A real-time online monitoring method and related device for GIL temperature distribution

Abstract

The present application discloses a real-time online monitoring method and related device for the temperature distribution of a GIL, including: establishing a GIL simulation model, and determining the variables and monitoring point locations that affect the overall temperature distribution of the GIL. Determine the selection range of the variables, obtain and export the data set containing the variables and the temperature field data set. Extract the temperature data set to obtain the monitoring point temperature data set and the solid domain temperature data set, and perform dimensionality reduction processing on the solid domain temperature data set. Construct an implicit nonlinear relationship between the monitoring point temperature data set and the low-dimensional data set to obtain a calculation model for the solid domain part of the overall temperature of the GIL, and construct a mapping relationship between the solid domain temperature data set and the temperature field data set to obtain an online monitoring model for the overall temperature of the GIL. Input the monitoring point temperature into the model to obtain the overall solid domain temperature distribution of the GIL, and reconstruct the overall temperature distribution of the GIL through the monitoring model, thereby solving the problem that the GIL cannot monitor the internal state of the device in real time.

Description

Technical Field

[0001] The present application relates to the field of electric power technology, and in particular to a real-time online monitoring method and related device for GIL temperature distribution. Background Art

[0002] Gas insulated transmission line (GIL) has been widely used in power systems. The long length of GIL, the large transmission power and its fully enclosed structure lead to high internal heating risks and complexity. Especially for the contact resistance position of the GIL current-carrying conductor, which has a small volume and large flow capacity, local overheating caused by poor contact will cause the insulation performance of GIL to deteriorate and cause short circuit failure.

[0003] At present, there are two main ways to monitor the operating temperature of GIL: indirect temperature measurement based on the shell and infrared non-contact temperature measurement of the conductor. However, the above methods can only provide GIL thermal fault status identification and positioning, and cannot provide accurate internal temperature information. Although simulation calculations can obtain the internal temperature field data of the equipment, finite element simulation software such as ANSYS and COMSOL are currently used, which consumes a lot of time. It is difficult to achieve fast calculation and real-time monitoring in practical applications, and cannot meet the needs of digital real-time evaluation and analysis of power equipment. Therefore, in order to solve the problem of obtaining the internal temperature field of GIL in real time using the limited data of existing external measurements, it is necessary to further develop a data-driven real-time temperature field calculation method to realize real-time status monitoring of the overall temperature field of the GIL internal sliding contact. Summary of the invention

[0004] The present application provides a real-time online monitoring method and related devices for GIL temperature distribution, which are used to solve the problem that the three-phase integrated GIL cannot monitor the internal status of the equipment in real time, and provide a reference for the construction of digital twins of power transmission and transformation equipment, fault diagnosis and status monitoring.

[0005] In view of this, the first aspect of the present application provides a real-time online monitoring method for GIL temperature distribution, the method comprising:

[0006] S1. Establish a three-dimensional simulation model of thermal-fluid coupling of the three-phase integrated GIL, determine the variable z that affects the overall temperature distribution of the three-phase integrated GIL, and determine the location of the monitoring point of the three-phase integrated GIL shell;

[0007] S2. Determine the selection range of the variable z according to the actual operating conditions of the three-phase integrated GIL, obtain a set of data sets Z containing different variables z according to the selection range, and simulate and calculate the corresponding temperature field data set Y, and export the data set according to the preset grid nodes;

[0008] S3, extracting the monitoring point location data in the temperature data set Y to obtain the monitoring point temperature data set Y l ; Extract the solid domain temperature data of the temperature data set Y to obtain the solid domain temperature data set Y s , and the solid domain temperature data set Y s Perform dimensionality reduction processing to obtain a low-dimensional data set D corresponding to the high-dimensional solid domain temperature data set;

[0009] S4, construct the monitoring point temperature data set Y l The implicit nonlinear relationship with the low-dimensional data set D is used to obtain a fast calculation model of the solid domain part of the overall temperature of the three-phase integrated GIL, and the solid domain temperature data set Y is constructed. s The mapping relationship with the temperature field data set Y is used to obtain the three-phase integrated GIL overall temperature online monitoring model;

[0010] S5. The temperature data Y of any monitoring point l The fast calculation model is input to obtain the overall solid domain temperature distribution of the three-phase integrated GIL, and the overall temperature distribution of the three-phase integrated GIL is reconstructed through the online monitoring model.

