CN115270633A - Prediction method, system, device and medium for three-dimensional physical field of fuel cell - Google Patents
Prediction method, system, device and medium for three-dimensional physical field of fuel cell Download PDFInfo
- Publication number
- CN115270633A CN115270633A CN202210929061.0A CN202210929061A CN115270633A CN 115270633 A CN115270633 A CN 115270633A CN 202210929061 A CN202210929061 A CN 202210929061A CN 115270633 A CN115270633 A CN 115270633A
- Authority
- CN
- China
- Prior art keywords
- fuel cell
- physical field
- dimensional
- twin
- snapshot
- 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
Images
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
- G06F30/27—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
- 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
- G06F30/28—Design optimisation, verification or simulation using fluid dynamics, e.g. using Navier-Stokes equations or computational fluid dynamics [CFD]
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16C—COMPUTATIONAL CHEMISTRY; CHEMOINFORMATICS; COMPUTATIONAL MATERIALS SCIENCE
- G16C10/00—Computational theoretical chemistry, i.e. ICT specially adapted for theoretical aspects of quantum chemistry, molecular mechanics, molecular dynamics or the like
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16C—COMPUTATIONAL CHEMISTRY; CHEMOINFORMATICS; COMPUTATIONAL MATERIALS SCIENCE
- G16C20/00—Chemoinformatics, i.e. ICT specially adapted for the handling of physicochemical or structural data of chemical particles, elements, compounds or mixtures
- G16C20/70—Machine learning, data mining or chemometrics
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2111/00—Details relating to CAD techniques
- G06F2111/10—Numerical modelling
-
- 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
- G06F2119/14—Force analysis or force optimisation, e.g. static or dynamic forces
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02E—REDUCTION OF GREENHOUSE GAS [GHG] EMISSIONS, RELATED TO ENERGY GENERATION, TRANSMISSION OR DISTRIBUTION
- Y02E60/00—Enabling technologies; Technologies with a potential or indirect contribution to GHG emissions mitigation
- Y02E60/30—Hydrogen technology
- Y02E60/50—Fuel cells
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Evolutionary Computation (AREA)
- Computing Systems (AREA)
- General Physics & Mathematics (AREA)
- Computer Hardware Design (AREA)
- General Engineering & Computer Science (AREA)
- Geometry (AREA)
- Artificial Intelligence (AREA)
- Bioinformatics & Computational Biology (AREA)
- Software Systems (AREA)
- Medical Informatics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Spectroscopy & Molecular Physics (AREA)
- Fluid Mechanics (AREA)
- Pure & Applied Mathematics (AREA)
- Algebra (AREA)
- Mathematical Analysis (AREA)
- Mathematical Optimization (AREA)
- Mathematical Physics (AREA)
- Data Mining & Analysis (AREA)
- Databases & Information Systems (AREA)
- Chemical & Material Sciences (AREA)
- Crystallography & Structural Chemistry (AREA)
- Fuel Cell (AREA)
Abstract
The invention discloses a prediction method, a system, equipment and a medium of a three-dimensional physical field of a fuel cell, wherein the prediction method comprises the following steps: acquiring variable input parameters of random working conditions of the fuel cell to be predicted; the variable input parameters of the random working conditions of the fuel cell to be predicted are used as the input of a preset digital twin model of the three-dimensional multi-physical field of the fuel cell, and the digital twin result of the three-dimensional multi-physical field is output to obtain the prediction result of the three-dimensional multi-physical field of the fuel cell to be predicted; the method can realize the rapid and accurate prediction of three-dimensional multi-physical fields in the fuel cell on the basis of a given fuel cell numerical model, and meet the demand of multi-physical field prediction in the on-line control scene of the proton exchange membrane fuel cell; the method realizes rapid and accurate prediction of three-dimensional multi-physical fields in the fuel cell based on the intrinsic orthogonal decomposition method, and performs prediction on weight coefficients under any random working condition, so that the prediction efficiency and the accuracy of prediction results are high.
