Aluminum electrolysis cell electric heating field distribution prediction method and device, storage medium and product

Abstract

The invention discloses an aluminum electrolysis cell electric heating field distribution prediction method and device, a storage medium and a product. The prediction method comprises the steps that an aluminum electrolysis cell numerical calculation model is constructed; electric heating fields under different working conditions are solved according to the aluminum electrolysis cell numerical calculation model, and aluminum electrolysis cell electric heating field distribution under different working conditions is obtained; constructing a data snapshot matrix according to the electric heating field distribution of the aluminum electrolysis cell under different working conditions; performing modal decomposition and interception on the data snapshot matrix to obtain a main characteristic mode and a modal coefficient thereof under each working condition; constructing a modal coefficient prediction model according to the modal coefficients of the main characteristic modes under different working conditions; and according to the modal coefficient prediction model and the main characteristic modal under each working condition, aluminum electrolysis cell electric heating field distribution prediction is carried out. According to the method, on the premise that the accuracy is high enough, the calculation efficiency is remarkably improved, the consumption of calculation resources is greatly reduced, and rapid prediction of the electric heating field distribution of the aluminum electrolysis cell is achieved.

Description

Technical Field

[0001] The present invention belongs to the technical field of aluminum electrolysis, and in particular relates to a method, device, storage medium and product for predicting the electric thermal field distribution of an aluminum electrolysis cell based on model reduction. Background Art

[0002] Aluminum electrolytic cells are the core equipment for industrial production of electrolytic aluminum. On the premise of ensuring stable production, improving the current efficiency of the electrolytic cell to reduce energy consumption has always been the development goal of the electrolytic aluminum industry. The current efficiency of the electrolytic cell is closely related to factors such as voltage and temperature. Accurately and timely obtaining the electric heating field of the aluminum electrolytic cell is of great significance to the energy saving and consumption reduction and stable operation of the electrolytic cell.

[0003] At present, the acquisition method of the electric thermal field of aluminum electrolytic cells has certain limitations. It is mainly obtained through distributed sensors set on the electrolytic cells and manual measurements, and the available information is very limited. In order to obtain a comprehensive distribution of the electric thermal field of aluminum electrolytic cells, the electric thermal field of the electrolytic cells can be numerically simulated based on the finite element simulation method. However, due to the complex model of aluminum electrolytic cells and the large number of grids, numerical simulation requires a lot of computing resources and takes a long time to calculate, which makes it difficult to apply to the actual production control process. Summary of the invention

[0004] The purpose of the present invention is to provide a method, device, storage medium and product for predicting the distribution of the electric thermal field of an aluminum electrolysis cell, so as to solve the problem that the numerical simulation calculation of the electric thermal field of an aluminum electrolysis cell using a finite element simulation method consumes a lot of computing resources, takes a long time to calculate, and is difficult to apply to actual production.

[0005] The present invention solves the above technical problems through the following technical solutions: A method for predicting the electric heating field distribution of an aluminum electrolytic cell, comprising:

[0006] Construct a numerical calculation model of aluminum electrolysis cell;

[0007] Solving the electric heating field under different working conditions according to the numerical calculation model of the aluminum electrolysis cell, and obtaining the electric heating field distribution of the aluminum electrolysis cell under different working conditions;

[0008] Construct a data snapshot matrix based on the electric and thermal field distribution of aluminum reduction cells under different working conditions;

[0009] Performing modal decomposition and truncation on the data snapshot matrix to obtain the main characteristic modes and modal coefficients under each working condition;

[0010] A modal coefficient prediction model is constructed based on the modal coefficients of the main characteristic modes under different working conditions;

[0011] The electric heating field distribution of the aluminum reduction cell is predicted based on the modal coefficient prediction model and the main characteristic modes under each working condition.

