CN117892246B - Data processing method for intelligent switch cabinet - Google Patents
Data processing method for intelligent switch cabinet Download PDFInfo
- Publication number
- CN117892246B CN117892246B CN202410276465.3A CN202410276465A CN117892246B CN 117892246 B CN117892246 B CN 117892246B CN 202410276465 A CN202410276465 A CN 202410276465A CN 117892246 B CN117892246 B CN 117892246B
- Authority
- CN
- China
- Prior art keywords
- current data
- abnormal
- degree
- data point
- points
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 238000003672 processing method Methods 0.000 title claims abstract description 11
- 230000002159 abnormal effect Effects 0.000 claims abstract description 96
- 238000000034 method Methods 0.000 claims abstract description 42
- 238000001514 detection method Methods 0.000 claims abstract description 12
- 230000005856 abnormality Effects 0.000 claims description 53
- 238000012937 correction Methods 0.000 claims description 11
- 238000004364 calculation method Methods 0.000 claims description 3
- 238000012545 processing Methods 0.000 claims description 3
- 238000007405 data analysis Methods 0.000 abstract description 2
- 238000005516 engineering process Methods 0.000 description 6
- 238000004458 analytical method Methods 0.000 description 2
- 238000012423 maintenance Methods 0.000 description 2
- 238000004891 communication Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 230000007613 environmental effect Effects 0.000 description 1
- 238000005259 measurement Methods 0.000 description 1
- 238000004377 microelectronic Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000005070 sampling Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
Landscapes
- Testing And Monitoring For Control Systems (AREA)
Abstract
The invention relates to the technical field of data analysis, in particular to a data processing method for an intelligent switch cabinet, which comprises the following steps: the method comprises the steps of obtaining current data and temperature data in a period of time of an intelligent switch cabinet, calculating the abnormal expression degree of each current data point according to the time span difference and the current difference between every two adjacent extreme points in the local range of each current data point, calculating the noise expression degree according to the abnormal expression degree and the temperature data of data on two sides of the current data point, correcting the abnormal expression degree by utilizing the noise expression degree, carrying out abnormal detection on the abnormal expression degree corrected by all current data points through an isolated forest algorithm to obtain an abnormal score value of each current data point, judging whether the current data is abnormal or not through the abnormal score value, controlling the intelligent switch cabinet, and improving the accuracy of abnormal detection of the current data of the switch cabinet.
Description
Technical Field
The present invention relates generally to the field of data analysis technology. More particularly, the invention relates to a data processing method for an intelligent switch cabinet.
Background
The intelligent switch cabinet is used as important control equipment of the power system, advanced technologies such as computer technology, microelectronic technology, communication technology and sensing technology are combined, main parameters of all components of the system are remotely measured through various sensors, centralized control and intelligent operation and maintenance of all power distribution equipment are achieved, the operation automation level of a transformer substation is effectively improved, and safe, reliable, economical and stable operation of the power system is ensured.
In order to ensure the normal operation of the intelligent switch cabinet, the current data in the acquisition switch cabinet is often required to be subjected to abnormality detection so as to find out problems in time and process, and the current method for detecting the abnormality of the current data in the switch cabinet adopts an isolated forest algorithm which is based on the idea of a tree structure, and abnormal values are easier to be isolated on a longer path by isolating normal samples on a shorter path of the tree structure, so that the abnormality in the current data is detected.
However, in the scene of the intelligent switch cabinet, due to the influence of external environmental problems and the current sensor, some noise exists in the collected current data, so that in the process of using an isolated forest to perform abnormality detection, the current data point with a higher abnormality score value may not be abnormal data, meanwhile, in the intelligent switch cabinet, the change of a load also causes the change of the current magnitude, if the collected current data point is directly used for performing abnormality detection through an isolated forest algorithm, the current data point generated by the change of the current magnitude due to the change of the load may be detected as abnormal, or the noise data point in the current is detected as abnormal, the accuracy of a data abnormality detection result is affected, and the switch cabinet cannot be accurately controlled.
