Transformer overheating fault identification method and device based on temperature inversion, electronic equipment and storage medium

Abstract

The invention relates to the technical field of transformers, and provides a transformer overheating fault identification method and device based on temperature inversion, electronic equipment and a storage medium. Comprising the steps that real-time monitoring data of a transformer are acquired, and the real-time monitoring data comprise the top layer oil temperature, the environment temperature and the load coefficient; based on the top oil temperature, the environment temperature and the load coefficient, inverse problem solving is conducted on a pre-established top oil temperature calculation model, and thermal characteristic parameters of the transformer are obtained; calculating a theoretical load current of the transformer based on the thermal characteristic parameters; and if the deviation between the theoretical load current and the actually measured load current exceeds a preset deviation threshold value, determining that the transformer has an overheating fault. The method can quickly and accurately identify the overheating fault of the transformer, and is of great significance for improving the reliability of a power system.

Description

Technical Field

[0001] This application relates to the field of transformer technology, specifically to a method, apparatus, electronic device, and storage medium for identifying transformer overheating faults based on temperature inversion. Background Technology

[0002] As an indispensable and crucial piece of equipment in power systems, the operating status of transformers directly affects the stability and security of the power system. Therefore, in-depth research on transformer condition assessment techniques is of significant theoretical and practical importance. With the continuous increase in voltage levels, transformer capacity, and wider application, the imbalance between the growth of power supply capacity and structural dimensions has led to increasingly frequent transformer failures. Overheating faults account for a large proportion of transformer failures, and overheating faults in transformer windings are among the most critical to address. Therefore, research on methods for identifying transformer overheating faults is of great importance for improving the reliability of power systems.

[0003] Currently, the main technologies used domestically and internationally for identifying transformer overheating faults include dissolved gas analysis (DGA), oil temperature monitoring (OTM), winding temperature analysis, and infrared thermography. Among these, DGA and infrared thermography suffer from slow response times and high false alarm rates. Oil temperature monitoring primarily reflects the temperature of the top layer oil and is insufficient for quickly detecting and identifying internal transformer overheating faults. Winding temperature is mainly calculated using methods outlined in load guidelines, but the accuracy of these calculations is poor.

[0004] The above-mentioned overheating fault identification method has great limitations in practical applications, making it difficult to quickly and accurately identify transformer overheating faults. Summary of the Invention

[0005] In view of this, the embodiments of this application provide a method, device, electronic device and storage medium for identifying transformer overheating faults based on temperature inversion, which can quickly and accurately identify transformer overheating faults and is of great significance for improving the reliability of power systems.

[0006] The first aspect of this application provides a method for identifying transformer overheating faults based on temperature inversion, including: Acquire real-time monitoring data of the transformer, including top oil temperature, ambient temperature, and load factor; Based on the top oil temperature, ambient temperature, and load factor, the inverse problem of the pre-established top oil temperature calculation model is solved to obtain the thermal characteristic parameters of the transformer. Based on the aforementioned thermal characteristic parameters, the theoretical load current of the transformer is calculated; If the deviation between the theoretical load current and the measured load current exceeds a preset deviation threshold, then the transformer is determined to have an overheating fault.

[0007] In one embodiment, the top oil temperature calculation model is expressed as: ; Where K is the load factor, R is the ratio of load loss at rated current to no-load loss at rated voltage, and x is the oil index. The top oil temperature rise under rated load, These are thermal model constants. The oil time constant, For ambient temperature, For a period of time, Let the top oil temperature be the temperature in the nth time period. This represents the top oil temperature during the (n-1)th time period.

[0008] In one embodiment, the inverse problem of solving a pre-established top oil temperature calculation model based on the top oil temperature, ambient temperature, and load factor is used to obtain the transformer's thermal characteristic parameters, including: Based on the top oil temperature calculation model, a matrix equation is obtained to characterize the relationship between the top oil temperature, ambient temperature, load factor, and thermal characteristic parameters. Substituting multiple sets of top oil temperature, ambient temperature, and load factor under the steady-state condition of the transformer into the matrix equation, we obtain an overdetermined set of equations. The QR decomposition method was used to solve the overdetermined equations to obtain the thermal characteristic parameters.

[0009] In one embodiment, the matrix equation is: ; in , , , ; k 1. k 2. k 3 represents thermal characteristic parameters. This is the initial value of the top oil temperature. This is the initial value of the ambient temperature. For K （0） An exponential function of variables. K （0） This is the initial value of the load factor. Let the top oil temperature be the temperature in the k-th time period. The top oil temperature is the temperature of the top layer in the (k-1)th time period. Let K be the ambient temperature during the (k-1)th time period. To calculate the k-th time period with K （k） An exponential function of variables. To calculate the (k-1)th time period, K （k-1） Let be an exponential function of variables, K be the load factor, R be the ratio of load loss at rated current to no-load loss at rated voltage, and x be the oil exponent. The top oil temperature rise under rated load, These are thermal model constants. The oil time constant, For the time period, k can be any natural number from 2 to n, and n is the upper limit of the preset time period value.

[0010] In one embodiment, solving the overdetermined equations using the QR decomposition method to obtain the thermal characteristic parameters includes: The matrix equation is expressed as A=B×T, where A is an N×1 matrix including the top oil temperature value for a preset time period, B is an N×3 matrix including the top oil temperature, ambient temperature and load-related terms for the corresponding time period, and T is the thermal characteristic parameter matrix to be solved. Perform QR decomposition on matrix B, decomposing it into an orthogonal matrix Q and an upper triangular matrix S, such that B = Q × S; The original equation A=B×T is transformed into the form Q×S×T=A through orthogonal transformation; By utilizing the triangular properties of the upper triangular matrix S, the thermal characteristic parameters in the thermal characteristic parameter matrix T are solved step by step using the back substitution method.