Description
Technical Field
The invention belongs to the technical field of fuel cells, and particularly relates to a method, a system, equipment and a medium for predicting a three-dimensional physical field of a fuel cell.
Background
With the change of global climate and the acceleration of carbon neutralization agenda, the energy industry is shifting from fossil fuel domination to renewable energy domination at an increasingly fast speed, however, the intermittency of renewable energy power generation limits the further popularization and application of the renewable energy power generation; the hydrogen energy is expected to be used as secondary energy, so that the problem of intermittence in power generation of renewable energy sources is solved; as one of hydrogen energy utilization devices, a proton exchange membrane fuel cell or an engine substitute to be most widely used in the future is expected. Commercial applications for pem fuel cells are currently rapidly evolving around the world.
The real-time state in the proton exchange membrane fuel cell is fully known, and the method has vital significance for online operation control and life evaluation optimization; because a large number of micro-scale structures exist in the proton exchange membrane fuel cell, the in-situ test of the internal physical field is difficult to carry out by adopting a conventional experimental method; therefore, scholars establish a series of proton exchange membrane fuel cell performance prediction models; wherein, the rapid prediction model suitable for the on-line control process of the proton exchange membrane fuel cell is usually simplified; the computational fluid dynamics model can obtain a detailed three-dimensional physical field in the proton exchange membrane fuel cell, but the simulation speed is slow, and the method is difficult to be used for online prediction of the internal physical field of the proton exchange membrane fuel cell.
Disclosure of Invention
Aiming at the technical problems in the prior art, the invention provides a method, a system, equipment and a medium for predicting a three-dimensional physical field of a fuel cell, and aims to solve the technical problems that the simulation speed of the three-dimensional multi-physical field of the proton exchange membrane fuel cell is low, and the online prediction of the three-dimensional multi-physical field in the fuel cell cannot be realized.
In order to achieve the purpose, the invention adopts the technical scheme that:
the invention provides a prediction method of a three-dimensional physical field of a fuel cell, which comprises the following steps:
acquiring variable input parameters of random working conditions of the fuel cell to be predicted;
the variable input parameters of the random working condition of the fuel cell to be predicted are used as the input of a preset digital twin model of the three-dimensional multi-physical field of the fuel cell, and the digital twin result of the three-dimensional multi-physical field is output to obtain the prediction result of the three-dimensional multi-physical field of the fuel cell to be predicted;
the construction process of the digital twin model of the preset three-dimensional multi-physical field of the fuel cell comprises the following steps:
solving a coupling model of a pre-constructed three-dimensional multi-physical field of the fuel cell to obtain a plurality of twin snapshots;
aiming at each type of three-dimensional physical field in the fuel cell, constructing a plurality of basis functions by adopting an intrinsic orthogonal decomposition method according to a plurality of twin snapshots, and acquiring weight coefficients of each basis function direction of each three-dimensional physical field under the working condition of each twin snapshot;
and taking the weight coefficient of each basis function direction of each three-dimensional physical field under each twin snapshot working condition as a sample set, and obtaining the preset digital twin model of the three-dimensional multi-physical field of the fuel cell based on a pre-selected machine learning algorithm, interpolation algorithm or regression algorithm.
Further, the variable input parameters of the random working condition of the fuel cell to be predicted comprise cathode pressure, anode pressure, cathode humidity, anode humidity, cathode stoichiometric ratio, anode stoichiometric ratio and operating temperature of the fuel cell to be predicted.
