CN117371291A - Power equipment temperature field distribution calculation method, device, equipment and medium - Google Patents
Power equipment temperature field distribution calculation method, device, equipment and medium Download PDFInfo
- Publication number
- CN117371291A CN117371291A CN202311440844.3A CN202311440844A CN117371291A CN 117371291 A CN117371291 A CN 117371291A CN 202311440844 A CN202311440844 A CN 202311440844A CN 117371291 A CN117371291 A CN 117371291A
- Authority
- CN
- China
- Prior art keywords
- fluid
- module
- flow
- flow rate
- rate
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000009826 distribution Methods 0.000 title claims abstract description 107
- 238000004364 calculation method Methods 0.000 title claims abstract description 44
- 239000012530 fluid Substances 0.000 claims abstract description 293
- 238000000034 method Methods 0.000 claims abstract description 64
- 238000013507 mapping Methods 0.000 claims abstract description 59
- 239000000463 material Substances 0.000 claims abstract description 44
- 238000013528 artificial neural network Methods 0.000 claims description 8
- 238000003860 storage Methods 0.000 claims description 6
- 238000000605 extraction Methods 0.000 claims description 4
- 238000010586 diagram Methods 0.000 description 10
- 230000008569 process Effects 0.000 description 9
- 238000004088 simulation Methods 0.000 description 8
- 238000004590 computer program Methods 0.000 description 7
- 238000010801 machine learning Methods 0.000 description 6
- 230000008878 coupling Effects 0.000 description 4
- 238000010168 coupling process Methods 0.000 description 4
- 238000005859 coupling reaction Methods 0.000 description 4
- 238000005516 engineering process Methods 0.000 description 4
- 230000006870 function Effects 0.000 description 4
- 238000012545 processing Methods 0.000 description 4
- 230000009471 action Effects 0.000 description 3
- 238000010276 construction Methods 0.000 description 3
- 238000012986 modification Methods 0.000 description 3
- 230000004048 modification Effects 0.000 description 3
- 229910000838 Al alloy Inorganic materials 0.000 description 2
- 238000012549 training Methods 0.000 description 2
- 239000004593 Epoxy Substances 0.000 description 1
- 230000004075 alteration Effects 0.000 description 1
- 238000004458 analytical method Methods 0.000 description 1
- 239000002131 composite material Substances 0.000 description 1
- 239000004020 conductor Substances 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000002500 effect on skin Effects 0.000 description 1
- 238000011156 evaluation Methods 0.000 description 1
- 239000012212 insulator Substances 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 239000011159 matrix material Substances 0.000 description 1
- 229910052751 metal Inorganic materials 0.000 description 1
- 239000002184 metal Substances 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 230000000750 progressive effect Effects 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 238000010408 sweeping Methods 0.000 description 1
- 238000002076 thermal analysis method Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F30/00—Computer-aided design [CAD]
- G06F30/20—Design optimisation, verification or simulation
- G06F30/23—Design optimisation, verification or simulation using finite element methods [FEM] or finite difference methods [FDM]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F30/00—Computer-aided design [CAD]
- G06F30/20—Design optimisation, verification or simulation
- G06F30/27—Design optimisation, verification or simulation using machine learning, e.g. artificial intelligence, neural networks, support vector machines [SVM] or training a model
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2113/00—Details relating to the application field
- G06F2113/08—Fluids
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2119/00—Details relating to the type or aim of the analysis or the optimisation
- G06F2119/08—Thermal analysis or thermal optimisation
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Evolutionary Computation (AREA)
- General Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- Geometry (AREA)
- Computer Hardware Design (AREA)
- Artificial Intelligence (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Medical Informatics (AREA)
- Software Systems (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention discloses a method, a device, equipment and a medium for calculating temperature field distribution of power equipment, which are used for solving the technical problems that the existing method for calculating temperature field distribution based on a finite element method is low in efficiency, and a rapid calculation mode of temperature field distribution based on data driving is easy to generate larger calculation errors locally. Comprising the following steps: calculating equipment temperature field distribution data of the power equipment under the condition of presetting a plurality of groups of side values; dividing a non-fluid material region of the electrical device into non-fluid modules; extracting a fluid flow rate of a fluid domain of the electrical device; dividing the fluid domain into a high flow rate fluid module and a low flow rate fluid module; respectively acquiring temperature data of the non-fluid module, the high-flow-rate fluid module and the low-flow-rate fluid module under the condition of each side value; respectively establishing mapping relations between each boundary condition and temperature data of the non-fluid module, the high-flow-rate fluid module and the low-flow-rate fluid module; and acquiring the temperature field distribution of the target equipment corresponding to the boundary value condition to be analyzed according to the boundary value condition and the mapping relation.
Description
Technical Field
The present invention relates to the field of power equipment technologies, and in particular, to a method, an apparatus, a device, and a medium for calculating a temperature field distribution of a power equipment.