[0011] In one embodiment, the theoretical load current is calculated using the following formula: ; ; I s = K (k) × I ; in, To calculate the k-th time period with K （k） An exponential function of variables. K （k） Let be the load factor for the k-th time period. The top oil temperature is the temperature of the (k+1)th time period. Let the top oil temperature be the temperature in the k-th time period. Let be the ambient temperature during the k-th time period. k 1. k 2.k 3 represents thermal characteristic parameters. I Rated current, I s denoted as the theoretical load current, and x as the oil index.

[0012] A second aspect of this application provides a transformer overheating fault identification device based on temperature inversion, comprising: The data acquisition module is used to acquire real-time monitoring data of the transformer, including top oil temperature, ambient temperature, and load factor. The thermal characteristic parameter calculation module is used to solve the inverse problem of the pre-established top oil temperature calculation model based on the top oil temperature, ambient temperature and load factor, so as to obtain the thermal characteristic parameters of the transformer. The load current calculation module is used to calculate the theoretical load current of the transformer based on the thermal characteristic parameters. The fault diagnosis module is used to determine that the transformer has an overheating fault if the deviation between the theoretical load current and the measured load current exceeds a preset deviation threshold.

[0013] In one embodiment, the top oil temperature calculation model is expressed as: ; Where K is the load factor, R is the ratio of load loss at rated current to no-load loss at rated voltage, and x is the oil index. The top oil temperature rise under rated load, These are thermal model constants. The oil time constant, For ambient temperature, For a period of time, Let the top oil temperature be the temperature in the nth time period. This represents the top oil temperature during the (n-1)th time period.

[0014] In one embodiment, the thermal characteristic parameter calculation module is further configured to: Based on the top oil temperature calculation model, a matrix equation is obtained to characterize the relationship between the top oil temperature, ambient temperature, load factor, and thermal characteristic parameters. Substituting multiple sets of top oil temperature, ambient temperature, and load factor under the steady-state condition of the transformer into the matrix equation, we obtain an overdetermined set of equations. The QR decomposition method was used to solve the overdetermined equations to obtain the thermal characteristic parameters.

[0015] In one embodiment, the matrix equation is: ; in , , , ; k 1. k 2. k 3 represents thermal characteristic parameters. This is the initial value of the top oil temperature. This is the initial value of the ambient temperature. For K （0） An exponential function of variables. K （0） This is the initial value of the load factor. Let the top oil temperature be the temperature in the k-th time period. The top oil temperature is the temperature of the top layer in the (k-1)th time period. Let K be the ambient temperature during the (k-1)th time period. To calculate the k-th time period with K （k） An exponential function of variables. To calculate the (k-1)th time period, K （k-1） Let be an exponential function of variables, K be the load factor, R be the ratio of load loss at rated current to no-load loss at rated voltage, and x be the oil exponent. The top oil temperature rise under rated load, These are thermal model constants. The oil time constant, For the time period, k can be any natural number from 2 to n, and n is the upper limit of the preset time period value.

[0016] In one embodiment, the thermal characteristic parameter calculation module is further configured to: The matrix equation is expressed as A=B×T, where A is an N×1 matrix including the top oil temperature value for a preset time period, B is an N×3 matrix including the top oil temperature, ambient temperature and load-related terms for the corresponding time period, and T is the thermal characteristic parameter matrix to be solved. Perform QR decomposition on matrix B, decomposing it into an orthogonal matrix Q and an upper triangular matrix S, such that B = Q × S; The original equation A=B×T is transformed into the form Q×S×T=A through orthogonal transformation; By utilizing the triangular properties of the upper triangular matrix S, the thermal characteristic parameters in the thermal characteristic parameter matrix T are solved step by step using the back substitution method.

[0017] In one embodiment, the theoretical load current is calculated using the following formula: ; ; I s = K (k) × I ; in, To calculate the k-th time period with K （k） An exponential function of variables. K （k） Let be the load factor for the k-th time period. The top oil temperature is the temperature of the (k+1)th time period. Let the top oil temperature be the temperature in the k-th time period. Let be the ambient temperature during the k-th time period. k 1. k 2. k 3 represents thermal characteristic parameters. I Rated current, I s denoted as the theoretical load current, and x as the oil index.

[0018] A third aspect of this application provides an electronic device including a processor, a memory, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, the electronic device implements the transformer overheating fault identification method based on temperature inversion provided in the first aspect of this application.

[0019] A fourth aspect of this application provides a computer program product including a computer program that, when run, causes the method described in the first aspect of this application to be performed.

[0020] The first aspect of this application provides a transformer overheating fault identification method based on temperature inversion, comprising: acquiring real-time monitoring data of the transformer, including top oil temperature, ambient temperature, and load factor; solving an inverse problem of a pre-established top oil temperature calculation model based on the top oil temperature, ambient temperature, and load factor to obtain the transformer's thermal characteristic parameters; calculating the transformer's theoretical load current based on the thermal characteristic parameters; and determining that the transformer has an overheating fault if the deviation between the theoretical load current and the measured load current exceeds a preset deviation threshold. By integrating real-time monitoring data acquisition and inverse problem solving, dynamic identification of transformer overheating faults is achieved. This method utilizes multi-source data such as top oil temperature, ambient temperature, and load factor to construct a data-driven fault detection mechanism. By combining empirical models with actual operating data through inverse problem solving, it avoids the limitations of traditional methods that rely on fixed parameters, thereby improving the accuracy and adaptability of fault identification. Simultaneously, the entire process is automated, reducing manual intervention and enhancing the system's real-time response capability. This method can quickly and accurately identify transformer overheating faults, which is of great significance for improving the reliability of power systems.

