Search

CN-122017419-A - Electrical appliance electricity utilization safety detection method, server, medium and program product

CN122017419ACN 122017419 ACN122017419 ACN 122017419ACN-122017419-A

Abstract

The application provides an electrical appliance electricity utilization safety detection method, a server, a medium and a program product, and relates to the technical field of electric digital data processing. And extracting and calculating the characteristics of a period difference value, a period median value and the like by collecting current data of a plurality of sampling points of the target electrical appliance according to a set period. After current data of a set number of periods are obtained, the total number of sampling points is recorded, two period differential thresholds are determined by combining related features, and a larger value is taken as a target threshold. And comparing the period differential value with a target threshold value, marking the sampling points with 0 or 1, and calculating the ratio of the total number of marks to the total number of the sampling points. If the ratio is not smaller than the set dangerous ratio, determining that an arc exists, and sending the result to the receiving end. By implementing the method, the early detection sensitivity of arc faults can be improved, and the method has stronger identification capability particularly for hidden dangers such as intermittent arcs which are difficult to capture by the traditional method.

Inventors

  • YAN NANSI
  • CAO GUOQING

Assignees

  • 北京三圣凯瑞科技有限公司

Dates

Publication Date
20260512
Application Date
20260226

Claims (10)

  1. 1. An electrical appliance electricity utilization safety detection method is applied to a server and is characterized by comprising the following steps: Sampling point data of a plurality of sampling points in a target electrical appliance are obtained at intervals of a set period, and corresponding current data are extracted from the sampling point data; Calculating a period differential value, a period median value, a relative gravity center differential value and a period differential average value corresponding to each sampling point according to the current data; recording the total number of current sampling points when the current data in the set number of the periods are acquired; Determining a first periodic differential threshold based on the periodic median and the relative center of gravity differential, and determining a second periodic differential threshold based on the periodic differential average; Determining the larger value of the first period differential threshold value and the second period differential threshold value as a target period differential threshold value; determining whether the period differential value in each sampling point is greater than or equal to the target period differential threshold value; If yes, marking the sampling point as a number 1, and if not, marking the sampling point as a number 0; Counting the total number of marks of all the sampling points, and calculating the ratio of the total number of marks to the total number of the sampling points; If the ratio is larger than or equal to the set dangerous ratio, determining that the electric arcs exist in the set number of periods, and sending an electric arc detection result to a receiving end.
  2. 2. The method of claim 1, wherein calculating the period differential value, the period median value, the relative center of gravity differential, and the period differential average value for each of the sampling points from the current data comprises: Acquiring first current data in sampling points in a first period and second current data in sampling points in a second period, wherein the first period and the second period are adjacent; The specific calculation steps of the period differential value are as follows: Calculating a difference value between the first current data and the corresponding second current data, and taking an absolute value of the difference value to obtain the period difference value; the period median is obtained by calculating the average value of the maximum value and the minimum value of the current data in each period and taking the absolute value; the specific calculation steps of the relative gravity center difference are as follows: Calculating a first harmonic gravity center value of a first period and a second harmonic gravity center value of a second period, calculating a difference between the second harmonic gravity center value and the first harmonic gravity center value, dividing the difference by the first harmonic gravity center value, and obtaining an absolute value of the result; The period differential average value is obtained by calculating an average value of the period differential values of the sampling points in each period.
  3. 3. The method of claim 1, wherein the determining a first periodic differential threshold based on the periodic median and the relative center of gravity differential, and the determining a second periodic differential threshold based on the periodic differential average, comprises: acquiring a first discrimination coefficient and a second discrimination coefficient corresponding to the target electrical appliance through a preset differential coefficient mapping table; Calculating the product of the first discrimination coefficient, the period median and the relative gravity center difference to determine a first period difference threshold; and calculating the product of the second discrimination coefficient and the period differential average value to determine a second period differential threshold value.
  4. 4. The method of claim 3, wherein the obtaining the first discrimination coefficient and the second discrimination coefficient corresponding to the target electrical appliance through a preset differential coefficient mapping table, and the constructing method of the differential coefficient mapping table includes: recording critical time of arc generation of all electric appliances in multiple tests of different electric appliances under different powers and experimental period difference value of the critical time Median value of experimental period Difference of relative gravity center of experiment And experimental period differential average ; Respectively calculating the discrimination coefficients of different electrical appliances at the critical moment, wherein a specific calculation formula comprises: , wherein Is the first discrimination coefficient of the first set, Is the second discrimination coefficient.
  5. 5. The method of claim 1, further comprising, after the step of determining that an arc exists for the set number of the cycles if the ratio is equal to or greater than a set hazard ratio: Acquiring a historical arc event characteristic data table, wherein the historical arc event characteristic data table at least comprises sampling point serial numbers, and the period differential values, period differential average values, period median values, relative gravity center differential values and time stamps recorded by all the sampling points; Acquiring a historical arc event tag table, wherein the historical arc event tag table at least comprises a starting sequence number of a sampling point in each period, an ending sequence number of the sampling point and a tag of whether the sampling point is an arc event or not; And training the multi-dimensional characteristic data in the historical arc event characteristic data table serving as input data and the data in the historical arc event label table serving as output data through a convolutional neural network to obtain an arc determination model.
  6. 6. The method of claim 1, further comprising, after the step of determining that an arc exists for the set number of the cycles: Inputting the characteristic data of the sampling points in the set number of the periods into an arc determination model to determine a first arc tag; And if the first arc label is yes, an arc early warning is sent out.
  7. 7. A method according to claim 1 or 3, wherein after the step of calculating the ratio of the total number of marks to the total number of sampling points, further comprising: If the ratio is smaller than the dangerous ratio, inputting the characteristic data of the sampling points in the set number of periods into an arc determination model to determine a second arc tag; if the second arc label is yes, a suspected arc early warning is sent out; acquiring an arc confirmation result of a user; If the arc confirmation result is false report, adding the characteristic data to the historical arc event characteristic data table, and updating the label of the corresponding sampling point in the historical arc event label table; training the updated historical arc event characteristic data table and the updated historical arc event label table through a convolutional neural network so as to update the arc determination model.
  8. 8. A server comprising one or more processors and memory coupled to the one or more processors, the memory to store computer program code comprising computer instructions that the one or more processors invoke to cause the server to perform the method of any of claims 1-7.
  9. 9. A computer readable storage medium comprising instructions which, when run on a server, cause the server to perform the method of any of claims 1-7.
  10. 10. A computer program product, characterized in that the computer program product, when run on a server, causes the server to perform the method according to any of claims 1-7.