Disclosure of Invention
In order to solve one or more of the technical problems, the invention provides a data processing method for an intelligent switch cabinet, which improves the accuracy of detecting the abnormality of the current data of the switch cabinet and can accurately control the switch cabinet. The technical scheme is as follows: a data processing method for an intelligent switch cabinet comprises the following steps:
Acquiring current data and temperature data of the intelligent switch cabinet within a period of time;
setting a local range of each current data point in the current data according to a preset range, and calculating a plurality of extreme points in the local range by using a difference method;
Calculating the abnormal performance degree of each current data point based on the time span difference and the current difference between every two adjacent extreme points in the plurality of extreme points in the local range;
dividing the local range of each current data point into a left range and a right range, and respectively calculating the left abnormality degree and the right abnormality degree based on extreme points contained in the left range and the right range;
Obtaining noise performance degree of each current data point according to the left side abnormality degree, the right side abnormality degree and the temperature data in the local range of the current data point;
Correcting the abnormal expression degree by utilizing the noise expression degree to obtain the corrected abnormal expression degree of each current data point;
The abnormal expression degree of each current data point after correction is taken as a characteristic value, and the characteristic values of all the current data points are subjected to abnormal detection through an isolated forest algorithm to obtain an abnormal score value of each current data point;
Judging whether the current data is abnormal or not according to the abnormal score value, and controlling the intelligent switch cabinet according to whether the current data is abnormal or not.
Further, the noise performance degree is used for correcting the abnormal performance degree, so that the abnormal performance degree of each current data point after correction is obtained, and the abnormal performance degree of each current data point after correction meets the following relation:
In the/> For/>Abnormal expression degree after correction of each current data point,/>For/>Degree of abnormal manifestation of individual current data points,/>For/>Noise performance level of individual current data points,/>Is an exponential function based on a natural constant e.
Further, the abnormal performance degree of each current data point satisfies the following relation:
In the method, in the process of the invention, For/>Degree of abnormal manifestation of individual current data points,/>For preset weight,/>For/>Number of extreme points within a local range of individual current data points,/>For the total number of permutation and combination of every two adjacent extreme points, each combination comprises two first adjacent extreme points and two second adjacent extreme points,/>For/>Combinations of/>For time,/>Is the current value,/>For/>Two first adjacent extreme points in the combination,/>For/>Two second adjacent extreme points in each combination,/>For the time span between the two first adjacent extreme points,/>For the time span between the two second adjacent extreme points,/>For the difference of the current values between the two first adjacent extreme points,/>Is the difference in current value between the two second adjacent extreme points.
Further, setting a local range of each current data point in the current data according to a preset range, including:
And taking each current data point as a center, taking the current data points, M current data points on the left side and M current data points on the right side as local ranges of the current data points, wherein M is a preset value.
Further, the local range of each current data point is divided into a left range and a right range, and the method comprises the following steps:
and taking the M current data points on the left side and each current data point as a left side range, and taking the M current data points on the right side and each current data point as a right side range.
Further, the left side abnormality degree and the right side abnormality degree are calculated by the same method as the abnormality expression degree of each current data point.
Further, according to the left side abnormality degree and the right side abnormality degree and the temperature data in the local range of the current data points, the noise performance degree of each current data point is obtained, and the following relation is satisfied:
In the method, in the process of the invention, For/>Noise performance level of individual current data points,/>As an exponential function based on a natural constant e,/>For/>Degree of left abnormality of each current data point,/>For/>Degree of abnormality on right side of individual current data points,/>For/>Variance of temperature data over a period of time corresponding to a local range of the individual current data points.
Further, judging whether the current data has abnormality or not according to the abnormality score value, wherein the method comprises the following steps:
Presetting a score threshold;
If the current data has the current data point with the abnormal score value larger than or equal to the preset score threshold value, the current data has the abnormality, otherwise, the current data has no abnormality.
