Fault diagnosis method, system, medium and product for double-break high-voltage vacuum circuit breaker

Abstract

A double-break high-voltage vacuum circuit breaker fault diagnosis method, system, medium, and product relate to the field of measuring electrical variables. The method includes: obtaining contact action timing data of the two breaks, vacuum chamber pressure data, as well as ambient temperature, ambient humidity, and system load index; calculating a mechanical characteristic coordination vector; calculating the heat imbalance coefficient of the two breaks; collecting the voltage sharing ratio and transition recovery voltage characteristics during the breaking process to determine a voltage tolerance difference index; inputting the mechanical characteristic coordination vector and the voltage tolerance difference index into a fault diagnosis model to obtain a fault diagnosis result; calculating the environmental impact factor of the high-voltage vacuum circuit breaker under the current operating conditions, generating an operating condition characteristic vector, and determining a fault warning threshold; generating a fault warning message when the warning parameter index of the fault diagnosis result exceeds the fault warning threshold. Implementing this application can promptly detect faults in double-break high-voltage vacuum circuit breakers.

Description

Technical Field

[0001] The present application relates to the field of measuring electrical variables, and in particular to a fault diagnosis method, system, medium and product for a double-break high-voltage vacuum circuit breaker. Background Art

[0002] High-voltage vacuum circuit breakers are essential switchgear used to control and protect circuits in power systems. Their primary function is to switch load current during normal operation and rapidly interrupt fault current in the event of a fault. Compared to single-break structures, double-break high-voltage vacuum circuit breakers utilize two vacuum interrupters connected in series, with each interrupter carrying half the recovery voltage. This provides higher interrupting capacity and stronger insulation performance, making them particularly suitable for transmission and distribution systems operating at voltage levels of 110 kV and above.

[0003] In related technologies, fault diagnosis for double-break high-voltage vacuum circuit breakers primarily relies on regular maintenance and simple online monitoring. Maintenance personnel typically use mechanical property testers to measure parameters such as the circuit breaker's opening and closing times and travel characteristics, and infrared thermometers to detect contact temperature distribution. Online monitoring systems primarily collect basic electrical parameters of the circuit breaker, such as operating current waveforms and switch position signals, and set fixed thresholds for fault alarms.

[0004] However, due to the different environments in which the equipment is located and the different probabilities of failure, the threshold alarm mechanism in related technologies often finds it difficult to perceive the corresponding environment. There is a delay in identifying faults in high-risk environments, and warnings are generally issued only after serious problems occur in the equipment, which often leads to increased maintenance costs. Summary of the Invention

[0005] The present application provides a double-break high-voltage vacuum circuit breaker fault diagnosis method, system, medium and product for timely detecting double-break high-voltage vacuum circuit breaker faults.

[0006] In the first aspect, the present application provides a double-break high-voltage vacuum circuit breaker fault diagnosis method, which is applied to a fault detection system. The method comprises: obtaining the contact action timing data of the high-voltage vacuum circuit breaker at the two breaks, the pressure data in the vacuum chamber, as well as the ambient temperature, ambient humidity and system load index; calculating the contact action speed difference and bounce characteristic parameters of the two breaks according to the contact action timing data, and generating a mechanical characteristic coordination vector in combination with the opening and closing energy consumption data of the two breaks; obtaining the temperature distribution data of the conductive circuit of the two breaks, and calculating the heat imbalance coefficient of the two breaks based on the temperature distribution data; collecting The voltage sharing ratio and transition recovery voltage characteristics of the two breakers during the breaking process are combined with the pressure data and heat imbalance coefficient in the vacuum chamber to determine the voltage tolerance difference index; the mechanical characteristic synergy vector and the voltage tolerance difference index are input into the fault diagnosis model to obtain the fault diagnosis result; based on the ambient temperature, ambient humidity and system load index, the environmental impact factor of the high-voltage vacuum circuit breaker under the current working condition is calculated, the working condition characteristic vector is generated, and the fault warning threshold of the corresponding working condition characteristic vector is determined; when the warning parameter index of the fault diagnosis result exceeds the fault warning threshold, a fault warning information is generated.

[0007] In the above embodiment, the fault detection system obtains data such as the contact action timing and pressure of the two breaks and combines them with environmental factors to calculate the difference indicators of mechanical characteristics and voltage tolerance capabilities. Then, the fault warning threshold is determined based on the environmental impact. This achieves accurate diagnosis and timely warning of double-break high-voltage vacuum circuit breaker faults, thereby reducing maintenance costs.

[0008] In combination with some embodiments of the first aspect, in some embodiments, when the warning parameter index of the fault diagnosis result exceeds the fault warning threshold, after the step of generating fault warning information, the method also includes: obtaining multiple historical fault data containing equipment number, fault type, fault degree and maintenance record, and constructing a historical fault database; performing model training based on the historical fault database to obtain a fault development prediction model; inputting the fault warning information into the fault development prediction model to obtain fault timing characteristics; generating a fault analysis report based on the fault timing characteristics; and pushing the fault analysis report to the mobile terminal of the target personnel.

[0009] In the above embodiment, the fault detection system constructs a historical fault database for model training, obtains a fault development prediction model, and generates an analysis report based on the fault timing characteristics, thereby achieving accurate prediction of the development trend of circuit breaker faults and reasonable planning of maintenance costs.

[0010] In combination with some embodiments of the first aspect, in some embodiments, the step of generating a fault analysis report based on the fault timing characteristics specifically includes: determining the expected service life of the high-voltage vacuum circuit breaker based on the fault timing characteristics; determining the maintenance cost budget based on the expected service life and maintenance records in the historical fault database; and generating a fault analysis report based on the expected service life and the maintenance cost budget.

[0011] In the above embodiment, the fault detection system determines the expected life by analyzing the fault time sequence characteristics and determines the maintenance cost budget based on the historical maintenance records, thereby achieving accurate prediction of the management and maintenance costs of the circuit breaker throughout its life cycle.

[0012] In combination with some embodiments of the first aspect, in some embodiments, after the steps of obtaining the contact action timing data of the high-voltage vacuum circuit breaker at two breaks, the pressure data in the vacuum chamber, and the ambient temperature, ambient humidity and system load index, the method also includes: determining the edge computing node closest to the location of the high-voltage vacuum circuit breaker; integrating the contact action timing data, the pressure data in the vacuum chamber, the ambient temperature, ambient humidity and the system load index into an original data packet; sending the original data packet to the edge computing node; and receiving the fault calculation result data packet returned by the edge computing node.

[0013] In the above embodiment, the fault detection system processes raw data through edge computing nodes, achieves rapid data processing and real-time response, and improves the efficiency and accuracy of fault diagnosis.

[0014] In combination with some embodiments of the first aspect, in some embodiments, after the step of receiving the fault diagnosis results and fault warning threshold returned by the edge computing node, the method also includes: extracting the computing node mark and data timestamp in the fault calculation result data packet; when the data timestamp is inconsistent with the original timestamp of the original data packet, sending a data acquisition request containing the original timestamp to the edge computing node.

[0015] In the above embodiment, the fault detection system ensures the accuracy of the timing of the data and the reliability of the diagnosis result by verifying the consistency of the data timestamps.

[0016] In combination with some embodiments of the first aspect, in some embodiments, when the warning parameter index of the fault diagnosis result exceeds the fault warning threshold, after the step of generating fault warning information, the method also includes: extracting the spatiotemporal distribution characteristics of the fault diagnosis result from the historical fault database; determining the correlation influence coefficient of the circuit breakers in each area based on the circuit breaker location data and spatiotemporal distribution characteristics of the geographic information system; when a preset power outage occurs, determining the fault spread range based on the correlation influence coefficient, and generating a partition maintenance priority list.

[0017] In the above embodiment, the fault detection system determines the correlation influence coefficient of the circuit breaker by analyzing the temporal and spatial distribution characteristics of the fault diagnosis results, thereby achieving accurate early warning of the preset power outage event and accurate prediction of the fault propagation range.

[0018] In combination with some embodiments of the first aspect, in some embodiments, when a preset power outage event occurs, after the step of determining the fault propagation range based on the associated impact coefficient and generating a partition maintenance priority list, the method also includes: determining a path planning table based on the partition maintenance priority list and real-time road conditions information; determining a maintenance scheduling plan based on maintenance personnel information, equipment supply information and the path planning table; determining a partition maintenance task sequence based on the maintenance scheduling plan, and pushing multiple maintenance tasks in the partition maintenance task sequence to the corresponding maintenance terminal.

[0019] In the above embodiment, the fault detection system formulates a maintenance scheduling plan by combining real-time road condition information, thereby achieving efficient deployment of maintenance resources and allocation of maintenance tasks.

[0020] In a second aspect, an embodiment of the present application provides a fault detection system, which includes: one or more processors and a memory; the memory is coupled to the one or more processors, the memory is used to store computer program code, the computer program code includes computer instructions, and the one or more processors call the computer instructions to enable the fault detection system to execute the method described in the first aspect and any possible implementation method of the first aspect.

[0021] In a third aspect, an embodiment of the present application provides a computer program product comprising instructions, which, when the computer program product is run on a fault detection system, enables the fault detection system to execute the method described in the first aspect and any possible implementation of the first aspect.

