Oiled paper insulation capacitive bushing full fault detection early warning system

Abstract

The invention relates to the field of power equipment monitoring, and discloses an oiled paper insulation capacitive bushing full fault detection early warning system, which comprises a multi-parameter sensor module, a data acquisition and transmission module, a data processing and analysis module and an early warning and decision module, the multi-parameter sensor module comprises an ultrahigh frequency (UHF) sensor which is installed near a sleeve flange plate and is used for monitoring a partial discharge signal in a frequency range of 300MHz-3GHz in the sleeve in real time; a plurality of high-precision optical fiber temperature sensors are arranged on a bushing capacitor core, an insulating oil layer and the surface of a bushing, and various types of sensors such as a partial discharge sensor, a temperature sensor, a pressure sensor, a humidity sensor and the like are integrated; according to the invention, parameter changes of electrical, thermal, mechanical, humidity and the like of the oil-paper insulation capacitive bushing in the operation process can be comprehensively monitored, so that comprehensive detection of various faults is realized, and the limitation of a single detection method is effectively avoided.

Description

Technical Field

[0001] This invention relates to the field of power equipment monitoring, specifically to a full fault detection and early warning system for oil-paper insulated capacitive bushings. Background Technology

[0002] As a key component of power transformers, the oil-paper insulated capacitive bushing plays a crucial role in leading the high voltage inside the transformer to the outside. Its operational reliability directly affects the safe and stable operation of the entire power system. However, in actual operation, due to the combined effects of long-term exposure to high voltage, high current, ambient temperature variations, and mechanical stress, oil-paper insulated capacitive bushings are prone to various faults.

[0003] Currently, there are numerous methods for fault detection in oil-paper insulated capacitive bushings. For example, traditional methods based on electrical parameter measurements, such as measuring the bushing's dielectric loss factor and capacitance, can reflect the bushing's insulation status to some extent, but they have low sensitivity to early, slowly developing faults and often fail to detect potential problems in a timely manner. Infrared thermography can detect abnormal surface temperatures of the bushing; however, this method is ineffective when the fault is located deep inside and has not yet significantly affected the surface temperature. Dissolved gas analysis in oil determines the fault type by detecting the composition and content of dissolved gases in the bushing's insulating oil; however, this method has drawbacks such as long detection cycles, inability to monitor in real time, and difficulty in providing timely warnings for some sudden faults.

[0004] Furthermore, most existing detection methods only monitor and analyze single fault types or single parameters, lacking a comprehensive and integrated assessment of the overall operating status of the bushing. In actual operation, bushing faults are often the result of the interaction of multiple factors, and a single detection method is insufficient to accurately determine the occurrence and development trend of complex faults. Moreover, the data from different detection methods are independent of each other and have not been effectively integrated and analyzed collaboratively, failing to fully realize the potential value of various detection data. Therefore, developing a system and method capable of comprehensively, accurately, and in real-time detecting various faults in oil-paper insulated capacitive bushings and providing timely early warnings is of significant practical importance. Summary of the Invention

[0005] (a) Technical problems to be solved

[0006] To address the shortcomings of existing technologies, this invention provides a full fault detection and early warning system for oil-paper insulated capacitive bushings, which has the advantages of comprehensive coverage of fault types and rapid real-time monitoring and response. It solves the problems of low sensitivity to early and deep fault detection and limitations of single parameter monitoring in existing technologies.

[0007] (II) Technical Solution

[0008] To achieve the above objectives, the present invention provides the following technical solution: a full fault detection and early warning system for oil-paper insulated capacitive bushings, comprising a multi-parameter sensor module, a data acquisition and transmission module, a data processing and analysis module, and an early warning and decision-making module;

[0009] The multi-parameter sensor module includes: an ultra-high frequency (UHF) sensor installed near the bushing flange for real-time monitoring of partial discharge signals in the 300MHz-3GHz frequency range inside the bushing; several high-precision fiber optic temperature sensors arranged on the bushing capacitor core, insulating oil layer, and bushing surface, with a measurement accuracy of ±0.1℃, for real-time monitoring of temperature changes in various parts; a pressure sensor tightly connected to the bushing oil inlet via a customized threaded interface for real-time monitoring of insulating oil pressure changes inside the bushing; and a polymer thin-film capacitive humidity sensor installed inside the bushing near the insulating paper layer for real-time monitoring of insulating paper humidity changes.