Further, the intelligent switch cabinet is controlled according to whether the current data has abnormality or not, and the method comprises the following steps:
If the current data is abnormal, the intelligent switch cabinet is controlled to stop operating, otherwise, the intelligent switch cabinet operates normally.
The invention has the following effects:
According to the invention, the abnormal performance degree of each current data point is calculated by analyzing the time span difference and the current value difference between the adjacent extreme values in the local range of the current data point, the abnormal performance degree of each current data point is used for representing the abnormal degree of the current data point, the local range of each current data point is divided into a left side range and a right side range, the abnormal performance of the current data on two sides of the current data point is judged, the influence of temperature is combined, the noise performance degree of the current data point is obtained, the abnormal performance degree of the current data point is corrected according to the noise performance degree, and the corrected current data point is subjected to isolated forest abnormality detection.
Drawings
The above, as well as additional purposes, features, and advantages of exemplary embodiments of the present invention will become readily apparent from the following detailed description when read in conjunction with the accompanying drawings. In the drawings, embodiments of the invention are illustrated by way of example and not by way of limitation, and like reference numerals refer to similar or corresponding parts and in which:
FIG. 1 is a schematic flow chart of the method of the present invention.
Detailed Description
The following description of the embodiments of the present invention will be made clearly and fully with reference to the accompanying drawings, in which it is evident that the embodiments described are some, but not all embodiments of the invention. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
Specific embodiments of the present invention are described in detail below with reference to the accompanying drawings.
Referring to fig. 1, a data processing method for an intelligent switch cabinet includes steps S1-S8, specifically as follows:
S1: and acquiring current data and temperature data of the intelligent switch cabinet within a period of time.
In the embodiment, time sequence current data and temperature data of the intelligent switch cabinet are respectively acquired through the current sensor and the temperature sensor, the acquisition frequency is set to be 10HZ, the current data and the temperature data of 5 minutes are acquired in a set mode, and the length of the acquisition time is specifically required to be set by oneself.
S2: setting a local range of each current data point in the current data according to a preset range, and calculating a plurality of extreme points in the local range by using a difference method.
Setting a local range of each current data point in the current data according to a preset range, wherein the local range comprises:
The current data point is taken as the center, the current data point, the left M current data points and the right M current data points are taken as the local range of the current data point, M is a preset value, M is set to be 10 in the embodiment, namely 21 current data points in total are taken as the local range of the current data point, and because the current data in a period, namely time sequence current data, are collected in the embodiment, a time sequence current curve graph can be drawn to analyze and calculate the current data in a more visual and convenient mode, the time sequence current curve graph takes the time as the horizontal axis, the current value as the vertical axis, and each time corresponds to one current data point.
The method comprises the steps of obtaining a plurality of extreme points in a local range, namely extreme points of current values, and specifically obtaining all the extreme points in the local range of current data through a difference method or other extreme point obtaining methods.
S3: and calculating the abnormal performance degree of each current data point based on the time span difference and the current difference between every two adjacent extreme points in the plurality of extreme points in the local range.
The abnormal performance degree of each current data point is calculated based on the time span difference and the current difference between every two adjacent extreme points in the plurality of extreme points in the local range, and the abnormal performance degree of each current data point meets the following relation:
In the method, in the process of the invention, For/>Degree of abnormal manifestation of individual current data points,/>For/>Number of extreme points within a local range of individual current data points,/>Meaning of/>The number of adjacent extremum point pairs in the local range of each current data point is defined as two adjacent extremum points as one adjacent extremum point pair, and if there are 1,2,3,4,5 total extremum points in the local range, there are 4 adjacent extremum point pairs, respectively 12, 23, 34, 45,/>The total number of permutation and combination for every two adjacent extreme points is defined as the number from the/>Combining all adjacent extremum point pairs within the local range of each current data point, optionally two adjacent extremum point pairs, such as combining extremum point pair 12 and extremum point pair 34 to obtain a first combination, wherein each combination comprises two first adjacent extremum points and two second adjacent extremum points, such as 1 and 2 respectively for the two first adjacent extremum points in the first combination and 3 and 4 respectively for the two second adjacent extremum points,/>For/>Combinations of/>For time,/>Is the current value,/>For/>Two first adjacent extreme points in the combination,/>For/>Two second adjacent extreme points in each combination,/>For the time span between the two first adjacent extreme points,/>For the time span between the two second adjacent extreme points,/>For the difference of the current values between the two first adjacent extreme points,/>For the difference in current values between the two second adjacent extreme points, then/>Then express the/>Consistency of time spans in individual permutation and combination,/>Represents the/>Consistency of current differences among the individual permutations.
