Intelligent service system for remote operation and maintenance of high-voltage switchgear

Abstract

The invention relates to the technical field of intelligent operation and maintenance of high-voltage electrical equipment, in particular to an intelligent service system for remote operation and maintenance of high-voltage switch equipment. Comprising the following parts: a data acquisition module for acquiring external gas density data, internal gas density data, environment temperature data and equipment internal temperature data of the circuit breaker in a high-altitude environment; the monitoring module is used for taking instantaneous change data of the external gas density data and the environment temperature data as analysis data of the internal field intensity of the circuit breaker; based on the analysis data, the accessory supply of the circuit breaker is optimized. According to the method, false alarm is suppressed through decoupling environment disturbance, and the fitting replacement priority is reconstructed and optimized based on the three-dimensional field intensity; a multi-source data calibration supply chain is fused to realize matching of a supply period and a field intensity degradation trend; a maintenance path is generated in combination with the field intensity deviation degree and the component relevance, a closed-loop system from abnormal sensing to accurate scheduling is constructed, and the operation and maintenance efficiency and decision reliability of the high-voltage equipment are improved.

Description

Technical Field

[0001] The present invention relates to the technical field of intelligent operation and maintenance of high-voltage electrical equipment, and particularly to a remote operation and maintenance intelligent service system for high-voltage switchgear. Background Art

[0002] As a key high-voltage switchgear in the power system, the high-voltage circuit breaker undertakes the core functions of rapid isolation of short-circuit faults and control of the system operation state, and its reliability directly affects the safety of the power grid. With the extension of ultra-high voltage and extra-high voltage transmission networks to complex environments such as high altitude and alpine regions, the equipment has been facing harsh working conditions such as low air pressure, strong radiation, and drastic day-night temperature differences for a long time. Traditional operation and maintenance technologies have significant limitations: First, conventional gas density monitoring relies on a fixed threshold alarm mechanism, which cannot effectively distinguish the natural fluctuation of SF6 gas density caused by low air pressure environment from the real leakage risk, resulting in a significant increase in the false alarm rate; Second, existing condition assessments are mostly based on regular maintenance and local sensor data, and it is difficult to real-time perceive the three-dimensional electric field intensity distribution inside the equipment, resulting in difficulty in timely discovery of hidden defects such as early partial discharge and floating potential; Third, most mainstream prediction models are trained with laboratory steady-state data, ignoring the dynamic coupling effect of gas thermodynamics characteristics and electromagnetic field distribution in high altitude environments, resulting in a significant decrease in prediction accuracy during on-site deployment. Although industrial Internet of Things and machine learning technologies have been gradually applied to equipment monitoring, pure data-driven methods are prone to generate field strength inference results that violate the actual working conditions due to the lack of embedding of the multi-physical field coupling mechanism. How to construct a high-precision operation and maintenance system that integrates physical laws and real-time data has become a technical bottleneck for the intelligent upgrade of high-voltage switchgear. Summary of the Invention

[0003] In order to overcome the shortcoming of insufficient operation and maintenance accuracy of high-voltage circuit breakers under multi-physical field coupling, the present invention provides a remote operation and maintenance intelligent service system for high-voltage switchgear.

[0004] The technical implementation solution of the present invention is: A remote operation and maintenance intelligent service system for high-voltage switchgear, including the following parts: Data acquisition module: Acquire the external gas density data, internal gas density data, ambient temperature data and internal temperature data of the circuit breaker in high altitude environments; Monitoring module: Use the instantaneous change data of the external gas density data and the ambient temperature data as the analysis data of the internal field strength of the circuit breaker; Based on the analysis data, optimize the spare parts supply of the circuit breaker; Analysis and processing module: Calculate the confidence weight based on the external gas density data, ambient temperature data and internal monitoring data; Calculate the comprehensive field strength based on the confidence weight; Decision-making and optimization module: Determine the spare parts supply of the circuit breaker by using the updated scheduling scoring formula based on the calculated value of the comprehensive field strength.

