A method and system for handling transformer faults

Abstract

The present application discloses a transformer fault processing method and system, the method comprising: obtaining the working condition information of the transformer to be tested; the working condition information comprises at least one of the use time, use operation and environmental information; according to the working condition information, obtaining the first probability of the transformer to be tested having a progressive fault and the second probability of the transformer to be tested having a sudden fault; if the first probability satisfies the first preset condition, collecting the first operation information of the transformer to be tested, judging whether the transformer to be tested has a progressive fault according to the first change trend of the first operation information within the first preset sliding window; if the second probability satisfies the second preset condition, collecting the second operation information of the transformer to be tested, judging whether the transformer to be tested has a sudden fault according to the second change trend of the second operation information within the second preset sliding window. The use of the embodiments of the present application can improve the accuracy of fault judgment.

Description

Technical Field

[0001] The present application relates to the technical field of transformers, and in particular to a transformer fault processing method and system. Background Art

[0002] As one of the most important equipment in the power system, the transformer operates under various complex electrical and mechanical conditions. Therefore, the effective detection of potential transformer faults has important engineering value for maintaining the efficient operation of the power grid. At present, the main method is to judge whether the transformer has a fault by comparing whether the equipment status parameters at a certain moment are greater than the threshold. This method is relatively simple and has low judgment accuracy. Summary of the invention

[0003] The present application provides a transformer fault processing method and system to solve the problem of low judgment accuracy in the prior art.

[0004] To achieve the above objectives, the present application provides a transformer fault processing method, comprising:

[0005] Acquire the working condition information of the transformer to be tested; the working condition information includes at least one of the usage time, usage operation and environmental information;

[0006] According to the working condition information, a first probability of a progressive fault occurring in the transformer to be tested and a second probability of a sudden fault occurring are obtained;

[0007] If the first probability satisfies a first preset condition, first operating information of the transformer to be tested is collected, and whether a progressive fault occurs in the transformer to be tested according to a first change trend of the first operating information within a first preset sliding window is determined; wherein the first operating information includes at least one of oil temperature, vibration information, and partial discharge information;

[0008] If the second probability meets the second preset condition, the second operating information of the transformer to be tested is collected, and according to the second change trend of the second operating information within the second preset sliding window, it is determined whether the transformer to be tested has a sudden fault; wherein, the first operating information includes at least one of oil temperature, vibration information and partial discharge information, and the size of the first preset sliding window is larger than the size of the second preset sliding window.

[0009] As an improvement of the above solution, judging whether a progressive fault occurs in the transformer to be tested according to a first change trend of the first operating information in a first preset sliding window includes:

[0010] Performing feature extraction on the first operation information in the first preset sliding window to obtain a first operation feature;

[0011] According to the first operating characteristic, drawing a first characteristic curve;

[0012] According to the first characteristic curve, it is determined whether a progressive fault occurs in the transformer to be tested.

[0013] As an improvement of the above solution, judging whether a progressive fault occurs in the transformer to be tested according to the first characteristic curve includes:

[0014] Using a pre-trained first fault determination model, judging whether a progressive fault occurs in the transformer to be tested according to the first characteristic curve;

[0015] Wherein, the first fault determination model is trained by the following steps:

[0016] Acquire first historical operation information of a first test transformer under a progressive fault;

[0017] Performing feature extraction on the first historical operation information in the first preset sliding window to obtain a first historical operation feature;

[0018] Draw a first historical characteristic curve according to the first historical operation characteristic;

[0019] The first historical characteristic curve is used to perform model training to obtain the first fault determination model.

[0020] As an improvement of the above solution, judging whether a sudden fault occurs in the transformer to be tested according to a second change trend of the second operating information in a second preset sliding window includes:

[0021] Performing feature extraction on the second operation information in the second preset sliding window to obtain a second operation feature;

[0022] According to the second operating characteristic, drawing a second characteristic curve;

[0023] According to the second characteristic curve, it is determined whether a sudden fault occurs in the transformer to be tested.

[0024] As an improvement of the above solution, judging whether a sudden fault occurs in the transformer to be tested according to the second characteristic curve includes:

[0025] Using a pre-trained second fault determination model, judging whether a sudden fault occurs in the transformer to be tested according to the second characteristic curve;

[0026] Wherein, the second fault determination model is trained by the following steps:

[0027] Acquire second historical operation information of the second test transformer under the sudden fault;

[0028] Performing feature extraction on the second historical operation information in the second preset sliding window to obtain a second historical operation feature;

[0029] According to the second historical operation characteristic, drawing a second historical characteristic curve;

[0030] The second historical characteristic curve is used to perform model training to obtain the second fault determination model.

[0031] As an improvement of the above solution, obtaining the first probability of a progressive fault occurring in the transformer to be tested and the second probability of a sudden fault occurring in the transformer to be tested according to the operating condition information includes:

[0032] Obtaining a first historical probability of a progressive fault occurring in the third test transformer under different historical operating condition information and a second historical probability of a sudden fault occurring;

[0033] Performing model training using the historical operating condition information, the first historical probability, and the second historical probability to obtain a trained fault probability determination model;

[0034] The fault probability determination model is used to obtain the first probability and the second probability according to the operating condition information.