In the formula:
an average first order difference representing the current difference between the extreme points in the local range;
an average first order difference representing a time span between adjacent extreme points in the local range;
Since the average first step difference is a small value for the time span and a large value for the current value, a weight is required to be set to prevent the similarity value over the time span from being too small to reduce the influence on the characteristic value, in this embodiment/> The empirical value is 0.7, which can be set by the user without limitation, but note/>The value of (2) should be in the range of 0 to 1.
It should be noted that, under the condition that the intelligent switch cabinet normally operates, the current data of the intelligent switch cabinet usually presents a regular waveform similar to a sine wave, and when the current data is abnormal, the current waveform may start to be distorted, so that a large difference exists between the waveform and the sine waveform, and therefore, the abnormal expression degree of the current data point can be calculated by analyzing whether the data change of the current data point in a local range presents the regular sine wave change, so as to represent the abnormal degree of the current data point.
If the data change of the current data point in the local range is to be analyzed, specific judgment is needed based on the characteristic of the sine wave, namely, one big characteristic of the sine wave is that the distance between adjacent extreme points is equal and the numerical value difference between the adjacent extreme points is equal, in this embodiment, if the current data collected in this embodiment does not have any abnormality, the time span between any two adjacent extreme points is the same and the difference value of the current values is the same in the time sequence current graph in S2, if the time span between every two adjacent extreme points is more equal and the difference value of the current values between every two adjacent extreme points is more equal, it is indicated that the current data in the local range of the current data point is similar to the change of the sine wave, the lower the abnormal expression degree of the current data points is, the higher the reverse is, so that the similarity of the distance between adjacent extreme points and the similarity between the extreme point differences can be reflected through the calculation, the more consistent the time span between the adjacent extreme points is indicated by the average first step difference of the time spans between the extreme points in the local range for the similarity of the distance between the extreme points, the better the similarity is, the similarity between the extreme point differences can be represented by the average first step difference of the current differences of the adjacent extreme points in the local range, and the smaller the average first step difference of the current differences of the adjacent extreme points is, the better the similarity is.
Further, if the similarity of the distances between adjacent extreme points in the local range is better, and the similarity of the difference values of the extreme points is better, it is explained that the change of the current data in the local range of the current data point is closer to the sine wave, and the regularity is better, the abnormal expression degree of the current data point is lower, so that the abnormal expression degree of the current data point is calculated by analyzing the similarity of the distances between the adjacent extreme points and the similarity between the difference values of the extreme points.
S4: dividing the local range of each current data point into a left range and a right range, and calculating the left abnormality degree and the right abnormality degree based on extreme points contained in the left range and the right range respectively.
The local range of each current data point is divided into a left side range and a right side range, specifically: each current data point and the left M current data points are taken as a left range, and each current data point and the right M current data points are taken as a right range.
The method for calculating the degree of abnormality of each current data point is the same as the method for calculating the degree of abnormality of each current data point in S3, except that the degree of abnormality of each current data point is calculated from adjacent extreme points in the entire local range, and the degree of abnormality of each current data point is calculated from adjacent extreme points in the left and right ranges in the local range according to the formula in S3, respectively.
S5: and obtaining the noise performance degree of each current data point according to the left side abnormality degree, the right side abnormality degree and the temperature data in the local range of the current data point.