[0005] Preferably, the data acquisition module: acquires the external gas density data, internal gas density data, ambient temperature data, and equipment internal temperature data of the circuit breaker in a high-altitude environment, including: Uses the external gas density data and ambient temperature data as the first monitoring data; Uses the internal gas density data and equipment internal temperature data as the second monitoring data; When the first monitoring data shows periodic changes, triggers the determination of the optimization period of the second monitoring data; The periodic change is the periodic change of the external gas density and ambient temperature in a high-altitude environment; The optimization period is defined as: the time period during which the second monitoring data does not change synchronously during the periodic change of the first monitoring data.

[0006] Preferably, the time period during which the second monitoring data does not change synchronously during the periodic change of the first monitoring data includes: The non-occurrence of the same change is quantified by the phase difference formula, and the phase difference formula is as follows.

[0007] Where, is the phase difference, is the change amount of the external environment parameter, is the change amount of the internal parameter, is the environmental conduction time delay, is the sampling window length, is the sampling time interval, is the serial number of the discrete sequence; Determination rule: When > is marked as a period to be optimized, is the preset phase difference threshold; Extracts the time period in the first monitoring data that continuously exceeds the preset threshold for a duration ≥ as the composition moment, is the shortest continuous over-threshold time; Based on the composition moment, constructs the optimization period of the second monitoring data; Based on the optimization period, generates a preliminary scheduling plan for the circuit breaker accessories.

[0008] Preferably, the generating a preliminary scheduling plan for the circuit breaker accessories based on the optimization period includes: Obtains the preliminary scheduling score value of the circuit breaker accessories through the scheduling scoring formula, and the scheduling scoring formula is as follows.

[0009] wherein, is the scheduling score value, is the phase difference, is the component 's basic maintenance weight, is the current timestamp, is the component the last maintenance timestamp, is the dynamic remaining life ratio, is the component 's theoretical maintenance cycle, is the associated component 's status anomaly score, , are the weight coefficients, is related to the component associated component set.

[0010] Preferably, the monitoring module: uses the instantaneous change data of the external gas density data and the environmental temperature data as the analysis data of the internal field strength of the circuit breaker; based on the analysis data, optimizes the accessory supply of the circuit breaker, including: Taking the moment before the instantaneous change of the external gas density as the starting point and the moment after the instantaneous change as the end point, constructs the instantaneous change rate of the external gas density; synchronously records the instantaneous change rate data of the external gas density and the environmental temperature throughout the change cycle; Based on the instantaneous change rate of the external gas density and the instantaneous change rate of the environmental temperature, obtains the internal field strength data of the circuit breaker.

[0011] Preferably, the obtaining the internal field strength data of the circuit breaker based on the instantaneous change rate of the external gas density and the instantaneous change rate of the environmental temperature includes: Normalizes the instantaneous change rate of the external gas density, the instantaneous change rate of the environmental temperature, and the internal field strength change rate respectively; Uses the normalized instantaneous change rate of the external gas density, the instantaneous change rate of the environmental temperature, and the internal field strength change rate as the input; Uses the predicted value of the internal field strength as the output; Uses Maxwell's equations and the gas state equation as physical constraints; Generates the full-field field strength distribution data under different working conditions through finite element simulation, and combines the collected data before and after abnormal events in actual operation and maintenance to construct a circuit breaker blind area field strength inference model.

[0012] Preferably, the calculating the confidence weight based on the external gas density data, the environmental temperature data, and the internal monitoring data includes:

[0013]

[0014] Among them, is the instantaneous change in external gas density, is the instantaneous change in ambient temperature, is the empirically set critical value of ambient mutation, is the confidence weight of external environment data, is the confidence weight of internal monitoring data; If the confidence weight of external environment data exceeds the first preset threshold, increase the confidence weight of external environment data; If the confidence weight of external environment data is lower than the second preset threshold, increase the confidence weight of internal monitoring data.

[0015] Preferably, calculating the comprehensive field strength based on the confidence weight includes: The comprehensive field strength calculation formula is as follows,

[0016] Among them, is the weighted comprehensive field strength value, is the field strength value directly monitored by the internal sensor, is the predicted value of the breaker blind area field strength inference model.