[0021] It is understood that the beneficial effects of the second to fourth aspects mentioned above can be found in the relevant descriptions in the first aspect mentioned above, and will not be repeated here. Attached Figure Description

[0022] To more clearly illustrate the technical solutions in the embodiments of this application, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0023] Figure 1 This is a schematic flowchart of a transformer overheating fault identification method based on temperature inversion provided in an embodiment of this application; Figure 2 This is a schematic flowchart of a transformer overheating fault identification method based on temperature inversion provided in another embodiment of this application; Figure 3 This is a schematic flowchart of a transformer overheating fault identification method based on temperature inversion provided in another embodiment of this application; Figure 4 This is a schematic diagram comparing the top-layer oil temperature of the transformer in this application with the measured value; Figure 5 This is a schematic diagram illustrating the relative error between the calculated and measured values ​​of the transformer load current in this application; Figure 6This is a schematic diagram of the structure of the transformer overheating fault identification device based on temperature inversion provided in the embodiments of this application; Figure 7 This is a schematic diagram of the structure of the electronic device provided in the embodiments of this application. Detailed Implementation

[0024] In the following description, specific details such as particular system architectures and techniques are set forth for illustrative purposes and not for limitation, in order to provide a thorough understanding of the embodiments of this application. However, those skilled in the art will understand that this application may also be implemented in other embodiments without these specific details. In other instances, detailed descriptions of well-known systems, apparatuses, circuits, and methods have been omitted so as not to obscure the description of this application with unnecessary detail.

[0025] It should be understood that, when used in this application specification and the appended claims, the term "comprising" indicates the presence of the described features, integrals, steps, operations, elements and / or components, but does not exclude the presence or addition of one or more other features, integrals, steps, operations, elements, components and / or a collection thereof.

[0026] It should also be understood that the term “and / or” as used in this application specification and the appended claims means any combination of one or more of the associated listed items and all possible combinations, and includes such combinations.

[0027] References to "one embodiment" or "some embodiments" as described in this specification mean that one or more embodiments of this application include a specific feature, structure, or characteristic described in connection with that embodiment. Therefore, the phrases "in one embodiment," "in some embodiments," "in other embodiments," "in still other embodiments," etc., appearing in different parts of this specification do not necessarily refer to the same embodiment, but rather mean "one or more, but not all, embodiments," unless otherwise specifically emphasized. The terms "comprising," "including," "having," and variations thereof mean "including but not limited to," unless otherwise specifically emphasized.

[0028] like Figure 1 As shown, the transformer overheating fault identification method based on temperature inversion provided in this application includes the following steps S101 to S104: Step S101: Obtain real-time monitoring data of the transformer, including top oil temperature, ambient temperature and load factor; Step S102: Based on the top oil temperature, ambient temperature and load factor, solve the inverse problem of the pre-established top oil temperature calculation model to obtain the thermal characteristic parameters of the transformer. Step S103: Calculate the theoretical load current of the transformer based on the thermal characteristic parameters; Step S104: If the deviation between the theoretical load current and the measured load current exceeds a preset deviation threshold, then it is determined that the transformer has an overheating fault.

[0029] In this application, temperature sensors and current measuring devices installed on the transformer first acquire real-time monitoring data such as top oil temperature, ambient temperature, and load factor. Then, based on this data, the inverse problem of a pre-established top oil temperature calculation model is solved. Numerical optimization algorithms, such as the least squares method, can be used to calculate thermal characteristic parameters, including thermal model constants and oil time constants. Next, the theoretical load current is derived using the thermal characteristic parameters through electrical relationships. Finally, the theoretical load current is compared with the measured load current. If the deviation exceeds a preset threshold, such as 5%, a fault alarm is triggered. Data acquisition can utilize a distributed sensor network for continuous monitoring, and iterative algorithms can be used to enhance the accuracy of the inverse problem solution.

[0030] This application's embodiments achieve dynamic identification of transformer overheating faults by integrating real-time monitoring data acquisition and inverse problem solving. This method utilizes multi-source data such as top-layer oil temperature, ambient temperature, and load factor to construct a data-driven fault detection mechanism. By combining empirical models with actual operating data through inverse problem solving, it avoids the limitations of traditional methods that rely on fixed parameters, thereby improving the accuracy and adaptability of fault identification. Simultaneously, the entire process is automated, reducing manual intervention and enhancing the system's real-time response capability. This method can quickly and accurately identify transformer overheating faults, which is of great significance for improving the reliability of power systems.

[0031] Based on the empirical model of top-layer oil temperature given in the load guidelines, this application establishes a relationship model between top-layer oil temperature, ambient temperature, load factor, and transformer thermal characteristic parameters using real-time monitored transformer top-layer oil temperature and ambient temperature data. Through an inverse problem-solving method, the theoretical load current of the transformer is calculated and compared with the actual operating current to assess whether an overheating fault exists within the transformer. The proposed temperature inversion-based transformer overheating fault identification method, combining field measurement data and a classic top-layer oil temperature calculation model, can identify overheating faults caused by inter-turn short circuits or winding strand breakage faults in the transformer windings.

[0032] In one embodiment, the top oil temperature calculation model is expressed as: ; Where K is the load factor, R is the ratio of load loss at rated current to no-load loss at rated voltage, and x is the oil index. The top oil temperature rise under rated load, These are thermal model constants. The oil time constant, For ambient temperature, For a period of time, Let the top oil temperature be the temperature in the nth time period. This represents the top oil temperature during the (n-1)th time period.

[0033] In application, the top oil temperature calculation model is built based on the international standard GB / T1094.7. The model parameters can be initialized through transformer nameplate data, and the formula can be applied using discrete-time iterative calculation.

[0034] In applications, the transformer top temperature is calculated using the empirical model proposed in GB / T1094.7-2024. The difference equation for the top oil temperature is as follows: ; Where K is the load factor (load current / rated current), R is the ratio of load loss at rated current to no-load loss at rated voltage, and x is the oil index. The temperature rise of the top oil under rated load is given by k11, where k11 is a thermal model constant. The oil time constant, The top oil temperature under the current load. The ambient temperature.