[0012] Furthermore, the specific construction process of the numerical calculation model of the aluminum electrolysis cell includes:

[0013] According to the geometric dimensions of the aluminum electrolysis cell, a three-dimensional model of the aluminum electrolysis cell is constructed;

[0014] Meshing the three-dimensional model of the aluminum electrolysis cell to obtain a finite element model of the aluminum electrolysis cell;

[0015] Based on the finite element model of the aluminum reduction cell, material properties and solution parameters are set to obtain the numerical calculation model of the aluminum reduction cell.

[0016] Furthermore, each of the operating conditions includes current intensity, electrolyte level, aluminum level, inter-electrode distance and ambient temperature; wherein the electrolyte level refers to the horizontal height of the electrolyte in the aluminum electrolysis cell, and the aluminum level refers to the horizontal height of the aluminum liquid in the aluminum electrolysis cell.

[0017] Furthermore, the data snapshot matrix is ​​modally decomposed and intercepted by using the intrinsic orthogonal decomposition method, which specifically includes:

[0018] Performing singular value decomposition on the data snapshot matrix to obtain the spatial eigenmode and its modal coefficient under each working condition;

[0019] The spatial characteristic modes and their modal coefficients under each working condition are intercepted to obtain the main characteristic modes and their modal coefficients under the corresponding working condition;

[0020] According to the spatial characteristic modes and their modal coefficients under each working condition and the main characteristic modes and their modal coefficients under the corresponding working condition, the interception error is calculated;

[0021] Determine whether the interception error meets the set error accuracy. If so, output the main characteristic modes and their modal coefficients under each working condition; if not, repeat the interception, interception error calculation and judgment steps until the interception error meets the set error accuracy.

[0022] Furthermore, the rule for intercepting the spatial characteristic modes and their modal coefficients under each working condition is:

[0023] R=arg min R∈(0,M] {I(R),I(R)≥99%};

[0024]

[0025] Where R represents the number of intercepted spatial characteristic modes or the number of main characteristic modes; M represents the number of grid nodes of the numerical calculation model of aluminum electrolytic cell; I represents the intermediate quantity; λ k represents the eigenvalue of matrix B, X irepresents the i-th column vector in the data snapshot matrix. Each column vector consists of the solution results of all grid nodes under the corresponding working condition. The superscript T represents transposition.

[0026] Furthermore, for each working condition, the specific calculation formula of the interception error is:

[0027]

[0028] Wherein, error represents the interception error; R represents the number of intercepted spatial characteristic modes or the number of main characteristic modes; M represents the number of grid nodes of the numerical calculation model of aluminum electrolytic cell; represents the k-th order spatial eigenmode; λ k represents the eigenvalue of matrix B, X i It represents the i-th column vector in the data snapshot matrix. Each column vector consists of the solution results of all grid nodes under the corresponding working condition. The superscript T represents the transpose, and ST represents the restriction condition.

[0029] Furthermore, the electric heat field distribution of the aluminum reduction cell is predicted based on the modal coefficient prediction model and the main characteristic modes under each working condition, including:

[0030] Acquire the actual working condition, and use the modal coefficient prediction model to predict the modal coefficients of the main characteristic modes under the actual working condition;

[0031] The electric thermal field distribution of the aluminum reduction cell under actual working conditions is calculated according to the modal coefficients of the main characteristic modes under actual working conditions and the main characteristic modes under different working conditions.

[0032] Based on the same concept, the present invention also provides an electronic device, including a memory, a processor, and a computer program / instructions stored in the memory, wherein the processor executes the computer program / instructions to implement the method for predicting the electric thermal field distribution of an aluminum electrolysis cell as described above.

[0033] Based on the same concept, the present invention also provides a computer-readable storage medium having a computer program / instruction stored thereon, which, when executed by a processor, implements the above-mentioned method for predicting the electric thermal field distribution of an aluminum electrolysis cell.

[0034] Based on the same concept, the present invention also provides a computer program product, including a computer program / instruction, which, when executed by a processor, implements the above-mentioned method for predicting the electric thermal field distribution of an aluminum electrolysis cell.