[0017] Preferably, the decision optimization module: Based on the comprehensive field strength calculation value, determine the accessory supply of the breaker using the updated scheduling score formula, including: The updated scheduling score formula is as follows,

[0018] Among them, is the updated dynamic scheduling score, is the scheduling score value, is the field strength safety threshold, is the field strength deviation sensitivity coefficient; Based on the updated scheduling score value, send relevant information to the management personnel.

[0019] Preferably, sending relevant information to the management personnel based on the updated scheduling score value includes: Push the updated scheduling score value to the management personnel terminal in a visual form and associate it with the work order processing process.

[0020] Beneficial effects: The present invention separates the high-altitude gas fluctuations from the intrinsic state of the equipment through an environmental disturbance decoupling mechanism, and suppresses redundant work orders caused by false alarms; based on the three-dimensional field strength dynamic reconstruction technology, accurately quantifies the defect level, drives the differentiation of the priority of spare part replacement, and optimizes the dynamic allocation of inventory resources; further, through the confidence fusion model, realizes the two-way calibration of the supply chain between simulation data and real-time monitoring, ensures that the spare part supply cycle is adaptively matched with the field strength deterioration trend; finally, relying on the dynamic scoring closed-loop mechanism, fuses the field strength deviation degree and component relevance, generates a multi-objective collaborative maintenance path planning, synchronously improves the operation and maintenance response efficiency and decision-making reliability, forms a full-link closed-loop optimization system from electromagnetic field anomaly perception to supply chain precise scheduling, and provides intelligent decision-making support for the preventive maintenance of high-voltage equipment under complex working conditions. Brief Description of the Drawings

[0021] Figure 1 It is a schematic structural diagram of the remote operation and maintenance intelligent service system for high-voltage switchgear of the present invention; Figure 2 It is a flowchart of the optimization cycle determination of the present invention. Detailed Embodiments

[0022] Next, the technical solutions in the embodiments of the present invention will be clearly and completely described in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative efforts shall fall within the protection scope of the present invention.

[0023] A remote operation and maintenance intelligent service system for high-voltage switchgear, as Figure 1 shown, includes the following parts: Data acquisition module: Acquire the external gas density data, internal gas density data, environmental temperature data and equipment internal temperature data of the circuit breaker in a high-altitude environment; Monitoring module: Use the instantaneous change data of the external gas density data and the environmental temperature data as the analysis data of the internal field strength of the circuit breaker; based on the analysis data, optimize the spare part supply of the circuit breaker; Analysis and processing module: Calculate the confidence weight based on the external gas density data, environmental temperature data and internal monitoring data; calculate the comprehensive field strength based on the confidence weight; Decision optimization module: Determine the spare part supply of the circuit breaker by using the updated scheduling scoring formula based on the comprehensive field strength calculation value.

[0024] Data acquisition module: Acquire the external gas density data, internal gas density data, environmental temperature data and equipment internal temperature data of the circuit breaker in a high-altitude environment, including: Take the external gas density data and the ambient temperature data as the first monitoring data; Take the internal gas density data and the device internal temperature data as the second monitoring data; When the first monitoring data shows periodic changes, trigger the optimization period determination of the second monitoring data; The periodic change is the periodic change of the external gas density and the ambient temperature in a high-altitude environment; The optimization period is defined as: in the periodic change of the first monitoring data, the time period when the second monitoring data does not change synchronously.

[0025] For further explanation, as Figure 2 shown, by dividing the high-altitude environment data (the first monitoring data) and the breaker internal data (the second monitoring data), an environment-device coupled monitoring system is constructed. Its core lies in dynamically calibrating the internal state monitoring frequency of the device using the environmental periodic change: the external gas density and temperature in high-altitude areas show regular fluctuations (periodic changes) due to factors such as day and night, seasons, etc., while the breaker internal data should remain stable under the ideal state of good sealing. If within the external environmental periodic change, the internal data does not fluctuate synchronously (such as the external temperature rises but the internal gas density remains unchanged or decreases abnormally), it is determined as potential leakage or component aging, and targeted detection is triggered. At this time, the system takes the external change period as the benchmark and shortens the monitoring interval (optimization period) of the internal data, realizing the upgrade from "fixed inspection" to "environment-responsive monitoring", which not only avoids misjudgment caused by high-altitude environment interference but also can quickly respond in case of real anomalies, achieving efficient allocation of operation and maintenance resources.

