Transformer thermal aging degree monitoring device and related device

By constructing the mapping relationship between the transformer hotspot temperature and load rate and ambient temperature, combined with the deep learning model, the thermal aging degree of transformer is monitored in real time, and the problem of untimely thermal aging monitoring in the existing technology is solved, real-time monitoring of the thermal aging degree of transformer is achieved and early warning improve the safety and stability of the power system and equipment life.

CN119066958APending Publication Date: 2024-12-03YUNNAN POWER GRID CO LTD ELECTRIC POWER RES INST
View PDF 0 Cites 1 Cited by

Patent Information

Application Number
CN202411074621.4
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-08-07
Publication Date
2024-12-03

AI Technical Summary

Technical Problem

In the prior art, the thermal aging monitoring of transformers is not timely, resulting in a shortening of the life of power equipment, a decrease in the power supply quality and reliability of the power grid, affecting the safe and stable operation of the power system.

Method used

By constructing the mapping relationship between the hot spot temperature, load rate and ambient temperature when the transformer to be tested does not have thermal aging, as well as the mapping relationship between the actual hot spot temperature and the top oil temperature, combined with the deep learning model, the thermal aging degree of the transformer is calculated. , obtain the actual load rate, ambient temperature and top oil temperature, monitor the degree of thermal aging in real time based on the objective function, and judge whether to make an early warning based on the early warning threshold.

Benefits of technology

Real-time monitoring of the thermal aging degree of transformers is realized, which facilitates detection of thermal aging, improves the safety and stability of the power system, extends the equipment life and reduces economic costs.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN119066958A_ABST
    Figure CN119066958A_ABST
Patent Text Reader

Abstract

The embodiment of the invention discloses a transformer thermal aging degree monitoring method and a related device, and the method comprises the steps: constructing a mapping relation among the thermal aging degree, the load rate, the environment temperature and the top oil temperature of a to-be-detected transformer through combining a first function and a second function, and obtaining a target function, the first function represents a mapping relation among the hot-spot temperature, the load rate and the environment temperature when the to-be-tested transformer is not subjected to thermal aging, and the second function represents a mapping relation between the actual hot-spot temperature and the top oil temperature of the to-be-tested transformer, and obtaining the actual load rate, the actual environment temperature and the actual top oil temperature of the to-be-tested transformer; and according to the actual load rate, the actual environment temperature and the actual top oil temperature, calculating the thermal aging degree of the to-be-tested transformer based on the objective function. According to the invention, the thermal aging condition of the transformer can be conveniently detected, and the thermal aging degree of the transformer can be monitored in real time.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention relates to the technical field of transformers, and in particular to a transformer thermal aging degree monitoring device and related devices. Background Art

[0003] As an important energy conversion equipment in the power grid, oil-immersed power transformers still have problems such as overload, local overheating and thermal aging, which shorten the remaining life of power equipment and reduce economic benefits. In addition, the deepening of the thermal aging of the transformer will reduce the performance of the transformer's power transmission, affecting the power supply quality and reliability of the entire power grid. If the thermal aging of the transformer is not detected in time, it will inevitably have a certain impact on the safe and stable operation of the power system. In order to adapt to the increasingly complex power grid regulation needs, it is necessary to monitor the thermal aging of the transformer in a timely manner. Summary of the invention

[0004] The main purpose of the present invention is to provide a method, device, computer equipment and storage medium for monitoring the thermal aging degree of a transformer, which can solve the problem of untimely monitoring of thermal aging of transformers in the prior art.

[0005] To achieve the above object, the present invention provides a method for monitoring thermal aging degree of a transformer in a first aspect, the method comprising:

[0006] Constructing a mapping relationship between the hot spot temperature, load rate and ambient temperature of the transformer to be tested when thermal aging has not occurred, to obtain a first function, and constructing a mapping relationship between the actual hot spot temperature of the transformer to be tested and the top oil temperature, to obtain a second function; wherein the first function is used to calculate the hot spot temperature of the transformer to be tested when thermal aging has not occurred, and the second function is used to calculate the actual hot spot temperature of the transformer to be tested;

[0007] Combining the first function and the second function, constructing a mapping relationship between the thermal aging degree, load rate, ambient temperature and top oil temperature of the transformer to be tested, and obtaining an objective function; the objective function is used to calculate the thermal aging degree of the transformer to be tested;

[0008] The actual load rate, actual ambient temperature and actual top oil temperature of the transformer to be tested are obtained, and the thermal aging degree of the transformer to be tested is calculated based on the objective function according to the actual load rate, actual ambient temperature and actual top oil temperature.

