Lightning arrester partial discharge monitoring method, system, equipment and medium

Abstract

The invention discloses a lightning arrester partial discharge monitoring method, system and device and a medium, and the method comprises the steps: determining the historical operation characteristics of a to-be-monitored lightning arrester in different discharge states, building a high-precision digital twin model through combining electromagnetic wave and ultrasonic multi-source sensor data, and dynamically mapping the structure and operation state of the lightning arrester; real-time operation features are extracted through a time domain and frequency domain waveform feature fusion technology, feature similarity comparison is carried out in combination with a historical feature library, the discharge capacity is dynamically calculated based on partial discharge current and discharge time, and accurate recognition and severity quantification of partial discharge are achieved; the position of the partial discharge source is accurately positioned by analyzing the abnormal time interval difference of ultrasonic and electromagnetic wave signals and combining a path optimization algorithm; digital twin modeling, multi-dimensional feature fusion and intelligent analysis technologies are adopted, the defects that a traditional method is high in misjudgment rate and fuzzy in positioning are overcome, and the real-time performance, accuracy and anti-interference capacity of monitoring are improved.

Description

Technical Field

[0001] The present invention relates to the technical field of lightning arresters, and in particular to a method, system, equipment and medium for monitoring partial discharge of a lightning arrester. Background Art

[0002] As a critical overvoltage protection device in power systems, the reliability of lightning arresters (LAAs) directly impacts the safe and stable operation of power grids. In recent years, with the rapid development of smart grid and Internet of Things (IoT) technologies, partial discharge (PD) monitoring has become an increasingly important tool for assessing the insulation condition of LAs. Traditional monitoring methods rely primarily on electromagnetic and ultrasonic sensors to collect signals. Combined with manual inspections and periodic testing, these methods analyze characteristics such as discharge pulses, amplitude, and frequency to provide a preliminary assessment of the LAs's PD activity. Furthermore, some advanced technologies have incorporated digital twins and big data analytics, building virtual models to simulate the operating status of LAs, thereby improving the real-time and predictive capabilities of monitoring. These technologies can, to a certain extent, capture early discharge signals, providing data support for fault warnings and becoming a key research direction in condition-based maintenance (CMS) for power equipment.

[0003] Lightning arresters may age, become damaged, or fail after prolonged use or exposure to external environmental influences. Monitoring partial discharge in lightning arresters is a crucial tool for ensuring equipment reliability and safety in power systems. Partial discharge (PD) refers to the release of charge within a small area of ​​an electrical insulating medium. This phenomenon can be an early sign of gradual insulation degradation and eventual failure. For lightning arresters, timely detection and assessment of PD activity can help prevent potential failures and extend equipment life. Therefore, accurate and effective PD monitoring of lightning arresters has become a pressing issue. Summary of the Invention

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

[0005] Therefore, the present invention provides a method and system for monitoring partial discharge of a lightning arrester to solve the technical problem of how to accurately and effectively monitor partial discharge of a lightning arrester.

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

[0007] In a first aspect, the present invention provides a method for monitoring partial discharge of a lightning arrester, comprising:

[0008] Determine the historical operating characteristics of the arrester to be monitored under different discharge states;

[0009] Build the required model of the lightning arrester based on the sensor data corresponding to the sensor;

[0010] Determine the real-time operating characteristics of the arrester to be monitored according to the model;

[0011] The arrester to be monitored is monitored according to historical operating characteristics and real-time operating characteristics.

[0012] As a preferred solution of the method for monitoring partial discharge of a lightning arrester according to the present invention, the method includes: constructing a model required for the lightning arrester according to sensor data corresponding to the sensor, including:

[0013] Construct a physical model based on the corresponding structural information of the arrester to be monitored;

[0014] Preset monitoring points on the arrester to be monitored and determine the corresponding discharge signal;

[0015] Obtaining data collected by sensors on the arrester to be monitored corresponding to the discharge signal;

[0016] The required model of the lightning arrester is constructed based on the data collected by the sensors and the physical model.

[0017] As a preferred solution of the method for monitoring partial discharge of a lightning arrester according to the present invention, determining the real-time operating characteristics of the lightning arrester to be monitored according to the model includes:

[0018] Determine the ultrasonic signal and electromagnetic wave signal corresponding to the required model of the lightning arrester;

[0019] Determine waveform characteristics corresponding to the ultrasonic signal and waveform characteristics corresponding to the electromagnetic wave signal;

[0020] The real-time operation characteristics corresponding to the detected lightning arrester are determined based on the waveform characteristics.