[0010] The data acquisition and transmission module uses a high-speed, high-precision data acquisition card to acquire the signals output by the multi-parameter sensor module, and transmits the digital signals after analog-to-digital conversion to the data processing and analysis module in real time through 5G wireless transmission technology.

[0011] The data processing and analysis module uses signal processing methods such as wavelet transform to denoise and extract features from the partial discharge signal. Combining the changing trends of parameters such as temperature, pressure, and humidity, it uses support vector machine (SVM) and random forest machine learning algorithms to construct a fault diagnosis model to determine the bushing's operating status, fault type, and severity.

[0012] The early warning and decision-making module, based on the results of the data processing and analysis module, will issue early warning signals to maintenance personnel through audible and visual alarms and SMS notifications when it is determined that the bushing has malfunctioned or its operating status is abnormal. It will also provide corresponding decision-making suggestions in conjunction with the pre-set emergency plan.

[0013] Preferably, the ultra-high frequency sensor is waterproof and dustproof, and its orientation and position are optimized during installation to achieve the best sensitivity. The temperature sensor is fixed to the part being measured by a special mounting clamp. For the sleeve surface temperature sensor, its installation position is selected to avoid the influence of external factors such as direct sunlight and rain.

[0014] Preferably, the oil inlet of the pressure sensor is cleaned and inspected before installation, and calibrated after installation to ensure measurement accuracy; the humidity sensor is fixed inside the sleeve near the insulating paper layer with an insulating bracket and is treated with moisture protection.

[0015] Preferably, the sampling frequency, sampling accuracy, and other parameters of the data acquisition card are set according to the sensor signal type and output range.

[0016] Preferably, the wireless communication module performs encryption processing when transmitting data to ensure data transmission security.

[0017] Preferably, in the data processing and analysis module, data processing algorithms and fault diagnosis models are written using programming languages ​​such as Python and MATLAB.

[0018] Preferably, the warning threshold of the warning and decision-making module is set according to actual needs, and the warning information and decision suggestions are clear, concise and feasible.

[0019] Preferably, the wavelet transform denoising formula is as follows:

[0020]

[0021] Among them, W T (a,b) are wavelet transform coefficients, a is the scaling factor, b is the translation factor, x(t) is the original partial discharge signal, and ψ(·) is the wavelet basis function.

[0022] Preferably, the Support Vector Machine (SVM) classification function is:

[0023]

[0024] Where, α i For Lagrange multipliers, y i Let K(x) be the sample label. i ,x) is the kernel function, b is the bias term, and sgn(·) is the sign function.

[0025] A method for full fault detection and early warning of oil-paper insulated capacitive bushings includes the following steps:

[0026] Step 1: Data Acquisition Steps: The multi-parameter sensor module collects parameters such as partial discharge signal, temperature, pressure, and humidity of the bushing in real time, and transmits the analog signals to the data acquisition and transmission module;

[0027] Step 2, Data Preprocessing: The data acquisition and transmission module performs analog-to-digital conversion on the signal and then transmits it to the data processing and analysis module. The data processing and analysis module uses wavelet transform to denoise the partial discharge signal and uses minimum-maximum normalization to normalize parameters such as temperature, pressure, and humidity.

[0028] Step 3, Fault Feature Extraction Step: Fourier transform is used to extract frequency features from the preprocessed partial discharge signal, and characteristic parameters such as amplitude and phase are calculated. For parameters such as temperature, pressure, and humidity, characteristic quantities such as rate of change, rate of rise, and magnitude of increase are calculated.

[0029] Step 4, Fault Diagnosis and Early Warning: Input the extracted fault feature parameters into the pre-trained Support Vector Machine (SVM) fault diagnosis model. The model judges the operating status of the bushing. When a fault or abnormality exists, the early warning and decision-making module issues an early warning signal and provides decision suggestions.

[0030] (III) Beneficial Effects

[0031] Compared with the prior art, the present invention provides a full fault detection and early warning system for oil-paper insulated capacitive bushings, which has the following beneficial effects:

[0032] 1. By integrating various types of sensors such as partial discharge sensors, temperature sensors, pressure sensors, and humidity sensors, it can comprehensively monitor changes in electrical, thermal, mechanical, and humidity parameters of oil-paper insulated capacitive bushings during operation, thereby achieving comprehensive detection of various faults and effectively avoiding the limitations of single detection methods.

[0033] 2. This invention can collect and process bushing operation data in real time. Once an abnormality is detected, it can immediately issue an early warning signal to promptly remind maintenance personnel to take corresponding measures. Compared with traditional detection methods, it greatly shortens the time for fault detection and handling, and effectively reduces the impact of faults on power system operation.