[0026] In the periodic change of the first monitoring data, the time period when the second monitoring data does not change synchronously includes: The non-occurrence of the same change is quantified by the phase difference formula. The phase difference formula is as follows,

[0027] where, is the phase difference, is the change amount of the external environmental parameter, is the change amount of the internal parameter, is the environmental conduction time delay, is the sampling window length, is the sampling time interval, is the serial number of the discrete sequence; Judgment rule: When > mark it as needing to optimize the period, is the preset phase difference threshold; Extract the continuous duration in the first monitoring data that exceeds the preset threshold ≥ The time period is used as the composition time, which is the shortest continuous time above the threshold; Based on the composition time, an optimized period of the second monitoring data is constructed; Based on the optimized period, a preliminary scheduling plan for the circuit breaker accessories is generated.

[0028] For further explanation, the change amount of the external environmental parameters is the comprehensive change amount of the first monitoring data (external gas density and environmental temperature), and the calculation method is: , where and are the weight coefficients of the external gas density and the environmental temperature respectively; and are the change amounts of the external gas density and the environmental temperature change amount respectively, , ; The internal parameter change amount is the comprehensive change rate of the second monitoring data (internal gas density and equipment environmental temperature), and the calculation method is the same; The mismatch degree of the internal and external parameter changes is quantified by the phase difference: the difference in the change rates between the external environment ( ) and the inside of the circuit breaker ( ) is corrected by the time delay , and the average absolute deviation ( ) within the window period is calculated. When exceeds the threshold , it indicates that the internal response is out of sync with the external excitation (for example, when the external temperature rises, the internal gas density does not contract as expected), triggering the optimization of the monitoring period. The essence of the formula is to construct a dynamic differential tracker - the external periodic disturbance is regarded as the "driving signal", and the internal response delay or abnormality is regarded as the "distortion of the system transfer function", and the fault characteristics such as insulation deterioration and seal leakage are captured through the differential difference ( The larger the value, the lower the system health).

[0029] Example, the day-night temperature difference in the plateau is 40 °C (external temperature +30 °C during the day → -10 °C at night). For a normal circuit breaker, due to good sealing, the daily fluctuation of the internal gas density should be <5%. One day, the following was monitored: The external temperature change rate = 1.67 °C / h (warming up during the day); The internal density change rate = -0.8 kg / m³ / h (abnormal leakage, = 2 h lag), and the calculated = 1.25 > (Set at 0.5), it is determined as invalid. The optimization cycle starts high-frequency monitoring at 12:00 - 16:00 when the external temperature changes drastically to accurately capture the leakage point.

[0030] Based on the above optimization cycle, generate a preliminary scheduling plan for circuit breaker accessories, including: Obtain the preliminary scheduling score value of the circuit breaker accessories through the scheduling score formula. The scheduling score formula is as follows.

[0031] Where, is the scheduling score value, is the phase difference, is the basic maintenance weight of component ; is the current timestamp, is component 's last maintenance timestamp, is the dynamic remaining life ratio, is component 's theoretical maintenance cycle, is the status anomaly score of the associated component ; , are the weight coefficients, is the set of components associated with component .

[0032] Further explanation: Through environment - equipment dynamic decoupling analysis ( ) and life - relevance scoring ( ), achieve precise operation and maintenance decision - making.

[0033] Fault prediction ( formula): Quantify the phase difference between external environment fluctuations and internal responses. When it exceeds the threshold, it is marked as a potential fault window; Life decay model ( formula): Dynamic remaining life ratio , , is the cumulative stress, is component 's dynamic corrected maintenance cycle. Compress the theoretical maintenance cycle according to the stress accumulation index (such as the high - altitude temperature difference cycle accelerating metal fatigue rising), and calculate the component health in real - time; Intelligent scheduling (scheduling score formula): Scheduling score , is the maintenance urgency, integrating the severity of the phase difference ( ), basic weight ( ), remaining life ( denominator-driven urgency), and abnormal associated components ( multiplication amplification of risks), output a priority score to drive the optimal allocation of accessory resources.