[0022] In a fourth aspect, an embodiment of the present application provides a computer-readable storage medium comprising instructions. When the instructions are executed on a fault detection system, the fault detection system executes the method described in the first aspect and any possible implementation of the first aspect.

[0023] It is understandable that the fault detection system provided in the second aspect, the computer program product provided in the third aspect, and the computer storage medium provided in the fourth aspect are all used to execute the methods provided in the embodiments of the present application. Therefore, the beneficial effects that can be achieved can be referenced to the beneficial effects of the corresponding methods and will not be repeated here.

[0024] One or more technical solutions provided in the embodiments of this application have at least the following technical effects or advantages:

[0025] 1. Due to the coordinated analysis of double-break contact action timing data and vacuum chamber pressure data, as well as the comprehensive evaluation of ambient temperature, humidity and load index, combined with the dual diagnosis mechanism of mechanical characteristic coordination vector and voltage tolerance difference index, and the introduction of environmental impact factors to dynamically adjust the fault warning threshold, the operating status of the circuit breaker can be comprehensively and accurately evaluated, effectively solving the problem that related technologies cannot adapt to different environmental conditions by relying solely on fixed thresholds. It thus realizes intelligent fault diagnosis and precise warning, and improves the operation and maintenance efficiency of circuit breakers.

[0026] 2. Due to the adoption of a distributed architecture that processes data at the nearest edge computing node, the original data is integrated and then locally calculated and processed, and the calculation results are quickly returned through the data packet transmission mechanism. This can greatly reduce data transmission delays and computing loads, effectively solving the response lag and resource waste problems caused by centralized processing in related technologies, thereby achieving real-time fault diagnosis and improving computing efficiency, and ensuring the system's rapid response capabilities.

[0027] 3. By adopting the spatiotemporal distribution characteristic analysis based on historical fault data, combining the circuit breaker location data of the geographic information system to build an associated impact model, and predicting the spread of faults when a preset power outage occurs, the risk of fault spread can be accurately assessed, effectively solving the problem of unpredictable fault chain reactions in related technologies, and thus achieving accurate prediction of the fault range and reasonable division of maintenance priorities, thereby improving the overall reliability of the power grid system. BRIEF DESCRIPTION OF THE DRAWINGS

[0028] Figure 1 This is a flow chart of a method for diagnosing a fault of a double-break high-voltage vacuum circuit breaker in an embodiment of the present application;

[0029] Figure 2 This is another flowchart of the double-break high-voltage vacuum circuit breaker fault diagnosis method according to an embodiment of the present application;

[0030] Figure 3 It is a schematic diagram of the structure of a physical device of the fault detection system in an embodiment of the present application. DETAILED DESCRIPTION

[0031] The terms used in the following examples of the present application are only for the purpose of describing specific embodiments and are not intended to limit the present application. As used in the specification of the present application, the singular expressions "a", "an", "above", "the", and "this" are intended to include plural expressions as well, unless the context clearly indicates otherwise. It should also be understood that the term "and / or" used in the present application refers to any or all possible combinations of one or more of the listed items.

[0032] In the following, the terms "first" and "second" are used for descriptive purposes only and should not be understood to imply or suggest relative importance or implicitly indicate the number of the technical features indicated. Therefore, the features defined as "first" and "second" may explicitly or implicitly include one or more of the features. In the description of the embodiments of this application, unless otherwise specified, "plurality" means two or more.

[0033] It should be noted that a double-break circuit breaker (DBC) refers to two vacuum interrupters (vacuum chambers) connected in series within the circuit breaker, each containing a pair of contacts (moving and static). The core feature of a double-break high-voltage vacuum circuit breaker lies in its two vacuum interrupters, each containing a pair of conductive contacts (moving and static). During normal operation, the contacts of both interrupters close simultaneously, forming a complete conductive path. To disconnect the circuit, the moving contacts of both interrupters must simultaneously separate from their corresponding static contacts. This allows the system recovery voltage to be evenly shared across the two interrupters, significantly improving the circuit breaker's insulation strength and interrupting capacity. Due to this structural feature, reliable operation of the circuit breaker requires highly synchronized mechanical operation of the two interrupters, while also ensuring balanced electrical performance. Therefore, when conducting fault diagnosis, it is important to focus on the coordination of contact operation timing and the balance of voltage sharing.

[0034] For ease of understanding, the application scenarios of the embodiments of the present application are introduced below.

[0035] A provincial power company operated a 110kV substation using a large number of double-break high-voltage vacuum circuit breakers as core switchgear. These circuit breakers share voltage through two series-connected vacuum interrupters, improving their interrupting capacity. However, the equipment operates in a complex and variable environment, with temperatures ranging from -20°C to 40°C, humidity varying from 20% to 95%, and seasonal load fluctuations. One summer, the region experienced consecutive high temperatures around 40°C, causing multiple circuit breakers to trip due to excessive environmental stress, resulting in widespread power outages. Traditional fixed-threshold warning mechanisms were unable to adapt to environmental changes and often triggered alarms only after equipment damage occurred. This not only increased maintenance costs but also compromised grid reliability.

[0036] In related technologies, basic circuit breaker fault detection can be achieved by using a mechanical property tester and a simple online monitoring system. Maintenance personnel regularly measure parameters such as the circuit breaker's opening and closing times and travel characteristics, and trigger fault alarms based on fixed thresholds. The following describes a scenario using the related art method for double-break high-voltage vacuum circuit breaker fault diagnosis.

[0037] A certain substation used a traditional circuit breaker fault diagnosis system, relying primarily on regular maintenance and simple online monitoring. Maintenance personnel used a mechanical property tester to measure parameters such as opening and closing times and travel characteristics quarterly, and an infrared thermometer to detect contact temperature distribution. The online monitoring system collected basic electrical parameters of the circuit breaker, such as the operating current waveform and switch position signal, and set fixed alarm thresholds. Early one year, an operating circuit breaker experienced abnormal heating, but the temperature did not reach the fixed alarm threshold of 85°C, so no warning was triggered. Subsequently, in humid weather, the circuit breaker experienced a phase-to-phase short circuit due to degraded insulation performance, resulting in equipment burnout. Subsequent analysis revealed that this accident could have been avoided if the warning threshold had been dynamically adjusted based on ambient humidity.

[0038] The double-break high-voltage vacuum circuit breaker fault diagnosis method in the embodiments of this application achieves accurate fault diagnosis and timely warning by collecting multi-dimensional operating data in real time and analyzing it in combination with environmental factors. It can dynamically adjust the warning threshold according to environmental conditions to achieve accurate fault judgment. The following describes scenarios in which the double-break high-voltage vacuum circuit breaker fault diagnosis method in this application is used.

[0039] A certain smart substation has introduced the fault diagnosis method of this application, collecting multi-dimensional data such as the circuit breaker's contact action timing, vacuum level, temperature distribution, etc. in real time, while monitoring the ambient temperature, humidity, and load level. The system quickly processes data through edge computing nodes to calculate the mechanical characteristic coordination vector and voltage tolerance difference index. In July of a certain year, the system detected that the contact temperature of a circuit breaker reached 65°C. Although it did not exceed the normal threshold, based on the extreme conditions of the ambient temperature of 38°C and humidity of 85% at the time, the system dynamically lowered the warning threshold to 60°C and issued a timely warning. Maintenance personnel carried out timely inspections and found that the contacts were micro-ablated. After replacement, a more serious failure was avoided.

[0040] It can be seen that the double-break high-voltage vacuum circuit breaker fault diagnosis method in the embodiment of the present application can not only achieve accurate fault detection, but also effectively solve the problems of poor environmental adaptability and delayed warning, thereby achieving optimization of fault prevention and maintenance costs.

[0041] For ease of understanding, the following describes the process of the method provided by this implementation in combination with the above scenario. Figure 1 , which is a flow chart of a double-break high-voltage vacuum circuit breaker fault diagnosis method in an embodiment of the present application.

[0042] S101. Acquire contact action timing data of the high-voltage vacuum circuit breaker at two breakers, pressure data in the vacuum chamber, and ambient temperature, ambient humidity, and system load index.

[0043] Among them, the contact action timing data represents the sampling data of the displacement, velocity and acceleration of the circuit breaker contacts changing with time during the opening and closing process; the vacuum chamber pressure data refers to the real-time monitoring value of the vacuum degree inside the vacuum interrupter, which is used to characterize the sealing performance of the vacuum chamber; the ambient temperature and ambient humidity respectively represent the temperature and relative humidity values ​​of the circuit breaker operating location; the system load index is used to indicate the load level of the power system where the circuit breaker is located, and is usually calculated comprehensively from parameters such as current and power factor.

[0044] The fault detection system needs to comprehensively collect various operating parameters during normal circuit breaker operation or routine testing. Specifically, the fault detection system first uses displacement sensors to collect the contact movement trajectory and simultaneously records the sampling time stamp to form a high-precision time-series data stream. A vacuum gauge also continuously monitors the internal pressure changes of the vacuum chamber, ensuring a sampling frequency of at least 100 Hz. Temperature and humidity sensors collect environmental data, and real-time load data is obtained from the system dispatcher. All data requires time synchronization and data calibration to ensure the accuracy of subsequent analysis.

