A Remote Monitoring Method for Low-Voltage Distribution Boxes Based on Big Data Analysis

By constructing interconnected distribution box groups and dynamically adjusting monitoring strategies, the problem of insufficient correlation in remote monitoring of low-voltage distribution boxes was solved, improving flexibility and accuracy, and ensuring the safe and efficient operation of the distribution boxes.

CN123122012APending Publication Date: 2026-11-17ZHEJIANG ZHONGFEIYA TECH CO LTD
View PDF 1 Cites 0 Cited by

Patent Information

Application Number
CN202611249109.8
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2026-08-18
Publication Date
2026-11-17

AI Technical Summary

Technical Problem

Existing remote monitoring methods for low-voltage distribution boxes fail to effectively consider the operational correlation between multiple distribution boxes in the same area, resulting in insufficient monitoring flexibility and accuracy in anomaly detection.

Method used

Based on big data analysis, by monitoring electrical and environmental parameters in the target area in real time, associated distribution box groups are constructed, parameter comparison thresholds and anomaly probabilities are determined, and monitoring cycles and combinations are dynamically adjusted to achieve differentiated management.

Benefits of technology

It improves the flexibility of monitoring and the accuracy of anomaly detection, enabling timely detection of gradual hidden dangers, avoiding ineffective warnings, optimizing monitoring strategies, and ensuring the safe operation of distribution boxes.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN123122012A_ABST
    Figure CN123122012A_ABST
Patent Text Reader

Abstract

This invention relates to the field of distribution box monitoring technology, and more particularly to a remote monitoring method for low-voltage distribution boxes based on big data analysis. The method includes: real-time monitoring of electrical and environmental parameters of several distribution boxes within a target area to identify several associated distribution box groups; determining the parameter comparison threshold and parameter anomaly probability for each associated distribution box group; determining the parameter change characterization value for each associated distribution box group based on the changes in electrical and environmental parameters of each distribution box within a preset time period, and determining whether to trigger early warning monitoring; if early warning monitoring is triggered, determining the parameter monitoring characterization value for each associated distribution box group; and determining the monitoring adjustment method based on the comparison result between the parameter comparison threshold and the parameter monitoring characterization value for each associated distribution box group, to monitor each distribution box within the target area. This invention improves monitoring flexibility and the accuracy of anomaly detection.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] This invention relates to the field of distribution box monitoring technology, and in particular to a remote monitoring method for low-voltage distribution boxes based on big data analysis. Background Technology

[0002] With the comprehensive advancement of smart cities, Industry 4.0, and new power systems, low-voltage distribution boxes, as core nodes connecting the power supply network and user loads at the end of the distribution network, are widely deployed in various scenarios such as residential buildings, industrial parks, commercial complexes, and industrial and mining enterprises. Their operational stability directly determines the reliability of power supply, electricity safety, and energy management efficiency. Traditional low-voltage distribution monitoring mainly relies on manual inspections, local instrument displays, and periodic maintenance. It depends on maintenance personnel to record data on-site and investigate potential hazards. This approach suffers from prominent problems such as large monitoring blind spots, delayed response, delayed fault detection, high labor costs, and subjective maintenance decisions, making it difficult to cope with the large-scale, high-density, and decentralized operation and maintenance needs of distribution boxes.

[0003] Driven by the Internet of Things (IoT), big data, and telecommunications technologies, existing remote monitoring systems are gradually realizing the collection and uploading of electrical and environmental parameters, and achieving basic data visualization and fixed threshold alarms through cloud platforms. Current mainstream solutions mostly adopt a single-device independent monitoring mode, configuring a fixed collection frequency and uniform threshold for each distribution box, without considering the topological affiliation and collaborative relationships of multiple distribution boxes for differentiated management. Monitoring cycles are mostly factory presets or manually configured, leading to asynchronous sampling and misaligned data timing among related devices within the same area. This makes it impossible to conduct horizontal consistency comparisons within the group, resulting in a lack of reference benchmarks for parameter anomaly judgment and difficulty in identifying latent faults and early degradation.

[0004] Chinese Patent Publication No. CN120433454A discloses a remote monitoring method for a distribution box and the distribution box itself. The method acquires electrical power data, target temperature data, and ambient temperature data within the distribution box during the current time period; based on changes in the electrical power data and the difference between the electrical power data and the target temperature data, it acquires the degree of thermal anomaly of the distribution box at the current moment; based on changes in the target temperature data and ambient temperature data during the target temperature cooling phase, the magnitude of the electrical power data, and changes in the target temperature data and ambient temperature data during the target temperature heating phase, it acquires the degree of heat dissipation anomaly of the distribution box at the current moment; and based on the degree of thermal anomaly and the degree of heat dissipation anomaly, it acquires the degree of fault of the distribution box at the current moment.

[0005] The existing technology has the following problems: it only uses a single distribution box as an independent monitoring unit, does not consider the operational correlation between multiple distribution boxes in the same area, and only relies on instantaneous changes and simple difference judgments, resulting in insufficient monitoring flexibility and accuracy of anomaly judgment. Summary of the Invention

[0006] To address this, the present invention provides a remote monitoring method for low-voltage distribution boxes based on big data analysis, which overcomes the problems of existing technologies that only use a single distribution box as an independent monitoring unit, without considering the operational correlation between multiple distribution boxes in the same area, resulting in insufficient monitoring flexibility and accuracy in anomaly judgment.

[0007] To achieve the above objectives, the present invention provides a remote monitoring method for low-voltage distribution boxes based on big data analysis, comprising: Real-time monitoring of electrical and environmental parameters of several distribution boxes within the target area is used to identify several associated distribution box groups. Each associated distribution box group includes several distribution boxes, and the initial monitoring cycle of each distribution box in the same group is the same. Based on the historical electrical parameters and historical environmental parameters of each distribution box in each of the associated distribution box groups, the parameter comparison threshold corresponding to each associated distribution box group is determined, and the parameter anomaly probability corresponding to each associated distribution box group is determined. Based on the changes in electrical parameters and environmental parameters of each distribution box within a preset time period, the parameter change characterization value corresponding to each associated distribution box group is determined, and whether to trigger early warning monitoring is determined based on the parameter change characterization value and the parameter anomaly probability. If an early warning monitoring is triggered, the current electrical parameters and current environmental parameters of each of the aforementioned distribution boxes are obtained to determine the parameter monitoring characterization values ​​corresponding to each of the associated distribution box groups. The monitoring adjustment method is determined based on the comparison results of the parameter comparison threshold and the parameter monitoring characterization value corresponding to each of the associated distribution box groups, so as to monitor each of the distribution boxes in the target area. The monitoring adjustment method includes adjusting the monitoring cycle and redetermining the associated distribution box groups.

[0008] Further, several of the aforementioned associated distribution box groups are identified, including: Based on the changes in electrical parameters of each distribution box within the target time period, construct the target electrical parameter change curve for each distribution box to determine the electrical difference range for each distribution box; Based on the changes in environmental parameters of each distribution box within the target time period, construct the target environmental parameter change curve for each distribution box to determine the environmental fluctuation range for each distribution box. Based on the comparison results of each of the electrical difference intervals and each of the environmental fluctuation intervals, several of the associated distribution box groups are determined.