[0034] Operation and maintenance actions: Dynamic monitoring: When exceeding the threshold, focus on optimizing the cycle for intensive sampling; Life warning: When < 0.3, trigger preventive replacement; Coordinated scheduling: Sort to generate an accessory work order, and give priority to processing high-score items (such as > 8 requires a response within 48 hours).

[0035] Example: A certain circuit breaker in a plateau substation = 1.8 ( = 1.0), the cumulative stress makes compress from 5 years to 3.2 years ( = 0.1), = 0.25, the associated disconnector = 0.5, calculated to get = ln(2.8) · [2.0 + 0.5 · (24 months / 0.25)] · 1.25 = 9.7, trigger an emergency replacement schedule, and synchronously check the associated components.

[0036] Monitoring module: Use the instantaneous change data of the external gas density data and the ambient temperature data as the analysis data of the internal field strength of the circuit breaker; Based on the analysis data, optimize the accessory supply of the circuit breaker, including: Taking the moment before the instantaneous change of the external gas density as the starting point and the moment after the instantaneous change as the end point, construct the instantaneous change rate of the external gas density; Synchronously record the instantaneous change rate data of the external gas density and the ambient temperature throughout the change cycle; Based on the instantaneous change rate of the external gas density and the instantaneous change rate of the ambient temperature, obtain the internal field strength data of the circuit breaker.

[0037] For further explanation, under the constraint of scarce internal sensors, by capturing the instantaneous change rate (instead of the steady-state value) of the gas density and temperature, the dynamic change trend of the internal field strength of the circuit breaker can be inversely deduced. The transient difference between the external environment mutation (such as sudden temperature rise) and the internal gas density response implies an insulation deterioration signal. After normalization processing to eliminate the dimension interference, input the multi-dimensional time series change rate into the scoring formula (such as ), drive the internal field strength degradation modeling using external measurable parameters, replace "absolute monitoring accuracy" with "change sensitivity", and solve the problem of state deduction under incomplete data. For example, when the temperature soars instantaneously, the gas density does not change synchronously, the normalized field strength curve mutates, triggering abnormal scoring, and giving priority to scheduling the overhaul of associated components.

[0038] Based on the instantaneous change rate of the external gas density and the instantaneous change rate of the ambient temperature, obtain the internal field strength data of the circuit breaker, including: Normalize the instantaneous change rate of the external gas density, the instantaneous change rate of the ambient temperature, and the internal field strength change rate respectively; Use the normalized instantaneous change rate of the external gas density, the instantaneous change rate of the ambient temperature, and the internal field strength change rate as inputs; Use the predicted value of the internal field strength as the output; Use Maxwell's equations and the gas state equation as physical constraints; Generate the full-field field strength distribution data under different working conditions through finite element simulation, and combine the collected data before and after abnormal events in actual operation and maintenance to construct a field strength inference model for the blind area of the circuit breaker.

[0039] For further explanation, make up for the sensor blind area through multi-physical field coupling inference: Input enhancement: After normalizing the external gas density, ambient temperature, and field strength change rate, it is necessary to supplement the time-series correlation analysis (such as dynamic causal network) to extract the cross-parameter lag effect; Mathematicalization of physical constraints: Transform Maxwell's equations (∇×E = 0) and the gas state equation (PV = nRT) into a field strength gradient loss function to force the predicted value to satisfy physical conservation; Data fusion: Generate the field strength distribution under extreme working conditions (such as arc reignition at -40°C) through finite element simulation, superimpose the sparse field strength segment data in actual events, construct a generalized field strength map through transfer learning, and output the blind area field strength prediction. Drive the internal insulation failure warning through external measurable parameters, and guide the setting of the replacement threshold of accessories (such as giving priority to scheduling the overhaul of the arc extinguishing chamber when the field strength > 25 kV / mm).