[0035] As an improvement of the above solution, the step of obtaining a first historical probability of a progressive fault occurring in the third test transformer under different historical operating condition information and a second historical probability of a sudden fault occurring includes:

[0036] Obtaining historical events of the third test transformer under different historical operating condition information, and counting the total number of events of the historical events;

[0037] Counting the number of first events in which progressive failures occurred and the number of second events in which sudden failures occurred in the historical events;

[0038] Calculating the first historical probability according to the total number of events and the first number of events;

[0039] The second historical probability is calculated based on the total number of events and the second number of events.

[0040] As an improvement of the above solution, after judging whether a progressive fault occurs in the transformer to be tested according to a first change trend of the first operating information in a first preset sliding window, the transformer fault processing method further includes:

[0041] If it is determined that the transformer to be tested has a progressive fault, then judging that the transformer to be tested is in a progressive fault stage according to the first change trend;

[0042] According to the stages, a repair strategy for the transformer to be tested is obtained.

[0043] As an improvement of the above solution, judging that the transformer to be tested is in a progressive fault stage according to the first change trend includes:

[0044] If the first change trend satisfies the first change trend condition, it is determined that the transformer to be tested is in a mild stage;

[0045] If the first change trend satisfies the second change trend condition, it is determined that the transformer to be tested is in a medium stage;

[0046] If the first change trend meets the third change trend condition, it is determined that the transformer to be tested is in a severe stage.

[0047] To achieve the above objectives, the present application also provides a transformer fault processing system, including:

[0048] A working condition information acquisition module, used to acquire working condition information of the transformer to be tested; the working condition information includes at least one of usage time, usage operation and environmental information;

[0049] A probability acquisition module, used to obtain a first probability of a progressive fault occurring in the transformer to be tested and a second probability of a sudden fault occurring in the transformer to be tested according to the operating condition information;

[0050] a first fault judgment module, configured to collect first operating information of the transformer to be tested if the first probability satisfies a first preset condition, and judge whether a progressive fault occurs in the transformer to be tested according to a first change trend of the first operating information within a first preset sliding window; wherein the first operating information includes at least one of oil temperature, vibration information and partial discharge information;

[0051] The second fault judgment module is used to collect second operating information of the transformer to be tested if the second probability meets a second preset condition, and judge whether a sudden fault occurs in the transformer to be tested according to a second change trend of the second operating information within a second preset sliding window; wherein the first operating information includes at least one of oil temperature, vibration information and partial discharge information, and the size of the first preset sliding window is larger than the size of the second preset sliding window.

[0052] Compared with the prior art, the transformer fault processing method and system provided in the embodiment of the present application obtains the working condition information of the transformer to be tested; the working condition information includes at least one of the use time, use operation and environmental information; according to the working condition information, the first probability of the transformer to be tested having a progressive fault and the second probability of the transformer to be tested having a sudden fault are obtained; if the first probability meets the first preset condition, the first operation information of the transformer to be tested is collected, and according to the first change trend of the first operation information in the first preset sliding window, it is judged whether the transformer to be tested has a progressive fault; if the second probability meets the second preset condition, the second operation information of the transformer to be tested is collected, and according to the second change trend of the second operation information in the second preset sliding window, it is judged whether the transformer to be tested has a sudden fault. It can be seen that the embodiment of the present application takes into account the different characteristics of progressive faults and sudden faults, and judges the probability of progressive faults and sudden faults according to the working condition information, so that different processing methods are adopted for these two possible faults, thereby improving the accuracy of fault judgment. BRIEF DESCRIPTION OF THE DRAWINGS

[0053] Figure 1 is a flow chart of a transformer fault processing method provided by an embodiment of the present application;

[0054] Figure 2 It is a structural block diagram of a transformer fault processing system provided in an embodiment of the present application;

[0055] Figure 3 It is a structural block diagram of a transformer fault handling device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0056] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0057] See also Figure 1 , Figure 1 : is a flowchart of a transformer fault processing method provided in an embodiment of the present application, the transformer fault processing method comprising:

[0058] S1. Obtaining operating condition information of the transformer to be tested; the operating condition information includes at least one of usage time, usage operation and environmental information;

[0059] S2. Obtaining, according to the operating condition information, a first probability of a progressive fault occurring in the transformer to be tested and a second probability of a sudden fault occurring;

[0060] S3. If the first probability satisfies a first preset condition, first operating information of the transformer to be tested is collected, and whether a progressive fault occurs in the transformer to be tested according to a first change trend of the first operating information within a first preset sliding window is determined; wherein the first operating information includes at least one of oil temperature, vibration information, and partial discharge information;

[0061] S4. If the second probability meets the second preset condition, the second operating information of the transformer to be tested is collected, and according to the second change trend of the second operating information within the second preset sliding window, it is determined whether a sudden fault occurs in the transformer to be tested; wherein the first operating information includes at least one of oil temperature, vibration information and partial discharge information, and the size of the first preset sliding window is larger than the size of the second preset sliding window.