Background
The key technology of multi-physical field simulation is one of important technologies for research, development and application of digital twin bodies, and solves the distribution characteristics of the whole multi-physical field of the equipment under a certain boundary value condition through coupling and constitutive relation among physical fields, so that the equipment is evaluated and analyzed according to field quantity distribution. However, most of the solution quantity of the multiple physical fields is in a partial differential equation or an integral form, and is more complex when the coupling condition is involved, so that the solution process needs long time and poor convergence, and often has higher requirements on hard addition, and meanwhile, the solution time in hours or days also does not meet the requirements of digital twin on the entity image. Therefore, a multi-physical-field distribution rapid extraction output technology with real-time performance is developed, the multi-physical-field simulation can be accurately output in real time when the digital twin system is applied, and the method has important significance for on-line evaluation analysis and state early warning of equipment.
The multi-physical-field rapid computing method based on machine learning is widely proposed, and according to limited multi-physical-field simulation grid node data, boundary conditions during simulation and fitting relations of all nodes are constructed, so that distribution results under other different conditions are rapidly obtained. However, the method always takes many results of the multi-physical-field simulation into the machine learning data set, and the adopted learning method and parameters do not consider the characteristics of the multi-physical-field distribution, so that local larger errors can be generated in the calculation process; meanwhile, a machine learning model is built on all data, the model is large in model quantity and high in cost, and the output efficiency of a calculation result is limited to a certain extent.
Disclosure of Invention
The invention provides a method, a device, equipment and a medium for calculating temperature field distribution of power equipment, which are used for solving the technical problems that the existing method for calculating temperature field distribution based on a finite element method is low in efficiency, and a rapid calculation mode of temperature field distribution based on data driving is easy to generate larger calculation errors locally.
The invention provides a method for calculating the temperature field distribution of power equipment, which comprises the following steps:
calculating equipment temperature field distribution data respectively corresponding to the power equipment under the condition of presetting a plurality of groups of side values;
acquiring a non-fluid material area of the power equipment, and dividing the non-fluid material area into a plurality of non-fluid modules;
extracting a fluid flow rate of a fluid domain of the electrical device according to the device temperature field distribution data;
dividing the fluid domain into a plurality of high-flow-rate fluid modules and low-flow-rate fluid modules according to the fluid flow rate;
temperature data of the non-fluid module, the high-flow-rate fluid module and the low-flow-rate fluid module under the boundary conditions are respectively obtained from the equipment temperature field distribution data;
respectively establishing mapping relations between each side value condition and temperature data of the non-fluid module, the high-flow-rate fluid module and the low-flow-rate fluid module;
acquiring an edge value condition to be analyzed, and acquiring target equipment temperature field distribution corresponding to the edge value condition to be analyzed according to the edge value condition and the mapping relation.
Optionally, the step of obtaining a non-fluid material area of the electrical device and dividing the non-fluid material area into a plurality of non-fluid modules includes:
acquiring a non-fluid material region of the electrical device;
the non-fluid material region is divided into a number of non-fluid modules, subject to a closed boundary.
Optionally, the device temperature field distribution data includes coordinates, temperature and flow rate.
Optionally, the step of dividing the fluid domain into a plurality of high flow rate fluid modules and low flow rate fluid modules according to the fluid flow rate includes:
obtaining a highest flow rate of the fluid domain;
determining a flow rate threshold according to the highest flow rate;
dividing a region where the fluid flow rate reaches the flow rate threshold into high-flow-rate fluid modules;
the region where the fluid flow rate is less than the flow rate threshold is divided into low flow rate fluid modules.
Optionally, the step of establishing a mapping relationship between each edge condition of the non-fluid module, the high-flow-rate fluid module, and the low-flow-rate fluid module and temperature data respectively includes:
constructing a mapping relation between the boundary value condition of the non-fluid module and temperature data by a linear fitting method;
constructing a mapping relation between the boundary value condition of the low-flow-rate fluid module and temperature data by a polynomial regression method;
and constructing the mapping relation between the boundary value condition of the high-flow-rate fluid and the temperature data by a neural network learning method.
The invention also provides a device for calculating the temperature field distribution of the power equipment, which comprises the following components:
the equipment temperature field distribution data calculation module is used for calculating equipment temperature field distribution data respectively corresponding to the power equipment under the condition of presetting a plurality of groups of side values;
the non-fluid module dividing module is used for acquiring a non-fluid material area of the power equipment and dividing the non-fluid material area into a plurality of non-fluid modules;
a fluid flow rate extraction module for extracting a fluid flow rate of a fluid domain of the electrical device according to the device temperature field distribution data;
the fluid module dividing module is used for dividing the fluid domain into a plurality of high-flow-rate fluid modules and low-flow-rate fluid modules according to the fluid flow rate;
the temperature data acquisition module is used for respectively acquiring temperature data of the non-fluid module, the high-flow-rate fluid module and the low-flow-rate fluid module under the boundary value conditions from the equipment temperature field distribution data;
the mapping relation establishing module is used for respectively establishing the mapping relation between the boundary value conditions and the temperature data of the non-fluid module, the high-flow-rate fluid module and the low-flow-rate fluid module;
the target equipment temperature field distribution acquisition module is used for acquiring the boundary value conditions to be analyzed and acquiring the target equipment temperature field distribution corresponding to the boundary value conditions to be analyzed according to the boundary value conditions and the mapping relation.