[0009] In combination with the first aspect, in a possible implementation, the mapping relationship between the hot spot temperature, load rate and ambient temperature when the transformer to be tested has not been thermally aged is constructed to obtain a first function, and the mapping relationship between the actual hot spot temperature of the transformer to be tested and the top oil temperature is constructed to obtain a second function, including:

[0010] Obtain a first sample training set and a second sample training set; the first sample training set includes different load rates, different ambient temperatures and hot spot temperatures at the different load rates and different ambient temperatures when the transformer to be tested has not aged, and the second sample training set includes the hot spot temperatures and top oil temperatures at the different load rates and different ambient temperatures;

[0011] The first deep learning model is trained using the target load rate and the target ambient temperature in the first sample training set as input features of the preset first deep learning model, and the target hotspot temperature corresponding to the target load rate and the target ambient temperature in the first sample training set is used as the output feature of the first deep learning model to obtain a first function; wherein the target load rate is any load rate in the first sample training set, and the target ambient temperature is an ambient temperature that has a corresponding relationship with the target load rate;

[0012] The second deep learning model is trained using the target top layer oil temperature in the second sample training set as the input feature of the preset second deep learning model and the target hot spot temperature corresponding to the target top layer oil temperature in the second sample training set as the output feature of the second deep learning model to obtain a second function; wherein the target top layer oil temperature is any top layer oil temperature in the second sample training set, and the target hot spot temperature is a hot spot temperature that has a corresponding relationship with the target top layer oil temperature.

[0013] In combination with the first aspect, in a possible implementation manner, the first function expression is:

[0014]

[0015] Among them, T E represents the hot spot temperature of the transformer under test when thermal aging does not occur, m is the number of hidden layer nodes of the first deep learning model; i represents the sequence number of the hidden layer node of the first deep learning model, ω i , γ i are the weights corresponding to the hidden layer nodes respectively.

[0016] In combination with the first aspect, in a possible implementation manner, the second function expression is:

[0017]

[0018] Among them, T R represents the actual hot spot temperature of the transformer to be tested, n is the number of hidden layer nodes of the second deep learning model; j represents the sequence number of the hidden layer node of the second deep learning model, σ j and j are the weights corresponding to the hidden layer nodes respectively.

[0019] In combination with the first aspect, in a possible implementation, the first function and the second function are combined to construct a mapping relationship between the thermal aging degree, load rate, ambient temperature and top oil temperature of the transformer to be tested, and an objective function is obtained, including:

[0020]

[0021] Where V represents the thermal aging degree of the transformer to be tested, T E Indicates the hot spot temperature of the transformer under test when no thermal aging occurs, T R Indicates the actual hot spot temperature of the transformer under test.

[0022] In combination with the first aspect, in a possible implementation manner, the obtaining of the first sample training set and the second sample training set includes:

[0023] Obtain the core loss and winding loss corresponding to the transformer to be tested at different load rates; based on the core loss and winding loss, calculate the hot spot temperature and top oil temperature of the transformer to be tested at different ambient temperatures, and obtain the hot spot temperature and top oil temperature of the transformer to be tested at different load rates and different ambient temperatures;

[0024] Based on the different load rates, the different ambient temperatures, and the hotspot temperatures and top oil temperatures at the different load rates and the different ambient temperatures, a first sample training set and a second sample training set are constructed.

[0025] In combination with the first aspect, in a possible implementation manner, after calculating the thermal aging degree of the transformer to be tested based on the objective function, the method further includes:

[0026] According to the thermal aging degree and the thermal aging degree warning threshold, it is determined whether to issue a warning for the transformer to be tested.

[0027] In combination with the first aspect, in a possible implementation manner, judging whether to issue an early warning for the transformer to be tested according to the thermal aging degree and the thermal aging degree early warning threshold includes:

[0028] If the thermal aging degree is greater than the thermal aging degree warning threshold, a warning is issued for the transformer to be tested;

[0029] If the thermal aging degree is not greater than the thermal aging degree warning threshold, no warning is issued for the transformer to be tested.

[0030] To achieve the above object, the second aspect of the present invention provides a transformer thermal aging degree monitoring device, the device comprising:

[0031] The first construction module is used to construct a mapping relationship between the hot spot temperature, load rate and ambient temperature of the transformer to be tested when thermal aging has not occurred, to obtain a first function, and to construct a mapping relationship between the actual hot spot temperature of the transformer to be tested and the top oil temperature, to obtain a second function; wherein the first function is used to calculate the hot spot temperature of the transformer to be tested when thermal aging has not occurred, and the second function is used to calculate the actual hot spot temperature of the transformer to be tested;

[0032] The second construction module is used to combine the first function and the second function to construct a mapping relationship between the thermal aging degree, load rate, ambient temperature and top oil temperature of the transformer to be tested, and obtain an objective function; the objective function is used to calculate the thermal aging degree of the transformer to be tested;

[0033] Calculation module: used to obtain the actual load rate, actual ambient temperature and actual top oil temperature of the transformer to be tested, and calculate the thermal aging degree of the transformer to be tested based on the objective function according to the actual load rate, actual ambient temperature and actual top oil temperature.