[0035] After derivation, the iterative calculation formula for the transformer top oil temperature can be obtained: ; Among them, the initial value of the top layer oil temperature It can be obtained from the following formula: .

[0036] Based on the international standard GB / T1094.7, this application's embodiments derive the discrete-time iterative form through difference equations. Iterative calculations can efficiently process continuous time series data, reducing computational complexity. Furthermore, by using historical temperature values ​​to recursively deduce the current state, the stability of the model under dynamic load conditions is improved. In addition, parameters in the formula, such as the oil index and thermal model constants, can be calibrated with actual data, enhancing the model's generalization ability.

[0037] In one embodiment, since the values ​​of thermal model constants, oil index, and oil time constant given in the guidelines are all empirical values, their applicability to different transformers is low. An inverse problem method is used to solve for these parameters using measured top oil temperature and ambient temperature, thereby calculating the transformer's load factor and load current inversely based on the temperature values. Since the focus is on early-stage overheating faults in the transformer, the top oil temperature rise does not exceed the limits given in the load guidelines. When faults such as inter-turn short circuits or winding strand breakage occur in the transformer windings, it can be assumed that the transformer's thermal model constants, oil index, and oil time constant remain unchanged. Therefore, based on the top oil temperature, ambient temperature, and load factor, an inverse problem is solved on the pre-established top oil temperature calculation model to obtain the transformer's thermal characteristic parameters, including the following steps S201 to S203: Step S201: Based on the top oil temperature calculation model, obtain the matrix equation that characterizes the relationship between the top oil temperature, ambient temperature, load factor and thermal characteristic parameters; Step S202: Substitute multiple sets of top oil temperature, ambient temperature and load factor under the steady state of the transformer into the matrix equation to obtain the overdetermined equation set; Step S203: Solve the overdetermined equations using the QR decomposition method to obtain the thermal characteristic parameters.

[0038] In application, the inverse problem solution process involves deriving a linear matrix equation from the top oil temperature calculation model. This equation establishes the mathematical relationship between the top oil temperature, ambient temperature, load factor, and thermal characteristic parameters. Then, multiple sets of continuous data collected under steady-state transformer operation, including top oil temperature, ambient temperature, and load factor sequences, are substituted into the matrix equation, forming an overdetermined system of equations with more equations than unknowns. Finally, the QR decomposition method is used to solve this overdetermined system of equations to obtain the thermal characteristic parameters k1, k2, and k3. The matrix equation construction can use the least squares fitting method, and the overdetermined system of equations can be solved using numerical computing libraries such as LAPACK for QR decomposition.

[0039] The embodiments of this application include deriving matrix equations from the model, constructing an overdetermined set of equations, and applying the QR decomposition method. The introduction of the overdetermined set of equations allows for the use of redundant data points to smooth noise, improving the robustness of parameter estimation. The QR decomposition method, as a numerically stable algorithm, effectively solves the ill-conditioned problem of the set of equations, ensuring the accuracy and reliability of the solution of thermal characteristic parameters. The entire process realizes closed-loop optimization from data to parameters.

[0040] In one embodiment, the matrix equation is: ; in , , , ;k 1. k 2. k 3 represents thermal characteristic parameters. This is the initial value of the top oil temperature. This is the initial value of the ambient temperature. For K （0） An exponential function of variables. K （0） This is the initial value of the load factor. Let the top oil temperature be the temperature in the k-th time period. The top oil temperature is the temperature of the top layer in the (k-1)th time period. Let K be the ambient temperature during the (k-1)th time period. To calculate the k-th time period with K （k） An exponential function of variables. To calculate the (k-1)th time period, K （k-1） Let be an exponential function of variables, K be the load factor, R be the ratio of load loss at rated current to no-load loss at rated voltage, and x be the oil exponent. The top oil temperature rise under rated load, These are thermal model constants. The oil time constant, For the time period, k can be any natural number from 2 to n, and n is the upper limit of the preset time period value. The top oil temperature for the first time period. The top oil temperature for the second time period. The ambient temperature for the first time period. For the first time period K （1） An exponential function with variable .

[0041] In application, the iterative calculation formula for the transformer top oil temperature is derived to obtain the relationship between the top oil temperature, ambient temperature, load factor, and transformer thermal characteristic parameters: ; in , , , .

[0042] When the transformer is operating normally, k1, k2, and k3 can be considered constants. Since most existing large transformers are equipped with top oil temperature monitoring devices, the values ​​of k1, k2, and k3 can be calculated using the ambient temperature and the top oil temperature.

[0043] To calculate the values ​​of k1, k2, and k3, the relationships between top oil temperature, ambient temperature, load factor, and transformer thermal characteristic parameters are simplified into matrix equations: .

[0044] To accurately obtain the values ​​of k1, k2, and k3, multiple sets of continuous top-layer oil temperature, ambient temperature, and load factor under the steady-state state of the transformer are selected and substituted into the matrix equations to form an overdetermined set of equations.

[0045] This application provides a specific mathematical expression of the matrix equation, clarifying the linear relationship between top oil temperature, ambient temperature, load-related terms, and thermal characteristic parameters. The matrix form simplifies complex physical relationships into a computable structure, facilitating software implementation and batch data processing. At the same time, the introduction of variables such as the W term in the equation directly relates to the load current, simplifying the parameter inversion process and enhancing the deployability of the method in real-time systems.