[0062] It is worth noting that sudden faults are usually manifested as a sharp change in state parameters at a certain moment, while progressive faults are manifested as a slow drift of state parameters. For example, in extreme weather (such as lightning strikes), transformers are prone to sudden faults; transformers are prone to progressive faults (such as aging) if they are used for too long; transformers are prone to progressive faults if they are not used in accordance with operating instructions (such as instructions). Therefore, for these two types of faults, the embodiments of the present application adopt two different information processing and judgment methods. Specifically, for progressive faults, the first change trend of the first operating information in the first preset sliding window is used to determine whether the transformer to be tested has a progressive fault. For sudden faults, the second change trend of the second operating information in the second preset sliding window is used to determine whether the transformer to be tested has a sudden fault, which can improve the accuracy of fault judgment.

[0063] In addition, before this, a preliminary judgment is made based on the operating condition information of the transformer to be tested whether a progressive fault or a sudden fault occurs in the transformer to be tested. Specifically, a first probability of a progressive fault occurring in the transformer to be tested and a second probability of a sudden fault occurring are obtained based on the operating condition information. If the first probability meets a first preset condition, a preliminary judgment is made that a progressive fault occurs in the transformer to be tested, so as to provide a basis for subsequent progressive fault judgments. If the second probability meets a second preset condition, a preliminary judgment is made that a sudden fault occurs in the transformer to be tested, so as to provide a basis for subsequent sudden fault judgments.

[0064] Optionally, the first preset condition includes that the first probability is greater than a first preset probability, and the second preset condition includes that the second probability is greater than a second preset probability.

[0065] The oil temperature reflects the thermal effect of sudden faults inside the transformer, and overheating faults can be judged by the oil temperature. For example, when a core short circuit fault occurs, the oil temperature rises rapidly by more than 5°C within 1 minute, which is a sudden fault, while the temperature rises slowly due to insulation aging, with a temperature rise of no more than 2°C per hour, which is a gradual fault.

[0066] The vibration signal reflects the degree of damage to the structural integrity of the transformer, and mechanical faults can be judged by the vibration signal. For example, when the core is loose, the vibration frequency jumps from 50 Hz to 300 Hz in 0.1 seconds, suddenly increasing by more than 5 times, which is a sudden fault; the vibration frequency caused by bearing wear increases slowly, and the vibration frequency does not increase by more than 20 Hz within 10 hours, which is a progressive fault.

[0067] Partial discharge information reveals the insulation breakdown process, and insulation faults can be judged through partial discharge information. For example, during insulation breakdown, the discharge amplitude surges from 50 mV to 500 mV within 1 microsecond, which is a sudden fault, while during insulation aging, the discharge amplitude slowly increases to 150 mV within 24 hours, which is a progressive fault.

[0068] The embodiment of the present application comprehensively judges the fault of the transformer through oil temperature, vibration information and partial discharge information.

[0069] In an optional embodiment, judging whether a progressive fault occurs in the transformer to be tested according to a first change trend of the first operating information in a first preset sliding window includes:

[0070] Performing feature extraction on the first operation information in the first preset sliding window to obtain a first operation feature;

[0071] According to the first operating characteristic, drawing a first characteristic curve;

[0072] According to the first characteristic curve, it is determined whether a progressive fault occurs in the transformer to be tested.

[0073] In the embodiment of the present application, for progressive faults, a first preset sliding window with a larger size is used, which can observe the change trend of the first operating information for a longer period of time, accurately capture the relevant characteristics of the progressive faults, and improve the accuracy of judgment.

[0074] In an optional embodiment, judging whether a progressive fault occurs in the transformer under test based on the first characteristic curve includes: calculating a first slope of the first characteristic curve; if the first slope is within a preset slope range, judging that a progressive fault occurs in the transformer under test; if the first slope is not within the preset slope range, judging that no progressive fault occurs in the transformer under test.

[0075] In an optional embodiment, judging whether a progressive fault occurs in the transformer to be tested according to the first characteristic curve includes:

[0076] Using a pre-trained first fault determination model, judging whether a progressive fault occurs in the transformer to be tested according to the first characteristic curve;

[0077] Wherein, the first fault determination model is trained by the following steps:

[0078] Acquire first historical operation information of a first test transformer under a progressive fault;

[0079] Performing feature extraction on the first historical operation information in the first preset sliding window to obtain a first historical operation feature;

[0080] Draw a first historical characteristic curve according to the first historical operation characteristic;

[0081] The first historical characteristic curve is used to perform model training to obtain the first fault determination model.

[0082] In the embodiment of the present application, whether a progressive fault occurs is determined by using a pre-trained first fault determination model, which can further improve the judgment accuracy compared to a simple threshold (first preset slope) judgment.

[0083] Specifically, the using the first historical characteristic curve to perform model training to obtain the first fault determination model includes:

[0084] Obtaining a first real fault result corresponding to a first historical characteristic curve;

[0085] Inputting the first historical characteristic curve into a preset first neural network model to obtain a first predicted fault result;

[0086] The first real fault result and the first predicted fault result are used to update the first neural network model to obtain the first fault determination model.