[0009] Further, determining the parameter comparison threshold corresponding to any of the associated distribution box groups includes: Based on the historical electrical parameters of each distribution box in the associated distribution box group, the historical electrical reference corresponding to each associated distribution box group is determined, so as to determine the electrical parameter characterization value corresponding to the associated distribution box group; Based on the historical environmental parameters of each distribution box in the associated distribution box group, the historical environmental benchmark corresponding to each associated distribution box group is determined, so as to determine the environmental parameter characterization value corresponding to the associated distribution box group; The parameter comparison threshold corresponding to the associated distribution box group is determined based on the electrical parameter characterization value and the environmental parameter characterization value.

[0010] Further, determining the probability of parameter anomalies corresponding to any of the associated distribution box groups includes: Based on the comparison results between the historical electrical reference corresponding to the associated distribution box group and the historical electrical parameters of each distribution box in the associated distribution box group, the deviation probability of the electrical parameters corresponding to the associated distribution box group is determined. Based on the comparison results between the historical environmental benchmark corresponding to the associated distribution box group and the historical environmental parameters of each distribution box in the associated distribution box group, the deviation probability of the environmental parameters corresponding to the associated distribution box group is determined. The abnormal parameter probability of the associated distribution box group is determined based on the deviation probability of the electrical parameters and the deviation probability of the environmental parameters.

[0011] Further, determining the parameter change characterization value corresponding to any of the associated distribution box groups includes: Based on the changes in electrical parameters of each distribution box in the associated distribution box group within a preset time period, construct the associated electrical parameter change curve corresponding to the associated distribution box group to determine the comprehensive electrical change index corresponding to the associated distribution box group; Based on the changes in environmental parameters of each distribution box in the associated distribution box group within a preset time period, construct the associated environmental parameter change curve corresponding to the associated distribution box group to determine the comprehensive environmental change index corresponding to the associated distribution box group; The parameter change characterization values ​​corresponding to the associated distribution box group are determined based on the comprehensive electrical change index and the comprehensive environmental change index.

[0012] Further, determine whether early warning monitoring has been triggered, including: Based on the parameter change characterization value and the abnormal probability of each parameter, determine the parameter early warning characterization value corresponding to each associated distribution box group; Whether to trigger early warning monitoring is determined based on the comparison results between the parameter early warning characterization value corresponding to each of the associated distribution box groups and the preset early warning characterization value.

[0013] Further, determining the parameter monitoring characterization value corresponding to any of the associated distribution box groups includes: Based on the comparison results between the current electrical parameters of each distribution box in the associated distribution box group and the preset electrical parameters, the fluctuation value of the electrical parameters corresponding to the associated distribution box group is determined. Based on the comparison results between the current environmental parameters of each distribution box in the associated distribution box group and the preset environmental parameters, the fluctuation value of the environmental parameters corresponding to the associated distribution box group is determined. The parameter monitoring characterization values ​​corresponding to the associated distribution box group are determined based on the fluctuation values ​​of the electrical parameters and the fluctuation values ​​of the environmental parameters.

[0014] Further, the monitoring adjustment method is determined, including: Based on the comparison results between the comparison threshold of each parameter and the monitoring characterization value of each parameter, the parameter monitoring deviation corresponding to each associated distribution box group is determined. Based on the comparison results of the parameter monitoring deviations of each associated distribution box group with the preset monitoring deviations, several key distribution box groups are identified to determine the monitoring adjustment method.

[0015] Furthermore, the monitoring and adjustment method is determined based on the comparison between the number of key distribution box groups and the preset number, wherein, When the number of key distribution boxes is less than the preset number, the monitoring adjustment method is determined to be adjusting the monitoring cycle; If the number of key distribution box groups is greater than or equal to the preset number, the monitoring and adjustment method is determined to be to redetermine the associated distribution box groups.

[0016] Furthermore, the monitoring cycle will be adjusted, including: Based on the comparison results of the parameter monitoring deviation and the preset monitoring deviation of each key distribution box group, the parameter adjustment coefficient of each key distribution box group is determined. The target monitoring period is determined based on the parameter adjustment coefficients and initial monitoring period corresponding to each of the key distribution box groups, so as to adjust the monitoring period.

[0017] Compared with existing technologies, the advantages of this invention are as follows: This invention conducts unified monitoring based on associated distribution box groups, grouping distribution boxes with similar operating characteristics and environmental conditions together to achieve differentiated and refined management of distribution boxes. The same initial monitoring cycle is used within the same associated group, ensuring synchronized data acquisition timing for each distribution box within the group. Targeted configuration of basic monitoring strategies can be achieved, improving monitoring flexibility and efficiency. By determining parameter comparison thresholds based on historical electrical and environmental parameters of each distribution box in the associated distribution box group, the invention aligns with the actual operating conditions of the distribution boxes within the group, improving threshold adaptability and avoiding misjudgments caused by fixed thresholds. By determining the parameter anomaly probability of each associated distribution box group, the invention quantifies the probability of the current state of the distribution boxes deviating from the normal state, improving the accuracy of anomaly judgment. The invention quantifies the parameter fluctuation trend and degree of abrupt change within a preset time period through parameter change characterization values. By integrating parameter change characterization values ​​and parameter anomaly probabilities for joint judgment, it considers both dynamic parameter change trends and historical anomaly possibilities, achieving a comprehensive risk judgment from two dimensions. This not only promptly captures gradual hidden dangers but also avoids ineffective warnings, improving the rationality and sensitivity of the early warning mechanism. Under the condition of triggering early warning monitoring, the system strengthens the collection of all current parameters and forms parameter monitoring characterization values, realizing accurate quantification of the real-time operating status of the distribution box and providing real-time data support for subsequent monitoring and analysis. By comparing the parameter comparison thresholds and parameter monitoring characterization values ​​corresponding to the associated distribution box groups, the system adaptively selects to adjust the monitoring cycle or re-divide the monitoring adjustment methods of the associated distribution box groups. It can flexibly optimize the monitoring strategy according to the actual operating deviation, reasonably adjust the monitoring frequency to allocate monitoring resources when there are local anomalies, and regroup to optimize the monitoring architecture when there are overall anomalies. While ensuring the safe operation of the distribution box, it can improve the monitoring flexibility and the accuracy of anomaly judgment.

[0018] Furthermore, by constructing target electrical parameter variation curves and determining electrical difference ranges, this invention can quantify the degree of difference in the electrical operating characteristics of each distribution box, avoiding the bias caused by relying solely on single-point electrical parameters, and providing an objective and stable electrical dimension basis for subsequent grouping. By constructing target environmental parameter variation curves and determining environmental fluctuation ranges, the similarity and difference of the environment in which each distribution box is located can be accurately characterized, fully considering the impact of environmental factors on the operating status of the distribution boxes, and improving the comprehensiveness of the grouping basis. By comparing and grouping distribution boxes based on both electrical difference ranges and environmental fluctuation ranges, distribution boxes with similar electrical characteristics and similar environmental conditions can be classified into the same related group, achieving refined and scientific classification of distribution boxes, and laying the foundation for subsequent unified threshold setting and anomaly judgment.

