Transformer hot-spot temperature early warning method based on digital twinning, medium and equipment

Abstract

The invention discloses a transformer hot-spot temperature early warning method based on digital twinning, a medium and equipment. The method comprises the following steps: building an electromagnetic thermal fluid field coupling model; obtaining transformer hot-spot temperature field distribution data based on an electromagnetic thermal fluid field coupling model; establishing a support vector regression machine model, selecting a thermal characteristic variable and a load characteristic variable as input quantities, obtaining a corresponding transformer hot-spot temperature from the transformer hot-spot temperature field distribution data as an output quantity, solving the support vector regression machine model, and obtaining an optimal weight vector and an optimal temperature deviation value in the support vector regression machine model; establishing a transformer hot-spot temperature virtual sensing model based on the optimal weight vector and the optimal temperature deviation value; and the operation state of the transformer is monitored in real time, a real-time thermal characteristic variable value and a real-time load characteristic variable value are obtained, and transformer hot-spot temperature real-time virtual sensing is achieved based on the transformer hot-spot temperature virtual sensing model. Accurate sensing and early warning of the hot-spot temperature of the transformer can be realized.

Description

Technical Field

[0001] The present invention relates to the technical field of transformer temperature monitoring, and in particular to a transformer hot spot temperature early warning method, medium and equipment based on digital twins. Background Art

[0002] Digital twin technology collects and analyzes data from physical entities, and establishes a digital twin model in the information technology platform that has the same physical operating characteristics and principles as the physical entity. The digital twin model can be corrected based on the data collected in real time to achieve synchronization with the actual physical entity. The digital twin model is used to simulate and predict specific working conditions, fault warnings, etc., to achieve optimal decision-making and control of the physical entity. This technology can truly reflect the characteristics and working principles of the physical entity. With the help of digital twin technology, digital models and physical entities can be synchronized in real time and have the ability to interact in virtual reality.

[0003] Transformer digital twin technology has been initially explored and applied in real-time detection of transformer internal faults, transformer winding fault diagnosis and remaining life prediction, transformer medium voltage monitoring based on low voltage measurement, and transformer on-load tap changer status estimation. Transformer digital twin technology can provide a technical means for accurate perception of transformer operating status and propose efficient operation and maintenance strategies.

[0004] Transformer oil-paper insulation has spatial locality and temporal accumulation characteristics under the action of electrothermal effect, and is significantly affected by the hot spot temperature of the winding, so it is necessary to sense the hot spot temperature of the transformer. However, real-time monitoring of the hot spot temperature of the transformer is difficult and requires high sensor performance. Therefore, it is necessary to provide a virtual perception and early warning method for hot spot temperature of the transformer based on transformer digital twin technology that does not require embedded sensors and has wide applicability. Summary of the invention

[0005] The present invention aims to solve one of the technical problems in the related art to at least a certain extent. To this end, the first object of the present invention is to provide a transformer hot spot temperature early warning method based on digital twin, which can realize accurate perception and early warning of transformer hot spot temperature.

[0006] A second object of the present invention is to provide a computer-readable storage medium.

[0007] A third object of the present invention is to provide an electronic device.

[0008] To achieve the above object, the present invention is implemented through the following technical solutions:

[0009] A transformer hot spot temperature early warning method based on digital twins, comprising:

[0010] Build the electromagnetic thermal fluid field coupling model of the transformer;

[0011] The transformer hot spot temperature field distribution data is calculated based on the electromagnetic thermal fluid field coupling model;

[0012] Establishing a support vector regression machine model, selecting thermal characteristic variables and load characteristic variables as input quantities of the support vector regression machine model, and obtaining the corresponding transformer hot spot temperature from the transformer hot spot temperature field distribution data as output quantity, solving the support vector regression machine model, and obtaining the optimal weight vector and optimal temperature deviation value in the support vector regression machine model;

[0013] A transformer hot spot temperature virtual perception model is established based on the optimal weight vector and the optimal temperature deviation value;

[0014] The operating state of the transformer is monitored in real time to obtain real-time thermal characteristic variable values ​​and load characteristic variable values, and real-time virtual perception of the hot spot temperature of the transformer is realized based on the virtual perception model of the hot spot temperature of the transformer.

[0015] Preferably, the method further comprises: performing transformer hot spot temperature warning according to the transformer hot spot temperature change amount and the transformer hot spot temperature.

