Transformer inter-turn short circuit fault location method and device, medium and terminal

Abstract

The application discloses a transformer inter-turn short-circuit fault position positioning method and device, medium and terminal, relates to the technical field of transformer fault diagnosis, and mainly aims at the problem that the transformer occurs internal fault due to the fact that the existing reaction is not timely, the action sensitivity is low, and the inter-turn short-circuit fault position cannot be accurately positioned. It comprises the following steps: when it is detected that a target transformer has an inter-turn short-circuit fault, micro-temperature field simulation data of the target transformer is acquired, the micro-temperature field simulation data is obtained based on a micro-temperature field digital twin model of the target transformer; based on a convolutional neural network, an inter-turn short-circuit fault characteristic parameter is extracted from the micro-temperature field simulation data; and based on a Bayesian inference method, the position of the inter-turn short-circuit fault of the target transformer is determined according to the inter-turn short-circuit fault characteristic parameter.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of transformer fault diagnosis, in particular to a transformer inter-turn short-circuit fault position positioning method and device, medium and terminal. BACKGROUND

[0002] As the core equipment in the power system equipment, the power transformer will seriously affect the reliability and safety of the power system if it fails. Among the transformer faults, the winding inter-turn short-circuit is a common fault type of the power transformer, which is prone to cause problems such as solid insulation aging and local hot spot diffusion.

[0003] In order to avoid the above problems, at present, the engineering mostly adopts gas protection, differential protection and oil dissolved gas as the main protection of the transformer.

[0004] However, due to the influence of factors such as insulating oil and inter-turn short-circuit fault position, the action time of the gas protection is prone to cause the problem of untimely reaction, resulting in internal failure of the transformer; the differential protection can basically only react to inter-turn short-circuit of more than 3% turns, and the action sensitivity is low, thereby causing internal failure of the transformer; the oil dissolved gas determines the abnormality of the transformer by the change of the gas and the composition of the gas when the fault occurs, which leads to the failure to accurately position the inter-turn short-circuit fault position. Therefore, there is an urgent need for a transformer inter-turn short-circuit fault position positioning method to solve the above problems. SUMMARY

[0005] Therefore, the present application provides a transformer inter-turn short-circuit fault position positioning method and device, medium and terminal, mainly aiming at the problem of internal failure of the transformer caused by untimely reaction, low action sensitivity and failure to accurately position the inter-turn short-circuit fault position.

[0006] According to one aspect of the present application, a transformer inter-turn short-circuit fault position positioning method is provided, comprising:

[0007] When it is detected that the target transformer has an inter-turn short-circuit fault, micro-thermal field simulation data of the target transformer is obtained, the micro-thermal field simulation data being obtained based on a micro-thermal field digital twin model of the target transformer, the micro-thermal field digital twin model being obtained by correcting real signals collected by sensors arranged in the micro-thermal field of the target transformer based on a multi-field coupling simulation model of the target transformer;

[0008] Based on a convolutional neural network, an inter-turn short-circuit fault characteristic parameter is extracted from the micro-thermal field simulation data;

[0009] According to the inter-turn short circuit fault characteristic parameter, a position of the inter-turn short circuit fault of the target transformer is determined based on a Bayesian inference method.

[0010] Preferably, before the micro-temperature field simulation data of the target transformer is acquired when it is detected that the target transformer has an inter-turn short circuit fault, the method further comprises:

[0011] Based on an electromagnetic field differential equation and a natural convection heat transfer mathematical model, a thermal field and flow field coupling model is constructed, and the electromagnetic field differential equation is expressed as the following formula

[0012]

[0013] Wherein, represents a vector differential operator, H represents a magnetic field intensity, J represents a current density, D represents an electric displacement vector, t represents time, B represents a magnetic induction intensity, E represents an electric field intensity, and p represents a charge density,

[0014] The natural convection heat transfer mathematical model is expressed as the following formula

[0015] q = h (T b -T o )

[0016] Wherein, q represents a heat flow density, h represents a convection heat transfer coefficient, T b represents a temperature of the transformer oil tank, T o represents an air temperature;

[0017] Based on a core and winding loss formula, a loss value is calculated, and the core and winding loss formula is expressed as the following formula

[0018]

[0019] Wherein, P 总 represents the loss value, P fe0 represents a core loss per unit volume before winding short circuit, B represents a maximum magnetic flux density in the core before winding short circuit, B0 represents a maximum magnetic flux density in the core after winding short circuit, P wN represents a loss per unit volume of the winding under rated current, I b represents a winding current of the inter-turn short circuit, I N represents a winding rated current of the inter-turn short circuit, I sh represents an equivalent fault resistance current of the inter-turn short circuit, R sh represents an equivalent fault resistance value of the inter-turn short circuit, n represents a proportion of the inter-turn short circuit, and V represents a volume of the fault winding.

[0020] The loss value and a preset inlet flow rate value in the flow field are input into the thermal field and flow field coupling model to obtain a multi-field coupling simulation model for the target transformer.

[0021] Preferably, after the multi-field coupling simulation model for the target transformer is obtained, the method further comprises:

[0022] Real signals collected by each sensor arranged in the micro-thermal field of the target transformer are acquired in real time;

[0023] Parameters of the multi-field coupling simulation model are corrected using the real signals until a preset accuracy threshold is met, so as to obtain a micro-thermal field digital twin model of the target transformer.

[0024] Preferably, the position of the turn-to-turn short circuit fault of the target transformer is determined based on a Bayesian inference method according to the turn-to-turn short circuit fault characteristic quantity, and the method comprises:

[0025] A total probability value of observing the turn-to-turn short circuit fault characteristic is calculated according to the turn-to-turn short circuit fault characteristic quantity based on a total probability calculation formula, and the total probability calculation formula is expressed as the following formula

[0026]

[0027] wherein, Y n represents the turn-to-turn short circuit fault characteristic quantity, P(Y n ) represents the total probability value of observing the turn-to-turn short circuit fault characteristic, represents the frequency of occurrence of the characteristic corresponding to the turn-to-turn short circuit fault, X m represents that the turn-to-turn short circuit fault occurs in the m region, and m represents A, B and C three regions, represents the total frequency of the turn-to-turn short circuit fault in A, B and C three regions;

[0028] The probability value of observing the turn-to-turn short circuit fault characteristic under the condition that the turn-to-turn short circuit fault occurs in each region is calculated based on the following formula,

[0029]

[0030] wherein, P(Y n |X m ) represents the probability value of observing the turn-to-turn short circuit fault characteristic under the condition that the turn-to-turn short circuit fault occurs in the m region, represents the probability value of the turn-to-turn short circuit fault occurring in A, B and C three regions respectively;

[0031] The probability value of the inter-turn short circuit fault occurring in each region under the condition of observing the inter-turn short circuit fault feature is calculated based on a Bayesian fault location formula according to the total probability value of observing the inter-turn short circuit fault feature and the probability value of observing the inter-turn short circuit fault feature under the condition of the inter-turn short circuit fault occurring in each region, and the Bayesian fault location formula is expressed as the following formula

[0032]

[0033] wherein, P(X m |Y n ) represents the probability value of the inter-turn short circuit fault occurring in the m region under the condition of observing the inter-turn short circuit fault feature, and P(X m ) represents a preset prior probability value of the inter-turn short circuit fault occurring in the m region;

[0034] The region corresponding to the maximum probability value is selected from the probability values of the inter-turn short circuit faults, and the region is determined as the position of the inter-turn short circuit fault of the target transformer.

[0035] Preferably, the micro-temperature field simulation data includes time sequence parameter data and image parameter data, and the inter-turn short circuit fault feature parameters are extracted from the micro-temperature field simulation data based on the convolutional neural network, including:

[0036] The time sequence parameter data is arranged based on a preset matrix rule to obtain a time sequence parameter matrix conforming to the preset matrix rule;

[0037] The time sequence parameter matrix is formally converted to make the time sequence parameter matrix and the data image have the same representation form;

[0038] The first inter-turn short circuit fault feature parameters corresponding to the time sequence parameters are extracted from the formally converted time sequence parameters based on a first convolutional neural network;

[0039] The second inter-turn short circuit fault feature parameters corresponding to the image parameters are extracted from the image parameter data based on a second convolutional neural network;

[0040] The first inter-turn short circuit fault feature parameters and the second inter-turn short circuit fault feature parameters are fused based on a preset weight ratio to obtain the inter-turn short circuit fault feature parameters of the micro-temperature field simulation data.

[0041] Preferably, when the target transformer is detected to have an inter-turn short circuit fault, the micro-temperature field simulation data of the target transformer is obtained, including:

[0042] When it is detected that the target transformer has a turn-to-turn short circuit fault, a target sensor group is screened out from the target transformer micro-temperature field according to the comprehensive score coefficient of each sensor arranged in the target transformer micro-temperature field, the comprehensive score coefficient being obtained by fusing the sensor temperature and hot spot temperature correlation basic weight vector, the sensor data reliability basic weight vector and the symmetry basic weight vector between sensor signals of each sensor to obtain a comprehensive score vector, and being obtained based on a game weighting algorithm;

[0043] Micro-temperature field simulation data corresponding to each sensor in the target sensor group is acquired as micro-temperature field simulation data of the target transformer for turn-to-turn short circuit fault location.