[0019] Furthermore, this invention determines historical electrical benchmarks and parameter characterization values ​​based on historical electrical parameters. This allows for the formation of electrical benchmarks that conform to the actual operating conditions of the distribution box using historical operating data, avoiding misjudgments or omissions caused by using uniform fixed thresholds and improving the adaptability of thresholds. Determining historical environmental benchmarks and environmental parameter characterization values ​​based on historical environmental parameters incorporates environmental impacts into the threshold system, ensuring that threshold settings closely match the actual operating environment of the distribution box and improving the rationality of the judgment criteria. Integrating electrical parameter characterization values ​​and environmental parameter characterization values ​​to determine parameter comparison thresholds enables multi-dimensional, adaptive threshold generation, improving the accuracy of anomaly identification.

[0020] Furthermore, this invention calculates the deviation probability of electrical parameters by comparing them with historical electrical benchmarks and parameters, enabling a quantitative assessment of the likelihood of electrical parameters deviating from normal conditions and achieving a probabilistic expression of electrical anomaly risks. By comparing environmental parameters with historical environmental benchmarks and parameters, the invention calculates the deviation probability of environmental parameters, allowing for a separate assessment of anomaly risks caused by environmental disturbances, distinguishing between electrical faults and fluctuations caused by the external environment, and improving anomaly tracing capabilities. By integrating the deviation probabilities of electrical and environmental parameters to obtain parameter anomaly probabilities, this invention achieves a comprehensive assessment of anomaly risks based on multi-factor weighting, making anomaly judgments more closely aligned with actual operating conditions and reducing false alarms caused by fluctuations in a single parameter.

[0021] Furthermore, this invention determines a comprehensive electrical change index by constructing associated electrical parameter change curves, which can dynamically reflect the changing trends and severity of electrical parameters in associated distribution boxes. It also determines a comprehensive environmental change index by constructing associated environmental parameter change curves, which can track the impact of environmental fluctuations on associated distribution box groups in real time and identify operational risks caused by sudden environmental changes. The comprehensive electrical change index and the comprehensive environmental change index yield parameter change characterization values, achieving a quantitative characterization of the overall operational trend of associated distribution box groups and providing a dynamic and continuous basis for early warning judgment.

[0022] Furthermore, this invention obtains a parameter warning characterization value by fusing parameter change characterization values ​​and parameter anomaly probabilities. This simultaneously considers current trends and historical anomaly probabilities, achieving a dual-dimensional risk assessment and improving warning reliability. By comparing the warning characterization value with a preset warning characterization value to determine whether a warning is triggered, a tiered and intelligent warning mechanism can be implemented, avoiding frequent invalid warnings and ensuring that high-risk conditions are identified promptly, balancing monitoring efficiency and safety.

[0023] Furthermore, this invention obtains electrical parameter fluctuation values ​​by comparing current electrical parameters with preset electrical parameters, which can intuitively reflect the degree to which the current electrical operating state deviates from the normal range, providing a quantitative indicator for real-time monitoring. By comparing current environmental parameters with preset environmental parameters, the invention obtains environmental parameter fluctuation values, which can quantify the degree of environmental disturbance in real time, providing environmental dimension support for judging the causes of anomalies. Integrating electrical parameter fluctuation values ​​and environmental parameter fluctuation values ​​yields parameter monitoring characterization values, achieving a comprehensive quantification of the current operating state, facilitating subsequent rapid comparison and decision-making.

[0024] Furthermore, this invention obtains the parameter monitoring deviation by comparing the parameter comparison threshold with the parameter monitoring characterization value, which can accurately calculate the deviation between the actual monitoring result and the expected standard, providing a quantitative basis for adjusting the monitoring strategy. Based on the parameter monitoring deviation, key distribution box groups are selected, and the adjustment method is selected based on the number of key distribution box groups, which can realize the adaptive optimization of the monitoring strategy. Attached Figure Description

[0025] Figure 1 This is a flowchart illustrating the remote monitoring method for low-voltage distribution boxes based on big data analysis, as described in an embodiment of the present invention. Figure 2 This is a schematic diagram illustrating the process of determining several associated distribution box groups in an embodiment of the present invention; Figure 3 This is a logic diagram illustrating whether to trigger early warning monitoring in an embodiment of the present invention. Figure 4 This is a logic diagram for determining the monitoring and adjustment method in an embodiment of the present invention. Detailed Implementation

[0026] To make the objectives and advantages of the present invention clearer, the present invention will be further described below with reference to embodiments; it should be understood that the specific embodiments described herein are merely for explaining the present invention and are not intended to limit the present invention.

[0027] Preferred embodiments of the present invention will now be described with reference to the accompanying drawings. Those skilled in the art should understand that these embodiments are merely illustrative of the technical principles of the present invention and are not intended to limit the scope of protection of the present invention.

[0028] Please see Figures 1-4 As shown, Figure 1 This is a flowchart illustrating the remote monitoring method for low-voltage distribution boxes based on big data analysis, as described in an embodiment of the present invention. Figure 2 This is a schematic diagram illustrating the process of determining several associated distribution box groups in an embodiment of the present invention; Figure 3 This is a logic diagram illustrating whether to trigger early warning monitoring in an embodiment of the present invention. Figure 4This is a logic diagram for determining the monitoring and adjustment method in an embodiment of the present invention; an embodiment of the present invention provides a remote monitoring method for low-voltage distribution boxes based on big data analysis, including: Step S1: Monitor the electrical and environmental parameters of several distribution boxes in the target area in real time to determine several associated distribution box groups. Each of the associated distribution box groups includes several distribution boxes, and the initial monitoring cycle of each distribution box in the same distribution box group is the same. In implementation, the target area can be the power distribution area of ​​industrial parks, industrial parks, commercial complexes, etc.

[0029] Specifically, in step S1, determining a plurality of the associated distribution box groups includes: Step S11: Based on the changes in electrical parameters of each distribution box within the target time period, construct the target electrical parameter change curve for each distribution box to determine the electrical difference range for each distribution box. Step S12: Based on the changes in environmental parameters of each distribution box within the target time period, construct the target environmental parameter change curve corresponding to each distribution box to determine the environmental fluctuation range corresponding to each distribution box. Step S13: Based on the comparison results of each of the electrical difference intervals and each of the environmental fluctuation intervals, determine a number of the associated distribution box groups.

[0030] During implementation, electrical parameters include, but are not limited to, three-phase voltage, three-phase current, active power, operating frequency, and harmonic distortion rate. Environmental parameters include, but are not limited to, internal enclosure temperature, ambient temperature, busbar contact temperature, internal enclosure humidity, and vibration amplitude. Parameters are collected several times within a target time period. Preferably, the target time period is set to a range of 30 to 60 minutes, and the parameter collection frequency is set to a range of 60 to 80 times per minute.