Optionally, the non-fluid module dividing module includes:
a non-fluid material region acquisition sub-module for acquiring a non-fluid material region of the electrical device;
and the non-fluid module dividing sub-module is used for dividing the non-fluid material area into a plurality of non-fluid modules on the condition of a closed boundary.
Optionally, the fluid module dividing module includes:
a maximum flow rate acquisition sub-module for acquiring a maximum flow rate of the fluid domain;
a flow rate threshold determining submodule for determining a flow rate threshold according to the highest flow rate;
dividing the region of the fluid flow rate reaching the flow rate threshold into high-flow-rate fluid modules by the high-flow-rate fluid module dividing sub-modules;
and the low-flow-rate fluid module is used for dividing the area with the fluid flow rate smaller than the flow rate threshold into low-flow-rate fluid modules.
The invention also provides an electronic device comprising a processor and a memory:
the memory is used for storing program codes and transmitting the program codes to the processor;
the processor is configured to perform the power device temperature field distribution calculation method according to any one of the above claims according to instructions in the program code.
The present invention also provides a computer-readable storage medium for storing program code for executing the power equipment temperature field distribution calculation method as set forth in any one of the above.
From the above technical scheme, the invention has the following advantages: the invention discloses a method for calculating the temperature field distribution of power equipment, which comprises the following steps: calculating equipment temperature field distribution data respectively corresponding to the power equipment under the condition of presetting a plurality of groups of side values; acquiring a non-fluid material area of the power equipment, and dividing the non-fluid material area into a plurality of non-fluid modules; extracting a fluid flow rate of a fluid domain of the electrical device according to the device temperature field distribution data; dividing the fluid domain into a plurality of high-flow-rate fluid modules and low-flow-rate fluid modules according to the flow rate of the fluid; respectively acquiring temperature data of a non-fluid module, a high-flow-rate fluid module and a low-flow-rate fluid module under the condition of each side value from equipment temperature field distribution data; respectively establishing mapping relations between each boundary condition and temperature data of the non-fluid module, the high-flow-rate fluid module and the low-flow-rate fluid module; acquiring the boundary value condition to be analyzed, and acquiring the temperature field distribution of the target equipment corresponding to the boundary value condition to be analyzed according to the boundary value condition and the mapping relation. According to the method, the region division is carried out according to the multi-physical-field distribution and the field solving characteristics of the power equipment, and different specific quick calculation methods are matched with different regions, so that the physical-field characteristics and the quick calculation methods are mutually related, the accuracy of the quick calculation method based on data driving can be effectively improved, and the distortion of local calculation results are avoided. On the basis of regional division, the method and the device realize quick matching between the boundary value condition and the equipment temperature field distribution in a mapping mode, thereby improving the calculation efficiency of the power equipment temperature field distribution.
Drawings
In order to more clearly illustrate the embodiments of the invention or the technical solutions of the prior art, the drawings which are used in the description of the embodiments or the prior art will be briefly described, it being obvious that the drawings in the description below are only some embodiments of the invention, and that other drawings can be obtained from these drawings without inventive faculty for a person skilled in the art.
Fig. 1 is a flowchart of steps of a method for calculating a temperature field distribution of an electrical device according to an embodiment of the present invention;
fig. 2 is a flowchart illustrating steps of a method for calculating a temperature field distribution of an electrical device according to another embodiment of the present invention;
FIG. 3 is a schematic diagram of a neural network according to an embodiment of the present invention;
fig. 4 is a block diagram of a temperature field distribution calculating device for an electrical device according to an embodiment of the present invention;
fig. 5 is a schematic diagram illustrating a division of a high-flow-rate fluid module and a low-flow-rate fluid module according to an embodiment of the present invention.
Detailed Description
The embodiment of the invention provides a method, a device, equipment and a medium for calculating temperature field distribution of power equipment, which are used for solving the technical problems that the existing method for calculating temperature field distribution based on a finite element method is low in efficiency, and a rapid calculation mode for temperature field distribution based on data driving is easy to generate larger calculation errors locally.
In order to make the objects, features and advantages of the present invention more comprehensible, the technical solutions in the embodiments of the present invention are described in detail below with reference to the accompanying drawings, and it is apparent that the embodiments described below are only some embodiments of the present invention, but not all embodiments of the present invention. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
Referring to fig. 1, fig. 1 is a flowchart illustrating steps of a method for calculating a temperature field distribution of an electrical device according to an embodiment of the present invention.