[0035] Beneficial Effects

[0036] Compared with the prior art, the advantages of the present invention are:

[0037] The present invention constructs a data snapshot matrix based on the numerical simulation results of the electric thermal field of an aluminum electrolytic cell, introduces the modal decomposition technology to extract the main spatial characteristic modes and corresponding modal coefficients of the data snapshot matrix, and establishes a modal coefficient prediction model, and finally realizes the prediction of the electric thermal field distribution of the aluminum electrolytic cell. Under the premise of ensuring sufficiently high accuracy, the present invention significantly improves the calculation efficiency, greatly reduces the consumption of computing resources, realizes the rapid prediction of the electric thermal field distribution of the aluminum electrolytic cell, and can realize the online prediction of the electric thermal field distribution of the aluminum electrolytic cell, which is beneficial to actual production application and provides basic support for further construction of a digital twin model of an aluminum electrolytic cell. BRIEF DESCRIPTION OF THE DRAWINGS

[0038] In order to more clearly illustrate the technical solution of the present invention, the drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the drawings described below are only one embodiment of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0039] Figure 1 is a flow chart of a method for predicting the electric heat field distribution of an aluminum electrolytic cell in an embodiment of the present invention;

[0040] Figure 2 : is a cloud diagram of electric field distribution of an aluminum electrolysis cell in an embodiment of the present invention;

[0041] Figure 3 It is a cloud diagram of the thermal field distribution of the aluminum electrolysis cell in an embodiment of the present invention. DETAILED DESCRIPTION

[0042] The following is a clear and complete description of the technical solutions in the present invention in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0043] The technical solution of the present application is described in detail with specific embodiments below. The following specific embodiments can be combined with each other, and the same or similar concepts or processes may not be described in detail in some embodiments.

[0044] Example 1

[0045] like Figure 1 As shown, a method for predicting the electric heating field distribution of an aluminum electrolysis cell provided by an embodiment of the present invention comprises the following steps:

[0046] Step 1: Construct a numerical calculation model of aluminum electrolysis cell.

[0047] In a specific embodiment of the present invention, the specific construction process of the numerical calculation model of the aluminum electrolysis cell includes:

[0048] Step 1.1: Construct a three-dimensional model of the aluminum electrolysis cell according to the geometric dimensions of the aluminum electrolysis cell;

[0049] Step 1.2: Mesh the three-dimensional model of the aluminum electrolysis cell to obtain a finite element model of the aluminum electrolysis cell;

[0050] Step 1.3: Based on the finite element model of the aluminum reduction cell, set the material properties and solution parameters to obtain the numerical calculation model of the aluminum reduction cell.

[0051] Step 2: Solve the electric heating field under different working conditions according to the numerical calculation model of the aluminum reduction cell to obtain the electric heating field distribution of the aluminum reduction cell under different working conditions.

[0052] According to the actual production, the operating condition variation range of the electric heating field of the aluminum electrolytic cell is determined, and the Latin Hypercube Sampling (LHS) method is used to generate N operating conditions from the operating condition variation range to ensure the uniform distribution of the N operating conditions in the operating condition variation range. In a specific embodiment of the present invention, each operating condition includes current intensity, electrolyte level, aluminum level, pole distance and ambient temperature; wherein, the electrolyte level refers to the horizontal height of the electrolyte in the aluminum electrolytic cell, and the horizontal height of the electrolyte represents the content of the liquid electrolyte in the cell. The content of the liquid electrolyte is at a suitable value to ensure the stability of the thermal capacity of the electrolytic cell and the effective dissolution of aluminum oxide. If the electrolyte level is high, the electrolyte amount is large, the thermal stability is good, and the aluminum oxide dissolution is large; if the electrolyte level is too high, the aluminum liquid will fluctuate, and if it is too low, the thermal stability will be reduced, thereby forming a sick cell. Wherein, the aluminum level refers to the horizontal height of the aluminum liquid in the aluminum electrolytic cell.