[0021] As a preferred solution of the method for monitoring partial discharge of a lightning arrester according to the present invention, the method of determining the real-time operating characteristics of the lightning arrester according to the waveform characteristics includes:

[0022] Transforming the ultrasonic signal and determining corresponding features of the transformed ultrasonic signal;

[0023] Transforming the electromagnetic wave signal and determining corresponding features of the transformed electromagnetic wave signal;

[0024] The ultrasonic and electromagnetic wave waveform characteristics and the corresponding characteristics after ultrasonic and electromagnetic wave transformation are fused to obtain the real-time operation characteristics of the lightning arrester to be monitored.

[0025] As a preferred solution of the method for monitoring partial discharge of a lightning arrester according to the present invention, the method of monitoring the lightning arrester to be monitored according to historical operating characteristics and real-time operating characteristics includes:

[0026] Calculate the feature similarity between historical operation features and real-time operation features;

[0027] Determine the discharge amount of the arrester to be monitored during operation according to the partial discharge current and discharge time corresponding to the arrester to be monitored;

[0028] Partial discharge monitoring of the monitored arrester is performed based on feature similarity and discharge amount.

[0029] As a preferred embodiment of the method for monitoring partial discharge of a lightning arrester according to the present invention, the method of performing partial discharge monitoring on the lightning arrester to be monitored based on feature similarity and discharge amount includes:

[0030] When the arrester to be monitored has partial discharge, determining the ultrasonic signal and electromagnetic wave signal corresponding to each partial discharge signal;

[0031] Determine the abnormal characteristics of ultrasonic signals and electromagnetic wave signals and determine the partial discharge position corresponding to the lightning arrester to be monitored.

[0032] As a preferred embodiment of the method for monitoring partial discharge of a lightning arrester according to the present invention, the method of determining abnormal characteristics of ultrasonic signals and electromagnetic wave signals and determining the partial discharge position corresponding to the lightning arrester to be monitored includes:

[0033] Determining an ultrasonic abnormality feature in the ultrasonic signal, and determining an ultrasonic abnormality period corresponding to the ultrasonic abnormality feature;

[0034] Determining an abnormal electromagnetic wave feature in the electromagnetic wave signal, and determining an abnormal electromagnetic wave period corresponding to the abnormal electromagnetic wave feature;

[0035] The partial discharge position corresponding to the arrester to be monitored is determined according to the ultrasonic abnormal period and the electromagnetic wave abnormal period.

[0036] In a second aspect, the present invention provides a lightning arrester partial discharge monitoring system, comprising:

[0037] A feature determination module is used to determine the historical operating characteristics of the arrester to be monitored under different partial discharge states, and is also used to determine the corresponding real-time operating characteristics of the arrester to be monitored based on the arrester digital twin model;

[0038] A model building module is used to build a digital twin model of the arrester based on the sensor data corresponding to the sensors on the arrester to be monitored;

[0039] The discharge monitoring module is used to perform partial discharge monitoring on the monitored arrester based on historical operating characteristics and real-time operating characteristics.

[0040] In a third aspect, the present invention provides an electronic device, comprising:

[0041] memory and processor;

[0042] The memory is used to store computer-executable instructions, and the processor is used to execute the computer-executable instructions. When the computer-executable instructions are executed by the processor, the steps of a method for monitoring partial discharge of a lightning arrester are realized.

[0043] In a fourth aspect, the present invention provides a computer-readable storage medium storing computer-executable instructions, which, when executed by a processor, implement the steps of the method for monitoring partial discharge of a lightning arrester.

[0044] Compared with the existing technology, the beneficial effects of the present invention are as follows: the present invention obtains the historical operating characteristics of the lightning arrester to be monitored under different discharge states, combines the sensor data to build a high-precision digital twin model of the lightning arrester, and provides a reliable data basis for subsequent analysis; utilizes the time domain and frequency domain waveform feature fusion technology of ultrasonic signals and electromagnetic wave signals to comprehensively capture the multi-dimensional information of the operating status of the lightning arrester, and significantly improves the integrity and anti-interference ability of feature extraction; based on the feature similarity calculation of historical and real-time operating characteristics, combined with the dynamic discharge amount evaluation of discharge current and time, accurate identification and severity quantification of partial discharge are achieved; by synchronously analyzing the abnormal time period differences of ultrasonic and electromagnetic wave signals, the partial discharge position is effectively located, solving the defect of fuzzy positioning of traditional methods. Overall, the present invention greatly improves the accuracy, real-time performance and reliability of monitoring, and provides intelligent technical support for the health status assessment and life extension of lightning arresters. BRIEF DESCRIPTION OF THE DRAWINGS

[0045] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0046] Figure 1 The figure is a schematic diagram of the overall process of a method for monitoring partial discharge of a lightning arrester according to an embodiment of the present invention.

[0047] Figure 2 The figure is a schematic diagram of a specific flow of step S30 of a method for monitoring partial discharge of a lightning arrester according to an embodiment of the present invention.

