Transformer state diagnosis method and device and electronic equipment

Abstract

The application is suitable for the field of transformer fault diagnosis technology, and provides a transformer state diagnosis method, device and electronic equipment, which comprises the following steps: determining the gas concentrations of different fault characteristic gases generated by the transformer at different time points respectively to obtain at least two gas data groups; determining the concentration ratio of various fault characteristic gases in different gas data groups and the total gas production in different gas data groups according to the at least two gas data groups; performing fault diagnosis on the transformer according to the concentration ratio of various fault characteristic gases in different gas data groups to obtain a fault diagnosis result, wherein the fault diagnosis result is used to indicate whether the transformer has a fault and the type of the fault when the transformer has a fault; and determining the state of the transformer according to the concentration ratio of various fault characteristic gases in different gas data groups, the total gas production in different gas data groups and the fault diagnosis result. The above method can improve the accuracy of the determined state of the transformer.

Description

TECHNICAL FIELD

[0001] The present application belongs to the technical field of fault diagnosis of transformers, and particularly relates to a transformer state diagnosis method and device, an electronic device, and a computer readable storage medium. BACKGROUND

[0002] A transformer is a device for changing alternating current voltage by using the principle of electromagnetic induction. Common faults occurring during use of the transformer include partial discharge and transformer overheating.

[0003] When a transformer fails, it often produces a variety of fault characteristic gases (i.e. gases produced due to the fault). The type and concentration of fault characteristic gases produced by a fault type are closely related to whether the transformer fails and even the type of fault. Therefore, the type and concentration of fault characteristic gases at a certain time can be used to determine whether the transformer fails and the type of fault.

[0004] However, the above method can only determine whether the transformer fails and the type of fault. That is, the user cannot determine other information of the transformer based on the type and concentration of fault characteristic gases, which makes the user obtain too little information and thus makes it difficult to effectively manage and control the transformer. SUMMARY

[0005] The embodiments of the present application provide a transformer state diagnosis method and device, an electronic device, and a computer readable storage medium, which can solve the problem that the existing method cannot effectively manage and control the transformer.

[0006] In a first aspect, the embodiments of the present application provide a transformer state diagnosis method, which comprises:

[0007] At different time points, the gas concentrations of different fault characteristic gases produced by the transformer are determined to obtain at least two gas data groups, wherein each gas data group corresponds to a time point.

[0008] The concentration ratios of various fault characteristic gases in different gas data groups and the total gas production in the different gas data groups are determined according to the at least two gas data groups.

[0009] The transformer is diagnosed according to the concentration ratios of various fault characteristic gases in the different gas data groups to obtain a fault diagnosis result, which is used to indicate whether the transformer fails and the type of fault when the transformer fails.

[0010] The state of the transformer is determined according to the concentration ratios of various fault characteristic gases in the different gas data groups, the total gas production in the different gas data groups, and the fault diagnosis result.

[0011] In a second aspect, the embodiments of the present application provide a state diagnosis device of a transformer, comprising:

[0012] a gas data set obtaining module, configured to determine gas concentrations of different fault characteristic gases generated by the transformer at different time points respectively, and obtain at least two gas data sets, wherein each of the gas data sets corresponds to one of the time points uniquely;

[0013] a concentration ratio determining module, configured to determine concentration ratios of various fault characteristic gases in different gas data sets and total gas production in the different gas data sets according to the at least two gas data sets;

[0014] a fault diagnosis result determining module, configured to perform fault diagnosis on the transformer according to the concentration ratios of various fault characteristic gases in the different gas data sets, and obtain a fault diagnosis result, wherein the fault diagnosis result is used to indicate whether the transformer has a fault, and a type of the fault when the transformer has the fault;

[0015] a state determining module of the transformer, configured to determine a state of the transformer according to the concentration ratios of various fault characteristic gases in the different gas data sets, the total gas production in the different gas data sets, and the fault diagnosis result.

[0016] In a third aspect, the embodiments of the present application provide an electronic device, comprising a memory, a processor, and a computer program stored in the memory and capable of running on the processor, wherein the processor implements the method of the first aspect when executing the computer program.

[0017] In a fourth aspect, the embodiments of the present application provide a computer readable storage medium, which stores a computer program, wherein the computer program is executed by a processor to implement the method of the first aspect.

[0018] In a fifth aspect, the embodiments of the present application provide a computer program product, which, when running on an electronic device, causes the electronic device to perform the method of the first aspect.

[0019] Compared with the prior art, the embodiments of the present application have the following beneficial effects:

[0020] In the embodiments of the present application, since the concentration ratio of each fault characteristic gas is determined according to at least two gas data sets, and each gas data set corresponds to a time point, the concentration ratio of each fault characteristic gas obtained is the concentration ratio corresponding to at least two time points, so that the fault diagnosis result obtained by diagnosing the transformer according to the concentration ratio of each fault characteristic gas is the fault diagnosis result corresponding to at least two time points. Since the state of the transformer is determined according to the concentration ratio of each fault characteristic gas in different gas data sets, the total gas production in different gas data sets, and the fault diagnosis result, and the concentration ratio of each fault characteristic gas, the total gas production, and the fault diagnosis result can reflect the running state of the transformer corresponding to at least two time points (for example, the fault diagnosis result can indicate whether the transformer has a fault, and the type of fault when the transformer has a fault), that is, the running state of the transformer corresponding to a period of time, therefore, by the above method, the accuracy of the obtained state of the transformer can be improved. In addition, since the concentration ratio can more directly determine the proportion of two gas concentrations, and the types and proportions of fault characteristic gases generated by different faults are usually different when the transformer fails, therefore, after determining the concentration ratio according to the gas concentration, diagnosing the fault of the transformer can improve the accuracy of the obtained fault diagnosis result, thereby facilitating effective management and control of the transformer.