[0016] Preferably, the transformer hot spot temperature warning is performed according to the transformer hot spot temperature change amount and the transformer hot spot temperature, including:

[0017] When the transformer hot spot temperature change is greater than a first threshold, or the transformer hot spot temperature is greater than a second threshold, a transformer hot spot temperature warning is issued, wherein the first threshold is less than the second threshold.

[0018] Preferably, the electromagnetic thermal fluid field coupling model of the transformer is constructed, including:

[0019] Construct a transformer electromagnetic field model, a transformer fluid thermal field model, a winding loss and temperature relationship model, and determine the transformer surface heat transfer coefficient. Build the electromagnetic thermal fluid field coupling model in the simulation software based on the transformer electromagnetic field model, the transformer fluid thermal field model, the winding loss and temperature relationship model and the transformer surface heat transfer coefficient.

[0020] Preferably, the thermal characteristic variables include at least the transformer top oil temperature, and the temperatures at the inlet and outlet of the transformer high-voltage side wide side heat sink; the load characteristic variables include at least the three-phase maximum load rate, the three-phase minimum load rate, and the sum of the three-phase load rates.

[0021] Preferably, the support vector regression model is expressed as follows:

[0022]

[0023] Among them, min is the minimum function, w is the weight vector, b is the temperature deviation value, ξ i , i * are the upper and lower tolerance errors of the i-th sample, C is the penalty coefficient, n is the number of samples, and y i is the transformer hot spot temperature value of the i-th sample, the transformer hot spot temperature value is obtained from the hot spot temperature field distribution data, φ(x i ) is the kernel function, x i is the i-th sample, τ is the tolerance, where each sample is a feature vector composed of multiple thermal characteristic variables and load characteristic variables.

[0024] Preferably, the transformer hot spot temperature virtual perception model is expressed as follows:

[0025] f(x)= <w * ,φ(x i )>+b *

[0026] Where f(x) represents the real-time sensed value of the transformer hot spot temperature, w * 、b * Represent the optimal weight vector and optimal temperature deviation value respectively.

[0027] To achieve the above-mentioned purpose, the second aspect of the present invention provides a computer-readable storage medium on which a computer program is stored. When the computer program is executed by a processor, the above-mentioned transformer hot spot temperature warning method based on digital twin is implemented.

[0028] To achieve the above-mentioned purpose, the third aspect of the present invention provides an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, the above-mentioned transformer hot spot temperature warning method based on digital twin is implemented.

[0029] The present invention has at least the following technical effects:

[0030] The present invention provides a transformer hot spot temperature early warning method based on digital twins. The method first builds an electromagnetic thermal fluid field coupling model of the transformer, then calculates the transformer hot spot temperature field distribution data based on the electromagnetic thermal fluid field coupling model, and then establishes a support vector regression machine model, selects thermal characteristic variables and load characteristic variables as input quantities of the support vector regression machine model, and obtains the corresponding transformer hot spot temperature from the transformer hot spot temperature field distribution data as an output quantity to solve the support vector regression machine model, obtain the optimal weight vector and the optimal temperature deviation value in the support vector regression machine model, and then establishes a transformer hot spot temperature virtual perception model based on the optimal weight vector and the optimal temperature deviation value. After obtaining the transformer hot spot temperature virtual perception model, the operating state of the transformer is monitored in real time to obtain the real-time thermal characteristic variable value and the load characteristic variable value, and the thermal characteristic variable value and the load characteristic variable value are substituted into the transformer hot spot temperature virtual perception model, so as to realize the real-time virtual perception of the transformer hot spot temperature. The present invention has wide applicability and does not need to embed sensors to monitor the winding temperature. At the same time, it can realize accurate virtual perception of the transformer hot spot temperature based on the digital twin model, that is, the transformer hot spot temperature virtual perception model, and can give an early warning according to the transformer hot spot temperature. Therefore, the present invention has important theoretical and application value for improving the safety level of transformer operation and the efficiency of transformer fault inspection and repair.

[0031] Additional aspects and advantages of the present invention will be given in part in the following description and in part will be obvious from the following description, or will be learned through practice of the present invention. BRIEF DESCRIPTION OF THE DRAWINGS

[0032] Figure 1 This is a flow chart of a transformer hotspot temperature warning method based on digital twins according to an embodiment of the present invention.