The invention provides a power equipment temperature field distribution calculation method, which specifically comprises the following steps:
step 101, calculating equipment temperature field distribution data respectively corresponding to the power equipment under the condition of presetting a plurality of groups of side values;
in the embodiment of the invention, the boundary value condition is the operation working condition which can influence the distribution of the temperature field of the power equipment when being simulated, and comprises current waveform, ambient temperature, ambient humidity, wind speed and the like.
In a specific implementation, an electromagnetic-thermal-flow coupling simulation calculation method can be adopted to calculate the boundary value condition Γ of the power equipment 1 、Γ 2 、……、Γ n The temperature field distribution data T of the equipment corresponding to the temperature field distribution data T 1 、T 2 、……、T n 。
The electromagnetic-thermal-flow coupling simulation method comprises the following calculation processes:
when the finite element simulation model, the boundary conditions and the calculated initial values are given, the magnetic field module in COMSOL Multiphysics is used for calculating the Joule loss considering the skin effect, node data are extracted and imported into ANSYS CFX to serve as a heat source for fluid thermal analysis to calculate temperature field distribution, and the material properties of metal and fluid are corrected according to the initial calculation result. If the ith iteration satisfies T i -T i-1 <δ, then the calculation iteration is considered to have converged,the temperature field distribution results are calculated stably. Otherwise, the Joule loss and the temperature field distribution are recalculated until the convergence condition is satisfied. Wherein delta takes a value of 0.1K.
The temperature field distribution data under different boundary conditions can be obtained by a sweeping mode, namely, after one combination (current waveform, ambient temperature, ambient humidity and wind speed) is input, one group of temperature field distribution data is obtained by calculation and the result is stored, then another group of combinations is input, and so on.
102, acquiring a non-fluid material area of an electric power device, and dividing the non-fluid material area into a plurality of non-fluid modules;
in an embodiment of the invention, the interior of the electrical device comprises a region of fluid material and a region of non-fluid material, the non-fluid material being a component of each device. Taking the three-phase common box GIL as an example, the non-fluid material includes an epoxy composite material for supporting an insulator, an aluminum alloy of a current carrying conductor, an aluminum alloy of a housing, and the like.
According to the material and property of the non-fluid material, the non-fluid material area can be divided into a plurality of non-fluid modules.
Step 103, extracting the fluid flow rate of the fluid domain of the electric power equipment according to the equipment temperature field distribution data;
the fluid domain is the region where the fluid material is located in the power equipment, and comprises gas, transformer oil and the like.
Fluid flow rate refers to the velocity of fluid within a fluid domain.
In the embodiment of the invention, the expression form of the equipment temperature field distribution data can be coordinate-temperature-flow rate, and the fluid flow rate of the fluid domain of the electric equipment under the condition of each side value can be extracted according to the equipment temperature field distribution data.
Step 104, dividing the fluid domain into a plurality of high-flow-rate fluid modules and low-flow-rate fluid modules according to the fluid flow rate;
the fluid domain may be divided into a number of high flow rate fluid modules and low flow rate fluid modules according to the fluid flow rate.
In one example, a flow rate below the maximum flow rate may be selected as a basis for dividing the high flow rate fluid module and the low flow rate fluid module based on the maximum flow rate of the fluid domain.
Step 105, respectively acquiring temperature data of a non-fluid module, a high-flow-rate fluid module and a low-flow-rate fluid module under the condition of each side value from equipment temperature field distribution data;
step 106, respectively establishing mapping relations between each boundary condition and temperature data of the non-fluid module, the high-flow-rate fluid module and the low-flow-rate fluid module;
after the module division result (including the non-fluid module, the high-flow-rate fluid module and the low-flow-rate fluid module) of the power equipment under each side value condition is obtained, temperature data can be matched for each module according to the equipment temperature field distribution data. And building mapping relation of gamma and T under different boundary values of each module, and outputting a mapping relation model A 1 、A 2 ……A m Where m is the number of modules.
And step 107, acquiring an edge value condition to be analyzed, and acquiring the temperature field distribution of the target equipment corresponding to the edge value condition to be analyzed according to the edge value condition and the mapping relation.
After the mapping relation model is built, inputting a specified boundary value condition to be analyzed, and obtaining the temperature field distribution A under each module by applying the mapping relation of each module 1 (Γ x )、A 2 (Γ x )、……、A m (Γ x )。
Because the mapping relation is split and modeled according to each module in the process of constructing the mapping relation, after the temperature field distribution of each module under the condition of the boundary value to be analyzed is calculated, the results are spliced for restoring the overall temperature field distribution of the power equipment, and specifically, the output results of the mapping relation model of each module can be recombined according to the geometric relation to obtain the temperature field distribution T under the condition of the boundary value to be analyzed x 。
According to the method, the region division is carried out according to the multi-physical-field distribution and the field solving characteristics of the power equipment, and different specific quick calculation methods are matched with different regions, so that the physical-field characteristics and the quick calculation methods are mutually related, the accuracy of the quick calculation method based on data driving can be effectively improved, and the distortion of local calculation results are avoided. On the basis of regional division, the method and the device realize quick matching between the boundary value condition and the equipment temperature field distribution in a mapping mode, thereby improving the calculation efficiency of the power equipment temperature field distribution. .