[0040] For further explanation, the normalization is a data standardization method (such as Z-score), which is used to eliminate the dimension difference and improve the model convergence speed; the Maxwell equations are a set of partial differential equations describing the relationship between electric fields and magnetic fields, which are used to constrain the model to conform to the physical laws of electromagnetic fields; the gas state equation is the ideal gas equation (such as PV=nRT), which is used to relate the changes in gas density, temperature and pressure; the finite element simulation is a numerical calculation method, which solves the field strength distribution in a complex geometry through mesh division and generates the virtual data required for training; the data before and after the abnormal event specifically refers to the monitoring data before and after the occurrence of circuit breaker failures (such as arc reignition, gas leakage), which is used for the training of the model generalization ability.

[0041] Based on the external gas density data, environmental temperature data and internal monitoring data, calculate the confidence weights, including:

[0042]

[0043] Wherein, is the instantaneous change amount of the external gas density, is the instantaneous change amount of the environmental temperature, is the empirically set critical value of environmental mutation, is the confidence weight of the external environmental data, is the confidence weight of the internal monitoring data; If the confidence weight of the external environmental data exceeds the first preset threshold, then increase the confidence weight of the external environmental data; If the confidence weight of the external environmental data is lower than the second preset threshold, then increase the confidence weight of the internal monitoring data.

[0044] For further explanation, let the first preset threshold > the second preset threshold (such as rely on external data when > 0.7, rely on internal data when < 0.3); Solve the conflict of credibility between internal and external data through dynamic weight allocation: Weight mechanism: The external confidence weight quantifies the intensity of environmental mutation (such as gas leakage > 0 or sudden temperature rise > 10 °C). If

[0045] > 0.8 (the first preset threshold), it is determined that the external interference is dominant, and the external data is preferentially used to calculate the internal field strength (such as the risk of arc reignition); if When \(x = 0.6\), the internal and external data are weighted and fused at 6:4 to avoid sudden change decisions.

[0046] Example: The circuit breaker of a plateau substation suddenly encounters intense sunlight. If \(T = 15^{\circ}C\) (threshold \(T_0 = 20^{\circ}C\)), If \(P = 0\) (sealing normal), then \(x = 15 / 20 = 0.75\), triggering the external priority mode, inferring the risk of local overheating of the insulating medium in combination with the temperature rise rate, and scheduling heat dissipation inspection; if If \(P = 18kPa\) (threshold \(P_0 = 20kPa\)), If \(\Delta T = 5^{\circ}C\), \(x = 23 / 20 = 1.15\), exceeding the limit and forcing external data drive to warn of gas leakage.

[0047] Based on the confidence weight, calculate the comprehensive field strength, including: The comprehensive field strength calculation formula is as follows.

[0048] Among them, \(E\) is the weighted comprehensive field strength value, \(E_1\) is the field strength value directly monitored by the internal sensor, \(E_2\) is the predicted value of the field strength inference model in the blind area of the circuit breaker.

[0049] For further explanation, improve the field strength estimation accuracy through dynamic credibility fusion: When the external environment changes drastically (such as a sudden temperature rise resulting in \(x>0.8\)), The weight of \(\hat{E}_2\) (blind area model prediction) increases, and it preferentially captures local distortion of the insulating medium (such as field strength spikes caused by arcs); when the environment is stable (\(x>0.7\)), \(x>0.7\)), \(E_1\) (sensor measured value) dominates to ensure basic reliability.

[0050] Example: When the circuit breaker is opened, near the arc extinguishing chamber The sudden increase in \(\hat{E}_2\) triggers \(x = 0.9\), the predicted blind area of the model \(\hat{E}_2 = 28kV / mm\) (measured \(E_1 = 15kV / mm\)), the comprehensive field strength \(E\approx25.2kV / mm\), identifying the risk of dielectric breakdown; if the environment is stable (\(x = 0.2\)), then \(E\approx0.8\times15 + 0.2\times16 = 15.2kV / mm\), fitting the actual working conditions. Decision optimization module: Based on the calculated value of the comprehensive field strength, use the updated scheduling score formula to determine the spare parts supply of the circuit breaker, including: The updated scheduling score formula is as follows.

[0051] Decision optimization module: Based on the calculated value of the comprehensive field strength, use the updated scheduling score formula to determine the spare parts supply of the circuit breaker, including: The updated scheduling score formula is as follows.