[0087] In an optional embodiment, judging whether a sudden fault occurs in the transformer to be tested according to a second change trend of the second operating information in a second preset sliding window includes:

[0088] Performing feature extraction on the second operation information in the second preset sliding window to obtain a second operation feature;

[0089] According to the second operating characteristic, drawing a second characteristic curve;

[0090] According to the second characteristic curve, it is determined whether a sudden fault occurs in the transformer to be tested.

[0091] In the embodiment of the present application, for sudden faults, a second preset sliding window of a smaller size is used, which can observe the changing trend of the second operating information in a shorter period of time, accurately capture the relevant characteristics of the sudden faults, and improve the accuracy of judgment.

[0092] In an optional embodiment, judging whether a sudden fault occurs in the transformer under test based on the second characteristic curve includes: calculating the second slope of the two characteristic curves; if the second slope is greater than the maximum value of a preset slope range, judging that a sudden fault occurs in the transformer under test; if the second slope is less than or equal to the maximum value of the preset slope range, judging that no sudden fault occurs in the transformer under test.

[0093] In an optional embodiment, judging whether a sudden fault occurs in the transformer to be tested according to the second characteristic curve includes:

[0094] Using a pre-trained second fault determination model, judging whether a sudden fault occurs in the transformer to be tested according to the second characteristic curve;

[0095] Wherein, the second fault determination model is trained by the following steps:

[0096] Acquire second historical operation information of the second test transformer under the sudden fault;

[0097] Performing feature extraction on the second historical operation information in the second preset sliding window to obtain a second historical operation feature;

[0098] According to the second historical operation characteristic, drawing a second historical characteristic curve;

[0099] The second historical characteristic curve is used to perform model training to obtain the second fault determination model.

[0100] In the embodiment of the present application, whether a sudden fault occurs is determined by using a pre-trained second fault determination model, which can further improve the judgment accuracy compared to a simple threshold (second preset slope) judgment.

[0101] Specifically, the using the second historical characteristic curve to perform model training to obtain the second fault determination model includes:

[0102] Obtaining a second real fault result corresponding to the second historical characteristic curve;

[0103] Inputting the second historical characteristic curve into a preset second neural network model to obtain a second predicted fault result;

[0104] The second neural network model is updated using the second real fault result and the second predicted fault result to obtain the second fault determination model.

[0105] In an optional embodiment, obtaining, according to the operating condition information, a first probability of a progressive fault occurring in the transformer to be tested and a second probability of a sudden fault occurring in the transformer to be tested includes:

[0106] Obtaining a first historical probability of a progressive fault occurring in the third test transformer under different historical operating condition information and a second historical probability of a sudden fault occurring;

[0107] Performing model training using the historical operating condition information, the first historical probability, and the second historical probability to obtain a trained fault probability determination model;

[0108] The fault probability determination model is used to obtain the first probability and the second probability according to the operating condition information.

[0109] In the embodiment of the present application, a first probability of a progressive failure and a second probability of a sudden failure are determined by using a pre-trained failure probability determination model.

[0110] Specifically, the using the historical operating condition information, the first historical probability and the second historical probability to perform model training to obtain a trained fault probability determination model includes:

[0111] Inputting the historical operating condition information into a preset third neural network model to obtain a first prediction probability and a second prediction probability;

[0112] The third neural network model is updated using the first predicted probability, the second predicted probability, the first historical probability, and the second historical probability to determine the fault probability determination model.

[0113] In an optional embodiment, obtaining a first historical probability of a progressive fault occurring in the third test transformer and a second historical probability of a sudden fault occurring in different historical operating condition information includes:

[0114] Obtaining historical events of the third test transformer under different historical operating condition information, and counting the total number of events of the historical events;

[0115] Counting the number of first events in which progressive failures occurred and the number of second events in which sudden failures occurred in the historical events;

[0116] Calculating the first historical probability according to the total number of events and the first number of events;

[0117] The second historical probability is calculated based on the total number of events and the second number of events.

[0118] Specifically, calculating the first historical probability according to the total number of events and the first number of events includes: dividing the first number of events by the total number of events to obtain the first historical probability.

[0119] Specifically, calculating the second historical probability according to the total number of events and the second number of events includes: dividing the second number of events by the total number of events to obtain the second historical probability.

[0120] The embodiment of the present application obtains the first historical probability and the second historical probability by counting the number of historical events, events of progressive failures, and events of sudden failures.

[0121] In an optional embodiment, after judging whether a progressive fault occurs in the transformer to be tested according to a first change trend of the first operating information in a first preset sliding window, the transformer fault processing method further includes:

[0122] If it is determined that the transformer to be tested has a progressive fault, then judging that the transformer to be tested is in a progressive fault stage according to the first change trend;

[0123] According to the stages, a repair strategy for the transformer to be tested is obtained.

[0124] It is understandable that progressive failures generally have multiple stages, such as a mild aging stage, a moderate aging stage, and a severe aging stage. Using different repair strategies for different stages of progressive failures can improve the repair rate.