[0011] Optionally, the variable z includes: ambient temperature, current carrying capacity and ambient wind speed.

[0012] Optionally, obtaining a set of data sets Z containing different variables z according to the selected range includes: obtaining a set of data sets Z containing different variables z in the selected range by an equal interval scanning method.

[0013] Optionally, the solid domain temperature data set Y s Perform dimensionality reduction processing, including: using singular value decomposition method to reduce the solid domain temperature data set Y s Perform dimensionality reduction processing.

[0014] Optionally, the construction of the monitoring point temperature data set Y l The implicit nonlinear relationship with the low-dimensional data set D is used to obtain a fast calculation model of the solid domain part of the overall temperature of the three-phase integrated GIL, and the solid domain temperature data set Y is constructed. s The mapping relationship with the temperature field data set Y is used to obtain the three-phase integrated GIL overall temperature online monitoring model, including:

[0015] The first deep learning method is used to map the monitoring point temperature data set Y l After SVD decomposition with the low-dimensional data set D, the resulting data set is The implicit nonlinear relationship between them is used to obtain a fast calculation model for the solid domain part of the overall temperature of the three-phase integrated GIL.

[0016] The solid domain temperature dataset Y is mapped using a second deep learning method s After SVD decomposition with the temperature field dataset Y, the solid domain temperature dataset Y is obtained. s The mapping relationship with the overall temperature data set Y is obtained to obtain the overall temperature online monitoring model of the three-phase integrated GIL.

[0017] Optionally, the first deep learning method is a BP neural network.

[0018] Optionally, the second deep learning method is a deep convolutional neural network.

[0019] A second aspect of the present application provides a real-time online monitoring system for GIL temperature distribution, the system comprising:

[0020] Establishing a unit for establishing a three-dimensional simulation model of thermal-fluid coupling of the three-phase integrated GIL, determining a variable z that affects the overall temperature distribution of the three-phase integrated GIL, and determining the location of monitoring points of the three-phase integrated GIL shell;

[0021] An acquisition unit is used to determine a selection range of the variable z according to the actual operating conditions of the three-phase integrated GIL, acquire a set of data sets Z containing different variables z according to the selection range, and simulate and calculate the corresponding temperature field data set Y, and export the data set according to the preset grid nodes;

[0022] An extraction unit is used to extract the monitoring point location data in the temperature data set Y to obtain the monitoring point temperature data set Y l ; Extract the solid domain temperature data of the temperature data set Y to obtain the solid domain temperature data set Y s , and the solid domain temperature data set Y s Perform dimensionality reduction processing to obtain a low-dimensional data set D corresponding to the high-dimensional solid domain temperature data set;

[0023] A construction unit, used to construct the monitoring point temperature data set Y l The implicit nonlinear relationship with the low-dimensional data set D is used to obtain a fast calculation model of the solid domain part of the overall temperature of the three-phase integrated GIL, and the solid domain temperature data set Y is constructed. s The mapping relationship with the temperature field data set Y is used to obtain the three-phase integrated GIL overall temperature online monitoring model;

[0024] Monitoring unit, used to convert the temperature data Y of any monitoring point l The fast calculation model is input to obtain the overall solid domain temperature distribution of the three-phase integrated GIL, and the overall temperature distribution of the three-phase integrated GIL is reconstructed through the online monitoring model.