[0031] Understandably, for any distribution box, using time as the independent variable and electrical parameters as the dependent variable, corresponding target electrical parameter change curves are constructed. For example, using time as the independent variable and three-phase voltage as the dependent variable, a target three-phase voltage change curve corresponding to the distribution box is constructed. The electrical difference interval is determined based on the slope of any target electrical parameter change curve. The absolute value of the slope of the electrical difference interval is greater than a first preset slope, and the duration of the electrical difference interval is greater than a preset duration. Similarly, using time as the independent variable and environmental parameters as the dependent variable, corresponding target environmental parameter change curves are constructed. The environmental fluctuation interval is determined based on the slope of any target environmental parameter change curve. The absolute value of the slope of the environmental fluctuation interval is greater than a second preset slope, and the duration of the environmental fluctuation interval is greater than a preset duration. The implementers can set a first preset slope based on the actual situation or the average slope of the electrical parameter change curves of distribution boxes that have passed the qualification test in historical data. The implementers can set a second preset slope based on the actual situation or the average slope of the environmental parameter change curves of distribution boxes that have passed the qualification test in historical data. The implementers can set a preset duration based on the actual situation. Preferably, the preset duration is set to a range of 20s to 30s. The qualification test refers to selecting data within a time period that is in normal operation (no fault alarms, no maintenance, no external interference events, etc. during operation) based on the historical operating data of distribution boxes in the target area. Specifically, it can be determined by expert rules: set reasonable working ranges for each parameter (such as voltage deviation ≤ ±5%, temperature ≤ 60℃, etc.). Data that meets the requirements of all parameter ranges is considered qualified. In actual application, data that is determined to be qualified in historical data is considered to have passed the qualification test.

[0032] It is understandable that for any distribution box, its electrical difference range and environmental fluctuation range are combined into a multi-dimensional feature vector. For example, if the electrical difference range is ΔE and the environmental fluctuation range is ΔH, then the feature vector is (ΔE, ΔH). A clustering algorithm is used to cluster the feature vectors of all distribution boxes. The clustering algorithm will group distribution boxes with similar features into the same class. The number of clusters can be determined by the elbow rule or the silhouette coefficient. There is no specific limitation on the clustering algorithm. For example, K-means, DBSCAN, hierarchical clustering, etc. The clustering result is several associated distribution box groups. Each associated distribution box group has a corresponding central distribution box, which is the corresponding cluster center.

[0033] Specifically, this invention, by constructing target electrical parameter variation curves and determining electrical difference ranges, can quantify the degree of difference in the electrical operating characteristics of each distribution box, avoiding the one-sidedness of judgments caused by relying solely on single-point electrical parameters, and providing an objective and stable electrical dimension basis for subsequent grouping. By constructing target environmental parameter variation curves and determining environmental fluctuation ranges, the similarity and difference of the environment in which each distribution box is located can be accurately characterized, fully considering the impact of environmental factors on the operating status of the distribution boxes, and improving the comprehensiveness of the grouping basis. By comparing and grouping distribution boxes based on both electrical difference ranges and environmental fluctuation ranges, distribution boxes with similar electrical characteristics and similar environmental conditions can be classified into the same related group, achieving refined and scientific classification of distribution boxes, laying the foundation for subsequent unified threshold setting and anomaly judgment.

[0034] Step S2: Based on the historical electrical parameters and historical environmental parameters of each distribution box in each associated distribution box group, determine the parameter comparison threshold corresponding to each associated distribution box group, and determine the parameter anomaly probability corresponding to each associated distribution box group. Specifically, in step S2, determining the parameter comparison threshold corresponding to any of the associated distribution box groups includes: Step S21: Determine the historical electrical reference corresponding to each associated distribution box group based on the historical electrical parameters of each distribution box in the associated distribution box group, so as to determine the electrical parameter characterization value corresponding to the associated distribution box group; Step S22: Determine the historical environmental benchmark corresponding to each associated distribution box group based on the historical environmental parameters of each distribution box in the associated distribution box group, so as to determine the environmental parameter characterization value corresponding to the associated distribution box group; Step S23: Determine the parameter comparison threshold corresponding to the associated distribution box group based on the electrical parameter characterization value and the environmental parameter characterization value.

[0035] In implementation, each electrical parameter is normalized and mapped to the 0-1 interval to eliminate dimensional interference. For example, for any electrical parameter, the normalization method can be Min-Max normalization, where X... a = (XX) min ) / (X max -X min ), where X is the original electrical parameter value, X a X represents the normalized electrical parameter value. min X represents the minimum original electrical parameters within the associated distribution box group. maxThis represents the maximum original electrical parameters within the associated distribution box group. The historical electrical baseline includes the baseline values ​​corresponding to each electrical parameter. For any associated distribution box group, the baseline values ​​corresponding to each electrical parameter are determined based on the average of the electrical parameters of each distribution box, thus obtaining the historical electrical baseline for that associated distribution box group. The electrical parameters of the central distribution box of the associated distribution box group are compared with the historical electrical baseline. The historical electrical parameters of the central distribution box are GY = (GY1, GY2, ..., GY...). g , ..., GY h ); among them, GY g =(GY g,1 GY g,2 , ..., GY g,j , ..., GY g,m Historical electrical benchmarks GE1, GE2, ..., GE j , ..., GE m Then the electrical parameter characterization value GP corresponding to the associated distribution box group is ∑ h g=1 ((∑ m j=1 GY g,j ×GE j ) / (sqrt(∑ m j=1 (GY g,j ) 2 )×sqrt(∑ m j=1 (GE j ) 2 ))) / h, sqrt() is the preset square root determination function, g=1,2,…,h, j=1,2,…,m, h is the number of parameter acquisitions, and m is the number of electrical parameters.

[0036] Understandably, normalizing each environmental parameter and mapping it to the 0-1 interval can eliminate interference from dimensions. For example, for any environmental parameter, the normalization method could be Min-Max normalization, where W... a =(WW) min ) / (W max -W min ), where W is the original environmental parameter value, W a W represents the normalized environmental parameter values. min To determine the minimum original environmental parameters within the associated distribution box group, W maxThis represents the maximum original environmental parameters within the associated distribution box group. The historical environmental baseline includes the baseline values ​​corresponding to each environmental parameter. For any associated distribution box group, the baseline values ​​corresponding to each environmental parameter are determined based on the average environmental parameters of each distribution box to obtain the historical environmental baseline for that associated distribution box group. The environmental parameters of the central distribution box of the associated distribution box group are compared with the historical environmental baseline. The historical environmental parameters of the central distribution box are defined as HY = (HY1, HY2, ..., HY...). g , ..., HY h ); among them, HY g =(HY g,1 HY g,2 , ..., HY g,i , ..., HY g,n Historical environmental baselines HE1, HE2, ..., HE i HE n Then the environmental parameter characterization value HP corresponding to the associated distribution box group is ∑ h g=1 ((∑ n i=1 HY i ×HE i ) / (sqrt(∑ n i=1 (HY i ) 2 )×sqrt(∑ n i=1 (HE i ) 2 ))) / h, i=1,2,…,n, where n is the number of environmental parameters.