[0044] Preferably, when it is detected that the target transformer has a turn-to-turn short circuit fault, a target sensor group is screened out from the target transformer micro-temperature field according to the comprehensive score coefficient of each sensor arranged in the target transformer micro-temperature field, the comprehensive score coefficient being obtained by fusing the sensor temperature and hot spot temperature correlation basic weight vector, the sensor data reliability basic weight vector and the symmetry basic weight vector between sensor signals of each sensor to obtain a comprehensive score vector, and being obtained based on a game weighting algorithm;

[0045] When it is detected that the target transformer has a turn-to-turn short circuit fault, a target sensor group is screened out from the target transformer micro-temperature field according to the comprehensive score coefficient of each sensor arranged in the target transformer micro-temperature field, the comprehensive score coefficient being obtained by fusing the sensor temperature and hot spot temperature correlation basic weight vector, the sensor data reliability basic weight vector and the symmetry basic weight vector between sensor signals of each sensor to obtain a comprehensive score vector, and being obtained based on a game weighting algorithm;

[0046]

[0047] Wherein, r represents the sensor temperature and hot spot temperature correlation vector, M represents the number of sensors, x j represents the hot spot temperature in the jth sensor, represents the average value of the hot spot temperature in the sensor, y j represents the temperature of the jth sensor, represents the average value of the sensor temperature;

[0048] The sensor data reliability basic weight vector is determined based on the signal variance of each sensor;

[0049] The symmetry index between each pair of sensor signals is calculated based on a symmetry index calculation formula to generate a symmetry basic weight vector between sensor signals, the symmetry index calculation formula being represented by the following formula

[0050] DS=R*ρ

[0051] Wherein, DS represents the symmetry index between each pair of sensor signals, R represents a distance coefficient, R=-ln(|r1-r2|), r1 and r2 respectively represent the root mean square values of the two sensors at the current monitoring point, and ρ represents the Spearman correlation coefficient;

[0052] fuse the basic weight vector of sensor temperature and hot spot temperature correlation, the basic weight vector of sensor data reliability, and the basic weight vector of symmetry between sensor signals to obtain a comprehensive score vector

[0053]

[0054] wherein W represents the comprehensive score vector, λ α represents a weight coefficient, α = 1 represents the basic weight vector of sensor temperature and hot spot temperature correlation, α = 2 represents the basic weight vector of sensor data reliability, α = 3 represents the basic weight vector of symmetry between sensor signals, and T represents a combination coefficient;

[0055] The weight coefficient is optimized based on a game weighting algorithm, so that the deviation between the comprehensive score vector and the basic weight vector of sensor temperature and hot spot temperature correlation, the basic weight vector of sensor data reliability, and the basic weight vector of symmetry between sensor signals is minimized, to obtain an optimal weight coefficient;

[0056] The optimal weight coefficient is normalized to obtain a comprehensive score coefficient of each sensor;

[0057] Based on a preset rule, a target sensor group is selected according to the comprehensive score coefficient of each sensor, so that the inter-turn short circuit fault position is positioned according to the micro-thermal field simulation data corresponding to each sensor in the target sensor group.

[0058] According to another aspect of the present application, a device for positioning the position of a transformer inter-turn short circuit fault is provided, comprising:

[0059] A micro-thermal field simulation data acquisition module is configured to acquire micro-thermal field simulation data of a target transformer when it is detected that the target transformer has an inter-turn short circuit fault, wherein the micro-thermal field simulation data is obtained based on a micro-thermal field digital twin model of the target transformer, and the micro-thermal field digital twin model is obtained by correcting a multi-field coupling simulation model of the target transformer using real signals collected by sensors arranged in the micro-thermal field of the target transformer;

[0060] An inter-turn short circuit fault characteristic parameter extraction module is configured to extract an inter-turn short circuit fault characteristic parameter from the micro-thermal field simulation data based on a convolutional neural network;

[0061] An inter-turn short circuit fault position positioning module is configured to determine the position of the inter-turn short circuit fault of the target transformer based on a Bayesian inference method according to the inter-turn short circuit fault characteristic parameter.

[0062] Preferably, before the micro-temperature field simulation data acquisition module, the device further comprises a micro-temperature field digital twin model construction module, which is used for:

[0063] Based on the electromagnetic field differential equation and the natural convection heat transfer mathematical model, a thermal field and flow field coupling model is constructed, and the electromagnetic field differential equation is expressed as the following formula

[0064]

[0065] Among them, The vector differential operator is represented by, H represents the magnetic field intensity, J represents the current density, D represents the electric displacement vector, t represents the time, B represents the magnetic induction intensity, E represents the electric field intensity, and p represents the charge density,

[0066] The natural convection heat transfer mathematical model is expressed as the following formula

[0067] q=h(T b -T o )

[0068] Among them, q represents the heat flow density, h represents the convection heat transfer coefficient, T b represents the temperature of the transformer oil tank, and T o represents the air temperature;

[0069] Based on the core and winding loss formula, the loss value is calculated, and the core and winding loss formula is expressed as the following formula

[0070]

[0071] Among them, P 总 represents the loss value, P fe0 represents the core loss per unit volume before winding short circuit, B represents the maximum magnetic flux density in the core before winding short circuit, B0 represents the maximum magnetic flux density in the core after winding short circuit, P wN represents the loss per unit volume of winding under rated current, I b represents the winding current of inter-turn short circuit, I N represents the rated current of the winding of inter-turn short circuit, I sh represents the equivalent fault resistance current of inter-turn short circuit, R sh represents the equivalent fault resistance value of inter-turn short circuit, n represents the proportion of inter-turn short circuit, and V represents the volume of the fault winding.

[0072] The loss value and the preset inlet flow rate value in the flow field are input into the thermal field and flow field coupling model to obtain a multi-field coupling simulation model for the target transformer.

[0073] Preferably, the micro-temperature field digital twin model construction module is further used for:

[0074] real signals collected by each sensor arranged in the micro-thermal field of the target transformer are acquired in real time;

[0075] parameters of the multi-field coupling simulation model are corrected using the real signals until a preset accuracy threshold is met, to obtain a micro-thermal field digital twin model of the target transformer.

[0076] Preferably, the turn-to-turn short-circuit fault position positioning module is configured to:

[0077] Based on a total probability calculation formula, a total probability value of observing the turn-to-turn short-circuit fault feature is calculated according to the turn-to-turn short-circuit fault feature quantity, and the total probability calculation formula is expressed as the following formula

[0078]

[0079] wherein Y n represents the turn-to-turn short-circuit fault feature quantity, P(Y n ) represents the total probability value of observing the turn-to-turn short-circuit fault feature, represents the frequency of occurrence of the feature corresponding to the turn-to-turn short-circuit fault, X m represents that the turn-to-turn short-circuit fault occurs in the m region, and m represents the A, B and C regions, represents the total frequency of the turn-to-turn short-circuit fault in the A, B and C regions;

[0080] Based on the following formula, the probability value of observing the turn-to-turn short-circuit fault feature under the condition that the turn-to-turn short-circuit fault occurs in each region is calculated,

[0081]

[0082] wherein P(Y n |X m ) represents the probability value of observing the turn-to-turn short-circuit fault feature under the condition that the turn-to-turn short-circuit fault occurs in the m region, represents the probability value of the turn-to-turn short-circuit fault occurring in the A, B and C regions, respectively;

[0083] Based on a Bayesian fault positioning formula, the probability value of the turn-to-turn short-circuit fault occurring in each region under the condition of observing the turn-to-turn short-circuit fault feature is calculated according to the total probability value of observing the turn-to-turn short-circuit fault feature and the probability value of observing the turn-to-turn short-circuit fault feature under the condition that the turn-to-turn short-circuit fault occurs in each region, and the Bayesian fault positioning formula is expressed as the following formula

[0084]

[0085] wherein P(X m |Y n) represents a probability value of the m region occurring the inter-turn short circuit fault under the condition of observing the inter-turn short circuit fault feature, P(X m ) represents a preset prior probability value of the m region occurring the inter-turn short circuit fault;

[0086] The region corresponding to the maximum probability value is filtered out from each of the probability values of the inter-turn short circuit fault, and the region is determined as the position of the inter-turn short circuit fault of the target transformer.

[0087] Preferably, the micro-temperature field simulation data includes time sequence parameter data and image parameter data, and the inter-turn short circuit fault feature parameter extraction module is configured to:

[0088] The time sequence parameter data is arranged based on a preset matrix rule to obtain a time sequence parameter matrix conforming to the preset matrix rule;

[0089] The time sequence parameter matrix is formally converted to make the time sequence parameter matrix and the data image have the same representation form;

[0090] The first inter-turn short circuit fault feature parameter corresponding to the time sequence parameter is extracted from the formally converted time sequence parameter based on a first convolutional neural network;

[0091] The second inter-turn short circuit fault feature parameter corresponding to the image parameter is extracted from the image parameter data based on a second convolutional neural network;

[0092] The first inter-turn short circuit fault feature parameter and the second inter-turn short circuit fault feature parameter are fused based on a preset weight ratio to obtain the inter-turn short circuit fault feature parameter of the micro-temperature field simulation data.

[0093] Preferably, the micro-temperature field simulation data acquisition module comprises:

[0094] A target sensor group screening unit is configured to, when detecting that the target transformer has an inter-turn short circuit fault, screen a target sensor group from each sensor arranged in a micro-temperature field of the target transformer according to a comprehensive score coefficient of each sensor, the comprehensive score coefficient being obtained by fusing a sensor temperature and a hotspot temperature correlation basic weight vector, a sensor data reliability basic weight vector, and a sensor signal symmetry basic weight vector of each sensor to obtain a comprehensive score vector, and being obtained by weight distribution based on a game weighting algorithm;

[0095] A micro-temperature field simulation data acquisition unit is configured to acquire micro-temperature field simulation data corresponding to each sensor in the target sensor group as micro-temperature field simulation data of the target transformer for inter-turn short circuit fault position positioning.