[0045] In some embodiments, high-quality data collection and preprocessing can be achieved through a variety of methods: Optionally, the fault detection system uses an adaptive sampling algorithm to dynamically adjust the sampling frequency, preprocesses the raw data through piecewise linear interpolation and wavelet denoising, and then uses the Kalman filter algorithm for data fusion to ultimately obtain time series data with a high signal-to-noise ratio; Optionally, the fault detection system is based on a distributed sensor network architecture, adopts a multi-source heterogeneous data collaborative collection solution, performs real-time data cleaning and feature extraction through edge computing nodes, and then achieves continuous data acquisition and updating through time window sliding. It is understandable that other data collection and preprocessing methods can also be used to obtain the required types of data, which are not limited here.

[0046] In some embodiments, the fault detection system uses multi-source sensors to collect circuit breaker operation data in real time. The contact action timing data is collected using a high-precision displacement sensor, which uses the magnetic encoding principle to achieve continuous tracking of the contact position. After the displacement signal x(t) is digitally filtered,

[0047] Calculate the velocity using the central difference method:

[0048] v(t)=(x(t+Δt)-x(t-Δt)) / (2Δt);

[0049] Acceleration:

[0050] a(t)=(v(t+Δt)-v(t-Δt)) / (2Δt); x(t) is the position of the contact at time t, in millimeters (mm); Δt is the sampling time interval, with a recommended value of 1 ms and a range of 0.5 ms to 2 ms; v(t) is the velocity of the contact at time t, in meters per second (m / s); a(t) is the acceleration of the contact at time t, in meters per square second (m / s²).

[0051] The vacuum chamber pressure is measured by an ionization vacuum gauge with a sensitivity of 10⁻ 6 Pa, the pressure signal is subjected to exponential smoothing filtering to eliminate high-frequency noise. Among the environmental parameters, temperature and humidity data are collected using a composite sensor, and the system load index F is calculated using the following formula:

[0052] F=α(I / I_n)²+β(cosφ)+γ(T / T_n); where I is the real-time current, I_n is the rated current, cosφ is the power factor, T is the ambient temperature, T_n is the rated operating temperature, and α, β, and γ are weight coefficients obtained through historical data regression.

[0053] For example, during the opening process of a circuit breaker, the contact position recorded by the displacement sensor moves uniformly from x1 = 0 mm to x2 = 200 mm in t = 50 ms. The calculated average velocity is 4 m / s, with a peak acceleration of 80 m / s². At the same time, the vacuum chamber pressure is recorded as 2 × 10⁻ 5 Pa, ambient temperature 35℃, humidity 75%RH, load current 0.8 times rated value, substitute into the load index formula to calculate F=0.85.

[0054] S102. Calculate the contact action speed difference and bounce characteristic parameters of the two fractures based on the contact action timing data, and generate a mechanical characteristic coordination vector by combining the opening and closing energy consumption data of the two fractures.

[0055] Among them, the difference in contact movement speed indicates the degree of speed inconsistency between the two break contacts during the opening and closing process; the bounce characteristic parameters include the number of bounces, bounce time and bounce amplitude; the opening and closing energy consumption data refers to the energy loss of the operating mechanism during the opening and closing process; the mechanical characteristic coordination vector is used to characterize the coordination of the mechanical actions of the two break contacts.

[0056] After acquiring the contact action timing data, the fault detection system needs to perform feature extraction and vector construction. Specifically, the fault detection system first performs a differential operation on the timing data to obtain a velocity curve. The correlation coefficient and root mean square error of the velocity curves of the two fractures are calculated to quantify the velocity difference. A peak detection algorithm is then used to identify key time points during the bounce process and extract the bounce characteristic parameters. Energy consumption is calculated using the current and voltage waveforms of the actuator. Finally, these features are combined into a feature vector that describes the synergy of the mechanical properties.

[0057] In some embodiments, mechanical characteristic analysis and vector construction can be achieved in a variety of ways: Optionally, the fault detection system uses wavelet transform to perform time-frequency analysis on the velocity curve, extracts the energy characteristics of each frequency band, combines the fuzzy clustering algorithm to calculate the velocity coordination index, and then reduces the dimension through principal component analysis to obtain the final feature vector; Optionally, the fault detection system uses a long short-term memory network based on deep learning methods to extract temporal features, captures the interaction relationship between the two fractures through the attention mechanism, and finally obtains a fixed-dimensional coordination vector through full-connection layer mapping. It is understandable that other feature extraction and vector construction methods can also be used to achieve quantitative representation of mechanical characteristics, which is not limited here.

[0058] In some embodiments, the synergy of the mechanical properties of the two fractures is quantitatively analyzed through three dimensions: contact movement speed difference, bounce characteristics, and energy consumption.

[0059] For the velocity curve v_k(t) of fracture k (k=1, 2), define the velocity difference function:

[0060] ΔV(t)=|v1(t)-v2(t)|;

[0061] Feature extraction is performed using the speed difference curve after wavelet denoising. The speed coordination index S_v is defined as: S_v = exp(-λ∫ΔV(t)²dt / T), where T is the total action time and λ is the scale factor.

[0062] The bounce characteristics are analyzed using continuous wavelet transform (CWT), using the Morlet wavelet with a scale range of a∈[1, 64]. Ridge extraction is performed on the wavelet coefficients W(a, b) of the bounce signal x(t), yielding the number of bounces n, the average bounce time τ, and the bounce amplitude sequence {A_i}. The bounce characteristic parameter B is calculated as:

[0063] B=w1n+w2τ+w3σ(A); where σ(A) is the standard deviation of the bounce amplitude, and w1, w2, and w3 are weight coefficients.

[0064] The energy consumption is calculated from the current i(t) and voltage u(t) of the actuator:

[0065] E = ∫u(t)i(t)dt;

[0066] The final mechanical property coordination vector M is composed of the above parameters:

[0067] M=[S_v, B, E].

[0068] For example, during the closing process of a circuit breaker, the maximum velocity difference between the two breakers was recorded to be 0.5 m / s, with a duration of 8 ms. The calculated S_v was 0.92. Bounce analysis showed three bounces with an average duration of 2.5 ms and an amplitude standard deviation of 0.3 mm, resulting in B=0.45. The operating mechanism consumed 850 J of energy. The resulting mechanical property coordination vector M = [0.92, 0.45, 0.85].

[0069] S103 , obtaining temperature distribution data of the conductive loops of the two breaks, and calculating the heat dissipation coefficient of the two breaks based on the temperature distribution data.

[0070] Among them, the temperature distribution data of the conductive circuit represents the spatial distribution of the temperature field of the circuit breaker contacts and their connecting conductors; the heat imbalance coefficient refers to the degree of difference in the temperature distribution between the two fractures and is used to characterize the heating uniformity of the conductive circuit; the temperature distribution data includes the temperature values ​​of multiple measuring points such as the contact surface temperature, the connecting conductor temperature, and the ambient reference temperature.

[0071] The fault detection system monitors temperature while the circuit breaker is energized. Specifically, it uses an infrared thermal imager to scan the conductive circuits between the two breakers, acquiring a high-resolution temperature field image. The temperature field image is then meshed and feature points extracted to create a three-dimensional temperature distribution model. The system then calculates the temperature difference between the two breakers and, combined with the spatial gradient information of the temperature field, uses a weighted average to determine the heat dissipation coefficient.

[0072] In some embodiments, temperature field analysis and imbalance assessment can be achieved in a variety of ways: Optionally, the fault detection system uses a thermal field finite element analysis method to construct a heat conduction model of the conductive circuit, obtains the steady-state temperature distribution by solving the temperature field distribution equation, and then uses statistical methods to calculate the discreteness index and unevenness coefficient of the temperature field; Optionally, the fault detection system uses computer vision technology to perform image segmentation and region recognition on infrared images, extract temperature features of key areas, establish a temperature distribution pattern through a deep learning model, and finally calculate the similarity of the temperature patterns of the two fractures to obtain the imbalance coefficient. It is understandable that other temperature field analysis methods can also be used to evaluate heat imbalance, which is not limited here.

[0073] In some embodiments, the calculation of the heat dissipation coefficient is based on temperature field data collected by an infrared thermal imager. The system uses a high-precision infrared thermal imager with a spatial resolution of 0.1 mm, scanning the conductive loops of the two fractures of the circuit breaker in real time at a frequency of 10 Hz. The temperature field data is preprocessed by gridding, converting the temperature distribution of each fracture into a two-dimensional matrix T(i, j), where i and j represent grid coordinates. For each fracture k (k = 1, 2), the spatial gradient of its temperature field is calculated:

[0074] G_k(i,j)=√[(∂T / ∂x)²+(∂T / ∂y)²];

[0075] The heat imbalance coefficient η of the two fractures is defined as:

[0076] η = ∑∑w(i, j) | T1(i, j) - T2(i, j) | / √[(G1(i, j) + G2(i, j)) / 2]; where w(i, j) is the position weight factor, reflecting the contribution of different positions to the heat dissipation. The weight factor is determined based on component importance, with the contact area receiving a higher weight (typically 0.6-0.8) and the connecting conductor area receiving a lower weight (typically 0.2-0.4). The resulting heat dissipation coefficient η is normalized to a value between 0 and 1, with larger values ​​indicating more severe heat dissipation.