Further, the process for constructing the preset digital twin model of the three-dimensional multi-physical field of the fuel cell specifically includes the following steps:
constructing a three-dimensional multi-physical field coupling model of the fuel cell;
obtaining model parameters of the fuel cell according to the coupling model of the three-dimensional multi-physical field of the fuel cell;
selecting variable parameters from the model parameters of the fuel cell to obtain variable input parameters of a plurality of snapshot working conditions;
taking variable input parameters of a plurality of snapshot working conditions as the input of a coupling model of a three-dimensional multi-physical field of the fuel cell, and obtaining a plurality of twin snapshots through simulation;
generating a plurality of snapshot matrixes under snapshot working conditions according to a plurality of twin snapshots aiming at each type of three-dimensional physical field in the fuel cell;
aiming at each type of three-dimensional physical field in the fuel cell, matrix decomposition and matrix transformation processing are carried out on a snapshot matrix under a plurality of snapshot working conditions by using a singular value decomposition method to obtain a plurality of basis functions;
projecting the twin snapshots to each basis function direction, and reconstructing to obtain a weight coefficient of each basis function direction of each three-dimensional physical field under the working condition of each twin snapshot;
and taking the weight coefficient of each basis function direction of each three-dimensional physical field under each twin snapshot working condition as a sample set, and obtaining the preset digital twin model of the three-dimensional multi-physical field of the fuel cell based on a pre-selected machine learning algorithm, interpolation algorithm or regression algorithm.
Further, the model parameters of the fuel cell include geometric parameters, physical parameters, electrochemical parameters and operating parameters of the fuel cell.
Further, the coupling model of the three-dimensional multi-physical field of the fuel cell is a three-dimensional two-phase non-isothermal numerical simulation model based on liquid pressure continuity.
Further, variable input parameters of a plurality of snapshot working conditions are used as input of a coupling model of a three-dimensional multi-physical field of the fuel cell, and a plurality of twin snapshots are obtained through simulation, specifically as follows:
compiling a three-dimensional multi-physical field coupling model of the fuel cell to be predicted into ANSYS Fluent software by adopting C language, taking variable input parameters of a plurality of snapshot working conditions as input, and performing simulation output to obtain a plurality of twin snapshots; wherein, a plurality of twin snapshots are output in a Tecplot file format.
Further, the preset digital twin model of the three-dimensional multi-physical field of the fuel cell is as follows:
wherein r is a number of a physical quantity; f' r A three-dimensional physical field of an r-th physical quantity under variable input parameters of the fuel cell to be predicted; b' r,j The weight coefficient of the three-dimensional physical field of the r physical quantity in the j basic function direction; psi r,j A jth basis function being an r physical quantity; j is the number of the above-mentioned base function; l r Is the truncation order of the r-th physical quantity.
The invention also provides a prediction system of the three-dimensional physical field of the fuel cell, which comprises the following steps:
the acquisition module is used for acquiring variable input parameters of random working conditions of the fuel cell to be predicted;
the prediction module is used for taking the variable input parameters of the random working conditions of the fuel cell to be predicted as the input of a preset digital twin model of the three-dimensional multi-physical field of the fuel cell and outputting the digital twin result of the three-dimensional multi-physical field to be obtained, namely the prediction result of the three-dimensional multi-physical field of the fuel cell to be predicted;
the construction process of the preset digital twin model of the three-dimensional multi-physical field of the fuel cell comprises the following steps:
solving a coupling model of a pre-constructed three-dimensional multi-physical field of the fuel cell to obtain a plurality of twin snapshots;
aiming at each type of three-dimensional physical field in the fuel cell, constructing a plurality of basis functions by adopting an intrinsic orthogonal decomposition method according to a plurality of twin snapshots, and acquiring a weight coefficient of each basis function direction of each three-dimensional physical field under the working condition of each twin snapshot;
and taking the weight coefficient of each basis function direction of each three-dimensional physical field under each twin snapshot working condition as a sample set, and obtaining the preset digital twin model of the three-dimensional multi-physical field of the fuel cell based on a pre-selected machine learning algorithm, interpolation algorithm or regression algorithm.
The invention also provides a prediction device of the three-dimensional physical field of the fuel cell, which comprises
A memory for storing a computer program;
a processor for implementing the steps of the method for predicting a three-dimensional physical field of a fuel cell when executing the computer program.