[0053] In a specific embodiment of the present invention, the current intensity varies in a range of 400×(1±5%) kA, the electrolyte level varies in a range of 15 to 30 cm, the aluminum level varies in a range of 15 to 30 cm, the inter-electrode distance varies in a range of 3 to 5 cm, and the ambient temperature varies in a range of 30 to 50° C. In this embodiment, ANSYS Mechanical APDL is used to solve the electric thermal field of the numerical calculation model of a single anode slice of an aluminum electrolytic cell under the conditions of a current intensity of 400 kA, a primary crystallization temperature of 940° C., an anode height of 38 cm, an upper covering material thickness of 15 cm, an electrolyte level of 18.5 cm, an aluminum level of 16.5 cm, an inter-electrode distance of 4.3 cm, and an ambient temperature of 40° C. The solution results are shown in FIG. Figure 2 and Figure 3 As shown, Figure 2 This is the electric field distribution cloud diagram of the aluminum electrolysis cell. Figure 2 The color code indicates the voltage, and the voltage unit is V; Figure 3 This is the thermal field distribution cloud map of aluminum electrolysis cell. Figure 3 The color scale indicates the temperature, and the temperature unit is ℃.

[0054] The numerical calculation model of the aluminum reduction cell constructed in step 1 is used to solve the electric thermal field under each working condition, and the electric thermal field distribution (i.e., electric field distribution and thermal field distribution) of the aluminum reduction cell under each working condition can be obtained.

[0055] Step 3: Construct a data snapshot matrix based on the electric thermal field distribution of the aluminum reduction cell under different working conditions.

[0056] The data snapshot matrix can be expressed as:

[0057]

[0058] Where A represents the data snapshot matrix; X i represents the i-th column vector in the data snapshot matrix, that is, the solution results of all grid nodes under the i-th working condition. The solution results of each grid node include the voltage value and temperature value of the grid node; x ij It represents the solution result of the jth grid node under the ith working condition; M represents the number of grid nodes of the numerical calculation model of aluminum electrolytic cell; N represents the number of working conditions.

[0059] Step 4: Perform modal decomposition and truncation on the data snapshot matrix to obtain the main eigenmodes and their modal coefficients under each working condition.

[0060] In a specific implementation of the present invention, the Proper Orthogonal Decomposition (POD) method is used to perform modal decomposition and interception on the data snapshot matrix. The specific implementation process of modal decomposition and interception includes:

[0061] Step 4.1: Perform singular value decomposition (SVD) on the data snapshot matrix to obtain the spatial eigenmodes and their modal coefficients under each working condition.

[0062] Perform singular value decomposition on the data snapshot matrix and obtain:

[0063] A=PΣQ T (2)

[0064] Among them, P represents the T The orthogonal matrix composed of orthogonal vectors of A. The superscript T indicates transposition; Q indicates the orthogonal matrix composed of A T A is an orthogonal matrix composed of orthogonal vectors; Σ represents a diagonal matrix of size M×N. Since M>>N, the diagonal elements Σ ii By M non-negative numbers σ i Composed and arranged in descending order, that is, σ1≥σ2≥...≥σM ≥0,σ1,σ2,...,σ M are the singular values ​​of the data snapshot matrix A.

[0065] Let PΣ=a, then A=aQ T . Let a=[a1,...,a M ], Then each column vector in the data snapshot matrix can be expressed as:

[0066]

[0067] Among them, a k represents the modal coefficient of the k-th order spatial eigenmode; represents the k-th order spatial eigenmode, is a spatial orthogonal basis function. Each working condition includes M spatial eigenmodes and M modal coefficients. The large number of grid nodes leads to a large number of spatial eigenmodes, which in turn leads to large consumption of computing resources and long calculation time.