[0025] A third aspect of the present application provides a real-time online monitoring device for GIL temperature distribution, the device comprising a processor and a memory:

[0026] The memory is used to store program code and transmit the program code to the processor;

[0027] The processor is used to execute the steps of the real-time online monitoring method of GIL temperature distribution as described in the first aspect according to the instructions in the program code.

[0028] A fourth aspect of the present application provides a computer-readable storage medium, wherein the computer-readable storage medium is used to store program codes, and the program codes are used to execute the real-time online monitoring method of GIL temperature distribution described in the first aspect above.

[0029] It can be seen from the above technical solutions that this application has the following advantages:

[0030] The present application provides a real-time online monitoring method for GIL temperature distribution, 1) combining data dimension reduction technology and deep learning technology, according to the known real structure and operating conditions of the three-phase integrated GIL, obtaining the implicit nonlinear mapping relationship between the high-fidelity simulation result data and the GIL shell monitoring point, which can realize the real-time state monitoring of the temperature of the three-phase integrated GIL through the sliding contact as a whole and the thermal fault diagnosis of the sliding contact contact resistance. 2) The overall temperature data of the three-phase integrated GIL is separated into fluid and solid, avoiding the influence of the fluid domain temperature data structure on the solid domain temperature data structure characteristics, making the physical characteristics of the solid domain data more obvious during singular value decomposition, and facilitating the accurate construction of the nonlinear relationship between the shell monitoring point temperature and the solid domain temperature. 3) Using the singular value decomposition algorithm based on BP neural network in the solid domain, the temperature prediction of the solid domain is more accurate; using the deep convolutional neural network in the fluid domain to construct the relationship between the solid domain temperature and the fluid domain temperature, it can effectively restore the temperature distribution of the three-phase integrated GIL through the sliding contact as a whole. Thereby solving the problem that the three-phase integrated GIL cannot monitor the internal state of the equipment in real time, and providing a reference for the construction of digital twins of power transmission and transformation equipment, fault diagnosis and state monitoring. BRIEF DESCRIPTION OF THE DRAWINGS

[0031] Figure 1 A schematic flow chart of a real-time online monitoring method for GIL temperature distribution provided in an embodiment of the present application;

[0032] Figure 2 A BP neural network structure diagram for solid domain temperature prediction of a three-phase integrated GIL device provided in an embodiment of the present application;

[0033] Figure 3A structural diagram of a deep convolutional neural network used for fluid domain temperature prediction of a three-phase integrated GIL device provided in an embodiment of the present application;

[0034] Figure 4 A distribution cloud diagram of the finite element calculation of the three-phase integrated GIL device provided in the embodiment of the present application is compared with the real-time simulation output result of the present application;

[0035] Figure 5 It is a diagram showing the error distribution between the prediction results of the three-phase integrated GIL equipment model and the finite element simulation results provided in the embodiment of the present application;

[0036] Figure 6 Schematic diagram of the structure of a real-time online monitoring system for GIL temperature distribution provided in an embodiment of the present application. DETAILED DESCRIPTION

[0037] In order to enable those skilled in the art to better understand the solution of the present application, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0038] See also Figure 1 , a real-time online monitoring method for GIL temperature distribution provided in an embodiment of the present application comprises:

[0039] Step 101: Establish a three-phase integrated GIL thermal-fluid coupled three-dimensional simulation model, determine the variable z that affects the overall temperature distribution of the three-phase integrated GIL, and determine the location of the three-phase integrated GIL shell monitoring point.

[0040] It should be noted that, in one embodiment, according to the actual size requirements of the three-phase integrated GIL, a three-dimensional simulation model of thermal flow coupling of the three-phase integrated GIL is established, the variable z that affects the overall temperature distribution of the three-phase integrated GIL is determined, and the position of the monitoring point of the three-phase integrated GIL shell is determined.

[0041] Among them, the variable z includes: ambient temperature, current carrying capacity and ambient wind speed; the location of the three-phase integrated GIL housing monitoring point needs to calculate the simulation model node number according to the actual location in order to extract its temperature data.