[0021] It can be understood that the beneficial effects of the above-mentioned second aspect to fifth aspect can be referred to the related description in the above-mentioned first aspect, which will not be repeated here. BRIEF DESCRIPTION OF DRAWINGS

[0022] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings needed to be used in the embodiments or prior art description will be briefly introduced as follows.

[0023] Figure 1 is a flow diagram of a transformer state diagnosis method provided by an embodiment of the present application;

[0024] Figure 2 is a structure diagram of a BP neural network model of a full connection layer provided by an embodiment of the present application;

[0025] Figure 3 is a structure diagram of a transformer state diagnosis device provided by an embodiment of the present application;

[0026] Figure 4 is a structure diagram of an electronic device provided by an embodiment of the present application. DETAILED DESCRIPTION

[0027] In the following description, for purposes of explanation and not limitation, specific details are set forth such as particular architectures, technologies, techniques, etc. in order to provide a thorough understanding of the embodiments of the present application. However, it will be apparent to those skilled in the art that the present application can be practiced in other embodiments that depart from these specific details. In other instances, detailed descriptions of well-known systems, devices, circuits, and methods are omitted so as not to obscure the description of the present application with unnecessary detail.

[0028] It is to be understood that the terminology "includes", "has", "holds", "contains" and / or "comprising", when used in this specification and in the following claims, indicates the presence of the described features, integers, steps, operations, elements, and / or components, but does not preclude the presence or addition of one or more other features, integers, steps, operations, elements, components, and / or groups thereof.

[0029] It is also to be understood that the terminology "and / or" when used in this specification and in the following claims, refers to at least one of the items, or any combination of the items, and includes all possible combinations when used in the description of the items.

[0030] In addition, in the description of the specification and the appended claims, the terms "first", "second", etc. are used only to distinguish different descriptions, and cannot be understood as indicating or implying relative importance.

[0031] Reference in the specification to "one embodiment" or "some embodiments" etc. means that a particular feature, structure, or characteristic described in connection with the embodiment is included in at least one embodiment of the application. Thus, the appearance of the phrases "in one embodiment", "in some embodiments", "in other embodiments", "in additional embodiments", etc. in various places in the specification are not necessarily all referring to the same embodiment, unless otherwise specifically noted.

[0032] The transformer often generates multiple fault characteristic gases when it fails. For oil-immersed transformers, most of the fault characteristic gases generated are dissolved in the transformer oil. Among them, the oil-immersed transformer is a transformer immersed in insulating oil as a medium. It not only can isolate the shell and the coil, but also can undertake multiple functions such as cooling and insulation of the transformer.

[0033] When detecting the fault characteristic gas, the fault characteristic gas obtained at a certain time is usually detected, and then it is judged whether the transformer fails according to the detection result. However, in the actual use process, in addition to knowing whether the transformer has failed, the user also wants to know whether the transformer can continue to be used, that is, wants to know the state (or operating state) of the transformer.

[0034] In order to facilitate the user to know the state of the transformer, the embodiment of the application provides a state diagnosis method of the transformer. In the method, the fault diagnosis result of the transformer is determined by acquiring the gas data acquired at at least two different time points, and the state of the transformer is determined according to the fault diagnosis result, the concentration ratio of the corresponding gas type in the gas data and the total gas production.

[0035] The state diagnosis method of the transformer provided by the embodiment of the application is described below in combination with the drawings.

[0036] Figure 1 A flowchart of the state diagnosis method of the transformer provided by the embodiment of the application is shown, and the state diagnosis method can be applied in a diagnosis device, such as a diagnosis device of a transformer in a nuclear power plant, and the details are as follows:

[0037] S11, the gas concentrations of different fault characteristic gases generated by the transformer are determined at different time points respectively, and at least two gas data groups are obtained, wherein each of the above gas data groups uniquely corresponds to one of the above time points.

[0038] Specifically, the fault characteristic gases generated by the transformer (i.e. the gases generated by the transformer when a fault occurs) can include one or more of hydrogen (H2), methane (CH4), acetylene (C2H2), ethylene (C2H4), ethane (C2H6), carbon monoxide (CO), carbon dioxide (CO2) and the like. Wherein, when the fault (or fault type) of the transformer is different, the fault characteristic gases generated by the transformer are usually different.

[0039] In the embodiment of the application, the gas information of the transformer is monitored at different time points, for the gas information monitored at each time point, the types of fault characteristic gases contained in the gas information are detected (i.e. whether H2 is included, whether CH4 is included, etc.), the gas concentrations corresponding to different fault characteristic gases (such as the gas concentration corresponding to H2) are calculated according to the mass of various fault characteristic gases and the total mass, and the gas data groups corresponding to each time point are obtained. That is, each gas data group includes the gas concentrations of each fault characteristic gas detected at the corresponding time point.

[0040] It should be pointed out that for oil-immersed transformers, since most of the fault characteristic gases generated by the oil-immersed transformer after a fault occurs are dissolved in the transformer oil, the gas information needs to be extracted from the transformer oil first, and then the gas concentration detection of the gas information can be performed. Of course, for non-oil-immersed transformers, if the fault characteristic gases generated by the non-oil-immersed transformer are not dissolved into other liquids, the gas concentration detection of the monitored gas information can be directly performed, which is not described here.

[0041] Optionally, considering that the fault characteristic gas generated by the transformer is usually released slowly, i.e., the difference of the fault characteristic gas detected at two adjacent time points is usually small, therefore, the time interval can be set to obtain a new gas data set after the time interval arrives. That is, after obtaining a gas data set, the next gas data set is obtained after the time interval arrives, and by such acquisition, more accurate gas data sets can be obtained, thereby facilitating the accuracy of the subsequent obtained state of the transformer. At this time, the time interval between the two adjacent time points needs to be determined first, i.e., before S11, also includes:

[0042] A1, determining the length of time during which the stable gas concentration is obtained.

[0043] Here, the stable gas concentration is relative, i.e., it does not mean that the gas concentration remains completely unchanged, but that the change value of the gas concentration is less than the preset concentration change threshold.