[0037] It is understood that for any associated distribution box group, the parameter comparison threshold CB corresponding to the associated distribution box group is CB = u1 × A1 + u2 × A2, where A1 is the electrical parameter characterization value corresponding to the associated distribution box group, A2 is the environmental parameter characterization value corresponding to the associated distribution box group, and u1 and u2 are the corresponding weight coefficients. The actual implementers can set them based on the actual situation, u1 + u2 = 1, preferably u1 = 0.8, u2 = 0.2, u1 + u2 = 1. In a specific embodiment, the entropy weight method can be used to determine the corresponding weight coefficients u1 and u2. For historical electrical parameters and historical environmental parameters, the information entropy E1 corresponding to the electrical parameters and the information entropy E2 corresponding to the environmental parameters are calculated respectively, and the corresponding information entropy difference is calculated. The electrical parameter difference D1 = 1 - E1, and the environmental parameter difference D2 = 1 - E2. Then the weight u1 corresponding to the electrical parameters is D1 / (D1 + D2), and the weight coefficient u2 corresponding to the environmental parameters is D2 / (D1 + D2).

[0038] Specifically, this invention determines historical electrical benchmarks and parameter characterization values ​​based on historical electrical parameters. This allows for the formation of electrical benchmarks that conform to the actual operating conditions of the distribution box using historical operational data, avoiding misjudgments or omissions caused by using uniform fixed thresholds and improving the adaptability of thresholds. Determining historical environmental benchmarks and environmental parameter characterization values ​​based on historical environmental parameters incorporates environmental impacts into the threshold system, ensuring that threshold settings closely match the actual operating environment of the distribution box and improving the rationality of the judgment criteria. Integrating electrical parameter characterization values ​​and environmental parameter characterization values ​​to determine parameter comparison thresholds enables multi-dimensional, adaptive threshold generation, improving the accuracy of anomaly identification.

[0039] Specifically, in step S2, determining the probability of parameter anomalies for any of the associated distribution box groups includes: Step S24: Based on the comparison results between the historical electrical reference corresponding to the associated distribution box group and the historical electrical parameters of each distribution box in the associated distribution box group, determine the deviation probability of the electrical parameters corresponding to the associated distribution box group; Step S25: Based on the comparison results between the historical environmental benchmark corresponding to the associated distribution box group and the historical environmental parameters of each distribution box in the associated distribution box group, determine the deviation probability of the environmental parameters corresponding to the associated distribution box group. Step S26: Determine the parameter anomaly probability corresponding to the associated distribution box group based on the electrical parameter deviation probability and the environmental parameter deviation probability.

[0040] In implementation, for any distribution box in any associated distribution box group, the historical electrical parameters YJ=(YJ1, YJ2, ..., YJ...) are... g , ..., YJ h ); among them, YJ g =(YJ g,1 YJ g,2 , ..., YJ g,j , ..., YJ g,m The historical electrical references EJ1, EJ2, ..., EJ corresponding to this associated distribution box group are... j , ..., EJ m The deviation of the electrical parameters corresponding to the associated distribution box group is DK=∑ h g=1 ((∑ m j=1 (YJ g,j -EJ j ) 2 If ) / m) / h, then the electrical parameter deviation probability DP corresponding to this associated distribution box group is 1 / (1+e -α×(DK-β)), where α is the deviation sensitivity coefficient and β is the deviation threshold coefficient. The actual implementer can set these values ​​based on the actual situation. The deviation sensitivity coefficient can control the steepness of the probability increase when the deviation increases. Preferably, the value of α is set to 5 to 10. β controls the deviation value of significant abnormality. Preferably, the value of β is set to 0.1 to 0.3.

[0041] It is understandable that for any distribution box in any associated distribution box group, the historical environmental parameter YL = (YL1, YL2, ..., YL...). g , ..., YL h ); where YL g =(YL g,1 YL g,2 , ..., YL g,i , ..., YL g,n The historical environmental references EL1, EL2, ..., EL1 for the associated distribution box group are: j , ..., EL m The degree of deviation of the environmental parameters corresponding to the associated distribution box group HK=∑ h g=1 ((∑ n i=1 (YJ g,i -EJ i ) 2 If ) / n) / h, then the environmental parameter deviation probability corresponding to this associated distribution box group is HP=1 / (1+e -α×(HK-β) ).

[0042] It is understandable that, for any associated distribution box group, the product of the electrical parameter deviation probability and the environmental parameter deviation probability is determined as the parameter anomaly probability corresponding to that associated distribution box group.

[0043] Specifically, this invention calculates the deviation probability of electrical parameters by comparing them with historical electrical benchmarks and parameters, enabling a quantitative assessment of the likelihood of electrical parameters deviating from normal conditions and achieving a probabilistic expression of electrical anomaly risks. By comparing environmental parameters with historical environmental benchmarks and parameters, the invention calculates the deviation probability of environmental parameters, allowing for a separate assessment of anomaly risks caused by environmental disturbances, distinguishing between electrical faults and fluctuations caused by the external environment, and improving anomaly tracing capabilities. By integrating the deviation probabilities of electrical and environmental parameters to obtain parameter anomaly probabilities, this invention achieves a comprehensive assessment of anomaly risks based on multi-factor weighting, making anomaly judgments more closely aligned with actual operating conditions and reducing false alarms caused by fluctuations in a single parameter.

[0044] Step S3: Based on the changes in electrical parameters and environmental parameters of each distribution box within a preset time period, determine the parameter change characterization value corresponding to each associated distribution box group, and determine whether to trigger early warning monitoring based on the parameter change characterization value and the parameter anomaly probability. Specifically, in step S3, determining the parameter change characterization value corresponding to any of the associated distribution box groups includes: Step S31: Based on the changes in electrical parameters of each distribution box in the associated distribution box group within a preset time period, construct the associated electrical parameter change curve corresponding to the associated distribution box group, so as to determine the comprehensive electrical change index corresponding to the associated distribution box group; Step S32: Based on the changes in environmental parameters of each distribution box in the associated distribution box group within a preset time period, construct the associated environmental parameter change curve corresponding to the associated distribution box group, so as to determine the comprehensive environmental change index corresponding to the associated distribution box group. Step S33: Determine the parameter change characterization value corresponding to the associated distribution box group based on the comprehensive electrical change index and the comprehensive environmental change index.

[0045] In practice, the implementers can set a preset time period based on the actual situation. Preferably, the preset time period can be set to 1 / 5 to 1 / 6 of the target time period length.

[0046] Understandably, for any associated distribution box group, with time as the independent variable and the average electrical parameters of each distribution box within the group as the dependent variable, corresponding associated electrical parameter change curves are constructed. For example, with time as the independent variable and the average three-phase voltage of each distribution box within the group as the dependent variable, associated three-phase voltage change curves corresponding to the associated distribution box group are constructed. For any electrical parameter, the absolute value of the ratio of the average rate of change to the maximum rate of change of the associated electrical parameter change curves corresponding to the associated distribution box group within a preset time period is determined as the single electrical change index corresponding to that electrical parameter. The average first derivative of the curve within the preset time period can be determined as the average rate of change, the maximum value of the first derivative of the curve within the preset time period can be determined as the maximum rate of change, and the average of the single electrical change indices corresponding to each electrical parameter can be determined as the comprehensive electrical change index corresponding to the associated distribution box group.