[0096] Preferably, the target sensor group screening unit is used for:

[0097] When it is detected that the target transformer has a turn-to-turn short circuit fault, a sensor temperature and hot spot temperature correlation basic weight vector is calculated based on a Pearson correlation coefficient formula, which is expressed as the following formula

[0098]

[0099] Wherein, r represents a sensor temperature and hot spot temperature correlation vector, M represents the number of sensors, x j represents the hot spot temperature in the jth sensor, x represents the average value of the hot spot temperature in the sensor, y j represents the temperature of the jth sensor, y represents the average value of the sensor temperature;

[0100] A sensor data reliability basic weight vector is determined based on the signal variance of each sensor;

[0101] A symmetry index between each pair of sensor signals is calculated based on a symmetry index calculation formula to generate a symmetry basic weight vector between sensor signals, which is expressed as the following formula

[0102] DS = R * p

[0103] Wherein, DS represents the symmetry index between each pair of sensor signals, R represents a distance coefficient, R = -ln(|r1-r2|), r1 and r2 respectively represent the root mean square values of the two sensors at the current monitoring point, and p represents the Spearman correlation coefficient;

[0104] The sensor temperature and hot spot temperature correlation basic weight vector, the sensor data reliability basic weight vector, and the symmetry basic weight vector between sensor signals are fused to obtain a comprehensive score vector

[0105]

[0106] Wherein, W represents the comprehensive score vector, and l α represents a weight coefficient, a = 1 represents the sensor temperature and hot spot temperature correlation basic weight vector, a = 2 represents the sensor data reliability basic weight vector, a = 3 represents the symmetry basic weight vector between sensor signals, and T represents a combination coefficient;

[0107] The weight coefficient is optimized based on a game weighting algorithm, so that the deviation between the comprehensive score vector and the sensor temperature and hot spot temperature correlation basic weight vector, the sensor data reliability basic weight vector, and the symmetry basic weight vector between sensor signals is minimized, to obtain an optimal weight coefficient.

[0108] normalizing the optimal weight coefficient to obtain a comprehensive score coefficient of each sensor;

[0109] According to a preset rule, a target sensor group is selected according to the comprehensive score coefficient of each sensor, so as to locate the turn-to-turn short circuit fault position according to the micro-temperature field simulation data corresponding to each sensor in the target sensor group.

[0110] According to another aspect of the present application, a storage medium is provided, and at least one executable instruction is stored in the storage medium, which causes the processor to perform the operations corresponding to the above-mentioned transformer turn-to-turn short circuit fault position locating method.

[0111] According to still another aspect of the present application, a terminal is provided, which comprises a processor, a memory, a communication interface and a communication bus, and the processor, the memory and the communication interface complete communication with each other through the communication bus.

[0112] The memory is used to store at least one executable instruction, and the executable instruction causes the processor to perform the operations corresponding to the above-mentioned transformer turn-to-turn short circuit fault position locating method.

[0113] Through the above technical solutions, the technical solutions provided by the embodiments of the present application have at least the following advantages:

[0114] The application provides a transformer inter-turn short circuit fault position positioning method and device, medium and terminal. First, when a target transformer is detected to have an inter-turn short circuit fault, micro-temperature field simulation data of the target transformer is acquired, the micro-temperature field simulation data is obtained based on a micro-temperature field digital twin model of the target transformer, and the micro-temperature field digital twin model is obtained by correcting real signals collected by sensors arranged in the micro-temperature field of the target transformer based on a multi-field coupling simulation model of the target transformer. Second, inter-turn short circuit fault characteristic parameters are extracted from the micro-temperature field simulation data based on a convolutional neural network. Finally, the position of the inter-turn short circuit fault of the target transformer is determined based on a Bayesian inference method according to the inter-turn short circuit fault characteristic parameters. Compared with the prior art, the micro-temperature field digital twin model is obtained by correcting real signals collected by sensors arranged in the micro-temperature field of the target transformer based on a multi-field coupling simulation model of the target transformer, so that the simulation data obtained based on the micro-temperature field digital twin model is highly similar to the actual operation of the target transformer. On this basis, the simulation data is used to position in advance before the fault occurs, thereby avoiding the problem of internal failure of the transformer caused by untimely reaction. Further, the inter-turn short circuit fault characteristic parameters are extracted from the micro-temperature field simulation data based on the convolutional neural network, the problem of being unable to discover the fault characteristics in time due to slow temperature change is overcome by using the high sensitivity of the convolutional neural network, the recognition sensitivity to the fault characteristics is improved, and the action sensitivity is further improved. Finally, the accurate position of the inter-turn short circuit fault is determined according to the inter-turn short circuit fault characteristic parameters by using the Bayesian inference method, and the defect that the inter-turn short circuit fault position cannot be accurately positioned in the prior art is overcome.

[0115] The above description is only a summary of the technical scheme of the application. In order to enable the technical means of the application to be more clearly understood, the application can be implemented according to the content of the specification, and in order to enable the above and other purposes, characteristics and advantages of the application to be more obvious and easy to understand, the following specific embodiments of the application are described. BRIEF DESCRIPTION OF DRAWINGS

[0116] Various other advantages and benefits will become apparent to those of ordinary skill in the art upon reading the following detailed description of the preferred embodiments. The accompanying drawings are included to provide a description of the preferred embodiments and are not meant to limit the present application. Moreover, the same reference numerals in the attached drawings indicate the same or similar components. In the drawings:

[0117] Figure 1 A flowchart of a transformer inter-turn short circuit fault position positioning method provided by an embodiment of the application is shown;

[0118] Figure 2A flow chart of a method for positioning a transformer turn-to-turn short circuit fault position is shown;

[0119] Figure 3 A schematic diagram of a transformer micro-temperature field heat dissipation process is shown;

[0120] Figure 4 An equivalent circuit diagram of a transformer is shown;

[0121] Figure 5 A mesh division schematic diagram is shown;

[0122] Figure 6 A comparison curve diagram of test measurement results and simulation results of winding temperature in a normal state is shown;

[0123] Figure 7 A comparison curve diagram of test measurement results and simulation results of winding temperature in a fault state is shown;

[0124] Figure 8 A block diagram of a positioning device for a transformer turn-to-turn short circuit fault position is shown;

[0125] Figure 9 A structure schematic diagram of a terminal is shown. DETAILED DESCRIPTION

[0126] Exemplary embodiments of the present disclosure will be described hereinafter with reference to the accompanying drawings. While exemplary embodiments of the present disclosure are shown in the drawings, it is understood that the present disclosure can be implemented in various forms and should not be limited by the embodiments set forth herein. Rather, these embodiments are provided so that this disclosure will be thorough and complete, and will fully convey the scope of the present disclosure to those skilled in the art.

[0127] It should be understood that the actual dimensions of the various parts shown in the drawings can not be to scale.

[0128] The following description of at least one exemplary embodiment is merely illustrative in nature and is in no way intended to limit the application or its application or uses.

[0129] Techniques, methods, and devices known to those of ordinary skill in the relevant art can not be discussed in detail herein, but should be considered part of the specification.

[0130] It should be noted that like reference numerals and characters refer to like items throughout the attached drawings and alternative embodiments thereof. Note, therefore, that no further discussion on the construction and operation of an item, once discussed in great detail, is required in connection with the same item appearing in a subsequent drawing.

[0131] Embodiments of the present application can be applied to a computer system / server, which can operate in connection with many other general purpose or special purpose computer system environments or configurations. Examples of well-known computing systems, environments, and / or configurations that can be suitable for use with computer system / server include, but are not limited to, personal computer systems, server computer systems, thin clients, thick clients, handheld or laptop devices, microprocessor-based systems, set-top boxes, programmable consumer electronics, network personal computers, minicomputers, mainframe computers, and distributed cloud computing environments that include any of the above systems or the like.

[0132] The computer system / server can be described in the general context of computer system-executable instructions, such as program modules, being executed by a computer system. Generally, program modules can include routines, programs, objects, components, logic, data structures, and the like, that perform particular tasks or implement particular abstract data types. Computer system / server can operate in a distributed cloud computing environment where tasks are performed by remote processing devices that are linked through a communications network. In a distributed cloud computing environment, program modules can be located in local or remote computer system storage media including memory storage devices.

[0133] Embodiments of the present application provide a method for positioning a transformer turn-to-turn short circuit fault position, as shown in Figure 1 The method comprises the following steps:

[0134] 101. When detecting that a target transformer has a turn-to-turn short circuit fault, micro-temperature field simulation data of the target transformer is acquired.

[0135] The micro-temperature field simulation data is obtained based on a micro-temperature field digital twin model of the target transformer. The micro-temperature field digital twin model is obtained by correcting a multi-field coupling simulation model of the target transformer based on real signals collected by sensors arranged in the micro-temperature field of the target transformer. It should be noted that the micro-temperature field simulation data is not limited by the position of the sensors and can obtain data at any position, thereby improving the accuracy of fault location based on simulation data. Further, in the embodiment of the present application, the micro-temperature field digital twin model is obtained by correcting the multi-field coupling simulation model of the target transformer based on real signals collected by sensors arranged in the micro-temperature field of the target transformer, so that the simulation data obtained based on the micro-temperature field digital twin model is highly similar to the actual operation of the target transformer. On this basis, the simulation data is used to locate the fault in advance before the fault occurs, thereby avoiding the problem of internal failure of the transformer due to delayed reaction. In the embodiment of the present application, the current execution end can be a turn-to-turn short circuit fault detection module in a transformer fault detection system, which can be used to locate the position of a turn-to-turn short circuit fault.

[0136] 102. Extracting a turn-to-turn short circuit fault feature parameter from the micro-temperature field simulation data based on a convolutional neural network.

[0137] Since temperature change is a slow process, it is easily ignored, making it difficult to discover fault features in a timely manner. To overcome this problem, in the embodiment of the present application, the recognition sensitivity to fault features is improved by using the high sensitivity of the convolutional neural network, thereby improving the sensitivity of the action.

[0138] 103. Determining the position of the turn-to-turn short circuit fault of the target transformer based on a Bayesian inference method according to the turn-to-turn short circuit fault feature parameter.