[0033] Figure 2 This is a specific flow chart of a transformer hotspot temperature warning method based on digital twins according to an embodiment of the present invention. DETAILED DESCRIPTION

[0034] The present embodiment is described in detail below, and examples of the embodiment are shown in the accompanying drawings, wherein the same or similar reference numerals throughout represent the same or similar elements or elements having the same or similar functions. The embodiments described below with reference to the accompanying drawings are exemplary and are intended to be used to explain the present invention, and should not be construed as limiting the present invention.

[0035] The following describes the transformer hot spot temperature warning method, medium and device based on digital twin of this embodiment with reference to the accompanying drawings.

[0036] Figure 1 FIG. 1 is a flow chart of a transformer hot spot temperature early warning method based on digital twins according to an embodiment of the present invention. Figure 1As shown, the method includes:

[0037] Step S1: Build an electromagnetic thermal fluid field coupling model of the transformer.

[0038] In this embodiment, an electromagnetic thermal fluid field coupling model of a transformer is built, including: constructing a transformer electromagnetic field model, a transformer fluid thermal field model, a winding loss and temperature relationship model, and determining the transformer surface heat transfer coefficient, and building an electromagnetic thermal fluid field coupling model in a simulation software according to the transformer electromagnetic field model, the transformer fluid thermal field model, the winding loss and temperature relationship model and the transformer surface heat transfer coefficient.

[0039] According to Maxwell's equations, the transformer electromagnetic field model is expressed as follows:

[0040]

[0041] in, is the gradient operator, H is the magnetic field intensity, J is the current intensity, E is the electric field intensity, B is the magnetic induction intensity, t is the time, is the divergence operator, and σ is the conductivity of the medium.

[0042] The transformer fluid thermal field model is specifically used to describe the heat dissipation process of the core, winding and oil, i.e. the fluid, and satisfies the three major theorems of conservation of mass, conservation of momentum and conservation of energy. The transformer fluid thermal field model is expressed as follows:

[0043]

[0044] Where ρ represents the fluid density, v is the fluid velocity, g is the gravitational acceleration, represents the gradient operator, P is the pressure, μ is the dynamic viscosity, c is the specific heat capacity of the fluid, λ is the thermal conductivity of the fluid, Δ represents the increment, T is the temperature, and q is the heat source per unit volume in the transformer.

[0045] The relationship model between winding loss and temperature is expressed as follows:

[0046] P s (T) = P0[1+α(T-T0)] (3)

[0047] Among them, P s (T) is the winding loss, P0 is the winding loss at the initial temperature T0 of the winding, α is the temperature coefficient of the winding material, and T is the winding temperature.

[0048] The external heat dissipation of the transformer depends on the heat convection and heat radiation on the transformer surface. The heat transfer coefficient of the transformer surface is expressed as follows:

[0049]

[0050] Among them, Nu is the Nusselt number, a and b are two constants, R is the Rayleigh number, h is the convection heat transfer coefficient, and L is the heat transfer length.

[0051] Step S2: Calculate the transformer hotspot temperature field distribution data based on the electromagnetic thermal fluid field coupling model.

[0052] like Figure 2 As shown, an electromagnetic thermal fluid field coupling model can be built in COMSOL (a simulation software) software based on the transformer electromagnetic field model, the transformer fluid thermal field model, the winding loss and temperature relationship model and the transformer surface heat transfer coefficient, and then the parameters are set to calculate the transformer hot spot temperature field distribution data.

[0053] Step S3: Establish a support vector regression machine model, select thermal characteristic variables and load characteristic variables as input quantities of the support vector regression machine model, and obtain the corresponding transformer hot spot temperature from the transformer hot spot temperature field distribution data as output quantity, solve the support vector regression machine model, and obtain the optimal weight vector and optimal temperature deviation value in the support vector regression machine model.

[0054] In this embodiment, the thermal characteristic variables include at least the transformer top oil temperature, the transformer high-voltage side wide side heat sink inlet and outlet temperatures; the load characteristic variables include at least the three-phase maximum load rate, the three-phase minimum load rate, and the sum of the three-phase load rates.