[0048] Figure 3 This is a schematic diagram of a specific flow of step S40 of a method for monitoring partial discharge of a lightning arrester according to an embodiment of the present invention.

[0049] Figure 4 The present invention is a schematic diagram of the module structure of a lightning arrester partial discharge monitoring system according to an embodiment of the present invention.

[0050] Figure 5 The present invention is a schematic structural diagram of a lightning arrester partial discharge monitoring device according to a lightning arrester partial discharge monitoring method according to an embodiment of the present invention. DETAILED DESCRIPTION

[0051] To make the above-mentioned objects, features, and advantages of the present invention more clearly understood, the following detailed description of the specific embodiments of the present invention is given in conjunction with the accompanying drawings. It is obvious that the described embodiments are only part of the embodiments of the present invention, not all of them. Based on the embodiments of the present invention, all other embodiments obtained by ordinary persons in this field without creative work should fall within the scope of protection of the present invention.

[0052] Example 1, with reference to Figure 1 , as one embodiment of the present invention, provides a method for monitoring partial discharge of a lightning arrester, comprising:

[0053] S10: determining the historical operating characteristics of the arrester to be monitored under different discharge states;

[0054] S20: constructing a model required for the lightning arrester according to the sensor data corresponding to the sensor;

[0055] S30: determining the real-time operating characteristics corresponding to the arrester to be monitored according to the model;

[0056] S40: Monitor the arrester to be monitored based on historical operating characteristics and real-time operating characteristics.

[0057] It should be noted that lightning arresters are prone to aging, damage, and failure due to long-term operation or environmental influences. Partial discharge, an early phenomenon of localized charge release in insulating dielectrics, can accelerate insulation degradation if not monitored promptly, threatening power system safety. Traditional monitoring methods, relying on single signal features or empirical thresholds, struggle to accurately identify true discharges under complex operating conditions. Furthermore, they lack the support of dynamic data fusion and high-precision models, resulting in high misjudgment rates, ambiguous positioning, and delayed assessments.

[0058] Therefore, in order to address the above-mentioned problems of insufficient monitoring accuracy, poor real-time performance and inaccurate positioning, through steps S10-S40, first, a multi-dimensional benchmark is established based on the historical operating characteristics of the arrester in different discharge states, and a high-precision digital twin model is constructed in combination with sensor data to simulate the actual structure; the time domain and frequency domain characteristics of ultrasonic and electromagnetic wave signals are analyzed in real time through the model, and real-time operating characteristics are dynamically integrated to generate real-time operation characteristics; finally, by comparing historical and real-time characteristics and combining them with discharge quantity calculation, accurate identification of partial discharge, quantification of severity and analysis of abnormal time periods are achieved, thereby accurately locating the fault point; this method breaks through traditional limitations, significantly improves monitoring reliability, and provides effective protection for extending the life of the arrester and providing effective protection for the safety of the power grid.

[0059] Example 2, reference Figure 2-Figure 3 , which is an embodiment of the present invention, provides a method for monitoring partial discharge of a lightning arrester based on the above embodiment.

[0060] In an embodiment of the present application, determining the historical operating characteristics of the lightning arrester to be monitored under different discharge states in step S10 is achieved by collecting and analyzing multi-dimensional signal data of its no partial discharge state, initial partial discharge state, developing partial discharge state, severe partial discharge state, and breakdown or near breakdown state. Specifically, it includes recording and processing the discharge acoustic wave signals, current waveform changes, electromagnetic wave characteristic parameters of the lightning arrester in each state, and combining environmental factors with operating condition data to construct a historical feature library reflecting the degree of insulation degradation.

[0061] In an optional embodiment, the historical operating characteristics of the monitored arrester under different discharge states determined in step S10 can also be determined by deploying a machine learning algorithm to automatically extract and classify multi-source sensor data, using the trained model to identify typical signal patterns under different discharge states, and optimizing the integrity and discrimination of the feature library in combination with long-term operation logs.

[0062] In another optional embodiment, the historical operating characteristics of the lightning arrester to be monitored under different discharge states determined in step S10 can also be determined by introducing a high-precision simulation platform to simulate the discharge behavior of the lightning arrester under extreme working conditions, generating a virtual feature data set covering the degradation path of the entire life cycle, and constructing a dynamically updated historical feature reference benchmark by calibrating with actual monitoring data.

[0063] In an embodiment of the present application, in step S20, the required model of the lightning arrester is constructed according to the sensor data corresponding to the sensor by collecting multi-source signal data of electromagnetic wave, ultrasonic wave and other sensors, combining the three-dimensional physical model of the lightning arrester (constructed based on design parameters, operation data and environmental information), and simulating the discharge behavior of the local discharge source at the preset monitoring point, and dynamically integrating real-time sensor data using big data analysis and machine learning algorithms to finally generate a high-precision, real-time updateable digital twin model of the lightning arrester; it should be understood that a number of sensors can be set on the lightning arrester to be monitored, which may include electromagnetic wave sensors, ultrasonic sensors, etc., and the corresponding sensor data may include electromagnetic wave signals, ultrasonic signals, etc.; then the digital twin model of the lightning arrester is constructed according to the sensor data. The digital twin model is a virtual model that accurately simulates the behavior or state of the lightning arrester.