[0046] In one embodiment, since the number of equations in the overdetermined system is greater than the number of unknowns, it exhibits ill-conditioned behavior and cannot be directly inverted. Therefore, the QS decomposition method is used to solve the overdetermined system of equations. The step of using the QR decomposition method to solve the overdetermined system of equations to obtain the thermal characteristic parameters includes the following steps S301 to S304: Step S301: Express the matrix equation in the form A=B×T, where A is an N×1 matrix including the top oil temperature value of a preset time period, B is an N×3 matrix including the top oil temperature, ambient temperature and load-related terms of the corresponding time period, and T is the thermal characteristic parameter matrix to be solved.

[0047] In application, , , .

[0048] Step S302: Perform QR decomposition on matrix B, decomposing it into an orthogonal matrix Q and an upper triangular matrix S, such that B = Q × S.

[0049] In applications, introducing orthogonal transformations can effectively reduce the ill-conditioned nature of the equation system, thereby improving the stability and accuracy of the solution.

[0050] Step S303: Transform the original equation A=B×T into the form Q×S×T=A through orthogonal transformation.

[0051] Step S304: Utilize the triangular properties of the upper triangular matrix S to solve for the thermal characteristic parameters in the thermal characteristic parameter matrix T step by step using the back substitution method.

[0052] In application, the QR decomposition method is used to solve the overdetermined equation system, which includes expressing the matrix equation as A = B × T, where A is an N×1 matrix composed of top oil temperature values, B is an N×3 design matrix composed of top oil temperature, ambient temperature and load-related terms for the corresponding time period, and T is the matrix of thermal characteristic parameters to be determined.

[0053] The matrix B is decomposed using QR decomposition. This can be achieved through the Gram-Schmidt process or Householder transformation, resulting in an orthogonal matrix Q and an upper triangular matrix S such that B = Q × S. Then, the original equation is transformed into the form Q × S × T = A using an orthogonal transformation. The orthogonality of Q simplifies the equation. Finally, leveraging the triangular properties of the upper triangular matrix S, a back-substitution method is used to progressively solve for the parameters in the thermal characteristic parameter matrix T, starting from the last row. QR decomposition reduces computational errors, while the back-substitution method improves solution efficiency.

[0054] The embodiments of this application include decomposing the matrix into an orthogonal matrix and an upper triangular matrix, and solving it using the back substitution method. The orthogonal transformation reduces numerical errors in the calculation process and improves the stability of the algorithm in a finite-precision calculation environment. The back substitution method solves the parameters step by step, avoiding the instability of matrix inversion and ensuring the continuity of thermal characteristic parameter output. This method is particularly suitable for resource-constrained scenarios in embedded systems.

[0055] In one embodiment, the theoretical load current is calculated using the following formula: ; ; I s = K (k) × I ; in, To calculate the k-th time period with K （k） An exponential function of variables. K （k） Let be the load factor for the k-th time period. The top oil temperature is the temperature of the (k+1)th time period. Let the top oil temperature be the temperature in the k-th time period. Let be the ambient temperature during the k-th time period. k 1. k 2. k 3 represents thermal characteristic parameters. I Rated current, I s This is the theoretical load current.

[0056] In applications, when a transformer experiences a short circuit between winding turns or a broken strand in the winding, the transformer load loss changes significantly. Ignoring changes in parameters such as the internal thermal conductivity coefficient of the transformer, the matrix equation is further derived to obtain the theoretical load current calculation formula as shown above.

[0057] This application provides an inversion calculation formula for theoretical load current, which directly derives the current value from thermal characteristic parameters and temperature data, eliminating intermediate conversion steps and realizing a rapid mapping from temperature to current, reducing calculation delay. At the same time, the inversion process is based on measured temperature, reducing dependence on additional sensors and improving the economy and practicality of the fault identification system.

[0058] It should be understood that the sequence number of each step in the above embodiments does not imply the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of this application.

[0059] To illustrate the temperature inversion-based transformer overheating fault identification method provided in the above embodiments, the following example uses overheating fault test data of a transformer for identification. This transformer is a 500kV single-phase transformer scaled down at a 10:1 ratio, with a rated capacity of 2000kVA and a rated voltage (kV) of 13.48 / 1.8. The ratio of load loss at rated current to no-load loss at rated voltage is 9.34. The transformer is continuously subjected to a load of 0.54 times its rated current from a cooling state until steady state. Subsequently, at 420, 520, and 590 minutes, abnormal heat sources of 500W, 1000W, and 2000W are applied to the upper non-inductive coil to simulate an internal overheating fault in the transformer and obtain relevant temperature data. The execution flow of this method is as follows: S1. Based on the empirical model proposed in the load guidelines for oil-immersed power transformers, an iterative calculation method for the top-layer oil temperature of the transformer is derived, specifically including: According to the iterative calculation formula for the top oil temperature of the transformer: ; Collect relevant real-time data of the transformer, including top oil temperature, ambient temperature, and load factor, and set Dt to 1 minute, with the oil index x reference load guideline set to 0.8. The relevant data are shown in Table 1 below: Table 1 The calculated value of the transformer top-layer oil temperature was obtained based on the above iterative calculation formula. This value was then compared with the measured value to verify the correctness of the method. Figure 4 As shown, when no overheating fault occurs, the calculated value of the top oil temperature is basically consistent with the measured value, verifying the correctness of this method.

[0060] S2. Based on the relationship model between top oil temperature, ambient temperature, load factor and transformer thermal characteristic parameters, multiple sets of continuous top oil temperature, ambient temperature and load factor under normal transformer conditions are substituted into the matrix equation to form an overdetermined equation set. The QR decomposition method is used to solve the overdetermined equation set to obtain the corresponding transformer thermal characteristic parameters k1, k2, k3.

[0061] Seventy sets of data from 280 to 350 minutes were collected and substituted into the matrix equations to form an overdetermined system of equations. QR decomposition was performed, yielding k1, k2, and k3 values ​​of 0.266, 2.583, and -2.989, respectively. The sum of squared residuals is 14.85, and the residual norm is 3.85. This indicates that, under this solution, the calculated top-layer oil temperature deviates from the measured value by less than 0.44℃, meeting the calculation requirements.