[0068] Step 4.2: In order to reduce the order, the spatial eigenmodes and their modal coefficients under each working condition are truncated to obtain the main eigenmodes and their modal coefficients under the working condition.

[0069] In a specific implementation of the present invention, the rule for intercepting the spatial characteristic modes and their modal coefficients under each working condition is:

[0070] R=arg min R∈(0,M] {I(R),I(R)≥99%} (4)

[0071]

[0072] Where R represents the number of intercepted spatial characteristic modes or the number of main characteristic modes; I represents the intermediate quantity; λ k represents the eigenvalue of matrix B, The order reduction is achieved by truncation of the main characteristic modes, thereby reducing computing resources and improving computing efficiency.

[0073] Step 4.3: For each working condition, calculate the truncation error based on the spatial eigenmodes and their modal coefficients and the main eigenmodes and their modal coefficients under the working condition.

[0074] For each working condition, the specific calculation formula of the interception error is:

[0075]

[0076] Among them, error represents the interception error; represents the ith column vector after truncation, is a column vector consisting of the solution results of R grid nodes under the i-th working condition, that is,

[0077] Multiply both sides of the equal sign in formula (3) by have to:

[0078]

[0079] Solved, Right now:

[0080]

[0081] Substituting formula (8) into formula (6), we get:

[0082]

[0083] make have:

[0084]

[0085] In order to minimize the interception error, combined with the Lagrange multiplier method, it can be converted to solve the eigenvector The solution is:

[0086]

[0087] Among them, λ k represents the eigenvalue of matrix B. Substituting formula (11) into formula (10), we can get:

[0088]

[0089] That is, the error between the matrix after truncating the main eigenmode and the original data snapshot matrix can be expressed as the sum of the (M-R) eigenvalues ​​of the real symmetric matrix B. In order to minimize the truncation error, the eigenvalues ​​of the matrix B are sorted from large to small, and the first R largest eigenvalues ​​are selected. The eigenvectors corresponding to the first R largest eigenvalues ​​are the main eigenmodes under the corresponding working conditions.

[0090] Step 4.4: Determine whether the intercepted error meets the set error accuracy. If so, output the main characteristic modes and their modal coefficients under each working condition; if not, go to step 4.2.

[0091] In this embodiment, the error accuracy is set to 1%, that is, when error>1%, the process proceeds to step 4.2; when error≤1%, the main characteristic modes and their modal coefficients under each working condition are obtained.

[0092] Step 5: Construct a modal coefficient prediction model based on the modal coefficients of the main characteristic modes under different working conditions.

[0093] In a specific embodiment of the present invention, based on the modal coefficients of the main characteristic modes under different working conditions, a modal coefficient prediction model is constructed using a surrogate model method. This embodiment uses the Kriging method to construct the modal coefficient prediction model.

[0094] Step 6: Predict the electric thermal field distribution of the aluminum reduction cell based on the modal coefficient prediction model and the main characteristic modes under each working condition.

[0095] In a specific embodiment of the present invention, the electric heat field distribution of the aluminum reduction cell is predicted according to the modal coefficient prediction model and the main characteristic modes under each working condition, including:

[0096] Step 6.1: Obtain the actual working condition and use the modal coefficient prediction model to predict the modal coefficients of the main characteristic modes under the actual working condition;

[0097] Step 6.2: Calculate the electric thermal field distribution of the aluminum reduction cell under actual working conditions based on the modal coefficients of the main characteristic modes under actual working conditions and the main characteristic modes under different working conditions.

[0098] After using the modal coefficient prediction model to predict the modal coefficients under actual working conditions, according to the formula The electric and thermal fields of R grid nodes under actual working conditions can be calculated, thereby realizing the prediction of the electric and thermal field distribution of the aluminum electrolysis cell.

[0099] Example 2

[0100] An embodiment of the present invention also provides an electronic device, which includes: a memory, a processor, and a computer program / instructions stored in the memory, and the processor executes the computer program / instructions to implement the method for predicting the electric thermal field distribution of an aluminum electrolysis cell in an embodiment of the present application.