[0034] 3. This invention employs advanced data processing and analysis algorithms to fuse and analyze multi-source sensor data, fully exploring the correlation information between various types of data, thereby improving the accuracy and reliability of fault diagnosis. By comprehensively considering the changes in multiple parameters, it can more accurately determine the type and severity of the fault, providing a strong basis for formulating reasonable maintenance strategies.

[0035] 4. This invention, through the combination of early warning and decision-making modules and fault diagnosis results, can provide intelligent decision-making suggestions for operation and maintenance personnel, helping them to quickly formulate reasonable maintenance plans, thereby improving the efficiency and quality of operation and maintenance work. At the same time, the system can also predict the remaining life of the bushing based on historical data and operating experience, providing a reference for equipment upgrades and renovations. Attached Figure Description

[0036] Figure 1 Here is a flowchart of a full fault detection and early warning system for oil-paper insulated capacitive bushings proposed in this invention;

[0037] Figure 2 This is a flowchart illustrating the steps of a full fault detection and early warning method for an oil-paper insulated capacitor bushing proposed in this invention. Detailed Implementation

[0038] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0039] Example:

[0040] See attached document Figures 1 to 2 As shown, a full fault detection and early warning system for oil-paper insulated capacitive bushings includes a multi-parameter sensor module, a data acquisition and transmission module, a data processing and analysis module, and an early warning and decision-making module.

[0041] The multi-parameter sensor module includes: an ultra-high frequency (UHF) sensor installed near the bushing flange for real-time monitoring of partial discharge signals in the 300MHz-3GHz frequency range inside the bushing;

[0042] Specifically, the ultra-high frequency sensor is tightly installed in the flange gap of the bushing to ensure that the sensor can effectively receive partial discharge signals generated inside the bushing. During installation, attention should be paid to the orientation and position of the sensor to ensure its sensitivity is at its optimal level. At the same time, the sensor should be waterproofed and dustproofed to withstand harsh outdoor working environments.

[0043] Several high-precision fiber optic temperature sensors are arranged on the bushing capacitor core, insulating oil layer and bushing surface, with a measurement accuracy of ±0.1℃, for real-time monitoring of temperature changes in various parts;

[0044] Specifically, specialized mounting clamps are used to secure fiber optic temperature sensors to key components such as the capacitor core, insulating oil layer, and surface of the bushing. This ensures tight contact between the sensor and the measured area, guaranteeing accurate temperature measurements. For temperature sensors on the bushing surface, suitable installation locations should be chosen to avoid the influence of external factors such as direct sunlight and rain.

[0045] A pressure sensor, which is tightly connected to the oil inlet of the bushing via a custom threaded interface, is used to monitor changes in the pressure of the insulating oil inside the bushing in real time.

[0046] Specifically, the pressure sensor is tightly connected to the oil inlet of the bushing via a customized threaded interface. Before installation, the oil inlet must be cleaned and inspected to ensure a good seal at the connection point and prevent leakage of insulating oil. After installation, the pressure sensor is calibrated to ensure its measurement accuracy meets requirements.

[0047] A polymer film capacitive humidity sensor is installed inside the sleeve near the insulating paper layer to monitor changes in the humidity of the insulating paper in real time.

[0048] Specifically, an insulating bracket is used to fix the humidity sensor inside the sleeve, near the insulating paper layer. During installation, care must be taken to avoid damaging the insulating paper layer, while ensuring the sensor can accurately measure changes in the humidity of the insulating paper. The humidity sensor should be treated with moisture-proof measures to prevent damage in high-humidity environments.

[0049] The data acquisition and transmission module uses a high-speed, high-precision data acquisition card to acquire signals output by the multi-parameter sensor module, and transmits the digital signals after analog-to-digital conversion to the data processing and analysis module in real time through 5G wireless transmission technology.

[0050] Specifically, a high-speed, high-precision data acquisition card is selected and connected to the output of the multi-parameter sensor module. Based on the sensor's signal type and output range, the sampling frequency, sampling accuracy, and other parameters of the data acquisition card are set to ensure accurate acquisition of sensor signals. The data acquired by the data acquisition card is transmitted in real-time to the data processing and analysis module via a wireless communication module, such as a 5G communication module. When configuring the wireless communication module, it is essential to ensure stable signal strength and a communication rate that meets data transmission requirements. Simultaneously, the communication data is encrypted to guarantee data transmission security.

[0051] The data processing and analysis module uses signal processing methods such as wavelet transform to denoise and extract features from partial discharge signals. Combining the changing trends of parameters such as temperature, pressure, and humidity, it uses support vector machine (SVM) and random forest machine learning algorithms to build a fault diagnosis model to determine the bushing's operating status, fault type, and severity.

[0052] Specifically, advanced data processing and analysis software is installed in the data processing and analysis module. Data processing algorithms and fault diagnosis models are developed using programming languages ​​such as Python and MATLAB. Signal processing methods such as wavelet transform and Fourier transform are employed to denoise and extract features from partial discharge signals; machine learning algorithms such as support vector machine (SVM) and random forest are used to classify and predict the operating status of the bushing. When building the fault diagnosis model, a large amount of bushing operating data is collected, including normal operation data and various fault data, to train and optimize the model, improving its accuracy and reliability.

[0053] The early warning and decision-making module, based on the results of the data processing and analysis module, will issue early warning signals to maintenance personnel through audible and visual alarms and SMS notifications when it is determined that the bushing has malfunctioned or its operating status is abnormal. It will also provide corresponding decision-making suggestions in conjunction with the pre-set emergency plan.

[0054] Specifically, the early warning and decision-making module should be configured according to actual needs. An early warning threshold should be set; when the results from the data processing and analysis module exceed the threshold, the early warning and decision-making module should immediately activate the early warning mechanism. Appropriate early warning methods should be selected, such as audible and visual alarms or SMS notifications, and the early warning information should be promptly sent to maintenance personnel. Simultaneously, based on pre-established emergency plans, corresponding decision-making suggestions should be provided to maintenance personnel, such as fault type, fault severity, and repair measures. When configuring the early warning and decision-making module, the actual needs and operating habits of maintenance personnel should be fully considered to ensure that the early warning information is clear and concise, and the decision-making suggestions are practical and feasible.

[0055] Furthermore, the ultra-high frequency sensor is waterproof and dustproof. Its orientation and position are optimized during installation to achieve the best sensitivity. The temperature sensor is fixed to the measured part by a special mounting clamp. For the sleeve surface temperature sensor, its installation position is selected to avoid the influence of external factors such as direct sunlight and rain.

[0056] Furthermore, the oil inlet of the pressure sensor is cleaned and inspected before installation, and calibration is performed after installation to ensure measurement accuracy; the humidity sensor is fixed inside the sleeve near the insulating paper layer with an insulating bracket and is treated with moisture protection.

[0057] Furthermore, the sampling frequency, sampling accuracy, and other parameters of the data acquisition card are set according to the sensor signal type and output range.

[0058] Furthermore, the wireless communication module encrypts data during transmission to ensure data transmission security.

[0059] Furthermore, in the data processing and analysis module, data processing algorithms and fault diagnosis models are written using programming languages ​​such as Python and MATLAB.

[0060] Furthermore, the warning thresholds of the early warning and decision-making module can be set according to actual needs, and the warning information and decision-making suggestions are clear, concise, and feasible.

[0061] Furthermore, the wavelet transform denoising formula is as follows:

[0062]

[0063] Among them, W T (a,b) are wavelet transform coefficients, a is the scaling factor, b is the translation factor, x(t) is the original partial discharge signal, and ψ(·) is the wavelet basis function.

[0064] Furthermore, the Support Vector Machine (SVM) classification function:

[0065]

[0066] Where, α i For Lagrange multipliers, y i Let K(x) be the sample label. i ,x) is the kernel function, b is the bias term, and sgn(·) is the sign function.

[0067] A method for full fault detection and early warning of oil-paper insulated capacitive bushings includes the following steps:

[0068] Step 1: Data Acquisition Steps: The multi-parameter sensor module collects parameters such as partial discharge signal, temperature, pressure, and humidity of the bushing in real time, and transmits the analog signals to the data acquisition and transmission module;

[0069] Step 2, Data Preprocessing: The data acquisition and transmission module performs analog-to-digital conversion on the signal and then transmits it to the data processing and analysis module. The data processing and analysis module uses wavelet transform to denoise the partial discharge signal and uses minimum-maximum normalization to normalize parameters such as temperature, pressure, and humidity.

[0070]

[0071] Where, x′ i For the normalized data, x i The original data is given, min(x) is the minimum value of the sample, and max(x) is the maximum value of the sample.

[0072] Step 3, Fault Feature Extraction Step: Fourier transform is used to extract frequency features from the preprocessed partial discharge signal, and characteristic parameters such as amplitude and phase are calculated. For parameters such as temperature, pressure, and humidity, characteristic quantities such as rate of change, rate of rise, and magnitude of increase are calculated.

[0073]

[0074] Where X(f) is the Fourier transform result, x(t) is the time-domain signal, f is the frequency, and j is the imaginary unit.

[0075]

[0076] Where r is the rate of change of the parameter, and p2 and p1 are the parameter values ​​at times t2 and t1, respectively.

[0077] Step 4, Fault Diagnosis and Early Warning: Input the extracted fault feature parameters into the pre-trained Support Vector Machine (SVM) fault diagnosis model. The model judges the operating status of the bushing. When a fault or abnormality exists, the early warning and decision-making module issues an early warning signal and provides decision suggestions.

[0078] Specific implementation methods:

[0079] Data Acquisition: The multi-parameter sensor module acquires parameters such as partial discharge signals, temperature, pressure, and humidity of the bushing in real time according to the set sampling frequency. The partial discharge sensor converts the detected ultra-high frequency signal into an electrical signal output; the temperature sensor converts temperature changes into optical or electrical signals output; the pressure sensor converts changes in insulating oil pressure into electrical signals output; and the humidity sensor converts changes in the humidity of the insulating paper into electrical signals output. These analog signals are transmitted to the data acquisition and transmission module via cable.

[0080] Data preprocessing: The data acquisition and transmission module performs analog-to-digital conversion on the acquired analog signals, converting them into digital signals before transmitting them to the data processing and analysis module. In the data processing and analysis module, the partial discharge signal is first denoised. Using wavelet transform, with appropriate wavelet basis functions and decomposition levels selected, the partial discharge signal is decomposed into multiple layers to remove noise and retain useful partial discharge characteristic signals. Then, parameters such as temperature, pressure, and humidity are normalized. A minimum-maximum normalization method is used to map the values ​​of each parameter to the [0,1] interval, eliminating the influence of different dimensions between parameters for subsequent comprehensive analysis.

[0081] Fault Feature Extraction: The preprocessed partial discharge signal is converted from a time-domain signal to a frequency-domain signal using Fourier transform to extract its frequency characteristics. Simultaneously, characteristic parameters such as amplitude and phase of the partial discharge signal are calculated. For parameters such as temperature, pressure, and humidity, characteristic quantities such as rate of change, rate of rise, and magnitude of increase are calculated. For example, when calculating the rate of temperature change, the temperature difference between two adjacent sampling times is divided by the sampling time interval; when calculating the rate of pressure rise, the pressure change over a period of time is divided by that time interval. By extracting these fault feature parameters, the operating status of the bushing can be more comprehensively reflected.

[0082] Fault Diagnosis and Early Warning: Extracted fault feature parameters are input into a pre-trained fault diagnosis model, which uses a Support Vector Machine (SVM) algorithm to classify and predict the operating status of the bushing. Based on the input fault feature parameters, the SVM model finds an optimal classification hyperplane in the feature space, classifying the bushing's operating status into different categories such as normal, minor fault, and severe fault. When the model determines that the bushing has a fault or an abnormal operating status, the early warning and decision-making module immediately issues an early warning signal. Based on the fault type and severity, appropriate decision recommendations are selected from pre-defined emergency plans. For example, for minor faults, it is recommended to strengthen monitoring and shorten the inspection cycle; for severe faults, it is recommended to immediately shut down power for repair, and specific repair plans are provided.

[0083] It should be noted that the term "comprising" or any other variation thereof is intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes said element.

[0084] Although embodiments of the invention have been shown and described, it will be understood by those skilled in the art that various changes, modifications, substitutions and alterations can be made to these embodiments without departing from the principles and spirit of the invention, the scope of which is defined by the appended claims and their equivalents.

Claims

1. A full fault detection and early warning system for oil-paper insulated capacitive bushings, characterized in that, It includes a multi-parameter sensor module, a data acquisition and transmission module, a data processing and analysis module, and an early warning and decision-making module; The multi-parameter sensor module includes: an ultra-high frequency (UHF) sensor installed near the bushing flange for real-time monitoring of partial discharge signals in the 300MHz-3GHz frequency range inside the bushing; several high-precision fiber optic temperature sensors arranged on the bushing capacitor core, insulating oil layer, and bushing surface, with a measurement accuracy of ±0.1℃, for real-time monitoring of temperature changes in various parts; a pressure sensor tightly connected to the bushing oil inlet via a customized threaded interface for real-time monitoring of insulating oil pressure changes inside the bushing; and a polymer thin-film capacitive humidity sensor installed inside the bushing near the insulating paper layer for real-time monitoring of insulating paper humidity changes. The data acquisition and transmission module uses a high-speed, high-precision data acquisition card to acquire the signals output by the multi-parameter sensor module, and transmits the digital signals after analog-to-digital conversion to the data processing and analysis module in real time through 5G wireless transmission technology. The data processing and analysis module uses signal processing methods such as wavelet transform to denoise and extract features from the partial discharge signal. Combining the changing trends of parameters such as temperature, pressure, and humidity, it uses support vector machine (SVM) and random forest machine learning algorithms to construct a fault diagnosis model to determine the bushing's operating status, fault type, and severity. The early warning and decision-making module, based on the results of the data processing and analysis module, will issue early warning signals to maintenance personnel through audible and visual alarms and SMS notifications when it is determined that the bushing has malfunctioned or its operating status is abnormal. It will also provide corresponding decision-making suggestions in conjunction with the pre-set emergency plan.

2. The oil-paper insulated capacitive bushing full fault detection and early warning system according to claim 1, characterized in that: The ultra-high frequency sensor is waterproof and dustproof. Its orientation and position are optimized during installation to achieve the best sensitivity. The temperature sensor is fixed to the part being measured by a special mounting clamp. For the sleeve surface temperature sensor, its installation position is selected to avoid the influence of external factors such as direct sunlight and rain.

3. The oil-paper insulated capacitive bushing full fault detection and early warning system according to claim 1, characterized in that: Before installation, the oil inlet of the pressure sensor is cleaned and inspected, and after installation, it is calibrated to ensure measurement accuracy. The humidity sensor is fixed inside the sleeve near the insulating paper layer with an insulating bracket and is treated to prevent moisture.

4. The oil-paper insulated capacitive bushing full fault detection and early warning system according to claim 1, characterized in that: The sampling frequency, sampling accuracy, and other parameters of the data acquisition card are set according to the sensor signal type and output range.

5. The oil-paper insulated capacitive bushing full fault detection and early warning system according to claim 1, characterized in that: The wireless communication module encrypts data during transmission to ensure data transmission security.

6. The oil-paper insulated capacitive bushing full fault detection and early warning system according to claim 1, characterized in that: In the data processing and analysis module, data processing algorithms and fault diagnosis models are written using programming languages ​​such as Python and MATLAB.

7. The full fault detection and early warning system for oil-paper insulated capacitive bushings according to claim 1, characterized in that: The warning threshold of the warning and decision-making module is set according to actual needs, and the warning information and decision suggestions are clear, concise and feasible.

8. The oil-paper insulated capacitive bushing full fault detection and early warning system according to claim 1, characterized in that: The wavelet transform denoising formula is as follows: Among them, W T (a,b) are wavelet transform coefficients, a is the scaling factor, b is the translation factor, x(t) is the original partial discharge signal, and ψ(·) is the wavelet basis function.

9. The oil-paper insulated capacitor bushing full fault detection and early warning system according to claim 1, characterized in that: The Support Vector Machine (SVM) classification function: Where, α i For Lagrange multipliers, y i Let K(x) be the sample label. i ,x) is the kernel function, b is the bias term, and sgn(·) is the sign function.

10. The method for full fault detection and early warning of oil-paper insulated capacitive bushings according to any one of claims 1-9, characterized in that, Includes the following steps: Step 1: Data Acquisition Steps: The multi-parameter sensor module collects parameters such as partial discharge signal, temperature, pressure, and humidity of the bushing in real time, and transmits the analog signals to the data acquisition and transmission module; Step 2, Data Preprocessing: The data acquisition and transmission module performs analog-to-digital conversion on the signal and then transmits it to the data processing and analysis module. The data processing and analysis module uses wavelet transform to denoise the partial discharge signal and uses minimum-maximum normalization to normalize parameters such as temperature, pressure, and humidity. Step 3, Fault Feature Extraction Step: Fourier transform is used to extract frequency features from the preprocessed partial discharge signal, and characteristic parameters such as amplitude and phase are calculated. For parameters such as temperature, pressure, and humidity, characteristic quantities such as rate of change, rate of rise, and magnitude of increase are calculated. Step 4, Fault Diagnosis and Early Warning: Input the extracted fault feature parameters into the pre-trained Support Vector Machine (SVM) fault diagnosis model. The model judges the operating status of the bushing. When a fault or abnormality exists, the early warning and decision-making module issues an early warning signal and provides decision suggestions.

Images