman spectrometer; A control device is communicatively connected to the near-infrared spectrometer and the Raman spectrometer, respectively, and the control device is used to execute the method for evaluating the aging state of cable insulation according to any one of claims 1 to 7.

Images