Transformer fault detection method and device, electronic equipment and storage medium

Abstract

The invention discloses a transformer fault detection method and apparatus, an electronic device and a storage medium. The method comprises the steps of obtaining dissolved gas concentration data within a historical time period when various faults of a transformer occur; for each type of faults, fitting is carried out according to the dissolved gas concentration data in the historical time period, and a first dissolved gas concentration curve used for representing the dissolved gas concentration change condition when the transformer has the corresponding fault is generated; acquiring dissolved gas concentration data of the transformer in a detection time period, and fitting the dissolved gas concentration data of the transformer in the detection time period to generate a second dissolved gas concentration curve for representing the change condition of the dissolved gas concentration of the transformer in the detection time period; calculating the similarity between the second dissolved gas concentration curve and the first dissolved gas concentration curve corresponding to each fault; and determining whether the transformer has a corresponding fault according to the similarity. According to the invention, potential faults of the transformer can be found in time.

Description

Technical Field

[0001] The present invention relates to the technical field of electric power equipment, and in particular to a transformer fault detection method, device, electronic equipment and storage medium. Background Art

[0002] As an important power equipment, the operating status of the transformer is directly related to the safety and stability of the power system. The oil-paper insulation system is often used inside the transformer. The transformer oil not only has an insulating function, but also can dissipate heat and protect the core, winding and other structures. When overheating, discharge and other faults occur inside the transformer, the hydrocarbons in the transformer oil will cause chemical bond breakage and reaction, and at the same time, the cellulose in the paper insulation material will be thermally decomposed or oxidized to generate small molecular gases such as carbon monoxide and carbon dioxide. Therefore, the composition and concentration of the dissolved gas in the transformer oil can reflect the real-time operating status of the transformer and is an important basis for fault diagnosis.

[0003] Existing technologies have a lag in transformer fault detection, making it difficult to detect potential hidden dangers in a timely manner, increasing the risk of equipment damage and power grid accidents. Usually, an online monitoring device is installed in the transformer to determine the fault by monitoring the concentration changes of dissolved gases in the transformer oil. When the concentration of a certain dissolved gas exceeds the preset judgment threshold, an alarm is triggered. However, this method often relies on the cumulative effect of gas concentration, resulting in the fault being detected only after it occurs and lasts for a period of time and the gas concentration reaches the judgment threshold. Summary of the invention

[0004] The embodiments of the present invention provide a transformer fault detection method, device, electronic device and storage medium. By implementing the present invention, potential transformer faults can be discovered in time, and early warning of transformer faults can be achieved.

[0005] An embodiment of the present invention provides a transformer fault detection method, comprising:

[0006] Obtain dissolved gas concentration data within a historical period when various transformer faults occur;

[0007] For each type of fault, fitting is performed based on dissolved gas concentration data in a historical time period to generate a first dissolved gas concentration curve for characterizing the change in dissolved gas concentration when a corresponding fault occurs in the transformer;

[0008] Acquire dissolved gas concentration data of the transformer within a detection period, and fit the dissolved gas concentration data of the transformer within the detection period to generate a second dissolved gas concentration curve for characterizing the change of dissolved gas concentration of the transformer within the detection period;

[0009] Calculate the similarity between the second dissolved gas concentration curve and the first dissolved gas concentration curve corresponding to each type of fault;

[0010] According to the similarity, it is determined whether the transformer has a corresponding fault.

[0011] Furthermore, for each type of fault, fitting is performed according to dissolved gas concentration data in a historical time period to generate a first dissolved gas concentration curve for characterizing the change in dissolved gas concentration when a corresponding fault occurs in the transformer, including:

[0012] For each type of fault, a polynomial fitting is performed based on the dissolved gas concentration data in the historical time period, the coefficients of the preset polynomial function are solved, and the fitted polynomial function is generated;

[0013] A first dissolved gas concentration curve is generated according to the fitted polynomial function, which is used to characterize the change of dissolved gas concentration when a corresponding fault occurs in the transformer.

[0014] Furthermore, the preset polynomial function is:

[0015] P(t i )=a 0 +a 1 t i +a 2 t i 2 +…+a m t i m

[0016] Among them, P(t i ) is a preset polynomial function; m is the degree of the polynomial function; a 0 , a 1 , ..., a m are the coefficients of the polynomial function; t i is the i-th time node in the dissolved gas concentration data.