Referring to fig. 2, fig. 2 is a flowchart illustrating a method for calculating a temperature field distribution of an electrical device according to another embodiment of the present invention. The method specifically comprises the following steps:
step 201, calculating equipment temperature field distribution data of the power equipment, which correspond to the power equipment under the condition of presetting a plurality of groups of side values;
in the embodiment of the present invention, step 201 is the same as step 101, and specific reference may be made to the description of step 101, which is not repeated here.
Step 202, acquiring a non-fluid material area of an electric power device;
step 203, dividing the non-fluid material area into a plurality of non-fluid modules on the condition of the closed boundary;
in embodiments of the present invention, the non-fluid material region with a closed boundary may be referred to as a non-fluid module.
Step 204, extracting the fluid flow rate of the fluid domain of the electric power equipment according to the equipment temperature field distribution data;
in embodiments of the present invention, the device temperature field distribution data may include coordinates, temperature, and flow rate; and according to the equipment temperature field distribution data, the fluid flow rate of the fluid domain of the electric equipment under the condition of each side value can be extracted. .
Step 205, dividing the fluid domain into a plurality of high-flow-rate fluid modules and low-flow-rate fluid modules according to the fluid flow rate;
the fluid domain may be divided into a number of high flow rate fluid modules and low flow rate fluid modules according to the fluid flow rate.
In one example, the step of dividing the fluid domain into a number of high flow rate fluid modules and low flow rate fluid modules according to the fluid flow rate may comprise the substeps of:
s51, obtaining the highest flow rate of the fluid domain;
s52, determining a flow rate threshold according to the highest flow rate;
s53, dividing the area where the fluid flow rate reaches the flow rate threshold into high-flow-rate fluid modules;
s54, dividing the area where the fluid flow rate is less than the flow rate threshold into low flow rate fluid modules.
In a specific implementation, a flow rate lower than the highest flow rate may be selected as a flow rate threshold based on the highest flow rate of the fluid domain, so as to divide the high flow rate fluid module and the low flow rate fluid module according to the flow rate threshold. Wherein the flow rate threshold may be 80% of the maximum flow rate. In addition, those skilled in the art may select other values according to actual needs, and the embodiment of the present invention is not limited thereto.
Further, after the fluid modules are divided according to the flow rate threshold, a minimum-scale rectangle surrounding the fluid modules (high-flow-rate fluid modules and low-flow-rate fluid modules) can be used as a criterion, and when the matrix boundary intersects with the fluid boundary layer, the boundary layer is converted into the fluid boundary to normalize the shape of the fluid modules. As shown in fig. 5 for module 6.
Step 206, respectively obtaining temperature data of the non-fluid module, the high-flow-rate fluid module and the low-flow-rate fluid module under the condition of each side value from the equipment temperature field distribution data;
step 207, respectively establishing mapping relations between each boundary condition and temperature data of the non-fluid module, the high-flow-rate fluid module and the low-flow-rate fluid module;
after the module division result (including the non-fluid module, the high-flow-rate fluid module and the low-flow-rate fluid module) of the power equipment under each side value condition is obtained, temperature data can be matched for each module according to the equipment temperature field distribution data. And building mapping relation of gamma and T under different boundary values of each module, and outputting a mapping relation model A 1 、A 2 ……A m Where m is the number of modules.
In one example, the step of respectively establishing the mapping relation between the side value conditions of the non-fluid module, the high-flow-rate fluid module and the low-flow-rate fluid module and the temperature data may specifically include the following substeps:
s71, constructing a mapping relation between the boundary value condition of the non-fluid module and temperature data by a linear fitting method;
in a specific implementation, the mapping model constructed by the linear fitting method is as follows:
t nj ＝k 1 Γ n1 +k 2 Γ n2 +k 3 Γ n3 +c
wherein t is nj As temperature data Γ n1 、Γ n2 、Γ n3 Respectively are different working conditions k in a group of boundary conditions 1 、k 2 、k 3 C can be obtained by the least squares method.
S72, constructing a mapping relation between the boundary value condition of the low-flow-rate fluid module and temperature data by a polynomial regression method;
in a specific implementation, the mapping model constructed by the polynomial regression method is as follows:
wherein epsilon is the observation error; Γ -shaped structure nq 、Γ np Different working conditions in a set of boundary conditions; beta 0 、β q 、β qq 、β pq Is the fitting coefficient.
S73, constructing a mapping relation between the boundary value condition of the high-flow-rate fluid and the temperature data through a neural network learning method.
In a specific implementation, by incorporating Γ n As an input to the neural network, T 'will be' n ＝(t n1 ,t n2 ,t n3 ,…,t nj ) As an output of the neural network, the neural network shown in fig. 3 is trained to obtain a corresponding mapping model.