[0139] The Bayesian inference method is a statistical method based on probability density to describe the mapping relationship between the feature parameter and the fault, and constantly adjusts the final fact according to new information. In the embodiment of the present application, the turn-to-turn short circuit fault feature parameter extracted from the micro-temperature field simulation data is used as new information required by the Bayesian inference method to participate in iteration, thereby determining the accurate position of the turn-to-turn short circuit fault, overcoming the defect that the existing method cannot accurately locate the position of the turn-to-turn short circuit fault.

[0140] Compared with the prior art, the embodiment of the application corrects the real signals collected by the sensors arranged in the micro-temperature field of the target transformer based on the multi-field coupling simulation model of the target transformer to obtain a micro-temperature field digital twin model, so that the simulation data obtained based on the micro-temperature field digital twin model is highly similar to the real operation of the target transformer, and the simulation data is used to locate the fault in advance before the fault occurs, thereby avoiding the problem of internal failure of the transformer caused by untimely reaction. Further, based on the convolutional neural network, the turn-to-turn short-circuit fault characteristic parameters are extracted from the micro-temperature field simulation data, the high sensitivity of the convolutional neural network is used to overcome the problem that the fault characteristics cannot be found in time due to slow temperature changes, the recognition sensitivity to the fault characteristics is improved, and the action sensitivity is further improved. Finally, the accurate position of the turn-to-turn short-circuit fault is determined according to the turn-to-turn short-circuit fault characteristic parameters by using the Bayesian inference method, thereby overcoming the defect that the position of the turn-to-turn short-circuit fault cannot be accurately located in the prior art.

[0141] The embodiment of the application provides another method for positioning the position of a transformer turn-to-turn short-circuit fault, as shown in Figure 2 The method comprises the following steps.

[0142] 201. Construct a micro-temperature field digital twin model of a target transformer.

[0143] In the embodiment of the application, first, a multi-field coupling simulation model of the target transformer is constructed. The temperature distribution inside the transformer involves multi-physical field coupling, among which the electromagnetic field is taken as the basis of the micro-temperature field. After the transformer is operated, heat is generated due to the loss of the core and winding, which causes the oil temperature to rise, generates a heat transfer process, and the heat dissipation process of the micro-temperature field of the transformer, as shown in Figure 3 When the temperature rises, the oil around the core and winding flows upwards, and the temperature of the upper surface is lower and flows downwards, forming natural convection of the oil. When the heated oil flows to the heat sink, the temperature is transferred to the heat sink, and the heat sink relies on natural convection and heat radiation to transfer to the external air, thereby realizing the heat dissipation of the transformer. Therefore, the heat exchange mode between the transformer oil tank and the air mainly considers the natural convection heat transfer mode in the heat convection. Based on this, specifically, a thermal field and flow field coupling model is constructed based on the electromagnetic field differential equation and the natural convection heat transfer mathematical model. The electromagnetic field differential equation is expressed as the following formula

[0144]

[0145] Among them, represents a vector differential operator, H represents the magnetic field intensity, J represents the current density, D represents the electric displacement vector, t represents time, B represents the magnetic induction intensity, E represents the electric field intensity, and p represents the charge density.

[0146] The mathematical model of natural convection heat transfer is expressed as the following formula

[0147] q = h (T b -T o )

[0148] Wherein, q represents the heat flow density, h represents the convection heat transfer coefficient, T b represents the temperature of the transformer oil tank, T o represents the air temperature;

[0149] The loss value is calculated based on the core and winding loss formula, and the core and winding loss formula is expressed as the following formula

[0150]

[0151] Wherein, P 总 represents the loss value, P fe0 represents the core loss per unit volume before winding short circuit, B represents the maximum magnetic flux density in the core before winding short circuit, B0 represents the maximum magnetic flux density in the core after winding short circuit, P wN represents the loss per unit volume of winding under rated current, I b represents the winding current of inter-turn short circuit, I N represents the rated current of inter-turn short circuit winding, I sh represents the equivalent fault resistance current of inter-turn short circuit, R sh represents the equivalent fault resistance value of inter-turn short circuit, n represents the proportion of inter-turn short circuit, and V represents the volume of the fault winding.

[0152] The loss value and the preset inlet flow rate value (such as 0.02 m / s) in the flow field are input into the thermal field and flow field coupling model to obtain a multi-field coupling simulation model for the target transformer.

[0153] Optionally, when constructing the multi-field coupling simulation model, the coupling of the thermal field and the flow field can be realized through the solid heat transfer module and the laminar flow module in the numerical simulation software COMSOL.

[0154] Further, the multi-field coupling simulation model is corrected through actual data to achieve digital twinning and realize real and consistent reflection of the change of the micro-temperature field. Specifically, real signals collected by each sensor arranged in the micro-temperature field of the target transformer are acquired in real time; the parameters of the multi-field coupling simulation model are corrected using the real signals until a preset precision threshold is met, so as to obtain a micro-temperature field digital twinning model of the target transformer.

[0155] Optionally, when the multi-field coupling simulation model is corrected by actual data, the coupling relationship between the transformer internal multi-physical field and the transformer structure can be used to effectively analyze and calculate the unknown parameters in the micro-temperature field digital twin model, so as to realize the dynamic tracking of the real equipment. The following formula can be used to realize it,

[0156]

[0157] Wherein, m(t) represents the current system state, u(t) represents the input data, n(t) represents the output data, F represents the state function, and H represents the output function. Further, the above model can be dual simplified to an equivalent system

[0158]

[0159] However, the pole number of the dual simplified system is much smaller than that of the original system, so after evaluating the dual simplified system, the grid division of the two models is realized through the micro-service unit, so as to realize the dynamic update of the micro-thermal field.

[0160] In a specific application scenario, when there is an inter-turn short circuit, according to the circuit principle, the equivalent circuit can be regarded as two windings in series, as shown in Figure 4 .

[0161] 202、Based on the micro-temperature field digital twin model, the micro-temperature field simulation temperature distribution data of the target transformer is obtained.

[0162] It can be understood that any period of simulation data at any position can be selected from the micro-temperature field simulation temperature distribution data.

[0163] 203、When detecting that the target transformer has an inter-turn short circuit fault, according to the comprehensive score coefficient of each sensor arranged in the micro-temperature field of the target transformer, the target sensor group is screened out.

[0164] Wherein, the comprehensive score coefficient is obtained by fusing the sensor temperature and the hot spot temperature correlation basic weight vector, the sensor data reliability basic weight vector, and the symmetry basic weight vector between the sensor signals to obtain a comprehensive score vector, and then performing weight distribution based on a game weighting algorithm.

[0165] Since the number of sensors is huge, if fault positioning is performed based on the collected data of all sensors, it is easy to cause the problem of slowing down the positioning efficiency due to the need to process massive data. Based on this, in the embodiments of the present application, valuable target sensor groups are pre-selected. It should be noted that since the position of the inter-turn short circuit is random, each sensor must reflect the fault characteristics, but due to the difference in fault position and degree, the importance of each sensor in reflecting the fault characteristics is not the same. The valuable sensors can be selected according to the contribution degree of the micro-temperature field analysis to capture the hotspot temperature and perform fault position positioning. In the embodiments of the present application, the comprehensive score coefficient is used as an evaluation index to select the sensors. Specifically, when it is detected that the target transformer has an inter-turn short circuit fault, the basic weight vector of the correlation between the sensor temperature and the hotspot temperature is calculated based on the Pearson correlation coefficient formula, and the Pearson correlation coefficient formula is expressed as the following formula

[0166]

[0167] Wherein, r represents the correlation vector between the sensor temperature and the hotspot temperature, M represents the number of sensors, x j represents the hotspot temperature in the jth sensor, represents the average value of the hotspot temperature in the sensor, y j represents the temperature of the jth sensor, represents the average value of the sensor temperature;

[0168] Based on the signal variance of each sensor, the basic weight vector of the sensor data reliability is determined, which can be expressed as V r = [V r1 , V r2 ,..., V rj ], wherein V r represents the basic weight vector of the sensor data reliability, and V rj represents the signal variance of the jth sensor.

[0169] Based on the symmetry index calculation formula, the symmetry index between each pair of sensor signals is calculated to generate the basic weight vector of the symmetry between the sensor signals, and the symmetry index calculation formula is expressed as the following formula

[0170] DS = R * p

[0171] Wherein, DS represents the symmetry index between each pair of sensor signals, R represents the distance coefficient, R = -ln(r1-r2), r1 and r2 respectively represent the root mean square values of the two sensors at the current monitoring point, and p represents the Spearman correlation coefficient.

[0172] The basic weight vector of the symmetry between the sensor signals can be expressed as the following formula

[0173]

[0174] wherein, d q represents a symmetry basic weight vector between sensor signals, d ij represents a symmetry index between the i th sensor and the j th sensor;

[0175] The sensor temperature and hot spot temperature correlation basic weight vector, the sensor data reliability basic weight vector, and the symmetry basic weight vector between sensor signals are fused to obtain a comprehensive score vector

[0176]

[0177] wherein, W represents the comprehensive score vector, λ α represents a weight coefficient, α = 1 represents the sensor temperature and hot spot temperature correlation basic weight vector, α = 2 represents the sensor data reliability basic weight vector, α = 3 represents the symmetry basic weight vector between sensor signals, and T represents a combination coefficient;

[0178] The weight coefficient is optimized based on a game weighting algorithm, so that the deviations between the comprehensive score vector and the sensor temperature and hot spot temperature correlation basic weight vector, the sensor data reliability basic weight vector, and the symmetry basic weight vector between sensor signals are all minimum values, to obtain an optimal weight coefficient. Preferably, the weight coefficient can be optimized by solving a minimum objective function, which can be expressed as the following formula

[0179]

[0180] wherein, y1 represents a minimum objective function between the comprehensive score vector and the sensor temperature and hot spot temperature correlation basic weight vector, y2 represents a minimum objective function between the comprehensive score vector and the sensor data reliability basic weight vector, and y3 represents a minimum objective function between the comprehensive score vector and the symmetry basic weight vector between sensor signals;

[0181] The optimal weight coefficient is normalized to obtain a comprehensive score coefficient of each sensor.