[0064] In an optional embodiment, in step S20, the model required for the lightning arrester is constructed based on the sensor data corresponding to the sensor. The sensor data can also be preprocessed and feature compressed in real time by introducing an edge computing node. After the feature extraction and noise reduction of key signals are completed locally, the streamlined data is uploaded to the digital twin platform for model fusion, thereby reducing data transmission delay and improving model construction efficiency.

[0065] In another optional embodiment, the model required for the lightning arrester constructed based on the sensor data corresponding to the sensor in step S20 can also be achieved by combining physical simulation with a deep learning generative adversarial network (GAN), using simulation data to train the generator to simulate signal characteristics under different discharge scenarios, and at the same time optimizing the matching degree between the real sensor data and the simulation data through the discriminator, thereby enhancing the adaptability and prediction accuracy of the digital twin model under complex working conditions.

[0066] In an embodiment of the present application, in step S20, a physical model is constructed according to the corresponding structural information of the lightning arrester to be monitored. When the preset monitoring point on the lightning arrester to be monitored is a local discharge source, the local discharge signal corresponding to each local discharge source is determined; sensor data collected by the sensor on the lightning arrester to be monitored corresponding to each local discharge signal is obtained; and a digital twin model of the lightning arrester is constructed according to the sensor data and the three-dimensional physical model; it can be understood that the structural information corresponding to the lightning arrester to be monitored can be the structural information of each component of the lightning arrester to be monitored. Specifically, the design parameters of the lightning arrester to be monitored, such as size, material properties, etc., can be obtained; operating data, such as real-time operating parameters such as voltage, current, and temperature; environmental data, such as climatic conditions at the installation location, pollution level, and other factors that may affect the performance of the lightning arrester; and based on the above-mentioned structural information, a three-dimensional physical model of the lightning arrester to be monitored is created using a modeling tool, which can accurately represent the actual structure and components of the lightning arrester to be monitored.

[0067] In an embodiment of the present application, in step S20, monitoring points are preset on the arrester to be monitored, and a number of preset monitoring points can be set on the arrester to be monitored to determine the corresponding discharge signal. Each preset monitoring point can be a local discharge source, that is, the point where local discharge may occur on the arrester to be monitored is used as a preset monitoring point.

[0068] In an embodiment of the present application, when the data collected by the sensor on the arrester to be monitored corresponding to the discharge signal obtained in step S20 is a local discharge source, a local discharge signal can be sent to the sensor on the arrester to be monitored, and the sensor can collect sensor data corresponding to the local discharge signal.

[0069] In an embodiment of the present application, in step S20, the required model of the lightning arrester is constructed based on the data collected by the sensor and the physical model, and the sensor data is transmitted to the digital twin platform. Big data analysis and machine learning algorithms are applied to process the data from the sensor. Finally, a digital twin model of the lightning arrester can be constructed based on the sensor data and the three-dimensional physical model, and the sensor data on the model can be updated in real time.

[0070] In an embodiment of the present application, in step S30, the real-time operating characteristics corresponding to the lightning arrester to be monitored can be determined according to the model, and the real-time operating characteristics corresponding to the lightning arrester to be monitored can be determined according to the digital twin model of the lightning arrester. Since the digital twin model of the lightning arrester is updated in real time, the real-time operating characteristics corresponding to the lightning arrester to be monitored can be determined according to the digital twin model of the lightning arrester, and the operating characteristics are also updated in real time.

[0071] In the embodiment of the present application, the real-time operating characteristics corresponding to the arrester to be monitored are determined according to the model in step S30, including the following steps: Figure 2 As shown:

[0072] Step S301: Determine the ultrasonic signal and electromagnetic wave signal corresponding to the arrester digital twin model.

[0073] Specifically, the ultrasonic signal and electromagnetic wave signal corresponding to the arrester digital twin model can be determined, that is, the ultrasonic signal and electromagnetic wave signal collected by the sensor, and these two signals may change in real time.

[0074] Step S302: Determine the ultrasonic time-domain waveform characteristics corresponding to the ultrasonic signal and the electromagnetic wave time-domain waveform characteristics corresponding to the electromagnetic wave signal.

[0075] Specifically, ultrasonic signals collected by ultrasonic sensors and electromagnetic wave signals collected by electromagnetic wave sensors are typically time-domain signals, which describe the signal's evolution over time, using time as the independent variable. The corresponding ultrasonic time-domain waveform characteristics of the ultrasonic signal can be determined, including instantaneous frequency, time-domain pulse rise and fall time, total pulse duration, and maximum pulse amplitude. Similarly, the corresponding electromagnetic wave time-domain waveform characteristics of the electromagnetic wave signal can be determined.

[0076] Step S303: determining the real-time operation characteristics corresponding to the arrester to be monitored according to the ultrasonic wave time-domain waveform characteristics and the electromagnetic wave time-domain waveform characteristics.

[0077] Specifically, the ultrasonic signal is Fourier transformed, and the ultrasonic frequency domain waveform characteristics corresponding to the transformed ultrasonic signal are determined; the electromagnetic wave signal is Fourier transformed, and the electromagnetic wave frequency domain waveform characteristics corresponding to the transformed electromagnetic wave signal are determined; the ultrasonic time domain waveform characteristics, the electromagnetic wave time domain waveform characteristics, the ultrasonic frequency domain waveform characteristics and the electromagnetic wave frequency domain waveform characteristics are feature fused to obtain the real-time operation characteristics corresponding to the lightning arrester to be monitored; since the ultrasonic signal and the electromagnetic wave signal are time domain signals, the ultrasonic signal and the electromagnetic wave signal can be Fourier transformed to convert the time domain signal into a frequency domain signal to obtain the transformed ultrasonic signal and the transformed electromagnetic wave signal. signal; and determine the ultrasonic frequency domain waveform characteristics corresponding to the transformed ultrasonic signal, which may include characteristics such as equivalent bandwidth, quadratic equivalent bandwidth, etc. Similarly, the electromagnetic wave frequency domain waveform characteristics corresponding to the transformed electromagnetic wave signal can be determined; the ultrasonic time domain waveform characteristics, the electromagnetic wave time domain waveform characteristics, the ultrasonic frequency domain waveform characteristics and the electromagnetic wave frequency domain waveform characteristics can be fused to obtain the real-time operation characteristics corresponding to the lightning arrester to be monitored. Specifically, different fusion weight values ​​can be assigned to each feature, and the feature selection method can be used to screen unimportant or redundant features, and then the selected features can be assigned appropriate weights, thereby reducing the number and dimension of features and improving the effect of feature fusion.

[0078] In an embodiment of the present application, in step S40, the arrester to be monitored is monitored based on the historical operating characteristics and the real-time operating characteristics, and the historical operating characteristics and the real-time operating characteristics can be compared. When the two characteristics are not much different, it indicates that the arrester to be monitored has a partial discharge phenomenon; when the two characteristics are greatly different, it indicates that the arrester to be monitored may not have a partial discharge phenomenon; wherein, the historical operating characteristics refer to the operating characteristics of the arrester to be monitored in the partial discharge state, and the real-time operating characteristics refer to the operating characteristics of the arrester to be monitored at the current moment.

[0079] In the embodiment of the present application, step S40 monitors the arrester to be monitored according to the historical operation characteristics and the real-time operation characteristics, including the following steps: Figure 3 As shown:

[0080] Step S401: Calculate the feature similarity between the historical operation feature and the real-time operation feature.

[0081] Specifically, the method for obtaining the historical operation characteristics of the arrester to be monitored may be similar to the method for obtaining the real-time operation characteristics described above, and the feature similarity between the historical operation characteristics and the real-time operation characteristics may be calculated using the cosine similarity calculation formula.

[0082] Step S402: determining the discharge amount of the arrester to be monitored during operation according to the partial discharge current and discharge time corresponding to the arrester to be monitored.

[0083] Specifically, the arrester to be monitored may be pre-tested for partial discharge, and the discharge amount generated by the arrester to be monitored during operation may be calculated. Specifically, the product of the partial discharge current and the discharge time of the arrester to be monitored during operation may be used as the discharge amount.

[0084] Step S403: performing partial discharge monitoring on the arrester to be monitored according to the feature similarity and the discharge amount.

[0085] Specifically, the characteristic similarity and the discharge amount are comprehensively considered to determine whether the arrester to be monitored has partial discharge; the characteristic similarity threshold and the discharge amount threshold can be set. When the characteristic similarity threshold is greater than or equal to the characteristic similarity threshold and the discharge amount is greater than or equal to the discharge amount threshold, it is determined that the arrester to be monitored has partial discharge phenomenon; when the characteristic similarity threshold is less than the characteristic similarity threshold and the discharge amount is less than the discharge amount threshold, it is determined that the arrester to be monitored does not have partial discharge phenomenon; when the characteristic similarity threshold is less than the characteristic similarity threshold and the discharge amount is greater than or equal to the discharge amount threshold, it is determined that the arrester to be monitored does not have partial discharge phenomenon phenomenon; when the feature similarity threshold is greater than or equal to the feature similarity threshold and the discharge amount is less than the discharge amount threshold, it is determined that there is no local discharge phenomenon in the lightning arrester to be monitored; when there is local discharge in the lightning arrester to be monitored, the ultrasonic signal and electromagnetic wave signal corresponding to each local discharge signal are determined; the ultrasonic abnormal characteristics in the ultrasonic signal are determined, and the ultrasonic abnormal time period corresponding to the ultrasonic abnormal characteristics is determined; the electromagnetic wave abnormal characteristics in the electromagnetic wave signal are determined, and the electromagnetic wave abnormal time period corresponding to the electromagnetic wave abnormal characteristics is determined; the local discharge position corresponding to the lightning arrester to be monitored is determined according to the ultrasonic abnormal time period and the electromagnetic wave abnormal time period.

[0086] It is understandable that when a partial discharge phenomenon occurs in the arrester to be monitored, the ultrasonic signal and electromagnetic wave signal collected by the sensor when the preset monitoring point sends a partial discharge signal can be determined. This embodiment can determine which partial discharge source sends the partial discharge signal, that is, determine the partial discharge position corresponding to the arrester to be monitored; the ultrasonic abnormality feature in the ultrasonic signal can be determined, and the ultrasonic abnormality feature may be a feature with a large amplitude, a large peak-to-peak value, and a wide pulse width; and the ultrasonic abnormality time period corresponding to the ultrasonic abnormality feature can be determined. Similarly, the electromagnetic wave abnormality feature in the electromagnetic wave signal can be determined, and the electromagnetic wave abnormality time period corresponding to the electromagnetic wave abnormality feature can be determined; the partial discharge corresponding to the arrester to be monitored can be determined based on the ultrasonic abnormality time period and the electromagnetic wave abnormality time period. Position; the ultrasonic shortest path between each preset monitoring point and the ultrasonic sensor can be determined in advance, and the electromagnetic wave shortest path between each preset monitoring point and the electromagnetic wave sensor can be determined, and then the ultrasonic transmission distance is obtained according to the ultrasonic abnormal time period and the ultrasonic transmission speed, and then the first partial discharge position is determined according to the ultrasonic transmission distance, the position of the ultrasonic sensor, and the ultrasonic shortest path. At the same time, the electromagnetic wave transmission distance can be obtained according to the electromagnetic wave abnormal time period and the electromagnetic wave transmission speed, and then the second partial discharge position is determined according to the electromagnetic wave transmission distance, the position of the electromagnetic wave sensor, and the electromagnetic wave shortest path; and then the first partial discharge position and the second partial discharge position are adjusted so that the final partial discharge position is on the preset monitoring point.

[0087] In summary, the present invention realizes dynamic monitoring of the entire life cycle of the arrester's partial discharge through multi-dimensional signal acquisition and high-precision modeling technology; based on the construction of a historical feature library of different discharge states and the real-time update of the digital twin model, combined with the fusion of time-domain and frequency-domain features and dynamic discharge calculation, it improves the accuracy and anti-interference ability of partial discharge identification; through the abnormal period analysis of ultrasonic and electromagnetic wave signals and the path optimization algorithm, the discharge point is accurately located, solving the pain points of high misjudgment rate and fuzzy positioning of traditional methods; at the same time, the introduction of advanced technologies such as machine learning, edge computing and generative adversarial networks further enhances the adaptability and prediction efficiency of the model. The overall solution not only extends the service life of the arrester, but also provides intelligent and highly reliable technical guarantees for the safe operation of the power grid.

[0088] Example 3, reference Figure 4-Figure 5 The above is a schematic scheme of a method for monitoring partial discharge of a lightning arrester. It should be noted that the technical solution of the system for monitoring partial discharge of a lightning arrester and the technical solution of the method for monitoring partial discharge of a lightning arrester are of the same concept. For details not described in detail in the technical solution of the system for monitoring partial discharge of a lightning arrester in this embodiment, please refer to the description of the technical solution of the method for monitoring partial discharge of a lightning arrester.

[0089] like Figure 4As shown, this embodiment also provides a lightning arrester partial discharge monitoring system, including:

[0090] The feature determination module 10 is used to determine the historical operating characteristics of the lightning arrester to be monitored under different partial discharge states; it is also used to determine the real-time operating characteristics corresponding to the lightning arrester to be monitored based on the digital twin model of the lightning arrester; it is also used to determine the ultrasonic signal and electromagnetic wave signal corresponding to the digital twin model of the lightning arrester; determine the ultrasonic time domain waveform characteristics corresponding to the ultrasonic signal and the electromagnetic wave time domain waveform characteristics corresponding to the electromagnetic wave signal; determine the real-time operating characteristics corresponding to the lightning arrester to be monitored based on the ultrasonic time domain waveform characteristics and the electromagnetic wave time domain waveform characteristics; it is also used to perform Fourier transform on the ultrasonic signal and determine the ultrasonic frequency domain waveform characteristics corresponding to the transformed ultrasonic signal; perform Fourier transform on the electromagnetic wave signal and determine the electromagnetic wave frequency domain waveform characteristics corresponding to the transformed electromagnetic wave signal; perform feature fusion on the ultrasonic time domain waveform characteristics, the electromagnetic wave time domain waveform characteristics, the ultrasonic frequency domain waveform characteristics and the electromagnetic wave frequency domain waveform characteristics to obtain the real-time operating characteristics corresponding to the lightning arrester to be monitored;

[0091] A model building module 20 is configured to build a digital twin model of the arrester based on sensor data corresponding to sensors on the arrester to be monitored; further configured to build a three-dimensional physical model based on structural information corresponding to the arrester to be monitored; when a preset monitoring point on the arrester to be monitored is a partial discharge source, determine the partial discharge signal corresponding to each partial discharge source; obtain sensor data collected by sensors on the arrester to be monitored corresponding to each partial discharge signal; and build the digital twin model of the arrester based on the sensor data and the three-dimensional physical model;

[0092] The discharge monitoring module 30 is used to perform partial discharge monitoring on the lightning arrester to be monitored based on the historical operation characteristics and the real-time operation characteristics; it is also used to calculate the feature similarity between the historical operation characteristics and the real-time operation characteristics; determine the discharge amount of the lightning arrester to be monitored during operation based on the local discharge current and discharge time corresponding to the lightning arrester to be monitored; perform partial discharge monitoring on the lightning arrester to be monitored based on the feature similarity and the discharge amount; it is also used to determine the ultrasonic signal and electromagnetic wave signal corresponding to each local discharge signal when the lightning arrester to be monitored has partial discharge; determine the ultrasonic abnormal feature in the ultrasonic signal, and determine the ultrasonic abnormal time period corresponding to the ultrasonic abnormal feature; determine the electromagnetic wave abnormal feature in the electromagnetic wave signal, and determine the electromagnetic wave abnormal time period corresponding to the electromagnetic wave abnormal feature; determine the partial discharge position corresponding to the lightning arrester to be monitored based on the ultrasonic abnormal time period and the electromagnetic wave abnormal time period.

[0093] like Figure 5As shown, this embodiment also provides an electronic device, which is applicable to a method for monitoring partial discharge of a lightning arrester, including: a processing device 1001 (such as a central processing unit, a graphics processing unit, etc.), which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM) 1002 or a program loaded from a storage device 1003 to a random access memory (RAM) 1004; various programs and data required for the operation of the lightning arrester partial discharge monitoring device are also stored in the RAM 1004; the processing device 1001, the ROM 1002 and the RAM 1004 are connected to each other through a bus 1005; an input / output (I / O) interface 1006 is also connected to the bus; generally, the following systems can be connected to the I / O interface 1006: an input device 1007 including, for example, a touch screen, a touchpad, a keyboard, a mouse, an image sensor, a microphone, an accelerometer, a gyroscope, etc.; an input device 1007 including, for example, a liquid crystal display (LCD); An output device 1008 including a display), a speaker, a vibrator, etc.; a storage device 1003 including, for example, a magnetic tape, a hard disk, etc.; and a communication device 1009; the communication device 1009 can allow the lightning arrester partial discharge monitoring device to communicate with other devices wirelessly or by wire to exchange data; and implement a lightning arrester partial discharge monitoring method as proposed in the above embodiment.

[0094] This embodiment further provides a storage medium storing a computer program. When the program is executed by a processor, a method for monitoring partial discharge of a lightning arrester as proposed in the above embodiment is implemented.

[0095] The storage medium proposed in this embodiment and the method for implementing a lightning arrester partial discharge monitoring method proposed in the above embodiment belong to the same inventive concept. Technical details not fully described in this embodiment can be referred to the above embodiment, and this embodiment has the same beneficial effects as the above embodiment.

[0096] Through the above description of the implementation methods, those skilled in the art can clearly understand that the present invention can be implemented with the help of software and necessary general hardware, and of course can also be implemented by hardware. Based on this understanding, the technical solution of the present invention is essentially or the part that contributes to the prior art can be embodied in the form of a software product, which can be stored in a computer-readable storage medium, such as a computer floppy disk, read-only memory (ROM), random access memory (RAM), flash memory (FLASH), hard disk or optical disk, etc., including a number of instructions for enabling a computer device (which can be a personal computer, server, or network device, etc.) to execute the methods of various embodiments of the present invention.

[0097] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and are not intended to limit the present invention. Although the present invention has been described in detail with reference to preferred embodiments, those skilled in the art should understand that the technical solutions of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical solutions of the present invention, which should all be included in the scope of the claims of the present invention.

Claims

1. A method for monitoring partial discharge of a lightning arrester, characterized in that: include: Determine the historical operating characteristics of the arrester to be monitored under different discharge states; Build the required model of the lightning arrester based on the sensor data corresponding to the sensor; Determine the real-time operating characteristics of the arrester to be monitored according to the model; The arrester to be monitored is monitored according to historical operating characteristics and real-time operating characteristics.

2. A method for monitoring partial discharge of a lightning arrester according to claim 1, characterized in that: Build the model required for the lightning arrester based on the sensor data corresponding to the sensor, including: Construct a physical model based on the corresponding structural information of the arrester to be monitored; Preset monitoring points on the arrester to be monitored and determine the corresponding discharge signal; Obtaining data collected by sensors on the arrester to be monitored corresponding to the discharge signal; The required model of the lightning arrester is constructed based on the data collected by the sensors and the physical model.

3. A method for monitoring partial discharge of a lightning arrester according to claim 2, characterized in that: Determine the real-time operating characteristics of the arrester to be monitored based on the model, including: Determine the ultrasonic signal and electromagnetic wave signal corresponding to the required model of the lightning arrester; Determine waveform characteristics corresponding to the ultrasonic signal and waveform characteristics corresponding to the electromagnetic wave signal; The real-time operation characteristics corresponding to the detected lightning arrester are determined based on the waveform characteristics.

4. A method for monitoring partial discharge of a lightning arrester according to claim 3, characterized in that: The step of determining the real-time operating characteristics corresponding to the lightning arrester according to the waveform characteristics includes: Transforming the ultrasonic signal and determining corresponding features of the transformed ultrasonic signal; Transforming the electromagnetic wave signal and determining corresponding features of the transformed electromagnetic wave signal; The ultrasonic and electromagnetic wave waveform characteristics and the corresponding characteristics after ultrasonic and electromagnetic wave transformation are fused to obtain the real-time operation characteristics of the lightning arrester to be monitored.

5. A method for monitoring partial discharge of a lightning arrester according to claim 4, characterized in that: Monitor the arrester to be monitored based on historical and real-time operating characteristics, including: Calculate the feature similarity between historical operation features and real-time operation features; Determine the discharge amount of the arrester to be monitored during operation according to the partial discharge current and discharge time corresponding to the arrester to be monitored; Partial discharge monitoring of the monitored arrester is performed based on feature similarity and discharge amount.

6. A method for monitoring partial discharge of a lightning arrester according to claim 5, characterized in that: The partial discharge monitoring of the arrester to be monitored according to the feature similarity and the discharge amount includes: When the arrester to be monitored has partial discharge, determining the ultrasonic signal and electromagnetic wave signal corresponding to each partial discharge signal; Determine the abnormal characteristics of ultrasonic signals and electromagnetic wave signals and determine the partial discharge position corresponding to the lightning arrester to be monitored.

7. A method for monitoring partial discharge of a lightning arrester according to claim 6, characterized in that: The method of determining abnormal characteristics of ultrasonic signals and electromagnetic wave signals and determining the partial discharge position corresponding to the arrester to be monitored includes: Determining an ultrasonic abnormality feature in the ultrasonic signal, and determining an ultrasonic abnormality period corresponding to the ultrasonic abnormality feature; Determining an abnormal electromagnetic wave feature in the electromagnetic wave signal, and determining an abnormal electromagnetic wave period corresponding to the abnormal electromagnetic wave feature; The partial discharge position corresponding to the arrester to be monitored is determined according to the ultrasonic abnormal period and the electromagnetic wave abnormal period.

8. A lightning arrester partial discharge monitoring system, applying the method according to any one of claims 1 to 7, characterized in that: include: A feature determination module is used to determine the historical operating characteristics of the arrester to be monitored under different partial discharge states, and is also used to determine the corresponding real-time operating characteristics of the arrester to be monitored based on the arrester digital twin model; A model building module is used to build a digital twin model of the arrester based on the sensor data corresponding to the sensors on the arrester to be monitored; The discharge monitoring module is used to perform partial discharge monitoring on the monitored arrester based on historical operating characteristics and real-time operating characteristics.

9. An electronic device comprising: memory and processor; The memory is used to store computer-executable instructions, and the processor is used to execute the computer-executable instructions. When the computer-executable instructions are executed by the processor, the steps of the arrester partial discharge monitoring method described in any one of claims 1 to 7 are implemented.

10. A computer-readable storage medium storing computer-executable instructions, wherein the computer-executable instructions, when executed by a processor, implement the steps of the method for monitoring partial discharge of a lightning arrester according to any one of claims 1 to 7.

Images