[0101] Although not shown, the electronic device includes a processor, which can perform various appropriate operations and processes according to the program and / or data stored in the read-only memory (ROM) or the program and / or data loaded from the storage portion into the random access memory (RAM). The processor can be a multi-core processor, or it can include multiple processors. In some embodiments, the processor can include a general main processor and one or more special coprocessors, such as a central processing unit, a graphics processing unit (GPU), a neural network processor (NPU), a digital signal processor (DSP), etc. In RAM, various programs and data required for device operation are also stored. The processor, ROM and RAM are connected to each other via a bus. The input / output (I / O) interface is also connected to the bus.

[0102] The processor and memory are used together to execute the program / instructions stored in the memory. When the program / instructions are executed by the computer, the methods, steps or functions described in the above embodiments can be implemented.

[0103] Although not shown, an embodiment of the present invention further provides a computer-readable storage medium having a computer program / instruction stored thereon, which, when executed by a processor, implements the method for predicting the electric thermal field distribution of an aluminum electrolysis cell in an embodiment of the present application.

[0104] Storage media in embodiments of the present invention include permanent and non-permanent, removable and non-removable items that can be implemented by any method or technology to store information. Examples of storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technology, compact disk read-only memory (CD-ROM), digital versatile disk (DVD) or other optical storage, magnetic cassettes, magnetic disk storage or other magnetic storage devices or any other non-transmission medium that can be used to store information that can be accessed by a computing device.

[0105] Readable storage media include permanent and non-permanent, removable and non-removable media that can be implemented by any method or technology to store information. Information can be computer-readable instructions, data structures, program modules or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technology, compact disk read-only memory (CD-ROM), digital versatile disk (DVD) or other optical storage, magnetic cassettes, disk storage or other magnetic storage devices or any other non-transmission media that can be used to store information that can be accessed by a computing device. As defined herein, computer-readable media does not include temporary computer-readable media (transitory media), such as modulated data signals and carrier waves.

[0106] Although not shown, an embodiment of the present invention further provides a computer program product, including: a computer program / instruction, which, when executed by a processor, implements the method for predicting the electric thermal field distribution of an aluminum electrolysis cell in an embodiment of the present application.

[0107] What is disclosed above is only a specific implementation mode of the present invention, but the protection scope of the present invention is not limited thereto. Any technician familiar with the technical field can easily think of changes or modifications within the technical scope disclosed in the present invention, which should be covered within the protection scope of the present invention.

Claims

1. A method for predicting the electric heating field distribution of an aluminum electrolysis cell, characterized in that: The prediction method comprises: Construct a numerical calculation model of aluminum electrolysis cell; Solving the electric heating field under different working conditions according to the numerical calculation model of the aluminum electrolysis cell, and obtaining the electric heating field distribution of the aluminum electrolysis cell under different working conditions; Construct a data snapshot matrix based on the electric and thermal field distribution of aluminum reduction cells under different working conditions; Performing modal decomposition and truncation on the data snapshot matrix to obtain the main characteristic modes and modal coefficients under each working condition; Construct a modal coefficient prediction model based on the modal coefficients of the main characteristic modes under different working conditions; The electric heating field distribution of the aluminum reduction cell is predicted based on the modal coefficient prediction model and the main characteristic modes under each working condition.

2. The method for predicting the electric heat field distribution of an aluminum reduction cell according to claim 1, characterized in that: The specific construction process of the numerical calculation model of the aluminum electrolysis cell includes: According to the geometric dimensions of the aluminum electrolysis cell, a three-dimensional model of the aluminum electrolysis cell is constructed; Meshing the three-dimensional model of the aluminum electrolysis cell to obtain a finite element model of the aluminum electrolysis cell; Based on the finite element model of the aluminum reduction cell, material properties and solution parameters are set to obtain the numerical calculation model of the aluminum reduction cell.