[0017] Furthermore, the coefficients of the preset polynomial function are solved in the following way:

[0018] Generate a square sum of errors function of a preset polynomial function according to dissolved gas concentration data in a historical time period and a preset polynomial function;

[0019] Generate partial derivatives of each coefficient in a preset polynomial function according to the error square sum function;

[0020] Set the partial derivatives of each coefficient to 0 to form a linear system of equations;

[0021] Solve linear equations and generate coefficients of pre-defined polynomial functions.

[0022] Furthermore, the error square sum function is:

[0023]

[0024] Where E is the error square sum function; P(t i ) is a preset polynomial function; t i is the i-th time node in the dissolved gas concentration data; c i is the concentration corresponding to the i-th time node in the dissolved gas concentration data.

[0025] Further, the similarity between the second dissolved gas concentration curve and the first dissolved gas concentration curve is calculated in the following manner:

[0026] Extracting the same number of first data points and second data points from the first dissolved gas concentration curve and the second dissolved gas concentration curve respectively at a preset sampling interval;

[0027] Calculate the Euclidean distance between each first data point and the corresponding second data point, and generate a distance matrix based on the Euclidean distances between all data points;

[0028] The dynamic time warping algorithm is used to generate the shortest matching path of the distance matrix;

[0029] The similarity between the second dissolved gas concentration curve and a first dissolved gas concentration curve is determined according to the shortest matching path.

[0030] Further, after determining whether the transformer has a corresponding fault according to the similarity, the method further includes:

[0031] When a corresponding fault occurs in the transformer, an alarm message is sent.

[0032] Based on the above method embodiment, the present invention provides a corresponding device embodiment.

[0033] An embodiment of the present invention provides a transformer fault detection device, comprising: a first dissolved gas concentration curve generating module, a second dissolved gas concentration curve generating module, a similarity calculating module and a fault determination module;

[0034] The first dissolved gas concentration curve generating module is used to obtain dissolved gas concentration data in a historical time period when various types of transformer faults occur; for each type of fault, fitting is performed based on the dissolved gas concentration data in the historical time period to generate a first dissolved gas concentration curve for characterizing the change in dissolved gas concentration when the corresponding fault occurs in the transformer;

[0035] The second dissolved gas concentration curve generating module is used to obtain dissolved gas concentration data of the transformer within a detection period, and to fit the dissolved gas concentration data of the transformer within the detection period to generate a second dissolved gas concentration curve for characterizing the change of dissolved gas concentration of the transformer within the detection period;

[0036] The similarity calculation module is used to calculate the similarity between the second dissolved gas concentration curve and the first dissolved gas concentration curve corresponding to each type of fault;

[0037] The fault determination module is used to determine whether the transformer has a corresponding fault according to the similarity.

[0038] Based on the above method embodiment, the present invention provides a corresponding electronic device embodiment.

[0039] An embodiment of the present invention provides an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, the transformer fault detection method described in any one of the above method embodiments can be implemented.

[0040] Based on the above method item embodiments, the present invention provides a corresponding storage medium item embodiment.

[0041] An embodiment of the present invention provides a storage medium having a computer program stored thereon. When the computer program is executed by a processor, the transformer fault detection method described in any one of the above method embodiments can be implemented.

[0042] Compared with the prior art, the present invention has the following beneficial effects:

[0043] The embodiment of the present invention provides a transformer fault detection method, device, electronic device and storage medium. The method obtains the dissolved gas concentration data of the transformer in the historical time period when various faults occur, and fits the data to generate a first dissolved gas concentration curve corresponding to each fault type to characterize the change characteristics of the dissolved gas concentration over time under different faults. The dissolved gas concentration data of the transformer in the detection period is obtained, and fitted to generate a second dissolved gas concentration curve reflecting the current state. Subsequently, by calculating the similarity between the second dissolved gas concentration curve and each first dissolved gas concentration curve, the degree of match between the state to be tested and the historical fault mode is measured; according to the size of the similarity, it is judged whether the transformer has a corresponding fault. This solution no longer relies on a single dissolved gas concentration exceeding a fixed threshold to trigger an alarm, but generates a dynamic curve of the dissolved gas concentration changing over time by fitting, and introduces a similarity matching mechanism to comprehensively consider the similarity between the concentration change trend and the historical fault characteristics, thereby achieving more robust fault identification. Compared with the method of triggering an alarm only when the concentration exceeds the limit, this solution can identify the abnormal change trend of dissolved gas concentration before it exceeds the limit, thereby perceiving potential faults in advance, helping to achieve early warning of transformers, and avoiding missed faults due to insufficient gas concentration accumulation. It effectively improves the timeliness and accuracy of transformer fault detection, and provides strong support for the intelligent operation and maintenance and precise maintenance of power equipment. BRIEF DESCRIPTION OF THE DRAWINGS

[0044] Figure 1 It is a flow chart of a transformer fault detection method provided by an embodiment of the present invention.