The invention also provides a computer-readable storage medium, in which a computer program is stored which, when being executed by a processor, carries out the steps of the method for predicting a three-dimensional physical field of a fuel cell.
Compared with the prior art, the invention has the beneficial effects that:
the invention provides a prediction method and a system of a three-dimensional physical field of a fuel cell, which realize the online prediction of the three-dimensional physical field in the fuel cell through a plurality of twin snapshots obtained based on offline simulation; solving a coupling model of a pre-constructed three-dimensional multi-physical field of the fuel cell to obtain a plurality of twin snapshots, and providing off-line snapshots; constructing a plurality of basis functions aiming at each type of three-dimensional physical field in the fuel cell by adopting an intrinsic orthogonal decomposition method, obtaining a weight coefficient of each basis function direction of each three-dimensional physical field under each twin snapshot working condition, realizing the establishment of a basis function coordinate system for describing the three-dimensional physical field of the fuel cell, projecting a plurality of twin snapshots under a three-dimensional Cartesian coordinate system to the basis function coordinate system, obtaining the weight coefficient of each basis function direction of each three-dimensional physical field under each snapshot working condition, and further realizing the re-characterization of the physical field in the fuel cell; because each base function has the characteristic that the captured information is very concentrated, the problem of prediction of the three-dimensional physical field of the fuel cell is converted into the problem of prediction of the weight coefficient by using a representation mode under a base function coordinate system, so that the problem of prediction of the three-dimensional physical field of the fuel cell is reduced in a large scale, and the prediction time can be reduced to the order of magnitude of seconds; meanwhile, a pre-selected machine learning algorithm model, an interpolation algorithm model and/or a regression algorithm model are used as a basic frame of the prediction model, the characteristic that the prediction model is constructed under the condition of multiple input parameters based on less snapshots is met, and the condition that the input parameters are more but the number of snapshots is not excessive in the prediction problem of the three-dimensional physical field of the fuel cell is solved; the prediction process is simple, the simulation speed of the three-dimensional multi-physical field of the proton exchange membrane fuel cell is high, the on-line prediction of the three-dimensional multi-physical field in the fuel cell can be realized, and the prediction efficiency and the accuracy of the prediction result are high.
Drawings
FIG. 1 is a flow chart of the construction of a digital twin model of a fuel cell three-dimensional multi-physical field preset in the present invention;
FIG. 2 is a graph showing the results of global relative errors of an electronic potential field, a temperature field, a film water content field and a liquid water saturation field in the digital twin results under random operating conditions in the example;
FIG. 3 is a diagram illustrating a comparison of simulation results and digital twin prediction results for a liquid water saturation field under a random condition in an embodiment;
FIG. 4 is a diagram illustrating a comparison of simulation results and digital twin prediction results for an electronic potential field under a random condition in an embodiment;
FIG. 5 is a comparison graph of simulation results and digital twin prediction results for a random operating condition temperature field in an embodiment.
Detailed Description
In order to make the technical problems, technical solutions and advantageous effects of the present invention more apparent, the present invention is further described in detail with reference to specific embodiments below. It should be understood that the specific embodiments described herein are merely illustrative of the invention and do not limit the invention.
The invention provides a prediction method of a three-dimensional physical field of a fuel cell, which comprises the following steps:
step 1, obtaining variable input parameters of random working conditions of a fuel cell to be predicted; the variable input parameters of the random working condition of the fuel cell to be predicted comprise cathode pressure, anode pressure, cathode humidity, anode humidity, cathode stoichiometric ratio, anode stoichiometric ratio and operating temperature of the fuel cell to be predicted.
And 2, taking the variable input parameters of the random working condition of the fuel cell to be predicted as the input of a preset digital twin model of the three-dimensional multi-physical field of the fuel cell, and outputting to obtain a digital twin result of the three-dimensional multi-physical field, namely obtaining a prediction result of the three-dimensional multi-physical field of the fuel cell to be predicted.