[0034] To achieve the above object, the third aspect of the present invention provides a computer-readable storage medium storing a computer program, wherein when the computer program is executed by a processor, the processor performs the following steps:

[0035] Constructing a mapping relationship between the hot spot temperature, load rate and ambient temperature of the transformer to be tested when thermal aging has not occurred, to obtain a first function, and constructing a mapping relationship between the actual hot spot temperature of the transformer to be tested and the top oil temperature, to obtain a second function; wherein the first function is used to calculate the hot spot temperature of the transformer to be tested when thermal aging has not occurred, and the second function is used to calculate the actual hot spot temperature of the transformer to be tested;

[0036] Combining the first function and the second function, constructing a mapping relationship between the thermal aging degree, load rate, ambient temperature and top oil temperature of the transformer to be tested, and obtaining an objective function; the objective function is used to calculate the thermal aging degree of the transformer to be tested;

[0037] The actual load rate, actual ambient temperature and actual top oil temperature of the transformer to be tested are obtained, and the thermal aging degree of the transformer to be tested is calculated based on the objective function according to the actual load rate, actual ambient temperature and actual top oil temperature.

[0038] To achieve the above object, a fourth aspect of the present invention provides a computer device, comprising a memory and a processor, wherein the memory stores a computer program, and when the computer program is executed by the processor, the processor performs the following steps:

[0039] Constructing a mapping relationship between the hot spot temperature, load rate and ambient temperature of the transformer to be tested when thermal aging has not occurred, to obtain a first function, and constructing a mapping relationship between the actual hot spot temperature of the transformer to be tested and the top oil temperature, to obtain a second function; wherein the first function is used to calculate the hot spot temperature of the transformer to be tested when thermal aging has not occurred, and the second function is used to calculate the actual hot spot temperature of the transformer to be tested;

[0040] Combining the first function and the second function, constructing a mapping relationship between the thermal aging degree, load rate, ambient temperature and top oil temperature of the transformer to be tested, and obtaining an objective function; the objective function is used to calculate the thermal aging degree of the transformer to be tested;

[0041] The actual load rate, actual ambient temperature and actual top oil temperature of the transformer to be tested are obtained, and the thermal aging degree of the transformer to be tested is calculated based on the objective function according to the actual load rate, actual ambient temperature and actual top oil temperature.

[0042] The embodiments of the present invention have the following beneficial effects:

[0043] The present invention provides a method for monitoring the thermal aging degree of a transformer. By combining a first function and a second function, a mapping relationship between the thermal aging degree, load rate, ambient temperature and top oil temperature of a transformer to be tested is constructed to obtain a target function, and the actual load rate, actual ambient temperature and actual top oil temperature of the transformer to be tested are obtained. According to the actual load rate, actual ambient temperature and actual top oil temperature, the thermal aging degree of the transformer to be tested is calculated based on the target function. Indicators such as load rate, actual ambient temperature and actual top oil temperature are easy to detect. According to indicators such as load rate, actual ambient temperature and actual top oil temperature, the thermal aging degree is predicted, and the thermal aging of the transformer can be easily detected, and real-time monitoring of the thermal aging degree of the transformer can be realized. BRIEF DESCRIPTION OF THE DRAWINGS

[0044] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0045] in:

[0046] Figure 1 A schematic diagram of a flow chart of a method for monitoring thermal aging degree of a transformer according to an embodiment of the present invention;

[0047] Figure 2 A detailed flow chart of a method for monitoring thermal aging degree of a transformer in an embodiment of the present invention;

[0048] Figure 3 A flowchart of a method for obtaining a training set in an embodiment of the present invention;

[0049] Figure 4 This is a structural block diagram of a transformer thermal aging degree monitoring device in an embodiment of the present invention;

[0050] Figure 5 4 is a structural block diagram of a computer device in an embodiment of the present invention. DETAILED DESCRIPTION

[0051] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0052] The embodiment of the present invention provides a method for monitoring the thermal aging degree of a transformer. The method is applicable to any scenario of monitoring the thermal aging degree of a transformer. Figure 1 , Figure 1 A flow chart of a method for monitoring thermal aging degree of a transformer provided by an embodiment of the present invention, and combined with Figure 2 , Figure 2 A detailed flow chart of a method for monitoring thermal aging degree of a transformer provided by an embodiment of the present invention is shown in FIG. Figure 1 and Figure 2 As shown, the specific steps of this method are as follows:

[0053] Step S101, constructing a mapping relationship between the hot spot temperature, load rate and ambient temperature of the transformer under test when thermal aging has not occurred, obtaining a first function, and constructing a mapping relationship between the actual hot spot temperature of the transformer under test and the top oil temperature, obtaining a second function.

[0054] The first function is used to calculate the hot spot temperature of the transformer to be tested when thermal aging has not occurred, and the second function is used to calculate the actual hot spot temperature of the transformer to be tested.