[0045] Figure 2 It is a structural schematic diagram of a transformer fault detection device provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0046] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0047] like Figure 1 As shown, an embodiment of the present invention provides a transformer fault detection method, which at least includes the following steps:

[0048] Step S1, obtaining dissolved gas concentration data within a historical time period when various transformer faults occur;

[0049] In the specific implementation, during the historical time period when various types of transformer faults occur, dissolved gas concentration data are collected, including but not limited to the concentration changes of characteristic gases such as hydrogen, methane, ethylene, and acetylene. These data can be obtained through an online monitoring device for dissolved gas in transformer oil or periodic oil sample detection, and the corresponding fault types are marked, such as overheating faults, discharge faults, partial discharges, etc. The selection of historical time periods is based on actual working conditions to ensure that the complete evolution process of the fault is covered, from the early signs of the fault, the development stage to the final state of the dissolved gas concentration changes, thereby forming a continuous and real dissolved gas concentration data sequence, laying the foundation for subsequent data fitting and fault feature extraction.

[0050] Step S2: for each type of fault, fitting is performed according to the dissolved gas concentration data in the historical time period to generate a first dissolved gas concentration curve for characterizing the change of dissolved gas concentration when the corresponding fault occurs in the transformer;

[0051] In a preferred embodiment, for each type of fault, fitting is performed according to dissolved gas concentration data in a historical time period to generate a first dissolved gas concentration curve for characterizing the change in dissolved gas concentration when a corresponding fault occurs in the transformer, including:

[0052] For each type of fault, a polynomial fitting is performed based on the dissolved gas concentration data in the historical time period, the coefficients of the preset polynomial function are solved, and the fitted polynomial function is generated;

[0053] A first dissolved gas concentration curve is generated according to the fitted polynomial function, which is used to characterize the change of dissolved gas concentration when a corresponding fault occurs in the transformer.

[0054] Specifically, the preset polynomial function is:

[0055] P(t i )=a 0 +a 1 t i +a 2 t i 2 +…+a m t i m

[0056] Among them, P(t i ) is a preset polynomial function; m is the degree of the polynomial function; a 0 , a 1 , ..., a m are the coefficients of the polynomial function; t i is the i-th time node in the dissolved gas concentration data.

[0057] In an optional embodiment, the coefficients of the preset polynomial function are solved in the following manner:

[0058] Generate a square sum of errors function of a preset polynomial function according to dissolved gas concentration data in a historical time period and a preset polynomial function;

[0059] Generate partial derivatives of each coefficient in a preset polynomial function according to the error square sum function;

[0060] Set the partial derivatives of each coefficient to 0 to form a linear system of equations;

[0061] Solve linear equations and generate coefficients of pre-defined polynomial functions.

[0062] In a specific implementation, a preset polynomial function reflecting the change of dissolved gas concentration over time is constructed based on the dissolved gas concentration data in the historical time period and the preset polynomial function model, and an error square sum function of the polynomial function is established based on the principle of least squares. The error square sum function is used to measure the degree of deviation between the preset polynomial function and the actual dissolved gas concentration data, and its expression is the sum of the squares of the fitting errors of all historical data points, thereby quantifying the degree of fit between the fitting function and the actual concentration change trend.

[0063] On this basis, in order to optimize the fitting effect of the preset polynomial function, the error square sum function is partially derived for each order coefficient in the polynomial function to obtain the partial derivative function of each coefficient. These partial derivatives reflect the sensitivity of the error square sum function to the change of each coefficient and are used to guide the subsequent coefficient solution process.

[0064] Subsequently, the partial derivative functions of each coefficient are set to zero to find the minimum point of the error square sum function, thereby forming a set of linear equations. The solutions to these linear equations are the optimal coefficient combinations that make the preset polynomial function closest to the historical dissolved gas concentration data.

[0065] Finally, by solving the linear equations, the coefficient set of the preset polynomial function is obtained, thereby generating a polynomial function that can accurately fit the trend of dissolved gas concentration changes in the historical time period. This polynomial function not only describes the overall change law of dissolved gas concentration, but also lays a mathematical foundation for the construction and comparison of concentration change curves of different fault types in the future.

[0066] Specifically, the error square sum function is:

[0067]

[0068] Where E is the error square sum function; P(t i ) is a preset polynomial function; ti is the i-th time node in the dissolved gas concentration data; c i is the concentration corresponding to the i-th time node in the dissolved gas concentration data.

[0069] It should be noted that for each type of fault, such as transformer overheating fault, discharge fault, partial discharge fault, etc., fitting processing is performed based on the dissolved gas concentration data collected in the historical time period. Data fitting uses polynomial fitting to fully consider the dynamic change trend of dissolved gas concentration during the occurrence, development and evolution of faults, thereby eliminating data noise and extracting key features that reflect the change of concentration over time. The fitted data generates the corresponding first dissolved gas concentration curve, and each curve accurately depicts the change law and evolution trajectory of dissolved gas concentration when a specific fault type occurs in the transformer. These first dissolved gas concentration curves not only retain the unique characteristic information of various faults, but also reflect the rate of change, peak position and growth or attenuation trend of gas concentration over time, laying a solid foundation for subsequent similarity comparison and fault identification.

[0070] Step S3, obtaining dissolved gas concentration data of the transformer within a detection period, and fitting the dissolved gas concentration data of the transformer within the detection period to generate a second dissolved gas concentration curve for characterizing the change of dissolved gas concentration of the transformer within the detection period;

[0071] Specifically, the dissolved gas concentration data of the transformer within a detection period is obtained, wherein the detection period is the time period for currently monitoring the transformer status, and the detection period can be set to a time window of fixed length according to actual needs, such as several hours, several days or other suitable time intervals, to fully reflect the changes in the dissolved gas concentration of the transformer within the time period.

[0072] After obtaining the dissolved gas concentration data within the detection period, the data is preprocessed, including but not limited to data cleaning, outlier removal, missing data interpolation and other operations to ensure the authenticity and continuity of the concentration data, thereby eliminating data deviations caused by sensor errors or sudden interference.

[0073] Subsequently, based on a preset polynomial fitting model, the dissolved gas concentration data within the detection period is fitted to obtain a mathematical model that can reflect the time variation law of the dissolved gas concentration of the transformer within the detection period, and generate a second dissolved gas concentration curve that characterizes the variation law.

[0074] The second dissolved gas concentration curve can accurately characterize the current dynamic characteristics of the dissolved gas concentration of the transformer, laying the foundation for the subsequent similarity comparison of the first dissolved gas concentration curves corresponding to various faults, thereby realizing real-time monitoring and abnormality identification of the transformer operating status.

[0075] Step S4, calculating the similarity between the second dissolved gas concentration curve and the first dissolved gas concentration curve corresponding to each type of fault;

[0076] In a preferred embodiment, the similarity between the second dissolved gas concentration curve and the first dissolved gas concentration curve is calculated in the following manner:

[0077] Extracting the same number of first data points and second data points from the first dissolved gas concentration curve and the second dissolved gas concentration curve respectively at a preset sampling interval;

[0078] Calculate the Euclidean distance between each first data point and the corresponding second data point, and generate a distance matrix based on the Euclidean distances between all data points;

[0079] The dynamic time warping algorithm is used to generate the shortest matching path of the distance matrix;

[0080] The similarity between the second dissolved gas concentration curve and a first dissolved gas concentration curve is determined according to the shortest matching path.

[0081] Specifically, the similarity between the second dissolved gas concentration curve and the first dissolved gas concentration curve is calculated to measure the similarity between the dissolved gas concentration change trend of the transformer during the detection period and the dissolved gas concentration change pattern in the historical fault stage, thereby achieving accurate comparison and abnormality identification of the current transformer status.

[0082] First, the first dissolved gas concentration curve and the second dissolved gas concentration curve are sampled at equal intervals according to a preset sampling interval, and the same number of first data points and second data points are extracted from the two curves to ensure the correspondence and comparability of the data points in the time dimension. The sampling interval can be flexibly set according to the change rate of the dissolved gas concentration, the sampling frequency of the monitoring equipment, and the actual detection requirements to ensure that the extracted data points can fully reflect the change trend of the concentration curve.

[0083] Then, the Euclidean distance between each first data point and the corresponding second data point is calculated to quantify the difference between the two curves at each sampling point. Based on the Euclidean distance between all data points, a distance matrix is ​​constructed to comprehensively reflect the difference relationship between the first dissolved gas concentration curve and the second dissolved gas concentration curve in the time dimension and the numerical dimension.

[0084] On this basis, the dynamic time warping (DTW) algorithm is used to process the distance matrix. The dynamic time warping algorithm can flexibly adjust the correspondence between the two curves on the time axis, allowing stretching or compression in the time dimension, thereby overcoming the comparison error caused by different concentration change rates, and ensuring that even if the two curves are misaligned in time, the consistency of their overall change patterns can be accurately measured. The DTW algorithm is used to generate the shortest matching path in the distance matrix, which represents the optimal comparison method between the two dissolved gas concentration curves.

[0085] Finally, according to the cumulative distance of the shortest matching path, the similarity between the second dissolved gas concentration curve and the first dissolved gas concentration curve is determined. The similarity value can reflect the closeness between the current trend of the dissolved gas concentration change of the transformer and the concentration change pattern of the historical fault stage, providing an accurate quantitative basis for subsequent fault diagnosis and early warning.

[0086] Preferably, the similarity is calculated by the following formula:

[0087]

[0088] Among them, S is the similarity, and D is the cumulative distance of the shortest matching path obtained by the dynamic time warping (DTW) algorithm. This formula ensures that when the cumulative distance D of the two curves approaches 0, S approaches 1, indicating that the two are very similar; and when D increases, S approaches 0, indicating that the similarity between the two is low.

[0089] Step S5: Determine whether the transformer has a corresponding fault according to the similarity.

[0090] In an optional embodiment, determining whether the transformer has a corresponding fault according to the similarity includes:

[0091] Determine whether the similarity exceeds the corresponding fault threshold, if so, determine that the transformer has the corresponding fault; if not, determine that the transformer does not have the corresponding fault;

[0092] It should be noted that if the similarity of a certain fault type exceeds the preset threshold, it means that the trend of the dissolved gas concentration change of the transformer is consistent with the historical pattern of the fault type, so that the transformer can be determined to have the corresponding fault type. However, considering that the transformer may have multiple fault types at the same time, especially in the case of composite faults, multi-point faults or secondary faults, judging only by the similarity of a single fault type may not fully and accurately reflect the actual fault state of the transformer.

[0093] For example, a compound fault usually manifests itself as a superposition of multiple fault modes, which may cause abnormal changes in dissolved gas concentration to meet the characteristics of multiple fault types at the same time. Multi-point faults refer to independent failures in multiple parts of the transformer, resulting in different types of gas concentration changes, which may eventually form a superposition effect. In addition, secondary faults are often chain reactions caused by initial faults, which may increase the release of more gas on the basis of the initial fault, further affecting the overall dissolved gas concentration.

[0094] Therefore, in practical applications, in addition to the judgment of a single fault type, if the similarity of multiple fault types exceeds the preset threshold (for example, similarity ≥ 0.8), it can be determined that the transformer may have multiple fault types at the same time, and then the state of compound fault, multi-point fault or secondary fault can be identified. Through this method, the fault information of the transformer can be captured more comprehensively and accurately, and more reliable data support can be provided for subsequent inspection and maintenance work, ensuring the safe operation of the transformer and timely handling of faults.

[0095] After determining whether the transformer has a corresponding fault according to the similarity, the method further includes:

[0096] When a corresponding fault occurs in the transformer, an alarm message is sent.

[0097] Based on the above method embodiment, the present invention provides a corresponding device embodiment.

[0098] like Figure 2 As shown, an embodiment of the present invention provides a transformer fault detection device, including: a first dissolved gas concentration curve generating module, a second dissolved gas concentration curve generating module, a similarity calculation module and a fault determination module;

[0099] The first dissolved gas concentration curve generating module is used to obtain dissolved gas concentration data in a historical time period when various types of transformer faults occur; for each type of fault, fitting is performed based on the dissolved gas concentration data in the historical time period to generate a first dissolved gas concentration curve for characterizing the change in dissolved gas concentration when the corresponding fault occurs in the transformer;

[0100] The second dissolved gas concentration curve generating module is used to obtain dissolved gas concentration data of the transformer within a detection period, and to fit the dissolved gas concentration data of the transformer within the detection period to generate a second dissolved gas concentration curve for characterizing the change of dissolved gas concentration of the transformer within the detection period;

[0101] The similarity calculation module is used to calculate the similarity between the second dissolved gas concentration curve and the first dissolved gas concentration curve corresponding to each type of fault;

[0102] The fault determination module is used to determine whether the transformer has a corresponding fault according to the similarity.

[0103] It should be noted that the embodiment of the device described above corresponds to the above-mentioned embodiment of the present invention, and it can implement any of the transformer fault detection methods described above in the present invention. In addition, the embodiment of the above-mentioned device is merely schematic, wherein the modules described as separate components may or may not be physically separated, and the components displayed as modules 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 embodiment of the device provided by the present invention, the connection relationship between the modules indicates that there is a communication connection between them, which can 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.

[0104] Based on the above method embodiment of the present invention, a corresponding electronic device embodiment is provided.

[0105] An embodiment of the present invention provides an electronic device, comprising a processor, a memory, and a computer program stored in the memory and configured to be executed by the processor, wherein when the processor executes the computer program, the transformer fault detection method described in any one of the present invention is implemented, or when the processor executes the computer program, the functions of the modules in the above-mentioned device embodiments are implemented.

[0106] Exemplarily, the computer program may be divided into one or more modules, which are stored in the memory and executed by the processor to implement the present invention. The one or more modules may be a series of computer program instruction segments capable of implementing specific functions, which are used to describe the execution process of the computer program in the terminal device.

[0107] The terminal device may be a computing device such as a desktop computer, a notebook, a PDA, a cloud server, etc. The terminal device may include, but is not limited to, a processor and a memory.

[0108] The processor may be a central processing unit (CPU), 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. The general-purpose processor may be a microprocessor or any conventional processor, etc. The processor is the control center of the terminal device, and uses various interfaces and lines to connect various parts of the entire terminal device.

[0109] The memory can be used to store the computer program and / or module, and the processor realizes various functions of the terminal device by running or executing the computer program and / or module stored in the memory, and calling the data stored in the memory. The memory can mainly include a program storage area and a data storage area, wherein the program storage area can store an operating system, at least one application required for a function, etc.; the data storage area can store data created according to the use of the mobile phone, etc. In addition, the memory 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.

[0110] Based on the above method embodiment, the present invention provides a storage medium embodiment;

[0111] Another embodiment of the present invention provides a storage medium, wherein the storage medium includes a stored computer program, wherein when the computer program is executed, the device where the storage medium is located is controlled to execute any one of the transformer fault detection methods described above in the present invention.

[0112] The storage medium is a computer-readable storage medium, and the computer program includes computer program code, which may 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, USB flash drive, mobile hard disk, magnetic disk, optical disk, computer memory, read-only memory (ROM), random access memory (RAM), electric carrier signal, telecommunication signal and software distribution medium, etc. It should be noted that the content contained in the computer-readable medium may be appropriately increased or decreased according to the requirements of legislation and patent practice in the jurisdiction. For example, in some jurisdictions, according to legislation and patent practice, computer-readable media do not include electric carrier signals and telecommunication signals.

[0113] In the description of this specification, the description with reference to the terms "one embodiment", "some embodiments", "example", "specific example" or "some examples" etc. means that the specific features, structures, materials or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present application. Moreover, the specific features, structures, materials or characteristics described may be combined in any one or more embodiments or examples in a suitable manner. In addition, those skilled in the art may combine and combine different embodiments or examples described in this specification and the features of different embodiments or examples, unless they are contradictory.

[0114] The above is a preferred embodiment of the present invention. It should be pointed out that a person skilled in the art can make several improvements and modifications without departing from the principle of the present invention. These improvements and modifications are also considered to be within the scope of protection of the present invention.

Claims

1. A transformer fault detection method, characterized in that: include: Obtain dissolved gas concentration data within a historical period when various transformer faults occur; For each type of fault, fitting is performed based on dissolved gas concentration data in a historical time period to generate a first dissolved gas concentration curve for characterizing the change in dissolved gas concentration when a corresponding fault occurs in the transformer; Acquire dissolved gas concentration data of the transformer within a detection period, and fit the dissolved gas concentration data of the transformer within the detection period to generate a second dissolved gas concentration curve for characterizing the change of dissolved gas concentration of the transformer within the detection period; Calculate the similarity between the second dissolved gas concentration curve and the first dissolved gas concentration curve corresponding to each type of fault; According to the similarity, it is determined whether the transformer has a corresponding fault.

2. The transformer fault detection method according to claim 1, characterized in that: For each type of fault, fitting is performed according to the dissolved gas concentration data in the historical time period to generate a first dissolved gas concentration curve for characterizing the change of dissolved gas concentration when the corresponding fault occurs in the transformer, including: For each type of fault, a polynomial fitting is performed based on the dissolved gas concentration data in the historical time period, the coefficients of the preset polynomial function are solved, and the fitted polynomial function is generated; A first dissolved gas concentration curve is generated according to the fitted polynomial function, which is used to characterize the change of dissolved gas concentration when a corresponding fault occurs in the transformer.

3. The transformer fault detection method according to claim 2, characterized in that: The preset polynomial function is: P(t i )=a0+a1t i +a2t i 2 +…+a m t i m Among them, P(t i ) is a preset polynomial function; m is the degree of the polynomial function; a0, a1, ..., a m are the coefficients of the polynomial function; t i is the i-th time node in the dissolved gas concentration data.

4. The transformer fault detection method according to claim 3, characterized in that: Solve for the coefficients of a preset polynomial function in the following way: Generate a square sum of errors function of a preset polynomial function according to dissolved gas concentration data in a historical time period and a preset polynomial function; Generate partial derivatives of each coefficient in a preset polynomial function according to the error square sum function; Set the partial derivatives of each coefficient to 0 to form a linear system of equations; Solve linear equations and generate coefficients of pre-defined polynomial functions.

5. The transformer fault detection method according to claim 4, characterized in that: The error sum of squares function is: Where E is the error square sum function; P(t i ) is a preset polynomial function; t i is the i-th time node in the dissolved gas concentration data; c i is the concentration corresponding to the i-th time node in the dissolved gas concentration data.

6. The transformer fault detection method according to claim 5, characterized in that: The similarity between the second dissolved gas concentration curve and the first dissolved gas concentration curve is calculated by: Extracting the same number of first data points and second data points from the first dissolved gas concentration curve and the second dissolved gas concentration curve respectively at a preset sampling interval; Calculate the Euclidean distance between each first data point and the corresponding second data point, and generate a distance matrix based on the Euclidean distances between all data points; The dynamic time warping algorithm is used to generate the shortest matching path of the distance matrix; The similarity between the second dissolved gas concentration curve and a first dissolved gas concentration curve is determined according to the shortest matching path.

7. The transformer fault detection method according to claim 6, characterized in that: After determining whether the transformer has a corresponding fault according to the similarity, the method further includes: When a corresponding fault occurs in the transformer, an alarm message is sent.

8. A transformer fault detection device, characterized in that: include: A first dissolved gas concentration curve generating module, a second dissolved gas concentration curve generating module, a similarity calculating module and a fault determining module; The first dissolved gas concentration curve generating module is used to obtain dissolved gas concentration data in a historical time period when various types of transformer faults occur; for each type of fault, fitting is performed based on the dissolved gas concentration data in the historical time period to generate a first dissolved gas concentration curve for characterizing the change in dissolved gas concentration when the corresponding fault occurs in the transformer; The second dissolved gas concentration curve generating module is used to obtain dissolved gas concentration data of the transformer within a detection period, and to fit the dissolved gas concentration data of the transformer within the detection period to generate a second dissolved gas concentration curve for characterizing the change of dissolved gas concentration of the transformer within the detection period; The similarity calculation module is used to calculate the similarity between the second dissolved gas concentration curve and the first dissolved gas concentration curve corresponding to each type of fault; The fault determination module is used to determine whether the transformer has a corresponding fault according to the similarity.

9. An electronic device, characterized in that: The invention comprises a memory, a processor and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, the transformer fault detection method according to any one of claims 1 to 7 can be implemented.

10. A storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the transformer fault detection method according to any one of claims 1 to 7 can be implemented.

Images