[0077] For example, during the operation of a circuit breaker, infrared imaging was used to obtain temperature distribution data for two fractures. The contact area at fracture A had a maximum temperature of 85°C, with a temperature gradient of 8°C / cm. The corresponding location at fracture B had a temperature of 65°C, with a temperature gradient of 5°C / cm. Substituting this into the calculation formula, and considering the contact area weight of 0.7, the resulting imbalance coefficient contribution for this area was 0.82. Similar calculations for other areas yielded an overall thermal imbalance coefficient of η = 0.76, indicating significant thermal imbalance.

[0078] S104. Collect the voltage sharing ratio and transition recovery voltage characteristics of the two breakers during the breaking process, and determine the voltage tolerance difference index by combining the pressure data and heat imbalance coefficient in the vacuum chamber.

[0079] Among them, the voltage sharing ratio indicates the proportion of overvoltage borne by the two fractures during the breaking process; the transition recovery voltage characteristics include parameters such as the rise rate, peak value, and oscillation frequency; the voltage tolerance difference index is used to characterize the degree of difference in the insulation performance of the two fractures; and the heat imbalance coefficient reflects the change in the contact resistance of the contacts.

[0080] The fault detection system measures voltage characteristics during circuit breaker opening. Specifically, the system first uses high-voltage probes to synchronously capture the instantaneous voltage waveforms at both breakpoints and calculates the dynamic changes in the voltage sharing ratio. It then extracts the time and frequency domain characteristics of the transition recovery voltage, including rise time, peak multiple, and oscillation period. It then performs a multi-dimensional correlation analysis between the voltage characteristics and the vacuum chamber pressure and thermal imbalance coefficient to comprehensively assess the difference in voltage tolerance between the two breakpoints, ultimately outputting a standardized difference index.

[0081] In some embodiments, voltage characteristic analysis and difference assessment can be achieved through various methods: Optionally, the fault detection system uses wavelet multi-resolution analysis to perform time-frequency decomposition of the voltage waveform, extract the energy distribution characteristics at each scale, and establish a multivariate regression model based on vacuum and temperature factors to calculate a comprehensive score for voltage tolerance. Optionally, the fault detection system uses artificial neural network technology to take voltage waveform characteristics, pressure data, and temperature coefficient as input, learns their inherent correlations through a multi-layer perceptron model, and outputs a normalized voltage tolerance difference index. It is understood that other analysis methods can also be used to evaluate voltage tolerance differences, which are not limited here.

[0082] In some embodiments, the voltage characteristics analysis during the circuit breaker opening process is based on a high-speed data acquisition system with a sampling rate of 10 MHz and a precision of 16 bits. For the instantaneous voltages u1(t) and u2(t) at the two breakers, the voltage sharing ratio K(t) is defined as:

[0083] K(t)=u1(t) / [u1(t)+u2(t)];

[0084] The system analyzes the transition recovery voltage characteristics through wavelet transform. Using the db4 wavelet basis function, the voltage signal is decomposed into five layers, extracting the energy coefficient E_j (j = 1, 2, ..., 5) for each frequency band. Combining the vacuum chamber pressure p and the heat dissipation coefficient η, the voltage tolerance difference index D is calculated as follows:

[0085] D=w1|K(t)-0.5|_max+w2∑(E1_j-E2_j)² / p+w3η;

[0086] Among them, w1, w2, and w3 are weight coefficients, which are set by the user based on experience.

[0087] For example, when a circuit breaker interrupts a short-circuit current, it is recorded that the recovery voltage at break A is 58%, while that at break B is 42%. Wavelet analysis shows that the energy difference in the high-frequency band (>1MHz) is as high as 30%, and the vacuum degree at this time is 3×10⁻ 5 Pa, and the heat dissipation coefficient is 0.76. Substituting this into the formula, the voltage withstand capability difference index D=0.68, indicating that there is a significant difference in the insulation performance of the two fractures.

[0088] S105 , inputting the mechanical characteristic coordination vector and the voltage tolerance difference index into the fault diagnosis model to obtain a fault diagnosis result.

[0089] Among them, the mechanical characteristic coordination vector characterizes the synchronization and stability of the mechanical actions of the two fractures; the voltage withstand capability difference index reflects the degree of inconsistency in the insulation performance of the two fractures; and the fault diagnosis results include information such as fault type, fault severity, and fault development trend.

[0090] After acquiring the feature vector, the fault detection system assesses the fault status. Specifically, the system first normalizes the mechanical characteristic synergy vector and the voltage tolerance difference index. The processed features are then fed into a pre-trained fault diagnosis model, which uses a multi-layered structure to process mechanical and electrical characteristics separately. The model then infers the fault probability distribution and uses an expert rule system to determine the fault type. Finally, a diagnostic report containing detailed fault information is generated.

[0091] It should be noted that the fault diagnosis model here utilizes a multi-layer neural network architecture, comprising three core layers: feature extraction, attention mechanism, and classification output. During the training phase, the model inputs mechanical characteristic synergy vectors (including contact velocity differences, bounce characteristics, and energy consumption data) and voltage tolerance difference indicators (including voltage sharing ratio, transition recovery characteristics, and vacuum level data) from historical operating data. The model outputs corresponding fault type and severity labels. The model parameters are optimized using a cross-entropy loss function, and model performance is evaluated through K-fold cross-validation. In practical applications, the model receives real-time collected operating parameters, dynamically calculates the fault probability distribution based on environmental influencing factors (temperature, humidity, and load index), and determines whether to trigger the early warning mechanism based on the confidence level. The model adaptively adjusts the weighting of different features to improve diagnostic accuracy.

[0092] In some embodiments, fault diagnosis uses a deep learning model structure that includes three modules: feature extraction, attention mechanism, and classification output. The input layer receives the mechanical characteristic coordination vector M and the voltage tolerance difference index D, and obtains a high-dimensional representation through feature mapping:

[0093] H = ReLU(W1[M;D]+b1);

[0094] The attention layer calculates the importance weight α of each feature:

[0095] e_i=v^Ttanh(W2h_i+b2);

[0096] α_i=softmax(e_i);

[0097] The weighted features are passed through the fully connected layer to obtain the fault type probability distribution p and the fault severity score s:

[0098] p=softmax(W3∑α_iH_i+b3);

[0099] s=σ(W4∑α_iH_i+b4); where σ is the sigmoid function.

[0100] The model is optimized using the cross entropy loss function:

[0101] L=-∑y_ilog(p_i)+λ|ss*|²; where y_i is the true label, s* is the true fault severity, and λ is the balance coefficient.

[0102] For example, the input feature vector of a circuit breaker is [0.92, 0.45, 0.85, 0.68], and the model calculates the fault type probability distribution [0.05, 0.82, 0.10, 0.03]. This indicates that the most likely fault is contact ablation (Category 2), with a fault severity score of 0.65, corresponding to a medium severity level.

[0103] S106. Calculate the environmental impact factor of the high-voltage vacuum circuit breaker under the current working condition based on the ambient temperature, ambient humidity, and system load index, generate a working condition characteristic vector, and determine a fault warning threshold corresponding to the working condition characteristic vector.

[0104] Among them, the environmental impact factor represents the comprehensive impact of environmental conditions on the performance of the circuit breaker; the operating condition feature vector refers to the feature set that describes the current operating status; the fault warning threshold is used to determine the dynamic boundary value of the fault severity; and the system load index reflects the actual load level of the circuit breaker.

[0105] The fault detection system needs to dynamically adjust its warning criteria based on environmental conditions. Specifically, it first uses multivariate regression analysis to calculate the weights of the impact of ambient temperature and humidity on circuit breaker performance. It then builds a working condition assessment model based on the system load index to generate a characteristic vector for the current working condition. Based on statistical analysis of historical data, it establishes a mapping between the characteristic vector and the probability of fault occurrence. Finally, an adaptive algorithm is used to calculate the fault warning threshold corresponding to the current working condition.

[0106] In some embodiments, environmental impact assessment and threshold calculation can be implemented in a variety of ways: Optionally, the fault detection system uses a fuzzy inference system, taking environmental parameters and load indicators as input variables, calculating environmental impact factors through fuzzy rule reasoning, and dynamically optimizing warning thresholds based on historical fault data; Optionally, the fault detection system uses reinforcement learning methods, taking environmental conditions as the state space and warning thresholds as the action space, and gradually optimizing the threshold adjustment strategy through a value function to achieve adaptive optimization of the warning mechanism. It is understandable that other methods can also be used to implement working condition assessment and threshold calculation, which are not limited here.

[0107] In some embodiments, the environmental impact factor is calculated using a multivariate nonlinear mapping model. Assuming that the baseline values ​​of the ambient temperature T, relative humidity H, and load index F are T0, H0, and F0, respectively, the environmental impact factor E is defined as:

[0108] E=α·exp[k1(T-T0) / T0]+β·exp[k2(H-H0) / H0]+γ·(F / F0)^n; where α, β, and γ are weight coefficients and satisfy α+β+γ=1, k1 and k2 are temperature and humidity sensitivity coefficients, and n is the nonlinear exponent of the load index.

[0109] The operating condition characteristic vector C is constructed through polynomial kernel transformation:

[0110] C=[E, E², T·H, H·F, T·F, φ(T, H, F)]; where φ(T, H, F) is the three-variable interaction term.