[0182] Based on a preset rule, a target sensor group is selected according to the comprehensive score coefficient of each sensor, so as to locate the inter-turn short circuit fault position according to the micro-thermal field simulation data corresponding to each sensor in the target sensor group. The preset rule can be that the comprehensive score coefficients of the sensors are sequentially sorted, and a preset number of sensors are selected from the first position to form the target sensor group. The preset rule can also be that a comprehensive score coefficient threshold is set, and the sensors exceeding the threshold are combined to form the target sensor group. The embodiments of the present application are not limited in this regard.

[0183] 204、acquire the micro-thermal field simulation data corresponding to each sensor in the target sensor group as the micro-thermal field simulation data of the target transformer to locate the turn-to-turn short-circuit fault position.

[0184] 205、extract the turn-to-turn short-circuit fault characteristic parameters from the micro-thermal field simulation data based on the convolutional neural network.

[0185] The micro-thermal field simulation data includes time sequence parameter data and image parameter data.

[0186] For the time sequence parameter data, first, the time sequence parameter data is arranged based on a preset matrix rule to obtain a time sequence parameter matrix conforming to the preset matrix rule; further, the time sequence parameter matrix is form converted to make the time sequence parameter matrix and the data image have the same representation form; further, the first turn-to-turn short-circuit fault characteristic parameters corresponding to the time sequence parameters are extracted from the form-converted time sequence parameters based on the first convolutional neural network. The time sequence parameter data can include oil temperature, oil speed, oil flow, etc.; the preset matrix rule is, for example, a K*N size matrix, K representing the category of time sequence and N representing the length of time sequence; the first convolutional neural network can adopt a shallow convolutional neural network, which, for example, includes one convolutional layer containing 32 5*5 size convolutional kernels, one nonlinear function Relu, one 2*2 size maximum pooling layer, and one 125 size fully connected layer.

[0187] For the image parameter data, the second turn-to-turn short-circuit fault characteristic parameters corresponding to the image parameters are extracted from the image parameter data based on the second convolutional neural network. The second convolutional neural network can adopt a mature convolutional neural network, such as the Faster R-CNN neural network, which can include two convolutional layers, each containing 64 3*3 size convolutional kernels.

[0188] Finally, the first turn-to-turn short-circuit fault characteristic parameters and the second turn-to-turn short-circuit fault characteristic parameters are fused based on a preset weight ratio to obtain the turn-to-turn short-circuit fault characteristic parameters of the micro-thermal field simulation data.

[0189] For example, the weight ratio of the first turn-to-turn short-circuit fault characteristic parameters is W1, the weight ratio of the second turn-to-turn short-circuit fault characteristic parameters is W2, the first turn-to-turn short-circuit fault characteristic parameters are a 1*125 feature matrix, and the second turn-to-turn short-circuit fault characteristic parameters are a 1*4096 feature matrix. Coupling the two according to their respective weight ratios can obtain a 1*4221 fusion feature matrix, which can be input into a 1*4096 fully connected layer to obtain a 1*4096 fusion feature matrix, i.e., the turn-to-turn short-circuit fault characteristic parameters of the micro-thermal field simulation data.

[0190] Preferably, W1 and W2 can be regarded as trainable parameters, and trained using cross-entropy loss or mean square error minimization objective, so as to reduce the influence of human factors and improve the objectivity of the inter-turn short circuit fault feature quantity.

[0191] 206、According to the inter-turn short circuit fault feature quantity, the position of the inter-turn short circuit fault of the target transformer is determined based on a Bayesian inference method.

[0192] Specifically, based on a total probability calculation formula, the total probability value of observing the inter-turn short circuit fault feature is calculated according to the inter-turn short circuit fault feature quantity, and the total probability calculation formula is expressed as the following formula

[0193]

[0194] Y = {Y1, Y2, Y3} represents the inter-turn short circuit fault feature quantity, P(Y n ) represents the total probability value of observing the inter-turn short circuit fault feature, n Xm represents the frequency of occurrence of the feature corresponding to the inter-turn short circuit fault, Xm represents that the inter-turn short circuit fault occurs in the m region, and m represents A, B, and C three regions. m represents the total frequency of the inter-turn short circuit fault of the three regions A, B, and C;

[0195] Based on the following formula, the probability value of observing the inter-turn short circuit fault feature under the condition that the inter-turn short circuit fault occurs in each region is calculated,

[0196]

[0197] Y = {Y1, Y2, Y3} represents the inter-turn short circuit fault feature quantity, P(Y n |X m ) represents the probability value of observing the inter-turn short circuit fault feature under the condition that the inter-turn short circuit fault occurs in the m region, represents the probability value of the inter-turn short circuit fault occurring in each of the three regions A, B, and C;

[0198] Based on a Bayesian fault positioning formula, the probability value of the inter-turn short circuit fault occurring in each region under the condition of observing the inter-turn short circuit fault feature is calculated according to the total probability value of observing the inter-turn short circuit fault feature and the probability value of observing the inter-turn short circuit fault feature under the condition that the inter-turn short circuit fault occurs in each region, and the Bayesian fault positioning formula is expressed as the following formula

[0199]

[0200] Y = {Y1, Y2, Y3} represents the inter-turn short circuit fault feature quantity, P(Y m |X n ) represents the probability value of the inter-turn short circuit fault occurring in the m region under the condition of observing the inter-turn short circuit fault feature, and P(X​​m represents a preset prior probability value of the m area occurring a turn-to-turn short circuit fault;

[0201] The area corresponding to the maximum probability value is selected from the probability values of the areas occurring the turn-to-turn short circuit fault, and the area is determined as the position of the target transformer occurring the turn-to-turn short circuit fault.

[0202] In order to verify the positioning accuracy of the positioning method of the transformer turn-to-turn short circuit fault position provided in the embodiments of the present application, a single-phase transformer is taken as an example for simulation and verification. The basic parameters of the transformer are shown in Table 1. In order to facilitate the simulation of the turn-to-turn short circuit model, the turn-to-turn short circuit is set in the primary winding. The winding is a pie structure, and the turn-to-turn short circuit at different positions is simulated.

[0203] Table 1 Transformer parameters

[0204] Among them, the winding and core parameters in the transformer are shown in Table 2. And considering that the oil in the transformer

[0205]

[0206] The density, specific heat capacity and dynamic viscosity and the like will change with temperature.

[0207] Table 2 Physical properties of transformer materials

[0208]

[0209] Since the three-dimensional model is closer to the actual transformer, in the embodiments of the present application, a three-dimensional transformer model is simulated. Considering the fault position and severity when the transformer occurs a turn-to-turn short circuit, in the modeling process, in order to eliminate the large error caused by poor grid quality and ensure the reliability of the results, the primary winding and secondary winding and the oil channel position are refined in the embodiments of the present application until some control parameters do not change. The grid division degree in the embodiments of the present application is as follows: Figure 5The transformer is evenly divided into three zones, and sensors are evenly installed in the three zones to provide prior probability for Bayesian inference of the probability of turn-to-turn short circuit fault in each zone. In order to verify the accuracy and effectiveness of the simulation model, in the embodiment of the present application, the transformer simulates the operating condition of the transformer through temperature rise experiment. For the entire transformer industry, it is very costly to install a large number of optical fiber probes in the transformer to detect the internal temperature of the transformer, and it is not practical to develop and prototype the same scale in the research scenario. Therefore, a reduced size experimental transformer model is designed and manufactured to analyze the heat transfer of the transformer, but this will not affect the experimental results, so as to obtain the conclusion. In terms of temperature measurement, considering the complexity of installing optical fiber sensors along the transformer winding, a group of T22 optical fiber temperature probes are placed in the oil duct between the primary winding and the secondary winding to verify the simulation model, the measurement range is-80℃-250℃, the corresponding time is 250ms, and the comparison between the experimental measurement result of the winding temperature under normal state and the simulation result is as shown in FIG. 6. Figure 6 The comparison between the experimental measurement result of the winding temperature under fault state and the simulation result is as shown in FIG. 7. Figure 7 As shown in FIG. 7, the trend of the simulation calculation temperature of the winding and the experimental measurement temperature of the winding is roughly consistent, and the overall temperature error is less than 3K. The error in the experiment mainly comes from the simplification of the simulation model, so that the simulation result and the experimental result cannot keep completely consistent.

[0210] The application provides a transformer inter-turn short circuit fault position positioning method. First, when a target transformer is detected to have an inter-turn short circuit fault, micro-thermal field simulation data of the target transformer is obtained, the micro-thermal field simulation data is obtained based on a micro-thermal field digital twin model of the target transformer, and the micro-thermal field digital twin model is obtained by correcting a real signal collected by a sensor arranged in a micro-thermal field of the target transformer based on a multi-field coupling simulation model of the target transformer. Second, an inter-turn short circuit fault characteristic parameter is extracted from the micro-thermal field simulation data based on a convolutional neural network. Finally, the position of the inter-turn short circuit fault of the target transformer is determined based on a Bayesian inference method according to the inter-turn short circuit fault characteristic parameter. Compared with the prior art, the micro-thermal field digital twin model is obtained by correcting the real signal collected by the sensor arranged in the micro-thermal field of the target transformer based on the multi-field coupling simulation model of the target transformer, so that the simulation data obtained based on the micro-thermal field digital twin model is highly similar to the actual operation of the target transformer. The simulation data is used for early positioning before the fault occurs, thereby avoiding the problem that the transformer has an internal fault due to untimely reaction. Further, the inter-turn short circuit fault characteristic parameter is extracted from the micro-thermal field simulation data based on the convolutional neural network, the high sensitivity of the convolutional neural network is used to overcome the problem that the fault characteristic cannot be found in time due to slow temperature change, the recognition sensitivity to the fault characteristic is improved, and the action sensitivity is further improved. Finally, the accurate position of the inter-turn short circuit fault is determined according to the inter-turn short circuit fault characteristic parameter by using the Bayesian inference method, thereby overcoming the defect that the inter-turn short circuit fault position cannot be accurately positioned in the prior art.

[0211] Further, as an implementation of the method shown in the above Figure 1 , the application embodiment provides a transformer inter-turn short circuit fault position positioning device, as shown in the above Figure 8 , the device comprises:

[0212] a micro-thermal field simulation data acquisition module 31, an inter-turn short circuit fault characteristic parameter extraction module 32, and an inter-turn short circuit fault position positioning module 33.

[0213] The micro-thermal field simulation data acquisition module 31 is used for acquiring micro-thermal field simulation data of a target transformer when the target transformer is detected to have an inter-turn short circuit fault, the micro-thermal field simulation data is obtained based on a micro-thermal field digital twin model of the target transformer, and the micro-thermal field digital twin model is obtained by correcting a real signal collected by a sensor arranged in a micro-thermal field of the target transformer based on a multi-field coupling simulation model of the target transformer.

[0214] The inter-turn short-circuit fault feature quantity extraction module 32 is configured to extract an inter-turn short-circuit fault feature quantity from the micro-thermal field simulation data based on a convolutional neural network.

[0215] The inter-turn short-circuit fault position positioning module 33 is configured to determine a position of the inter-turn short-circuit fault of the target transformer based on a Bayesian inference method according to the inter-turn short-circuit fault feature quantity.

[0216] In a specific application scenario, before the micro-thermal field simulation data acquisition module, the device further comprises a micro-thermal field digital twin model construction module configured to:

[0217] Based on an electromagnetic field differential equation and a natural convection heat transfer mathematical model, a thermal field and flow field coupling model is constructed, and the electromagnetic field differential equation is expressed as the following formula

[0218]

[0219] Among them, denotes a vector differential operator, H denotes a magnetic field intensity, J denotes a current density, D denotes an electric displacement vector, t denotes time, B denotes a magnetic induction intensity, E denotes an electric field intensity, and p denotes a charge density,

[0220] The natural convection heat transfer mathematical model is expressed as the following formula

[0221] q=h(T b -T o )

[0222] Among them, q denotes a heat flow density, h denotes a convection heat transfer coefficient, T b denotes a transformer oil tank temperature, and T o denotes an air temperature.

[0223] A loss value is calculated based on a core and winding loss formula, and the core and winding loss formula is expressed as the following formula

[0224]

[0225] Among them, P 总 denotes a loss value, P fe0 denotes a core loss per unit volume before winding short-circuit, B denotes a maximum magnetic flux density in the core before winding short-circuit, B0 denotes a maximum magnetic flux density in the core after winding short-circuit, P wN denotes a loss per unit volume of winding under rated current, I b denotes a winding current of inter-turn short-circuit, I N denotes a winding rated current of inter-turn short-circuit, I sh denotes an equivalent fault resistance current of inter-turn short-circuit, and R shrepresents an equivalent fault resistance value of a turn-to-turn short circuit, n represents a proportion of the turn-to-turn short circuit, and V represents a volume of a fault winding;

[0226] input the loss value and a preset inlet flow rate value in the flow field into the thermal field-flow field coupling model to obtain a multi-field coupling simulation model for the target transformer.

[0227] In a specific application scenario, the micro-temperature field digital twin model construction module is further configured to:

[0228] real-time acquisition of real signals collected by each sensor arranged in the micro-temperature field of the target transformer;

[0229] correcting parameters of the multi-field coupling simulation model using the real signals until a preset accuracy threshold is met, to obtain a micro-temperature field digital twin model of the target transformer.

[0230] In a specific application scenario, the turn-to-turn short circuit fault location module is configured to:

[0231] calculating a total probability value of observing the turn-to-turn short circuit fault feature based on a total probability calculation formula according to the turn-to-turn short circuit fault feature parameters, the total probability calculation formula being represented by the following formula

[0232]

[0233] wherein Y n represents a turn-to-turn short circuit fault feature parameter, P(Y n ) represents a total probability value of observing the turn-to-turn short circuit fault feature, represents a frequency of occurrence of a feature corresponding to a turn-to-turn short circuit fault, X m represents a turn-to-turn short circuit fault occurring in an m region, and m represents A, B, and C three regions, represents a total frequency of turn-to-turn short circuit faults in A, B, and C three regions;

[0234] calculating a probability value of observing the turn-to-turn short circuit fault feature under the condition that a turn-to-turn short circuit fault occurs in each region based on the following formula,

[0235]

[0236] wherein P(Y n |X m ) represents a probability value of observing the turn-to-turn short circuit fault feature under the condition that a turn-to-turn short circuit fault occurs in an m region, represents a probability value of a turn-to-turn short circuit fault occurring in A, B, and C three regions respectively;

[0237] According to the total probability value of the observed inter-turn short circuit fault feature and the probability value of the observed inter-turn short circuit fault feature under the condition that the inter-turn short circuit fault occurs in each region, the probability value of the inter-turn short circuit fault occurring in each region under the condition of observing the inter-turn short circuit fault feature is calculated respectively based on a Bayesian fault location formula, and the Bayesian fault location formula is expressed as the following formula

[0238]

[0239] Wherein, P(X m |Y n ) represents the probability value of the inter-turn short circuit fault occurring in the m region under the condition of observing the inter-turn short circuit fault feature, and P(X m ) represents the preset prior probability value of the inter-turn short circuit fault occurring in the m region.

[0240] The region corresponding to the maximum probability value is selected from the probability values of the inter-turn short circuit faults, and the region is determined as the position of the inter-turn short circuit fault of the target transformer.

[0241] In a specific application scenario, the micro-temperature field simulation data includes time sequence parameter data and image parameter data, and the inter-turn short circuit fault feature parameter extraction module is used to:

[0242] The time sequence parameter data is arranged based on a preset matrix rule to obtain a time sequence parameter matrix conforming to the preset matrix rule.

[0243] The time sequence parameter matrix is form converted so that the time sequence parameter matrix and the data image have the same representation form.

[0244] The first inter-turn short circuit fault feature parameter corresponding to the time sequence parameter is extracted from the form converted time sequence parameter based on a first convolutional neural network.

[0245] The second inter-turn short circuit fault feature parameter corresponding to the image parameter is extracted from the image parameter data based on a second convolutional neural network.

[0246] The first inter-turn short circuit fault feature parameter and the second inter-turn short circuit fault feature parameter are fused based on a preset weight ratio to obtain the inter-turn short circuit fault feature parameter of the micro-temperature field simulation data.

[0247] In a specific application scenario, the micro-temperature field simulation data acquisition module includes:

[0248] The target sensor group screening unit is configured to, when detecting that the target transformer has a turn-to-turn short circuit fault, screen a target sensor group from the target transformer micro-temperature field according to a comprehensive score coefficient of each sensor in the target sensor group, the comprehensive score coefficient being obtained by fusing a sensor temperature and hot spot temperature correlation basic weight vector, a sensor data reliability basic weight vector, and a sensor signal symmetry basic weight vector to obtain a comprehensive score vector, and then performing weight distribution based on a game weighting algorithm;

[0249] The micro-temperature field simulation data acquisition unit is configured to acquire micro-temperature field simulation data corresponding to each sensor in the target sensor group as micro-temperature field simulation data of the target transformer, so as to locate a turn-to-turn short circuit fault position.

[0250] In a specific application scenario, the target sensor group screening unit is configured to:

[0251] When detecting that the target transformer has a turn-to-turn short circuit fault, the sensor temperature and hot spot temperature correlation basic weight vector is calculated based on a Pearson correlation coefficient formula, the Pearson correlation coefficient formula being expressed as the following formula

[0252]

[0253] wherein r represents a sensor temperature and hot spot temperature correlation vector, M represents a sensor quantity, x j represents a hot spot temperature in the jth sensor, represents a hot spot temperature average value in the sensor, y j represents a temperature of the jth sensor, represents a sensor temperature average value;

[0254] The sensor data reliability basic weight vector is determined based on a signal variance of each sensor.

[0255] The symmetry index between each pair of sensor signals is calculated based on a symmetry index calculation formula to generate a sensor signal symmetry basic weight vector, the symmetry index calculation formula being expressed as the following formula

[0256] DS=R*ρ

[0257] wherein DS represents the symmetry index between each pair of sensor signals, R represents a distance coefficient, R=-ln(|r1-r2|), r1 and r2 respectively represent root mean square values of two sensors at a current monitoring point, and ρ represents a Spearman correlation coefficient.

[0258] fuse the sensor temperature and hot spot temperature correlation basic weight vector, the sensor data reliability basic weight vector, and the symmetry basic weight vector between sensor signals to obtain a comprehensive score vector

[0259]

[0260] wherein W represents the comprehensive score vector, λ α represents a weight coefficient, α = 1 represents the sensor temperature and hot spot temperature correlation basic weight vector, α = 2 represents the sensor data reliability basic weight vector, and α = 3 represents the symmetry basic weight vector between sensor signals, and T represents a combination coefficient;

[0261] The weight coefficient is optimized based on a game weighting algorithm, so that the deviation between the comprehensive score vector and the sensor temperature and hot spot temperature correlation basic weight vector, the sensor data reliability basic weight vector, and the symmetry basic weight vector between sensor signals is minimized, to obtain an optimal weight coefficient;

[0262] The optimal weight coefficient is normalized to obtain a comprehensive score coefficient of each sensor;

[0263] Based on a preset rule, a target sensor group is selected according to the comprehensive score coefficient of each sensor, so that the turn-to-turn short circuit fault position is positioned according to the micro-temperature field simulation data corresponding to each sensor in the target sensor group.

[0264] The application provides a transformer inter-turn short circuit fault position positioning device. First, when a target transformer is detected to have an inter-turn short circuit fault, micro-temperature field simulation data of the target transformer is acquired, the micro-temperature field simulation data being obtained based on a micro-temperature field digital twin model of the target transformer, the micro-temperature field digital twin model being obtained by correcting a real signal collected by a sensor arranged in a micro-temperature field of the target transformer based on a multi-field coupling simulation model of the target transformer. Second, an inter-turn short circuit fault characteristic parameter is extracted from the micro-temperature field simulation data based on a convolutional neural network. Finally, the position of the inter-turn short circuit fault of the target transformer is determined based on a Bayesian inference method according to the inter-turn short circuit fault characteristic parameter. Compared with the prior art, the micro-temperature field digital twin model is obtained by correcting the real signal collected by the sensor arranged in the micro-temperature field of the target transformer based on the multi-field coupling simulation model of the target transformer, so that the simulation data obtained based on the micro-temperature field digital twin model is highly similar to the real operation of the target transformer. On this basis, the simulation data is used to position in advance before the fault occurs, thereby avoiding the problem that the transformer has an internal fault due to untimely reaction. Further, the inter-turn short circuit fault characteristic parameter is extracted from the micro-temperature field simulation data based on the convolutional neural network, the problem that the fault characteristic cannot be found in time due to slow temperature change is overcome by using the high sensitivity of the convolutional neural network, the recognition sensitivity to the fault characteristic is improved, and the action sensitivity is further improved. Finally, the accurate position of the inter-turn short circuit fault is determined according to the inter-turn short circuit fault characteristic parameter by using the Bayesian inference method, thereby overcoming the defect that the inter-turn short circuit fault position cannot be accurately positioned in the prior art.

[0265] According to an embodiment of the application, a storage medium is provided, and the storage medium stores at least one executable instruction. The computer executable instruction can execute the positioning method of the transformer inter-turn short circuit fault position in any method embodiment described above.

[0266] Based on such understanding, the technical scheme of the application can be embodied in the form of a software product. The software product can be stored in a non-volatile storage medium (which can be a CD-ROM, a U disk, a mobile hard disk, etc.), and includes a plurality of instructions for causing a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the method described in each embodiment scenario of the application.

[0267] Figure 9 A structural schematic diagram of a terminal according to an embodiment of the application is shown, and the specific implementation of the terminal is not limited in the specific embodiments of the application.

[0268] As Figure 9As shown, the terminal can include a processor 402, a communications interface 404, a memory 406, and a communications bus 408.

[0269] The processor 402, the communications interface 404, and the memory 406 can communicate with each other through the communications bus 408.

[0270] The communications interface 404 is configured to communicate with network elements such as clients or other servers.

[0271] The processor 402 is configured to execute the program 410, and can specifically execute the related steps in the transformer inter-turn short circuit fault positioning method embodiments described above.

[0272] Specifically, the program 410 can include program code including computer operation instructions.

[0273] The processor 402 can be a central processing unit (CPU), or an application specific integrated circuit (ASIC), or one or more integrated circuits configured to implement the embodiments of the present application. The one or more processors included in the computer device can be processors of the same type, such as one or more CPUs, or processors of different types, such as one or more CPUs and one or more ASICs.

[0274] The memory 406 is configured to store the program 410. The memory 406 can include a high-speed RAM memory, and can also include a non-volatile memory such as at least one disk memory.

[0275] The program 410 can specifically be used to cause the processor 402 to perform the following operations:

[0276] When it is detected that the target transformer has an inter-turn short circuit fault, micro-thermal field simulation data of the target transformer is acquired, the micro-thermal field simulation data being obtained based on a micro-thermal field digital twin model of the target transformer, the micro-thermal field digital twin model being obtained by correcting a multi-field coupling simulation model of the target transformer based on real signals collected by sensors arranged in a micro-thermal field of the target transformer;

[0277] Based on a convolutional neural network, an inter-turn short circuit fault characteristic parameter is extracted from the micro-thermal field simulation data.

[0278] Based on the inter-turn short-circuit fault characteristic parameters, the location of the inter-turn short-circuit fault in the target transformer is determined using a Bayesian inference method.

[0279] The storage medium may also include an operating system and a network communication module. The operating system is a program that manages the hardware and software resources of the physical device for locating the inter-turn short-circuit fault in the aforementioned transformer, supporting the operation of information processing programs and other software and / or programs. The network communication module is used to enable communication between the various components within the storage medium, as well as communication with other hardware and software in the information processing physical device.

[0280] The various embodiments in this specification are described in a progressive manner, with each embodiment focusing on its differences from other embodiments. Similar or identical parts between embodiments can be referred to interchangeably. For system embodiments, since they largely correspond to method embodiments, the description is relatively simple; relevant parts can be referred to the descriptions in the method embodiments.

[0281] The methods and systems of this application may be implemented in many ways. For example, they may be implemented by software, hardware, firmware, or any combination of software, hardware, and firmware. The above-described order of steps for the methods is for illustrative purposes only, and the steps of the methods of this application are not limited to the order specifically described above, unless otherwise specifically stated. Furthermore, in some embodiments, this application may also be implemented as a program recorded on a recording medium, the program including machine-readable instructions for implementing the methods according to this application. Thus, this application also covers recording media storing programs for performing the methods according to this application.

[0282] Obviously, those skilled in the art should understand that the modules or steps of this application described above can be implemented using general-purpose computing devices. They can be centralized on a single computing device or distributed across a network of multiple computing devices. Optionally, they can be implemented using computer-executable program code, thereby storing them in a storage device for execution by a computing device. In some cases, the steps shown or described can be performed in a different order than those presented here, or they can be fabricated as separate integrated circuit modules, or multiple modules or steps can be fabricated as a single integrated circuit module. Thus, this application is not limited to any particular combination of hardware and software.

[0283] The above description is merely a preferred embodiment of this application and is not intended to limit this application. Various modifications and variations can be made to this application by those skilled in the art. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of this application should be included within the scope of protection of this application.

Claims

1. A method of locating a transformer turn-to-turn short circuit fault location, characterized by, The method comprises the steps of: When it is detected that the target transformer has a turn-to-turn short circuit fault, micro-thermal field simulation data of the target transformer is obtained, the micro-thermal field simulation data being obtained based on a micro-thermal field digital twin model of the target transformer, the micro-thermal field digital twin model being obtained by correcting a multi-field coupling simulation model of the target transformer by using real signals collected by sensors arranged in the micro-thermal field of the target transformer, the micro-thermal field simulation data comprising time-series parameter data and image parameter data; Based on a convolutional neural network, turn-to-turn short circuit fault characteristic parameters are extracted from the micro-thermal field simulation data; Based on Bayesian inference, the position of the turn-to-turn short circuit fault of the target transformer is determined according to the turn-to-turn short circuit fault characteristic parameters; The method comprises the steps of: Based on a preset matrix rule, the time-series parameter data is arranged to obtain a time-series parameter matrix conforming to the preset matrix rule; The time-series parameter matrix is formally converted so that the time-series parameter matrix and a data image have the same representation form; Based on a first convolutional neural network, first turn-to-turn short circuit fault characteristic parameters corresponding to the time-series parameters are extracted from the time-series parameters after the form conversion; Based on a second convolutional neural network, second turn-to-turn short circuit fault characteristic parameters corresponding to the image parameters are extracted from the image parameter data; Based on a preset weight ratio, the first turn-to-turn short circuit fault characteristic parameters and the second turn-to-turn short circuit fault characteristic parameters are fused to obtain turn-to-turn short circuit fault characteristic parameters of the micro-thermal field simulation data; When it is detected that the target transformer has a turn-to-turn short circuit fault, micro-thermal field simulation data of the target transformer is obtained, comprising the steps of: When it is detected that the target transformer has a turn-to-turn short circuit fault, a target sensor group is selected according to a comprehensive score coefficient of each sensor arranged in the micro-thermal field of the target transformer, the comprehensive score coefficient being obtained by fusing a sensor temperature and hot spot temperature correlation basic weight vector, a sensor data reliability basic weight vector, and a sensor signal symmetry basic weight vector to obtain a comprehensive score vector, and then performing weight distribution based on a game weighting algorithm; Micro-thermal field simulation data corresponding to each sensor in the target sensor group is obtained as the micro-thermal field simulation data of the target transformer for turn-to-turn short circuit fault position positioning; The method comprises the steps of: When it is detected that the target transformer has a turn-to-turn short circuit fault, a sensor temperature and hot spot temperature correlation basic weight vector is calculated based on a Pearson correlation coefficient formula, the Pearson correlation coefficient formula being expressed as the following formula, ， wherein, represents a sensor temperature and hot spot temperature correlation vector, represents a number of sensors, represents a hot spot temperature in the jth sensor, represents a mean value of hot spot temperatures in the sensors, represents a temperature of the jth sensor, represents a mean value of sensor temperatures; Based on signal variances of each sensor, a sensor data reliability basic weight vector is determined; The symmetry index between each pair of sensor signals is calculated based on a symmetry index calculation formula to generate a symmetry basic weight vector between the sensor signals, the symmetry index calculation formula being represented as the following formula, ， wherein, denotes the index of symmetry between each pair of sensor signals, denotes the distance coefficient, , , denote the root mean square values of the two sensors at the current monitoring point, respectively, denotes the Spearman correlation coefficient; The sensor temperature and hotspot temperature correlation basic weight vector, the sensor data reliability basic weight vector and the symmetry basic weight vector between the sensor signals are fused to obtain a comprehensive score vector, ， wherein, represents a combined score vector, represents a weight coefficient, represents a sensor temperature and hot spot temperature correlation base weight vector, represents a sensor data reliability base weight vector, represents a sensor signal between symmetry base weight vector, T represents a combination coefficient; The weight coefficients are optimized based on a game weighting algorithm so that the deviations between the comprehensive score vector and the sensor temperature and hotspot temperature correlation basic weight vector, the sensor data reliability basic weight vector and the symmetry basic weight vector between the sensor signals are all minimum, and optimal weight coefficients are obtained; The optimal weight coefficients are normalized to obtain comprehensive score coefficients of each sensor; Based on a preset rule, a target sensor group is selected according to the comprehensive score coefficients of each sensor, so that the inter-turn short circuit fault position is located according to the micro-thermal field simulation data corresponding to each sensor in the target sensor group.

2. The method of claim 1, wherein, Before the micro-thermal field simulation data of the target transformer is obtained when it is detected that the target transformer has an inter-turn short circuit fault, the method further comprises: Based on an electromagnetic field differential equation and a natural convection heat transfer mathematical model, a thermal field and flow field coupling model is constructed, the electromagnetic field differential equation being represented as the following formula wherein denotes the vector differential operator, denotes the magnetic field strength, denotes the current density, denotes the electric displacement vector, denotes time, denotes the magnetic induction, denotes the electric field strength, denotes the charge density, The natural convection heat transfer mathematical model is represented as the following formula wherein, represents the heat flux density, represents the convective heat transfer coefficient, represents the transformer oil tank temperature, represents the air temperature; A loss value is calculated based on a core and winding loss formula, the core and winding loss formula being represented as the following formula wherein, represents a loss value, represents a core loss per unit volume before winding short circuit, represents a maximum magnetic flux density in the core before winding short circuit, represents a maximum magnetic flux density in the core after winding short circuit, represents a winding loss per unit volume at rated current, represents a winding current for inter-turn short circuit, represents a winding rated current for inter-turn short circuit, represents an equivalent fault resistance current for inter-turn short circuit, represents an equivalent fault resistance value for inter-turn short circuit, represents a ratio for inter-turn short circuit, represents a fault winding volume; The loss value and a preset inlet flow rate value in the flow field are input into the thermal field and flow field coupling model to obtain a multi-field coupling simulation model for the target transformer.

3. The method of claim 2, wherein, After the multi-field coupling simulation model for the target transformer is obtained, the method further comprises: Real signals collected by each sensor arranged in the micro-thermal field of the target transformer are obtained in real time; The parameters of the multi-field coupling simulation model are corrected using the real signals until a preset precision threshold is met, so that a micro-thermal field digital twin model of the target transformer is obtained.

4. The method of claim 1, wherein, The position of the inter-turn short circuit fault of the target transformer is determined based on a Bayesian inference method according to the inter-turn short circuit fault characteristic parameters, which comprises: Based on a total probability calculation formula, a total probability value of observing the inter-turn short circuit fault characteristics is calculated according to the inter-turn short circuit fault characteristic parameters, the total probability calculation formula being represented as the following formula wherein, represents the inter-turn short circuit fault characteristic parameter, represents the total probability value of observing the inter-turn short circuit fault characteristic, represents the frequency of occurrence of the characteristic corresponding to the inter-turn short circuit fault, represents that an inter-turn short circuit fault occurs in the m region, and m represents A, B, and C three regions, represents the total frequency of inter-turn short circuit faults in A, B, and C three regions; Based on the following formula, a probability value of observing the inter-turn short circuit fault characteristics under the condition that an inter-turn short circuit fault occurs in each region is calculated, wherein, represents a probability value of observing a turn-to-turn short circuit fault feature under a condition that a turn-to-turn short circuit fault occurs in the m region, represents a probability value of a turn-to-turn short circuit fault occurring in each of the A, B, and C regions; Based on a Bayesian fault positioning formula, the probability values of inter-turn short circuit faults occurring in each region under the condition of observing the inter-turn short circuit fault characteristics are respectively calculated according to the total probability value of observing the inter-turn short circuit fault characteristics and the probability value of observing the inter-turn short circuit fault characteristics under the condition that an inter-turn short circuit fault occurs in each region, the Bayesian fault positioning formula being represented as the following formula wherein, represents a probability value of the m region occurring the inter-turn short circuit fault under the condition of observing the inter-turn short circuit fault feature, represents a preset prior probability value of the m region occurring the inter-turn short circuit fault. The region corresponding to the maximum probability value is screened out from the probability values of the turn-to-turn short circuit faults, and the region is determined as the position of the turn-to-turn short circuit fault of the target transformer.

5. A device for locating a transformer turn-to-turn short fault location, characterized by Comprise: The micro-temperature field simulation data acquisition module is configured to acquire micro-temperature field simulation data of the target transformer when it is detected that the target transformer has a turn-to-turn short circuit fault, wherein the micro-temperature field simulation data is obtained based on a micro-temperature field digital twin model of the target transformer, and the micro-temperature field digital twin model is obtained by correcting a multi-field coupling simulation model of the target transformer based on real signals collected by sensors arranged in a micro-temperature field of the target transformer, and the micro-temperature field simulation data comprises time-series parameter data and image parameter data. The turn-to-turn short circuit fault feature parameter extraction module is configured to extract turn-to-turn short circuit fault feature parameters from the micro-temperature field simulation data based on a convolutional neural network. The turn-to-turn short circuit fault position positioning module is configured to determine the position of the turn-to-turn short circuit fault of the target transformer based on Bayesian inference based on the turn-to-turn short circuit fault feature parameters. The turn-to-turn short circuit fault feature parameter extraction module is configured to: arrange the time-series parameter data based on a preset matrix rule to obtain a time-series parameter matrix that conforms to the preset matrix rule; perform form conversion on the time-series parameter matrix to make the time-series parameter matrix and a data image have the same representation form; extract first turn-to-turn short circuit fault feature parameters corresponding to the time-series parameters from the time-series parameters after the form conversion based on a first convolutional neural network; extract second turn-to-turn short circuit fault feature parameters corresponding to the image parameters from the image parameter data based on a second convolutional neural network; fuse the first turn-to-turn short circuit fault feature parameters and the second turn-to-turn short circuit fault feature parameters based on a preset weight ratio to obtain turn-to-turn short circuit fault feature parameters of the micro-temperature field simulation data. The micro-temperature field simulation data acquisition module comprises: The target sensor group screening unit is configured to screen a target sensor group from sensors arranged in a micro-temperature field of the target transformer based on comprehensive score coefficients of the sensors when it is detected that the target transformer has a turn-to-turn short circuit fault, wherein the comprehensive score coefficients are obtained by fusing a sensor temperature and hot spot temperature correlation basic weight vector, a sensor data reliability basic weight vector, and a sensor signal symmetry basic weight vector to obtain a comprehensive score vector, and then performing weight distribution based on a game weighting algorithm. The micro-temperature field simulation data acquisition unit is configured to acquire micro-temperature field simulation data corresponding to each sensor in the target sensor group as the micro-temperature field simulation data of the target transformer for turn-to-turn short circuit fault position positioning. The target sensor group screening unit is configured to: calculate a sensor temperature and hot spot temperature correlation basic weight vector based on a Pearson correlation coefficient formula when it is detected that the target transformer has a turn-to-turn short circuit fault, wherein the Pearson correlation coefficient formula is expressed as the following formula, ， wherein, represents a sensor temperature and hot spot temperature correlation vector, represents a number of sensors, represents a hot spot temperature in the jth sensor, represents a hot spot temperature average in the sensor, represents a temperature of the jth sensor, represents a sensor temperature average; determine a sensor data reliability basic weight vector based on signal variance of each of the sensors; calculate a symmetry index between each pair of sensor signals based on a symmetry index calculation formula to generate a symmetry between sensor signals basic weight vector, the symmetry index calculation formula is expressed as the following formula, ， wherein, denotes the index of symmetry between each pair of sensor signals, denotes the distance coefficient, , , denote the root mean square values of the two sensors at the current monitoring point, respectively, denotes the Spearman correlation coefficient; fuse the sensor temperature and hot spot temperature correlation basic weight vector, the sensor data reliability basic weight vector, the symmetry between sensor signals basic weight vector to obtain a comprehensive score vector, ， wherein, represents a combined score vector, represents a weight coefficient, represents a sensor temperature and hot spot temperature correlation base weight vector, represents a sensor data reliability base weight vector, represents a sensor signal between symmetry base weight vector, T represents a combination coefficient; optimize the weight coefficients based on a game weighting algorithm, so that the deviation between the comprehensive score vector and the sensor temperature and hot spot temperature correlation basic weight vector, the sensor data reliability basic weight vector, the symmetry between sensor signals basic weight vector is the minimum, to obtain the optimal weight coefficients; normalize the optimal weight coefficients to obtain the comprehensive score coefficient of each sensor; based on a preset rule, filter out a target sensor group according to the comprehensive score coefficient of each sensor, so as to locate the turn-to-turn short circuit fault position according to the micro-thermal field simulation data corresponding to each sensor in the target sensor group.

6. A storage medium having stored therein at least one executable instruction, characterized in that, The executable instructions make the processor execute the operations corresponding to the transformer turn-to-turn short circuit fault position locating method in any one of claims 1-4.

7. A terminal comprising: The processor, the memory, the communication interface and the communication bus, the processor, the memory and the communication interface complete the communication among each other through the communication bus; The memory is used to store at least one executable instruction, characterized in that the executable instruction makes the processor execute the operations corresponding to the transformer turn-to-turn short circuit fault position locating method in any one of claims 1-4.

Images