A non-intrusive partial discharge monitoring and early warning method and system for a small ring network box

Abstract

The present invention discloses a non-intrusive partial discharge monitoring and early warning method and system for a small ring network box, which relates to the technical field of power equipment monitoring, including obtaining partial discharge signals and environmental data; performing preliminary processing on partial discharge signals; extracting partial discharge features and constructing partial discharge feature vectors; constructing a dynamic threshold algorithm; dividing partial discharge risk levels according to partial discharge feature vectors and in combination with dynamic thresholds; and implementing early warning strategies at different levels. The signal quality and analysis accuracy are enhanced through preliminary processing such as signal amplification, filtering, and analog-to-digital conversion. The partial discharge features are deeply refined by combining fast Fourier transform and amplitude calculation, and feature vectors are constructed by integrating multivariate information. The dynamic threshold algorithm and risk level division mechanism of environmental factors are introduced, which realizes the full-chain optimization of partial discharge monitoring from precise signal extraction, intelligent feature analysis to efficient early warning strategies, greatly improving the accuracy, adaptability, and operation and maintenance efficiency of power equipment fault early warning.

Description

Technical Field

[0001] The present invention relates to the technical field of power equipment monitoring, and in particular to a non-intrusive partial discharge monitoring and early warning method and system for a small ring network box. Background Art

[0002] The intelligentization of power systems has led to an upgrade in the demand for small ring network box monitoring technology. Non-intrusive partial discharge monitoring technology has attracted much attention due to its advantage of non-stop power supply. Existing technologies are mainly faced with three major challenges: environmental noise interference, insufficient consideration of environmental factors, and limited early warning accuracy. Especially in complex power distribution environments, it is particularly important to effectively distinguish partial discharge signals.

[0003] The present invention introduces an innovative monitoring and early warning solution, which configures multiple sensors around the ring network box, synchronously monitors partial discharge signals and environmental parameters, and purifies signals through preprocessing. The core of this solution is to deeply analyze signal characteristics, build a dynamic threshold model, consider the impact of equipment aging, and improve the dynamic adaptability of risk assessment. Finally, the risk level is divided according to the characteristic vector and dynamic threshold, and corresponding early warning measures are taken, which enhances the practicality and accuracy of the monitoring system and provides a more intelligent and efficient solution for power operation and maintenance. Summary of the invention

[0004] In view of the above existing problems, the present invention is proposed.

[0005] Therefore, the present invention provides a non-intrusive partial discharge monitoring and early warning method and system for a small ring network box to solve the problems of environmental noise interference, insufficient consideration of environmental factors and limited early warning accuracy.

[0006] In order to solve the above technical problems, the present invention provides the following technical solutions:

[0007] In a first aspect, an embodiment of the present invention provides a non-intrusive partial discharge monitoring and early warning method for a small ring network box, which includes obtaining partial discharge signals and environmental data based on multiple sensors;

[0008] Carry out preliminary processing of partial discharge signals;

[0009] Based on the processed partial discharge signal, partial discharge features are extracted and partial discharge feature vectors are constructed;

[0010] Build a dynamic threshold algorithm based on historical partial discharge signals and environmental data;

[0011] Based on the partial discharge feature vector and dynamic threshold, the partial discharge risk level is divided;

[0012] Implement different levels of early warning strategies according to the level of partial discharge risk.

[0013] As a preferred solution of the non-intrusive partial discharge monitoring and early warning method for a small ring network box described in the present invention, the multiple sensors include ultrasonic sensors, transient voltage-to-ground sensors and environmental sensors.

[0014] As a preferred solution of the non-intrusive partial discharge monitoring and early warning method for a small ring network box of the present invention, the preliminary processing of the partial discharge signal includes:

[0015] Set the partial discharge signal to , the gain factor is , the amplified partial discharge signal It is expressed as,

[0016] ,

[0017] The amplified partial discharge signal , use a bandpass filter to remove abnormal frequency components;

[0018] The PD signal with abnormal frequency components removed Use analog-to-digital conversion to digitize partial discharge signals , the formula is expressed as,

[0019] ,

[0020] In the formula, represents the ADC reference voltage, m represents the number of bits of the converter, Indicates rounding to the nearest integer;

[0021] Use moving average filtering to filter S consecutive partial discharge signals Noise reduction processing is performed, and the signal after noise reduction It is expressed as,

[0022] ,

[0023] In the formula, represents the PD signal value at time t after noise reduction, Indicates that at the kth time point The partial discharge signal value, k represents the time variable, Indicates time, S indicates partial discharge signal The number of .