[0042] Step 102: determine the selection range of the variable z according to the actual operating conditions of the three-phase integrated GIL, obtain a set of data sets Z containing different variables z according to the selection range, and simulate and calculate the corresponding temperature field data set Y, and export the data set according to the preset grid nodes.

[0043] It should be noted that, in one embodiment, according to the actual operating conditions of the three-phase integrated GIL, the selection range of the variable z is determined, and a set of data sets Z containing different variables z is obtained within a given range by scanning at equal intervals. N}, simulate and calculate the corresponding temperature field data set Y = {T1, T2, …, TN}, and export it according to the given grid nodes.

[0044] Among them, the equal-interval scanning method needs to determine the upper and lower limits of the main variable parameters according to the simulation calculation, and perform equal-interval sampling on the variable z. Exporting by given grid nodes means that the temperature results under different variables z obtained by simulation calculation without changing the grid division are in the same format, that is, one node coordinate (x, y, z) corresponds to one temperature result.

[0045] Step 103: Extract the monitoring point location data in the temperature data set Y to obtain the monitoring point temperature data set Y l ; Extract the solid domain temperature data of the temperature data set Y to obtain the solid domain temperature data set Y s , and for the solid domain temperature data set Y s Dimensionality reduction processing is performed to obtain a low-dimensional data set D corresponding to the high-dimensional solid domain temperature data set.

[0046] It should be noted that, in one embodiment, the monitoring point location data in the temperature data set Y obtained in step 102 is extracted to obtain the monitoring point temperature data set Y. l ={T l1 ,T l2 ,…,T lN}; Extract the solid domain temperature data of the temperature data set obtained in step 102 to obtain Y s ={T s1 ,T s2 ,…,T sN}, and perform dimensionality reduction processing on it to obtain the low-dimensional data set D corresponding to the high-dimensional solid domain temperature data set.

[0047] Among them, for the solid domain temperature data set Y s The dimensionality reduction process is carried out by using the singular value decomposition method. The processing process is as follows:

[0048] Define the temperature matrix Y sn×m SVD:

[0049] Y s =UΣV T (1)

[0050] Where: U is an n×n matrix, n represents the number of grid nodes, and is a left singular vector; Σ is an n×m matrix, m represents the number of cases of variable z, and is a right singular vector.

[0051] The elements on the diagonal are all singular values, and the rest are all 0 except for the elements on the diagonal; V is an m×m matrix. Arrange the singular values ​​from large to small, and the left and right singular vectors correspond to the singular values ​​one by one. The larger the singular value, the more the corresponding left and right singular vectors occupy the original signal energy. Take the first j singular values ​​and truncate them, then Take the first j rows and first j columns to get a j×j singular matrix. Similarly, we get The original temperature data can be reconstructed by multiplying according to formula (1):

[0052]

[0053] First, the extracted solid domain temperature data is decomposed by SVD, and the specific decomposition is as follows:

[0054] Let matrix A∈R m*n , then there exists an orthogonal matrix U∈R m*m and the orthogonal matrix V∈R n*n ,have

[0055] A=U∑V T (3)

[0056] in: ∑=diag(λ1,λ2,…,λ α )(α=min(m,n)), singular value λ α Satisfies λ1≥λ2≥...≥λ α > 0. The column vector of U is AA T The eigenvector of V is A. T The eigenvector of A.

[0057] According to linear algebra theory, equation (3) can be written in vector form:

[0058]

[0059] u i is the column vector of U, v i is the column vector of V. In order to ensure the accuracy of calculation and prediction model, the singular value λ i The following conditions need to be met:

[0060]

[0061] Among them, η rIt represents the ratio of the first r-order singular values ​​to the sum of all singular values. Under the premise of satisfying the calculation accuracy and not greatly increasing the calculation time, ε is selected as 99.999%. At this time, the reconstructed matrix It can be written as:

[0062]

[0063] Furthermore, the above-mentioned cutoff value j is determined according to the percentage of the first j singular values ​​to the total singular values. Generally, in order to ensure the calculation accuracy, it is required that the percentage of the first j singular values ​​to the total singular values ​​reaches 99.999%.

[0064] It is understandable that in order to ensure the calculation accuracy, after the singular value decomposition of the matrix, the ratio of the first r-order singular values ​​to the total energy must reach 99.999%. When the singular value decomposition is performed on the solid domain, the energy occupied by the first 3-order singular values ​​reaches 99.999%, that is, the original high-order data (180097-order) is reduced to low-order data (3rd order, corresponding to the temperature characteristics of the three current-carrying conductors and the surrounding shell of the three-in-one GIL). However, when the singular value decomposition is performed on the entire calculation domain, the energy occupied by the first 14 singular values ​​can reach 99.999%, that is, the data is reduced to 14th order. Therefore, the fluid-solid separation method can improve the order reduction efficiency of the solid domain temperature and improve the prediction accuracy, making the physical interpretability of the network model stronger.

[0065] Step 104: Construct the monitoring point temperature data set Y l The implicit nonlinear relationship with the low-dimensional data set D is used to obtain a fast calculation model for the solid domain part of the overall temperature of the three-phase integrated GIL, and the solid domain temperature data set Y is constructed. s The mapping relationship with the temperature field data set Y is used to obtain the overall temperature online monitoring model of the three-phase integrated GIL.

[0066] It should be noted that the construction of 103 datasets Y l The implicit nonlinear relationship with the data set D in step 103 is used to obtain the fast calculation model G1 of the solid domain part of the overall temperature of the three-phase integrated GIL. s The mapping relationship with the data set Y in step 102 is used to obtain the three-phase integrated GIL overall temperature online monitoring model G2.

[0067] Furthermore, in one embodiment, a BP neural network is used to map the monitoring point temperature data set Y l After SVD decomposition with the low-dimensional dataset D, the resulting dataset is The implicit nonlinear relationship between them is used to obtain a fast calculation model for the solid domain part of the overall temperature of the three-phase integrated GIL; a deep convolutional neural network is used to map the solid domain temperature dataset Y sAfter SVD decomposition with the temperature field dataset Y, the solid domain temperature dataset Y is obtained. s The mapping relationship between the overall temperature data set Y and the three-phase integrated GIL overall temperature online monitoring model is obtained. Among them, the BP neural network structure diagram is as follows Figure 4 As shown in the figure, the structure of the deep convolutional neural network is as follows Figure 3 shown.

[0068] It should be noted that deep learning methods, including BP neural network, convolutional neural network, etc., are used to construct Y l and The relationship between; the convolutional neural network has a complex structure and is used to construct Y s The relationship between and Y.

[0069] It can be understood that a neural network is a multi-layer feedforward neural network that performs error correction through an error back propagation algorithm. Its structure includes an input layer, a hidden layer, and an output layer, wherein each hidden layer contains multiple neurons for learning the relationship between input and output data. The neural network is based on the U-Net network structure, a classic network for medical image segmentation, and adopts an encoder plus decoder structure as a whole, wherein the encoder is mainly a convolutional layer, which is used to extract the intrinsic features of solid domain temperature data; the decoder is mainly a transposed convolutional layer, which is used to expand the intrinsic features to the original dimension and predict the fluid domain temperature.

[0070] Step 105: The temperature data Y of any monitoring point l The fast calculation model is input to obtain the overall solid domain temperature distribution of the three-phase integrated GIL, and the overall temperature distribution of the three-phase integrated GIL is reconstructed through the online monitoring model.

[0071] It should be noted that the reconstruction method, at any monitoring point temperature data Under the input, the BP neural network model predicts the output result use Reconstruct the data set to obtain the temperature data of the monitoring point Solid domain temperature field distribution data under Then the convolutional neural network model is used to predict the temperature of the solid domain. The entire overall temperature distribution data under.

[0072] Among them, the distribution cloud diagram calculated by finite element method is compared with the real-time simulation output result of this application. Figure 4 As shown, Figure 4 The left half is the finite element calculation result, and the right half is the real-time simulation calculation result of this application. The error distribution diagram between the equipment model prediction result and the finite element simulation result is shown in the figure. Figure 5 shown.

[0073] A real-time online monitoring method for GIL temperature distribution provided in the embodiment of the present application, 1) combining data dimension reduction technology and deep learning technology, according to the real structure and operating conditions of the known three-phase integrated GIL, obtains the implicit nonlinear mapping relationship between the high-fidelity simulation result data and the GIL shell monitoring point, which can realize the real-time state monitoring of the temperature of the three-phase integrated GIL through the sliding contact as a whole and the thermal fault diagnosis of the sliding contact contact resistance. 2) The overall temperature data of the three-phase integrated GIL is separated into fluid and solid, avoiding the influence of the fluid domain temperature data structure on the solid domain temperature data structure characteristics, making the physical characteristics of the solid domain data more obvious during singular value decomposition, and facilitating the accurate construction of the nonlinear relationship between the shell monitoring point temperature and the solid domain temperature. 3) Using the singular value decomposition algorithm based on BP neural network in the solid domain, the temperature prediction of the solid domain is more accurate; using the deep convolutional neural network in the fluid domain to construct the relationship between the solid domain temperature and the fluid domain temperature, it can effectively restore the temperature distribution of the three-phase integrated GIL through the sliding contact as a whole. Thereby solving the problem that the three-phase integrated GIL cannot monitor the internal state of the equipment in real time, and providing a reference for the construction of digital twins of power transmission and transformation equipment, fault diagnosis and state monitoring.

[0074] The above is a real-time online monitoring method for GIL temperature distribution provided in an embodiment of the present application, and the following is a real-time online monitoring system for GIL temperature distribution provided in an embodiment of the present application.

[0075] See also Figure 6 , a real-time online monitoring system for GIL temperature distribution provided in an embodiment of the present application comprises:

[0076] The establishment unit 201 is used to establish a three-phase integrated GIL thermal-fluid coupling three-dimensional simulation model, determine the variable z that affects the overall temperature distribution of the three-phase integrated GIL, and determine the position of the three-phase integrated GIL shell monitoring point.

[0077] The acquisition unit 202 is used to determine the selection range of the variable z according to the actual operating conditions of the three-phase integrated GIL, obtain a set of data sets Z containing different variables z according to the selection range, and simulate and calculate the corresponding temperature field data set Y, and export the data set according to the preset grid nodes.

[0078] Extraction unit 203, used to extract the monitoring point location data in the temperature data set Y to obtain the monitoring point temperature data set Y l ; Extract the solid domain temperature data of the temperature data set Y to obtain the solid domain temperature data set Y s , and for the solid domain temperature data set Y s Dimensionality reduction processing is performed to obtain a low-dimensional data set D corresponding to the high-dimensional solid domain temperature data set.

[0079] Construction unit 204, used to construct monitoring point temperature data set Y l The implicit nonlinear relationship with the low-dimensional data set D is used to obtain a fast calculation model for the solid domain part of the overall temperature of the three-phase integrated GIL, and the solid domain temperature data set Y is constructed. s The mapping relationship with the temperature field data set Y is used to obtain the overall temperature online monitoring model of the three-phase integrated GIL.

[0080] Monitoring unit 205, used to convert the temperature data Y of any monitoring point l The fast calculation model is input to obtain the overall solid domain temperature distribution of the three-phase integrated GIL, and the overall temperature distribution of the three-phase integrated GIL is reconstructed through the online monitoring model.

[0081] Furthermore, a real-time online monitoring device for GIL temperature distribution is provided in an embodiment of the present application, and the device includes a processor and a memory:

[0082] The memory is used to store program code and transmit the program code to the processor;

[0083] The processor is used to execute the steps of the real-time online monitoring method of GIL temperature distribution as described in the above method embodiment according to the instructions in the program code.