[0047] Understandably, for any associated distribution box group, with time as the independent variable and the average environmental parameter of each distribution box within the group as the dependent variable, corresponding associated environmental parameter change curves are constructed. For example, with time as the independent variable and the average ambient temperature of each distribution box within the group as the dependent variable, an associated ambient temperature change curve is constructed for the associated distribution box group. For any environmental parameter, the absolute value of the ratio of the average rate of change to the maximum rate of change of the associated environmental parameter change curves for the associated distribution box group within a preset time period is determined as the single environmental change index for that environmental parameter. The average of the single environmental change indices for each environmental parameter is determined as the comprehensive environmental change index for the associated distribution box group.

[0048] It is understandable that for any associated distribution box group, the parameter change characterization value CD corresponding to the associated distribution box group is CD=u1×R1+u2×R2, where R1 is the comprehensive electrical change index corresponding to the associated distribution box group, and R2 is the comprehensive environmental change index corresponding to the associated distribution box group.

[0049] Specifically, this invention determines a comprehensive electrical change index by constructing associated electrical parameter change curves, which dynamically reflects the changing trends and severity of electrical parameters in associated distribution boxes. It also determines a comprehensive environmental change index by constructing associated environmental parameter change curves, enabling real-time tracking of the impact of environmental fluctuations on associated distribution box groups and identifying operational risks caused by sudden environmental changes. The comprehensive electrical change index and the comprehensive environmental change index yield parameter change characterization values, achieving a quantitative representation of the overall operational trend of associated distribution box groups and providing a dynamic and continuous basis for early warning judgments.

[0050] Specifically, in step S3, determining whether to trigger early warning monitoring includes: Step S34: Determine the parameter warning characterization value corresponding to each of the associated distribution box groups based on the parameter change characterization value and the parameter abnormality probability. Step S35: Determine whether to trigger early warning monitoring based on the comparison result between the parameter early warning characterization value corresponding to each of the associated distribution box groups and the preset early warning characterization value.

[0051] In implementation, for any associated distribution box group, the product of the parameter change characterization value corresponding to the associated distribution box group and the parameter abnormality probability is determined as the parameter early warning characterization value corresponding to the associated distribution box group. If the parameter early warning characterization value corresponding to the associated distribution box group is greater than the preset early warning characterization value, it is determined that early warning monitoring is triggered. If the parameter early warning characterization value corresponding to the associated distribution box group is less than or equal to the preset early warning characterization value, it is determined that early warning monitoring is not triggered. In practice, implementers can set preset warning values ​​based on actual conditions or the average value of parameter warning values ​​that have passed the qualification test in historical data. In a specific embodiment, the corresponding parameter warning values ​​are calculated based on the electrical and environmental parameters of each distribution box in each associated distribution box group that have passed the qualification test in the most recent N consecutive batches of historical data. The average value of the parameter warning values ​​is calculated and used as the preset warning value. In any batch, the data is continuous and passes the qualification test. If any data in any set of historical data fails the qualification test, it is considered the end of the batch. The data that fails the qualification test is not included in the data of that batch. In addition, the continuous time period corresponding to any batch is longer than the preset time period. In this way, N sets of test batch data are obtained. In order to meet the basic requirements of the statistical central limit theorem for sample size, ensure data reliability and stability, and avoid over-reliance on historical data leading to slow response, preferably, the value range of N is set to 30 to 50.

[0052] Specifically, this invention obtains a parameter warning characterization value by fusing parameter change characterization values ​​and parameter anomaly probabilities. This simultaneously considers current trends and historical anomaly probabilities, achieving a dual-dimensional risk assessment and improving warning reliability. By comparing the warning characterization value with a preset warning characterization value to determine whether a warning is triggered, a tiered and intelligent warning mechanism is implemented, avoiding frequent invalid warnings and ensuring that high-risk conditions are identified promptly, balancing monitoring efficiency and safety.

[0053] Step S4: If the early warning monitoring is triggered, the current electrical parameters and current environmental parameters of each distribution box are obtained to determine the parameter monitoring characterization value corresponding to each associated distribution box group. Specifically, in step S4, determining the parameter monitoring characteristic value corresponding to any of the associated distribution box groups includes: Step S41: Based on the comparison results between the current electrical parameters of each distribution box in the associated distribution box group and the preset electrical parameters, determine the electrical parameter fluctuation value corresponding to the associated distribution box group; Step S42: Based on the comparison results between the current environmental parameters of each distribution box in the associated distribution box group and the preset environmental parameters, determine the environmental parameter fluctuation value corresponding to the associated distribution box group. Step S43: Determine the parameter monitoring characterization value corresponding to the associated distribution box group based on the electrical parameter fluctuation value and the environmental parameter fluctuation value.

[0054] In implementation, for any distribution box within any associated distribution box group, all electrical parameters are normalized. The current electrical parameters KY1, KY2, ..., KY j , ..., KY m Preset electrical parameters KE1, KE2, ..., KE j , ..., KE m Then the electrical parameter fluctuation index KP corresponding to this distribution box is KP=(∑ m j=1 KY j ×KE j ) / (sqrt(∑ m j=1 (KY j ) 2 )×sqrt(∑ m j=1 (KE j ) 2 The average value of the electrical parameter fluctuation index corresponding to each distribution box is determined as the electrical parameter fluctuation value corresponding to the associated distribution box group. Implementers can set preset electrical parameters based on actual conditions or the average value of electrical parameters that have passed qualification tests in historical data.

[0055] It is understandable that, for any distribution box within any associated distribution box group, the environmental parameters are normalized, and the current environmental parameters are QY1, QY2, ..., QY i QY n Preset environmental parameters QE1, QE2, ..., QE i QE n Then the environmental parameter fluctuation index QP corresponding to this distribution box is (∑ n i=1 QY i ×QE i ) / (sqrt(∑ n i=1 (QY i ) 2 )×sqrt(∑ n i=1 (QE i ) 2 The average environmental parameter fluctuation index corresponding to each distribution box is determined as the environmental parameter fluctuation value corresponding to the associated distribution box group. Implementers can set preset environmental parameters based on actual conditions or the average environmental parameters that have passed compliance testing in historical data.

[0056] It is understandable that for any associated distribution box group, the parameter monitoring characterization value FB corresponding to the associated distribution box group is FB=u1×T1+u2×T2, where T1 is the electrical parameter fluctuation value corresponding to the associated distribution box group, and T2 is the environmental parameter fluctuation value corresponding to the associated distribution box group.

[0057] It is understandable that if the early warning monitoring is not triggered, the above steps S1-S3 will be repeated to re-perform the early warning monitoring judgment.