[0052] Among them, is the updated dynamic scheduling score, is the scheduling score value, is the field strength safety threshold, is the field strength deviation sensitivity coefficient; Based on the updated scheduling score value, relevant information is sent to the management personnel.

[0053] For further explanation, when the comprehensive field strength deviates from the safety threshold the scheduling score is amplified according to the deviation ratio ( control sensitivity). For example, set = 25 kV / mm. If the blind area of a certain circuit breaker = 30 kV / mm and = 0.5, then the score increase is 0.5×(5 / 25) = 10%. The original score = 80 is updated to 88, exceeding the conventional task priority.

[0054] When the field strength exceeds the limit (such as > 1.2 ), the score rises exponentially and an emergency work order is triggered.

[0055] Updating the scheduling score formula achieves the following purposes: hierarchical response: define a piecewise function. For example, when > 0.3, = 1.2 to accelerate the scheduling of high-risk equipment; Data linkage: After the score is updated, it automatically associates the inventory system (such as spare parts inventory) with the personnel positioning data, and pushes the optimal work order of "priority - reachability - resource matching" (such as tasks with a score > 90 and sufficient spare parts are dispatched to the nearest operation and maintenance team).

[0056] Example: Multiple circuit breakers in a substation alarm simultaneously. For device A = 95, and for device B ( = 85), the system preferentially schedules device A and automatically allocates on-vehicle arc extinguishing chamber accessories to the work order, and at the same time pushes the operation guide of the insulation detector to the on-site personnel terminal.

[0057] Based on the updated scheduling score value, relevant information is sent to the management personnel, including: The updated scheduling score value is pushed to the management personnel terminal in a visual form and associated with the work order processing process.

[0058] The above has introduced the present application in detail. Specific examples are used herein to elaborate on the principle and implementation manner of the present application. The description of the above embodiments is only used to help understand the method and its core idea of the present application; at the same time, for those of ordinary skill in the art, according to the idea of the present application, there will be changes in the specific implementation manner and application scope. In summary, the content of this specification should not be construed as a limitation to the present application.

Claims

1. A high-voltage switchgear remote operation and maintenance intelligent service system, characterized in that: Includes the following parts: Data acquisition module: obtains external gas density data, internal gas density data, ambient temperature data and internal temperature data of the circuit breaker in a high-altitude environment; Monitoring module: using the instantaneous change data of the external gas density data and the ambient temperature data as analysis data of the internal field strength of the circuit breaker; optimizing the supply of accessories for the circuit breaker based on the analysis data; Analysis and processing module: calculating the confidence weight based on the external gas density data, the ambient temperature data and the internal monitoring data; Based on the confidence weight, calculating the integrated field strength; Decision optimization module: Based on the comprehensive field strength calculation value, the supply of circuit breaker accessories is determined using the updated scheduling scoring formula.

2. A high-voltage switchgear remote operation and maintenance intelligent service system as claimed in claim 1, characterized in that: The data acquisition module is used to acquire external gas density data, internal gas density data, ambient temperature data and internal temperature data of the circuit breaker in a high altitude environment, including: Using external gas density data and ambient temperature data as first monitoring data; The internal gas density data and the internal temperature data of the equipment are used as the second monitoring data; When the first monitoring data undergoes periodic changes, an optimization period determination of the second monitoring data is triggered; The periodic changes are periodic changes in external gas density and ambient temperature in a high altitude environment; The optimization period is defined as a period during which the second monitoring data does not undergo synchronous changes during the periodic changes of the first monitoring data.

3. A high-voltage switchgear remote operation and maintenance intelligent service system as claimed in claim 2, characterized in that: The period during which the second monitoring data does not undergo synchronous changes during the periodic changes of the first monitoring data includes: The lack of the same change is quantified by the phase difference formula, which is as follows: in, is the phase difference, is the change of external environmental parameters, is the internal parameter variation, is the environmental transmission delay, is the sampling window length, is the sampling time interval, is the serial number of the discrete sequence; Judgment rules: When > When , it is marked as a cycle that needs to be optimized. is a preset phase difference threshold; Extract the first monitoring data that continuously exceeds the preset threshold for a duration of ≥ As the component moments, is the shortest time of continuous exceeding threshold value; Based on the composition time, construct an optimization period of the second monitoring data; Based on the optimization cycle, a preliminary scheduling plan for circuit breaker accessories is generated.

