CN-121984230-A - Power distribution cabinet running state real-time monitoring method and system based on edge calculation

CN121984230ACN 121984230 ACN121984230 ACN 121984230ACN-121984230-A

Abstract

The invention provides a method and a system for monitoring the running state of a power distribution cabinet in real time based on edge calculation, and relates to the technical field of data processing, wherein the method comprises the following steps: the method comprises the steps of forming a state segment by taking a change relation of an operation state between adjacent sampling points as a connection condition, extracting a change direction sequence and a change amplitude sequence of each operation data in the state segment, determining an operation data type with the highest contribution degree as a main disturbance source, calculating disturbance intensity of the main disturbance source to obtain a state disturbance index, determining start-stop boundaries and peak shape parameters of each disturbance pulse unit, identifying boundary intervals and peak shape differences of the adjacent disturbance pulse units, fusing peak position migration directions and peak shape expansion directions of the disturbance pulse units, calculating a change trend of the operation state of the power distribution cabinet to obtain a state evolution index, analyzing the current operation state of the power distribution cabinet to obtain operation state judgment data. According to the invention, the state judgment is carried out on the edge side of the power distribution cabinet, so that the running state of the power distribution cabinet can be analyzed in real time.

Inventors

CHEN SICHAO
Hong can
Liu Mixiu

Assignees

亿华平电气有限公司

Dates

Publication Date: 20260505
Application Date: 20260407

Claims (10)