[0044] A2, determining the time interval between the two adjacent time points according to the length of time.

[0045] Specifically, considering that the probability of failure of the transformer during operation is relatively large, i.e., the probability of generating fault characteristic gas during operation of the transformer is relatively large, therefore, the operation time of the transformer can be determined as the length of time during which the transformer has a stable gas concentration. If the operation time of the transformer is directly used as the above-mentioned time interval, it is equivalent to obtaining a set of gas data each time the transformer stops operation.

[0046] Of course, the above-mentioned time interval can also be determined by other ways, for example, assuming that the transformer is an oil-immersed transformer, before obtaining the gas data, the fault characteristic gas needs to be extracted from the transformer oil, and then the types, concentrations and total gas production of the fault characteristic gas are detected. Since the extraction of the fault characteristic gas and other detections all need a certain time, therefore, the cumulative time obtained by adding the time required for performing an extraction behavior of the fault characteristic gas (each extraction behavior includes one or more extraction actions) and the time required for various detections can be used as the above-mentioned time interval, for example, when the above-mentioned cumulative time is about 2 hours, the time interval can be set to 2 hours. It should be pointed out that the time interval determined by this way is usually less than the operation time of the transformer, at this time, the gas data obtained according to the time interval can more timely determine the state of the transformer.

[0047] S12, determining the concentration ratio of various fault characteristic gases in different gas data sets and the total gas production in the above-mentioned different gas data sets according to the above-mentioned at least two gas data sets.

[0048] Specifically, the concentration ratio here refers to the ratio between the values of the concentrations of two gases, and the total gas production can be determined according to the total mass of each fault characteristic gas.

[0049] Here, the concentration ratio and the total gas production are both calculated in groups. For example, assuming that the first gas data group includes fault characteristic gas 1 and fault characteristic gas 2, and the second gas data group includes fault characteristic gas 1 and fault characteristic gas 3. For the first gas data group, the concentration ratio corresponding to fault characteristic gas 1 in the group can be related to fault characteristic gas 2, but not to fault characteristic gas 3, and the total gas production corresponding to the first gas data group is determined according to fault characteristic gas 1 and fault characteristic gas 2. Similarly, for the second gas data group, the concentration ratio corresponding to fault characteristic gas 1 in the group can be related to fault characteristic gas 3, but not to fault characteristic gas 2, and the total gas production corresponding to the second gas data group is determined according to fault characteristic gas 1 and fault characteristic gas 3. That is, the concentration ratio corresponding to fault characteristic gas 1 in the first gas data group and the concentration ratio corresponding to fault characteristic gas 1 in the second gas data group are independent of each other, that is, the two concentration ratios corresponding to fault characteristic gas 1 in different gas data groups can be the same or different.

[0050] In the embodiments of the present application, when at least two gas data groups are obtained, the concentration ratio of the fault characteristic gas in the corresponding group can be directly determined according to the obtained gas data of each group, or the obtained at least two gas data groups can be processed first, and then the concentration ratio of the fault characteristic gas in the corresponding group is determined according to the processed gas data, which is not limited here.

[0051] S13, diagnosing the fault of the transformer according to the concentration ratios of various fault characteristic gases in different gas data groups to obtain a fault diagnosis result, wherein the fault diagnosis result is used to indicate whether the transformer has a fault and the type of the fault when the transformer has a fault.

[0052] Specifically, the concentration ratio of each fault characteristic gas corresponding to each gas data group can be used to diagnose the fault of the transformer to obtain a fault diagnosis result. That is, the fault diagnosis result includes the diagnosis results corresponding to each gas data group participating in the fault diagnosis.

[0053] For example, assuming that there are two gas data groups participating in the fault diagnosis, the fault diagnosis result includes the diagnosis results corresponding to the two gas data groups, each diagnosis result is used to indicate whether the transformer has a fault and the type of the fault when the transformer has a fault, and the two diagnosis results are combined to obtain the fault diagnosis result.

[0054] In the embodiments of the present application, the faults of the transformer include transformer oil overheating, transformer oil and insulation paper overheating, transformer oil and insulation paper partial discharge, spark discharge in transformer oil, electric arc in transformer oil, electric arc in transformer oil and insulation paper, etc. For example, if the detected fault characteristic gases include CH4, C2H4, H2, and C2H6, and the concentration ratio of these fault characteristic gases satisfies the preset condition, it is determined that the transformer has the fault of transformer oil overheating.

[0055] S14, determining the state of the transformer according to the concentration ratio of each fault characteristic gas in the different gas data sets, the total gas production in the different gas data sets, and the fault diagnosis result.

[0056] Here, the state of the transformer can include healthy, immediate shutdown, and needing maintenance, etc.

[0057] Specifically, a plurality of state conditions can be preset, each state condition including the concentration ratio of fault characteristic gases, the total gas production, and the fault diagnosis result, and different state conditions correspond to different states. After obtaining the concentration ratio of each fault characteristic gas, the total gas production, and the fault diagnosis result corresponding to the different gas data sets, the obtained concentration ratio of each fault characteristic gas, the total gas production, and the fault diagnosis result corresponding to each gas data set are matched with the preset state conditions, and the state of the transformer is determined according to the matching result.

[0058] Of course, the state of the transformer can also be determined in other ways. For example, a neural network model for determining the state of the transformer is trained in advance, and then the state of the transformer is determined according to the neural network model and the concentration ratio of each fault characteristic gas, the total gas production, and the fault diagnosis result.