And step 208, acquiring the boundary value condition to be analyzed, and acquiring the temperature field distribution of the target equipment corresponding to the boundary value condition to be analyzed according to the boundary value condition and the mapping relation.
Building a mapping relation modelThen, inputting the designated boundary value condition to be analyzed, and obtaining the temperature field distribution A under each module by applying the mapping relation of each module 1 (Γ x )、A 2 (Γ x )、……、A m (Γ x )。
Because the mapping relation is split and modeled according to each module in the process of constructing the mapping relation, after the temperature field distribution of each module under the condition of the boundary value to be analyzed is calculated, the results are spliced for restoring the overall temperature field distribution of the power equipment, and specifically, the output results of the mapping relation model of each module can be recombined according to the geometric relation to obtain the temperature field distribution T under the condition of the boundary value to be analyzed x 。
According to the method, the region division is carried out according to the multi-physical-field distribution and the field solving characteristics of the power equipment, and different specific quick calculation methods are matched with different regions, so that the physical-field characteristics and the quick calculation methods are mutually related, the accuracy of the quick calculation method based on data driving can be effectively improved, and the distortion of local calculation results are avoided. Furthermore, on the basis of region division, the invention builds a high-level machine learning model for the complex region, and selects a linear method for the simple linear region, so that the model building and training time of the multi-physical-field rapid calculation method is short, and the model training cost of the whole data set as input is reduced. Furthermore, because the high-level multi-level machine learning model has large quantity, the time required for word output is slower than that of the common model, and the regional module division is adopted, so that the data quantity required to be output by the high-level machine learning model is greatly reduced, and the low-level linear model is used as a substitute, so that the output time of quick calculation can be effectively shortened, and the instantaneity of a calculation result is further improved.
Referring to fig. 4, fig. 4 is a block diagram illustrating a temperature field distribution calculating apparatus for an electrical device according to an embodiment of the present invention.
The embodiment of the invention provides a power equipment temperature field distribution calculating device, which comprises:
the device temperature field distribution data calculation module 401 is configured to calculate device temperature field distribution data corresponding to the power device under the condition of preset multiple groups of edge values;
a non-fluid module dividing module 402, configured to obtain a non-fluid material area of the electrical device, and divide the non-fluid material area into a plurality of non-fluid modules;
a fluid flow rate extraction module 403 for extracting a fluid flow rate of a fluid domain of the electrical device from the device temperature field distribution data;
a fluid module dividing module 404, configured to divide the fluid domain into a plurality of high-flow-rate fluid modules and low-flow-rate fluid modules according to the flow rate of the fluid;
a temperature data obtaining module 405, configured to obtain temperature data of the non-fluid module, the high-flow-rate fluid module, and the low-flow-rate fluid module under each boundary condition from the device temperature field distribution data;
the mapping relation establishing module 406 is configured to establish mapping relation between each side value condition of the non-fluid module, the high-flow-rate fluid module, and the low-flow-rate fluid module and the temperature data;
the target device temperature field distribution obtaining module 407 is configured to obtain an edge value condition to be analyzed, and obtain a target device temperature field distribution corresponding to the edge value condition to be analyzed according to the edge value condition and the mapping relationship.
In an embodiment of the present invention, the non-fluid module dividing module 402 includes:
a non-fluid material region acquisition sub-module for acquiring a non-fluid material region of the electrical device;
the non-fluid module divides the sub-module and is used for dividing the non-fluid material area into a plurality of non-fluid modules on the condition of the closed boundary.
In an embodiment of the present invention, the fluid module dividing module 404 includes:
a maximum flow rate acquisition sub-module for acquiring a maximum flow rate of the fluid domain;
the flow rate threshold value determining submodule is used for determining a flow rate threshold value according to the highest flow rate;
dividing the region of the fluid flow rate reaching the flow rate threshold into high-flow-rate fluid modules by the high-flow-rate fluid module dividing sub-modules;
the low-flow-rate fluid module divides the region where the fluid flow rate is smaller than the flow rate threshold into low-flow-rate fluid modules.
In the embodiment of the present invention, the mapping relationship establishing module 406 includes:
the first mapping relation construction submodule is used for constructing a mapping relation between the edge value condition of the non-fluid module and the temperature data through a linear fitting method;
the second mapping relation construction submodule is used for constructing the mapping relation between the edge value condition of the low-flow-rate fluid module and the temperature data through a polynomial regression method;
and the third mapping relation construction sub-module is used for constructing the mapping relation between the boundary value condition of the high-flow-rate fluid and the temperature data through a neural network learning method.
The embodiment of the invention also provides electronic equipment, which comprises a processor and a memory:
the memory is used for storing the program codes and transmitting the program codes to the processor;
the processor is configured to execute the power equipment temperature field distribution calculation method according to the embodiment of the present invention according to the instructions in the program code.
The embodiment of the invention also provides a computer readable storage medium, which is used for storing program codes, and the program codes are used for executing the electric power equipment temperature field distribution calculation method.
It will be clear to those skilled in the art that, for convenience and brevity of description, specific working procedures of the above-described systems, apparatuses and units may refer to corresponding procedures in the foregoing method embodiments, which are not repeated herein.
In this specification, each embodiment is described in a progressive manner, and each embodiment is mainly described by differences from other embodiments, and identical and similar parts between the embodiments are all enough to be referred to each other.
It will be apparent to those skilled in the art that embodiments of the present invention may be provided as a method, apparatus, or computer program product. Accordingly, embodiments of the present invention may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, embodiments of the invention may take the form of a computer program product on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, etc.) having computer-usable program code embodied therein.
Embodiments of the present invention are described with reference to flowchart illustrations and/or block diagrams of methods, terminal devices (systems), and computer program products according to embodiments of the invention. It will be understood that each flow and/or block of the flowchart illustrations and/or block diagrams, and combinations of flows and/or blocks in the flowchart illustrations and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing terminal device to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing terminal device, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
While preferred embodiments of the present invention have been described, additional variations and modifications in those embodiments may occur to those skilled in the art once they learn of the basic inventive concepts. It is therefore intended that the following claims be interpreted as including the preferred embodiment and all such alterations and modifications as fall within the scope of the embodiments of the invention.
Finally, it is further noted that relational terms such as first and second, and the like are used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions. Moreover, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or terminal that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or terminal. Without further limitation, an element defined by the phrase "comprising one … …" does not exclude the presence of other like elements in a process, method, article or terminal device comprising the element.
The above embodiments are only for illustrating the technical solution of the present invention, and not for limiting the same; although the invention has been described in detail with reference to the foregoing embodiments, it will be understood by those of ordinary skill in the art that: the technical scheme described in the foregoing embodiments can be modified or some technical features thereof can be replaced by equivalents; such modifications and substitutions do not depart from the spirit and scope of the technical solutions of the embodiments of the present invention.
Claims (10)
1. A method for calculating a temperature field distribution of an electrical device, comprising:
calculating equipment temperature field distribution data respectively corresponding to the power equipment under the condition of presetting a plurality of groups of side values;
acquiring a non-fluid material area of the power equipment, and dividing the non-fluid material area into a plurality of non-fluid modules;
extracting a fluid flow rate of a fluid domain of the electrical device according to the device temperature field distribution data;
dividing the fluid domain into a plurality of high-flow-rate fluid modules and low-flow-rate fluid modules according to the fluid flow rate;
temperature data of the non-fluid module, the high-flow-rate fluid module and the low-flow-rate fluid module under the boundary conditions are respectively obtained from the equipment temperature field distribution data;
respectively establishing mapping relations between each side value condition and temperature data of the non-fluid module, the high-flow-rate fluid module and the low-flow-rate fluid module;
acquiring an edge value condition to be analyzed, and acquiring target equipment temperature field distribution corresponding to the edge value condition to be analyzed according to the edge value condition and the mapping relation.
2. The method of claim 1, wherein the step of obtaining a non-fluid material region of the electrical device, dividing the non-fluid material region into a number of non-fluid modules, comprises:
acquiring a non-fluid material region of the electrical device;
the non-fluid material region is divided into a number of non-fluid modules, subject to a closed boundary.
3. The method of claim 1, wherein the device temperature field distribution data comprises coordinates, temperature, and flow rate.
4. The method of claim 1, wherein the step of dividing the fluid domain into a number of high flow rate fluid modules and low flow rate fluid modules according to the fluid flow rate comprises:
obtaining a highest flow rate of the fluid domain;
determining a flow rate threshold according to the highest flow rate;
dividing a region where the fluid flow rate reaches the flow rate threshold into high-flow-rate fluid modules;
the region where the fluid flow rate is less than the flow rate threshold is divided into low flow rate fluid modules.
5. The method of claim 1, wherein the step of establishing a mapping of each edge condition of the non-fluid module, the high flow rate fluid module, and the low flow rate fluid module to temperature data, respectively, comprises:
constructing a mapping relation between the boundary value condition of the non-fluid module and temperature data by a linear fitting method;
constructing a mapping relation between the boundary value condition of the low-flow-rate fluid module and temperature data by a polynomial regression method;
and constructing the mapping relation between the boundary value condition of the high-flow-rate fluid and the temperature data by a neural network learning method.
6. A power equipment temperature field distribution calculation apparatus, comprising:
the equipment temperature field distribution data calculation module is used for calculating equipment temperature field distribution data respectively corresponding to the power equipment under the condition of presetting a plurality of groups of side values;
the non-fluid module dividing module is used for acquiring a non-fluid material area of the power equipment and dividing the non-fluid material area into a plurality of non-fluid modules;
a fluid flow rate extraction module for extracting a fluid flow rate of a fluid domain of the electrical device according to the device temperature field distribution data;
the fluid module dividing module is used for dividing the fluid domain into a plurality of high-flow-rate fluid modules and low-flow-rate fluid modules according to the fluid flow rate;
the temperature data acquisition module is used for respectively acquiring temperature data of the non-fluid module, the high-flow-rate fluid module and the low-flow-rate fluid module under the boundary value conditions from the equipment temperature field distribution data;
the mapping relation establishing module is used for respectively establishing the mapping relation between the boundary value conditions and the temperature data of the non-fluid module, the high-flow-rate fluid module and the low-flow-rate fluid module;
the target equipment temperature field distribution acquisition module is used for acquiring the boundary value conditions to be analyzed and acquiring the target equipment temperature field distribution corresponding to the boundary value conditions to be analyzed according to the boundary value conditions and the mapping relation.
7. The apparatus of claim 6, wherein the non-fluid module dividing module comprises:
a non-fluid material region acquisition sub-module for acquiring a non-fluid material region of the electrical device;
and the non-fluid module dividing sub-module is used for dividing the non-fluid material area into a plurality of non-fluid modules on the condition of a closed boundary.
8. The apparatus of claim 6, wherein the fluid module dividing module comprises:
a maximum flow rate acquisition sub-module for acquiring a maximum flow rate of the fluid domain;
a flow rate threshold determining submodule for determining a flow rate threshold according to the highest flow rate;
dividing the region of the fluid flow rate reaching the flow rate threshold into high-flow-rate fluid modules by the high-flow-rate fluid module dividing sub-modules;
and the low-flow-rate fluid module is used for dividing the area with the fluid flow rate smaller than the flow rate threshold into low-flow-rate fluid modules.
9. An electronic device, the device comprising a processor and a memory:
the memory is used for storing program codes and transmitting the program codes to the processor;
the processor is configured to perform the power device temperature field distribution calculation method of any one of claims 1-5 according to instructions in the program code.
10. A computer readable storage medium for storing a program code for performing the power equipment temperature field distribution calculation method of any one of claims 1-5.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311440844.3A CN117371291A (en) | 2023-11-01 | 2023-11-01 | Power equipment temperature field distribution calculation method, device, equipment and medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311440844.3A CN117371291A (en) | 2023-11-01 | 2023-11-01 | Power equipment temperature field distribution calculation method, device, equipment and medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN117371291A true CN117371291A (en) | 2024-01-09 |
Family
ID=89403880
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311440844.3A Pending CN117371291A (en) | 2023-11-01 | 2023-11-01 | Power equipment temperature field distribution calculation method, device, equipment and medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117371291A (en) |
-
2023
- 2023-11-01 CN CN202311440844.3A patent/CN117371291A/en active Pending
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112396191B (en) | Method, system and device for updating model parameters based on federal learning | |
| CN111008473A (en) | Simulation analysis method and device for power equipment and storage medium | |
| CN111461445B (en) | Short-term wind speed prediction method and device, computer equipment and storage medium | |
| CN114492675B (en) | Intelligent fault cause diagnosis method for capacitor voltage transformer | |
| CN113283222B (en) | Automatic report generation method and device, computer equipment and storage medium | |
| Tian et al. | Fast and self-learning indoor airflow simulation based on in situ adaptive tabulation | |
| Alsmadi et al. | Substructure preservation sylvester-based model order reduction with application to power systems | |
| CN116070302A (en) | Cable insulation state prediction method and device | |
| CN111401514A (en) | Semi-supervised symbol network embedding method and system based on improved graph convolutional network | |
| CN110795898A (en) | Simulation method and device for coupling of multiple physical fields of wall bushing and storage medium | |
| Liu et al. | Grey-based approach for estimating Weibull model and its application | |
| CN113904915A (en) | Intelligent power communication fault analysis method and system based on Internet of things | |
| CN113625144A (en) | IGBT fault prediction method and system | |
| CN117875241A (en) | Simulation calculation method, device and equipment for cascade H-bridge converter energy storage system | |
| CN117371291A (en) | Power equipment temperature field distribution calculation method, device, equipment and medium | |
| Eryilmaz | On an application of concomitants of order statistics | |
| JP2019008794A (en) | Computer implementation method for simulation of whole electric circuit | |
| CN117057258A (en) | Black-start overvoltage prediction method and system based on weight distribution correlation coefficient | |
| CN115422817A (en) | Method, device, equipment and storage medium for predicting molecular collision cross section | |
| CN116343943A (en) | Method for coding ionic liquid characteristics based on graph neural network | |
| CN111353635B (en) | Optimal fitting method and system for propagation matrix modulus based on particle swarm optimization | |
| CN114282598A (en) | Multi-source heterogeneous power grid data fusion method, device, equipment and computer medium | |
| JP2014178751A (en) | Simulation method for power system and power system simulator | |
| Hu et al. | Optimal structure screening for large-scale multi-state series-parallel systems based on structure ordinal optimization | |
| CN110930172A (en) | Neural network-based cross-country market joint marginal price prediction method and system |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |