Old power cable defect identification device based on partial discharge signal

Abstract

The utility model provides an old power cable defect identification device based on partial discharge signals. The device comprises a partial discharge signal acquisition unit and a data server unit, the cable section comprises a polypropylene cable defect section; the high-voltage control experiment table is provided with a table type electrical display device, a first transformer, a first protective resistor, a capacitive voltage divider and a low-voltage matching unit; high voltage is led out through a capacitive voltage divider and is applied to the defect section of the polypropylene cable, and a current signal acquired by the high-frequency current transformer HFCT in real time is used as a partial discharge signal of the defect section of the polypropylene cable; a current signal acquired by the high-frequency current transformer HFCT in real time passes through the high-pass filter and then is transmitted to a data acquisition system based on a PC (Personal Computer) through a high-speed communication interface; and the data server unit generates a defect identification result aiming at the defect section of the polypropylene cable. Therefore, the structure is reasonable, various types of signals can be processed, and the voltage grade range is wide.

Description

Technical Field

[0001] This utility model belongs to the field of power cable monitoring technology, specifically relating to a defect identification device for old power cables based on partial discharge signals. Background Technology

[0002] With the development of power systems, power cables, as an important component of power transmission and distribution networks, are receiving increasing attention for their operational safety and reliability.

[0003] Partial discharge is an early sign of aging and insulation failure in power cables. Timely and effective detection of partial discharge signals and subsequent identification of cable defects are crucial for preventing cable failures.

[0004] Existing defect identification devices for old power cables based on partial discharge signals have reasonable and simple structures, but can only process a limited number of signal types. They suffer from high false positive rates and low detection efficiency, making it difficult to meet the needs of condition analysis and evaluation of a large number of old cables. Utility Model Content

[0005] In view of this, this utility model proposes a defect identification device for old power cables based on partial discharge signals, aiming to solve the problems of simple structure and limited signal types in existing defect identification devices for old power cables.

[0006] The present invention proposes a defect identification device for old power cables based on partial discharge signals, comprising:

[0007] Partial discharge signal acquisition unit and data server unit; the partial discharge signal acquisition unit is installed at the power cable monitoring station; the data server unit is set at a preset distance from the partial discharge signal acquisition unit;

[0008] The partial discharge signal acquisition unit includes a cable condition monitoring module; the cable condition monitoring module includes a data acquisition and processing unit, a sensing device, and a cable segment.

[0009] The cable segment includes: a defective segment of a polypropylene cable;

[0010] The sensing device includes a high-frequency current transformer (HFCT).

[0011] The data acquisition and processing unit includes: a high-pass filter, a data acquisition card, and a data acquisition system;

[0012] The power cable monitoring station is equipped with a high-voltage control test bench.

[0013] The high-voltage control test bench is equipped with a desktop electrical display device, a first transformer, a first protective resistor, a capacitor voltage divider, and a low-voltage matching unit. The AC power supply forms a circuit through the first transformer, the first protective resistor, the capacitor voltage divider, the low-voltage matching unit, and the desktop electrical display device.

[0014] High voltage is led out through a capacitor divider and applied to the defective section of the polypropylene cable. The current signal collected in real time by the high-frequency current transformer (HFCT) serves as the partial discharge signal of the defective section of the polypropylene cable.

[0015] The current signal acquired in real time by the high-frequency current transformer (HFCT) is transmitted to the PC-based data acquisition system through the high-pass filter and then through the high-speed communication interface.

[0016] The cable condition monitoring module collects partial discharge signals of the cable segment in real time, and the data server unit processes the collected partial discharge signals of the cable segment and generates defect identification results for defective segments of polypropylene cables.

[0017] Furthermore, the defective segment of the polypropylene cable includes at least one of the following defects: circumferential cutting marks, irregular grinding, stress cone displacement, and metal spikes.

[0018] Furthermore, the cable segment includes: an old power cable with unknown defects;

[0019] The sensing device also includes a temperature sensor;

[0020] The data acquisition and processing unit includes: a multi-parameter monitoring system;

[0021] The power cable monitoring station is equipped with a control console, a second transformer, a second protective resistor, a voltage divider capacitor, a short-circuit copper busbar, and a through-core induction transformer. AC power is supplied through the second transformer, the second protective resistor, the voltage divider capacitor, the through-core induction transformer, and the old power cable with unknown defects to form a circuit, and voltage and current are applied to the old power cable with unknown defects.

[0022] The current signal collected in real time by the high-frequency current transformer (HFCT) serves as the partial discharge signal of the old power cable with unknown defects.

[0023] The current signal collected in real time by the high-frequency current transformer (HFCT) and the temperature signal collected by the temperature sensor are transmitted to the multi-parameter monitoring system.

[0024] The data server unit processes the partial discharge signals of the old power cables with unknown defects and generates defect identification results for the old power cables with unknown defects.

[0025] Furthermore, the cable segment is an ABC three-phase cable.

[0026] Furthermore, the voltages applied to the cable segments include: 8kV, 10kV, 12kV, 13kV, 15kV, 16kV, 18kV, 20kV, 22kV, and 24kV.

[0027] Furthermore, the partial discharge signal acquisition unit also includes a communication module;

[0028] The communication module transmits the partial discharge signals of the cable segment collected in real time by the cable condition monitoring module to the data server unit.

[0029] Furthermore, the communication module includes multiple data transceivers, each equipped with a 5G communication chip.

[0030] Furthermore, it also includes a display unit;

[0031] The display unit includes: a human-computer interaction channel, a defect identification result display module, and a data integration display module;

[0032] The defect identification result display module is used to display the defect identification results for the partial discharge signal of the cable segment;

[0033] The data integration and display module is used to display the real-time acquired partial discharge signals, the power line to which the cable segment belongs, and the geographical information of the power line where the cable segment is located.

[0034] Furthermore, the data server unit includes a data interface, a partial discharge database, and a power cable defect identification module;

[0035] The power cable defect identification module obtains the partial discharge signal of the cable segment collected in real time by the cable condition monitoring module from the data interface, extracts database data from the partial discharge database, processes the partial discharge signal of the cable segment in combination with the database data, and generates a defect identification result for the partial discharge signal of the cable segment.

[0036] Furthermore, the partial discharge database includes a typical defect discharge database, a partial discharge characteristic database, a device information database, and an offline detection database;

[0037] The partial discharge database stores the received partial discharge signals and the multi-parameter features corresponding to each received partial discharge signal in the partial discharge feature database.

[0038] Additional aspects and advantages of this invention will be set forth in part in the description which follows, and in part will be obvious from the description, or may be learned by practice of the invention. Attached Figure Description

[0039] Various other advantages and benefits will become apparent to those skilled in the art upon reading the following detailed description of preferred embodiments. The accompanying drawings are for illustrative purposes only and are not intended to limit the scope of the invention. Furthermore, the same reference numerals denote the same parts throughout the drawings. In the drawings:

[0040] Figure 1 This is a schematic diagram of the composition of the defect identification device for old power cables based on partial discharge signals according to an embodiment of the present invention;

[0041] Figure 2 A schematic diagram of the test system used to collect partial discharge signals of power cables with known defect types under laboratory conditions;

[0042] Figure 3 A schematic diagram of the test system used to collect partial discharge signals of power cables with unknown defect types under field operating conditions;

[0043] Figure 4 To utilize Figure 2 The test system shown presents PRPD spectra of stress cone displacement defects at various voltage levels (10kV, 16kV, 18kV and 22kV) under laboratory conditions.

[0044] Figure 5 To utilize Figure 2 The test system shown presents PRPD spectra of metal spike defects at various voltage levels (13kV, 16kV, 20kV and 22kV) under laboratory conditions.

[0045] Figure 6 To utilize Figure 2 The test system shown presents PRPD spectra at various voltage levels (8kV, 12kV, 18kV and 24kV) under laboratory conditions for grinding irregular defects.

[0046] Figure 7 To utilize Figure 2 The test system shown presents PRPD spectra of various voltage levels (12kV, 15kV, 20kV and 24kV) under laboratory conditions with circumferential knife mark defects.

[0047] Figure 8 To utilize Figure 2 The experimental system shown illustrates the variation trend of partial discharge of irregular defects from grinding under laboratory conditions with voltage level.

[0048] Figure 9 To utilize Figure 2 The experimental system shown illustrates the variation trend of partial discharge of circumferential cutting marks as a function of voltage level under laboratory conditions.

[0049] Figure 10 To utilize Figure 2 The experimental system shown illustrates the variation of partial discharge of metal spike defects with voltage level under laboratory conditions.

[0050] Figure 11 To utilize Figure 2 The test system shown illustrates the variation trend of partial discharge of stress cone displacement defects with voltage level under laboratory conditions. Detailed Implementation

[0051] Exemplary embodiments of the present disclosure will now be described in more detail with reference to the accompanying drawings. While exemplary embodiments of the present disclosure are shown in the drawings, it should be understood that the present disclosure may be implemented in various forms and should not be limited to the embodiments set forth herein. Rather, these embodiments are provided to enable a more thorough understanding of the present disclosure and to fully convey the scope of the disclosure to those skilled in the art. It should be noted that, unless otherwise specified, embodiments and features in the embodiments of the present invention can be combined with each other.