[0055] The support vector regression model is expressed as follows:

[0056]

[0057] Where min is the minimum function, w is the weight vector, b is the temperature deviation value, ξ i , i * are the upper and lower tolerance errors of the i-th sample, C is the penalty coefficient, n is the number of samples, and y i is the transformer hot spot temperature value of the i-th sample, which is obtained from the hot spot temperature field distribution data. i ) is the kernel function, x i is the i-th sample, τ is the tolerance, where each sample is a feature vector composed of multiple thermal characteristic variables and load characteristic variables.

[0058] Among them, the kernel function φ(x i ) is expressed as follows:

[0059]

[0060] Among them, γ represents the bandwidth parameter of the kernel function, x φ represents the φth sample, that is, another sample, ‖xi -x φ Represents the Euclidean distance between two samples.

[0061] Furthermore, the input and output are input and the support vector regression algorithm is used to solve the above support vector regression model to obtain a set of optimal solutions w * 、b * .w * is the optimal weight vector obtained by solving, b * is the optimal temperature deviation value obtained by solving.

[0062] Step S4: A transformer hot spot temperature virtual perception model is established based on the optimal weight vector and the optimal temperature deviation value.

[0063] The virtual perception model of transformer hot spot temperature is expressed as follows:

[0064] f(x)= <w * ,φ(x i )>+b * (7)

[0065] Where f(x) represents the real-time sensed value of the transformer hot spot temperature, w * 、b * Represent the optimal weight vector and optimal temperature deviation value respectively.

[0066] Step S5: monitor the operating status of the transformer in real time, obtain real-time thermal characteristic variable values ​​and load characteristic variable values, and realize real-time virtual perception of the hot spot temperature of the transformer based on the virtual perception model of the hot spot temperature of the transformer.

[0067] Specifically, after real-time monitoring of the operating status of the transformer, the real-time thermal characteristic variable values ​​and load characteristic variable values ​​can be obtained, and then substituted into the transformer hot spot temperature virtual perception model, so as to directly realize the real-time virtual perception of the transformer hot spot temperature.

[0068] In one embodiment of the present invention, the method further includes: performing a transformer hot spot temperature warning according to the transformer hot spot temperature change and the transformer hot spot temperature. Performing a transformer hot spot temperature warning according to the transformer hot spot temperature change and the transformer hot spot temperature includes: performing a transformer hot spot temperature warning when the transformer hot spot temperature change is greater than a first threshold value, or when the transformer hot spot temperature is greater than a second threshold value, wherein the first threshold value is less than the second threshold value.

[0069] The first threshold and the second threshold are respectively set as follows:

[0070]

[0071]

[0072] Specifically, when the hot spot temperature of the transformer exceeds 65 degrees or the hot spot temperature exceeds 90 degrees, an alarm will be issued and relevant personnel will be arranged to go to the site for maintenance or inspection.

[0073] In summary, the present invention provides a transformer hot spot temperature early warning method based on digital twins. The method first builds an electromagnetic thermal fluid field coupling model of the transformer, then calculates the transformer hot spot temperature field distribution data based on the electromagnetic thermal fluid field coupling model, and then establishes a support vector regression machine model, selects thermal characteristic variables and load characteristic variables as input quantities of the support vector regression machine model, and obtains the corresponding transformer hot spot temperature from the transformer hot spot temperature field distribution data as an output quantity to solve the support vector regression machine model, obtain the optimal weight vector and the optimal temperature deviation value in the support vector regression machine model, and then establishes a transformer hot spot temperature virtual perception model based on the optimal weight vector and the optimal temperature deviation value. After obtaining the transformer hot spot temperature virtual perception model, the operating state of the transformer is monitored in real time to obtain the real-time thermal characteristic variable value and the load characteristic variable value, and the thermal characteristic variable value and the load characteristic variable value are substituted into the transformer hot spot temperature virtual perception model, so as to realize the real-time virtual perception of the transformer hot spot temperature. The present invention has wide applicability and does not require embedded sensors to monitor the winding temperature. At the same time, it can realize accurate virtual perception of the transformer hot spot temperature based on the digital twin model, that is, the transformer hot spot temperature virtual perception model, and can give an early warning according to the transformer hot spot temperature. Therefore, the present invention has important theoretical and application value for improving the safety level of transformer operation and the efficiency of transformer fault inspection and repair.

[0074] Furthermore, the present invention also provides a computer-readable storage medium on which a computer program is stored. When the computer program is executed by a processor, the above-mentioned transformer hot spot temperature warning method based on digital twin can be implemented.

[0075] Furthermore, the present invention also provides an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, the above-mentioned transformer hot spot temperature warning method based on digital twins can be implemented.

[0076] It should be noted that, in this article, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, the elements defined by the sentence "comprise a ..." do not exclude the existence of other identical elements in the process, method, article or device including the elements.

[0077] Although the content of the present invention has been described in detail through the above preferred embodiments, it should be appreciated that the above description should not be considered as a limitation of the present invention. After reading the above content, it will be apparent to those skilled in the art that various modifications and substitutions of the present invention will occur. Therefore, the protection scope of the present invention should be limited by the appended claims.

Claims

1. A transformer hot spot temperature early warning method based on digital twin, characterized in that: include: Build the electromagnetic thermal fluid field coupling model of the transformer; The transformer hotspot temperature field distribution data is calculated based on the electromagnetic thermal fluid field coupling model; Establishing a support vector regression machine model, selecting thermal characteristic variables and load characteristic variables as input quantities of the support vector regression machine model, and obtaining the corresponding transformer hot spot temperature from the transformer hot spot temperature field distribution data as output quantity, solving the support vector regression machine model, and obtaining the optimal weight vector and optimal temperature deviation value in the support vector regression machine model; A transformer hot spot temperature virtual perception model is established based on the optimal weight vector and the optimal temperature deviation value; The operating state of the transformer is monitored in real time to obtain real-time thermal characteristic variable values ​​and load characteristic variable values, and real-time virtual perception of the hot spot temperature of the transformer is realized based on the virtual perception model of the hot spot temperature of the transformer.

2. The transformer hot spot temperature early warning method based on digital twin according to claim 1 is characterized in that: The method further includes: performing a transformer hot spot temperature early warning according to the transformer hot spot temperature variation and the transformer hot spot temperature.

3. The transformer hot spot temperature early warning method based on digital twin according to claim 2 is characterized in that: The transformer hot spot temperature warning is carried out according to the transformer hot spot temperature change and the transformer hot spot temperature, including: When the transformer hot spot temperature change is greater than a first threshold, or the transformer hot spot temperature is greater than a second threshold, a transformer hot spot temperature warning is issued, wherein the first threshold is less than the second threshold.

4. The transformer hot spot temperature early warning method based on digital twin according to claim 1 is characterized in that: Build the electromagnetic thermal fluid field coupling model of the transformer, including: Construct a transformer electromagnetic field model, a transformer fluid thermal field model, a winding loss and temperature relationship model, and determine the transformer surface heat transfer coefficient. Build the electromagnetic thermal fluid field coupling model in the simulation software based on the transformer electromagnetic field model, the transformer fluid thermal field model, the winding loss and temperature relationship model and the transformer surface heat transfer coefficient.

5. The transformer hot spot temperature early warning method based on digital twin according to claim 1 is characterized in that: The thermal characteristic variables include at least the transformer top oil temperature, the transformer high-voltage side wide side heat sink inlet and outlet temperatures; the load characteristic variables include at least the three-phase maximum load rate, the three-phase minimum load rate, and the sum of the three-phase load rates.

6. The transformer hot spot temperature early warning method based on digital twin according to claim 1 is characterized in that: The support vector regression model is expressed as follows: Among them, min is the minimum function, w is the weight vector, b is the temperature deviation value, ξ i , i * are the upper and lower tolerance errors of the i-th sample, C is the penalty coefficient, n is the number of samples, and y i is the transformer hot spot temperature value of the i-th sample, the transformer hot spot temperature value is obtained from the hot spot temperature field distribution data, φ(x i ) is the kernel function, x i is the i-th sample, τ is the tolerance, where each sample is a feature vector composed of multiple thermal characteristic variables and load characteristic variables.

7. The transformer hot spot temperature early warning method based on digital twin according to claim 6 is characterized in that: The transformer hot spot temperature virtual perception model is expressed as follows: f(x)=<w * ,φ(x i )>+b * Where f(x) represents the real-time sensed value of the transformer hot spot temperature, w * , b * Represent the optimal weight vector and optimal temperature deviation value respectively.

8. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the transformer hot spot temperature early warning method based on digital twins as described in any one of claims 1 to 7 is implemented.

9. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the computer program, the transformer hot spot temperature early warning method based on digital twin is implemented as described in any one of claims 1 to 7.

Images