Wherein the noise performance level of each current data point satisfies the following relationship:
In the method, in the process of the invention, For/>Noise performance level of individual current data points,/>As an exponential function based on a natural constant e,/>For/>The degree of abnormality to the left of the individual current data points, its negative exponent power/>Can characterize the/>The current data in the right range of the individual current data points is expressed as the extent of the sine wave,/>For/>The degree of abnormality on the right side of each current data point, its negative exponent power/>Can characterize the/>The current data in the right range of the individual current data points appear to be the extent of the sine wave, thus/>Can characterize the/>In the case of sine waves on the left and right sides of each current data point,Can reflect the/>The left and right sides of each current data point appear as a sine wave difference, and the smaller the value, the more/>The more uniform the sine wave behavior on the left and right sides of the individual current data points, the more/>The higher the probability that the individual current data points are noise, and therefore, the negative exponent power/>Then/>For/>Noise performance level of individual current data points,/>For current data points/>The variance of the temperature data points in the corresponding time period of the local range is used as the credibility of the noise performance degree, and the larger the variance is, the more severe the temperature change is, and the acuteness of the temperature change in the local range of the current data points can be reflected.
It should be noted that, the noise usually represents an outlier, and the noise in the current data may cause the change of the normal current data to lose the characteristic of the sine wave, that is, the abnormal performance degree of the current data point is calculated based on the characteristic of the sine wave in S3 to measure the deviation of the abnormal situation of the current data point, so that the analysis of the performance characteristic of the noise is required, and the correction of the abnormal performance degree of the current data point obtained in S3 in the subsequent step S5 is required.
Because noise is only expressed as outliers, the influence of the noise on surrounding data is small, namely, the data on two sides of the noise still presents a sine wave change rule, so that the consistency of sine wave conditions on two sides of a current data point, the degree of sine wave expression and the intensity of temperature change can be utilized to obtain the noise expression degree of the current data point, if the sine wave conditions on two sides of the current data point are more consistent, the probability that the current data point is normal data and noise data is larger, and the change of internal resistance of a current sensor is possibly caused by considering the change of temperature, so that the measurement accuracy is influenced, namely, the probability that the noise appears is possibly increased due to the change of temperature, normal data and noise data can be distinguished by utilizing the expression characteristics of the temperature, and if the data change of the temperature data in a time period corresponding to the local range of the current data point is more intense, the probability that the current data point is noise is larger is indicated, and otherwise the current data point is more likely to be normal data.
Since the abnormal representation degree of the current data point is obtained based on the analysis of the current data change in the local range of the sine wave characteristics, the smaller the abnormal representation degree of the current data point is, the more the current data of the current data point in the local range shows the sine wave change, therefore, the consistency of the sine wave conditions at two sides of the current data point is passed by utilizing the negative exponent power of the abnormal representation degree of the current data point in the embodimentEmbodying, by/>Reflecting the difference of sine waves at the left side and the right side of a current data point, wherein the smaller the value is, the more consistent the sine wave conditions at the two sides of the current data point are, the higher the consistency of the sine wave conditions at the two sides is, and the degree of the representation of the sine wave is passed/>Embodying,/>And/>The smaller the value of (2), the smaller the degree of abnormal manifestation on the left and right sides of the current data point, the/>The larger the value of (i) is, the better the degree of the sine wave performance on the left and right sides of the current data point is, and the larger the variance is, the more severe the temperature change is, i.e., the variance of the temperature data is represented in a period corresponding to the local range of the current data point is.
S6: and correcting the abnormal performance degree by utilizing the noise performance degree to obtain the corrected abnormal performance degree of each current data point.
If the current data point has higher noise performance degree, the probability of being noise is higher, namely, the current data point is not abnormal data, so the abnormal performance degree of the current data point should be reduced, and the correction of the abnormal performance degree should be larger, and the specific correction method is as follows:
In the method, in the process of the invention, For/>Abnormal expression degree after correction of each current data point,/>For/>Degree of abnormal manifestation of individual current data points,/>For/>Noise performance level of individual current data points, then/>I.e. the correction factor.
And (5) obtaining the corrected abnormal expression degree according to the method steps of S2-S5 for each current data point.
S7: and taking the corrected abnormal expression degree of each current data point as a characteristic value, and carrying out abnormal detection on the characteristic values of all the current data points through an isolated forest algorithm to obtain an abnormal score value of each current data point.
Based on the abnormal expression degree of each current data point, performing abnormal detection by using an isolated forest algorithm, wherein the abnormal detection comprises the following steps: obtaining 80 sub-sample sets from current data of 5 minutes by using simple random sampling, wherein each sub-sample set contains 70 current data points, respectively establishing 80 isolated trees (namely, 1 sub-sample set is used for establishing 1 isolated tree) by taking the corrected abnormal expression degree of the current data points as a characteristic value, and then obtaining the abnormal score value of each current data point by using a mode of calculating the abnormal score value in an isolated forest algorithm.
S8: judging whether the current data is abnormal or not according to the abnormal score value, and controlling the intelligent switch cabinet according to whether the current data is abnormal or not.
Judging whether the current data is abnormal or not according to the abnormal score value, wherein the method comprises the following steps:
the preset score threshold value, in this embodiment, the score threshold value 0.67 is an empirical value, which can be specifically set by itself, if the abnormal score value of the current data point in the current data is greater than or equal to the preset score threshold value, the current data is abnormal, otherwise, no abnormality exists.
The intelligent switch cabinet is controlled according to the judging result, and the method comprises the following steps:
If the current data is abnormal, controlling the intelligent switch cabinet to stop running, particularly, cutting off a circuit of the intelligent switch cabinet by using a circuit breaker to stop running and informing maintenance; otherwise, the intelligent switch cabinet is kept to normally operate without processing.
In the description of the present specification, the meaning of "a plurality", "a number" or "a plurality" is at least two, for example, two, three or more, etc., unless explicitly defined otherwise.
While various embodiments of the present invention have been shown and described herein, it will be obvious to those skilled in the art that such embodiments are provided by way of example only. Many modifications, changes, and substitutions will now occur to those skilled in the art without departing from the spirit and scope of the invention. It should be understood that various alternatives to the embodiments of the invention described herein may be employed in practicing the invention.
Claims (6)
1. The data processing method for the intelligent switch cabinet is characterized by comprising the following steps of:
Acquiring current data and temperature data of the intelligent switch cabinet within a period of time;
setting a local range of each current data point in the current data according to a preset range, and calculating a plurality of extreme points in the local range by using a difference method;
Calculating the abnormal performance degree of each current data point based on the time span difference and the current difference between every two adjacent extreme points in the plurality of extreme points in the local range;
dividing the local range of each current data point into a left range and a right range, and respectively calculating the left abnormality degree and the right abnormality degree based on extreme points contained in the left range and the right range;
Obtaining noise performance degree of each current data point according to the left side abnormality degree, the right side abnormality degree and the temperature data in the local range of the current data point;
Correcting the abnormal expression degree by utilizing the noise expression degree to obtain the corrected abnormal expression degree of each current data point;
The abnormal expression degree of each current data point after correction is taken as a characteristic value, and the characteristic values of all the current data points are subjected to abnormal detection through an isolated forest algorithm to obtain an abnormal score value of each current data point;
judging whether the current data is abnormal or not according to the abnormal score value, and controlling the intelligent switch cabinet according to whether the current data is abnormal or not;
the calculation method of the left side abnormality degree and the right side abnormality degree is the same as the calculation method of the abnormality expression degree of each current data point;
The abnormal performance degree of each current data point satisfies the following relation:
In the method, in the process of the invention, For/>Degree of abnormal manifestation of individual current data points,/>For preset weight,/>For/>Number of extreme points within a local range of individual current data points,/>For the total number of permutation and combination of every two adjacent extreme points, each combination comprises two first adjacent extreme points and two second adjacent extreme points,/>For/>Combinations of/>For time,/>Is the current value,/>For/>Two first adjacent extreme points in the combination,/>For/>Two second adjacent extreme points in each combination,/>For the time span between the two first adjacent extreme points,/>For the time span between the two second adjacent extreme points,For the difference of the current values between the two first adjacent extreme points,/>Is the difference of the current values between the two second adjacent extreme points;
Obtaining the noise performance degree of each current data point according to the left side abnormality degree, the right side abnormality degree and the temperature data in the local range of the current data point, wherein the noise performance degree of each current data point satisfies the following relation:
In the method, in the process of the invention, For/>Noise performance level of individual current data points,/>As an exponential function based on a natural constant e,For/>Degree of left abnormality of each current data point,/>For/>Degree of abnormality on right side of individual current data points,/>For/>Variance of temperature data over a period of time corresponding to a local range of the individual current data points.
2. The method for processing data for an intelligent switch cabinet according to claim 1, wherein the noise performance level is used to correct the abnormal performance level to obtain the corrected abnormal performance level of each current data point, and the corrected abnormal performance level of each current data point satisfies the following relation:
In the method, in the process of the invention, For/>Abnormal expression degree after correction of each current data point,/>For/>Degree of abnormal manifestation of individual current data points,/>For/>Noise performance level of individual current data points,/>Is an exponential function based on a natural constant e.
3. The data processing method for an intelligent switch cabinet according to claim 1, wherein setting the local range of each current data point in the current data according to a preset range comprises:
And taking each current data point as a center, taking the current data points, M current data points on the left side and M current data points on the right side as local ranges of the current data points, wherein M is a preset value.
4. A method for processing data for an intelligent switch cabinet according to claim 3, wherein the local range of each current data point is divided into a left range and a right range, and the method comprises the steps of:
and taking the M current data points on the left side and each current data point as a left side range, and taking the M current data points on the right side and each current data point as a right side range.
5. The data processing method for an intelligent switch cabinet according to claim 1, wherein the abnormality score value is used for judging whether the current data has abnormality or not, the method comprising:
Presetting a score threshold;
If the current data has the current data point with the abnormal score value larger than or equal to the preset score threshold value, the current data has the abnormality, otherwise, the current data has no abnormality.
6. The data processing method for an intelligent switch cabinet according to claim 5, wherein the intelligent switch cabinet is controlled according to whether the current data has abnormality, the method comprising:
If the current data is abnormal, the intelligent switch cabinet is controlled to stop operating, otherwise, the intelligent switch cabinet operates normally.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410276465.3A CN117892246B (en) | 2024-03-12 | 2024-03-12 | Data processing method for intelligent switch cabinet |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410276465.3A CN117892246B (en) | 2024-03-12 | 2024-03-12 | Data processing method for intelligent switch cabinet |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN117892246A CN117892246A (en) | 2024-04-16 |
| CN117892246B true CN117892246B (en) | 2024-05-31 |
Family
ID=90647459
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202410276465.3A Active CN117892246B (en) | 2024-03-12 | 2024-03-12 | Data processing method for intelligent switch cabinet |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117892246B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN118091325B (en) * | 2024-04-17 | 2024-06-25 | 江苏裕荣光电科技有限公司 | Intelligent cable detection method and system |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116702081A (en) * | 2023-08-07 | 2023-09-05 | 西安格蒂电力有限公司 | Intelligent inspection method for power distribution equipment based on artificial intelligence |
| CN117330816A (en) * | 2023-12-01 | 2024-01-02 | 南京中旭电子科技有限公司 | Monitoring data optimization method for Hall current sensor |
| CN117411189A (en) * | 2023-12-14 | 2024-01-16 | 山东德源电力科技股份有限公司 | Monitoring data enhancement method of micro-grid coordination controller |
| CN117420346A (en) * | 2023-12-19 | 2024-01-19 | 东莞市兴开泰电子科技有限公司 | Circuit protection board overcurrent value detection method and system |