[0055] Step S102: combining the first function and the second function, constructing a mapping relationship among the thermal aging degree, load rate, ambient temperature and top oil temperature of the transformer to be tested, and obtaining an objective function.

[0056] The objective function is used to calculate the thermal aging degree of the transformer under test.

[0057] Step S103, obtaining the actual load rate, actual ambient temperature and actual top oil temperature of the transformer to be tested, and calculating the thermal aging degree of the transformer to be tested based on the objective function according to the actual load rate, actual ambient temperature and actual top oil temperature.

[0058] In this embodiment, the first function T is constructed E =f 1 (k,T 0 ), wherein the first function represents the mapping relationship between the hot spot temperature, load rate and ambient temperature of the transformer to be tested when thermal aging has not occurred, the first function is used to calculate the hot spot temperature of the transformer to be tested when thermal aging has not occurred, and to construct the second function T R =f 2 (T oil ), the second function represents the mapping relationship between the actual hot spot temperature of the transformer to be tested and the top oil temperature, and the second function is used to calculate the actual hot spot temperature of the transformer to be tested.

[0059] In addition, the thermal aging degree of the transformer under test can be calculated by the following formula:

[0060]

[0061] Where V represents the thermal aging degree of the transformer to be tested, T E Indicates the hot spot temperature of the transformer under test when no thermal aging occurs, T R Indicates the actual hot spot temperature of the transformer under test.

[0062] Therefore, the objective function of the transformer to be tested can be constructed by combining the first function and the second function. Since the first function represents the mapping relationship between the hot spot temperature, load rate and ambient temperature when the transformer to be tested has not been thermally aged, and the second function represents the mapping relationship between the actual hot spot temperature and the top oil temperature of the transformer to be tested, the objective function can represent the mapping relationship between the thermal aging degree, load rate, ambient temperature and top oil temperature of the transformer to be tested. The objective function V=f(k,T 0 ,T oil ) is used to calculate the thermal aging degree of the transformer under test.

[0063] The objective function can be used to calculate the thermal aging degree of the transformer to be tested. Specifically, the actual load rate, actual ambient temperature and actual top oil temperature of the transformer to be tested are obtained, and the thermal aging degree of the transformer to be tested is calculated based on the objective function according to the actual load rate, actual ambient temperature and actual top oil temperature. That is, the obtained actual load rate, actual ambient temperature and actual top oil temperature are substituted into the objective function to calculate the thermal aging degree of the transformer to be tested, thereby realizing real-time monitoring of the thermal aging degree of the transformer to be tested.

[0064] In a possible implementation, the first function and the second function are constructed by a deep learning model, as shown in steps S201 to S203:

[0065] Step S201, obtaining a first sample training set and a second sample training set; the first sample training set includes different load rates, different ambient temperatures and hot spot temperatures at the different load rates and different ambient temperatures when the transformer to be tested has not aged, and the second sample training set includes the hot spot temperatures and top oil temperatures at the different load rates and different ambient temperatures.

[0066] Step S202: Use the target load rate and target ambient temperature in the first sample training set as input features of the preset first deep learning model, and use the target hotspot temperature corresponding to the target load rate and target ambient temperature in the first sample training set as output features of the first deep learning model to train the first deep learning model to obtain a first function.

[0067] The target load rate is any load rate in the first sample training set, and the target ambient temperature is an ambient temperature that has a corresponding relationship with the target load rate.

[0068] Step S203, using the target top layer oil temperature in the second sample training set as the input feature of the preset second deep learning model, and using the target hot spot temperature corresponding to the target top layer oil temperature in the second sample training set as the output feature of the second deep learning model, to train the second deep learning model to obtain a second function.

[0069] The target top layer oil temperature is any top layer oil temperature in the second sample training set, and the target hot spot temperature is a hot spot temperature that has a corresponding relationship with the target top layer oil temperature.

[0070] A first sample training set and a second sample training set are obtained, wherein the first sample training set includes different load rates, different ambient temperatures, and hotspot temperatures at the different load rates and different ambient temperatures when the transformer to be tested has not aged. Obviously, there is a corresponding relationship between the load rate, ambient temperature, and hotspot temperature in the first sample training set. The first sample training set is used to train a preset first deep learning model to construct a first function.

[0071] The second sample training set includes hot spot temperatures and top oil temperatures at different load rates and different ambient temperatures. Obviously, there is a corresponding relationship between the hot spot temperature, top oil temperature, load rate, and ambient temperature in the second sample training set. The second sample training set is used to train the preset second deep learning model to construct the second function.