[0058] Specifically, this invention obtains electrical parameter fluctuation values ​​by comparing current electrical parameters with preset electrical parameters, which can intuitively reflect the degree to which the current electrical operating state deviates from the normal range, providing quantitative indicators for real-time monitoring. It also obtains environmental parameter fluctuation values ​​by comparing current environmental parameters with preset environmental parameters, enabling real-time quantification of the degree of environmental disturbance and providing environmental dimension support for determining the causes of anomalies. Finally, it integrates electrical parameter fluctuation values ​​and environmental parameter fluctuation values ​​to obtain parameter monitoring characterization values, achieving comprehensive quantification of the current operating state, facilitating subsequent rapid comparison and decision-making.

[0059] Step S5: Based on the comparison results of the parameter comparison threshold and parameter monitoring characterization value corresponding to each of the associated distribution box groups, a monitoring adjustment method is determined to monitor each of the distribution boxes in the target area. The monitoring adjustment method includes adjusting the monitoring cycle and re-determining the associated distribution box groups.

[0060] Specifically, in step S5, determining the monitoring adjustment method includes: Step S51: Based on the comparison results between the comparison thresholds of each parameter and the monitoring characterization values ​​of each parameter, determine the parameter monitoring deviation corresponding to each associated distribution box group; Step S52: Based on the comparison results of the parameter monitoring deviations and preset monitoring deviations of each associated distribution box group, several key distribution box groups are determined to determine the monitoring adjustment method.

[0061] In implementation, for any associated distribution box group, the absolute value of the difference between the parameter comparison threshold and the parameter monitoring characterization value corresponding to the associated distribution box group is determined as the first difference, and the ratio of the first difference to the parameter comparison threshold is determined as the parameter monitoring deviation corresponding to the associated distribution box group.

[0062] It is understood that for any associated distribution box group, if the parameter monitoring deviation corresponding to the associated distribution box group is greater than the preset monitoring deviation, then the associated distribution box group is identified as a critical distribution box group. Practitioners can set the preset monitoring deviation based on the actual situation or the average parameter monitoring deviation from historical data that has passed the qualification test. In a specific embodiment, the corresponding parameter monitoring deviation is calculated based on the electrical and environmental parameters of each distribution box in each associated distribution box group that passed the qualification test in the most recent M consecutive batches of historical data. The average of the parameter monitoring deviations is then used as the preset monitoring deviation. In any batch, the data is continuous and passes the qualification test. Data that fails the qualification test in any set of historical data is considered the end of the batch and is not included in that batch. This yields M sets of batch data. To meet the basic requirements of the Central Limit Theorem for sample size, ensure data reliability and stability, and avoid over-reliance on historical data leading to slow response, preferably, the value of M is set to 30–50.

[0063] Specifically, in step S52, the monitoring and adjustment method is determined based on the comparison between the number of key distribution box groups and the preset number, wherein... When the number of key distribution boxes is less than the preset number, the monitoring adjustment method is determined to be adjusting the monitoring cycle; If the number of key distribution box groups is greater than or equal to the preset number, the monitoring and adjustment method is determined to be to redetermine the associated distribution box groups.

[0064] In practice, when the number of key distribution box groups is small, the anomaly is localized and can be improved by adjusting the monitoring cycle to increase sampling accuracy. When the number of key distribution box groups is large, it indicates that the original grouping structure has failed and the association relationship needs to be redefined to restore grouping consistency. The implementers can set a preset number based on the actual situation. Preferably, the preset number is set to 1 / 3 to 1 / 4 of the total number of associated distribution box groups.

[0065] Specifically, this invention obtains the parameter monitoring deviation by comparing the parameter comparison threshold with the parameter monitoring characterization value, which can accurately calculate the deviation between the actual monitoring result and the expected standard, providing a quantitative basis for adjusting the monitoring strategy. Based on the parameter monitoring deviation, key distribution box groups are selected, and the adjustment method is selected based on the number of key distribution box groups, which can realize the adaptive optimization of the monitoring strategy.

[0066] Specifically, adjusting the monitoring cycle includes: Step S53: Based on the comparison results of the parameter monitoring deviation and the preset monitoring deviation of each key distribution box group, determine the parameter adjustment coefficient of each key distribution box group. Step S54: Determine the target monitoring period based on the parameter adjustment coefficients and initial monitoring period corresponding to each of the key distribution box groups, so as to adjust the monitoring period.

[0067] In implementation, for any associated distribution box group, the ratio of the preset monitoring deviation to the parameter monitoring deviation corresponding to the associated distribution box group is determined as the parameter adjustment coefficient corresponding to the associated distribution box group. The product of the parameter adjustment coefficient corresponding to the associated distribution box group and the initial monitoring cycle is determined as the target monitoring cycle corresponding to the associated distribution box group. Then, the monitoring cycle of each distribution box in the associated distribution box group is adjusted to the target monitoring cycle.

[0068] This invention implements unified monitoring based on associated distribution box groups. Distribution boxes with similar operating characteristics and environmental conditions are grouped together, enabling differentiated and refined management of the distribution boxes. The same initial monitoring cycle is used within the same associated group to ensure synchronized data acquisition timing for each distribution box. Targeted configuration of basic monitoring strategies can be achieved, improving monitoring flexibility and efficiency. Parameter comparison thresholds are determined based on historical electrical and environmental parameters of each distribution box within the associated group, aligning with the actual operating conditions of the distribution boxes within the group, improving threshold adaptability, and avoiding misjudgments caused by fixed thresholds. By determining the parameter anomaly probability of each associated distribution box group, the probability value of the current state of the distribution boxes deviating from the normal state is quantified, improving the accuracy of anomaly detection. Parameter change characterization values ​​quantify the parameter fluctuation trend and degree of abrupt change within a preset time period. The parameter change characterization values ​​and parameter anomaly probabilities are combined for joint judgment, taking into account both dynamic parameter change trends and historical anomaly possibilities, achieving a comprehensive risk assessment from two dimensions. This can promptly capture gradual hidden dangers while avoiding ineffective warnings, improving the rationality and sensitivity of the early warning mechanism. Under the condition of triggering early warning monitoring, the system strengthens the collection of all current parameters and forms parameter monitoring characterization values, realizing accurate quantification of the real-time operating status of the distribution box and providing real-time data support for subsequent monitoring and analysis. By comparing the parameter comparison thresholds and parameter monitoring characterization values ​​corresponding to the associated distribution box groups, the system adaptively selects to adjust the monitoring cycle or re-divide the monitoring adjustment methods of the associated distribution box groups. It can flexibly optimize the monitoring strategy according to the actual operating deviation, reasonably adjust the monitoring frequency to allocate monitoring resources when there are local anomalies, and regroup to optimize the monitoring architecture when there are overall anomalies. While ensuring the safe operation of the distribution box, it can improve the monitoring flexibility and the accuracy of anomaly judgment.

[0069] The technical solution of the present invention has been described above with reference to the preferred embodiments shown in the accompanying drawings. However, it will be readily understood by those skilled in the art that the scope of protection of the present invention is obviously not limited to these specific embodiments. Without departing from the principles of the present invention, those skilled in the art can make equivalent changes or substitutions to the relevant technical features, and the technical solutions after these changes or substitutions will all fall within the scope of protection of the present invention.

Claims

1. A remote monitoring method for low-voltage distribution boxes based on big data analysis, characterized in that, include: Real-time monitoring of electrical and environmental parameters of several distribution boxes within the target area is used to identify several associated distribution box groups. Each associated distribution box group includes several distribution boxes, and the initial monitoring cycle of each distribution box in the same group is the same. Based on the historical electrical parameters and historical environmental parameters of each distribution box in each of the associated distribution box groups, the parameter comparison threshold corresponding to each associated distribution box group is determined, and the parameter anomaly probability corresponding to each associated distribution box group is determined. Based on the changes in electrical parameters and environmental parameters of each distribution box within a preset time period, the parameter change characterization value corresponding to each associated distribution box group is determined, and whether to trigger early warning monitoring is determined based on the parameter change characterization value and the parameter anomaly probability. If an early warning monitoring is triggered, the current electrical parameters and current environmental parameters of each of the aforementioned distribution boxes are obtained to determine the parameter monitoring characterization values ​​corresponding to each of the associated distribution box groups. The monitoring adjustment method is determined based on the comparison results of the parameter comparison threshold and the parameter monitoring characterization value corresponding to each of the associated distribution box groups, so as to monitor each of the distribution boxes in the target area. The monitoring adjustment method includes adjusting the monitoring cycle and redetermining the associated distribution box groups.

2. The method for remote monitoring of low-voltage distribution boxes based on big data analysis according to claim 1, characterized in that, Determine several of the aforementioned associated distribution box groups, including: Based on the changes in electrical parameters of each distribution box within the target time period, construct the target electrical parameter change curve for each distribution box to determine the electrical difference range for each distribution box; Based on the changes in environmental parameters of each distribution box within the target time period, construct the target environmental parameter change curve for each distribution box to determine the environmental fluctuation range for each distribution box. Based on the comparison results of each of the electrical difference intervals and each of the environmental fluctuation intervals, several of the associated distribution box groups are determined.

3. The remote monitoring method for low-voltage distribution boxes based on big data analysis according to claim 2, characterized in that, Determining the parameter comparison threshold for any of the associated distribution box groups includes: Based on the historical electrical parameters of each distribution box in the associated distribution box group, the historical electrical reference corresponding to each associated distribution box group is determined, so as to determine the electrical parameter characterization value corresponding to the associated distribution box group; Based on the historical environmental parameters of each distribution box in the associated distribution box group, the historical environmental benchmark corresponding to each associated distribution box group is determined, so as to determine the environmental parameter characterization value corresponding to the associated distribution box group; The parameter comparison threshold corresponding to the associated distribution box group is determined based on the electrical parameter characterization value and the environmental parameter characterization value.

4. The method for remote monitoring of low-voltage distribution boxes based on big data analysis according to claim 3, characterized in that, Determining the probability of parameter anomalies for any of the associated distribution box groups includes: Based on the comparison results between the historical electrical reference corresponding to the associated distribution box group and the historical electrical parameters of each distribution box in the associated distribution box group, the deviation probability of the electrical parameters corresponding to the associated distribution box group is determined. Based on the comparison results between the historical environmental benchmark corresponding to the associated distribution box group and the historical environmental parameters of each distribution box in the associated distribution box group, the deviation probability of the environmental parameters corresponding to the associated distribution box group is determined. The abnormal parameter probability of the associated distribution box group is determined based on the deviation probability of the electrical parameters and the deviation probability of the environmental parameters.

5. The remote monitoring method for low-voltage distribution boxes based on big data analysis according to claim 4, characterized in that, Determining the parameter change characterization value corresponding to any of the associated distribution box groups includes: Based on the changes in electrical parameters of each distribution box in the associated distribution box group within a preset time period, construct the associated electrical parameter change curve corresponding to the associated distribution box group to determine the comprehensive electrical change index corresponding to the associated distribution box group; Based on the changes in environmental parameters of each distribution box in the associated distribution box group within a preset time period, construct the associated environmental parameter change curve corresponding to the associated distribution box group to determine the comprehensive environmental change index corresponding to the associated distribution box group; The parameter change characterization values ​​corresponding to the associated distribution box group are determined based on the comprehensive electrical change index and the comprehensive environmental change index.

6. The method for remote monitoring of low-voltage distribution boxes based on big data analysis according to claim 5, characterized in that, Determining whether early warning monitoring has been triggered includes: Based on the parameter change characterization value and the abnormal probability of each parameter, determine the parameter early warning characterization value corresponding to each associated distribution box group; Whether to trigger early warning monitoring is determined based on the comparison results between the parameter early warning characterization value corresponding to each of the associated distribution box groups and the preset early warning characterization value.

7. The method for remote monitoring of low-voltage distribution boxes based on big data analysis according to claim 6, characterized in that, Determining the parameter monitoring characteristic value corresponding to any of the associated distribution box groups includes: Based on the comparison results between the current electrical parameters of each distribution box in the associated distribution box group and the preset electrical parameters, the fluctuation value of the electrical parameters corresponding to the associated distribution box group is determined. Based on the comparison results between the current environmental parameters of each distribution box in the associated distribution box group and the preset environmental parameters, the fluctuation value of the environmental parameters corresponding to the associated distribution box group is determined. The parameter monitoring characterization values ​​corresponding to the associated distribution box group are determined based on the fluctuation values ​​of the electrical parameters and the fluctuation values ​​of the environmental parameters.

8. The remote monitoring method for low-voltage distribution boxes based on big data analysis according to claim 7, characterized in that, Determining the monitoring adjustment method includes: Based on the comparison results between the comparison threshold of each parameter and the monitoring characterization value of each parameter, the parameter monitoring deviation corresponding to each associated distribution box group is determined. Based on the comparison results of the parameter monitoring deviations of each associated distribution box group with the preset monitoring deviations, several key distribution box groups are identified to determine the monitoring adjustment method.

9. The method for remote monitoring of low-voltage distribution boxes based on big data analysis according to claim 8, characterized in that, The monitoring and adjustment method is determined based on the comparison between the number of key distribution box groups and the preset number, wherein... When the number of key distribution boxes is less than the preset number, the monitoring adjustment method is determined to be adjusting the monitoring cycle; If the number of key distribution box groups is greater than or equal to the preset number, the monitoring and adjustment method is determined to be to redetermine the associated distribution box groups.

10. The remote monitoring method for low-voltage distribution boxes based on big data analysis according to claim 9, characterized in that, Adjusting the monitoring cycle, including: Based on the comparison results of the parameter monitoring deviation and the preset monitoring deviation of each key distribution box group, the parameter adjustment coefficient of each key distribution box group is determined. The target monitoring period is determined based on the parameter adjustment coefficients and initial monitoring period corresponding to each of the key distribution box groups, so as to adjust the monitoring period.

Citation Information

Patent Citations

  • Remote monitoring method of distribution box and distribution box

    CN120433454A