[0052] Partial discharge in power cables refers to a discharge phenomenon where the applied voltage generates a field strength sufficient to cause breakdown in a localized area of ​​the insulation. Partial discharge signals can indicate the presence of certain types of defects in power cables.

[0053] Phase-related partial discharge (PRPD) maps are used to describe the amplitude (e.g., in picocoulombs pC) and phase angle (e.g., 360 degrees) of partial discharge signals, and can visually demonstrate the partial discharge activity within 360 degrees of one AC cycle.

[0054] Existing power cable defect identification devices based on partial discharge signals struggle to balance real-time performance and accuracy when processing complex and diverse partial discharge signals, leading to missed detections or misjudgments of partial discharge signals and defects.

[0055] like Figure 1 , Figure 2 As shown, the defect identification device for old power cables based on partial discharge signals according to an embodiment of this utility model includes:

[0056] Partial discharge signal acquisition unit and data server unit; the partial discharge signal acquisition unit is installed at the power cable monitoring station; the data server unit is set at a preset distance from the partial discharge signal acquisition unit;

[0057] The partial discharge signal acquisition unit includes a cable condition monitoring module; the cable condition monitoring module includes a data acquisition and processing unit, a sensing device, and a cable segment.

[0058] The cable segment is an ABC three-phase cable;

[0059] The cable segment includes: a defective segment of a polypropylene cable;

[0060] The sensing device includes a high-frequency current transformer (HFCT).

[0061] The data acquisition and processing unit includes: a high-pass filter, a data acquisition card, and a data acquisition system;

[0062] The power cable monitoring station is equipped with a high-voltage control test bench.

[0063] The high-voltage control test bench is equipped with a desktop electrical display device, a first transformer, a first protective resistor, a capacitor voltage divider, and a low-voltage matching unit. The AC power supply forms a circuit through the first transformer, the first protective resistor, the capacitor voltage divider, the low-voltage matching unit, and the desktop electrical display device.

[0064] High voltage is led out through a capacitor divider and applied to the defective section of the polypropylene cable. The current signal collected in real time by the high-frequency current transformer (HFCT) serves as the partial discharge signal of the defective section of the polypropylene cable.

[0065] The current signal acquired in real time by the high-frequency current transformer (HFCT) is transmitted to the PC-based data acquisition system through the high-pass filter and then through the high-speed communication interface.

[0066] The cable condition monitoring module collects partial discharge signals of the cable segment in real time, and the data server unit processes the collected partial discharge signals of the cable segment and generates defect identification results for defective segments of polypropylene cables.

[0067] like Figures 4 to 11 As shown, the defective section of the polypropylene cable includes at least one of the following defects: circumferential cutting marks, irregular grinding, stress cone displacement, and metal spikes.

[0068] like Figure 1 , Figure 3 As shown, in some embodiments, the cable segment includes: an old power cable with unknown defects;

[0069] The sensing device also includes a temperature sensor;

[0070] The data acquisition and processing unit includes: a multi-parameter monitoring system;

[0071] The power cable monitoring station is equipped with a control console, a second transformer, a second protective resistor, a voltage divider capacitor, a short-circuit copper busbar, and a through-core induction transformer. AC power is supplied through the second transformer, the second protective resistor, the voltage divider capacitor, the through-core induction transformer, and the old power cable with unknown defects to form a circuit, and voltage and current are applied to the old power cable with unknown defects.

[0072] The current signal collected in real time by the high-frequency current transformer (HFCT) serves as the partial discharge signal of the old power cable with unknown defects.

[0073] The current signal collected in real time by the high-frequency current transformer (HFCT) and the temperature signal collected by the temperature sensor are transmitted to the multi-parameter monitoring system.

[0074] The data server unit processes the partial discharge signals of the old power cables with unknown defects and generates defect identification results for the old power cables with unknown defects.

[0075] like Figures 4 to 11 As shown, the voltages applied to the cable segments include: 8kV, 10kV, 12kV, 13kV, 15kV, 16kV, 18kV, 20kV, 22kV, and 24kV.

[0076] like Figure 1 As shown, the partial discharge signal acquisition unit also includes a communication module;

[0077] The communication module transmits the partial discharge signals of the cable segment collected in real time by the cable condition monitoring module to the data server unit; the communication module includes multiple data transceivers, and the data transceivers are equipped with 5G communication chips.