1. The method for monitoring the running state of the power distribution cabinet in real time based on edge calculation is characterized by comprising the following steps of: Acquiring an operation data set of the operation state of the power distribution cabinet, and forming a state fragment by taking the change relation of the operation state between adjacent sampling points as a connection condition to obtain a state fragment set; according to the state fragment set, extracting a change direction sequence and a change amplitude sequence of each operation data in the state fragment, and identifying the synchronization degree of a change relation in the state fragment to obtain fragment consistency data; determining the contribution degree of each operation data in the state fragment to the consistency according to the fragment consistency data, and determining the operation data type with the highest contribution degree as a main disturbance source to obtain disturbance source identification data; According to the disturbance source identification data, the direction turning times, the amplitude mutation times and the continuous offset length of the main disturbance source in the state segment are identified, and the disturbance intensity of the main disturbance source is calculated to obtain a state disturbance index; decomposing a state disturbance index in a continuous time interval into a plurality of disturbance pulse units according to a local peak shape structure, and determining start-stop boundaries and peak shape parameters of each disturbance pulse unit to obtain disturbance pulse data; According to the disturbance pulse data, identifying boundary intervals and peak shape differences of adjacent disturbance pulse units, and fusing a peak position migration direction and a peak shape expansion direction of the disturbance pulse units to obtain disturbance evolution direction data; Calculating the change trend of the running state of the power distribution cabinet according to the disturbance evolution direction data to obtain a state evolution index; and carrying out edge side state merging according to the state evolution index, analyzing the current running state of the power distribution cabinet, and obtaining running state judgment data.
2. The method for monitoring the operation state of the power distribution cabinet based on edge calculation according to claim 1, wherein the steps of extracting the sequence of the change direction and the sequence of the change amplitude of each operation data in the state segment according to the state segment set, and identifying the synchronization degree of the change relation in the state segment to obtain the segment consistency data comprise the following steps: Determining the time boundary of each state segment according to the state segment set, and intercepting a sampling value subsequence of each operation data in the state segment based on the time boundary to obtain a segment sampling data set; Calculating the differential value of adjacent sampling values of each operation data according to the fragment sampling data set, and generating a change direction mark according to the sign of the differential value to obtain a change direction sequence; According to the segment sampling data set, carrying out interval mapping on differential values of adjacent sampling values of each operation data, and mapping the differential values into amplitude marks to obtain a variation amplitude sequence; According to the change direction sequence and the change amplitude sequence, identifying whether the direction and the amplitude change of each operation data at the same sampling point are consistent or not, and obtaining an index consistency judging result; and counting the number of sampling points meeting index consistency in the state fragments according to the index consistency judging result, and calculating the degree of synchronization of the change relation in the state fragments to obtain fragment consistency data.
3. The method for monitoring the operation state of the power distribution cabinet in real time based on edge calculation according to claim 2, wherein the step of identifying the number of direction turning times, the number of amplitude mutation times and the continuous offset length of the main disturbance source in the state segment according to the disturbance source identification data, and calculating the disturbance intensity of the main disturbance source to obtain the state disturbance index comprises the following steps: according to the direction turning times and the amplitude mutation times of the main disturbance source in the state segment, calculating the structural complexity degree of disturbance of the main disturbance source in the state segment to obtain a turning mutation association; According to the continuous offset length of the main disturbance source in the state segment and the number of sampling points in the state segment, calculating the continuous degree of disturbance of the main disturbance source in the state segment to obtain a continuous offset enhancement item; according to the differential values of adjacent sampling points of the main disturbance source in the state segment, calculating the coupling relation between the disturbance intensity and the complexity degree of the main disturbance source in the state segment to obtain an amplitude structure interaction item; And carrying out fusion calculation on the flip mutation association item, the continuous offset enhancement item and the amplitude structure interaction item, and calculating the comprehensive disturbance intensity of the main disturbance source in the state segment to obtain a state disturbance index.
4. The method for monitoring the operation state of a power distribution cabinet based on edge calculation according to claim 3, wherein the method for obtaining the disturbance pulse data by decomposing the state disturbance index in the continuous time interval into a plurality of disturbance pulse units according to the local peak shape structure and determining the start-stop boundary and peak shape parameters of each disturbance pulse unit comprises the following steps: according to the state disturbance indexes in the continuous time interval, a state disturbance index sequence is constructed according to a time sequence, and the position where the change direction of the state disturbance index is switched is identified to obtain trend turning point data; dividing state disturbance index intervals between adjacent trend turning points according to the trend turning point data, and determining each index interval as a disturbance pulse unit to obtain a disturbance pulse unit set; According to the disturbance pulse unit set, determining the starting index and the ending index of each disturbance pulse unit as starting and stopping boundaries, and extracting the peak position and the peak size in the disturbance pulse unit to obtain pulse characteristic data; And determining the distribution characteristics of the state disturbance in the continuous time interval according to the start-stop boundary and the pulse characteristic data to obtain disturbance pulse data.
5. The method for monitoring the operation state of a power distribution cabinet based on edge calculation according to claim 4, wherein the method for identifying the boundary interval and the peak shape difference of adjacent disturbance pulse units according to disturbance pulse data, and fusing the peak position migration direction and the peak shape expansion direction of the disturbance pulse units to obtain disturbance evolution direction data comprises the following steps: according to the disturbance pulse data, calculating the time interval between adjacent disturbance pulse units to obtain pulse boundary interval data; Comparing the peak position change and the peak size change of adjacent disturbance pulse units according to the disturbance pulse data to obtain peak shape difference data; according to the pulse boundary interval data and the peak shape difference data, identifying the peak position migration direction of the adjacent disturbance pulse units in the time dimension and the peak shape expansion direction of the amplitude dimension, and obtaining pulse migration characteristic data; and according to the pulse migration characteristic data, fusing the migration direction and the expansion direction of the adjacent disturbance pulse units, determining the evolution trend of disturbance in a continuous time interval, and obtaining disturbance evolution direction data.
6. The method for monitoring the operation state of the power distribution cabinet in real time based on edge calculation according to claim 5, wherein calculating the change trend of the operation state of the power distribution cabinet according to disturbance evolution direction data to obtain a state evolution index comprises: according to disturbance evolution direction data, calculating whether disturbance directions in adjacent time intervals are consistent or not, and determining a continuation relation of the disturbance evolution directions in continuous time intervals to obtain evolution continuity items; Calculating the proportion of the peak position change relative to the pulse width change according to the disturbance pulse data, and determining the degree of synergy between the migration behavior and the expansion behavior of disturbance to obtain a migration expansion coupling item; calculating the joint strength between the peak value size change and the pulse width change according to the disturbance pulse data to obtain an evolution driving item; And fusing the evolution coherent item, the migration expansion coupling item and the evolution driving item, and calculating the change trend of the running state of the power distribution cabinet in a continuous time interval to obtain a state evolution index.
7. The method for monitoring the operation state of the power distribution cabinet in real time based on edge calculation according to claim 6, wherein the step of merging the edge states according to the state evolution index, analyzing the current operation state of the power distribution cabinet to obtain the operation state judgment data comprises the steps of: according to the state evolution index in the continuous time interval, constructing a change process of the state evolution index in the time dimension as an evolution track; According to the evolution track, analyzing the turning characteristics of the state evolution index in a continuous time interval, and identifying evolution nodes from stable to aggravated and from aggravated to stable in state evolution to obtain evolution node data; segment merging is carried out on the evolution track according to the evolution node data, and time intervals with the same evolution node are merged into the same running state segment to obtain running state segment data; and comprehensively judging the characteristics of each operation state segment according to the operation state segment data, and identifying the current operation state of the power distribution cabinet to obtain operation state judgment data.
8. A real-time monitoring system for the operation state of a power distribution cabinet based on edge calculation, characterized in that it is adapted to perform the method according to any one of claims 1 to 7, said system comprising: the data acquisition module is used for acquiring an operation data set of the operation state of the power distribution cabinet, forming a state fragment by taking the change relation of the operation state between adjacent sampling points as a connection condition, and obtaining a state fragment set; The synchronous analysis module is used for extracting a change direction sequence and a change amplitude sequence of each operation data in the state fragment according to the state fragment set, and identifying the synchronous degree of the change relation in the state fragment to obtain fragment consistency data; The disturbance identification module is used for determining the contribution degree of each piece of operation data in the state fragment to the consistency according to the fragment consistency data, and determining the type of the operation data with the highest contribution degree as a main disturbance source to obtain disturbance source identification data; The disturbance intensity module is used for identifying the direction turning times, the amplitude mutation times and the continuous offset length of the main disturbance source in the state segment according to the disturbance source identification data, and calculating the disturbance intensity of the main disturbance source to obtain a state disturbance index; the disturbance pulse module is used for decomposing a state disturbance index in a continuous time interval into a plurality of disturbance pulse units according to a local peak shape structure, and determining start-stop boundaries and peak shape parameters of each disturbance pulse unit to obtain disturbance pulse data; The disturbance evolution module is used for identifying boundary intervals and peak shape differences of adjacent disturbance pulse units according to disturbance pulse data, and fusing peak position migration directions and peak shape expansion directions of the disturbance pulse units to obtain disturbance evolution direction data; The trend analysis module is used for calculating the change trend of the running state of the power distribution cabinet according to the disturbance evolution direction data to obtain a state evolution index; the state judging module is used for carrying out edge side state merging according to the state evolution index, analyzing the current running state of the power distribution cabinet and obtaining running state judging data.
9. A computing device, comprising: One or more processors; Storage means for storing one or more programs which when executed by the one or more processors cause the one or more processors to implement the method of any of claims 1to 7.
10. A computer readable storage medium, characterized in that the computer readable storage medium has stored therein a program which, when executed by a processor, implements the method according to any of claims 1 to 7.