[0072] The first deep learning model is trained with the target load rate and target ambient temperature in the first sample training set as the input features of the preset first deep learning model, and the target hotspot temperature corresponding to the target load rate and target ambient temperature in the first sample training set as the output feature of the first deep learning model, wherein the target load rate is any load rate in the first sample training set, and the target ambient temperature is an ambient temperature that has a corresponding relationship with the target load rate. That is to say, the load rate and ambient temperature in each corresponding relationship in the first sample training set are used as input features, and the hotspot temperature corresponding to each load rate and ambient temperature is used as an output feature, so as to construct a first function through the first deep learning model.

[0073] In this embodiment, the first function expression may be:

[0074]

[0075] Among them, T E represents the hot spot temperature of the transformer under test when thermal aging does not occur, m is the number of hidden layer nodes of the first deep learning model; i represents the sequence number of the hidden layer node of the first deep learning model, ω i , γ i are the weights corresponding to the hidden layer nodes respectively.

[0076] The second deep learning model is trained with the target top oil temperature in the second sample training set as the input feature of the preset second deep learning model and the target hotspot temperature corresponding to the target top oil temperature in the second sample training set as the output feature of the second deep learning model, wherein the target top oil temperature is any top oil temperature in the second sample training set, and the target hotspot temperature is a hotspot temperature that has a corresponding relationship with the target top oil temperature. That is to say, the top oil temperature in each corresponding relationship in the second sample training set is used as the input feature, and the hotspot temperature corresponding to each top oil temperature is used as the output feature, so as to construct a second function through the second deep learning model.

[0077] In this embodiment, the second function expression may be:

[0078]

[0079] Among them, T R represents the actual hot spot temperature of the transformer to be tested, n is the number of hidden layer nodes of the second deep learning model; j represents the sequence number of the hidden layer node of the second deep learning model, σ j and j are the weights corresponding to the hidden layer nodes respectively.

[0080] The deep learning model can use the digital twin technology of the extreme learning machine. In this embodiment, the first sample training set and the second sample training set can be divided into a training set and a test set in a ratio of 8:1, and the deep learning model is constructed using the extreme learning machine network. After the first deep learning model or the second deep learning model is trained, the test set is used to perform performance testing on it, and the accuracy of the training results of the two sets of training data is tested with the corresponding test sets, mainly using the mean relative error MRE as an indicator for judgment. The calculation expression of MRE is as follows:

[0081]

[0082] In the formula, Z is the total number of test set samples, y k and are the actual value of the sample and the predicted value of the deep learning model, respectively.

[0083] When MRE<0.5%, it proves that the network prediction effect is good and the currently trained deep learning model can be used. When MRE≥0.5%, it proves that the network prediction effect is not ideal, so the model parameters should be optimized and retrained.

[0084] Therefore, the objective function can be expressed as:

[0085]

[0086] Where V represents the thermal aging degree of the transformer to be tested, T E Indicates the hot spot temperature of the transformer under test when no thermal aging occurs, T R Indicates the actual hot spot temperature of the transformer under test.

[0087] In this embodiment, a method for obtaining a first sample training set and a second sample training set is proposed. Figure 3 , Figure 3 A flow chart of a training set acquisition method provided by an embodiment of the present invention is shown as follows: Figure 2 As shown, the method is specifically shown in step S301-step S302:

[0088] Step S301, obtaining the core loss and winding loss corresponding to the transformer to be tested at different load rates; based on the core loss and winding loss, calculating the hotspot temperature and top oil temperature of the transformer to be tested at different ambient temperatures, and obtaining the hotspot temperature and top oil temperature of the transformer to be tested at different load rates and different ambient temperatures.

[0089] Step S302: construct a first sample training set and a second sample training set based on the different load rates, the different ambient temperatures, and the hotspot temperatures and top layer oil temperatures under the different load rates and the different ambient temperatures.

[0090] The core loss and winding loss corresponding to the transformer to be tested at different load rates are obtained. In this embodiment, a transformer electromagnetic loss calculation model can be constructed according to parameters such as the core, winding, and oil tank structure of the transformer to be tested, wherein the transformer electromagnetic loss calculation model is a simulation model, which is used to simulate and calculate the electromagnetic loss of the transformer. The electromagnetic loss includes at least core loss and winding loss. Specifically, the conductivity, magnetic flux and other parameters of the simulation model are set according to the parameters provided in the power transformer manual, and the core loss PFE and winding loss PCU under different load rates k are obtained through finite element simulation.

[0091] Considering the core, winding, oil tank, oil baffle, insulating oil paper and heat sink structure of the transformer to be tested, the transformer flow-heat coupling simulation model is drawn based on the SpaceClaim scripting language. According to the material parameters of the transformer structural parts before aging provided in the power transformer manual, the material parameters of the structural parts mainly involve the physical and mechanical properties of the materials, such as corrosion resistance, thermal stability, conductivity, etc., the density, constant pressure heat capacity and thermal conductivity of each part of the flow-heat coupling simulation model are set, and the core loss PFE and winding loss PCU calculated by the transformer electromagnetic loss calculation model are input into the heat source of the flow-heat coupling simulation model, and the ambient temperature is set. The winding hot spot temperature T and the top oil temperature Toil of the transformer to be tested under different load rates k and different ambient temperatures T0 are calculated through finite volume simulation.