3. The method for predicting the electric heat field distribution of an aluminum electrolysis cell according to claim 1, characterized in that: Each of the operating conditions includes current intensity, electrolyte level, aluminum level, inter-electrode distance and ambient temperature; wherein the electrolyte level refers to the horizontal height of the electrolyte in the aluminum electrolysis cell, and the aluminum level refers to the horizontal height of the aluminum liquid in the aluminum electrolysis cell.

4. The method for predicting the electric heat field distribution of an aluminum reduction cell according to any one of claims 1 to 3, characterized in that: The data snapshot matrix is ​​modally decomposed and intercepted by using the intrinsic orthogonal decomposition method, which specifically includes: Performing singular value decomposition on the data snapshot matrix to obtain the spatial eigenmode and its modal coefficient under each working condition; The spatial characteristic modes and their modal coefficients under each working condition are intercepted to obtain the main characteristic modes and their modal coefficients under the corresponding working condition; According to the spatial characteristic modes and their modal coefficients under each working condition and the main characteristic modes and their modal coefficients under the corresponding working condition, the interception error is calculated; Determine whether the interception error meets the set error accuracy. If so, output the main characteristic modes and their modal coefficients under each working condition; if not, repeat the interception, interception error calculation and judgment steps until the interception error meets the set error accuracy.

5. The method for predicting the electric heat field distribution of an aluminum electrolysis cell according to claim 4, characterized in that: The rule for intercepting the spatial characteristic modes and their modal coefficients under each working condition is: R=ang min R∈(0,M] {I(R),I(R)≥99%}; Where R represents the number of intercepted spatial characteristic modes or the number of main characteristic modes; M represents the number of grid nodes of the numerical calculation model of aluminum electrolytic cell; I represents the intermediate quantity; λ k represents the eigenvalue of matrix B, X i represents the i-th column vector in the data snapshot matrix. Each column vector consists of the solution results of all grid nodes under the corresponding working condition. The superscript T represents transposition.

6. The method for predicting the electric heat field distribution of an aluminum reduction cell according to claim 4, characterized in that: For each working condition, the specific calculation formula of the interception error is: Wherein, error represents the interception error; R represents the number of intercepted spatial characteristic modes or the number of main characteristic modes; M represents the number of grid nodes of the numerical calculation model of aluminum electrolytic cell; represents the k-th order spatial eigenmode; λ k represents the eigenvalue of matrix B, X i It represents the i-th column vector in the data snapshot matrix. Each column vector consists of the solution results of all grid nodes under the corresponding working condition. The superscript T represents the transpose, and ST represents the restriction condition.

7. The method for predicting the electric heat field distribution of an aluminum electrolysis cell according to any one of claims 1 to 3, characterized in that: The electric heating field distribution of the aluminum reduction cell is predicted based on the modal coefficient prediction model and the main characteristic modes under each working condition, including: Acquire the actual working condition, and use the modal coefficient prediction model to predict the modal coefficients of the main characteristic modes under the actual working condition; The electric thermal field distribution of the aluminum reduction cell under actual working conditions is calculated according to the modal coefficients of the main characteristic modes under actual working conditions and the main characteristic modes under different working conditions.

8. An electronic device comprising a memory, a processor, and a computer program / instruction stored in the memory, characterized in that: The processor executes the computer program / instructions to implement the method for predicting the electric thermal field distribution of an aluminum electrolysis cell according to any one of claims 1 to 7.

9. A computer-readable storage medium having a computer program / instruction stored thereon, characterized in that: When the computer program / instruction is executed by a processor, the method for predicting the electric thermal field distribution of an aluminum electrolysis cell as described in any one of claims 1 to 7 is implemented.

10. A computer program product comprising a computer program / instructions, characterized in that When the computer program / instruction is executed by a processor, the method for predicting the electric thermal field distribution of an aluminum electrolysis cell as described in any one of claims 1 to 7 is implemented.

Images