[0125] In an optional embodiment, judging, according to the first change trend, that the transformer to be tested is in a progressive fault stage includes:

[0126] If the first change trend satisfies the first change trend condition, it is determined that the transformer to be tested is in a mild stage;

[0127] If the first change trend satisfies the second change trend condition, it is determined that the transformer to be tested is in a medium stage;

[0128] If the first change trend meets the third change trend condition, it is determined that the transformer to be tested is in a severe stage.

[0129] For example, during normal operation, the oil temperature is stable at 55°C; when the first change trend satisfies that the oil temperature rises by 0-1°C per hour, it belongs to the mild aging stage; when the first change trend satisfies that the oil temperature rises by 1-2°C per hour, it belongs to the moderate aging stage; when the first change trend satisfies that the oil temperature rises by 2°C per hour, it belongs to the severe aging stage.

[0130] During normal operation, the vibration frequency is stable at 50 Hz; when the first change trend meets the vibration frequency slowly rising to 60 Hz, it belongs to the light wear stage; when the first change trend meets the vibration frequency slowly rising to 70 Hz, it belongs to the moderate wear stage; when the first change trend meets the vibration frequency slowly rising to 80 Hz, it belongs to the heavy wear stage;

[0131] Under normal conditions, the number of discharges per hour is less than 10 times; when the first change trend meets the condition that the number of discharges increases to 20 times per hour and the discharge amplitude rises to 50 mV, it belongs to the mild degradation stage; when the first change trend meets the condition that the number of discharges reaches 50 times per hour and the discharge amplitude rises to 100 mV, it belongs to the moderate degradation stage; when the first change trend meets the condition that the number of discharges exceeds 100 times per hour and the discharge amplitude rises to 150 mV, it belongs to the severe degradation stage.

[0132] In an optional embodiment, after judging whether a sudden fault occurs in the transformer to be tested according to the second change trend of the second operating information in the second preset sliding window, the transformer fault processing method further includes:

[0133] If it is determined that a sudden fault occurs in the transformer under test, a repair strategy for the transformer under test is obtained according to the second change trend.

[0134] The embodiment of the present application adopts a corresponding repair strategy for sudden failures, which can improve the repair rate.

[0135] A transformer fault processing method provided in an embodiment of the present application, by obtaining the working condition information of the transformer to be tested; the working condition information includes at least one of the use time, use operation and environmental information; according to the working condition information, a first probability of a progressive fault and a second probability of a sudden fault of the transformer to be tested are obtained; if the first probability meets the first preset condition, the first operation information of the transformer to be tested is collected, and according to the first change trend of the first operation information in the first preset sliding window, it is judged whether the transformer to be tested has a progressive fault; if the second probability meets the second preset condition, the second operation information of the transformer to be tested is collected, and according to the second change trend of the second operation information in the second preset sliding window, it is judged whether the transformer to be tested has a sudden fault. It can be seen that the embodiment of the present application takes into account the different characteristics of progressive faults and sudden faults, and judges the probability of progressive faults and sudden faults according to the working condition information, so that different processing methods are adopted for these two possible faults, thereby improving the accuracy of fault judgment.

[0136] See also Figure 2 , Figure 2 1 is a structural block diagram of a transformer fault processing system 10 provided in an embodiment of the present application, wherein the transformer fault processing system 10 comprises:

[0137] The working condition information acquisition module 11 is used to acquire the working condition information of the transformer to be tested; the working condition information includes at least one of the use time, use operation and environmental information;

[0138] A probability acquisition module 12, configured to obtain a first probability of a progressive fault occurring in the transformer to be tested and a second probability of a sudden fault occurring in the transformer to be tested according to the operating condition information;

[0139] A first fault judgment module 13 is used to collect first operating information of the transformer to be tested if the first probability meets a first preset condition, and judge whether a progressive fault occurs in the transformer to be tested according to a first change trend of the first operating information within a first preset sliding window; wherein the first operating information includes at least one of oil temperature, vibration information and partial discharge information;

[0140] The second fault judgment module 14 is used to collect second operating information of the transformer to be tested if the second probability meets a second preset condition, and judge whether a sudden fault occurs in the transformer to be tested according to a second change trend of the second operating information within a second preset sliding window; wherein the first operating information includes at least one of oil temperature, vibration information and partial discharge information, and the size of the first preset sliding window is larger than the size of the second preset sliding window.

[0141] Optionally, judging whether a progressive fault occurs in the transformer to be tested according to a first change trend of the first operating information in a first preset sliding window includes:

[0142] Performing feature extraction on the first operation information in the first preset sliding window to obtain a first operation feature;

[0143] According to the first operating characteristic, drawing a first characteristic curve;

[0144] According to the first characteristic curve, it is determined whether a progressive fault occurs in the transformer to be tested.

[0145] Optionally, judging whether a progressive fault occurs in the transformer to be tested according to the first characteristic curve includes:

[0146] Using a pre-trained first fault determination model, judging whether a progressive fault occurs in the transformer to be tested according to the first characteristic curve;

[0147] Wherein, the first fault determination model is trained by the following steps:

[0148] Acquire first historical operation information of a first test transformer under a progressive fault;

[0149] Performing feature extraction on the first historical operation information in the first preset sliding window to obtain a first historical operation feature;

[0150] Draw a first historical characteristic curve according to the first historical operation characteristic;

[0151] The first historical characteristic curve is used to perform model training to obtain the first fault determination model.