[0084] Furthermore, a computer-readable storage medium is provided in an embodiment of the present application, and the computer-readable storage medium is used to store program codes, and the program codes are used to execute the real-time online monitoring method of GIL temperature distribution described in the above method embodiment.

[0085] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the systems and units described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0086] The terms "first", "second", "third", "fourth", etc. (if any) in the specification of the present application and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchangeable where appropriate, so that the embodiments of the present application described herein can be implemented in an order other than those illustrated or described herein, for example. In addition, the terms "including" and "having" and any of their variations are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device comprising a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0087] It should be understood that in the present application, "at least one (item)" means one or more, and "plurality" means two or more. "And / or" is used to describe the association relationship of associated objects, indicating that three relationships may exist. For example, "A and / or B" can mean: only A exists, only B exists, and A and B exist at the same time, where A and B can be singular or plural. The character " / " generally indicates that the objects associated before and after are in an "or" relationship. "At least one of the following" or similar expressions refers to any combination of these items, including any combination of single or plural items. For example, at least one of a, b or c can mean: a, b, c, "a and b", "a and c", "b and c", or "a and b and c", where a, b, c can be single or multiple.

[0088] In the several embodiments provided in the present application, it should be understood that the disclosed systems, devices and methods can be implemented in other ways. For example, the device embodiments described above are only schematic. For example, the division of the units is only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be an indirect coupling or communication connection through some interfaces, devices or units, which can be electrical, mechanical or other forms.

[0089] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0090] In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.

[0091] If the integrated unit is implemented in the form of 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, the technical solution of the present application is essentially or the part that contributes to the prior art or all or part of the technical solution can be embodied in the form of a software product, and the computer software product is stored in a storage medium, including a number of instructions to enable a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present application. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (full name in English: Read-Only Memory, English abbreviation: ROM), random access memory (full name in English: Random Access Memory, English abbreviation: RAM), disk or optical disk and other media that can store program codes.

[0092] As described above, the above embodiments are only used to illustrate the technical solutions of the present application, rather than to limit them. Although the present application has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present application.

Claims

1. A real-time online monitoring method for GIL temperature distribution, characterized in that: include: S1. Establish a three-dimensional simulation model of thermal-fluid coupling of the three-phase integrated GIL, determine the variable z that affects the overall temperature distribution of the three-phase integrated GIL, and determine the location of the monitoring point of the three-phase integrated GIL shell; S2. Determine the selection range of the variable z according to the actual operating conditions of the three-phase integrated GIL, obtain a set of data sets Z containing different variables z according to the selection range, and simulate and calculate the corresponding temperature field data set Y, and export the data set according to the preset grid nodes; S3, extracting the monitoring point location data in the temperature data set Y to obtain the monitoring point temperature data set Y l ; Extract the solid domain temperature data of the temperature data set Y to obtain the solid domain temperature data set Y s , and the solid domain temperature data set Y s Perform dimensionality reduction processing to obtain a low-dimensional data set D corresponding to the high-dimensional solid domain temperature data set; S4, construct the monitoring point temperature data set Y l The implicit nonlinear relationship with the low-dimensional data set D is used to obtain a fast calculation model of the solid domain part of the overall temperature of the three-phase integrated GIL, and the solid domain temperature data set Y is constructed. s The mapping relationship with the temperature field data set Y is used to obtain the three-phase integrated GIL overall temperature online monitoring model; S5. The temperature data Y of any monitoring point l The fast calculation model is input to obtain the overall solid domain temperature distribution of the three-phase integrated GIL, and the overall temperature distribution of the three-phase integrated GIL is reconstructed through the online monitoring model.

2. The real-time online monitoring method of GIL temperature distribution according to claim 1, characterized in that: The variable z includes: ambient temperature, current carrying capacity and ambient wind speed.

3. The real-time online monitoring method of GIL temperature distribution according to claim 1, characterized in that: Acquiring a set of data sets Z containing different variables z according to the selected range includes: acquiring a set of data sets Z containing different variables z in the selected range by an equal interval scanning method.

4. The real-time online monitoring method of GIL temperature distribution according to claim 1, characterized in that: The solid domain temperature data set Y s Perform dimensionality reduction processing, including: using singular value decomposition method to reduce the solid domain temperature data set Y s Perform dimensionality reduction processing.

5. The real-time online monitoring method of GIL temperature distribution according to claim 1, characterized in that: The construction of the monitoring point temperature data set Y l The implicit nonlinear relationship with the low-dimensional data set D is used to obtain a fast calculation model of the solid domain part of the overall temperature of the three-phase integrated GIL, and the solid domain temperature data set Y is constructed. s The mapping relationship with the temperature field data set Y is used to obtain the three-phase integrated GIL overall temperature online monitoring model, including: The first deep learning method is used to map the monitoring point temperature data set Y l After SVD decomposition with the low-dimensional data set D, the resulting data set is The implicit nonlinear relationship between them is used to obtain a fast calculation model for the solid domain part of the overall temperature of the three-phase integrated GIL. The solid domain temperature dataset Y is mapped using a second deep learning method s After SVD decomposition with the temperature field dataset Y, the solid domain temperature dataset Y is obtained. s The mapping relationship with the overall temperature data set Y is obtained to obtain the overall temperature online monitoring model of the three-phase integrated GIL.

6. The real-time online monitoring method of GIL temperature distribution according to claim 5, characterized in that: The first deep learning method is BP neural network.

7. The real-time online monitoring method of GIL temperature distribution according to claim 5, characterized in that: The second deep learning method is a deep convolutional neural network.

8. A real-time online monitoring system for GIL temperature distribution, characterized in that: include: Establishing a unit for establishing a three-dimensional simulation model of thermal-fluid coupling of the three-phase integrated GIL, determining a variable z that affects the overall temperature distribution of the three-phase integrated GIL, and determining the location of monitoring points of the three-phase integrated GIL shell; An acquisition unit is used to determine a selection range of the variable z according to the actual operating conditions of the three-phase integrated GIL, acquire a set of data sets Z containing different variables z according to the selection range, and simulate and calculate the corresponding temperature field data set Y, and export the data set according to the preset grid nodes; An extraction unit is used to extract the monitoring point location data in the temperature data set Y to obtain the monitoring point temperature data set Y l ; Extract the solid domain temperature data of the temperature data set Y to obtain the solid domain temperature data set Y s , and the solid domain temperature data set Y s Perform dimensionality reduction processing to obtain a low-dimensional data set D corresponding to the high-dimensional solid domain temperature data set; A construction unit, used to construct the monitoring point temperature data set Y l The implicit nonlinear relationship with the low-dimensional data set D is used to obtain a fast calculation model of the solid domain part of the overall temperature of the three-phase integrated GIL, and the solid domain temperature data set Y is constructed. s The mapping relationship with the temperature field data set Y is used to obtain the three-phase integrated GIL overall temperature online monitoring model; Monitoring unit, used to convert the temperature data Y of any monitoring point l The fast calculation model is input to obtain the overall solid domain temperature distribution of the three-phase integrated GIL, and the overall temperature distribution of the three-phase integrated GIL is reconstructed through the online monitoring model.

9. A real-time online monitoring device for GIL temperature distribution, characterized in that: The device comprises a processor and a memory: The memory is used to store program code and transmit the program code to the processor; The processor is used to execute the real-time online monitoring method of GIL temperature distribution according to any one of claims 1 to 7 according to the instructions in the program code.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium is used to store program codes, and the program codes are used to execute the real-time online monitoring method of GIL temperature distribution according to any one of claims 1 to 7.

Images