A method for detecting faults of power equipment in a power transformation and distribution system

By analyzing the changes in power data and abnormal situations, the fault areas in the substation distribution system are screened out, and the problem of inaccurate detection of power equipment faults is solved, and the detection efficiency and system stability are improved.

CN118914732BActive Publication Date: 2024-12-06JIANGSU SHANGRONG ELECTRIC TECH CO LTD
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202411407883.8
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2024-10-10
Publication Date
2024-12-06
Estimated Expiration
2044-10-10

AI Technical Summary

Technical Problem

In the substation distribution system, the fault detection of power equipment is inaccurate, resulting in waste of manpower and material resources, and the failure of the power transformer is not recognized in time, affecting the stability of the system.

Method used

By obtaining the power data of each area, analyzing the power changes and abnormal data during the descent period, calculating the normal degree of decline, user degree of decline and power regulation, filtering out suspected fault areas, and then conducting accurate fault detection.

Benefits of technology

It improves the identification efficiency of fault areas, accurately eliminates normal decline and regulation factors, saves manpower and material resources, and ensures the power supply reliability and stability of the substation and distribution system.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN118914732B_ABST
    Figure CN118914732B_ABST
Patent Text Reader

Abstract

The present invention relates to the field of electric quantity testing technology, and in particular to a method for detecting faults in electric power equipment in a power transformation and distribution system. The method obtains electric quantity data; obtains the normal decline degree according to the change of electric quantity data in the decline time period of the electric quantity decline area and the distribution of abnormal electric quantity data, as well as the overall change trend of the electric quantity data in the electric quantity decline area, and then screens out the first suspected fault area; obtains the user decline degree according to the user change in the first suspected fault area, and then screens out the second suspected fault area; obtains the electric quantity control degree according to the difference in electric quantity demand and electric quantity distribution between the second suspected fault area and each other area, and then screens out the fault area; and performs fault detection on the electric power equipment in the fault area. The present invention improves the fault detection efficiency of the electric power equipment and saves a lot of manpower and material resources by accurately obtaining the fault area and then accurately determining the area where the electric power equipment fault exists.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention relates to the technical field of electric quantity testing, and in particular to a method for detecting faults of electric power equipment in a power transformation and distribution system. Background Art

[0002] In the power distribution system, power equipment is used for the conversion and distribution of electric energy. The normal and stable operation of power equipment is crucial to the power supply reliability and stability of the power distribution system. The most critical power equipment for power conversion and transmission in the power distribution system is the power transformer. Therefore, it is necessary to detect the power transformer in time, find out the fault of the power transformer in time and repair it to ensure the stable and reliable operation of the power distribution system.

[0003] In the power transformation and distribution system, the power data of each area is obtained in real time through the server. In the existing method, the power data of each area obtained from the server is directly analyzed. When the power data decreases, it prompts that the power transformer in the corresponding area is suspected to be faulty, and then the power transformer in the corresponding area is promptly detected and repaired. However, in actual situations, there are many reasons for the decrease and change of power data, such as high-energy-consuming units or high-energy-consuming equipment actively shutting down for maintenance, users using a large number of self-provided power sources such as solar panels, a decrease in power users in the region, and power regulation between regions. All of these will cause the power data in the region to decrease, which will lead to inaccurate fault detection of power equipment in different regions, wasting a lot of manpower and material resources. Summary of the invention

[0004] In order to solve the technical problem of inaccurate fault detection of power equipment in a region, the purpose of the present invention is to provide a method for detecting faults of power equipment in a power transformation and distribution system. The technical solution adopted is as follows:

[0005] An embodiment of the present invention provides a method for detecting faults of power equipment in a power transformation and distribution system, the method comprising the following steps:

[0006] Get the power data of each area at each moment in the current time period;

[0007] Obtain the decline time period of each power decline area at the current moment, and obtain the normal decline degree of each power decline area according to the change of power data and the distribution of abnormal power data in the decline time period of each power decline area, as well as the overall change trend of power data in each power decline area in the current time period; and screen out the first suspected fault area based on the normal decline degree;

[0008] According to the difference in the number of users between the falling time period of each first suspected fault area and the current time period of other parts of the non-falling time period, the degree of user decline of each first suspected fault area is obtained; and the second suspected fault area is screened out based on the degree of user decline;

[0009] According to the power demand difference and power distribution difference between each second suspected fault area and each other area at the current moment, the power control degree of each second suspected fault area is obtained; and the fault area at the current moment is screened out based on the power control degree;

[0010] Perform fault detection on the electrical equipment in the fault area.

[0011] Furthermore, the method for obtaining the normal decline degree is:

[0012] For any area where the power is decreasing, the power data in the current time period of the area where the power is decreasing is fitted into a curve according to the time sequence as the power data curve of the area where the power is decreasing;

[0013] Decompose the power data curve using the STL decomposition algorithm to obtain the trend curve and seasonal curve of the power decline area;

[0014] Obtain the slope of the fitted straight line corresponding to the trend curve as the overall change value of the power reduction area;

[0015] The seasonal curve corresponding to the decreasing time period of the power decreasing area is used as the reference seasonal curve of the power decreasing area;

[0016] According to the changes of the reference seasonal curve, the seasonal decrease degree of the power decrease area is obtained;

[0017] The abnormal power data in the falling time period of the power drop area is obtained by using the local outlier factor detection algorithm, and the abnormal sporadic degree of the power drop area is obtained according to the distribution of the abnormal power data;

[0018] According to the overall change value, seasonal decline degree and abnormal occasional degree of the power decline area, the normal decline degree of the power decline area is obtained; among which, the overall change value is negatively correlated with the normal decline degree, and the seasonal decline degree and the abnormal occasional degree are positively correlated with the normal decline degree.

[0019] Furthermore, the method for obtaining the seasonal decline degree is:

[0020] For any area where the power consumption decreases, the accumulated result of the time periods corresponding to all the decreasing parts in the reference seasonal curve of the area where the power consumption decreases is taken as the first time period;

[0021] The accumulated result of the time periods corresponding to all the rising parts in the reference seasonal curve of the area where the power consumption decreases is taken as the second time period;

[0022] Obtaining a data drop rate of each drop portion in the reference seasonal curve of the power drop area as a first rate of the corresponding drop portion;

[0023] Obtaining a data rising rate of each rising portion in the reference seasonal curve of the power reduction area as a second rate of the corresponding rising portion;

[0024] According to the difference between the first time period and the second time period, and the difference between the mean of the first rate and the mean of the second rate, the seasonal decline degree of the power decline area is obtained; wherein, the difference between the first time period and the second time period, and the difference between the mean of the first rate and the mean of the second rate are positively correlated with the seasonal decline degree.