| CN117609929A (en) * | 2024-01-24 | 2024-02-27 | 湖南易比特大数据有限公司 | Industrial production line fault online diagnosis method and system based on big data |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US11755932B2 (en) * | 2020-04-23 | 2023-09-12 | Actimize Ltd. | Online unsupervised anomaly detection |
-
2024
- 2024-03-12 CN CN202410276465.3A patent/CN117892246B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116702081A (en) * | 2023-08-07 | 2023-09-05 | 西安格蒂电力有限公司 | Intelligent inspection method for power distribution equipment based on artificial intelligence |
| CN117330816A (en) * | 2023-12-01 | 2024-01-02 | 南京中旭电子科技有限公司 | Monitoring data optimization method for Hall current sensor |
| CN117411189A (en) * | 2023-12-14 | 2024-01-16 | 山东德源电力科技股份有限公司 | Monitoring data enhancement method of micro-grid coordination controller |
| CN117420346A (en) * | 2023-12-19 | 2024-01-19 | 东莞市兴开泰电子科技有限公司 | Circuit protection board overcurrent value detection method and system |
| CN117609929A (en) * | 2024-01-24 | 2024-02-27 | 湖南易比特大数据有限公司 | Industrial production line fault online diagnosis method and system based on big data |
Non-Patent Citations (1)
| Title |
|---|
| 孤立森林算法在智能监控中的应用;闻明 等;《科技创新导报》;20200511(第14期);第140-141页 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN117892246A (en) | 2024-04-16 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN117093879B (en) | Intelligent operation management method and system for data center | |
| CN117892246B (en) | Data processing method for intelligent switch cabinet | |
| CN116702081B (en) | Intelligent inspection method for power distribution equipment based on artificial intelligence | |
| CN116628529B (en) | Data anomaly detection method for intelligent load control system at user side | |
| CN111277332B (en) | Performance state detection method and device of optical module in engineering application and electronic equipment | |
| CN109115257B (en) | Method, device, equipment and storage medium for correcting sensor characteristic curve | |
| CN117421610B (en) | Data anomaly analysis method for electric energy meter running state early warning | |
| CN115689393A (en) | Real-time dynamic monitoring system and method for power system based on Internet of things | |
| CN116111727A (en) | Comprehensive distribution box abnormity monitoring method based on dynamic temperature threshold | |
| CN116226766B (en) | High-voltage electrical apparatus running state monitoring system | |
| CN116183058A (en) | Monitoring method of intelligent capacitor | |
| CN116365716B (en) | Electricity inspection system based on internet of things platform | |
| CN116994416B (en) | Fan operation fault early warning method and system based on artificial intelligence | |
| CN112504511A (en) | Generator stator temperature monitoring method, device and medium | |
| CN106405280B (en) | A kind of intelligent substation on-line monitoring parameter trend method for early warning | |
| CN110488128A (en) | Bilateral accumulation and event detecting method | |
| CN117368799A (en) | Diagnosis method for short-circuit fault of power transmission line of power system | |
| CN113988723A (en) | User behavior locking method and system based on power consumption data anomaly analysis | |
| CN117150244B (en) | Intelligent power distribution cabinet state monitoring method and system based on electrical parameter analysis | |
| CN117318310B (en) | Remote unmanned intelligent monitoring system for explosion-proof power distribution cabinet | |
| CN113091832B (en) | Intelligent monitoring method for power transformation and distribution station based on big data visualization and cloud monitoring platform | |
| CN110992205A (en) | State detection method and system for generator winding of wind turbine generator and related components | |
| CN115713312A (en) | Combined identification method and device for unfavorable working conditions of hydraulic and hydroelectric engineering environmental quantity | |
| CN115600879A (en) | Circuit breaker abnormity early warning method, system and related device | |
| CN113704323A (en) | Timing sequence anomaly detection algorithm based on HTM improvement |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |