Transformer fault diagnosis method and system based on data analysis

Abstract

The invention discloses a transformer fault diagnosis method and system based on data analysis, and relates to the technical field of transformer fault diagnosis, and the method comprises the steps: obtaining the historical operation data of a transformer and the maintenance data of the transformer, and carrying out the causal analysis of the historical operation data of the transformer and the maintenance data of the transformer, data sets with relevance are determined. According to the method, the historical operation data of the transformer is subjected to data matching and data calculation through the maintenance data of the transformer, the data set with relevance is determined, in addition, the change delay time of the associated data is determined by performing time analysis on the data set with relevance, and the change delay time of the associated data is determined. When the data change rule corresponding to the data set with the relevance accords with the change delay time of the relevance data, it can be determined that the transformer is abnormal, maintenance personnel can be dispatched to maintain the transformer, frequent maintenance of the transformer by the maintenance personnel is avoided, the work intensity of the maintenance personnel is reduced, and the maintenance efficiency is improved. And the maintenance cost of the transformer is also reduced.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of transformer fault diagnosis, in particular to a transformer fault diagnosis method and system based on data analysis. BACKGROUND

[0002] The transformer refers to the device for changing the alternating voltage by using the principle of electromagnetic induction. The transformer can be divided into power transformer and special transformer according to the use. The power transformer is mainly used for power transmission and distribution line, and changes the alternating voltage to meet the needs of different users. The special transformer is used in smelting, electric processing, electric drive, communication, automatic control and other special fields. The main components are primary coil, secondary coil and core (magnetic core). The main functions of the transformer are: voltage transformation, current transformation, impedance transformation, isolation, voltage stabilization (magnetic saturation transformer) and the like. The transformer is a basic equipment for power transmission and distribution, and is widely used in industry, agriculture, transportation, urban community and other fields.

[0003] When the transformer fails, multiple operating data will change, however, if only one operating data changes, it does not mean that the operation of the transformer is abnormal. If the transformer is repaired only when one operating data changes, not only the maintenance cost of the transformer is increased, but also the work intensity of the repair personnel is increased. SUMMARY

[0004] In order to solve the above technical problems, the present application provides a transformer fault diagnosis method and system based on data analysis, which solves the problems in the background technology.

[0005] In order to achieve the above purposes, the technical scheme adopted by the present application is:

[0006] A transformer fault diagnosis method based on data analysis, comprising:

[0007] Obtaining historical operating data of the transformer and maintenance data of the transformer, performing causal analysis on the historical operating data of the transformer and the maintenance data of the transformer, and determining a data group with correlation;

[0008] According to the data group with correlation, performing time analysis processing to determine the change delay time of the correlation data;

[0009] Obtaining real-time operating data of the transformer, performing fault diagnosis on the real-time operating data of the transformer according to the change delay time of the correlation data, and determining the real-time state of the transformer.

[0010] Preferably, the step of obtaining the historical operating data of the transformer and the maintenance data of the transformer, performing causal analysis on the historical operating data of the transformer and the maintenance data of the transformer, and determining the data group with correlation comprises the following steps:

[0011] acquire a virtual storage identifier of the transformer to be diagnosed, perform identifier matching processing on the database system according to the virtual storage identifier of the transformer to be diagnosed, and determine a data storage position of the transformer to be diagnosed;

[0012] perform data reading processing according to the data storage position of the transformer to be diagnosed, and acquire historical operation data of the transformer and maintenance data of the transformer;

[0013] perform data reading processing on the maintenance data of the transformer according to a transformer maintenance type, and determine a transformer fault occurrence time and a transformer fault maintenance completion time; the transformer maintenance type includes transformer fault maintenance and transformer normal maintenance;

[0014] perform causal analysis processing on the historical operation data of the transformer according to the transformer fault occurrence time and the transformer fault maintenance completion time, and determine a data group having correlation.

[0015] Preferably, the performing of the causal analysis processing on the historical operation data of the transformer according to the transformer fault occurrence time and the transformer fault maintenance completion time, and the determining of the data group having correlation specifically include the following steps:

[0016] perform data reading processing on the historical operation data of the transformer according to the transformer fault occurrence time and the transformer fault maintenance completion time, respectively, acquire operation data of the transformer at the time of the fault and operation data of the transformer at the time of normal operation;

[0017] perform intercept processing on the historical operation data of the transformer according to the operation data of the transformer at the time of normal operation, and acquire operation data of the transformer before the fault; the operation data of the transformer before the fault is specifically operation data of the transformer closest to the transformer fault occurrence time;

[0018] perform difference calculation processing on the operation data of the transformer before the fault and the operation data of the transformer at the time of the fault, and acquire a first deviation value of the operation data of the transformer;

[0019] perform calculation and analysis processing based on the first deviation value of the operation data of the transformer, and determine the data group having correlation.

[0020] Preferably, the performing of the calculation and analysis processing based on the first deviation value of the operation data of the transformer, and the determining of the data group having correlation specifically include the following steps:

[0021] perform difference calculation processing on a time corresponding to the operation data of the transformer before the fault and the transformer fault occurrence time, and determine an abnormal change time of the transformer;

[0022] The first deviation value of the transformer operation data is processed by mean calculation based on the abnormal change time of the transformer, to determine the unit time change rate of the transformer operation data.

[0023] The unit time change rate of the transformer operation data is processed by comparative analysis based on the historical operation data of the transformer and the maintenance data of the transformer, to determine the data group with correlation.

[0024] Preferably, the unit time change rate of the transformer operation data is processed by comparative analysis based on the historical operation data of the transformer and the maintenance data of the transformer, to determine the data group with correlation, which specifically includes the following steps:

[0025] The maintenance data of the transformer is processed by data matching based on the fault occurrence time of the transformer and the transformer maintenance type, to determine the last fault maintenance completion time of the transformer;

[0026] The last fault maintenance completion time of the transformer and the fault occurrence time of the transformer are processed by difference calculation, to determine the operation time of the transformer after the fault maintenance is completed;

[0027] The historical operation data of the transformer is processed by interception based on the last fault maintenance completion time of the transformer, to obtain the operation data of the transformer after the last fault maintenance is completed;

[0028] The unit time change rate of the transformer operation data is processed by comparative analysis based on the operation time of the transformer after the fault maintenance is completed and the operation data of the transformer after the last fault maintenance is completed, to determine the data group with correlation.

[0029] Preferably, the unit time change rate of the transformer operation data is processed by comparative analysis based on the operation time of the transformer after the fault maintenance is completed and the operation data of the transformer after the last fault maintenance is completed, to determine the data group with correlation, which specifically includes the following steps:

[0030] The operation data of the transformer after the last fault maintenance is completed and the operation data of the transformer at the fault time are processed by difference calculation, to determine the second deviation value of the transformer operation data;

[0031] The second deviation value of the transformer operation data is processed by mean calculation based on the operation time of the transformer after the fault maintenance is completed, to determine the unit time standard change rate of the transformer operation data;

[0032] The unit time change rate of the transformer operation data is processed by verification based on the unit time standard change rate of the transformer operation data;

[0033] If the unit time change rate of the transformer operation data is greater than the unit time standard change rate of the transformer operation data, the transformer fault is related to the operation data, and the transformer operation data greater than the unit time standard change rate of the transformer operation data is set as a data group with correlation;

[0034] If the unit time change rate of the transformer operation data is less than or equal to the unit time standard change rate of the transformer operation data, the transformer fault is not related to the operation data.

[0035] Preferably, the time analysis processing according to the data group with correlation determines the change delay time of the correlation data, and specifically includes the following steps:

[0036] Based on the data group with correlation, the operation data of the transformer in normal state and the operation data before the transformer fault are subjected to data type matching processing to determine the normal operation data of the data group with correlation and the operation data to be verified of the data group with correlation.

[0037] Based on the normal operation data of the data group with correlation, the operation data to be verified of the data group with correlation is subjected to time analysis processing to determine the change delay time of the correlation data.

[0038] Preferably, the time analysis processing based on the normal operation data of the data group with correlation to determine the change delay time of the correlation data specifically includes the following steps:

[0039] Based on the normal operation data of the data group with correlation, the operation data to be verified of the data group with correlation is subjected to matching processing.

[0040] When the first data different from the normal operation data of the data group with correlation appears in the operation data to be verified of the data group with correlation, the appearance time of the data is recorded as the first starting time of operation anomaly.

[0041] When the second data different from the normal operation data of the data group with correlation appears in the operation data to be verified of the data group with correlation, the appearance time of the data is recorded as the second starting time of operation anomaly.

[0042] The first starting time of operation anomaly and the second starting time of operation anomaly are subjected to difference calculation processing to determine the change delay time of the correlation data.

[0043] Preferably, the fault diagnosis of the real-time operation data of the transformer according to the change delay time of the correlation data determines the real-time state of the transformer, and specifically includes the following steps:

[0044] Based on the normal operation data of the data group with correlation, the real-time operation data of the transformer is diagnosed for fault;

[0045] If all the operation data in the real-time operation data of the transformer is completely same as the normal operation data of the data group with correlation, the transformer is normal operation;

[0046] If the first operation data different from the normal operation data of the data group with correlation appears in all the operation data in the real-time operation data of the transformer, and the second operation data different from the normal operation data of the data group with correlation appears in the real-time operation data of the transformer within the change extension time of the correlation data, the transformer is abnormal operation;

[0047] If the first operation data different from the normal operation data of the data group with correlation appears in all the operation data in the real-time operation data of the transformer, and the second operation data different from the normal operation data of the data group with correlation does not appear in the real-time operation data of the transformer within the change extension time of the correlation data, the transformer is normal operation.

[0048] Further, a transformer fault diagnosis system based on data analysis is proposed, which is used to realize the transformer fault diagnosis method based on data analysis as above, comprising:

[0049] A fault diagnosis terminal is used to control each module to perform causal analysis, time analysis and fault diagnosis on the historical operation data of the transformer and the maintenance data of the transformer, and determine the real-time state of the transformer; the fault diagnosis terminal is used to control data transmission and information interaction between each module;

[0050] A data retrieval module is used to perform data retrieval processing on the database system according to the virtual storage identifier of the transformer to be diagnosed, and obtain the historical operation data of the transformer and the maintenance data of the transformer;

[0051] A database system is used to store the historical operation data of the transformer and the maintenance data of the transformer;

[0052] A data matching module is used to perform data matching processing on the historical operation data of the transformer according to the maintenance data of the transformer, and determine the operation data when the transformer fails and the operation data before the transformer fails;

[0053] A first deviation value calculation module is used to perform difference calculation processing on the operation data before the transformer fails and the operation data when the transformer fails, and obtain the first deviation value of the operation data of the transformer;

[0054] The change rate calculation module is configured to perform mean value calculation on the first deviation value of the transformer operation data, and determine the change rate per unit time of the transformer operation data.

[0055] The second difference calculation module is configured to perform difference calculation on the operation data after the last fault maintenance of the transformer and the operation data when the transformer fails, and determine the second deviation value of the transformer operation data.

[0056] The correlation analysis module is configured to perform correlation analysis on the change rate per unit time of the transformer operation data and the second deviation value of the transformer operation data, and determine the data group with correlation.

[0057] The time analysis module is configured to perform time analysis on the to-be-verified operation data of the data group with correlation based on the normal operation data of the data group with correlation, and determine the change delay time of the correlation data.

[0058] The state diagnosis module is configured to perform fault diagnosis on the real-time operation data of the transformer according to the change delay time of the correlation data, and determine the real-time state of the transformer.

[0059] Compared with the prior art, the present application provides a transformer fault diagnosis method and system based on data analysis, which has the following beneficial effects:

[0060] The present application determines the data group with correlation by matching and calculating the historical operation data of the transformer based on the maintenance data of the transformer. In addition, the change delay time of the correlation data is determined by analyzing the data group with correlation in time. When the data change rule corresponding to the data group with correlation conforms to the change delay time of the correlation data, it can be determined that the transformer is abnormal, and the maintenance personnel can be dispatched to maintain the transformer. This avoids frequent maintenance of the transformer by the maintenance personnel, reduces the working intensity of the maintenance personnel, and reduces the maintenance cost of the transformer. BRIEF DESCRIPTION OF DRAWINGS

[0061] Figure 1 A flowchart of steps S100-S300 in a transformer fault diagnosis method based on data analysis is provided.

[0062] Figure 2 A structural block diagram of a transformer fault diagnosis system based on data analysis is provided. DETAILED DESCRIPTION

[0063] The following description is used to disclose the present application to enable a person skilled in the art to implement the present application. The preferred embodiments in the following description are only as examples, and other obvious modifications can be thought of by those skilled in the art.

[0064] Referring to Figure 1 As shown in the figure, a transformer fault diagnosis method based on data analysis comprises:

[0065] S100, obtaining historical operation data of the transformer and maintenance data of the transformer, performing causal analysis on the historical operation data of the transformer and the maintenance data of the transformer, and determining a data group with correlation;

[0066] S200, according to the data group with correlation, performing time analysis processing, and determining a change delay time of the correlation data;

[0067] S300, obtaining real-time operation data of the transformer, performing fault diagnosis on the real-time operation data of the transformer according to the change delay time of the correlation data, and determining a real-time state of the transformer;

[0068] Those skilled in the art can understand that when the transformer fails, multiple operation data will be abnormal, and there will be a certain correlation between the abnormal operation data. For example, transformer short circuit causes temperature rise, and in the process of transformer short circuit, voltage, current and temperature will change. However, the abnormal data does not change at the same time. A certain period of time after the occurrence of abnormal data, the data with correlation will change. For example, after the transformer short circuit, the temperature does not rise immediately, but rises in a certain period of time. Therefore, when a certain data of the transformer changes, it cannot be said that the transformer is abnormal immediately. It is necessary to analyze other data with correlation to determine whether the data with correlation changes in a certain period of time. If there is no change, it means that the transformer will not fail. If a data is abnormal, the transformer will be repaired, which will increase the repair cost of the transformer and the work intensity of the repair personnel.

[0069] Embodiment 1

[0070] Step S100, obtaining historical operation data of the transformer and maintenance data of the transformer, performing causal analysis on the historical operation data of the transformer and the maintenance data of the transformer, and determining a data group with correlation comprises the following steps:

[0071] S101, obtaining a virtual storage identifier of the transformer to be diagnosed, performing identifier matching processing on the database system according to the virtual storage identifier of the transformer to be diagnosed, and determining a data storage position of the transformer to be diagnosed;

[0072] It can be understood that when data is stored, a virtual identifier is assigned to the stored data to facilitate subsequent data reading. Therefore, the data storage location of the transformer is determined by the virtual storage identifier;

[0073] S102, according to the data storage location of the transformer to be diagnosed, data reading processing is performed to obtain the historical operation data of the transformer and the maintenance data of the transformer;

[0074] S103, according to the transformer maintenance type, the maintenance data of the transformer is subjected to data reading processing to determine the fault occurrence time of the transformer and the fault maintenance completion time of the transformer; wherein the transformer maintenance type includes transformer fault maintenance and transformer normal maintenance;

[0075] S104, according to the fault occurrence time of the transformer and the fault maintenance completion time of the transformer, the historical operation data of the transformer is subjected to causal analysis processing to determine the data group with correlation.

[0076] The step S104, according to the fault occurrence time of the transformer and the fault maintenance completion time of the transformer, the historical operation data of the transformer is subjected to causal analysis processing to determine the data group with correlation, specifically includes the following steps:

[0077] S1041, according to the fault occurrence time of the transformer and the fault maintenance completion time of the transformer, the historical operation data of the transformer is subjected to data reading processing to obtain the operation data of the transformer at the time of fault and the operation data of the transformer at the time of normal operation;

[0078] S1042, according to the operation data of the transformer at the time of normal operation, the historical operation data of the transformer is subjected to intercept processing to obtain the operation data of the transformer before the fault occurs; wherein the operation data of the transformer before the fault occurs is specifically the operation data of the transformer closest to the fault occurrence time of the transformer;

[0079] It can be understood that after the completion of the transformer fault maintenance, the operation data of the transformer is normal data. Therefore, the operation data of the transformer before the fault is intercepted by the normal operation data of the transformer. However, the data of the transformer before the fault is normal data. If all the normal operation data is analyzed, the calculation amount will be increased. Therefore, the normal operation data of the transformer needs to be screened. The fault of the transformer does not occur suddenly, but is a process. During this process, some data of the transformer is abnormal. The beginning of this process is the last normal operation data before the fault of the transformer. Therefore, the time information of the operation data of the transformer before the fault is closest to the fault occurrence time of the transformer;

[0080] S1043, difference calculation is performed on the operation data before the transformer failure and the operation data when the transformer fails to obtain a first deviation value of the transformer operation data;

[0081] S1044, based on the first deviation value of the transformer operation data, calculation and analysis processing is performed to determine a data group having relevance;

[0082] It can be understood that in order to determine which data of the transformer has relevance, the operation data when the transformer fails needs to be analyzed, because only when the transformer fails, the data having relevance will change, and the failure time of the transformer is recorded in the maintenance data of the transformer.

[0083] The step S1044, based on the first deviation value of the transformer operation data, calculation and analysis processing is performed to determine a data group having relevance, specifically includes the following steps:

[0084] S10441, difference calculation is performed on the time corresponding to the operation data before the transformer failure and the failure time of the transformer to determine an abnormal change time of the transformer;

[0085] S10442, based on the abnormal change time of the transformer, mean calculation is performed on the first deviation value of the transformer operation data to determine a unit time change rate of the transformer operation data;

[0086] S10443, based on the historical operation data of the transformer and the maintenance data of the transformer, comparison and analysis processing is performed on the unit time change rate of the transformer operation data to determine a data group having relevance;

[0087] It can be understood that when the transformer fails, it is a process, and the data change rate causing the transformer failure is higher or lower than the change rate during normal operation, so to determine the parameters causing the transformer failure, the unit time change rate of the transformer operation data needs to be determined first, and then comparison and judgment are performed on the unit time change rate of the transformer operation data to determine the data group having relevance causing the transformer failure.

[0088] The step S10443, based on the historical operation data of the transformer and the maintenance data of the transformer, comparison and analysis processing is performed on the unit time change rate of the transformer operation data to determine a data group having relevance, specifically includes the following steps:

[0089] S104431, based on the failure time of the transformer and the maintenance type of the transformer, data matching processing is performed on the maintenance data of the transformer to determine the completion time of the last failure maintenance of the transformer;

[0090] S104432, difference calculation processing is performed on the last transformer fault repair completion time and the transformer fault occurrence time to determine the operation time of the transformer after the fault repair is completed;

[0091] S104433, based on the last transformer fault repair completion time, the historical operation data of the transformer is intercepted to obtain the operation data of the transformer after the last fault repair is completed;

[0092] S104434, according to the operation time of the transformer after the fault repair is completed and the operation data of the transformer after the last fault repair is completed, the unit time change rate of the transformer operation data is compared and analyzed to determine the data group with correlation;

[0093] In step S104434, according to the operation time of the transformer after the fault repair is completed and the operation data of the transformer after the last fault repair is completed, the unit time change rate of the transformer operation data is compared and analyzed to determine the data group with correlation, which specifically includes the following steps:

[0094] S1044341, difference calculation processing is performed on the operation data of the transformer after the last fault repair is completed and the operation data of the transformer at the time of the fault to determine the second deviation value of the transformer operation data;

[0095] S1044342, based on the operation time of the transformer after the fault repair is completed, the second deviation value of the transformer operation data is mean value calculated to determine the unit time standard change rate of the transformer operation data;

[0096] S1044343, based on the unit time standard change rate of the transformer operation data, the unit time change rate of the transformer operation data is verified;

[0097] S1044344, if the unit time change rate of the transformer operation data is greater than the unit time standard change rate of the transformer operation data, the transformer fault is related to the operation data, and the transformer operation data greater than the unit time standard change rate of the transformer operation data is set as the data group with correlation;

[0098] S1044345, if the unit time change rate of the transformer operation data is less than or equal to the unit time standard change rate of the transformer operation data, the transformer fault is not related to the operation data;

[0099] It can be understood that the unit time change rate of the transformer operation data represents whether the operation of the transformer is abnormal, and whether the unit time change rate of the transformer operation data is abnormal needs to set a control group, and the control group is determined by the normal operation data of the transformer, so by calculating and analyzing the normal operation data of the transformer, the unit time standard change rate of the transformer operation data is determined, and then the unit time standard change rate of the transformer operation data and the unit time change rate of the transformer operation data are compared and judged to determine the data group with correlation.

[0100] Embodiment 2

[0101] Step S200, according to the data group with correlation, time analysis processing is performed to determine the change delay time of the correlation data, which specifically includes the following steps:

[0102] S201, based on the data group with correlation, data type matching processing is performed on the normal operation data of the transformer and the operation data before the transformer fails to determine the normal operation data of the data group with correlation and the operation data to be verified of the data group with correlation;

[0103] S202, based on the normal operation data of the data group with correlation, time analysis processing is performed on the operation data to be verified of the data group with correlation to determine the change delay time of the correlation data.

[0104] Among them, step S202, based on the normal operation data of the data group with correlation, time analysis processing is performed on the operation data to be verified of the data group with correlation to determine the change delay time of the correlation data, specifically includes the following steps:

[0105] S2021, based on the normal operation data of the data group with correlation, matching processing is performed on the operation data to be verified of the data group with correlation;

[0106] S2022, when the first data different from the normal operation data of the data group with correlation appears in the operation data to be verified of the data group with correlation, the appearance time of the data is recorded as the first starting time of operation exception;

[0107] S2023, when the second data different from the normal operation data of the data group with correlation appears in the operation data to be verified of the data group with correlation, the appearance time of the data is recorded as the second starting time of operation exception;

[0108] S2024, difference calculation processing is performed on the first starting time of operation exception and the second starting time of operation exception to determine the change delay time of the correlation data;

[0109] It can be understood that when the transformer is abnormal, not all the associated data are abnormal at the same time, but the data changes in a certain time, that is, the change delay time of the associated data, when the data of the transformer changes, the change of the other associated data is monitored within the change delay time of the associated data to determine whether the change of the other associated data occurs, if the change occurs, it indicates that the transformer is abnormal and needs to be repaired, if the change does not occur, it indicates that the transformer is normal.

[0110] Embodiment 3

[0111] Step S300, according to the change delay time of the associated data, the real-time running data of the transformer is diagnosed for fault, and the real-time state of the transformer is determined, which specifically includes the following steps:

[0112] S301, based on the normal running data of the data group with correlation, the real-time running data of the transformer is diagnosed for fault;

[0113] S302, if all the running data in the real-time running data of the transformer is the same as the normal running data of the data group with correlation, the transformer is normal;

[0114] S303, if the first running data in the real-time running data of the transformer is different from the normal running data of the data group with correlation, and the second running data in the real-time running data of the transformer is different from the normal running data of the data group with correlation within the change delay time of the associated data, the transformer is abnormal;

[0115] S304, if the first running data in the real-time running data of the transformer is different from the normal running data of the data group with correlation, and the second running data in the real-time running data of the transformer is not different from the normal running data of the data group with correlation within the change delay time of the associated data, the transformer is normal;

[0116] It can be understood that during the operation of the transformer, the fluctuation of the data may occur, and the fluctuation of the data may be abnormal. If only one data is used to determine that the operation of the transformer is abnormal, the judgment result is one-sided. Therefore, whether the operation of the transformer is abnormal is determined by whether the other data is abnormal within the change delay time of the associated data, so as to avoid frequent repair of the transformer.

[0117] Referring to Figure 2 Fig. 1 shows a transformer fault diagnosis system based on data analysis, which is used to realize the transformer fault diagnosis method based on data analysis as described above, and includes:

[0118] The fault diagnosis terminal is used for controlling each module to perform causal analysis, time analysis and fault diagnosis on historical operation data of the transformer and maintenance data of the transformer, and determine the real-time state of the transformer; the fault diagnosis terminal is used for controlling data transmission and information interaction between each module;

[0119] The data retrieval module performs data retrieval processing on the database system according to the virtual storage identifier of the transformer to be diagnosed, and obtains the historical operation data of the transformer and the maintenance data of the transformer;

[0120] The database system is used for storing the historical operation data of the transformer and the maintenance data of the transformer;

[0121] The data matching module performs data matching processing on the historical operation data of the transformer according to the maintenance data of the transformer, and determines the operation data when the transformer fails and the operation data before the transformer fails;

[0122] The first deviation value calculation module performs difference calculation processing on the operation data before the transformer fails and the operation data when the transformer fails, and obtains the first deviation value of the operation data of the transformer;

[0123] The change rate calculation module is used for performing mean value calculation processing on the first deviation value of the operation data of the transformer, and determining the unit time change rate of the operation data of the transformer;

[0124] The second difference calculation module is used for performing difference calculation processing on the operation data after the last fault maintenance of the transformer is completed and the operation data when the transformer fails, and determining the second deviation value of the operation data of the transformer;

[0125] The correlation analysis module performs correlation analysis on the unit time change rate of the operation data of the transformer and the second deviation value of the operation data of the transformer, and determines the data group with correlation;

[0126] The time analysis module performs time analysis processing on the to-be-verified operation data of the data group with correlation based on the normal operation data of the data group with correlation, and determines the change delay time of the correlation data;

[0127] The state diagnosis module performs fault diagnosis on the real-time operation data of the transformer according to the change delay time of the correlation data, and determines the real-time state of the transformer.

[0128] The above shows and describes the basic principles, main features and advantages of the present application. Those skilled in the art should understand that the present application is not limited to the above-mentioned embodiments, and the above-mentioned embodiments and descriptions in the specification are only the principles of the present application. Various changes and improvements can be made without departing from the spirit and scope of the present application, and these changes and improvements all fall within the scope of the claimed present application. The scope of protection of the present application is defined by the appended claims and their equivalents.

Claims

1. A transformer fault diagnosis method based on data analysis, characterized by, include: Obtain historical operating data and maintenance data of the transformer, perform causal analysis on the historical operating data and maintenance data of the transformer, and identify data groups with correlation. Based on the correlated data groups, perform time analysis to determine the change delay time of the correlated data; The system acquires real-time operating data of the transformer, extends the time frame based on changes in related data, performs fault diagnosis on the real-time operating data of the transformer, and determines the real-time status of the transformer.

2. The transformer fault diagnosis method based on data analysis according to claim 1, characterized in that, The process of acquiring historical operating data and maintenance data of the transformer, and performing causal analysis on the historical operating data and maintenance data to determine correlated data groups specifically includes the following steps: Obtain the virtual storage identifier of the transformer to be diagnosed, and perform identifier matching processing on the database system based on the virtual storage identifier of the transformer to be diagnosed to determine the data storage location of the transformer to be diagnosed. Based on the data storage location of the transformer to be diagnosed, data reading and processing are performed to obtain the transformer's historical operating data and maintenance data; Based on the transformer repair type, the transformer maintenance data is read and processed to determine the time when the transformer fault occurred and the time when the transformer fault repair was completed; wherein, the transformer repair type includes transformer fault repair and transformer normal maintenance; Based on the timing of transformer failures and the completion of repairs, causal analysis is performed on historical transformer operating data to identify correlated data groups.

3. The transformer fault diagnosis method based on data analysis according to claim 2, characterized in that, The step of performing causal analysis on the historical operating data of the transformer based on the time of transformer fault occurrence and the time of transformer fault repair completion to determine the data groups with correlation specifically includes the following steps: Based on the time of transformer failure and the time of completion of transformer repair, the historical operating data of the transformer is read and processed to obtain the operating data when the transformer is in failure and the operating data when the transformer is in normal operation. Based on the transformer's normal operating data, the historical operating data of the transformer is extracted and processed to obtain the operating data before the transformer failed; specifically, the operating data before the transformer failed refers to the operating data of the transformer closest to the time when the transformer failed. The operating data before the transformer failure and the operating data at the time of the transformer failure are calculated by difference to obtain the first deviation value of the transformer operating data. Based on the first deviation value of the transformer operation data, calculation and analysis are performed to determine the data groups with correlation.

4. The transformer fault diagnosis method based on data analysis according to claim 3, characterized in that, The process of calculating and analyzing the first deviation value of transformer operating data to determine the correlated data groups specifically includes the following steps: The time of abnormal change in the transformer is determined by calculating the difference between the time corresponding to the operating data before the transformer failure and the time when the transformer failure occurred. Based on the time of abnormal changes in transformers, the first deviation value of transformer operating data is averaged to determine the rate of change of transformer operating data per unit time. The unit time change rate of the transformer operation data is compared and analyzed based on the historical operation data and the maintenance data of the transformer, and a data group with correlation is determined.

5. The transformer fault diagnosis method based on data analysis according to claim 4, characterized in that, The unit time change rate of the transformer operation data is compared and analyzed based on the historical operation data and the maintenance data of the transformer, and a data group with correlation is determined. The maintenance data of the transformer is matched based on the fault occurrence time of the transformer and the transformer maintenance type, and the last fault maintenance completion time of the transformer is determined. The running time of the transformer after the fault maintenance is completed is determined by calculating the difference between the last fault maintenance completion time of the transformer and the fault occurrence time of the transformer. The historical operation data of the transformer is intercepted based on the last fault maintenance completion time of the transformer, and the operation data after the last fault maintenance completion of the transformer is obtained. The unit time change rate of the transformer operation data is compared and analyzed based on the running time of the transformer after the fault maintenance is completed and the operation data after the last fault maintenance completion of the transformer, and a data group with correlation is determined.

6. The transformer fault diagnosis method based on data analysis according to claim 5, characterized in that, The unit time change rate of the transformer operation data is compared and analyzed based on the running time of the transformer after the fault maintenance is completed and the operation data after the last fault maintenance completion of the transformer, and a data group with correlation is determined. The second deviation value of the transformer operation data is determined by calculating the difference between the operation data after the last fault maintenance completion of the transformer and the operation data at the time of the fault of the transformer. The unit time standard change rate of the transformer operation data is determined by mean calculation of the second deviation value of the transformer operation data based on the running time of the transformer after the fault maintenance is completed. The unit time change rate of the transformer operation data is verified based on the unit time standard change rate of the transformer operation data. If the unit time change rate of the transformer operation data is greater than the unit time standard change rate of the transformer operation data, the transformer fault is related to the operation data, and the transformer operation data greater than the unit time standard change rate of the transformer operation data is set as the data group with correlation. If the unit time change rate of the transformer operation data is less than or equal to the unit time standard change rate of the transformer operation data, the transformer fault is not related to the operation data.

7. The transformer fault diagnosis method based on data analysis according to claim 1, characterized in that, The change delay time of the related data is determined by time analysis of the data group with correlation, which includes the following steps: The normal operation data of the data group with correlation and the operation data to be verified of the data group with correlation are determined by data type matching of the operation data of the transformer when normal and the operation data of the transformer before the fault occurs based on the data group with correlation. The change delay time of the related data is determined by time analysis of the operation data to be verified of the data group with correlation based on the normal operation data of the data group with correlation.

8. The transformer fault diagnosis method based on data analysis according to claim 7, characterized in that, The time analysis processing of the to-be-verified running data of the data group with correlation based on the normal running data of the data group with correlation comprises the following steps: The matching processing of the to-be-verified running data of the data group with correlation based on the normal running data of the data group with correlation; When the first data different from the normal running data of the data group with correlation appears in the to-be-verified running data of the data group with correlation, the time of the data is recorded as the first starting time of running anomaly; When the second data different from the normal running data of the data group with correlation appears in the to-be-verified running data of the data group with correlation, the time of the data is recorded as the second starting time of running anomaly; The difference calculation processing of the first starting time of running anomaly and the second starting time of running anomaly is performed to determine the change delay time of the correlation data.

9. The transformer fault diagnosis method based on data analysis according to claim 1, characterized in that, The fault diagnosis of the real-time running data of the transformer based on the change delay time of the correlation data to determine the real-time state of the transformer comprises the following steps: The fault diagnosis of the real-time running data of the transformer based on the normal running data of the data group with correlation; If all the running data in the real-time running data of the transformer are completely the same as the normal running data of the data group with correlation, the transformer is in normal operation; If the first running data different from the normal running data of the data group with correlation appears in the real-time running data of the transformer, and the second running data different from the normal running data of the data group with correlation appears in the real-time running data of the transformer within the change delay time of the correlation data, the transformer is in abnormal operation; If the first running data different from the normal running data of the data group with correlation appears in the real-time running data of the transformer, and the second running data different from the normal running data of the data group with correlation does not appear in the real-time running data of the transformer within the change delay time of the correlation data, the transformer is in normal operation.

10. A transformer fault diagnosis system based on data analysis, for implementing a transformer fault diagnosis method based on data analysis as claimed in any one of claims 1-9, characterized in that, It comprises: A fault diagnosis terminal for controlling each module to perform causal analysis, time analysis and fault diagnosis on the historical running data of the transformer and the maintenance data of the transformer to determine the real-time state of the transformer; the fault diagnosis terminal is used for controlling data transmission and information interaction between each module; A data retrieval module for performing data retrieval processing on a database system according to a virtual storage identifier of a to-be-diagnosed transformer to obtain the historical running data of the transformer and the maintenance data of the transformer; A database system for storing the historical running data of the transformer and the maintenance data of the transformer; A data matching module for performing data matching processing on the historical running data of the transformer according to the maintenance data of the transformer to determine the running data when the transformer is in fault and the running data before the transformer is in fault; The first deviation value calculation module is configured to calculate the difference between the operation data before the transformer fails and the operation data when the transformer fails to obtain a first deviation value of the operation data of the transformer. The change rate calculation module is configured to calculate the mean value of the first deviation value of the operation data of the transformer to determine the change rate of the operation data of the transformer per unit time. The second difference value calculation module is configured to calculate the difference between the operation data after the last fault maintenance of the transformer is completed and the operation data when the transformer fails to determine a second deviation value of the operation data of the transformer. The correlation analysis module is configured to analyze the correlation between the change rate of the operation data of the transformer per unit time and the second deviation value of the operation data of the transformer to determine a data group with correlation. The time analysis module is configured to analyze the to-be-verified operation data of the data group with correlation based on the normal operation data of the data group with correlation to determine the change delay time of the correlation data. The state diagnosis module is configured to diagnose the real-time operation data of the transformer based on the change delay time of the correlation data to determine the real-time state of the transformer.

Images