[0078] like Figure 1 As shown, the old power cable defect identification device based on partial discharge signals also includes a display unit;

[0079] The display unit includes: a human-computer interaction channel, a defect identification result display module, and a data integration display module;

[0080] The defect identification result display module is used to display the defect identification results for the partial discharge signal of the cable segment;

[0081] The data integration and display module is used to display the real-time acquired partial discharge signals, the power line to which the cable segment belongs, and the geographical information of the power line where the cable segment is located.

[0082] like Figure 1 As shown, the data server unit includes a data interface, a partial discharge database, and a power cable defect identification module;

[0083] The power cable defect identification module obtains the partial discharge signal of the cable segment collected in real time by the cable condition monitoring module from the data interface, extracts database data from the partial discharge database, processes the partial discharge signal of the cable segment in combination with the database data, and generates a defect identification result for the partial discharge signal of the cable segment.

[0084] like Figure 1 As shown, the partial discharge database includes a typical defect discharge database, a partial discharge characteristic database, an equipment information database, and an offline detection database;

[0085] The partial discharge database stores the received partial discharge signals and the multi-parameter features corresponding to each received partial discharge signal in the partial discharge feature database.

[0086] The above-described embodiment of the present invention, which is a defect identification device for old power cables based on partial discharge signals, has a reasonable structure, can process a wide variety of signals, and has a wide voltage range. It is beneficial to reduce the misjudgment rate of defect identification results for old power cables, improve detection efficiency, and meet the needs of condition analysis and evaluation of a large number of old cables.

[0087] like Figure 1 As shown, the defect identification device for old power cables based on partial discharge signals according to this utility model embodiment includes: a display unit 10, a partial discharge signal acquisition unit 20, and a data server unit 30.

[0088] Typically, the partial discharge signal acquisition unit 20 is located at each power cable monitoring station; the data server unit 30 is located in the cloud or at a remote location relative to each partial discharge signal acquisition unit 20, and the physical distance between the two may be thousands of kilometers.

[0089] The display unit 10 includes: a human-machine interaction channel 11 for controlling the switching, function selection, and page selection of the entire device; a defect identification result display module 12 for displaying the defect identification results or discharge mode identification results after real-time monitoring and analysis; and a data integration display module 13 for displaying the real-time collected partial discharge signals (such as pulse waveforms) and the cable segment to which they belong, and displaying the geographical information of the power cable where the cable segment is located based on integrated GIS data.

[0090] The partial discharge signal acquisition unit 20 includes a cable condition monitoring module 21 and a communication module 22. The cable condition monitoring module 21 acquires partial discharge signals from each cable in real time and transmits them to the data server unit 30 through the communication module for data analysis, partial discharge pattern recognition, or defect identification.

[0091] like Figure 1 As shown, the cable status monitoring module includes a data acquisition and processing unit 1, a sensing device 2, and a cable segment 3; the communication module 22 includes multiple data transceivers, each equipped with a 5G communication chip. Power from the power supply cabinet supplies power to the data acquisition and processing unit 1.

[0092] The data server unit 30 includes a data interface 31, a partial discharge database 32, and a power cable defect identification module 33. The power cable defect identification module 33 acquires partial discharge signals of each cable collected in real time by the cable condition monitoring module from the data interface 31, extracts database data from the partial discharge database 32, processes the partial discharge signals of each cable in conjunction with the database data, and generates defect identification results, i.e., defect types, for each cable partial discharge signal. The defect identification results include at least one of the following: circumferential cutting mark defects, grinding irregularities, stress cone displacement defects, and metal spike defects. The defect identification results for each cable partial discharge signal are transmitted back to the display unit 10. Correspondingly, the defect identification result display module 12 displays the defect identification results for each cable partial discharge signal, and the data integration display module 13 displays the waveform of each cable partial discharge signal and the cable segment to which it belongs.

[0093] Specifically, the partial discharge database 32 includes a typical defect discharge database, a partial discharge feature database, an equipment information database, and an offline detection database. The partial discharge database updates the received partial discharge signals in real time. For example, the multi-parameter features corresponding to each received partial discharge signal are stored in the partial discharge feature database as a dataset for training the defect identification model.

[0094] Thus, the old power cable defect identification device based on partial discharge signals includes a display unit, a partial discharge signal acquisition unit, and a data server unit. The display unit functions include: (1) a human-machine interaction channel, used to control the switching, function selection, page selection, and other functions of the entire device; (2) a defect identification result display module, which displays the defect type identification results after real-time monitoring and analysis; and (3) integrated data display, used to display the real-time acquired partial discharge signals and the cable segments to which they belong.

[0095] Thus, the partial discharge signal acquisition unit also includes a communication module, which transmits the real-time acquired cable status information to the data server unit for data analysis and pattern recognition.

[0096] The data server unit includes a data interface 31, a partial discharge database 32, and a defect identification module 33. The data interface receives real-time data collected by the partial discharge signal acquisition unit and sends the results back to the display unit for result presentation. The partial discharge database updates and stores the received partial discharge signals in real time, serving as the dataset for training the defect identification model. The defect identification module 33 employs an incremental learning algorithm based on neural networks. This algorithm can dynamically update the model, maintaining the stability of existing knowledge when introducing new defects. The defect identification model uses an online learning structure, requiring only partial weight updates each time new data is identified, avoiding the waste of computational resources caused by full retraining. The defect identification module performs real-time analysis and pattern recognition on the processed signals using the defect identification model, identifying potential defect types or faults in the cable and generating alarm signals.

[0097] In some embodiments, the old power cable defect identification device also provides statistical analysis functions based on historical data to help technicians conduct more in-depth fault diagnosis.

[0098] In some embodiments, the old power cable defect identification device also provides a monitoring and alarm module, which displays the cable operating status in real time through a display interface. When an abnormal defect type is detected, the system will notify maintenance personnel through audible and visual alarms, SMS and email, and automatically generate a diagnostic report.

[0099] like Figure 2 As shown, when conducting partial discharge signal acquisition tests on power cables with known defects under laboratory conditions, the partial discharge signal acquisition unit set up at the power cable monitoring station includes:

[0100] Defective polypropylene cable sections (cable sections with known defects artificially created), HFCT (high-frequency current transformer), high-pass filter, data acquisition card, PC- or laptop-based data acquisition system, high-voltage control test bench;

[0101] The high-voltage control test bench is equipped with a desktop electrical display device, current transformer, transformer, protective resistor, capacitive voltage divider, and low-voltage matching unit; the AC power supply forms a circuit through the transformer, protective resistor, capacitive voltage divider, low-voltage matching unit, and desktop electrical display device.

[0102] Current transformers are used to detect the supply current and are connected to a desktop electrical display device to display the supply current reading in real time.

[0103] High voltage is drawn out via a capacitor divider and applied to the defective section of the polypropylene cable;

[0104] HFCT installed on a power cable with a defective section of polypropylene cable acquires partial discharge signals in real time.

[0105] The current signal acquired in real time by the HFCT is filtered by a high-pass filter and then transmitted to the data acquisition system through a high-speed communication interface (such as a PCI, PCIe, or USB interface acquisition card).

[0106] The data acquisition system includes a signal processing module, which preprocesses the acquired partial discharge signals, including noise reduction and feature extraction. Specifically, adaptive filtering technology is used to improve signal processing efficiency and ensure high data fidelity.

[0107] The data acquisition system uses an HFCT installed on the power cable to collect partial discharge signals in real time. The collected data is transmitted to the signal processing module via a high-speed communication interface.

[0108] like Figure 3 As shown, when conducting partial discharge signal acquisition tests on old power cables with unknown defects under field operating conditions, the partial discharge signal acquisition unit set up at the power cable monitoring station includes:

[0109] The system includes a polypropylene test cable section (field-operated cable, without artificially introduced defects of known type), a temperature sensor, a high-frequency current transformer, and a multi-parameter monitoring system; the multi-parameter monitoring system includes a high-pass filter, a data acquisition card, and a PC or laptop-based data acquisition system.

[0110] Control console, transformer, protective resistor, voltage divider, shorting copper busbar, feedthrough induction transformer;

[0111] The control console is equipped with a desktop electrical display device, a current transformer, and a low-voltage matching unit. The AC power supply forms a circuit through a transformer, a protective resistor, a capacitor voltage divider, a short-circuiting copper busbar, a through-core induction transformer, and a polypropylene test cable section, and applies voltage and current to the polypropylene test cable section.

[0112] A high-frequency current transformer installed on the polypropylene test cable section collects partial discharge signals in real time.

[0113] Temperature sensors installed on polypropylene test cable sections collect real-time temperature signals from the cable surface or the environment.

[0114] The real-time acquired current or temperature signals are filtered by a high-pass filter and then transmitted to the data acquisition system through a high-speed communication interface (such as a PCI, PCIe, or USB interface acquisition card).

[0115] The data acquisition system includes a signal processing module, which preprocesses the acquired partial discharge signals, including noise reduction and feature extraction. Specifically, adaptive filtering technology is used to improve signal processing efficiency and ensure high data fidelity.

[0116] The data acquisition system uses an HFCT installed on the power cable to collect partial discharge signals in real time. The collected data is transmitted to the signal processing module via a high-speed communication interface.

[0117] above Figure 2 and Figure 3 In partial discharge experiments, the test subjects, experimental environments, and operating environments of the acquisition equipment differ. Therefore, the samples obtained under laboratory conditions and in industrial settings not only differ in quantity but also in the noise or interference within the partial discharge signals. Specifically, Figure 2 The test involves applying voltage to cables with defects. Figure 3 The test involves applying voltage and current simultaneously to an actual operating cable (without any artificially created defects). Figure 2 Only voltage is applied, so the cable will not heat up; Figure 3 An electric current is added, which causes the cable to heat up. Therefore, a temperature sensor is installed, and the multi-parameter monitoring system measures the temperature of the cable.

[0118] Specifically, the normalized partial discharge PRPD patterns monitored in power cables with different types of defects are as follows: Figures 4 to 7 As shown, where, Figure 4 The partial discharge PRPD spectra of power cables under laboratory conditions with stress cone displacement defects at voltage levels of 10kV, 16kV, 18kV and 22kV. Figure 5 PRPD spectra of partial discharge of power cables at voltage levels of 13kV, 16kV, 20kV and 22kV under laboratory conditions with metallic spike defects; Figure 6 PRPD (partial discharge) patterns of power cables at voltage levels of 8kV, 12kV, 18kV, and 24kV under laboratory conditions with irregular defects after grinding. Figure 7 This presents PRPD (partial discharge pulse-damping) patterns of power cables at voltage levels of 12kV, 15kV, 20kV, and 24kV under laboratory conditions with circumferential cutting defects. (This is related to...) Figures 4 to 7 The normalized PRPD maps shown can be used to extract high-dimensional features of VGG, ResNET, SENet, and FPNet maps, as well as color, shape, LBP, and geometric features.

[0119] The pulse parameter characteristics of partial discharge signals extracted from power cables with different types of defects are as follows: Figures 8 to 11 As shown. Figure 8 The diagram shows the variation trend of partial discharge signal with voltage level when there are irregular grinding defects in the cable section under laboratory conditions. The physical meaning of the left vertical axis is the discharge quantity (in pC), and the physical meaning of the right vertical axis is the pulse repetition rate (in pulses / second). Figure 9The partial discharge signal varies with voltage level when there are circumferential cutting marks on the cable section under laboratory conditions. The physical meaning of the left vertical axis is the discharge quantity (in pC), and the physical meaning of the right vertical axis is the pulse repetition rate (in pulses / second). Figure 10 The partial discharge signal varies with voltage level under laboratory conditions when there are metal spike defects in the cable section. The physical meaning of the left vertical axis is the discharge quantity (in pC), and the physical meaning of the right vertical axis is the pulse repetition rate (in pulses / second). Figure 11 This figure shows the variation of partial discharge signal with voltage level under laboratory conditions when a cable section has a stress cone displacement defect. The left vertical axis represents the discharge quantity (in pC), and the right vertical axis represents the pulse repetition rate (in pulses / second). Figures 8 to 11 The pulse parameter characteristics of the partial discharge signals of various power cables shown include: discharge quantity and pulse repetition rate.

[0120] The defect identification device for old power cables proposed in this invention can be divided into two stages when identifying defects in old power cables based on partial discharge signals. The first stage is data acquisition and construction of typical defect samples; the second stage is defect identification based on semi-supervised CNNL incremental learning.

[0121] Specifically, in the first phase, data collection and the construction of typical defect samples include:

[0122] Partial discharge signal acquisition of power cables with typical defects was carried out under laboratory conditions.

[0123] Partial discharge signal acquisition of power cables with unknown defect types in industrial sites;

[0124] Data preprocessing is performed on the partial discharge signals of power cables collected under the above two methods;

[0125] The normalized phase spectrum of the partial discharge signal of each power cable after data preprocessing was determined respectively;

[0126] Using circumferential cutting marks, grinding irregularities, stress cone defects, and metal spike defects as sample labels, multi-parameter features of partial discharge signals of each power cable after data preprocessing were extracted.

[0127] The multi-parameter features include: high-dimensional features of VGG, ResNET, SENet, and FPNet maps; color features, shape features, LBP features, and geometric features; pulse rise time, pulse repetition rate, pulse skewness, and pulse kurtosis.

[0128] Multi-parameter features corresponding to partial discharge signals of power cables collected under laboratory conditions are fused;

[0129] Multi-parameter features corresponding to partial discharge signals of power cables collected in industrial sites are fused.

[0130] In the second stage, a semi-supervised defect identification model based on CNNL is used for defect identification, including:

[0131] S301: Use the multi-parameter features and corresponding defect types of the partial discharge signals of power cables collected under fused laboratory conditions as labeled data to train a CNN-based defect recognition model.

[0132] S302: The multi-parameter features corresponding to the partial discharge signals of power cables collected from the fused industrial site are used as unlabeled data and combined with the trained CNN-based defect recognition model for self-training to generate a semi-supervised defect recognition model based on CNNL.

[0133] Specifically, the self-training of the trained CNN-based defect recognition model generates a semi-supervised defect recognition model based on CNNL, including: taking the characteristic parameters of power cables based on typical defects in the industrial field environment as unlabeled data, extracting 30% of the data with replacement as unlabeled dataset 1 and sending it into the trained CNN-based power cable defect recognition model described in step S301 to obtain pseudo-labels 1 for the unlabeled data in the industrial field.

[0134] S303: Extract 30% of the industrial field data again with replacement as unlabeled dataset 2 and feed it into the CNN-based power cable defect identification model that was trained in step S201. Fine-tune the incremental learner based on pseudo-label 1 to obtain pseudo-label 2.

[0135] S304: For the fine-tuning incremental learner described in steps S302 and S303, by using data feature replay, firstly train the CNN-based power cable defect identification network model by replaying real data, and then replay the generated data based on unlabeled data and its generated pseudo-labels to fine-tune the existing CNN defect identification network, generate a new CNN-based power cable defect identification model, and obtain new pseudo-labels generated for the unlabeled data;

[0136] S305: Repeat the above steps until the CNN-based power cable defect identification network achieves the expected convergence effect, completes the self-training process, and finally obtains a semi-supervised defect identification model based on CNNL (Continuous Neural Network Learning).

[0137] Specifically, a semi-supervised defect identification model based on CNNL is used to perform defect identification based on semi-supervised CNNL incremental learning. In this process, the multi-parameter features corresponding to the partial discharge signals of power cables in the industrial field collected in real time are fused and used as unlabeled data. This data is then combined with the trained semi-supervised defect identification model based on CNNL for self-training, updating the semi-supervised defect identification model based on CNNL, and determining the defect type corresponding to the partial discharge signals of power cables in the industrial field collected in real time.

[0138] In a substation application, the old power cable defect identification device proposed in this invention identifies various complex partial discharge patterns caused by cable aging based on partial discharge signals, thereby identifying the defect type. Experimental results show that the overall identification accuracy reaches over 95%, greatly improving the early warning capability for old cable faults.

[0139] The present invention proposes a defect identification device for old power cables based on partial discharge signals. It is optimized for special partial discharge signals that may occur in old cables, ensuring that partial discharge modes and defect types can still be effectively identified under cable aging conditions, and providing early warning.

[0140] In the description of this specification, the references to terms such as "one embodiment," "some embodiments," "example," "specific example," or "some examples," etc., indicate that a specific feature, structure, material, or characteristic described in connection with that embodiment or example is included in at least one embodiment or example of the present invention. In this specification, the illustrative expressions of the above terms do not necessarily refer to the same embodiment or example. Furthermore, the specific features, structures, materials, or characteristics described may be combined in any suitable manner in one or more embodiments or examples. Moreover, without contradiction, those skilled in the art can combine and integrate the different embodiments or examples described in this specification, as well as the features of different embodiments or examples.

[0141] Although embodiments of the present invention have been shown and described above, it is understood that the above embodiments are exemplary and should not be construed as limiting the present invention. Those skilled in the art can make changes, modifications, substitutions and variations to the above embodiments within the scope of the present invention.

[0142] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of this utility model, and not to limit it; although the utility model has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features; and these modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of this utility model.

[0143] The above description is illustrative only and not restrictive of this utility model. Those skilled in the art will understand that many modifications, variations or equivalents can be made without departing from the spirit and scope defined by the claims, and all such modifications, variations or equivalents will fall within the protection scope of this utility model.

Claims

1. A defect identification device for old power cables based on partial discharge signals, characterized in that, include: Partial discharge signal acquisition unit and data server unit; The partial discharge signal acquisition unit is installed at the power cable monitoring station; the data server unit is set at a preset distance from the partial discharge signal acquisition unit. The partial discharge signal acquisition unit includes a cable condition monitoring module; The cable condition monitoring module includes a data acquisition and processing unit, sensing devices, and cable segments. The cable segment includes: a defective segment of a polypropylene cable; The sensing device includes a high-frequency current transformer (HFCT). The data acquisition and processing unit includes: a high-pass filter, a data acquisition card, and a data acquisition system; The power cable monitoring station is equipped with a high-voltage control test bench. The high-voltage control test bench is equipped with a desktop electrical display device, a first transformer, a first protective resistor, a capacitor voltage divider, and a low-voltage matching unit. The AC power supply forms a circuit through the first transformer, the first protective resistor, the capacitor voltage divider, the low-voltage matching unit, and the desktop electrical display device. High voltage is led out through a capacitor divider and applied to the defective section of the polypropylene cable. The current signal collected in real time by the high-frequency current transformer (HFCT) serves as the partial discharge signal of the defective section of the polypropylene cable. The current signal acquired in real time by the high-frequency current transformer (HFCT) is transmitted to the PC-based data acquisition system through the high-pass filter and then through the high-speed communication interface. The cable condition monitoring module collects partial discharge signals of the cable segment in real time, and the data server unit processes the collected partial discharge signals of the cable segment and generates defect identification results for defective segments of polypropylene cables.

2. The defect identification device for old power cables based on partial discharge signals as described in claim 1, characterized in that, The defective section of the polypropylene cable includes at least one of the following defects: circumferential cutting marks, irregular grinding, stress cone displacement, and metal spikes.

3. The defect identification device for old power cables based on partial discharge signals as described in claim 2, characterized in that, The cable segment includes: old power cables with unknown defects; The sensing device also includes a temperature sensor; The data acquisition and processing unit includes: a multi-parameter monitoring system; The power cable monitoring station is equipped with a control console, a second transformer, a second protective resistor, a voltage divider capacitor, a short-circuit copper busbar, and a through-core induction transformer. AC power is supplied through the second transformer, the second protective resistor, the voltage divider capacitor, the through-core induction transformer, and the old power cable with unknown defects to form a circuit, and voltage and current are applied to the old power cable with unknown defects. The current signal collected in real time by the high-frequency current transformer (HFCT) serves as the partial discharge signal of the old power cable with unknown defects. The current signal collected in real time by the high-frequency current transformer (HFCT) and the temperature signal collected by the temperature sensor are transmitted to the multi-parameter monitoring system. The data server unit processes the partial discharge signals of the old power cables with unknown defects and generates defect identification results for the old power cables with unknown defects.

4. The defect identification device for old power cables based on partial discharge signals as described in claim 3, characterized in that, The cable segment is an ABC three-phase cable.

5. The defect identification device for old power cables based on partial discharge signals as described in claim 4, characterized in that, The voltages applied to the cable segments include: 8kV, 10kV, 12kV, 13kV, 15kV, 16kV, 18kV, 20kV, 22kV and 24kV.

6. The defect identification device for old power cables based on partial discharge signals as described in claim 5, characterized in that, The partial discharge signal acquisition unit also includes a communication module; The communication module transmits the partial discharge signals of the cable segment collected in real time by the cable condition monitoring module to the data server unit.

7. The defect identification device for old power cables based on partial discharge signals as described in claim 6, characterized in that, The communication module includes multiple data transceivers, each equipped with a 5G communication chip.

8. The defect identification device for old power cables based on partial discharge signals as described in claim 7, characterized in that, It also includes a display unit; The display unit includes: a human-computer interaction channel, a defect identification result display module, and a data integration display module; The defect identification result display module is used to display the defect identification results for the partial discharge signal of the cable segment; The data integration and display module is used to display the real-time acquired partial discharge signals, the power line to which the cable segment belongs, and the geographical information of the power line where the cable segment is located.

9. The defect identification device for old power cables based on partial discharge signals as described in claim 8, characterized in that, The data server unit includes a data interface, a partial discharge database, and a power cable defect identification module. The power cable defect identification module obtains the partial discharge signal of the cable segment collected in real time by the cable condition monitoring module from the data interface, extracts database data from the partial discharge database, processes the partial discharge signal of the cable segment in combination with the database data, and generates a defect identification result for the partial discharge signal of the cable segment.

10. The defect identification device for old power cables based on partial discharge signals as described in claim 9, characterized in that, The partial discharge database includes a typical defect discharge database, a partial discharge characteristic database, an equipment information database, and an offline detection database; The partial discharge database stores the received partial discharge signals and the multi-parameter features corresponding to each received partial discharge signal in the partial discharge feature database.

Images