[0024] As a preferred solution of the non-intrusive partial discharge monitoring and early warning method for a small ring network box of the present invention, wherein: the extraction of partial discharge features includes:

[0025] After processing, the partial discharge signal The fast Fourier transform is used to calculate the spectrum characteristics, and the formula is expressed as:

[0026] ,

[0027] In the formula, Indicates at frequency point The spectrum amplitude at is the processed value of the nth sampling point value, Indicates the total number of sampling points;

[0028] The average amplitude and maximum amplitude are calculated for a specific frequency point. The formula is:

[0029] ,

[0030] ,

[0031] In the formula, represents the average amplitude, Indicates the maximum magnitude;

[0032] Get partial discharge characteristics .

[0033] As a preferred solution of the non-intrusive partial discharge monitoring and early warning method for a small ring network box of the present invention, wherein: the construction of the partial discharge feature vector refers to weighted fusion of the partial discharge features to construct the partial discharge feature vector , the formula is expressed as,

[0034] ,

[0035] in, represents the weight of the spectrogram feature, represents the weight of the average amplitude, Indicates the weight of the maximum magnitude.

[0036] As a preferred solution of the non-intrusive partial discharge monitoring and early warning method for a small ring network box described in the present invention, the environmental data includes humidity and temperature.

[0037] As a preferred solution of the non-intrusive partial discharge monitoring and early warning method for a small ring network box of the present invention, wherein: the dynamic threshold algorithm is constructed based on historical partial discharge signals and environmental data, including:

[0038] Define the temperature as , humidity is , the baseline threshold is set based on the historical partial discharge signal ;

[0039] Based on the PD eigenvector ,temperature and humidity , construct feature integration function , expressed as,

[0040] ,

[0041] Based on temperature and humidity , construct the environmental impact function , expressed as,

[0042] ,

[0043] In the formula, Indicates time, Indicates the maximum time range;

[0044] Based on baseline threshold , feature integration function and environmental impact function , construct a dynamic threshold algorithm, the formula is expressed as,

[0045] ,

[0046] In the formula, represents the dynamic threshold, represents the normalization parameter, Indicates the adjustment factor for environmental impact.

[0047] As a preferred solution of the non-intrusive partial discharge monitoring and early warning method for a small ring network box of the present invention, the partial discharge risk level is divided based on the partial discharge feature vector and the dynamic threshold, including:

[0048] Using the PD eigenvector With dynamic threshold , calculate the risk index , expressed as,

[0049] ,

[0050] In the formula, is the feature weight vector;

[0051] Set the first risk threshold to , the second risk threshold is , ;

[0052] when It is defined as the first risk level. It is defined as the second risk level. It is defined as the third risk level.

[0053] As a preferred solution of the non-intrusive partial discharge monitoring and early warning method of the small ring network box of the present invention, wherein: the early warning strategies of different levels are implemented according to the partial discharge risk level, including:

[0054] When the risk level is the first, the first-level warning is triggered, the system automatically records the first risk event, and notifies the operation and maintenance personnel via SMS to conduct routine inspections on related equipment;

[0055] When the risk level reaches the second level, the second-level warning is triggered, which immediately triggers an instant alarm and notifies the operation and maintenance team through the emergency communication system to conduct an on-site inspection;

[0056] When it is at the third risk level, the third level warning is triggered, the equipment emergency shutdown procedure is immediately executed, the faulty equipment is quickly isolated, the emergency response team is activated, on-site command and coordination are carried out, comprehensive fault diagnosis is performed, the third risk event is analyzed, and the preventive maintenance and monitoring strategies are updated.

[0057] In a second aspect, the present invention provides a non-intrusive partial discharge monitoring and early warning system for a small ring network box, including a data acquisition module for acquiring partial discharge signals and environmental data based on a variety of sensors;

[0058] A signal preprocessing module is used to perform preliminary processing on the partial discharge signal;

[0059] A vector construction module, used for extracting partial discharge features and constructing partial discharge feature vectors based on the processed partial discharge signal;

[0060] Dynamic threshold algorithm module, used to build a dynamic threshold algorithm based on historical partial discharge signals and environmental data;

[0061] A risk level classification module is used to classify the partial discharge risk level based on the partial discharge feature vector and the dynamic threshold;

[0062] The early warning strategy implementation module is used to implement early warning strategies of different levels according to the partial discharge risk level.

[0063] In a third aspect, an embodiment of the present invention provides a computer device, comprising a memory and a processor, wherein the memory stores a computer program, wherein: when the computer program is executed by the processor, any step of the non-intrusive partial discharge monitoring and early warning method for a small ring network box as described in the first aspect of the present invention is implemented.

[0064] In a fourth aspect, an embodiment of the present invention provides a computer-readable storage medium having a computer program stored thereon, wherein: when the computer program is executed by a processor, any step of the non-intrusive partial discharge monitoring and early warning method for a small ring network box as described in the first aspect of the present invention is implemented.

[0065] The beneficial effects of the present invention are as follows: signal quality and analysis accuracy are enhanced through preliminary processing such as signal amplification, filtering and analog-to-digital conversion; local discharge characteristics are deeply refined by combining fast Fourier transform and amplitude calculation and feature vectors are constructed by integrating multivariate information; a dynamic threshold algorithm and a risk level division mechanism for environmental factors are introduced, thereby achieving full-chain optimization of local discharge monitoring from precise signal extraction, intelligent feature analysis to efficient early warning strategies, greatly improving the accuracy, adaptability and operation and maintenance efficiency of power equipment fault early warning, and ensuring the safety and stability of power grid operation. BRIEF DESCRIPTION OF THE DRAWINGS

[0066] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the accompanying drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other accompanying drawings can be obtained based on these accompanying drawings without paying creative work.

[0067] Figure 1 This is a flow chart of the non-intrusive partial discharge monitoring and early warning method for small and medium-sized ring network boxes in Example 1.

[0068] Figure 2 This is a determination diagram of risk level and warning level in Example 1. DETAILED DESCRIPTION

[0069] In order to make the above-mentioned objects, features and advantages of the present invention more obvious and easy to understand, the specific implementation methods of the present invention are described in detail below in conjunction with the accompanying drawings.

[0070] Example 1, reference Figure 1 and Figure 2 , which is the first embodiment of the present invention, and provides a non-intrusive partial discharge monitoring and early warning method for a small ring network box, comprising the following steps:

[0071] S1. Obtain partial discharge signals and environmental data based on multiple sensors;

[0072] Carry out preliminary processing of partial discharge signals;

[0073] Based on the processed partial discharge signal, partial discharge features are extracted and partial discharge feature vectors are constructed;

[0074] Build a dynamic threshold algorithm based on historical partial discharge signals and environmental data;

[0075] Based on the partial discharge characteristic vector and combined with the dynamic threshold, the partial discharge risk level is divided;

[0076] Implement different levels of early warning strategies according to the level of partial discharge risk.

[0077] A variety of sensors including ultrasonic sensors, transient ground voltage sensors, and environmental sensors;

[0078] Partial discharge signals include ultrasonic signals and transient voltage-to-ground signals.

[0079] S2. Preliminary processing of partial discharge signals includes:

[0080] Set the partial discharge signal to (volts), the gain factor is , the amplified partial discharge signal (volt) is expressed as,

[0081] ,

[0082] The amplified partial discharge signal , use a bandpass filter to remove abnormal frequency components;

[0083] The PD signal with abnormal frequency components removed Use analog-to-digital conversion to digitize partial discharge signals , the formula is expressed as,

[0084] ,

[0085] In the formula, represents the ADC reference voltage (volts), m represents the number of bits of the converter, Indicates rounding to the nearest integer;

[0086] Use moving average filtering to filter S consecutive partial discharge signals (volts) for noise reduction, the signal after noise reduction (volt) is expressed as,

[0087] ,

[0088] In the formula, represents the PD signal value at time t after noise reduction, Indicates that at the kth time point The partial discharge signal value, k represents the time variable, Indicates time, S indicates partial discharge signal The number of

[0089] It should be noted that signal amplification and filtering noise reduction technology significantly enhances the detection of weak partial discharge signals, improves data processing accuracy, and lays the foundation for accurate analysis.

[0090] S3. Extraction of partial discharge features includes:

[0091] After processing, the partial discharge signal The fast Fourier transform is used to calculate the spectrum characteristics, and the formula is expressed as:

[0092] ,

[0093] In the formula, Indicates at frequency point Spectral amplitude (volts) at (Hz), is the processed PD signal value of the nth sampling point, Indicates the total number of sampling points;

[0094] The average amplitude and maximum amplitude are calculated for a specific frequency point. The formula is:

[0095] ,

[0096] ,

[0097] In the formula, represents the average amplitude (volts), Indicates the maximum amplitude (volts);

[0098] Get partial discharge characteristics ;

[0099] Partial discharge characteristics include ultrasonic characteristics and transient voltage characteristics to ground ;

[0100] It should be noted that the partial discharge characteristics are effectively extracted through FFT transformation and amplitude calculation, and the fault identification capability is enhanced by combining ultrasonic and voltage characteristics, thereby improving the comprehensiveness of monitoring.

[0101] S4. Constructing the local discharge characteristic vector means,

[0102] Perform weighted fusion on the partial discharge features to construct the partial discharge feature vector , the formula is expressed as,

[0103] ,

[0104] in, represents the weight of the spectrogram feature, represents the weight of the average amplitude, represents the weight of the maximum magnitude;

[0105] It should be noted that the feature vector weighted fusion strategy integrates multiple information, increases the robustness of the evaluation, and can be flexibly adjusted according to needs to improve the level of intelligence.

[0106] S5, environmental data including humidity and temperature;

[0107] Based on historical partial discharge signals and environmental data, a dynamic threshold algorithm is constructed, including:

[0108] Define the temperature as (°C), humidity is (Unit is percentage, used to express relative humidity), and the baseline threshold is set based on the historical partial discharge signal. (volt);

[0109] Based on the PD eigenvector ,temperature and humidity , construct feature integration function , expressed as,

[0110] ,

[0111] The feature integration function The design basis is to comprehensively consider the influence of partial discharge characteristic vector, temperature and humidity, and balance the contribution of each factor through mathematical operation, so as to achieve a more comprehensive and balanced assessment of partial discharge risk. It can be simplified into a square root form, but the logarithmic-exponential form has better numerical stability, smoothing performance, and comprehensive consideration of nonlinear factors. Through this combined design, the contribution of partial discharge characteristics, temperature, and humidity can be better balanced, making the monitoring system more sensitive to extreme values ​​and changes in different variables, and improving the accuracy and robustness of the evaluation.

[0112] Based on temperature (°C) and humidity (Unit is percentage, used to express relative humidity), construct environmental impact function , expressed as,

[0113]

[0114] In the formula, Indicates time in seconds. Indicates the maximum time range, usually used to describe the cumulative impact or observation time over a period of time;

[0115] Environmental Impact Function The design aims to comprehensively reflect the impact of temperature and humidity on partial discharge monitoring through the hyperbolic tangent function and integral term, especially considering the cumulative effect over time, so as to improve the sensitivity and adaptability of the dynamic threshold algorithm to environmental factors;

[0116] Based on baseline threshold , feature integration function and environmental impact function , construct a dynamic threshold algorithm, the formula is expressed as,

[0117] ,

[0118] In the formula, represents the dynamic threshold, represents the normalization parameter, An adjustment factor indicating environmental impact;

[0119] It should be noted that the dynamic threshold algorithm takes environmental variables into consideration, overcomes the limitations of static thresholds, ensures monitoring adaptability, reduces false alarms and missed alarms, and improves early warning accuracy.

[0120] S6. Based on the partial discharge feature vector and dynamic threshold, the partial discharge risk level is divided into:

[0121] Using the PD eigenvector With dynamic threshold , calculate the risk index , expressed as,

[0122] ,

[0123] In the formula, is the feature weight vector;

[0124] Setting the first risk threshold , the second risk threshold ;

[0125] when When , it is defined as the first risk level, indicating that the partial discharge activity is slight;

[0126] when When , it is defined as the second risk level, indicating that there is obvious partial discharge activity;

[0127] when When , it is defined as the third risk level, indicating that the partial discharge activity is serious.

[0128] It should be noted that the risk level classification establishes a direct risk assessment system by quantifying local discharge risks and environmental impacts, thereby enhancing the pertinence and timeliness of operation and maintenance decisions.

[0129] S7. According to the level of partial discharge risk, different levels of early warning strategies are implemented, including:

[0130] When the risk level is the first, the first-level warning is triggered, the system automatically records the first risk event, and notifies the operation and maintenance personnel via SMS to conduct routine inspections on related equipment;

[0131] When the risk level reaches the second level, the second-level warning is triggered, which immediately triggers an instant alarm and notifies the operation and maintenance team through the emergency communication system to conduct an on-site inspection;

[0132] When it is at the third risk level, the third level warning is triggered, the equipment emergency shutdown procedure is immediately executed, the faulty equipment is quickly isolated, the emergency response team is activated, on-site command and coordination are carried out, comprehensive fault diagnosis is performed, the third risk event is analyzed, and the preventive maintenance and monitoring strategies are updated.

[0133] It should be noted that the graded early warning strategy responds accurately based on the risk level, optimizes the allocation of operation and maintenance resources, ensures rapid disposal, and maximizes the safety and stability of power grid operation.

[0134] This embodiment also provides a small-sized ring network box non-intrusive partial discharge monitoring and early warning system, including a data acquisition module for acquiring partial discharge signals and environmental data based on a variety of sensors;

[0135] A signal preprocessing module is used to perform preliminary processing on the partial discharge signal;

[0136] A vector construction module, used for extracting partial discharge features and constructing partial discharge feature vectors based on the processed partial discharge signal;

[0137] Dynamic threshold algorithm module, used to build a dynamic threshold algorithm based on historical partial discharge signals and environmental data;

[0138] A risk level classification module is used to classify the partial discharge risk level based on the partial discharge feature vector and the dynamic threshold;

[0139] The early warning strategy implementation module is used to implement early warning strategies of different levels according to the partial discharge risk level.

[0140] This embodiment also provides a computer device, which is suitable for the case of a non-intrusive partial discharge monitoring and early warning method for a small ring network box, including: a memory and a processor; the memory is used to store computer executable instructions, and the processor is used to execute computer executable instructions to implement the non-intrusive partial discharge monitoring and early warning method for a small ring network box as proposed in the above embodiment.

[0141] The computer device may be a terminal, and the computer device includes a processor, a memory, a communication interface, a display screen and an input device connected through a system bus. Among them, the processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The communication interface of the computer device is used to communicate with an external terminal in a wired or wireless manner, and the wireless manner can be achieved through WIFI, an operator network, NFC (near field communication) or other technologies. The display screen of the computer device may be a liquid crystal display screen or an electronic ink display screen, and the input device of the computer device may be a touch layer covered on the display screen, or a key, trackball or touchpad provided on the housing of the computer device, or an external keyboard, touchpad or mouse, etc.

[0142] This embodiment also provides a storage medium on which a computer program is stored. When the program is executed by a processor, the non-intrusive partial discharge monitoring and early warning method for a small ring network box proposed in the above embodiment is implemented; the storage medium can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (Static Random Access Memory, referred to as SRAM), electrically erasable programmable read-only memory (Electrically Erasable Programmable Read-Only Memory, referred to as EEPROM), erasable programmable read-only memory (Erasable Programmable Read Only Memory, referred to as EPROM), programmable read-only memory (Programmable Red-Only Memory, referred to as PROM), read-only memory (Read-Only Memory, referred to as ROM), magnetic storage, flash memory, magnetic disk or optical disk.

[0143] In summary, the beneficial effects of the present invention are to enhance signal quality and analysis accuracy through preliminary processing such as signal amplification, filtering and analog-to-digital conversion, combine fast Fourier transform and amplitude calculation to deeply refine partial discharge characteristics and integrate multivariate information to construct feature vectors, introduce dynamic threshold algorithms and risk level division mechanisms of environmental factors, and realize full-chain optimization of partial discharge monitoring from precise signal extraction, intelligent feature analysis to efficient early warning strategies, which greatly improves the accuracy, adaptability and operation and maintenance efficiency of power equipment fault early warning, and ensures the safety and stability of power grid operation.

[0144] Example 2

[0145] Referring to Table 1, which is the second embodiment of the present invention, in order to further verify the advancement of the present invention, experimental simulation data of a non-intrusive partial discharge monitoring and early warning method for a small ring network box is provided.

[0146] In order to verify the innovation and practicality of the present invention, we designed a set of detailed experiments and selected three typical small ring network boxes (marked as S1, S2, S3) as monitoring objects. Each ring network box was equipped with an ultrasonic sensor, a transient ground voltage sensor and an environmental sensor. The experiments were carried out under different climatic conditions and load levels to ensure the diversity and representativeness of the data.

[0147] First, we preliminarily processed the partial discharge signal of each ring network box, and enhanced the signal strength by adjusting the gain factor G to the optimal value. Then, a bandpass filter was used to remove abnormal frequency components to ensure signal quality. After the signal was converted to digital, a moving average filter was used to further reduce noise, and a high-quality digital partial discharge signal was obtained. .

[0148] Next, we Applying fast Fourier transform, the spectrum features are extracted , and calculated the average amplitude and maximum amplitude , which constitutes the partial discharge characteristic Then, the partial discharge feature vector is constructed through the weighted fusion strategy. , where the weight , , Determined based on optimization of historical data.

[0149] At the same time, the environmental data of each ring network box was collected, including temperature and humidity , these data are used to construct the feature integration function and environmental impact function , thus forming a dynamic threshold According to the partial discharge characteristic vector and dynamic threshold , we calculated the risk index R, and divided the partial discharge risk level accordingly, and implemented corresponding early warning strategies.

[0150] The details are shown in the following table:

[0151] Table 1 Experimental record table

[0152]

[0153] By analyzing the above data, we can observe the following points:

[0154] 1. Significant influence of environmental factors: In the data of S2 ring network box at 14:00, under the high temperature and humidity environment (30°C, 75%), the partial discharge characteristics are significantly enhanced, with the maximum amplitude Reaching 0.25, the risk level was raised to the third level compared with other ring network boxes on the same day. This shows that environmental factors have a significant impact on partial discharge activities. The present invention effectively considers this variable through the dynamic threshold algorithm, which improves the accuracy and adaptability of early warning.

[0155] 2. Reasonableness of risk level division: At different time points, the fluctuation of risk level of each ring network box reflects the change of partial discharge activity. For example, the risk level of S2 changes from level 2 to level 3 at different time points, while S1 and S3 mainly maintain at a lower risk level. This not only proves the rationality of risk level division, but also shows the hierarchical response mechanism of the early warning strategy, which can take corresponding measures according to different severity levels to avoid ineffective allocation of resources.

[0156] 3. Innovation and advantages: Compared with the traditional static threshold warning system, the dynamic threshold algorithm of the present invention (taking into account the characteristics of partial discharge and environmental factors) shows higher sensitivity and accuracy, especially when the environmental conditions change drastically, it can more accurately identify potential partial discharge risks and avoid false alarms or missed alarms caused by changes in environmental factors. In addition, by implementing different levels of early warning strategies, the refined management of partial discharge problems is achieved, providing a strong guarantee for the safe operation of the power system.

[0157] It should be noted that the above embodiments are only used to illustrate the technical solution of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solution of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical solution of the present invention.

Claims

1. A non-intrusive partial discharge monitoring and early warning method for a small ring network box, characterized in that: include, Based on a variety of sensors, obtain partial discharge signals and environmental data; Carry out preliminary processing of partial discharge signals; Based on the processed partial discharge signal, partial discharge features are extracted and partial discharge feature vectors are constructed; Build a dynamic threshold algorithm based on historical partial discharge signals and environmental data; Based on the partial discharge feature vector and dynamic threshold, the partial discharge risk level is divided; Implement different levels of early warning strategies according to the level of partial discharge risk; The dynamic threshold algorithm is constructed based on historical partial discharge signals and environmental data, including: Define the temperature as , humidity is , the baseline threshold is set based on the historical partial discharge signal ; Based on the PD eigenvector ,temperature and humidity , construct feature integration function , expressed as, ； Based on temperature and humidity , construct the environmental impact function , expressed as, ； In the formula, Indicates time, Indicates the maximum time range; Based on baseline threshold , feature integration function and environmental impact function , construct a dynamic threshold algorithm, the formula is expressed as, ； In the formula, represents the dynamic threshold, represents the normalization parameter, An adjustment factor indicating environmental impact; According to the level of partial discharge risk, different levels of early warning strategies are implemented, including: When the risk level is the first, the first-level warning is triggered, the system automatically records the first risk event, and notifies the operation and maintenance personnel via SMS to conduct routine inspections on related equipment; When the risk level reaches the second level, the second-level warning is triggered, which immediately triggers an instant alarm and notifies the operation and maintenance team through the emergency communication system to conduct an on-site inspection; When it is at the third risk level, the third level warning is triggered, the equipment emergency shutdown procedure is immediately executed, the faulty equipment is quickly isolated, the emergency response team is activated, on-site command and coordination are carried out, comprehensive fault diagnosis is performed, the third risk event is analyzed, and the preventive maintenance and monitoring strategies are updated.

2. The non-intrusive partial discharge monitoring and early warning method for a small ring network box according to claim 1, characterized in that: The various sensors include ultrasonic sensors, transient ground voltage sensors and environmental sensors.

3. The non-intrusive partial discharge monitoring and early warning method for a small ring network box according to claim 2, characterized in that: The preliminary processing of the partial discharge signal comprises: Set the partial discharge signal to , the gain factor is , the amplified partial discharge signal It is expressed as, ； The amplified partial discharge signal , use a bandpass filter to remove abnormal frequency components; The PD signal with abnormal frequency components removed Use analog-to-digital conversion to digitize partial discharge signals , the formula is expressed as, ； In the formula, represents the ADC reference voltage, m represents the number of bits of the converter, Indicates rounding to the nearest integer; Use moving average filtering to filter S consecutive partial discharge signals Noise reduction processing is performed, and the signal after noise reduction It is expressed as, ； In the formula, represents the PD signal value at time t after noise reduction, represents the value at the kth time point The partial discharge signal value, k represents the time variable, Indicates time, S indicates partial discharge signal The number of .

4. The non-intrusive partial discharge monitoring and early warning method for a small ring network box as claimed in claim 3 is characterized by: The extracting of partial discharge features comprises: After processing, the partial discharge signal The fast Fourier transform is used to calculate the spectrum characteristics, and the formula is expressed as: ； In the formula, Indicates at frequency point The spectrum amplitude at is the processed PD signal value of the nth sampling point, Indicates the total number of sampling points; The average amplitude and maximum amplitude are calculated for a specific frequency point. The formula is: ； ； In the formula, represents the average amplitude, Indicates the maximum magnitude; Get partial discharge characteristics .

5. The non-intrusive partial discharge monitoring and early warning method for a small ring network box according to claim 4, characterized in that: The construction of the partial discharge feature vector refers to weighted fusion of the partial discharge features to construct the partial discharge feature vector , the formula is expressed as, ； in, represents the weight of the spectrogram feature, represents the weight of the average amplitude, Indicates the weight of the maximum magnitude.

6. The non-intrusive partial discharge monitoring and early warning method for a small ring network box according to claim 5, characterized in that: The environmental data includes humidity and temperature.

7. The non-intrusive partial discharge monitoring and early warning method for a small ring network box according to claim 6, characterized in that: The partial discharge risk level is divided based on the partial discharge feature vector and the dynamic threshold, including: Using the PD eigenvector With dynamic threshold , calculate the risk index , expressed as, ； In the formula, is the feature weight vector; Set the first risk threshold to , the second risk threshold is , ; when It is defined as the first risk level. It is defined as the second risk level. It is defined as the third risk level.

8. A small-sized ring network box non-intrusive partial discharge monitoring and early warning system, based on the small-sized ring network box non-intrusive partial discharge monitoring and early warning method according to any one of claims 1 to 7, characterized in that: include, Data acquisition module, used to obtain partial discharge signals and environmental data based on a variety of sensors; A signal preprocessing module is used to perform preliminary processing on the partial discharge signal; A vector construction module, used for extracting partial discharge features and constructing partial discharge feature vectors based on the processed partial discharge signal; Dynamic threshold algorithm module, used to build a dynamic threshold algorithm based on historical partial discharge signals and environmental data; A risk level classification module is used to classify the risk level of partial discharge based on the partial discharge feature vector and the dynamic threshold; The early warning strategy implementation module is used to implement early warning strategies of different levels according to the partial discharge risk level.

Images