[0062] S3. Substituting the obtained transformer thermal characteristic parameters k1, k2, and k3 into the theoretical load current calculation formula, the load factor of the transformer under its current state can be calculated. Details are as follows: Data from 100 to 900 minutes was collected, substituted into the theoretical load current calculation formula, and the transformer load current value was obtained. This value was then compared with the measured value, and the relative error was calculated as follows: Figure 5 As shown.

[0063] As shown in the figure, when the transformer enters steady state (300-420 min), the relative error of its load current is less than 4%. At 420 min, an overheating fault with an energy of 500W occurs. After 50 min, the relative error of its load current is greater than 4%.

[0064] Based on the above results, when using this method to determine transformer overheating faults, the relative error threshold of the load current is set to 4%, and the response time is 50 minutes when the fault energy is 9% of the transformer load.

[0065] This application also provides a transformer overheating fault identification device based on temperature inversion, used to execute the steps in the above-described embodiments of the transformer overheating fault identification method based on temperature inversion. The transformer overheating fault identification device based on temperature inversion can be a virtual appliance in an electronic device, run by the processor of the electronic device, or it can be the electronic device itself.

[0066] like Figure 6 As shown in the embodiment of this application, the transformer overheating fault identification device 100 based on temperature inversion includes: The data acquisition module 101 is used to acquire real-time monitoring data of the transformer, including top oil temperature, ambient temperature and load factor. The thermal characteristic parameter calculation module 102 is used to solve the inverse problem of the pre-established top oil temperature calculation model based on the top oil temperature, ambient temperature and load factor to obtain the thermal characteristic parameters of the transformer. The load current calculation module 103 is used to calculate the theoretical load current of the transformer based on the thermal characteristic parameters. The fault judgment module 104 is used to determine that the transformer has an overheating fault if the deviation between the theoretical load current and the measured load current exceeds a preset deviation threshold.

[0067] In one embodiment, the top oil temperature calculation model is expressed as: ; Where K is the load factor, R is the ratio of load loss at rated current to no-load loss at rated voltage, and x is the oil index. The top oil temperature rise under rated load, These are thermal model constants. The oil time constant, For ambient temperature, For a period of time, Let the top oil temperature be the temperature in the nth time period. This represents the top oil temperature during the (n-1)th time period.

[0068] In one embodiment, the thermal characteristic parameter calculation module is further configured to: Based on the top oil temperature calculation model, a matrix equation is obtained to characterize the relationship between the top oil temperature, ambient temperature, load factor, and thermal characteristic parameters. Substituting multiple sets of top oil temperature, ambient temperature, and load factor under the steady-state condition of the transformer into the matrix equation, we obtain an overdetermined set of equations. The QR decomposition method was used to solve the overdetermined equations to obtain the thermal characteristic parameters.

[0069] In one embodiment, the matrix equation is: ; in , , , ; k 1. k 2. k 3 represents thermal characteristic parameters. This is the initial value of the top oil temperature. This is the initial value of the ambient temperature. For K （0） An exponential function of variables. K（0） This is the initial value of the load factor. Let the top oil temperature be the temperature in the k-th time period. The top oil temperature is the temperature of the top layer in the (k-1)th time period. Let K be the ambient temperature during the (k-1)th time period. To calculate the k-th time period with K （k） An exponential function of variables. To calculate the (k-1)th time period, K （k-1） Let be an exponential function of variables, K be the load factor, R be the ratio of load loss at rated current to no-load loss at rated voltage, and x be the oil exponent. The top oil temperature rise under rated load, These are thermal model constants. The oil time constant, For the time period, k can be any natural number from 2 to n, and n is the upper limit of the preset time period value.

[0070] In one embodiment, the thermal characteristic parameter calculation module is further configured to: The matrix equation is expressed as A=B×T, where A is an N×1 matrix including the top oil temperature value for a preset time period, B is an N×3 matrix including the top oil temperature, ambient temperature and load-related terms for the corresponding time period, and T is the thermal characteristic parameter matrix to be solved. Perform QR decomposition on matrix B, decomposing it into an orthogonal matrix Q and an upper triangular matrix S, such that B = Q × S; The original equation A=B×T is transformed into the form Q×S×T=A through orthogonal transformation; By utilizing the triangular properties of the upper triangular matrix S, the thermal characteristic parameters in the thermal characteristic parameter matrix T are solved step by step using the back substitution method.

[0071] In one embodiment, the theoretical load current is calculated using the following formula: ; ; I s = K (k) × I ; in, To calculate the k-th time period with K （k） An exponential function of variables. K （k） Let be the load factor for the k-th time period. The top oil temperature is the temperature of the (k+1)th time period. Let the top oil temperature be the temperature in the k-th time period. Let be the ambient temperature during the k-th time period. k 1. k 2. k 3 represents thermal characteristic parameters. I Rated current, I s This is the theoretical load current.

[0072] In applications, the modules in the transformer overheating fault identification device based on temperature inversion can be software program modules, or they can be implemented by different logic circuits integrated in a processor, or they can be implemented by multiple distributed processors.

[0073] like Figure 7 As shown, this application embodiment also provides an electronic device 200, including: at least one processor 201 ( Figure 7 The diagram shows only one processor, memory 202, and computer program 203 stored in memory 202 and executable on at least one processor 201. When processor 201 executes computer program 203, it implements the steps in the various method embodiments described above.

[0074] In applications, electronic devices may include, but are not limited to, processors and memory. Those skilled in the art will understand that... Figure 7 This is merely an example of an electronic device and does not constitute a limitation on the electronic device. It may include more or fewer components than shown, or a combination of certain components, or different components.

[0075] In applications, the processor can be a Central Processing Unit (CPU), but it can also be other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general-purpose processor can be a microprocessor or any conventional processor.

[0076] In applications, memory can be an internal storage unit of an electronic device in some embodiments, such as a hard drive or RAM. In other embodiments, memory can be an external storage device of the electronic device, such as a plug-in hard drive, Smart Media Card (SMC), Secure Digital (SD) card, or Flash Card. Furthermore, memory can include both internal and external storage units of the electronic device. Memory is used to store operating systems, applications, bootloaders, data, and other programs, such as program code for computer programs. Memory can also be used to temporarily store data that has been output or will be output.

[0077] It should be noted that the information interaction and execution process between the above-mentioned devices / units are based on the same concept as the method embodiments of this application. For details on their specific functions and technical effects, please refer to the method embodiments section, and they will not be repeated here.

[0078] Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the above-described division of functional units and modules is merely an example. In practical applications, the above functions can be assigned to different functional units and modules as needed, that is, the internal structure of the device can be divided into different functional units or modules to complete all or part of the functions described above. The functional units and modules in the embodiments can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit. Furthermore, the specific names of the functional units and modules are only for easy differentiation and are not intended to limit the scope of protection of this application. The specific working process of the units and modules in the above system can be referred to the corresponding process in the foregoing method embodiments, and will not be repeated here.

[0079] This application also provides a computer-readable storage medium storing a computer program, which, when executed by a processor, implements the steps described in the various method embodiments above.

[0080] This application provides a computer program product, including a computer program, which, when run on an electronic device, enables the electronic device to perform the steps described in the various method embodiments above.

[0081] If the integrated unit is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, all or part of the processes in the methods of the above embodiments of this application can be implemented by a computer program instructing related hardware. The computer program can be stored in a computer-readable storage medium, and when executed by a processor, it can implement the steps of the various method embodiments described above. The computer program includes computer program code, which can be in the form of source code, object code, executable files, or certain intermediate forms. A computer-readable medium can include at least: any entity or device capable of carrying computer program code to a device / electronic device, a recording medium, a computer memory, a read-only memory (ROM), a random access memory (RAM), an electrical carrier signal, a telecommunication signal, and a software distribution medium. Examples include USB flash drives, portable hard drives, magnetic disks, or optical disks. In some jurisdictions, according to legislation and patent practice, computer-readable media cannot be electrical carrier signals or telecommunication signals.

[0082] In the above embodiments, the descriptions of each embodiment have different focuses. For parts that are not described in detail or recorded in a certain embodiment, please refer to the relevant descriptions of other embodiments.

[0083] Those skilled in the art will recognize that the units and algorithm steps of the various examples described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this application.

[0084] In the embodiments provided in this application, it should be understood that the disclosed apparatus and methods can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative. For instance, the division of modules or units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be through some interfaces; the indirect coupling or communication connection between apparatuses or units may be electrical, mechanical, or other forms.

[0085] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0086] The above embodiments are only used to illustrate the technical solutions of this application, and are not intended to limit them. Although this application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features. Such modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of this application, and should all be included within the protection scope of this application.

Claims

1. A method for identifying transformer overheating faults based on temperature inversion, characterized in that, include: Acquire real-time monitoring data of the transformer, including top oil temperature, ambient temperature, and load factor; Based on the top oil temperature, ambient temperature, and load factor, the inverse problem of the pre-established top oil temperature calculation model is solved to obtain the thermal characteristic parameters of the transformer. Based on the aforementioned thermal characteristic parameters, the theoretical load current of the transformer is calculated; If the deviation between the theoretical load current and the measured load current exceeds a preset deviation threshold, then the transformer is determined to have an overheating fault.

2. The transformer overheating fault identification method based on temperature inversion as described in claim 1, characterized in that, The top oil temperature calculation model is expressed as follows: ； Where K is the load factor, R is the ratio of load loss at rated current to no-load loss at rated voltage, and x is the oil index. The top oil temperature rise under rated load, These are thermal model constants. The oil time constant, For ambient temperature, For a period of time, Let the top oil temperature be the temperature in the nth time period. This represents the top oil temperature during the (n-1)th time period.

3. The transformer overheating fault identification method based on temperature inversion as described in claim 1, characterized in that, Based on the top oil temperature, ambient temperature, and load factor, the inverse problem of the pre-established top oil temperature calculation model is solved to obtain the transformer's thermal characteristic parameters, including: Based on the top oil temperature calculation model, a matrix equation is obtained to characterize the relationship between the top oil temperature, ambient temperature, load factor, and thermal characteristic parameters. Substituting multiple sets of top oil temperature, ambient temperature, and load factor under the steady-state condition of the transformer into the matrix equation, we obtain an overdetermined set of equations. The QR decomposition method was used to solve the overdetermined equations to obtain the thermal characteristic parameters.

4. The transformer overheating fault identification method based on temperature inversion as described in claim 3, characterized in that, The matrix equation is: ； in , , , ; k 1. k 2. k 3 represents thermal characteristic parameters. This is the initial value of the top oil temperature. This is the initial value of the ambient temperature. For K （0） An exponential function of variables. K （0） This is the initial value of the load factor. Let the top oil temperature be the temperature in the k-th time period. The top oil temperature is the temperature of the top layer in the (k-1)th time period. Let K be the ambient temperature during the (k-1)th time period. To calculate the k-th time period with K （k） An exponential function of variables. To calculate the (k-1)th time period, K （k-1） Let be an exponential function of variables, K be the load factor, R be the ratio of load loss at rated current to no-load loss at rated voltage, and x be the oil exponent. The top oil temperature rise under rated load, These are thermal model constants. The oil time constant, For the time period, k can be any natural number from 2 to n, and n is the upper limit of the preset time period value.

5. The transformer overheating fault identification method based on temperature inversion as described in claim 3 or 4, characterized in that, The method of solving the overdetermined equations using QR decomposition to obtain the thermal characteristic parameters includes: The matrix equation is expressed as A=B×T, where A is an N×1 matrix including the top oil temperature value for a preset time period, B is an N×3 matrix including the top oil temperature, ambient temperature and load-related terms for the corresponding time period, and T is the thermal characteristic parameter matrix to be solved. Perform QR decomposition on matrix B, decomposing it into an orthogonal matrix Q and an upper triangular matrix S, such that B = Q × S; The original equation A=B×T is transformed into the form Q×S×T=A through orthogonal transformation; By utilizing the triangular properties of the upper triangular matrix S, the thermal characteristic parameters in the thermal characteristic parameter matrix T are solved step by step using the back substitution method.

6. The transformer overheating fault identification method based on temperature inversion as described in claim 1, characterized in that, The theoretical load current is calculated using the following formula: ； ； I s = K (k) × I ； in, To calculate the k-th time period with K （k） An exponential function of variables. K （k） Let be the load factor for the k-th time period. The top oil temperature is the temperature of the (k+1)th time period. Let the top oil temperature be the temperature in the k-th time period. Let be the ambient temperature during the k-th time period. k 1. k 2. k 3 represents thermal characteristic parameters. I Rated current, I s denoted as the theoretical load current, and x as the oil index.

7. A transformer overheating fault identification device based on temperature inversion, characterized in that, include: The data acquisition module is used to acquire real-time monitoring data of the transformer, including top oil temperature, ambient temperature, and load factor. The thermal characteristic parameter calculation module is used to solve the inverse problem of the pre-established top oil temperature calculation model based on the top oil temperature, ambient temperature and load factor, so as to obtain the thermal characteristic parameters of the transformer. The load current calculation module is used to calculate the theoretical load current of the transformer based on the thermal characteristic parameters. The fault diagnosis module is used to determine that the transformer has an overheating fault if the deviation between the theoretical load current and the measured load current exceeds a preset deviation threshold.

8. The transformer overheating fault identification device based on temperature inversion as described in claim 7, characterized in that, The top oil temperature calculation model is expressed as follows: ； Where K is the load factor, R is the ratio of load loss at rated current to no-load loss at rated voltage, and x is the oil index. The top oil temperature rise under rated load, These are thermal model constants. The oil time constant, For ambient temperature, For a period of time, Let the top oil temperature be the temperature in the nth time period. This represents the top oil temperature during the (n-1)th time period.

9. The transformer overheating fault identification device based on temperature inversion as described in claim 7, characterized in that, The thermal characteristic parameter calculation module is also used for: Based on the top oil temperature calculation model, a matrix equation is obtained to characterize the relationship between the top oil temperature, ambient temperature, load factor, and thermal characteristic parameters. Substituting multiple sets of top oil temperature, ambient temperature, and load factor under the steady-state condition of the transformer into the matrix equation, we obtain an overdetermined set of equations. The QR decomposition method was used to solve the overdetermined equations to obtain the thermal characteristic parameters.

10. The transformer overheating fault identification device based on temperature inversion as described in claim 9, characterized in that, The matrix equation is: ； in , , , ; k 1. k 2. k 3 represents thermal characteristic parameters. This is the initial value of the top oil temperature. This is the initial value of the ambient temperature. For K （0） An exponential function of variables. K （0） This is the initial value of the load factor. Let the top oil temperature be the temperature in the k-th time period. The top oil temperature is the temperature of the top layer in the (k-1)th time period. Let K be the ambient temperature during the (k-1)th time period. To calculate the k-th time period with K （k） An exponential function of variables. To calculate the (k-1)th time period, K （k-1） Let be an exponential function of variables, K be the load factor, R be the ratio of load loss at rated current to no-load loss at rated voltage, and x be the oil exponent. The top oil temperature rise under rated load, These are thermal model constants. The oil time constant, For the time period, k can be any natural number from 2 to n, and n is the upper limit of the preset time period value.

11. The transformer overheating fault identification device based on temperature inversion as described in claim 9 or 10, characterized in that, The thermal characteristic parameter calculation module is also used for: The matrix equation is expressed as A=B×T, where A is an N×1 matrix including the top oil temperature value for a preset time period, B is an N×3 matrix including the top oil temperature, ambient temperature and load-related terms for the corresponding time period, and T is the thermal characteristic parameter matrix to be solved. Perform QR decomposition on matrix B, decomposing it into an orthogonal matrix Q and an upper triangular matrix S, such that B = Q × S; The original equation A=B×T is transformed into the form Q×S×T=A through orthogonal transformation; By utilizing the triangular properties of the upper triangular matrix S, the thermal characteristic parameters in the thermal characteristic parameter matrix T are solved step by step using the back substitution method.

12. The transformer overheating fault identification device based on temperature inversion as described in claim 7, characterized in that, The theoretical load current is calculated using the following formula: ； ； I s = K (k) × I ； in, To calculate the k-th time period with K （k） An exponential function of variables. K （k） Let be the load factor for the k-th time period. The top oil temperature is the temperature of the (k+1)th time period. Let the top oil temperature be the temperature in the k-th time period. Let be the ambient temperature during the k-th time period. k 1. k 2. k 3 represents thermal characteristic parameters. I Rated current, I s denoted as the theoretical load current, and x as the oil index.

13. An electronic device, characterized in that, The device includes a processor, a memory, and a computer program stored in the memory and executable on the processor, characterized in that, when the processor executes the computer program, the electronic device performs the method as described in any one of claims 1-6.

14. A computer-readable storage medium storing a computer program, characterized in that, A computer-readable storage medium stores a computer program that, when executed by a processor, implements the steps of the method as described in any one of claims 1 to 6.

Images