Description

Power distribution cabinet running state real-time monitoring method and system based on edge calculation Technical Field The invention relates to the technical field of data processing, in particular to a method and a system for monitoring the running state of a power distribution cabinet in real time based on edge calculation. Background In the existing power distribution automation system, the operation state of the power distribution cabinet is monitored, a temperature sensor, a current sensor, a voltage sensor and a switching value acquisition device are arranged in the power distribution cabinet, multi-dimensional state parameters reflecting the operation working condition of the power distribution cabinet are acquired, and the acquired state parameters are summarized by a field control unit. The on-site control unit generally uploads the collected state parameters to the background monitoring platform in a wired or wireless communication mode, the background monitoring platform analyzes and judges the running state of the power distribution cabinet according to a preset threshold value or a rule model, alarm information is generated when an abnormal state is detected, and a control instruction is issued to the power distribution cabinet or a related execution unit, so that state monitoring, fault early warning and intelligent control of the power distribution cabinet are realized. The analysis and judgment of the running state of the power distribution cabinet are mainly concentrated on a background monitoring platform, when the power distribution cabinet is in an edge scene such as an industrial park and a branch node of a transformer substation, the running state parameters need to be transmitted through a communication link to participate in the state judgment, abnormal states which change rapidly in a short time appear in the power distribution cabinet, for example, when the local temperature in the cabinet rises continuously in a short time, the state parameters acquired by the background monitoring platform may lag behind the actual running state of the power distribution cabinet due to transmission delay, so that the transient abnormal changes of the power distribution cabinet at the edge side may not be reflected timely after the triggering time of a fault early warning or control instruction is delayed. Disclosure of Invention The invention aims to provide a method and a system for monitoring the running state of a power distribution cabinet in real time based on edge calculation, and aims to solve the problems in the background art. In order to solve the technical problems, the technical scheme of the invention is as follows: in a first aspect, a method for monitoring an operation state of a power distribution cabinet in real time based on edge calculation includes: Acquiring an operation data set of the operation state of the power distribution cabinet, and forming a state fragment by taking the change relation of the operation state between adjacent sampling points as a connection condition to obtain a state fragment set; according to the state fragment set, extracting a change direction sequence and a change amplitude sequence of each operation data in the state fragment, and identifying the synchronization degree of a change relation in the state fragment to obtain fragment consistency data; determining the contribution degree of each operation data in the state fragment to the consistency according to the fragment consistency data, and determining the operation data type with the highest contribution degree as a main disturbance source to obtain disturbance source identification data; According to the disturbance source identification data, the direction turning times, the amplitude mutation times and the continuous offset length of the main disturbance source in the state segment are identified, and the disturbance intensity of the main disturbance source is calculated to obtain a state disturbance index; decomposing a state disturbance index in a continuous time interval into a plurality of disturbance pulse units according to a local peak shape structure, and determining start-stop boundaries and peak shape parameters of each disturbance pulse unit to obtain disturbance pulse data; According to the disturbance pulse data, identifying boundary intervals and peak shape differences of adjacent disturbance pulse units, and fusing a peak position migration direction and a peak shape expansion direction of the disturbance pulse units to obtain disturbance evolution direction data; Calculating the change trend of the running state of the power distribution cabinet according to the disturbance evolution direction data to obtain a state evolution index; and carrying out edge side state merging according to the state evolution index, analyzing the current running state of the power distribution cabinet, and obtaining running state judgment data. Further, according to the state fragment set, e