Description

Electrical appliance electricity utilization safety detection method, server, medium and program product Technical Field The application relates to the technical field of electric digital data processing, in particular to an electric safety detection method, a server, a medium and a program product for electric appliances. Background With the popularization and intelligent development of electric appliances, the electric safety problem is increasingly prominent. Arc faults are one of the main causes of electrical fires, and concealment and burstiness thereof place extremely high demands on early detection. In the prior art, the mainstream arc detection relies on traditional hardware protection devices (such as circuit breakers and fuses), and the devices trigger protection mechanisms by detecting obvious fault signals such as overcurrent and overvoltage. However, the prior art can only passively respond after an arc fault is formed and causes a significant current abnormality, and it is difficult to accurately position a specific electrical appliance with potential danger for early warning in an arc germination stage (such as intermittent arc caused by poor contact), and the limitation causes significant potential safety hazards in the existing scheme, so that the safety requirement of a modern family diversified electricity utilization scene is difficult to meet. Disclosure of Invention The application provides an electrical appliance electricity utilization safety detection method, a server, a medium and a program product, which are used for solving the problems that in the prior art, only the current abnormality is obvious in passive response, early warning cannot be performed in advance, and potential danger cannot be accurately positioned, and realizing early detection, accurate early warning and intelligent judgment on the electrical appliance electricity utilization safety. The application provides an electric appliance electricity utilization safety detection method which is applied to a server and comprises the steps of obtaining sampling point data of a plurality of sampling points in a target electric appliance every set period, extracting corresponding current data from the sampling point data, calculating period difference values, period median values, relative gravity center differences and period difference average values corresponding to the sampling points according to the current data, recording the total number of the current sampling points when the current data in the set number of the periods are obtained, determining a first period difference threshold value based on the period median values and the relative gravity center differences, determining a second period difference threshold value based on the period difference average values, determining whether the larger value of the first period difference threshold value and the second period difference threshold value is the target period difference threshold value, determining whether the period difference value in the sampling points is larger than or equal to the target period difference threshold value, if yes, marking the sampling points as digital 1, if not, marking the sampling points as digital 0, counting the total number of marks of all the sampling points, calculating the total number of the marks, and comparing the total number of the marks with the total number of the sampling points, if the ratio is larger than the set number, determining that the dangerous arc is larger than the set number, and sending the dangerous arc to the set number to the receiving end. By adopting the technical scheme, a plurality of sampling point data are periodically acquired, current characteristics are extracted, and basic data are provided for subsequent analysis. The method is characterized in that the sudden change characteristic of current can be captured by calculating the period differential value (absolute value of the current differential value of adjacent periods), the sudden change characteristic is an important representation of arc faults, the period median reflects the current fluctuation range, the relative gravity center differential represents harmonic distribution change, the combination of the period median and the relative gravity center differential represents the distortion characteristic of current waveforms, and the period differential average value smoothes noise interference to enhance the characteristic stability. These characteristics complement each other, draw the electric current anomaly from different angles, promote the early detection sensitivity of electric arc trouble notably, especially have stronger recognition ability to intermittent electric arc such hidden danger that traditional method was difficult to catch. In combination with some embodiments of the first aspect, in some embodiments, the calculating a period difference value, a period median value, a relative barycentric difference and a period diffe