[0111] Establish an adaptive function of the fault warning threshold η based on historical data:

[0112] η=η0·[1+μ1tanh(w1C1)+μ2tanh(w2C2)+…+μ_ntanh(w_nC_n)]; where η0 is the baseline threshold, and μᵢ and wᵢ are adaptive coefficients.

[0113] For example, a circuit breaker operates in an ambient temperature of 38°C (baseline 20°C), humidity of 85% (baseline 65%), and a load index of 0.9 (baseline 0.8). The calculated environmental impact factor E = 1.35. The generated operating condition feature vector is then threshold mapped, adjusting the baseline warning threshold from 0.8 to 1.08.

[0114] S107 : When the warning parameter index of the fault diagnosis result exceeds the fault warning threshold, generate fault warning information.

[0115] Among them, the warning parameter index refers to the quantitative indicator used to evaluate the severity of the fault; the fault warning threshold represents the critical value that triggers the warning; the fault warning information includes the fault type, location, severity, and handling suggestions.

[0116] Fault detection systems need to issue timely warnings when they detect an anomaly. Specifically, the system first monitors the changing trends of various warning parameters in real time. When a parameter exceeds the corresponding warning threshold, the system immediately triggers the warning mechanism. It then assesses the urgency of the fault based on the degree and duration of the overshoot. It then generates a warning report containing detailed fault information and recommended solutions. Finally, it pushes the warning information to relevant maintenance personnel through various communication channels.

[0117] In some embodiments, early warning triggering and information push can be implemented in a variety of ways: Optionally, the fault detection system can employ a multi-level early warning mechanism, setting different warning levels based on the degree of parameter excursion, determining the overall warning level through weight calculation, and selecting the corresponding push strategy and processing flow based on the warning level; Optionally, the fault detection system can establish a network of equipment-fault-measure associations based on knowledge graph technology, matching the most appropriate treatment plan in real time, and scheduling maintenance tasks through an intelligent scheduling system. It is understood that other methods can also be used to implement early warning management, which are not limited here.

[0118] In practical applications, multiple edge nodes can be deployed according to the distribution of substations to achieve a reasonable allocation of computing resources. The following supplements the scenario of this embodiment.

[0119] A regional power grid company, building on this solution, further integrated its historical fault database and geographic information system. During a thunderstorm in August of that year, the system detected circuit breaker anomalies at multiple substations. Based on spatiotemporal distribution analysis and impact assessment, the system quickly located the substation at the source of the fault and predicted the likely path of propagation. Using a zoning maintenance priority list and intelligent scheduling scheme, the system planned optimal repair routes for maintenance personnel and assigned tasks based on their expertise. Ultimately, the entire maintenance process was completed within four hours, minimizing the scope of the power outage.

[0120] After combining the above scenarios, the following is a more detailed description of the process of the method provided by this implementation. Figure 2 , is another flow chart of the double-break high-voltage vacuum circuit breaker fault diagnosis method in an embodiment of the present application.

[0121] S201. Acquire contact action timing data of the high-voltage vacuum circuit breaker at two breakers, pressure data in the vacuum chamber, and ambient temperature, ambient humidity, and system load index.

[0122] Referring to step S101 , the fault detection system acquires various operating data and environmental data.

[0123] In some embodiments, after acquiring the data, the fault detection system may not refer to the above steps S102-S106 for data processing. The fault detection system may send the data to the edge device for calculation to improve computing efficiency. Specifically, the fault detection system will determine the edge computing node closest to the high-voltage vacuum circuit breaker, and then integrate the contact action timing data, vacuum chamber pressure data, ambient temperature, ambient humidity and system load index into the original data packet; then send the original data packet to the edge computing node, and receive the fault calculation result data packet returned by the edge computing node.

[0124] Among them, edge devices refer to computing devices deployed at the edge of the network; raw data packets represent unprocessed multi-source data sets; edge computing nodes refer to local computing units with data processing capabilities; and fault calculation result data packets contain processed feature vectors and diagnostic results.

[0125] Fault detection systems need to fully utilize distributed computing resources. Specifically, they first obtain available node information from the edge computing node registry and select the nearest computing node based on geographic location. They then encapsulate the collected multi-source heterogeneous data into a standard data packet containing data identifiers, timestamps, and raw data. These data packets are then sent to edge nodes via secure channels for parallel computing, enabling distributed processing of the computing load.

[0126] In some embodiments, the selection of edge computing nodes adopts a comprehensive evaluation mechanism based on physical distance, network latency and computing load. The system uses a weighted distance function:

[0127] D(i)=w1d(p0, p_i)+w2L(i)+w3C(i) calculates the optimal node, where physical distance d, network delay L and computing load C are assigned different weights respectively.

[0128] Data transmission uses a reliability guarantee mechanism, which is dynamically adjusted through an adaptive retransmission timeout (RTO). The RTO value is calculated based on the smoothed round-trip delay (RTT), specifically:

[0129] RTO(i)=RTT(i)+4σ(RTT).

[0130] The original data packet is designed with a three-segment structure, consisting of a header containing device identification, timestamp, and priority, a data payload containing contact action timing, vacuum chamber pressure, and environmental parameters, and a checksum based on the entire packet data.

[0131] To ensure transmission reliability, the system monitors the round-trip time (RTT) in real time and dynamically updates the retransmission strategy. The RTT is calculated using the exponentially weighted moving average method, namely:

[0132] RTT(i)=α·RTT(i-1)+(1-α)·(t_ack-t_send).

[0133] For example, after a circuit breaker triggered a fault alarm, the system selected the optimal edge node (physical distance 2 kilometers, network delay 15 milliseconds) within 50 milliseconds through the above mechanism. The total time for data transmission and calculation was 530 milliseconds. The entire process was completed automatically and data consistency was guaranteed.

[0134] In some embodiments, the fault detection system needs to perform data verification after receiving the data packet returned by the edge computing node; specifically, the fault detection system will extract the computing node mark and data timestamp in the fault calculation result data packet, and when the data timestamp is inconsistent with the original timestamp of the original data packet, it will send a data acquisition request containing the original timestamp to the edge computing node.

[0135] Among them, the computing node tag is used to uniquely identify the edge node that processes data; the data timestamp represents the time information of data processing; the original timestamp refers to the time stamp when the data is collected; and the data acquisition request is used to re-acquire the calculation results.

[0136] The fault detection system must ensure the timing consistency of data processing. Specifically, it first parses the metadata in the returned data packet to extract the compute node tag and processing timestamp. It then compares these timestamps with the original data packet to determine if there are any timing discrepancies. If a time discrepancy is detected, it immediately generates a data retrieval request containing the original timestamp to ensure data timing accuracy.

[0137] In some embodiments, the data verification mechanism implements timestamp consistency checking based on a distributed clock synchronization protocol. The system calculates the relationship between the edge node timestamp, the original timestamp, and the transmission delay using a time deviation function Δt, i.e., Δt = |T_edge - T_origin - T_trans|.

[0138] Taking into account the randomness of network transmission, the system uses a dynamic fault tolerance threshold ε(t) = ε0 + k·log(1 + σ²(RTT)) for judgment, where the basic fault tolerance threshold ε0 is set according to system stability, k is the adjustment coefficient, and σ²(RTT) is the variance of the round-trip delay.

[0139] When it is detected that the time deviation exceeds the fault tolerance threshold, the system automatically generates a re-retrieval request containing the original timestamp, data range and verification code. The verification code is generated based on the session key through the HMAC algorithm to ensure the authenticity of the request.

[0140] For example, during a data verification, the system discovered that the timestamp of the data packet returned by the edge node was delayed by 2.5 seconds, significantly exceeding the fault tolerance threshold of 200 milliseconds. It immediately triggered the data retrieval mechanism to ensure the temporal consistency of the data.

[0141] S202. Calculate the contact action speed difference and bounce characteristic parameters of the two fractures according to the contact action timing data, and generate a mechanical characteristic coordination vector by combining the opening and closing energy consumption data of the two fractures.

[0142] Referring to step S102 , the fault detection system calculates a mechanical characteristic coordination vector.

[0143] S203 , obtaining temperature distribution data of the conductive loops of the two breaks, and calculating the heat dissipation coefficient of the two breaks based on the temperature distribution data.

[0144] Referring to step S103 , the fault detection system calculates the heat imbalance coefficient.

[0145] S204. Collect the voltage sharing ratio and transition recovery voltage characteristics of the two breakers during the breaking process, and determine the voltage tolerance difference index by combining the pressure data and the heat imbalance coefficient in the vacuum chamber.

[0146] Referring to step S104 , the fault detection system calculates a voltage tolerance difference index.

[0147] S205 : Input the mechanical characteristic coordination vector and the voltage tolerance difference index into the fault diagnosis model to obtain a fault diagnosis result.

[0148] Referring to step S105 , the fault detection system determines a fault diagnosis result.

[0149] S206. Calculate the environmental impact factor of the high-voltage vacuum circuit breaker under the current working condition based on the ambient temperature, ambient humidity, and system load index, generate a working condition characteristic vector, and determine a fault warning threshold corresponding to the working condition characteristic vector.

[0150] Referring to step S106 , the fault detection system determines a fault warning threshold.

[0151] S207: When the warning parameter index of the fault diagnosis result exceeds the fault warning threshold, generate fault warning information.

[0152] Referring to step S107 , the fault detection system generates a warning message when the fault diagnosis result is abnormal.

[0153] S208: Acquire multiple historical fault data including equipment numbers, fault types, fault severity and maintenance records, and build a historical fault database.

[0154] Among them, the historical fault database refers to a structured data set that stores the historical operation fault information of the circuit breaker; the equipment number is used to uniquely identify each circuit breaker; the fault type indicates the specific classification of the fault; the fault degree reflects the severity of the fault; and the maintenance record contains fault handling methods and effect evaluation information.

[0155] A fault detection system requires a complete historical data management system. Specifically, the system first extracts historical fault records from the equipment management system, including basic information such as the time, type, and location of the fault. It then collects fault handling reports completed by maintenance personnel, extracting fault cause analysis and treatment plans. The data is then cleaned and standardized to establish a unified data format. Finally, a relational database is constructed to establish a fault type index and device associations.

[0156] In some embodiments, historical data collection and management can be achieved through various methods: Optionally, the fault detection system can adopt a distributed database architecture, design a multi-layered data model encompassing dimensions such as equipment information, operating status, fault records, and repair measures, and analyze fault patterns and evolution patterns through data mining techniques; Optionally, the fault detection system can establish a decentralized data storage system based on blockchain technology to ensure data traceability and immutability, enabling secure sharing of fault data. It is understood that other methods can also be used to achieve historical data management, and these are not limited here.

[0157] In some embodiments, the historical fault database uses a spatiotemporal multidimensional index structure. Each fault record is represented as a vector: F = [ID, t, l, s, {x_i}, {y_j}, {z_k}], where t is the timestamp, l is the location coordinate, s is the fault severity, {x_i} is the device parameter set, {y_j} is the environmental parameter set, and {z_k} is the maintenance record set.

[0158] Build an R-tree spatial index:

[0159] Node={MBR, childPtr[], entryCount};

[0160] MBR=[t_min,t_max,l_min,l_max];

[0161] Data retrieval uses multidimensional range query: Q(t1, t2, l1, l2) = {F|t1≤Ft≤t2∧l1≤Fl≤l2}; realizing spatiotemporal correlation analysis and pattern mining.

[0162] For example, the system recorded 534 circuit breaker failures in a certain area over five years. Through spatiotemporal indexing, it can quickly locate 68 contact failures that occurred during the high temperature period of a certain summer, providing data support for failure mode analysis.

[0163] S209: Perform model training based on the historical fault database to obtain a fault development prediction model.

[0164] Among them, the fault development prediction model refers to a mathematical model used to predict the fault evolution trend. The model training process includes steps such as feature engineering, parameter optimization and performance verification; the historical fault database provides the sample data required for model training.

[0165] Fault detection systems need to build prediction models based on historical data. Specifically, the system first performs time-series analysis on historical data to extract key characteristics and patterns of fault development. It then designs a deep learning model structure suitable for time-series prediction, including a data preprocessing layer, a feature extraction layer, and a prediction output layer. The system then uses a training dataset for model training and parameter optimization, evaluating model performance through cross-validation. Finally, the optimal model is selected for fault prediction.

[0166] It should be noted that the fault development prediction model here is based on a long short-term memory (LSTM) network and includes two functional modules: time series feature extraction and multi-step prediction. Training data comes from a historical fault database and contains multi-dimensional time series information such as device number, fault type, fault severity, and maintenance records. The model optimizes by minimizing mean squared error (MSE) and adjusts network parameters using a backpropagation algorithm. An attention mechanism is used to capture feature changes at key time points, improving prediction accuracy. In application, the model inputs current fault warning information and outputs a prediction of the fault development trend, including an estimated service life and maintenance cost budget, to inform maintenance decisions. The model can handle long-term dependencies and achieve predictions across multiple time scales.

[0167] S210 , inputting fault warning information into a fault development prediction model to obtain fault time sequence characteristics.

[0168] Among them, the fault time series characteristics represent the set of time dimension features in the fault development process; the fault warning information contains various indicators of the current fault status; the fault development prediction model is a trained time series prediction model; the time series characteristics include information such as the fault development speed, trend direction and key time nodes.

[0169] Fault detection systems need to predict and analyze fault development trends. Specifically, the system first converts fault warning information into a standardized model input format. It then uses the prediction model to perform multi-step time series predictions, obtaining estimates of the fault state at different future time points. It then performs confidence analysis on the prediction results to assess the reliability of the predictions. Finally, it extracts key feature points from the prediction sequence to form a complete time series feature description.

[0170] S211. Generate a fault analysis report based on the fault timing characteristics.

[0171] Among them, the fault analysis report is a systematic description document of the fault status; the fault timing characteristics reflect the development law of the fault; the analysis report contains multiple parts such as fault diagnosis results, development trend prediction, maintenance suggestions, etc.; the report format must comply with standardization requirements.

[0172] The fault detection system needs to generate professional analysis reports. Specifically, the system first determines the report's overall framework and content structure based on a pre-set report template. It then converts the fault's timing characteristics into easy-to-understand charts and text descriptions. Finally, based on historical maintenance experience, it provides targeted treatment recommendations and preventive measures. Finally, through natural language generation technology, it produces a logically clear and well-structured analysis report.

[0173] In some embodiments, report generation and content organization can be achieved through a variety of methods: Optionally, the fault detection system utilizes a rule-based expert system to automatically match treatment solutions based on fault characteristics and prediction results, generating a comprehensive report containing fault analysis, risk assessment, and repair recommendations. Optionally, the fault detection system utilizes deep learning-based natural language processing technology to convert data analysis results into professional technical documentation and generate differentiated report content based on different user roles. It is understood that other methods can also be used to achieve intelligent generation of analysis reports, and these are not limited here.

[0174] In some embodiments, report generation is based on a deep learning natural language processing model. First, a professional terminology knowledge graph G is constructed:

[0175] G = (V, E, R);

[0176] V={equipment term, fault type, maintenance measures};

[0177] E={relationship type};

[0178] R: V × V → E;

[0179] Perform semantic mapping on the fault diagnosis result F:

[0180] S=Encoder(F);

[0181] A=Attention(S,G);

[0182] T = Decoder (A);

[0183] Where S is the semantic vector, A is the attention weight, and T is the generated text description. The report template is defined as: M = {paragraph structure, keyword position, format specification};

[0184] Fill the template by conditionally generating a network:

[0185] P(w_t|w_{ <t},M,F)=softmax(W_oh_t+b_o);

[0186] h_t=GRU(embed(w_{t-1}),h_{t-1},c_t);

[0187] Where w_t is the t-th word and c_t is the context vector.

[0188] For example, after the system analyzes the fault data of a circuit breaker, it automatically generates an analysis report containing complete content such as "basic equipment information, fault phenomenon description, cause analysis, development trend prediction, and processing suggestions."

[0189] In some embodiments, the fault detection system will display the service life and maintenance budget in the report; specifically, the fault detection system will determine the expected service life of the high-voltage vacuum circuit breaker based on the fault timing characteristics; then determine the maintenance cost budget based on the expected service life and maintenance records in the historical fault database; and then generate a fault analysis report based on the expected service life and maintenance cost budget.

[0190] Among them, the expected service life indicates the remaining time that the equipment is expected to operate normally; the maintenance cost budget refers to the expected equipment maintenance cost; and the maintenance record contains historical maintenance costs and maintenance plan information.

[0191] Fault detection systems require lifespan assessment and cost forecasting. Specifically, the system first establishes a lifespan prediction model based on fault time series characteristics to estimate the equipment's remaining useful life. It then analyzes cost data from historical maintenance records to establish a maintenance cost forecast model. Finally, combining the lifespan prediction results with the cost model, it generates a detailed budget plan, including cost estimates for both scheduled and emergency repairs.

[0192] In some embodiments, the system uses a Weibull distribution model to estimate the expected life of the circuit breaker, using the failure rate function:

[0193] λ(t)=(β / η)(t / η)^(β-1); t is the operating time in years; β is the shape parameter, reflecting the failure rate trend, with a range of [2.0, 3.5] and a recommended value of 2.8; η is the scale parameter, representing the characteristic life in years, with a range of [10, 15] and a recommended value of 12; λ(t) is the failure rate function, representing the probability of failure per unit time.

[0194] And the reliability function:

[0195] R(t)=exp[-(t / η)^β]; describes the aging characteristics of the equipment, where β and η are the shape parameter and scale parameter, respectively. R(t) is the reliability function, which represents the probability of normal operation before time t.

[0196] The maintenance cost budget adopts a polynomial model that takes time decay into account, namely:

[0197] C(t) = ∑[c_i · exp(-ri_i · t)] + ε(t), where the base cost item c_i is affected by the depreciation rate ri_i, and the random fluctuation term ε(t) represents the uncertainty caused by market factors. c_i is the base maintenance cost of the i-th item, in 10,000 yuan; ri is the depreciation rate of the i-th cost, ranging from [0.05 to 0.15], with a recommended value of 0.1; t is the time variable, in years; ε(t) is the random fluctuation term, which follows a normal distribution with a mean of 0 and a standard deviation of 5% of the total cost; M(t) is the maintenance cost at time t, in 10,000 yuan / year; O(t) is the operating cost at time t, in 10,000 yuan / year; LCC is the total life cycle cost, in 10,000 yuan, with an integral interval of [0 to life expectancy].

[0198] The total life cycle cost is obtained by integrating the maintenance cost M(t) and the operating cost O(t) over time, that is, LCC=∫[M(t)+O(t)]dt.

[0199] For example, for a circuit breaker that has been in operation for 5 years, the Weibull distribution parameters β=2.8 and η=12 years are obtained through failure data analysis. The remaining service life is predicted to be 5.8 years, and the maintenance budget for the next 3 years is estimated to be 1.85 million yuan.

[0200] S212: Push the fault analysis report to the target person's mobile terminal.

[0201] Among them, the target personnel include equipment maintenance personnel, operation and maintenance management personnel and other relevant responsible persons; mobile terminals refer to portable devices such as smartphones and tablets; push methods include message notifications, emails, text messages and other channels.

[0202] The fault detection system must ensure that reports reach relevant personnel in a timely manner. Specifically, the system first determines the target personnel list based on the fault level and handling authority; then selects the appropriate delivery channel based on personnel configuration information; then converts the analysis report into a format suitable for mobile terminal display; and finally, pushes the report to the target terminal via a secure communication protocol and tracks and confirms receipt status.

[0203] In some embodiments, report push and status tracking can be implemented in a variety of ways: Optionally, the fault detection system can employ a multi-level push strategy, setting different push priorities and reminder methods based on fault severity, ensuring push reliability through message queues, and recording report reading and processing status. Optionally, the fault detection system can be based on a microservices architecture to achieve high availability of the report push service, support flexible configuration of multiple push channels, and provide real-time push status feedback. It is understood that other methods can also be used to implement intelligent report push, which are not limited here.

[0204] In some embodiments, information push uses a dynamic priority scheduling algorithm. The message priority function is defined as: P(m) = w1U(m) + w2D(m) + w3T(m); where U(m) is the urgency of the message, D(m) is the scope of impact, and T(m) is the timeliness.

[0205] The push time interval Δt is optimized through the Markov decision process:

[0206] V(s)=max_a{R(s,a)+γ∑P(s'|s,a)V(s')}; where s is the system state, a is the push action, R is the immediate reward, and γ is the discount factor.

[0207] The reception confirmation mechanism uses a reliable transmission protocol:

[0208] ACK(m)=Hash(m||t||key);

[0209] Retry(m)=min(2^n·T0,T_max); where Hash is the hash function, m is the message content, t is the timestamp, key is the session key, n is the number of retries, T0 is the basic timeout, and T_max is the maximum timeout. The recommended value is 300 seconds.

[0210] For example, if the system detects an abnormal temperature on a circuit breaker contact and calculates a message priority of 0.85, it will immediately push the message to the on-duty personnel via the app, with a copy sent to the supervisor via SMS. If no confirmation is received within 15 minutes, the push level will be automatically upgraded.

[0211] In some embodiments, the fault detection system will quickly locate the maintenance focus when a circuit breaker failure causes a large-scale impact; specifically, the fault detection system will extract the spatiotemporal distribution characteristics of the fault diagnosis results from the historical fault database, and then determine the correlation influence coefficient of the circuit breakers in each area based on the circuit breaker location data and spatiotemporal distribution characteristics of the geographic information system; when a preset power outage occurs, the fault detection system will determine the fault spread range based on the correlation influence coefficient and generate a zoning maintenance priority list.

[0212] Among them, the spatiotemporal distribution characteristics represent the distribution law of faults in the time and space dimensions; the correlation influence coefficient is used to quantify the degree of mutual influence between circuit breakers; and the partition maintenance priority list guides the on-site maintenance sequence.

[0213] Fault detection systems need to respond quickly to large-scale failures. Specifically, they first analyze the spatiotemporal patterns of historical fault data to establish a fault propagation model. Then, they combine the device location relationships in the geographic information system to calculate a correlation coefficient matrix between devices. When a major fault occurs, they immediately initiate a fault impact assessment program, determine the fault's propagation range based on the correlation coefficient, and generate a zoning maintenance plan.

[0214] In some embodiments, fault propagation analysis can be implemented in a variety of ways: Optionally, the fault detection system employs complex network theory to establish a circuit breaker fault propagation network model, identifying key nodes and propagation paths through network topology analysis. Optionally, the fault detection system employs a graph neural network to learn the complex relationships between devices and accurately predict the impact of a fault. It is understood that other methods can also be used to implement fault analysis, and these are not limited here.

[0215] It should be noted that the fault propagation network model here uses a graph convolutional network (GCN) architecture and includes two submodules: spatial feature aggregation and time series evolution prediction. The training process uses the spatiotemporal distribution data of historical faults. Inputs include the geographic location of circuit breakers, the physical connections between devices, and historical fault propagation records. Graph convolution operations are used to learn fault correlation patterns between devices. The model uses a combined cross-entropy and mean squared error loss function to optimize the accuracy of calculating the correlation influence coefficients between devices. In large-scale fault scenarios, the model receives information about the initial fault point, predicts the possible propagation path and impact range of the fault, and outputs a prioritized list of zoning repairs based on fault severity and urgency. The advantage of this model lies in its ability to effectively capture fault propagation patterns in complex networks and support emergency decision-making.

[0216] The system analyzes the fault propagation effect by constructing a circuit breaker association graph G = (V, E). The edge weight w (i, j) comprehensively considers the topological distance and fault correlation, that is:

[0217] w(i, j) = α·d(i, j)^(-γ) + β·f(i, j); where d(i, j) is the physical distance between devices i and j, in kilometers (km); γ is the distance attenuation exponent, ranging from [1.5 to 2.5], with a recommended value of 2.0; f(i, j) is the fault correlation, ranging from [0 to 1], and is obtained from historical data statistics; α is the distance impact weight, ranging from [0.4 to 0.6], with a recommended value of 0.5; and β is the correlation weight, ranging from [0.4 to 0.6], with a recommended value of 0.5.

[0218] The propagation impact intensity I(v) is obtained by weighted accumulation of the impact of each source point, that is:

[0219] I(v)=∑w(u,v)·s(u)·p(u,v), where s(u) is the severity of the source fault, ranging from [0, 1]; p(u,v) is the probability of fault propagation, ranging from [0, 1], calculated based on historical data; w(i,j) is the edge weight, indicating the impact strength between devices; I(v) is the intensity of the propagation impact on node v, ranging from [0, 1].

[0220] The maintenance priority is calculated based on the impact intensity, load importance and repair time, namely:

[0221] Priority(v)=w1I(v)+w2C(v)+w3T(v).

[0222] For example, after a circuit breaker failure in a substation, the system uses the above model analysis to show that it may affect 12 devices in three surrounding areas. Through priority calculation, area 2 with the heaviest load is listed as the highest maintenance priority.

[0223] In some embodiments, the fault detection system will further generate a personnel maintenance plan; specifically, the fault detection system will determine the path planning table based on the partition maintenance priority list and real-time road condition information, and then determine the maintenance scheduling plan based on the maintenance personnel information, equipment supply information and the path planning table; the fault detection system will determine the partition maintenance task sequence according to the maintenance scheduling plan, and push multiple maintenance tasks in the partition maintenance task sequence to the corresponding maintenance terminal.

[0224] Among them, the maintenance scheduling plan includes personnel allocation, equipment deployment and time arrangement; the path planning table guides maintenance personnel to the optimal travel route; and the maintenance task sequence is a list of maintenance work sorted by priority.

[0225] The fault detection system needs to implement intelligent scheduling of maintenance resources. Specifically, the system first plans the optimal maintenance route based on zone maintenance priorities and real-time traffic data. It then generates a detailed scheduling plan based on the maintenance personnel's professional skills, equipment inventory status, and route planning. Finally, the maintenance tasks are broken down into specific work instructions and pushed to on-site personnel via mobile devices.

[0226] In some embodiments, the system uses an improved A* algorithm for maintenance path planning, and the heuristic function h(n) comprehensively considers spatial distance, travel time, and congestion cost, namely:

[0227] h(n)=w1d(n,goal)+w2t(n)+w3c(n). The maintenance scheduling problem is modeled as a multi-objective optimization problem with the objective function:

[0228] F(x)=[f1(x), f2(x), ..., f_m(x)] includes multiple dimensions such as total repair time, personnel utilization, and equipment deployment efficiency.

[0229] Task sequence generation uses priority-based queue management. The priority calculation formula is:

[0230] priority = w1u (task) + w2r (task) + w3s (task) balances task urgency, resource readiness, and system impact.

[0231] For example, after a chain reaction failure occurred in a certain area, the system completed the optimal allocation of 15 maintenance tasks within 10 minutes through the above-mentioned planning mechanism, planned the optimal path for the three maintenance teams, and expected that all repair work could be completed within 4 hours.

[0232] In the embodiment of the present application, due to the use of collaborative analysis technology for double-break contact action timing data and vacuum chamber pressure data, combined with a comprehensive evaluation mechanism for ambient temperature, humidity, and load index, and the introduction of an edge computing architecture and a dynamic warning threshold adjustment strategy, it is possible to achieve accurate diagnosis and rapid processing of faults, effectively solving the problems of poor environmental adaptability, low data processing efficiency, and delayed fault warning of the fixed threshold warning mechanism in traditional technologies, thereby achieving improved equipment reliability, effective reduction in maintenance costs, and efficient collaborative processing in large-scale fault scenarios. Through historical data mining and spatiotemporal feature analysis, the system can also predict fault development trends and optimize the allocation of maintenance resources, providing a comprehensive intelligent solution for power grid operation and maintenance management.

[0233] The following describes the fault detection system in the embodiment of the present invention from the perspective of hardware processing. Figure 3 , is a schematic diagram of the physical device structure of the fault detection system in an embodiment of the present application.

[0234] It should be noted that Figure 3 The structure of the fault detection system shown is only an example and should not limit the functions and scope of use of the embodiments of the present invention.

[0235] like Figure 3As shown, the fault detection system includes a central processing unit (CPU) 301, which can perform various appropriate actions and processes, such as the methods described in the above embodiments, based on programs stored in a read-only memory (ROM) 302 or programs loaded from a storage unit 308 into a random access memory (RAM) 303. RAM 303 also stores various programs and data required for system operation. CPU 301, ROM 302, and RAM 303 are interconnected via a bus 304. An input / output (I / O) interface 305 is also connected to bus 304.

[0236] The following components are connected to the I / O interface 305: an input section 306 including an audio input device, push button switches, and the like; an output section 307 including a liquid crystal display (LCD), an audio output device, indicator lights, and the like; a storage section 308 including a hard disk and the like; and a communication section 309 including a network interface card such as a LAN (Local Area Network) card or a modem. The communication section 309 performs communication processing via a network such as the Internet. A drive 310 is also connected to the I / O interface 305 as needed. Removable media 311, such as a magnetic disk, an optical disk, a magneto-optical disk, or a semiconductor memory, is installed in the drive 310 as needed, so that computer programs read from the removable media can be installed in the storage section 308 as needed.

[0237] In particular, according to embodiments of the present invention, the processes described above with reference to the flowcharts can be implemented as computer software programs. For example, embodiments of the present invention include a computer program product comprising a computer program carried on a computer-readable medium, the computer program including a computer program for executing the methods illustrated in the flowcharts. In such embodiments, the computer program can be downloaded and installed from a network via the communication section 309 and / or installed from removable media 311. When executed by the central processing unit (CPU) 301, the computer program performs the various functions defined in the present invention.

[0238] It should be noted that specific examples of computer-readable storage media may include, but are not limited to, an electrical connection having one or more conductors, a portable computer disk, a hard disk, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM), flash memory, optical fiber, portable compact disc read-only memory (CD-ROM), optical storage device, magnetic storage device, or any suitable combination thereof. In the present invention, a computer-readable storage medium may be any tangible medium containing or storing a program that can be used by or in conjunction with an instruction execution system, apparatus, or device.

[0239] The flowcharts and block diagrams in the accompanying drawings illustrate the possible architecture, functions and operations of the systems, methods and computer program products according to various embodiments of the present invention. Each box in the flowchart or block diagram can represent a module, program segment, or part of the code, and the above-mentioned module, program segment, or part of the code contains one or more executable instructions for implementing the specified logical functions. It should also be noted that in some alternative implementations, the functions marked in the box can also occur in an order different from that marked in the accompanying drawings.

[0240] Specifically, the fault detection system of this embodiment includes a processor and a memory. The memory stores a computer program. When the computer program is executed by the processor, the double-break high-voltage vacuum circuit breaker fault diagnosis method provided in the above embodiment is implemented.

[0241] As another aspect, the present invention further provides a computer-readable storage medium, which may be included in the fault detection system described in the above embodiments, or may exist independently and not be incorporated into the fault detection system. The storage medium carries one or more computer programs, and when executed by a processor of the fault detection system, the fault detection system implements the double-break high-voltage vacuum circuit breaker fault diagnosis method provided in the above embodiments.

[0242] As described above, the above embodiments are only used to illustrate the technical solutions of the present application, rather than to limit them. Although the present application has been described in detail with reference to the above embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the above embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not cause the essence of the corresponding technical solutions to deviate from the scope of the technical solutions of the embodiments of the present application.

[0243] As used in the above embodiments, the term “when” may be interpreted to mean “if” or “after” or “in response to determining that” or “in response to detecting that”, depending on the context. Similarly, the phrases “upon determining that” or “if (stated condition or event) is detected” may be interpreted to mean “if determining that” or “in response to determining that” or “upon detecting (stated condition or event)” or “in response to detecting (stated condition or event)”, depending on the context.

[0244] Those skilled in the art will appreciate that all or part of the process steps in the above-described method embodiments can be implemented by a computer program instructing the relevant hardware. The program can be stored in a computer-readable storage medium, and when executed, the program can include the process steps in the above-described method embodiments. The aforementioned storage medium includes various media capable of storing program code, such as ROM or random access memory (RAM), magnetic disks, or optical disks.

Claims

1. A double-break high-voltage vacuum circuit breaker fault diagnosis method, characterized in that: Applied to a fault detection system, the method comprises: Obtain contact action timing data of the high-voltage vacuum circuit breaker at two breakers, pressure data in the vacuum chamber, as well as ambient temperature, ambient humidity and system load index; Calculating the contact action speed difference and bounce characteristic parameters of the two fractures according to the contact action timing data, and generating a mechanical characteristic coordination vector in combination with the opening and closing energy consumption data of the two fractures; Acquiring temperature distribution data of the conductive loops of the two fractures, and calculating the heat dissipation coefficient of the two fractures based on the temperature distribution data; collecting the voltage sharing ratio and transition recovery voltage characteristics of the two faults during the breaking process, and determining a voltage tolerance difference index based on the pressure data in the vacuum chamber and the heat imbalance coefficient; Inputting the mechanical characteristic coordination vector and the voltage tolerance difference index into a fault diagnosis model to obtain a fault diagnosis result; Calculating an environmental impact factor of the high-voltage vacuum circuit breaker under a current operating condition based on the ambient temperature, the ambient humidity, and the system load index, generating an operating condition characteristic vector, and determining a fault warning threshold corresponding to the operating condition characteristic vector; When the warning parameter index of the fault diagnosis result exceeds the fault warning threshold, fault warning information is generated.

2. The method according to claim 1, characterized in that When the warning parameter index of the fault diagnosis result exceeds the fault warning threshold, after the step of generating fault warning information, the method further includes: Obtain multiple historical fault data including equipment number, fault type, fault severity and maintenance records to build a historical fault database; Performing model training based on the historical fault database to obtain a fault development prediction model; Inputting the fault warning information into the fault development prediction model to obtain fault time sequence characteristics; generating a fault analysis report based on the fault timing characteristics; Push the fault analysis report to the target person's mobile terminal.

3. The method according to claim 2, characterized in that The step of generating a fault analysis report based on the fault timing characteristics specifically includes: determining the expected service life of the high-voltage vacuum circuit breaker according to the fault timing characteristics; determining a maintenance cost budget based on the expected service life and maintenance records in the historical failure database; A failure analysis report is generated based on the expected service life and the maintenance cost budget.

4. The method according to claim 1, wherein After the step of obtaining the contact action timing data of the high-voltage vacuum circuit breaker at the two breaks, the pressure data in the vacuum chamber, and the ambient temperature, ambient humidity and system load index, the method further includes: Determine an edge computing node closest to the location of the high-voltage vacuum circuit breaker; Integrating the contact action timing data, the pressure data in the vacuum chamber, the ambient temperature, the ambient humidity, and the system load index into an original data packet; Sending the original data packet to the edge computing node; Receive the fault calculation result data packet returned by the edge computing node.

5. The method according to claim 4, characterized in that After the step of receiving the fault diagnosis result and the fault warning threshold returned by the edge computing node, the method further includes: Extracting the computing node mark and data timestamp from the fault computing result data packet; When the data timestamp is inconsistent with the original timestamp of the original data packet, a data acquisition request including the original timestamp is sent to the edge computing node.

6. The method according to claim 1, characterized in that When the warning parameter index of the fault diagnosis result exceeds the fault warning threshold, after the step of generating fault warning information, the method further includes: Extracting the spatiotemporal distribution characteristics of fault diagnosis results from the historical fault database; Determining the correlation influence coefficient of the circuit breakers in each area based on the circuit breaker location data of the geographic information system and the spatiotemporal distribution characteristics; When a preset power outage event occurs, the fault propagation range is determined according to the correlation impact coefficient, and a partition maintenance priority list is generated.

7. The method according to claim 6, characterized in that When a preset power outage event occurs, after the steps of determining the fault propagation range according to the correlation influence coefficient and generating a partition maintenance priority list, the method further includes: Determine a route planning table based on the partition maintenance priority list and real-time traffic information; Determine a maintenance scheduling plan based on maintenance personnel information, equipment supply information, and the path planning table; Determine a partition maintenance task sequence according to the maintenance scheduling plan, and push multiple maintenance tasks in the partition maintenance task sequence to corresponding maintenance terminals.

8. A fault detection system, characterized in that: The fault detection system includes: one or more processors and a memory; the memory is coupled to the one or more processors, the memory is used to store computer program code, the computer program code includes computer instructions, and the one or more processors call the computer instructions to enable the fault detection system to execute the method described in any one of claims 1-7.

9. A computer-readable storage medium comprising instructions, characterized in that: When the instruction is executed on a fault detection system, the fault detection system is caused to perform the method according to any one of claims 1 to 7.

Images