[0152] Optionally, judging whether a sudden fault occurs in the transformer to be tested according to a second change trend of the second operating information in a second preset sliding window includes:

[0153] Performing feature extraction on the second operation information in the second preset sliding window to obtain a second operation feature;

[0154] According to the second operating characteristic, drawing a second characteristic curve;

[0155] According to the second characteristic curve, it is determined whether a sudden fault occurs in the transformer to be tested.

[0156] Optionally, judging whether a sudden fault occurs in the transformer to be tested according to the second characteristic curve includes:

[0157] Using a pre-trained second fault determination model, judging whether a sudden fault occurs in the transformer to be tested according to the second characteristic curve;

[0158] Wherein, the second fault determination model is trained by the following steps:

[0159] Acquire second historical operation information of the second test transformer under the sudden fault;

[0160] Performing feature extraction on the second historical operation information in the second preset sliding window to obtain a second historical operation feature;

[0161] According to the second historical operation characteristic, drawing a second historical characteristic curve;

[0162] The second historical characteristic curve is used to perform model training to obtain the second fault determination model.

[0163] Optionally, obtaining, according to the operating condition information, a first probability of a progressive fault occurring in the transformer to be tested and a second probability of a sudden fault occurring in the transformer to be tested includes:

[0164] Obtaining a first historical probability of a progressive fault occurring in the third test transformer under different historical operating condition information and a second historical probability of a sudden fault occurring;

[0165] Performing model training using the historical operating condition information, the first historical probability, and the second historical probability to obtain a trained fault probability determination model;

[0166] The fault probability determination model is used to obtain the first probability and the second probability according to the operating condition information.

[0167] Optionally, obtaining a first historical probability of a progressive fault occurring in the third test transformer and a second historical probability of a sudden fault occurring in different historical operating condition information includes:

[0168] Obtaining historical events of the third test transformer under different historical operating condition information, and counting the total number of events of the historical events;

[0169] Counting the number of first events in which progressive failures occurred and the number of second events in which sudden failures occurred in the historical events;

[0170] Calculating the first historical probability according to the total number of events and the first number of events;

[0171] The second historical probability is calculated based on the total number of events and the second number of events.

[0172] Optionally, the transformer fault processing system 10 further includes:

[0173] A repair module is used to determine, if it is determined that the transformer under test has a progressive fault, whether the transformer under test is in a progressive fault stage according to the first change trend; and obtain a repair strategy for the transformer under test according to the stage.

[0174] Optionally, judging, according to the first change trend, that the transformer to be tested is in a progressive fault stage includes:

[0175] If the first change trend satisfies the first change trend condition, it is determined that the transformer to be tested is in a mild stage;

[0176] If the first change trend satisfies the second change trend condition, it is determined that the transformer to be tested is in a medium stage;

[0177] If the first change trend meets the third change trend condition, it is determined that the transformer to be tested is in a severe stage.

[0178] It is worth noting that the working process of each module in the transformer fault handling system 10 described in the embodiment of the present application can refer to the working process of the transformer fault handling method described in the above embodiment, and will not be repeated here.

[0179] A transformer fault processing system 10 provided in an embodiment of the present application obtains the working condition information of the transformer to be tested; the working condition information includes at least one of the use time, use operation and environmental information; according to the working condition information, a first probability of a progressive fault and a second probability of a sudden fault of the transformer to be tested are obtained; if the first probability meets the first preset condition, the first operation information of the transformer to be tested is collected, and according to the first change trend of the first operation information in the first preset sliding window, it is judged whether the transformer to be tested has a progressive fault; if the second probability meets the second preset condition, the second operation information of the transformer to be tested is collected, and according to the second change trend of the second operation information in the second preset sliding window, it is judged whether the transformer to be tested has a sudden fault. It can be seen that the embodiment of the present application takes into account the different characteristics of progressive faults and sudden faults, and judges the probability of progressive faults and sudden faults according to the working condition information, so that different processing methods are adopted for these two possible faults, thereby improving the accuracy of fault judgment.

[0180] In addition, an embodiment of the present application further provides a computer-readable storage medium, which includes a stored computer program; wherein, when the computer program is running, it controls the device where the computer-readable storage medium is located to execute the transformer fault handling method as described in any of the above embodiments.

[0181] In addition, an embodiment of the present application further provides a computer program product, including a computer program / instruction, which, when executed by a processor, implements the transformer fault processing method as described in any of the above embodiments.

[0182] See also Figure 3 , Figure 3 1 is a structural block diagram of a transformer fault processing device 20 provided in an embodiment of the present application, and the transformer fault processing device 20 includes: a processor 21, a memory 22, and a computer program stored in the memory 22 and executable on the processor 21. When the processor 21 executes the computer program, the steps in the above transformer fault processing method embodiment are implemented. Alternatively, when the processor 21 executes the computer program, the functions of each module / unit in the above device embodiments are implemented.

[0183] Exemplarily, the computer program may be divided into one or more modules / units, which are stored in the memory 22 and executed by the processor 21 to complete the present application. The one or more modules / units may be a series of computer program instruction segments capable of completing specific functions, which are used to describe the execution process of the computer program in the transformer fault processing device 20.

[0184] The transformer fault processing device 20 may include, but is not limited to, a processor 21 and a memory 22. Those skilled in the art will appreciate that the schematic diagram is merely an example of the transformer fault processing device 20 and does not constitute a limitation on the transformer fault processing device 20. The transformer fault processing device 20 may include more or fewer components than shown in the figure, or may combine certain components, or different components. For example, the transformer fault processing device 20 may also include input and output devices, network access devices, buses, etc.

[0185] The processor 21 may be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general-purpose processor may be a microprocessor or any conventional processor, etc. The processor 21 is the control center of the transformer fault processing device 20, and uses various interfaces and lines to connect various parts of the entire transformer fault processing device 20.

[0186] The memory 22 can be used to store the computer program and / or module. The processor 21 realizes various functions of the transformer fault processing device 20 by running or executing the computer program and / or module stored in the memory 22 and calling the data stored in the memory 22. The memory 22 can mainly include a program storage area and a data storage area, wherein the program storage area can store an operating system, an application required for at least one function (such as a sound playback function, an image playback function, etc.), etc.; the data storage area can store data created according to the use of the mobile phone (such as audio data, a phone book, etc.), etc. In addition, the memory 22 can include a high-speed random access memory, and can also include a non-volatile memory, such as a hard disk, a memory, a plug-in hard disk, a smart memory card (Smart Media Card, SMC), a secure digital (SecureDigital, SD) card, a flash card (Flash Card), at least one disk storage device, a flash memory device, or other volatile solid-state storage devices.

[0187] Wherein, if the module / unit integrated in the transformer fault processing device 20 is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on such an understanding, the present application implements all or part of the processes in the above-mentioned embodiment method, and can also be completed by instructing the relevant hardware through a computer program. The computer program can be stored in a computer-readable storage medium, and the computer program can implement the steps of the above-mentioned various method embodiments when executed by the processor 21. Wherein, the computer program includes computer program code, and the computer program code can be in source code form, object code form, executable file or some intermediate form, etc. The computer-readable medium may include: any entity or device capable of carrying the computer program code, recording medium, U disk, mobile hard disk, disk, optical disk, computer memory, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), electric carrier signal, telecommunication signal and software distribution medium, etc.

[0188] It should be noted that the device embodiments described above are merely schematic, wherein the units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they may be located in one place, or they may be distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the scheme of this embodiment. In addition, in the accompanying drawings of the device embodiments provided by the present application, the connection relationship between the modules indicates that there is a communication connection between them, which may be specifically implemented as one or more communication buses or signal lines. A person of ordinary skill in the art can understand and implement it without paying any creative work.

[0189] The above is a preferred embodiment of the present application. It should be pointed out that for ordinary technicians in this technical field, several improvements and modifications can be made without departing from the principles of the present application. These improvements and modifications are also considered to be within the scope of protection of the present application.

Claims

1. A transformer fault handling method, characterized in that: include: Obtaining the working condition information of the transformer to be tested; The working condition information includes at least one of usage duration, usage operation and environmental information; According to the working condition information, a first probability of a progressive fault occurring in the transformer to be tested and a second probability of a sudden fault occurring are obtained; If the first probability satisfies a first preset condition, first operating information of the transformer to be tested is collected, and whether a progressive fault occurs in the transformer to be tested is determined according to a first change trend of the first operating information within a first preset sliding window; wherein the first operating information includes at least one of oil temperature, vibration information, and partial discharge information; and the first preset condition includes that the first probability is greater than a first preset probability; If the second probability satisfies a second preset condition, second operating information of the transformer to be tested is collected, and whether a sudden fault occurs in the transformer to be tested is determined according to a second change trend of the second operating information within a second preset sliding window; wherein the second operating information includes at least one of oil temperature, vibration information, and partial discharge information, and the size of the first preset sliding window is larger than the size of the second preset sliding window; and the second preset condition includes that the second probability is larger than the second preset probability; Wherein, obtaining a first probability of a progressive fault occurring in the transformer to be tested and a second probability of a sudden fault occurring in the transformer to be tested according to the operating condition information includes: Obtaining a first historical probability of a progressive fault occurring in the third test transformer under different historical operating condition information and a second historical probability of a sudden fault occurring; Performing model training using the historical operating condition information, the first historical probability, and the second historical probability to obtain a trained fault probability determination model; Using the fault probability determination model, obtaining the first probability and the second probability according to the operating condition information; The obtaining of a first historical probability of a progressive fault occurring in the third test transformer under different historical operating condition information and a second historical probability of a sudden fault occurring includes: Obtaining historical events of the third test transformer under different historical operating condition information, and counting the total number of events of the historical events; Counting the number of first events in which progressive failures occurred and the number of second events in which sudden failures occurred in the historical events; Calculating the first historical probability according to the total number of events and the first number of events; The second historical probability is calculated based on the total number of events and the second number of events.