[0059] In the embodiments of the present application, the gas concentrations of different fault characteristic gases generated by the transformer are determined at different time points, at least two groups of gas data are obtained, the concentration ratios of various fault characteristic gases in the corresponding gas data groups and the total gas production in the different gas data groups are determined according to the at least two groups of gas data, the transformer is diagnosed according to the concentration ratios of various fault characteristic gases in the different gas data groups, the fault diagnosis result is obtained, and the state of the transformer is determined according to the concentration ratios of various fault characteristic gases in the different gas data groups, the total gas production in the different gas data groups, and the fault diagnosis result. Since the concentration ratios of various fault characteristic gases are determined according to at least two groups of gas data, and each group of gas data corresponds to a time point, the obtained concentration ratios of various fault characteristic gases are the concentration ratios corresponding to at least two time points, so that the fault diagnosis result obtained by diagnosing the transformer according to the concentration ratios of various fault characteristic gases is the fault diagnosis result corresponding to at least two time points. Since the state of the transformer is determined according to the concentration ratios of various fault characteristic gases in the different gas data groups, the total gas production in the different gas data groups, and the fault diagnosis result, and the concentration ratios of various fault characteristic gases, the total gas production, and the fault diagnosis result can reflect the running state of the transformer corresponding to at least two time points (for example, the fault diagnosis result can indicate whether the transformer has a fault, and the type of fault when the transformer has a fault), that is, the running state of the transformer corresponding to a period of time, therefore, by the above method, the accuracy of the obtained state of the transformer can be improved. In addition, since the concentration ratio can more directly determine the proportion of two gas concentrations, and the types and proportions of fault characteristic gases generated by different faults are usually different when the transformer fails, therefore, after determining the concentration ratio according to the gas concentration, the fault diagnosis of the transformer can improve the accuracy of the obtained fault diagnosis result, thereby facilitating effective management and control of the transformer.

[0060] In some embodiments, the obtained at least two groups of gas data can be processed first, and then the concentration ratios of fault characteristic gases in the corresponding groups are determined according to the processed gas data groups, that is, before S12, the method further comprises:

[0061] The unqualified gas data groups in the at least two groups of gas data are filtered out, and the remaining gas data groups are obtained.

[0062] Correspondingly, S12 comprises:

[0063] The concentration ratios of various fault characteristic gases in different gas data groups and the total gas production in the different gas data groups are determined according to the above remaining gas data groups.

[0064] The unqualified gas data group includes: a gas data group having a larger difference from an adjacent gas data group. The larger difference includes: a larger difference in the type of fault characteristic gas included in the gas data group from the type of fault characteristic gas included in the adjacent gas data group, and / or a larger difference in the gas concentration of the same fault characteristic gas included in the gas data group from the gas concentration of the same fault characteristic gas included in the adjacent gas data group.

[0065] In the embodiments of the present application, considering that the gas data included in the gas data group needs to be determined after the type detection and quality determination of the fault characteristic gas, if the transformer is an oil-immersed transformer, the fault characteristic gas also needs to be extracted from the transformer oil first, and each action error may cause the determined gas data to have an error, that is, may cause an unqualified gas data group to be generated. Therefore, after obtaining a plurality of gas data groups, the unqualified gas data groups in the gas data groups can be filtered out first, and then the concentration ratio and the total gas production are determined according to the remaining gas data groups, which is beneficial to improve the accuracy of the obtained concentration ratio and the total gas production.

[0066] In some embodiments, when filtering out the unqualified gas data group, the gas concentration can be fitted by a curve, at this time, the above filtering out the unqualified gas data group in the above at least two gas data groups to obtain the remaining gas data group, includes:

[0067] A1, fitting the above at least two gas data groups to obtain a gas diffusion curve.

[0068] A2, filtering out the unqualified gas data group in the above at least two gas data groups according to the above gas diffusion curve to obtain the remaining gas data group.

[0069] Specifically, the gas concentration of the same fault characteristic gas in each gas data group is determined, and the gas diffusion curve corresponding to the fault characteristic gas is obtained according to each gas concentration and the corresponding time point. That is, in the embodiments of the present application, the number of gas diffusion curves is equal to the number of types of fault characteristic gases included in each gas data group.

[0070] For example, assuming that for acetylene C2H2, n gas data groups in each gas data group include the gas concentration corresponding to C2H2, that is, there are n data pairs corresponding to the time point and the gas concentration, and n is a natural number greater than 1. Assuming that xn represents the time point and yn represents the gas concentration, the n data pairs are represented as (x1, y1)(x2, y2)...(xn, yn).

[0071] Through research and analysis, it is found that the change of the gas concentration of acetylene C2H2 can be expressed by a curve equation similar to a parabola y=a2x2 +a1x+a0. Wherein, a0, a1, a2 are unknown coefficients. If (x1, y1) is substituted into the equation, we can get That is Then (xi, yi), we have:

[0072] The combination matrix is: Assume is A, is T, is X, then AX = T. Then x = (A T A) -1 A T T, and then get the curve equation, and the curve corresponding to the curve equation is the gas dispersion curve corresponding to C2H2.

[0073] After obtaining the gas dispersion curve corresponding to C2H2, data pairs with different trends from the gas dispersion curve are determined as unqualified data pairs, and the gas data groups corresponding to the unqualified data pairs are determined as unqualified gas data groups. Or, data pairs with the same trend but not on the gas dispersion curve are determined as unqualified data pairs, and the gas data groups corresponding to the unqualified data pairs are determined as unqualified gas data groups.

[0074] Since the dispersion curve can more intuitively present the trend of the gas concentration of the same fault characteristic gas changing with time, the unqualified gas data groups can be more intuitively filtered out through the dispersion curve, and the accuracy of the remaining gas data groups obtained is improved.

[0075] In some embodiments, the above determination of the concentration ratio of various fault characteristic gases in different gas data groups and the total gas production in the above different gas data groups according to the above remaining gas data groups comprises:

[0076] Determining the relative concentration ratio and the absolute concentration ratio of various fault characteristic gases in different gas data groups and determining the total gas production in the above different gas data groups according to the above remaining gas data.

[0077] Wherein, the relative concentration ratio refers to the two gas concentrations corresponding to two different fault characteristic gases, and the absolute concentration ratio refers to the two gas concentrations corresponding to the same fault characteristic gas.

[0078] For example, assuming that C2H2, C2H4, C2H6, H2, CH4, these five fault characteristic gases are detected at time point 1, and the concentration ratio includes the relative concentration ratio and the absolute concentration ratio, the relative concentration ratio and the absolute concentration ratio of the five fault characteristic gases corresponding to time point 1 are calculated respectively, and the concentration ratio is shown in Table 1.

[0079] Table 1:

[0080]

[0081] In Figure 1 , the "1" corresponding to the serial number 1 represents the absolute concentration ratio value corresponding to C2H2, "X2" represents the ratio of the gas concentration of C2H2 to the gas concentration of C2H4 at time point 1, "X3" represents the ratio of the gas concentration of C2H2 to the gas concentration of C2H6 at time point 1, "X4" represents the ratio of the gas concentration of C2H2 to the gas concentration of H2 at time point 1, and "X5" represents the ratio of the gas concentration of C2H2 to the gas concentration of CH4 at time point 1. The concentration ratio values corresponding to other serial numbers are explained similarly to the concentration ratio value corresponding to the serial number 1, which will not be described here.

[0082] After obtaining the concentration ratio value corresponding to each time point, the diagnostic result corresponding to each time point can be determined according to the concentration ratio value, and the fault diagnostic result of the transformer is obtained by combining the diagnostic results.

[0083] In the embodiments of the present application, the relative concentration ratio and the absolute concentration ratio are calculated when calculating the concentration ratio, the relative concentration ratio can reflect the proportion of the gas concentrations of two different fault characteristic gases, and the absolute concentration ratio can reflect the proportion of the gas concentrations of two same fault characteristic gases,

[0084] In some embodiments, the state of the transformer can be determined by a neural network model, and at this time, S14 includes:

[0085] The concentration ratio values of various fault characteristic gases in the different gas data groups, the total gas production in the different gas data groups, and the fault diagnostic result are taken as inputs of a preset state diagnostic model, and the state of the transformer output by the state diagnostic model is obtained, wherein the preset state diagnostic model is a BP neural network model of a full connection layer.

[0086] The state diagnostic model to be trained is trained according to the obtained sample data (such as the concentration ratio values, the total gas production, and the fault types of the fault characteristic gases corresponding to different faults) until a required model is trained, and the preset state diagnostic model is obtained.

[0087] The BP neural network model of the full connection layer is as shown in Figure 2 In Figure 2 , the BP neural network model includes an input layer, a hidden layer, and an output layer, and each node in the hidden layer is connected to each node of the input layer, and each node of the output layer is connected to each node of the hidden layer.

[0088] In the embodiments of the present application, it is considered that the BP neural network model has strong non-linear mapping capability, and the relationship among the concentration ratio of fault characteristic gas, total gas production and fault diagnosis result does not belong to linear relationship. Meanwhile, the number of neurons in each layer of the BP neural network model can be arbitrarily set according to actual situation, and the number of concentration ratios of fault characteristic gas generated by different faults can be different. Therefore, the state diagnosis model is constructed according to the BP neural network model, which is conducive to improving the accuracy of the subsequent state of the transformer. In addition, there is a certain relationship among the concentration ratio of fault characteristic gas, total gas production and fault diagnosis result, for example, different concentration ratios affect the fault diagnosis result, and the network structure of the full connection layer is conducive to the integration of the characteristics, thereby further improving the accuracy of the subsequent state of the transformer.

[0089] In some embodiments, it is considered that the higher the gas concentration of the generated fault characteristic gas, the more accurate the analysis result (such as the fault diagnosis result, such as the state of the transformer) obtained according to the gas concentration. However, in some cases, the concentration of fault characteristic gas can be low for a period of time. At this time, more gas data sets can be obtained for analysis to improve the subsequent analysis result. At this time, the above S11 includes:

[0090] B1, the gas concentration of different fault characteristic gases generated by the transformer is determined at M1 different time points respectively, to obtain M1 gas data sets, wherein M1 is a natural number greater than or equal to 2.

[0091] B2, according to the above M1 gas data sets, the average value of the gas concentration of each kind of the above fault characteristic gas is counted respectively.

[0092] B3, for each kind of the above fault characteristic gas, if the average value of the gas concentration of the above fault characteristic gas is less than the preset average concentration threshold corresponding to the above fault characteristic gas, the gas concentration of different fault characteristic gases generated by the transformer is continued to be determined at M2 time points respectively, until the average value of the gas concentration of the above fault characteristic gas is not less than the preset average concentration threshold corresponding to the above fault characteristic gas, wherein M2 is a natural number greater than 1.

[0093] Of course, if the average value of the gas concentration of each fault characteristic gas of the M1 gas data sets is not less than the corresponding average concentration threshold after obtaining the M1 gas data sets, the concentration ratio of the corresponding fault characteristic gas can be determined according to the M1 gas data sets.

[0094] In the embodiments of the present application, the number of the average concentration thresholds is equal to the number of the types of the fault characteristic gases. For example, if there are five types of fault characteristic gases, C2H2, C2H4, C2H6, H2 and CH4, there are also five preset average concentration thresholds, i.e., C2H2, C2H4, C2H6, H2 and CH4 correspond to different preset average concentration thresholds respectively.

[0095] Suppose that a group of gas data groups including C2H2 is obtained at time point 1 and time point 2 respectively, then the average values of the gas concentrations of C2H2 of the two groups of gas data are calculated, if the calculated average value of the gas concentration is less than the average concentration threshold corresponding to C2H2, then M2 groups of gas data are continuously obtained, if the average value of the gas concentration of C2H2 calculated according to the newly obtained gas data is equal to the average concentration threshold corresponding to C2H2, then the concentration ratios of various fault characteristic gases in different groups of gas data and the total gas production in different groups of gas data are determined according to the (2+M2) groups of gas data respectively.

[0096] In the embodiments of the present application, the concentration ratios of various fault characteristic gases in the corresponding groups of gas data are calculated according to the obtained groups of gas data only after it is determined that the average value of the gas concentration of the fault characteristic gas is not less than the preset average concentration threshold corresponding to the fault characteristic gas. Since the higher the gas concentration is, the higher the accuracy of the concentration ratio, the fault diagnosis result and the state of the transformer obtained by relying on the gas concentration is, therefore, when the gas concentration is high, the number of the groups of gas data obtained timely is small, and the accuracy of the state of the transformer obtained subsequently can also be improved. Moreover, when the gas concentration is low, more groups of gas data will be obtained, therefore, the state of the transformer can be determined by relying on more gas data subsequently, so as to improve the accuracy of the state of the transformer obtained subsequently.

[0097] It should be understood that the size of the serial number of each step in the above embodiments does not mean the order of execution, the execution order of each process should be determined according to its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present application.

[0098] corresponding to the transformer state diagnosis method described in the above embodiments, Figure 3 The structure block diagram of the transformer state diagnosis apparatus provided by the embodiments of the present application is shown, only the parts related to the embodiments of the present application are shown for the convenience of description.

[0099] Referring to Figure 3 The transformer state diagnosis apparatus 3 comprises a gas data group obtaining module 31, a concentration ratio determining module 32, a fault diagnosis result determining module 33 and a transformer state determining module 34.

[0100] Among them:

[0101] The gas data set obtaining module 31 is configured to determine the gas concentrations of different fault characteristic gases generated by the transformer at different time points respectively, and obtain at least two gas data sets, wherein each of the gas data sets corresponds to a time point.

[0102] The concentration ratio determining module 32 is configured to determine the concentration ratios of the fault characteristic gases in different gas data sets and the total gas production in the different gas data sets according to the at least two gas data sets.

[0103] The fault diagnosis result determining module 33 is configured to perform fault diagnosis on the transformer according to the concentration ratios of the fault characteristic gases in the different gas data sets, and obtain a fault diagnosis result, wherein the fault diagnosis result is used to indicate whether the transformer has a fault and the type of the fault when the transformer has a fault.

[0104] The transformer state determining module 34 is configured to determine the state of the transformer according to the concentration ratios of the fault characteristic gases in the different gas data sets, the total gas production in the different gas data sets, and the fault diagnosis result.

[0105] In the embodiments of the present application, the concentration ratios of the fault characteristic gases are determined according to the at least two gas data sets, and each of the gas data sets corresponds to a time point, so that the concentration ratios of the fault characteristic gases obtained are the concentration ratios corresponding to at least two time points, and thus the fault diagnosis result obtained by performing fault diagnosis on the transformer according to the concentration ratios of the fault characteristic gases is the fault diagnosis result corresponding to at least two time points. In addition, the state of the transformer is determined according to the concentration ratios of the fault characteristic gases in the different gas data sets, the total gas production in the different gas data sets, and the fault diagnosis result, and the concentration ratios of the fault characteristic gases, the total gas production, and the fault diagnosis result can reflect the running state of the transformer corresponding to at least two time points (for example, the fault diagnosis result can indicate whether the transformer has a fault and the type of the fault when the transformer has a fault), that is, the running state of the transformer corresponding to a period of time, so that the accuracy of the state of the transformer obtained can be improved by the above method. In addition, the concentration ratio can more directly determine the proportion of two gas concentrations, and the types and proportions of the fault characteristic gases generated by different faults are usually different when the transformer has a fault, so that the accuracy of the fault diagnosis result obtained can be improved by determining the concentration ratio according to the gas concentration and then performing fault diagnosis on the transformer, thereby facilitating effective management and control of the transformer.

[0106] In some embodiments, the transformer state diagnosis apparatus 3 provided by the embodiments of the present application further comprises:

[0107] a time length determination unit configured to determine a time length for obtaining stable gas concentrations before the different fault characteristic gases generated by the transformer at different time points are determined to obtain at least two gas data sets.

[0108] a time interval determination unit configured to determine a time interval between two adjacent time points according to the time length.

[0109] In some embodiments, the transformer state diagnosis apparatus 3 provided by the embodiments of the present application further comprises:

[0110] a disqualified gas data filtering module configured to filter out disqualified gas data sets from the at least two gas data sets to obtain remaining gas data sets before determining concentration ratios of various fault characteristic gases in different gas data sets and total gas production in the different gas data sets according to the at least two gas data sets.

[0111] Correspondingly, the concentration ratio determination module 32 is specifically configured to:

[0112] determine concentration ratios of various fault characteristic gases in different gas data sets and total gas production in the different gas data sets according to the remaining gas data sets.

[0113] In some embodiments, when filtering out the disqualified gas data from the at least two gas data sets to obtain the remaining gas data sets, the disqualified gas data filtering module is specifically configured to:

[0114] fit the at least two gas data sets to obtain a gas dissipation curve, and filter out the disqualified gas data sets from the at least two gas data sets according to the gas dissipation curve to obtain the remaining gas data sets.

[0115] In some embodiments, when determining concentration ratios of various fault characteristic gases in different gas data sets and total gas production in the different gas data sets according to the remaining gas data sets, the concentration ratio determination module 32 is specifically configured to:

[0116] determine relative concentration ratios and absolute concentration ratios of various fault characteristic gases in different gas data sets and total gas production in the different gas data sets according to the remaining gas data.

[0117] In some embodiments, the fault diagnosis result determination module 33 is specifically configured to:

[0118] The concentration ratios of various fault characteristic gases in the above-mentioned different gas data groups, the total gas production in the above-mentioned different gas data groups, and the above-mentioned fault diagnosis results are used as inputs to a preset state diagnosis model to obtain the state of the above-mentioned transformer output by the above-mentioned state diagnosis model. The above-mentioned preset state diagnosis model is a BP neural network model with a fully connected layer.

[0119] In some embodiments, the gas data acquisition module 31 includes:

[0120] M1 gas data group units are used to determine the gas concentration of different fault characteristic gases generated by the transformer at M1 different time points, resulting in M1 gas data groups, where M1 is a natural number greater than or equal to 2.

[0121] The gas concentration average value statistics unit is used to calculate the average gas concentration of each of the above-mentioned fault characteristic gases based on the above-mentioned M1 gas data groups.

[0122] The average gas concentration is relatively uniform and is used for each of the above-mentioned fault characteristic gases. If the average gas concentration of the above-mentioned fault characteristic gas is less than the preset average concentration threshold corresponding to the above-mentioned fault characteristic gas, then the gas concentration of different fault characteristic gases generated by the transformer is determined at M2 time points respectively, until the average gas concentration of the above-mentioned fault characteristic gas is not less than the preset average concentration threshold corresponding to the above-mentioned fault characteristic gas, where M2 is a natural number greater than 1.

[0123] It should be noted that the information interaction and execution process between the above-mentioned devices / units are based on the same concept as the method embodiments of this application. For details on their specific functions and technical effects, please refer to the method embodiments section, and they will not be repeated here.

[0124] Figure 4 This is a schematic diagram of the structure of an electronic device provided in an embodiment of this application. Figure 4 As shown, the electronic device 4 of this embodiment includes: at least one processor 40 ( Figure 4 The diagram shows only one processor, a memory 41, and a computer program 42 stored in the memory 41 and executable on the at least one processor 40, which, when executing the computer program 42, performs the steps in any of the above method embodiments.

[0125] The electronic device 4 can be a desktop computer, laptop, handheld computer, cloud server, or other computing device. This electronic device may include, but is not limited to, a processor 40 and a memory 41. Those skilled in the art will understand that... Figure 4The electronic device 4 is merely an example and does not limit the electronic device 4, which can include more or less components than shown, or combine some components, or different components, such as an input / output device, a network access device, etc.

[0126] The processor 40 can be a central processing unit (CPU), and can also be other general-purpose processors, a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field-programmable gate array (FPGA) or other programmable logic device, discrete gate or transistor logic, discrete hardware components, etc. The general-purpose processor can be a microprocessor or the processor can also be any conventional processor.

[0127] The memory 41 can be an internal storage unit of the electronic device 4, such as a hard disk or a memory of the electronic device 4 in some embodiments. The memory 41 can also be an external storage device of the electronic device 4, such as a plug-in hard disk, a smart media card (SMC), a secure digital (SD) card, a flash card, etc. equipped on the electronic device 4 in other embodiments. Further, the memory 41 can include both the internal storage unit and the external storage device of the electronic device 4. The memory 41 is used to store an operating system, an application program, a boot loader, data, and other programs, such as program codes of the computer program, etc. The memory 41 can also be used to temporarily store data that has been output or will be output.

[0128] Those skilled in the art can clearly understand that, for the convenience and brevity of description, only the above-mentioned division of each functional unit and module is exemplified, and in actual application, the above-mentioned functions can be completed by different functional units and modules according to needs, that is, the internal structure of the device is divided into different functional units or modules to complete all or part of the functions described above. Each functional unit and module in the embodiment can be integrated in one processing unit, or each unit can be physically present separately, or two or more units can be integrated in one unit. The integrated unit can be realized in the form of hardware or software functional unit. In addition, the specific name of each functional unit and module is only for easy distinction, and does not limit the protection scope of the application. The specific working process of the unit and module in the system can refer to the corresponding process in the foregoing method embodiment, which will not be described here.

[0129] The embodiment of the application further provides a computer readable storage medium, which stores a computer program. When the computer program is executed by a processor, the steps in each of the method embodiments described above can be implemented.

[0130] The embodiment of the application provides a computer program product. When the computer program product is run on an electronic device, the electronic device can execute the steps in each of the method embodiments described above.

[0131] The integrated unit, if realized in the form of a software functional unit and sold or used as an independent product, can be stored in a computer readable storage medium. Based on this understanding, the embodiment of the application can implement all or part of the processes in the above-mentioned method embodiments by a computer program to instruct related hardware to complete, and the computer program can be stored in a computer readable storage medium. When the processor executes the computer program, the steps in each of the method embodiments described above can be implemented. The computer program includes computer program code, which can be in the form of source code, object code, executable file or some intermediate form. The computer readable medium at least includes any entity or device capable of carrying the computer program code to the photographing device / electronic device, recording medium, computer memory, read-only memory (ROM), random access memory (RAM), electrical carrier signal, telecommunication signal and software distribution medium. For example, U disk, mobile hard disk, magnetic disk or optical disk, etc. In some jurisdictions, according to legislation and patent practice, the computer readable medium cannot be an electrical carrier signal and a telecommunication signal.

[0132] In the above embodiments, the description of each embodiment focuses on different aspects, and the parts not described or recorded in a certain embodiment can be referred to the relevant description of other embodiments.

[0133] Those skilled in the art can realize that the units and algorithm steps of each example described in combination with the embodiments disclosed herein can be realized by electronic hardware or a combination of computer software and electronic hardware. Whether the functions are realized in hardware or software depends on the specific application and design constraints of the technical solution. The skilled person can use different methods to realize the described functions for each specific application, but such implementation should not be considered beyond the scope of the present application.

[0134] In the embodiments provided in the present application, it should be understood that the disclosed apparatus / network device and method can be implemented in other ways. For example, the apparatus / network device embodiments described above are merely schematic, for example, the division of the modules or units is only a logical function division, and actual implementation can have another division manner, for example, a plurality of units or components can be combined or integrated into another system, or some features can be ignored or not executed. In addition, the coupling or direct coupling or communication connection between the displayed or discussed each other can be indirect coupling or communication connection through some interfaces, devices or units, and can be electrical, mechanical or other forms.

[0135] The units described as separate components can or can not be physically separated, and the components shown as units can or can not be physical units, that is, they can be located in one place, or can be distributed on a plurality of network units. Part or all of the units can be selected according to actual needs to achieve the purpose of the embodiments of the present application.

[0136] The above described embodiments are only used to illustrate the technical solutions of the present application, but not to limit them; although the present application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that the technical solutions recorded in the foregoing embodiments can be modified, or some technical features can be replaced by equivalents; and these modifications or replacements do not make the essence of the corresponding technical solutions deviate from the spirit and scope of the technical solutions of the embodiments of the present application, and should be included in the protection scope of the present application.

Claims

1. A method of diagnosing a state of a transformer, characterized by, The method comprises the following steps: determining the time length of stable gas concentration of the transformer, wherein the stable gas concentration refers to the value of the change of the gas concentration being less than a preset concentration change threshold value; determining the time interval between two adjacent time points according to the time length; determining the gas concentration of different fault characteristic gases generated by the transformer at different time points according to the time interval between the two adjacent time points, thereby obtaining at least two groups of gas data, wherein each group of gas data corresponds to a time point; determining the concentration ratio of various fault characteristic gases in different groups of gas data and the total gas production in the different groups of gas data according to the at least two groups of gas data; performing fault diagnosis on the transformer according to the concentration ratio of various fault characteristic gases in different groups of gas data, thereby obtaining a fault diagnosis result, wherein the fault diagnosis result is used to indicate whether the transformer has a fault and the type of the fault if the transformer has a fault; determining the state of the transformer according to the concentration ratio of various fault characteristic gases in different groups of gas data, the total gas production in the different groups of gas data, and the fault diagnosis result.

2. The method of diagnosing the state of a transformer according to Claim 1, wherein Before the step of determining the concentration ratio of various fault characteristic gases in different groups of gas data and the total gas production in the different groups of gas data according to the at least two groups of gas data, the method further comprises the following steps: filtering out unqualified groups of gas data from the at least two groups of gas data, thereby obtaining remaining groups of gas data; the step of determining the concentration ratio of various fault characteristic gases in different groups of gas data and the total gas production in the different groups of gas data according to the at least two groups of gas data comprises the following step: determining the concentration ratio of various fault characteristic gases in different groups of gas data and the total gas production in the different groups of gas data according to the remaining groups of gas data.

3. The method of diagnosing the state of a transformer according to claim 2, wherein the step of filtering out unqualified groups of gas data from the at least two groups of gas data, thereby obtaining remaining groups of gas data, comprises the following steps: fitting the at least two groups of gas data, thereby obtaining a gas diffusion curve; filtering out unqualified groups of gas data from the at least two groups of gas data according to the gas diffusion curve, thereby obtaining remaining groups of gas data.

4. The method of diagnosing the state of a transformer according to Claim 2, wherein the step of determining the concentration ratio of various fault characteristic gases in different groups of gas data and the total gas production in the different groups of gas data according to the remaining groups of gas data comprises the following step: determining the relative concentration ratio and the absolute concentration ratio of various fault characteristic gases in different groups of gas data and the total gas production in the different groups of gas data according to the remaining groups of gas data.

5. The method of diagnosing the state of a transformer according to any one of claims 1 to 4, characterized by, the step of determining the state of the transformer according to the concentration ratio of various fault characteristic gases in different groups of gas data, the total gas production in the different groups of gas data, and the fault diagnosis result comprises the following step: inputting the concentration ratio of various fault characteristic gases in different groups of gas data, the total gas production in the different groups of gas data, and the fault diagnosis result into a preset state diagnosis model as an input of the state diagnosis model, thereby obtaining the state of the transformer output by the state diagnosis model, wherein the preset state diagnosis model is a BP neural network model with full connection layers.

6. The method of diagnosing the state of a transformer according to any one of claims 1 to 4, characterized by, The gas concentrations of different fault characteristic gases generated by the transformer are determined at different time points respectively to obtain at least two gas data sets, including: M1 different time points are determined to obtain M1 gas data sets, where M1 is a natural number greater than or equal to 2; The average values of the gas concentrations of various fault characteristic gases are respectively calculated according to the M1 gas data sets; For each fault characteristic gas, if the average value of the gas concentration of the fault characteristic gas is less than the preset average concentration threshold corresponding to the fault characteristic gas, the gas concentrations of different fault characteristic gases generated by the transformer are determined at M2 time points respectively until the average value of the gas concentration of the fault characteristic gas is not less than the preset average concentration threshold corresponding to the fault characteristic gas, where M2 is a natural number greater than 1.

7. A condition diagnosis device for a transformer, characterized in that, The time length determination unit is configured to determine a time length for obtaining a stable gas concentration of the transformer, where the stable gas concentration refers to a value of a gas concentration change being less than a preset concentration change threshold. The time interval determination unit is configured to determine a time interval between adjacent two time points according to the time length. The gas data set acquisition module is configured to determine the gas concentrations of different fault characteristic gases generated by the transformer at different time points respectively according to the time interval between the adjacent two time points to obtain at least two gas data sets, where each gas data set uniquely corresponds to one time point. The concentration ratio determination module is configured to determine the concentration ratios of various fault characteristic gases in different gas data sets and the total gas production in the different gas data sets according to the at least two gas data sets. The fault diagnosis result determination module is configured to perform fault diagnosis on the transformer according to the concentration ratios of various fault characteristic gases in the different gas data sets to obtain a fault diagnosis result, where the fault diagnosis result is used to indicate whether the transformer has a fault and, if the transformer has a fault, the type of the fault. The transformer state determination module is configured to determine the state of the transformer according to the concentration ratios of various fault characteristic gases in the different gas data sets, the total gas production in the different gas data sets, and the fault diagnosis result. The processor executes the computer program to implement the method in any one of claims 1 to 6.

8. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, The computer program is executed by the processor to implement the method in any one of claims 1 to 6.

9. A computer-readable storage medium storing a computer program, the computer program comprising instructions that, when executed by a computer, cause the computer to perform the method of any one of claims 1 to 8. ​

Images