[0092] Therefore, there is a corresponding relationship between the load rate, ambient temperature, hot spot temperature, and top oil temperature. The first sample training set and the second sample training set can be constructed based on the hot spot temperatures and top oil temperatures at different load rates, different ambient temperatures, and different load rates and different ambient temperatures.

[0093] In this embodiment, after calculating the thermal aging degree of the transformer to be tested based on the objective function, step S104 is further performed to determine whether to issue a warning to the transformer to be tested according to the thermal aging degree and the thermal aging degree warning threshold.

[0094] In order to improve the safety of the transformer under test, an early warning is given to the transformer under test, and a thermal aging degree early warning threshold θ is set. If the thermal aging degree is greater than the thermal aging degree early warning threshold θ, it means that the transformer has exceeded the life limit and may need to be replaced, and an early warning is given to the transformer under test. If the thermal aging degree is not greater than the thermal aging degree early warning threshold, it means that the transformer can continue to operate, and no early warning is given to the transformer under test. The early warning threshold θ can be set as needed. According to the Institute of Electrical and Electronics Engineers (IEEE) standard, the threshold θ can be set within 0.7 to 0.8.

[0095] The advantages of the present invention are: on the one hand, compared with parameters such as the conductivity of transformer oil, the conductivity of insulating baffles and oil paper, and the thermal conductivity coefficient, the ambient temperature and top oil temperature of the transformer are easier to detect. The degree of thermal aging can be predicted based on these indicators, and the thermal aging of the transformer can be easily detected; on the other hand, the digital twin technology based on the extreme learning machine has extremely high prediction accuracy and prediction speed in predicting the degree of thermal aging of the transformer, which can realize real-time monitoring of the degree of thermal aging of the transformer and timely update the transformer equipment with excessively high aging degree.

[0096] In order to better implement the above method, the embodiment of the present invention provides a transformer thermal aging degree monitoring device, which can implement all the steps of the above method, referring to Figure 4 , Figure 4 A structural block diagram of a transformer thermal aging degree monitoring device provided by an embodiment of the present invention, such as Figure 4 As shown, the device 40 specifically includes:

[0097] The first construction module 401 is used to construct a mapping relationship between the hot spot temperature, load rate and ambient temperature of the transformer to be tested when thermal aging has not occurred, to obtain a first function, and to construct a mapping relationship between the actual hot spot temperature of the transformer to be tested and the top oil temperature, to obtain a second function; wherein the first function is used to calculate the hot spot temperature of the transformer to be tested when thermal aging has not occurred, and the second function is used to calculate the actual hot spot temperature of the transformer to be tested.

[0098] The second construction module 402 is used to combine the first function and the second function to construct a mapping relationship between the thermal aging degree, load rate, ambient temperature and top oil temperature of the transformer to be tested, and obtain an objective function; the objective function is used to calculate the thermal aging degree of the transformer to be tested.

[0099] Calculation module 403: used to obtain the actual load rate, actual ambient temperature and actual top oil temperature of the transformer to be tested, and calculate the thermal aging degree of the transformer to be tested based on the objective function according to the actual load rate, actual ambient temperature and actual top oil temperature.

[0100] In a possible design, the first construction module 401 is specifically used to: obtain a first sample training set and a second sample training set; the first sample training set includes different load rates, different ambient temperatures and hot spot temperatures at different load rates and different ambient temperatures when the transformer to be tested has not aged, and the second sample training set includes the hot spot temperatures and top oil temperatures at different load rates and different ambient temperatures; the target load rate and target ambient temperature in the first sample training set are used as input features of a preset first deep learning model, and the target hot spot temperature corresponding to the target load rate and target ambient temperature in the first sample training set is used as an output feature of the first deep learning model to train the The first deep learning model is used to obtain a first function; wherein the target load rate is any load rate in the first sample training set, and the target ambient temperature is an ambient temperature corresponding to the target load rate; the target top layer oil temperature in the second sample training set is used as the input feature of the preset second deep learning model, and the target hot spot temperature corresponding to the target top layer oil temperature in the second sample training set is used as the output feature of the second deep learning model to train the second deep learning model to obtain a second function; wherein the target top layer oil temperature is any top layer oil temperature in the second sample training set, and the target hot spot temperature is a hot spot temperature corresponding to the target top layer oil temperature.

[0101] In a possible design, the first function expression in the first building block 401 is:

[0102]

[0103] Among them, T E represents the hot spot temperature of the transformer under test when thermal aging does not occur, m is the number of hidden layer nodes of the first deep learning model; i represents the sequence number of the hidden layer node of the first deep learning model, ω i , γ i are the weights corresponding to the hidden layer nodes respectively.