[0025] Furthermore, the method for obtaining the degree of abnormal sporadic occurrence is:

[0026] For any area where the power is decreasing, the abnormal power data in the decreasing time period of the area is clustered by using the DBSCAN density clustering algorithm to obtain a cluster cluster;

[0027] Obtain the number of abnormal power data in each cluster as the first number;

[0028] The difference between the largest first quantity and the mean of the first quantity is taken as the first characteristic difference;

[0029] Acquire the quantity of all abnormal power data in the power reduction time period of the power reduction area as the second quantity;

[0030] According to the difference between the number of clusters and the second number, and the first characteristic difference, the abnormality and contingency degree of the power drop area is obtained; wherein, the difference between the number of clusters and the second number and the abnormality and contingency degree are positively correlated, and the first characteristic difference and the abnormality and contingency degree are negatively correlated.

[0031] Furthermore, the method for obtaining the first suspected fault area is:

[0032] When the normal decrease degree does not meet the preset normal decrease degree range, the corresponding power decrease area is the first suspected fault area.

[0033] Furthermore, the method for obtaining the user's decline degree is:

[0034] For any first suspected fault area, the number of users at each moment in the falling time period of the first suspected fault area is obtained as the first number of users;

[0035] Obtain the number of users at each moment in the other parts of the current time period of the non-falling time period of the first suspected fault area, and use them as the second number of users;

[0036] According to the difference between the mean of the second number of users and the mean of the first number of users, the degree of user decline in the first suspected fault area is obtained; wherein the difference between the mean of the second number of users and the mean of the first number of users and the degree of user decline are positively correlated.

[0037] Furthermore, the method for obtaining the second suspected fault area is:

[0038] When the user's descent degree does not satisfy a preset user's descent degree range, the first suspected fault area corresponds to the second suspected fault area.

[0039] Furthermore, the method for obtaining the power control degree is:

[0040] Obtain the power demand data and power distribution data of each area at the current moment;

[0041] For any second suspected fault area, obtain the mean value of the power demand data and the mean value of the power allocation data of all other areas except the second suspected fault area, and use them as reference power demand data and reference power allocation data respectively;

[0042] taking a difference between the reference power demand data and the power demand data of the second suspected fault area as a first difference;

[0043] Taking the difference between the reference power distribution data and the power distribution data of the second suspected fault area as the second difference;

[0044] According to the first difference and the second difference, the power control degree of the second suspected fault area is obtained; wherein the first difference and the second difference are both positively correlated with the power control degree.

[0045] Furthermore, the method for obtaining the fault area is:

[0046] When the power control degree does not satisfy the preset power control degree range, the corresponding second suspected fault area is the fault area at the current moment.

[0047] Furthermore, the method for obtaining the power reduction area and the power reduction time period is:

[0048] The time period consisting of the last preset number of consecutive moments in each area in the current time period is used as the reference time period for each area;

[0049] For any area, when all power data in the reference time period of the area are less than the preset power data threshold of the area, the area is a power reduction area at the current moment;

[0050] For any area where the power is decreasing, the time corresponding to the power data which is closest to the current time and is greater than or equal to the preset power data threshold of the area within the current time period of the area where the power is decreasing is taken as the target time;

[0051] The time period formed by the next moment of the target moment and the current moment is used as the decreasing time period of the power decreasing area.

[0052] The present invention has the following beneficial effects:

[0053] Obtain each area of ​​power decline at the current moment, determine the area where the power equipment failure may exist, and improve the efficiency of obtaining the fault area; in order to obtain the fault area, obtain the normal decline degree of each power decline area according to the change of power data and the distribution of abnormal power data in the decline time period of each power decline area, and the overall change trend of power data in each power decline area in the current time period, reflecting the possibility that the power data of each power decline area is the normal changing power data at the current moment, accurately exclude the power decline area with normal decline at the current moment, preliminarily identify the suspected fault area, and then screen out the first suspected fault area based on the normal decline degree, which is conducive to the subsequent accurate and efficient identification of the fault area; further obtain the user decline degree of each first suspected fault area according to the difference in the number of users between the decline time period of each first suspected fault area and the other parts of the non-decline time period, and accurately reflect the first suspected fault area at the current moment. The changes in users in the network are conducive to accurately excluding the first suspected fault area where the power data decreases due to the reduction in users, further identifying the suspected fault area, and then screening out the second suspected fault area based on the degree of user decline, which is more conducive to the subsequent accurate and efficient identification of the fault area; in order to accurately obtain the fault area, and then according to the power demand difference and power distribution difference between each second suspected fault area and each other area at the current moment, the power control degree of each second suspected fault area is obtained, accurately reflecting the possibility of power being regulated in each second suspected fault area, accurately excluding the second suspected fault area where the power data decreases due to power control factors at the current moment, and then accurately screening out the fault area at the current moment based on the power control degree, and then performing fault detection on the power equipment in the fault area, accurately and efficiently detecting the fault of the power equipment, saving a lot of manpower and material resources, and at the same time, it is conducive to timely repairing the fault of the power equipment to ensure the power supply reliability and stability of the power distribution system. BRIEF DESCRIPTION OF THE DRAWINGS

[0054] In order to more clearly illustrate the technical solutions and advantages in the embodiments of the present invention or the prior art, the drawings required for use in the embodiments or the prior art descriptions are briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0055] Figure 1 A schematic flow chart of a method for detecting faults of power equipment in a power transformation and distribution system provided by an embodiment of the present invention;

[0056] Figure 2 A flow chart of a method for obtaining a normal descent degree provided by an embodiment of the present invention;

[0057] Figure 3 A flow chart of a method for obtaining seasonal decline degree provided by an embodiment of the present invention;

[0058] Figure 4 A structural diagram of a power equipment fault detection system for a power transformation and distribution system provided by an embodiment of the present invention;

[0059] Figure 5 A schematic diagram of a computer device provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0060] In order to further explain the technical means and effects adopted by the present invention to achieve the predetermined invention purpose, the following is a detailed description of the specific implementation method, structure, features and effects of a power equipment fault detection method for a power distribution system proposed by the present invention in combination with the accompanying drawings and preferred embodiments. In the following description, different "one embodiment" or "another embodiment" does not necessarily refer to the same embodiment. In addition, specific features, structures or characteristics in one or more embodiments may be combined in any suitable form.

[0061] Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs.

[0062] The specific scheme of the method for detecting faults of power equipment in a power transformation and distribution system provided by the present invention is described in detail below with reference to the accompanying drawings.

[0063] Embodiment 1:

[0064] The specific scenario of this embodiment is: the most critical power equipment for power conversion and transmission in the power distribution system is the power transformer. The safe operation of the power distribution system is the first line of defense to avoid power grid accidents, and the power transformer is one of the most critical power equipment in the line of defense. In order to perform accurate fault detection on the power transformer in each area in a timely manner, this embodiment first obtains the power decline area where the power transformer fault may exist according to the change of the power data in each area in the current time period; then analyzes the change of the power data in the decline time period of each power decline area, excludes the power decline area where the current power data decreases normally, and screens out the first suspected fault area where the power transformer fault may exist; further analyzes the change of the number of power users in each first suspected fault area, excludes the first suspected fault area where the power data decreases due to the decrease of power users, and further screens out the second suspected fault area where the power transformer fault may exist; further analyzes the power control situation of each second suspected fault area and each other area at the current moment, determines the second suspected fault area where the power data decreases due to the power control factors at the current moment, and accurately screens out the fault area at the current moment; finally, the power transformer in the fault area is inspected and repaired, which improves the efficiency of power transformer fault detection and saves a lot of manpower and material resources.

[0065] The present invention proposes a method for detecting faults in power equipment in a power distribution system. Figure 1 , which shows a schematic flow chart of a method for detecting faults of power equipment in a power distribution system provided by an embodiment of the present invention, the method comprising the following steps:

[0066] Step S1: Obtain the power data of each area at each moment in the current time period.

[0067] Specifically, each user in each area controlled by a power transformation and distribution system corresponds to a smart meter, and the power data of each user in each area at each moment can be obtained through the smart meter. In actual situations, each smart meter stores power data for a specified time period and transmits it to the server in the power transformation and distribution system. This embodiment obtains the power data in the server in real time and analyzes it to detect the faults of power transformers in each area in a timely manner. This embodiment sets the specified time period to 1 hour. The implementer can set the length of the specified time period according to actual conditions, which is not limited here. In order to improve the efficiency of analyzing the changes in power data in each area, this embodiment accumulates the power data of all users in each area at the same time as the power data of the corresponding area at the same time, and thus obtains the power data of each area at each moment. It should be noted that the areas appearing in this embodiment are all areas controlled by the same power transformation and distribution system.

[0068] In order to analyze in real time whether there is a fault in the power transformer of each area, this embodiment obtains the power data of each area at each moment in the current time period in the server of the power transformation and distribution system, analyzes the power data in the current time period of each area, and then accurately analyzes whether there is a fault in the power transformer of each area at the current moment. In this embodiment, the current time period is set to 3 years, and the terminal moment of the current time period must be the current moment, and the time interval between two adjacent moments in the current time period is set to 24 hours. The implementer can set the size of the time interval between the current time period and the two adjacent moments according to the actual situation, which is not limited here.

[0069] Step S2: Obtain the decline time period of each power decline area at the current moment, and obtain the normal decline degree of each power decline area according to the change of power data and the distribution of abnormal power data in the decline time period of each power decline area, as well as the overall change trend of power data in each power decline area in the current time period; screen out the first suspected fault area based on the normal decline degree.

[0070] It is known that when a power transformer in a certain area fails, the electric quantity data in the area must decrease, and the decrease in electric quantity data must be a continuous process. Therefore, in this embodiment, the time period composed of the last preset number of consecutive moments in each area in the current time period is used as the reference time period for each area, wherein the terminal moment of the reference time period is the current moment. In this embodiment, the preset number is set to 10. The implementer can set the size of the preset number according to the actual situation, which is not limited here. When the electric quantity data in the reference time period of a certain area is smaller, it means that the area is more likely to be in a declining stage in the reference time period, which indirectly indicates that the area may be an area with a power transformer failure. Therefore, in this embodiment, a preset electric quantity data threshold is set for each area. For any area, when all the electric quantity data in the reference time period of the area are less than the preset electric quantity data threshold of the area, the area is an electric quantity decrease area where a power transformer failure may exist at the current moment. So far, each electric quantity decrease area at the current moment is obtained.

[0071] Preferably, in some possible implementations of this embodiment, the method for obtaining the preset power data threshold is: for any area, obtain the average value of all power data in the area in the current time period as the reference value of the area; multiply the first preset constant by the reference value as the preset power data threshold of the area, wherein the first preset constant is greater than 0 and less than 1. In this embodiment, the first preset constant is set to 0.8. The implementer can set the size of the first preset constant according to the actual situation, which is not limited here. So far, the preset power data threshold of each area is obtained.

[0072] In order to accurately analyze the decline in the power data of each power drop area at the current moment, this embodiment obtains the decline time period of each power drop area at the current moment according to the change in the power data of each power drop area. In some possible implementations of this embodiment, the method for obtaining the decline time period is: for any power drop area, the moment corresponding to the power data that is closest to the current moment and greater than or equal to the preset power data threshold of the area within the current time period of the power drop area is used as the target moment; the time period formed by the next moment of the target moment and the current moment is used as the decline time period of the power drop area. The power data in the decline time period of each power drop area is less than the preset power data threshold of the corresponding power drop area. At this point, the decline time period of each power drop area is obtained.

[0073] In actual situations, due to seasonal changes or other normal factors, the power data in each area will decrease. For example, it is hot in summer, and almost all users in each area will use air conditioning. The weather in spring is more suitable and there is no need to use air conditioning. Therefore, in each area, the power data in spring is lower than that in summer. In order to determine whether the power data in the decreasing time period of each power decreasing area is normally changing power data, this embodiment first analyzes the change of power data in the decreasing time period of each power decreasing area. When the decreasing part of the power data in the decreasing time period of a certain power decreasing area is more than the increasing part, and the decreasing rate of the power data is relatively fast, it means that the power data in the decreasing time period of the power decreasing area is more likely to be normally changing power data, and the power decreasing area is less likely to be a power transformer fault area.

[0074] It is known that the abnormal power data generated by power transformer failure is distributed in a relatively aggregated manner, while the abnormal power data generated by other accidental accidents such as power data entry errors is distributed in a relatively discrete manner. Therefore, this embodiment first obtains the abnormal power data in the falling time period of each power drop area through a local outlier factor detection algorithm, and then analyzes the distribution of the abnormal power data in the falling time period of each power drop area. The more discrete the distribution of the abnormal power data in the falling time period of a power drop area, the less likely it is that the power drop area is a power transformer failure area. Among them, the local outlier factor detection algorithm is a well-known technology and will not be described in detail.

[0075] In actual situations, when the overall change trend of the power data in a power drop area is more downward, it means that the power data in the power drop area at the current moment is more likely to be normally changing power data, and the power drop area is less likely to be a power transformer fault area.

[0076] Therefore, this embodiment obtains the normal decline degree of each power decline area according to the change of power data in the decline time period of each power decline area and the distribution of abnormal power data, as well as the overall change trend of power data in each power decline area in the current time period. The greater the normal decline degree, the more normal the change of power data in the decline time period of the corresponding power decline area, and the less likely the corresponding power decline area is to be a power transformer fault area. Then, based on the normal decline degree, the first suspected fault area where the power transformer fault may exist is preliminarily screened out, thereby improving the detection efficiency of the fault area.

[0077] It should be noted that in order to accurately analyze the changes in the power data and the overall trend of each power reduction area, this embodiment fits the power data in the current time period of each power reduction area into a curve according to the time sequence, as the power data curve of each power reduction area; each power data curve is decomposed by the STL (Standard Template Library) decomposition algorithm to obtain the trend curve and seasonal curve of each power reduction area. The overall trend of the power data in each power reduction area is analyzed by the trend curve, and the change of the power data in each power reduction area is analyzed by the seasonal curve. Among them, the curve fitting method and the STL (Standard Template Library) decomposition algorithm are both well-known technologies and will not be described in detail.

[0078] Preferably, in some possible implementations of this embodiment, the method for obtaining the normal decline degree can be found in Figure 2 , which shows a flow chart of a method for obtaining a normal descent degree provided by an embodiment of the present invention, the method comprising the following steps:

[0079] Step S201: Obtain the overall change value.

[0080] It is known that the trend curve of each power drop area can reflect the overall change of the power data of each power drop area. Therefore, in this embodiment, the trend curve of each power drop area is fitted into a straight line, and the slope of each straight line is obtained as the overall change value of each power drop area. The smaller the overall change value, the lower the overall change trend of the power data in the corresponding power drop area is. It indirectly indicates that the power data in the declining time period of the corresponding power drop area is more likely to be normally changing power data, and the corresponding power drop area is less likely to be a power transformer failure area.

[0081] Step S202: Obtain the seasonal decline degree.

[0082] In order to further analyze whether the power data in the declining time period of each power decline area is the power data of normal decline, this embodiment uses the partial seasonal curve corresponding to the declining time period of each power decline area as the reference seasonal curve of each power decline area. The change of the power data in the declining time period of each power decline area can be accurately analyzed by referring to the seasonal curve. When there are more time periods in which the data is declining in the reference seasonal curve of a certain power decline area, and the data decline rate is relatively fast, it means that the power data in the declining time period of the power decline area is more likely to be the power data of normal decline. Furthermore, this embodiment obtains the seasonal decline degree of each power decline area according to the change of the reference seasonal curve of each power decline area. The greater the seasonal decline degree, the more likely the power data in the declining time period of the corresponding power decline area is to be the power data of normal decline, which indirectly indicates that the corresponding power decline area is less likely to be the fault area of ​​the power transformer.

[0083] Preferably, in some possible implementations of this embodiment, the method for obtaining the seasonal decline degree can be found in Figure 3 , which shows a flow chart of a method for obtaining the seasonal decline degree provided by an embodiment of the present invention, the method comprising the following steps:

[0084] Step S202-1: For any area where power consumption decreases, the accumulated result of the time periods corresponding to all the decreasing parts in the reference seasonal curve of the area where power consumption decreases is taken as the first time period.

[0085] The larger the first time period is, the more the normal change of the power data in the decreasing time period of the power decrease area tends to decrease, which means that the power data in the decreasing time period of the power decrease area is more likely to be normally changing power data, and the power decrease area is less likely to be a power transformer fault area.

[0086] Step S202-2: The accumulated result of the time periods corresponding to all the rising parts in the reference seasonal curve of the power reduction area is taken as the second time period.

[0087] The smaller the second time period is, the more the change of the power data in the decreasing time period of the power decreasing area tends to decrease, which means that the power data in the decreasing time period of the power decreasing area is more likely to be normally decreasing power data.

[0088] Step S202-3: Obtain the data decrease rate of each decreasing portion in the reference seasonal curve of the power decrease area as the first rate of the corresponding decreasing portion.

[0089] The larger the first rate, the more obvious the data drop of the corresponding descending part. The first rate is obtained by: for any descending part in the reference seasonal curve, the difference between the maximum value and the minimum value of the descending part is obtained as the first value; the ratio of the first value to the time period corresponding to the descending part is taken as the first rate of the descending part.

[0090] Step S202-4: Obtain the data rising rate of each rising portion in the reference seasonal curve of the power reduction area as the second rate of the corresponding rising portion.

[0091] The larger the second rate is, the more obvious the corresponding rising portion of the data rises. The method for obtaining the second rate is the same as the method for obtaining the first rate, and will not be described in detail.

[0092] Step S202-5: According to the difference between the first time period and the second time period, and the difference between the mean of the first rate and the mean of the second rate, obtain the seasonal decrease degree of the power decrease area; wherein, the difference between the first time period and the second time period, and the difference between the mean of the first rate and the mean of the second rate are positively correlated with the seasonal decrease degree.

[0093] When the difference between the first time period and the second time period is greater, the power data in the falling time period of the power drop area tends to decrease, indicating that the power data in the falling time period of the power drop area is more likely to be a normal decrease. In order to further determine whether the power data in the falling time period of the power drop area is a normal decrease in power data, the significant changes in the power data in the falling time period of the power drop area are further analyzed. When the first rate is greater than the second rate, the more obvious the decrease in power data in the falling time period of the power drop area is, which indirectly indicates that the falling time period of the power drop area is more likely to be a normal change time period. Therefore, according to the difference between the first time period and the second time period, and the difference between the mean of the first rate and the mean of the second rate, the seasonal decrease degree of the power drop area is obtained; wherein, the difference between the first time period and the second time period, and the difference between the mean of the first rate and the mean of the second rate are positively correlated with the seasonal decrease degree.

[0094] In order to accurately indicate the normality of the power data in the falling time period of the power drop area, this embodiment specifically quantifies the seasonal drop degree into a seasonal drop degree value. The larger the seasonal drop degree value, the more likely the power data in the falling time period of the power drop area is to be normal drop power data, and the less likely the power drop area is to be a power transformer fault area. The calculation formula of the seasonal drop degree value is: ; In the formula, is the seasonal decrease value of the ath power decrease area; is the first time period of the ath power reduction area; is the second time period of the ath power reduction area; is the average value of the first rate of the ath power drop area; is the average value of the second rate of the ath battery drop area. The greater the sum The larger the The larger the value is, the more likely the power data in the a-th power drop area is to be normal power data, and the less likely the a-th power drop area is to be a power failure area. So far, the seasonal drop degree value of each power drop area is obtained.

[0095] Step S203: Obtain the degree of abnormality.

[0096] It is known that when the distribution of abnormal power data in the falling time period of a certain power drop area is more discrete, it means that the abnormal power data in the falling time period of the power drop area is less likely to be caused by a power transformer failure, which indirectly means that the power drop area is less likely to be a power transformer failure area. Therefore, this embodiment obtains the abnormal sporadic degree of each power drop area according to the distribution of abnormal power data in the falling time period of each power drop area; the greater the abnormal sporadic degree, the less likely the corresponding power drop area is to be a power transformer failure area.

[0097] Preferably, in some possible implementations of this embodiment, the method for obtaining the degree of abnormal sporadicity is: for any area of ​​power decline, the abnormal power data in the decline time period of the area of ​​power decline is clustered by the DBSCAN density clustering algorithm to obtain cluster clusters; when the distribution of cluster clusters is more discrete and the abnormal power data in each cluster cluster is less, it means that the abnormal power data in the decline time period of the area of ​​power decline is more likely to be caused by accidental unexpected circumstances, the abnormal power data in the decline time period of the area of ​​power decline is less likely to be caused by a power transformer failure, and the area of ​​power decline is less likely to be a power transformer failure area. Among them, the DBSCAN density clustering algorithm is a well-known technology and will not be described in detail. In order to accurately analyze the distribution of abnormal power data in the falling time period of the power drop area, and then obtain the number of abnormal power data in each cluster, all as the first number; the difference between the largest first number and the mean of the first number is taken as the first characteristic difference; the first characteristic difference must be a non-negative number, and the smaller the first characteristic difference, the more consistent the distribution of abnormal power data in the cluster; further obtain the number of all abnormal power data in the falling time period of the power drop area as the second number, when the number of clusters is more equal to the second number, under the premise of the smaller the first characteristic difference, it is more explained that the distribution of all abnormal power data in the falling time period of the power drop area is more discrete. Therefore, according to the difference between the number of clusters and the second number, and the first characteristic difference, the abnormal sporadic degree of the power drop area is obtained; wherein, the difference between the number of clusters and the second number is positively correlated with the abnormal sporadic degree, and the first characteristic difference is negatively correlated with the abnormal sporadic degree.

[0098] In order to accurately indicate the degree to which the abnormal power data in the falling time period of the power drop area is caused by accidental situations, this embodiment specifically quantifies the abnormal accidental degree as an abnormal accidental degree value. The larger the abnormal accidental degree value, the more likely the abnormal power data in the falling time period of the power drop area is caused by accidental accidents, which indirectly indicates that the power drop area is less likely to be a power transformer fault area. The calculation formula of the abnormal accidental degree value is: ; In the formula, is the value of the abnormal sporadic degree of the a-th power drop area; is the number of clusters in the drop time period of the ath power drop area; is the second number of the ath power drop area; is the largest first quantity in the drop time period of the a-th power drop area; is the mean value of the first quantity in the falling time period of the ath power falling area; exp is an exponential function with a natural constant as the base; The first characteristic difference. The bigger, The smaller it is, the more discrete the distribution of abnormal power data in the falling time period of the a-th power decline area is, and the more likely the abnormal power data in the falling time period of the a-th power decline area is to be caused by accidental accidents. The larger the value is, the less likely the ath power drop area is to be a power transformer fault area. Thus, the abnormal sporadic degree value of each power drop area is obtained.

[0099] Step S204: Obtain the normal descent degree.

[0100] It is known that the smaller the overall change value is, the overall change trend of the electric quantity data in the corresponding electric quantity drop area is downward, which indirectly indicates that the electric quantity data in the drop time period of the corresponding electric quantity drop area is more likely to be the electric quantity data of normal change, and the corresponding electric quantity drop area is less likely to be the power transformer fault area; the greater the seasonal drop degree is, the more likely the electric quantity data in the drop time period of the corresponding electric quantity drop area is to be the electric quantity data of normal drop, and the corresponding electric quantity drop area is less likely to be the power transformer fault area; the greater the abnormal sporadic degree is, the more likely the abnormal electric quantity data in the drop time period of the corresponding electric quantity drop area is to be caused by accidental accidents, and the corresponding electric quantity drop area is less likely to be the power transformer fault area. Therefore, this embodiment obtains the normal drop degree of each electric quantity drop area according to the overall change value, seasonal drop degree and abnormal sporadic degree of each electric quantity drop area; wherein, the overall change value is negatively correlated with the normal drop degree, and the seasonal drop degree and abnormal sporadic degree are both positively correlated with the normal drop degree. The greater the normal drop degree is, the more likely the electric quantity data in the drop time period of the corresponding electric quantity drop area is to be the electric quantity data of normal drop, and the corresponding electric quantity drop area is less likely to be the power transformer fault area.

[0101] In order to accurately represent the normality of the power data in the falling time period of each power drop area, this embodiment specifically quantifies the normal drop degree into a normal drop degree value. The larger the normal drop degree value, the more likely the power data in the falling time period of the corresponding power drop area is normal drop power data. The calculation formula of the normal drop degree value is: ; In the formula, is the normal decrease value of the ath power decrease area; is the seasonal decrease value of the ath power decrease area; is the value of the abnormal sporadic degree of the a-th power drop area; is the overall change value of the ath power drop area; is the second preset constant, which is greater than 0; norm is the normalization function. The value range of the normal decline degree value is 0 to 1.

[0102] This embodiment will Set to 1 to avoid the denominator being 0. Implementers can set it according to actual conditions. The size of is not limited here. So far, the normal decrease degree value of each power decrease area is obtained.

[0103] It is known that the larger the normal decrease value is, the less likely the corresponding power decrease area is to be a power transformer fault area. Therefore, this embodiment sets the preset normal decrease value threshold to 0.8. The implementer can set the size of the preset normal decrease value threshold according to the actual situation, and it is not limited here. When the normal decrease value is greater than the preset normal decrease value threshold, the power data in the decrease time period of the corresponding power decrease area is the normally changing power data, and the corresponding power decrease area is definitely not a power transformer fault area; when the normal decrease value is less than or equal to the preset normal decrease value threshold, the corresponding power decrease area may be a power transformer fault area. Therefore, this embodiment uses the power decrease area corresponding to the normal decrease value that is less than or equal to the preset normal decrease value threshold as the first suspected fault area. The first suspected fault area will continue to be analyzed later to improve the efficiency of obtaining the fault area.

[0104] Step S3: Obtain the degree of user decline of each first suspected fault area according to the difference in the number of users between the decline time period of each first suspected fault area and the other part of the current time period of the non-decline time period; and select the second suspected fault area based on the degree of user decline.

[0105] Specifically, in actual situations, when the number of users in a certain area decreases, the power data in the area will also decrease. Therefore, this embodiment analyzes the change in the number of users in each first suspected fault area, and further obtains the area where the power transformer fault actually exists at the current moment. Among them, the number of users in each area at each moment can be directly obtained in the power transformation and distribution system. When the number of users in the decline time period of a first suspected fault area is less than the number of users in the other part of the current time period of the non-decline time period, it means that the power data in the decline time period of the first suspected fault area is more likely to be the normal change of power data, and then according to the difference in the number of users between the decline time period of each first suspected fault area and the other part of the current time period of the non-decline time period, the degree of decline of users in each first suspected fault area is obtained; the greater the degree of decline of users, the less likely the corresponding first suspected fault area is to be a power transformer fault area.

[0106] Preferably, in some possible implementations of this embodiment, the method for obtaining the degree of user decline is: for any first suspected fault area, obtaining the number of users at each moment in the decline time period of the first suspected fault area, all of which are used as the first number of users; obtaining the number of users at each moment in the current time period of the other part of the non-decline time period of the first suspected fault area, all of which are used as the second number of users; in order to represent the number of users in the decline time period of the first suspected fault area and the number of users in the current time period of the other part of the non-decline time period, this embodiment obtains the mean of the first number of users to represent the number of users in the decline time period of the first suspected fault area, and obtains the mean of the second number of users to represent the number of users in the current time period of the other part of the non-decline time period of the first suspected fault area, and then obtains the degree of user decline of the first suspected fault area according to the difference between the mean of the second number of users and the mean of the first number of users; wherein, the difference between the mean of the second number of users and the mean of the first number of users is positively correlated with the degree of user decline.

[0107] In order to accurately represent the decline of users in each first suspected fault area during the decline time period, this embodiment specifically quantifies the degree of user decline as a user decline degree value. The larger the user decline degree value, the less likely the corresponding first suspected fault area is the power transformer fault area. The calculation formula of the user decline degree value is: ; In the formula, is the user decline value of the bth first suspected fault area; is the average number of all second users in the bth first suspected fault area; is the average value of the number of all first users in the bth first suspected fault area; norm is a normalization function. The value range of the user decline degree value is 0 to 1. So far, the user decline degree value of each first suspected fault area is obtained.

[0108] It is known that the larger the user decline value is, the less likely it is that the corresponding first suspected fault area is the power transformer fault area. Therefore, this embodiment sets the preset user decline value threshold to 0.8. The implementer can set the size of the preset user decline value threshold according to the actual situation, and it is not limited here. When the user decline value is greater than the preset user decline value threshold, the corresponding first suspected fault area must not be the power transformer fault area; when the user decline value is less than or equal to the preset user decline value threshold, the corresponding first suspected fault area may be the power transformer fault area; therefore, this embodiment uses the first suspected fault area corresponding to the user decline value that is less than or equal to the preset user decline value threshold as the second suspected fault area. The second suspected fault area will continue to be analyzed later to improve the efficiency of obtaining the real power transformer fault area.

[0109] Step S4: according to the power demand difference and power distribution difference between each second suspected fault area and each other area at the current moment, obtain the power control degree of each second suspected fault area; and filter out the fault area at the current moment based on the power control degree.

[0110] Specifically, in actual situations, some areas temporarily need more electricity consumption. In order to meet the needs of these areas, the power distribution system needs to regulate the electricity consumption of other areas, which will cause the electricity data of other areas to decrease. In order to determine whether each second suspected fault area at the current moment is due to the occurrence of a decline time period caused by power regulation, this embodiment first directly obtains the power demand data and power distribution data of each area at the current moment through the power distribution system. When the power demand data and power distribution data of a second suspected fault area are smaller, the power data of the decline time period of the second suspected fault area is more likely to be caused by power regulation between regions, and the second suspected fault area is less likely to be a power transformer fault area. Therefore, this embodiment obtains the power regulation degree of each second suspected fault area according to the power demand difference and power distribution difference between each second suspected fault area and each other area at the current moment; the greater the power regulation degree, the less likely the corresponding second suspected fault area is to be a power transformer fault area. Then, the fault area at the current moment is accurately screened out based on the power regulation degree.

[0111] Preferably, in some possible implementation methods of this embodiment, the method for obtaining the degree of power control is: for any second suspected fault area, obtain the mean of the power demand data and the mean of the power distribution data of all other areas except the second suspected fault area, and use them as reference power demand data and reference power distribution data respectively; use the difference between the reference power demand data and the power demand data of the second suspected fault area as the first difference; the larger the first difference is, the smaller the power demand data of the second suspected fault area is; use the difference between the reference power distribution data and the power distribution data of the second suspected fault area as the second difference; the larger the second difference is, the smaller the power distribution data of the second suspected fault area at the current moment is; the larger the first difference and the larger the second difference are, the greater the possibility that the second suspected fault area is regulated by the power transformation and distribution system at the current moment, and then according to the first difference and the second difference, obtain the power control degree of the second suspected fault area; wherein the first difference and the second difference are both positively correlated with the degree of power control. In order to accurately indicate the possibility that each second suspected fault area is regulated by the power distribution system, this embodiment specifically quantifies the degree of power regulation as a power regulation degree value. The larger the power regulation degree value, the more likely that the power data in the falling time period corresponding to the second suspected fault area is generated by power regulation between regions, and the less likely that the second suspected fault area is a power transformer fault area. The calculation formula for the power regulation degree value is: ; In the formula, is the power control degree value of the dth second suspected fault area; It is the reference electricity demand data; is the power demand data of the dth second suspected fault area; Assign data to reference power; The power distribution data for the dth second suspected fault area; is the first difference; is the first difference; norm is the normalization function. Wherein, the value range of the power control degree value is 0 to 1. So far, the power control degree value of each second suspected fault area is obtained.

[0112] It is known that the larger the power control degree value is, the less likely it is that the corresponding second suspected fault area is the power transformer fault area. Therefore, this embodiment sets the preset power control degree value threshold to 0.8. The implementer can set the size of the preset power control degree value threshold according to the actual situation, and it is not limited here. When the power control degree value is greater than the preset power control degree value threshold, the corresponding second suspected fault area must not be the power transformer fault area; when the power control degree value is less than or equal to the preset power control degree value threshold, the corresponding second suspected fault area must be the power transformer fault area, that is, the fault area. At this point, the area where the power transformer fault exists is accurately determined.

[0113] Step S5: Perform fault detection on the power equipment in the fault area.

[0114] Through the monitoring system or on-site investigation, the fault detection of the power transformer in the fault area at the current moment is directly carried out, which improves the efficiency of power transformer fault detection, is conducive to timely detection of power transformer faults, saves a lot of manpower and material resources, and at the same time, ensures the stable and reliable operation of the power distribution system in a timely manner.

[0115] In summary, this embodiment obtains power data; obtains the normal decline degree according to the change of power data in the decline time period of the power decline area and the distribution of abnormal power data, as well as the overall change trend of power data in the power decline area, and then screens out the first suspected fault area; obtains the user decline degree according to the user change in the first suspected fault area, and then screens out the second suspected fault area; obtains the power control degree according to the power demand difference and power distribution difference between the second suspected fault area and each other area, and then screens out the fault area; performs fault detection on the power equipment in the fault area. The present invention improves the fault detection efficiency of power equipment and saves a lot of manpower and material resources by accurately obtaining the fault area and then accurately determining the area where the power equipment fault exists.

[0116] Embodiment 2:

[0117] The present invention also proposes a power equipment fault detection system for a power transformer and distribution system, see Figure 4 , which shows a structural diagram of a power equipment fault detection system for a power distribution system provided by an embodiment of the present invention, the system includes: an acquisition module 10, a first suspected fault area acquisition module 20, a second suspected fault area acquisition module 30, a fault area acquisition module 40 and a processing module 50.

[0118] The acquisition module 10 is used to acquire the power data of each area at each moment in the current time period.

[0119] The first suspected fault area acquisition module 20 is used to obtain the decline time period of each power decline area at the current moment, and obtain the normal decline degree of each power decline area according to the change of power data and the distribution of abnormal power data in the decline time period of each power decline area, as well as the overall change trend of power data in each power decline area in the current time period; and screen out the first suspected fault area based on the normal decline degree.

[0120] The second suspected fault area acquisition module 30 is used to obtain the user decline degree of each first suspected fault area according to the difference in the number of users between the decline time period of each first suspected fault area and the other part of the current time period of the non-decline time period; and screen out the second suspected fault area based on the user decline degree.

[0121] The fault area acquisition module 40 is used to obtain the power control degree of each second suspected fault area according to the power demand difference and power allocation difference between each second suspected fault area and each other area at the current moment; and screen out the fault area at the current moment based on the power control degree.

[0122] The processing module 50 is used to perform fault detection on the power equipment in the fault area.

[0123] It should be noted that: the system provided in the above embodiment is only illustrated by the division of the above functional modules. In actual applications, the above functions can be assigned to different functional modules as needed, that is, the internal structure of the computer device is divided into different functional modules to complete all or part of the functions described above. In addition, the power equipment fault detection system of the power substation system and the power equipment fault detection method of the power substation system provided in the above embodiment belong to the same concept. The specific implementation process is detailed in the method embodiment and will not be repeated here.

[0124] Embodiment 3:

[0125] The present invention also proposes a device for detecting faults of power equipment in a power distribution system, the device comprising a memory and a processor, wherein the memory stores an executable program code, and the processor is used to call and execute the executable program code to execute a method for detecting faults of power equipment in a power distribution system provided in an embodiment of the present application. The device can be a chip, a component or a module, and the chip can include a connected processor and a memory; wherein the memory is used to store instructions, and when the processor calls and executes the instructions, the chip can execute a method for detecting faults of power equipment in a power distribution system provided in the above embodiment.

[0126] In addition, the present application embodiment also protects a computer device, see Figure 5 The computer device includes a memory 401, a processor 402, and a computer program 403 stored in the memory 401 and running on the processor 402, wherein when the processor 402 executes the computer program 403, the computer device can execute any one of the above-mentioned methods for detecting faults of power equipment in a transformer and distribution system.

[0127] Embodiment 4:

[0128] This embodiment also provides a computer-readable storage medium, in which a computer program code is stored. When the computer program code is executed on a computer, the computer executes the above-mentioned related method steps to implement a method for detecting faults of power equipment in a transformer and distribution system provided in the above embodiment.

[0129] Embodiment 5:

[0130] This embodiment also provides a computer program product. When the computer program product runs on a computer, it enables the computer to execute the above-mentioned related steps to implement a method for detecting faults of power equipment in a power transformation and distribution system provided in the above embodiment.

[0131] Among them, the device, computer-readable storage medium, computer program product or chip provided in this embodiment is used to execute the corresponding method provided above. Therefore, the beneficial effects that can be achieved can refer to the beneficial effects in the corresponding method provided above, and will not be repeated here.

[0132] It should be noted that the sequence of the above embodiments of the present invention is only for description and does not represent the advantages and disadvantages of the embodiments. The processes depicted in the accompanying drawings do not necessarily require the specific order or continuous order shown to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0133] The various embodiments in this specification are described in a progressive manner, and the same or similar parts between the various embodiments can be referenced to each other, and each embodiment focuses on the differences from other embodiments.

Claims

1. A method for detecting faults in power equipment in a power transformation and distribution system, characterized in that: The method comprises the following steps: Get the power data of each area at each moment in the current time period; Obtain the decline time period of each power decline area at the current moment, and obtain the normal decline degree of each power decline area according to the change of power data and the distribution of abnormal power data in the decline time period of each power decline area, as well as the overall change trend of power data in each power decline area in the current time period; and screen out the first suspected fault area based on the normal decline degree; According to the difference in the number of users between the falling time period of each first suspected fault area and the current time period of other parts of the non-falling time period, the degree of user decline of each first suspected fault area is obtained; and the second suspected fault area is screened out based on the degree of user decline; According to the power demand difference and power distribution difference between each second suspected fault area and each other area at the current moment, the power control degree of each second suspected fault area is obtained; and the fault area at the current moment is screened out based on the power control degree; Perform fault detection on the electrical equipment in the fault area.

2. A method for detecting faults in power equipment in a power transformation and distribution system according to claim 1, characterized in that: The method for obtaining the normal decline degree is: For any area where the power is decreasing, the power data in the current time period of the area where the power is decreasing is fitted into a curve according to the time sequence as the power data curve of the area where the power is decreasing; Decompose the power data curve using the STL decomposition algorithm to obtain the trend curve and seasonal curve of the power decline area; Obtain the slope of the fitted straight line corresponding to the trend curve as the overall change value of the power reduction area; The seasonal curve corresponding to the decreasing time period of the power decreasing area is used as the reference seasonal curve of the power decreasing area; According to the changes of the reference seasonal curve, the seasonal decrease degree of the power decrease area is obtained; The abnormal power data in the falling time period of the power drop area is obtained by using the local outlier factor detection algorithm, and the abnormal sporadic degree of the power drop area is obtained according to the distribution of the abnormal power data; According to the overall change value, seasonal decline degree and abnormal occasional degree of the power decline area, the normal decline degree of the power decline area is obtained; among which, the overall change value is negatively correlated with the normal decline degree, and the seasonal decline degree and the abnormal occasional degree are positively correlated with the normal decline degree.

3. A method for detecting faults in power equipment in a power transformation and distribution system according to claim 2, characterized in that: The method for obtaining the seasonal decline degree is: For any area where the power consumption decreases, the accumulated result of the time periods corresponding to all the decreasing parts in the reference seasonal curve of the area where the power consumption decreases is taken as the first time period; The accumulated result of the time periods corresponding to all the rising parts in the reference seasonal curve of the area where the power consumption decreases is taken as the second time period; Obtaining a data drop rate of each drop portion in the reference seasonal curve of the power drop area as a first rate of the corresponding drop portion; Obtaining a data rising rate of each rising portion in the reference seasonal curve of the power reduction area as a second rate of the corresponding rising portion; According to the difference between the first time period and the second time period, and the difference between the mean of the first rate and the mean of the second rate, the seasonal decline degree of the power decline area is obtained; wherein, the difference between the first time period and the second time period, and the difference between the mean of the first rate and the mean of the second rate are positively correlated with the seasonal decline degree.

4. A method for detecting faults in power equipment in a power transformation and distribution system according to claim 2, characterized in that: The method for obtaining the abnormal sporadic degree is: For any area where the power is decreasing, the abnormal power data in the decreasing time period of the area is clustered by using the DBSCAN density clustering algorithm to obtain a cluster cluster; Obtain the number of abnormal power data in each cluster as the first number; The difference between the largest first quantity and the mean of the first quantity is taken as the first characteristic difference; Acquire the quantity of all abnormal power data in the power reduction time period of the power reduction area as the second quantity; According to the difference between the number of clusters and the second number, and the first characteristic difference, the abnormality and contingency degree of the power drop area is obtained; wherein, the difference between the number of clusters and the second number and the abnormality and contingency degree are positively correlated, and the first characteristic difference and the abnormality and contingency degree are negatively correlated.

5. A method for detecting faults in power equipment in a power transformation and distribution system according to claim 1, characterized in that: The method for obtaining the first suspected fault area is: When the normal decrease degree does not meet the preset normal decrease degree range, the corresponding power decrease area is the first suspected fault area.

6. A method for detecting faults in power equipment in a power transformation and distribution system according to claim 1, characterized in that: The method for obtaining the user's decline degree is: For any first suspected fault area, the number of users at each moment in the falling time period of the first suspected fault area is obtained as the first number of users; Obtain the number of users at each moment in the other parts of the current time period of the non-falling time period of the first suspected fault area, and use them as the second number of users; According to the difference between the mean of the second number of users and the mean of the first number of users, the degree of user decline in the first suspected fault area is obtained; wherein the difference between the mean of the second number of users and the mean of the first number of users and the degree of user decline are positively correlated.

7. A method for detecting faults in power equipment in a power transformation and distribution system according to claim 1, characterized in that: The method for obtaining the second suspected fault area is: When the user's descent degree does not satisfy a preset user's descent degree range, the first suspected fault area corresponds to the second suspected fault area.

8. A method for detecting faults in power equipment in a power transformation and distribution system according to claim 1, characterized in that: The method for obtaining the power control degree is: Obtain the power demand data and power distribution data of each area at the current moment; For any second suspected fault area, obtain the mean value of the power demand data and the mean value of the power allocation data of all other areas except the second suspected fault area, and use them as reference power demand data and reference power allocation data respectively; taking a difference between the reference power demand data and the power demand data of the second suspected fault area as a first difference; taking a difference between the reference power distribution data and the power distribution data of the second suspected fault area as a second difference; According to the first difference and the second difference, the power control degree of the second suspected fault area is obtained; wherein the first difference and the second difference are both positively correlated with the power control degree.

9. A method for detecting faults in power equipment in a power transformation and distribution system according to claim 1, characterized in that: The method for obtaining the fault area is: When the power control degree does not satisfy the preset power control degree range, the corresponding second suspected fault area is the fault area at the current moment.

10. A method for detecting faults in power equipment in a power transformation and distribution system according to claim 1, characterized in that: The method for obtaining the power reduction area and the power reduction time period is as follows: The time period consisting of the last preset number of consecutive moments in each area within the current time period is used as the reference time period for each area; For any area, when all power data in the reference time period of the area are less than the preset power data threshold of the area, the area is a power reduction area at the current moment; For any area where the power is decreasing, the time corresponding to the power data which is closest to the current time and is greater than or equal to the preset power data threshold of the area within the current time period of the area where the power is decreasing is taken as the target time; The time period formed by the next moment of the target moment and the current moment is used as the decreasing time period of the power decreasing area.