2. The transformer fault handling method according to claim 1, characterized in that: The step of judging whether a progressive fault occurs in the transformer to be tested according to a first change trend of the first operating information in a first preset sliding window includes: Performing feature extraction on the first operation information in the first preset sliding window to obtain a first operation feature; According to the first operating characteristic, drawing a first characteristic curve; According to the first characteristic curve, it is determined whether a progressive fault occurs in the transformer to be tested.

3. The transformer fault handling method according to claim 2, characterized in that: The step of judging whether a progressive fault occurs in the transformer to be tested according to the first characteristic curve includes: Using a pre-trained first fault determination model, judging whether a progressive fault occurs in the transformer to be tested according to the first characteristic curve; Wherein, the first fault determination model is trained by the following steps: Acquire first historical operation information of a first test transformer under a progressive fault; Performing feature extraction on the first historical operation information in the first preset sliding window to obtain a first historical operation feature; Draw a first historical characteristic curve according to the first historical operation characteristic; The first historical characteristic curve is used to perform model training to obtain the first fault determination model.

4. The transformer fault handling method according to claim 1, characterized in that: The step of judging whether a sudden fault occurs to the transformer to be tested according to a second change trend of the second operating information within a second preset sliding window includes: Performing feature extraction on the second operation information in the second preset sliding window to obtain a second operation feature; According to the second operating characteristic, drawing a second characteristic curve; According to the second characteristic curve, it is determined whether a sudden fault occurs in the transformer to be tested.

5. The transformer fault handling method according to claim 4, characterized in that: The step of judging whether a sudden fault occurs in the transformer to be tested according to the second characteristic curve includes: Using a pre-trained second fault determination model, judging whether a sudden fault occurs in the transformer to be tested according to the second characteristic curve; Wherein, the second fault determination model is trained by the following steps: Acquire second historical operation information of the second test transformer under the sudden fault; Performing feature extraction on the second historical operation information in the second preset sliding window to obtain a second historical operation feature; According to the second historical operation characteristic, drawing a second historical characteristic curve; The second historical characteristic curve is used to perform model training to obtain the second fault determination model.

6. The transformer fault handling method according to claim 1, characterized in that: After determining whether a progressive fault occurs in the transformer to be tested according to the first change trend of the first operating information in the first preset sliding window, the transformer fault processing method further includes: If it is determined that the transformer to be tested has a progressive fault, then judging that the transformer to be tested is in a progressive fault stage according to the first change trend; According to the stages, a repair strategy for the transformer to be tested is obtained.

7. The transformer fault handling method according to claim 6, characterized in that: The step of judging, according to the first change trend, that the transformer to be tested is in a progressive fault stage includes: If the first change trend satisfies the first change trend condition, it is determined that the transformer to be tested is in a mild stage; If the first change trend satisfies the second change trend condition, it is determined that the transformer to be tested is in a medium stage; If the first change trend meets the third change trend condition, it is determined that the transformer to be tested is in a severe stage.

8. A transformer fault handling system, characterized in that: include: A working condition information acquisition module, used to acquire working condition information of the transformer to be tested; the working condition information includes at least one of usage time, usage operation and environmental information; A probability acquisition module, used to obtain a first probability of a progressive fault occurring in the transformer to be tested and a second probability of a sudden fault occurring in the transformer to be tested according to the operating condition information; A first fault judgment module is used for collecting first operating information of the transformer to be tested if the first probability meets a first preset condition, and judging whether a progressive fault occurs in the transformer to be tested according to a first change trend of the first operating information within a first preset sliding window; wherein the first operating information includes at least one of oil temperature, vibration information and partial discharge information; and the first preset condition includes that the first probability is greater than a first preset probability; A second fault judgment module is used for collecting second operating information of the transformer to be tested if the second probability meets a second preset condition, and judging whether a sudden fault occurs in the transformer to be tested according to a second change trend of the second operating information in a second preset sliding window; wherein the second operating information includes at least one of oil temperature, vibration information and partial discharge information, and the size of the first preset sliding window is larger than the size of the second preset sliding window; and the second preset condition includes that the second probability is larger than the second preset probability; Wherein, obtaining a first probability of a progressive fault occurring in the transformer to be tested and a second probability of a sudden fault occurring in the transformer to be tested according to the operating condition information includes: Obtaining a first historical probability of a progressive fault occurring in the third test transformer under different historical operating condition information and a second historical probability of a sudden fault occurring; Performing model training using the historical operating condition information, the first historical probability, and the second historical probability to obtain a trained fault probability determination model; Using the fault probability determination model, obtaining the first probability and the second probability according to the operating condition information; The obtaining of a first historical probability of a progressive fault occurring in the third test transformer under different historical operating condition information and a second historical probability of a sudden fault occurring includes: Obtaining historical events of the third test transformer under different historical operating condition information, and counting the total number of events of the historical events; Counting the number of first events in which progressive failures occurred and the number of second events in which sudden failures occurred in the historical events; Calculating the first historical probability according to the total number of events and the first number of events; The second historical probability is calculated based on the total number of events and the second number of events.

Images