[0104] In a possible design, the second function expression in the first building block 401 is:

[0105]

[0106] Among them, T R represents the actual hot spot temperature of the transformer to be tested, n is the number of hidden layer nodes of the second deep learning model; j represents the sequence number of the hidden layer node of the second deep learning model, σ j and j are the weights corresponding to the hidden layer nodes respectively.

[0107] In a possible design, the above-mentioned first construction module 401 is specifically used to: obtain the core loss and winding loss corresponding to the transformer to be tested at different load rates; based on the core loss and winding loss, calculate the hot spot temperature and top oil temperature of the transformer to be tested at different ambient temperatures, and obtain the hot spot temperature and top oil temperature of the transformer to be tested at different load rates and different ambient temperatures; based on the different load rates, different ambient temperatures and the hot spot temperature and top oil temperature at the different load rates and different ambient temperatures, construct a first sample training set and a second sample training set.

[0108] In a possible design, the objective function expression in the second building module 402 is:

[0109]

[0110] Where V represents the thermal aging degree of the transformer to be tested, T E Indicates the hot spot temperature of the transformer under test when no thermal aging occurs, T R Indicates the actual hot spot temperature of the transformer under test.

[0111] In a possible design, the calculation module 402 is specifically used to determine whether to issue an early warning for the transformer to be tested according to the thermal aging degree and the thermal aging degree early warning threshold.

[0112] In a possible design, the calculation module 402 is specifically used to: if the thermal aging degree is greater than the thermal aging degree warning threshold, issue a warning to the transformer under test; if the thermal aging degree is not greater than the thermal aging degree warning threshold, do not issue a warning to the transformer under test.

[0113] Based on the above device, the thermal aging of the transformer can be easily detected, the real-time monitoring of the thermal aging degree of the transformer can be realized, and early warning can be given in time for transformer equipment with excessive aging degree.

[0114] Figure 5 FIG. 1 shows an internal structure diagram of a computer device in an embodiment. The computer device may be a terminal or a server. Figure 5 As shown, the computer device includes a processor, a memory and a network interface connected via a system bus. The memory includes a non-volatile storage medium and an internal memory. The non-volatile storage medium of the computer device stores an operating system and may also store a computer program. When the computer program is executed by the processor, the processor can implement all the steps of the above method. The internal memory may also store a computer program. When the computer program is executed by the processor, the processor can implement all the steps of the above method. Those skilled in the art will understand that Figure 5The structure shown in the figure is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components.

[0115] In one embodiment, a computer device is provided, including a memory and a processor, wherein the memory stores a computer program, and when the computer program is executed by the processor, the processor executes each step of the aforementioned method.

[0116] In one embodiment, a computer-readable storage medium is provided, which stores a computer program. When the computer program is executed by a processor, the processor executes each step of the aforementioned method.

[0117] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program, and the program can be stored in a non-volatile computer-readable storage medium. When the program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to memory, storage, database or other media used in the embodiments provided in this application can include non-volatile and / or volatile memory. Non-volatile memory may include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM) or flash memory. Volatile memory may include random access memory (RAM) or external cache memory. As an illustration and not limitation, RAM is available in many forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous link (Synchlink) DRAM (SLDRAM), memory bus (Rambus) direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM).

[0118] The technical features of the above embodiments may be combined arbitrarily. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0119] The above-mentioned embodiments only express several implementation methods of the present application, and the descriptions thereof are relatively specific and detailed, but they cannot be understood as limiting the scope of the present application. It should be pointed out that, for a person of ordinary skill in the art, several variations and improvements can be made without departing from the concept of the present application, and these all belong to the protection scope of the present application. Therefore, the protection scope of the present application shall be subject to the attached claims.

Claims

1. A method for monitoring the thermal aging degree of a transformer, characterized in that: The method comprises: Constructing a mapping relationship between the hot spot temperature, load rate and ambient temperature of the transformer to be tested when thermal aging has not occurred, to obtain a first function, and constructing a mapping relationship between the actual hot spot temperature of the transformer to be tested and the top oil temperature, to obtain a second function; wherein the first function is used to calculate the hot spot temperature of the transformer to be tested when thermal aging has not occurred, and the second function is used to calculate the actual hot spot temperature of the transformer to be tested; Combining the first function and the second function, constructing a mapping relationship between the thermal aging degree, load rate, ambient temperature and top oil temperature of the transformer to be tested, and obtaining an objective function; the objective function is used to calculate the thermal aging degree of the transformer to be tested; The actual load rate, actual ambient temperature and actual top oil temperature of the transformer to be tested are obtained, and the thermal aging degree of the transformer to be tested is calculated based on the objective function according to the actual load rate, actual ambient temperature and actual top oil temperature.

2. The method according to claim 1, characterized in that The mapping relationship between the hot spot temperature, load rate and ambient temperature of the transformer to be tested when thermal aging does not occur is constructed to obtain a first function, and the mapping relationship between the actual hot spot temperature of the transformer to be tested and the top oil temperature is constructed to obtain a second function, including: Obtain a first sample training set and a second sample training set; the first sample training set includes different load rates, different ambient temperatures and hot spot temperatures at the different load rates and different ambient temperatures when the transformer to be tested has not aged, and the second sample training set includes the hot spot temperatures and top oil temperatures at the different load rates and different ambient temperatures; The first deep learning model is trained using the target load rate and the target ambient temperature in the first sample training set as input features of the preset first deep learning model, and the target hotspot temperature corresponding to the target load rate and the target ambient temperature in the first sample training set is used as the output feature of the first deep learning model to obtain a first function; wherein the target load rate is any load rate in the first sample training set, and the target ambient temperature is an ambient temperature that has a corresponding relationship with the target load rate; The second deep learning model is trained using the target top layer oil temperature in the second sample training set as the input feature of the preset second deep learning model and the target hot spot temperature corresponding to the target top layer oil temperature in the second sample training set as the output feature of the second deep learning model to obtain a second function; wherein the target top layer oil temperature is any top layer oil temperature in the second sample training set, and the target hot spot temperature is a hot spot temperature that has a corresponding relationship with the target top layer oil temperature.

3. The method according to claim 2, characterized in that The first function expression is: Among them, T E represents the hot spot temperature of the transformer under test when thermal aging does not occur, m is the number of hidden layer nodes of the first deep learning model; i represents the sequence number of the hidden layer node of the first deep learning model, ω i , γ i are the weights corresponding to the hidden layer nodes respectively.

4. The method according to claim 2, characterized in that: The second function expression is: Among them, T R represents the actual hot spot temperature of the transformer to be tested, n is the number of hidden layer nodes of the second deep learning model; j represents the sequence number of the hidden layer node of the second deep learning model, σ j and j are the weights corresponding to the hidden layer nodes respectively.

5. The method according to claim 1, characterized in that The first function and the second function are combined to construct a mapping relationship between the thermal aging degree, load rate, ambient temperature and top oil temperature of the transformer to be tested, and an objective function is obtained, including: Where V represents the thermal aging degree of the transformer to be tested, T E Indicates the hot spot temperature of the transformer under test when no thermal aging occurs, T R Indicates the actual hot spot temperature of the transformer under test.

6. The method according to claim 2, characterized in that The obtaining of the first sample training set and the second sample training set comprises: Obtain the core loss and winding loss corresponding to the transformer to be tested at different load rates; based on the core loss and winding loss, calculate the hot spot temperature and top oil temperature of the transformer to be tested at different ambient temperatures, and obtain the hot spot temperature and top oil temperature of the transformer to be tested at different load rates and different ambient temperatures; Based on the different load rates, the different ambient temperatures, and the hotspot temperatures and top oil temperatures at the different load rates and the different ambient temperatures, a first sample training set and a second sample training set are constructed.

7. The method according to claim 1, characterized in that After calculating the thermal aging degree of the transformer to be tested based on the objective function, the method further includes: According to the thermal aging degree and the thermal aging degree warning threshold, it is determined whether to issue a warning for the transformer to be tested.

8. The method according to claim 7, characterized in that The step of judging whether to issue an early warning to the transformer to be tested according to the degree of thermal aging and the early warning threshold of the degree of thermal aging includes: If the thermal aging degree is greater than the thermal aging degree warning threshold, a warning is issued for the transformer to be tested; If the thermal aging degree is not greater than the thermal aging degree warning threshold, no warning is issued for the transformer to be tested.

9. A transformer thermal aging degree monitoring device, characterized in that: The device comprises: The first construction module is used to construct a mapping relationship between the hot spot temperature, load rate and ambient temperature of the transformer to be tested when thermal aging has not occurred, to obtain a first function, and to construct a mapping relationship between the actual hot spot temperature of the transformer to be tested and the top oil temperature, to obtain a second function; wherein the first function is used to calculate the hot spot temperature of the transformer to be tested when thermal aging has not occurred, and the second function is used to calculate the actual hot spot temperature of the transformer to be tested; The second construction module is used to combine the first function and the second function to construct a mapping relationship between the thermal aging degree, load rate, ambient temperature and top oil temperature of the transformer to be tested, and obtain an objective function; the objective function is used to calculate the thermal aging degree of the transformer to be tested; Calculation module: used to obtain the actual load rate, actual ambient temperature and actual top oil temperature of the transformer to be tested, and calculate the thermal aging degree of the transformer to be tested based on the objective function according to the actual load rate, actual ambient temperature and actual top oil temperature.

10. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the processor is caused to perform the steps of the method according to any one of claims 1 to 8.

Citation Information

Cited By

  • Transformer winding insulation monitoring system

    CN119881566A