4. A high-voltage switchgear remote operation and maintenance intelligent service system as claimed in claim 3, characterized in that: The generating a preliminary dispatching plan for circuit breaker accessories based on the optimization cycle includes: The preliminary dispatch score value of the circuit breaker accessories is obtained through the dispatch score formula. The dispatch score formula is as follows: in, is the scheduling score value, is the phase difference, For components The basic maintenance weight, is the current timestamp, For components Last maintenance timestamp, is the dynamic remaining life ratio, For components Theoretical maintenance cycle, For associated components The state anomaly score, , is the weight coefficient, For components A collection of associated components.

5. A high-voltage switchgear remote operation and maintenance intelligent service system as claimed in claim 1, characterized in that: The monitoring module: uses the instantaneous change data of the external gas density data and the ambient temperature data as analysis data of the internal field strength of the circuit breaker; Based on the analysis data, the supply of circuit breaker accessories is optimized, including: The instantaneous change rate of the external gas density is constructed by taking the moment before the instantaneous change of the external gas density as the starting point and the moment after the instantaneous change as the end point; the instantaneous change rate data of the external gas density and the ambient temperature in the entire change cycle are synchronously recorded; Based on the instantaneous change rate of the external gas density and the instantaneous change rate of the ambient temperature, the internal field strength data of the circuit breaker is obtained.

6. A high-voltage switchgear remote operation and maintenance intelligent service system as claimed in claim 5, characterized in that: The acquiring the internal field strength data of the circuit breaker based on the instantaneous change rate of the external gas density and the instantaneous change rate of the ambient temperature includes: Normalize the instantaneous change rate of external gas density, the instantaneous change rate of ambient temperature and the change rate of internal field strength respectively; The normalized instantaneous change rate of external gas density, the instantaneous change rate of ambient temperature and the change rate of internal field strength are used as input; The predicted value of internal field strength is used as output; Maxwell's equations and gas state equations are used as physical constraints; The full-field field strength distribution data of different working conditions are generated through finite element simulation. Combined with the collected data before and after abnormal events in actual operation and maintenance, a circuit breaker blind area field strength inference model is constructed.

7. A high-voltage switchgear remote operation and maintenance intelligent service system as claimed in claim 1, characterized in that: The calculating of the confidence weight based on the external gas density data, the ambient temperature data and the internal monitoring data includes: in, is the instantaneous change of external gas density, is the instantaneous change of ambient temperature, The critical value of environmental mutation set by experience, is the confidence weight of the external environment data, is the confidence weight of the internal monitoring data; If the confidence weight of the external environment data exceeds a first preset threshold, increasing the confidence weight of the external environment data; If the confidence weight of the external environment data is lower than the second preset threshold, the confidence weight of the internal monitoring data is increased.

8. The high-voltage switchgear remote operation and maintenance intelligent service system according to claim 1, characterized in that: The calculating of the comprehensive field strength based on the confidence weight includes: the comprehensive field strength calculation formula is as follows: in, is the weighted comprehensive field strength value, is the field strength value directly monitored by the internal sensor, It is the predicted value of the field strength inference model of the circuit breaker blind area.

9. A high-voltage switchgear remote operation and maintenance intelligent service system as claimed in claim 1, characterized in that: The decision optimization module: based on the comprehensive field strength calculation value, uses the updated scheduling scoring formula to determine the supply of circuit breaker accessories, including: the updated scheduling scoring formula is as follows, in, Score the updated dynamic scheduling, is the scheduling score value, is the field strength safety threshold, is the field intensity deviation sensitivity coefficient; Based on the updated scheduling score value, relevant information is sent to the management staff.

10. A high-voltage switchgear remote operation and maintenance intelligent service system as claimed in claim 9, characterized in that: The updated scheduling score value is used to send relevant information to the management personnel, including: The updated scheduling score value is pushed to the management terminal in a visual form and associated with the work order processing process.

Images