The construction process of the digital twin model of the preset three-dimensional multi-physical field of the fuel cell comprises the following steps:
solving a coupling model of a pre-constructed three-dimensional multi-physical field of the fuel cell to obtain a plurality of twin snapshots;
aiming at each type of three-dimensional physical field in the fuel cell, constructing a plurality of basis functions by adopting an intrinsic orthogonal decomposition method according to a plurality of twin snapshots, and acquiring a weight coefficient of each basis function direction of each three-dimensional physical field under the working condition of each twin snapshot;
and taking the weight coefficient of each basis function direction of each three-dimensional physical field under each twin snapshot working condition as a sample set, and obtaining the preset digital twin model of the three-dimensional multi-physical field of the fuel cell based on a pre-selected machine learning algorithm, an interpolation algorithm or a regression algorithm.
As shown in fig. 1, the process for constructing the digital twin model of the preset three-dimensional multi-physical field of the fuel cell specifically includes the following steps:
step 201, constructing a three-dimensional multi-physical field coupling model of the fuel cell; the coupling model of the three-dimensional multi-physical field of the fuel cell is a three-dimensional two-phase non-isothermal numerical simulation model based on liquid pressure continuity.
Step 202, obtaining model parameters of the fuel cell according to the coupling model of the three-dimensional multi-physical field of the fuel cell.
Wherein the model parameters of the fuel cell comprise geometric parameters, physical parameters, electrochemical parameters and operating parameters of the fuel cell; specifically, the geometric parameters include the length of a flow channel, the ridge width ratio and the layer thickness of the fuel cell; the physical parameters comprise layer conductivity, diffusion coefficient and density pole thermal conductivity of the fuel cell; the electrochemical parameters include a reference exchange current, a reference concentration, and a platinum to carbon ratio for the fuel cell; the operating parameters include a cathode pressure, an anode pressure, a cathode humidity, an anode humidity, a cathode stoichiometry, an anode stoichiometry, and an operating temperature of the fuel cell.
Step 203, selecting variable parameters from the model parameters of the fuel cell, and determining to obtain variable input parameters of a plurality of snapshot working conditions by adopting a test design method when the numerical value of the variable parameters changes; wherein, the variable input parameters of the plurality of snapshot conditions include: cathode pressure, anode pressure, cathode humidity, anode humidity, cathode stoichiometry, anode stoichiometry, and operating temperature of the fuel cell.
And 204, taking the variable input parameters of the plurality of snapshot working conditions as the input of the coupling model of the three-dimensional multi-physical field of the fuel cell, and obtaining the three-dimensional multi-physical field simulation results under the plurality of snapshot working conditions through simulation so as to obtain a plurality of twin snapshots.
The method comprises the following specific processes:
compiling a three-dimensional multi-physical field coupling model of the fuel cell to be predicted into ANSYS Fluent software by adopting C language, taking variable input parameters of a plurality of snapshot working conditions as input, and performing simulation output to obtain a plurality of twin snapshots; wherein, a plurality of twin snapshots are output in a Tecplot file format.
And 205, generating snapshot matrixes under the working conditions of a plurality of snapshots according to a plurality of twin snapshots for each type of three-dimensional physical field in the fuel cell.
And step 206, aiming at each type of three-dimensional physical field in the fuel cell, carrying out matrix decomposition and matrix transformation processing on the snapshot matrixes under a plurality of snapshot working conditions by using a singular value decomposition method to obtain a plurality of basis functions.
And step 207, projecting the twin snapshots to each basis function direction, and reconstructing to obtain the weight coefficient of each basis function direction of each three-dimensional physical field under the working condition of each twin snapshot.
And 208, taking the weight coefficient of each basis function direction of each three-dimensional physical field under each twin snapshot working condition as a sample set, and obtaining the preset digital twin model of the three-dimensional multi-physical field of the fuel cell based on a pre-selected machine learning algorithm, an interpolation algorithm or a regression algorithm.
The preset digital twin model of the three-dimensional multi-physical field of the fuel cell is as follows:
wherein: r is the number of physical quantity; f' r A three-dimensional physical field of an r-th physical quantity under variable input parameters of the fuel cell to be predicted; b' r,j The weight coefficient of the three-dimensional physical field of the r physical quantity in the j basic function direction; psi r,j A jth basis function being an r physical quantity; j is the number of the above-mentioned base function; l r Is the truncation order of the r-th physical quantity. The truncation order refers to the number of basis functions that need to be considered in such a three-dimensional physical field.
The invention also provides a prediction system of the three-dimensional physical field of the fuel cell, which comprises an acquisition module and a prediction module; the acquisition module is used for acquiring variable input parameters of random working conditions of the fuel cell to be predicted; the prediction module is used for taking the variable input parameters of the random working conditions of the fuel cell to be predicted as the input of a preset digital twin model of the three-dimensional multi-physical field of the fuel cell and outputting the digital twin result of the three-dimensional multi-physical field to be obtained, namely the prediction result of the three-dimensional multi-physical field of the fuel cell to be predicted; the construction process of the digital twin model of the preset three-dimensional multi-physical field of the fuel cell comprises the following steps: solving a coupling model of a pre-constructed three-dimensional multi-physical field of the fuel cell to obtain a plurality of twin snapshots; aiming at each type of three-dimensional physical field in the fuel cell, constructing a plurality of basis functions by adopting an intrinsic orthogonal decomposition method according to a plurality of twin snapshots, and acquiring a weight coefficient of each basis function direction of each three-dimensional physical field under the working condition of each twin snapshot; and taking the weight coefficient of each basis function direction of each three-dimensional physical field under each twin snapshot working condition as a sample set, and obtaining the preset digital twin model of the three-dimensional multi-physical field of the fuel cell based on a pre-selected machine learning algorithm, interpolation algorithm or regression algorithm.
The invention also provides a prediction device of the three-dimensional physical field of the fuel cell, which comprises the following components: a memory for storing a computer program; a processor for implementing the steps of the method for predicting a three-dimensional physical field of a fuel cell when executing said computer program.
The processor, when executing the computer program, implements the steps of the method for predicting a three-dimensional physical field of a fuel cell, such as: acquiring variable input parameters of random working conditions of the fuel cell to be predicted; the variable input parameters of the random working condition of the fuel cell to be predicted are used as the input of a preset digital twin model of the three-dimensional multi-physical field of the fuel cell, and the digital twin result of the three-dimensional multi-physical field is output to obtain the prediction result of the three-dimensional multi-physical field of the fuel cell to be predicted; the construction process of the preset digital twin model of the three-dimensional multi-physical field of the fuel cell comprises the following steps: solving a coupling model of a pre-constructed three-dimensional multi-physical field of the fuel cell to obtain a plurality of twin snapshots; aiming at each type of three-dimensional physical field in the fuel cell, constructing a plurality of basis functions by adopting an intrinsic orthogonal decomposition method according to a plurality of twin snapshots, and acquiring a weight coefficient of each basis function direction of each three-dimensional physical field under the working condition of each twin snapshot; and taking the weight coefficient of each basis function direction of each three-dimensional physical field under each twin snapshot working condition as a sample set, and obtaining the preset digital twin model of the fuel cell three-dimensional multi-physical field based on a pre-selected machine learning algorithm, interpolation algorithm or regression algorithm.
Alternatively, the processor implements the functions of the modules in the system when executing the computer program, for example: the acquisition module is used for acquiring variable input parameters of random working conditions of the fuel cell to be predicted; the prediction module is used for taking the variable input parameters of the random working conditions of the fuel cell to be predicted as the input of a preset digital twin model of the three-dimensional multi-physical field of the fuel cell and outputting the digital twin result of the three-dimensional multi-physical field to be obtained, namely the prediction result of the three-dimensional multi-physical field of the fuel cell to be predicted; the construction process of the digital twin model of the preset three-dimensional multi-physical field of the fuel cell comprises the following steps: solving a coupling model of a pre-constructed three-dimensional multi-physical field of the fuel cell to obtain a plurality of twin snapshots; aiming at each type of three-dimensional physical field in the fuel cell, constructing a plurality of basis functions by adopting an intrinsic orthogonal decomposition method according to a plurality of twin snapshots, and acquiring weight coefficients of each basis function direction of each three-dimensional physical field under the working condition of each twin snapshot; and taking the weight coefficient of each basis function direction of each three-dimensional physical field under each twin snapshot working condition as a sample set, and obtaining the preset digital twin model of the three-dimensional multi-physical field of the fuel cell based on a pre-selected machine learning algorithm, interpolation algorithm or regression algorithm.
Illustratively, the computer program may be partitioned into one or more modules/units that are stored in the memory and executed by the processor to implement the invention. The one or more modules/units may be a series of computer program instruction segments capable of performing preset functions, the instruction segments being used to describe the execution process of the computer program in the prediction device of the three-dimensional physical field of the fuel cell. For example, the computer program may be divided into an acquisition module and a prediction module, and the specific functions of each module are as follows: the acquisition module is used for acquiring variable input parameters of random working conditions of the fuel cell to be predicted; and the prediction module is used for taking the variable input parameters of the random working conditions of the fuel cell to be predicted as the input of a preset digital twin model of the three-dimensional multi-physical field of the fuel cell and outputting a digital twin result of the three-dimensional multi-physical field, namely a prediction result of the three-dimensional multi-physical field of the fuel cell to be predicted.
The prediction device of the three-dimensional physical field of the fuel cell can be a desktop computer, a notebook computer, a palm computer, a cloud server and other computing devices. The prediction device of the three-dimensional physical field of the fuel cell can comprise, but is not limited to, a processor and a memory. It will be understood by those skilled in the art that the foregoing is an example of a device for predicting a three-dimensional physical field of a fuel cell, and does not constitute a limitation of the device for predicting a three-dimensional physical field of a fuel cell, and may include more components than the foregoing, or some components in combination, or different components, for example, the device for predicting a three-dimensional physical field of a fuel cell may further include an input-output device, a network access device, a bus, and the like.
The processor may be a Central Processing Unit (CPU), other general purpose processor, a Digital Signal Processor (DSP), an Application Specific Integrated Circuit (ASIC), an off-the-shelf programmable gate array (FPGA) or other programmable logic device, discrete gate or transistor logic, discrete hardware components, etc. The general purpose processor may be a microprocessor or the processor may be any conventional processor or the like, the processor being the control center of the fuel cell three dimensional physical field prediction device, various interfaces and lines connecting the various parts of the entire fuel cell three dimensional physical field prediction device.
The memory may be used to store the computer programs and/or modules, and the processor may implement the various functions of the prediction device of the three-dimensional physical field of the fuel cell by executing or executing the computer programs and/or modules stored in the memory, and calling up the data stored in the memory.
The memory may mainly include a storage program area and a storage data area, wherein the storage program area may store an operating system, an application program required by at least one function (such as a sound playing function, an image playing function, etc.), and the like; the storage data area may store data (such as audio data, a phonebook, etc.) created according to the use of the cellular phone, etc. In addition, the memory may include high-speed random access memory, and may also include non-volatile memory, such as a hard disk, a memory, a plug-in hard disk, a Smart Media Card (SMC), a Secure Digital (SD) card, a flash memory card (FlashCard), at least one magnetic disk storage device, a flash memory device, or other volatile solid state storage device.
The invention also provides a computer-readable storage medium, in which a computer program is stored which, when being executed by a processor, carries out the steps of the method for predicting a three-dimensional physical field of a fuel cell.
The modules/units integrated by the prediction system of the three-dimensional physical field of the fuel cell can be stored in a computer readable storage medium if the modules/units are realized in the form of software functional units and sold or used as independent products.
Based on such understanding, all or part of the flow in the method for predicting the three-dimensional physical field of the fuel cell according to the present invention may be implemented by a computer program, which may be stored in a computer-readable storage medium, and when the computer program is executed by a processor, the steps of the method for predicting the three-dimensional physical field of the fuel cell may be implemented. Wherein the computer program comprises computer program code, which may be in the form of source code, object code, an executable file or a pre-set intermediate form, etc.
The computer-readable storage medium may include: any entity or device capable of carrying the computer program code, recording medium, usb disk, removable hard disk, magnetic disk, optical disk, computer memory, read-only memory (ROM), random Access Memory (RAM), electrical carrier wave signals, telecommunications signals, software distribution medium, etc.
It should be noted that the computer readable storage medium may contain content that is subject to appropriate increase or decrease as required by legislation and patent practice in jurisdictions, for example, in some jurisdictions, computer readable storage media that does not include electrical carrier signals and telecommunications signals in accordance with legislation and patent practice.
Examples
Taking the prediction process of three-dimensional multi-physical field of the hydrogen fuel proton exchange membrane fuel cell as an example; the hydrogen fuel proton exchange membrane fuel cell is a parallel flow channel.
The embodiment provides a method for predicting a three-dimensional physical field of a fuel cell, which comprises the following steps:
step 1, constructing a three-dimensional multi-physical-field coupling model of the fuel cell; the coupling model of the three-dimensional multi-physical field of the fuel cell is a three-dimensional two-phase non-isothermal numerical simulation model based on liquid pressure continuity; the three-dimensional two-phase non-isothermal numerical simulation model based on liquid pressure continuity comprises twelve conservation equations and a plurality of submodels; wherein the twelve conservation equations comprise: mass conservation equation, three momentum conservation equations, energy conservation equation, three component conservation equation, electron potential conservation equation, proton potential conservation equation, membrane state water conservation equation and liquid water pressure conservation equation; the plurality of submodels comprise an aggregate submodel, a gas-liquid phase change submodel and a membrane-water phase change submodel; wherein, the three-dimensional multi-physical field includes but is not limited to an electronic potential field, a temperature field, a liquid water saturation field and a film water content field.
Step 2, obtaining model parameters of the fuel cell according to the coupling model of the three-dimensional multi-physical field of the fuel cell; the model parameters of the fuel cell comprise geometric parameters, physical parameters, electrochemical parameters and operating parameters of the fuel cell.
Wherein the geometric parameters comprise the length of a flow channel of the fuel cell, the ridge width ratio and the layer thickness; the physical parameters comprise layer conductivity, diffusion coefficient and density pole thermal conductivity of the fuel cell; the electrochemical parameters include a reference exchange current, a reference concentration, and a platinum/carbon ratio of the fuel cell; the operating parameters include cathode pressure, anode pressure, cathode humidity, anode humidity, cathode stoichiometry, anode stoichiometry, and operating temperature of the fuel cell.
Step 3, selecting variable parameters from the model parameters of the fuel cell, and determining to obtain variable input parameters of a plurality of snapshot working conditions by adopting a test design method when the numerical value of the variable parameters changes; wherein, the variable input parameters of the plurality of snapshot conditions include: cathode pressure, anode pressure, cathode humidity, anode humidity, cathode stoichiometry, anode stoichiometry, and operating temperature of the fuel cell; in this embodiment, based on a paired test design method, a PICT (Picture Independent combining Testing) software is used to develop a test design, and 139 sets of variable input parameters of snapshot conditions are designed in total.
And 4, taking the variable input parameters of the plurality of snapshot working conditions as the input of the coupling model of the three-dimensional multi-physical field of the fuel cell, and obtaining a plurality of twin snapshots through simulation.
The simulation process specifically comprises the following steps:
compiling a coupling model of the three-dimensional multi-physical field of the fuel cell into ANSYS Fluent software by adopting C language, taking variable input parameters of a plurality of snapshot working conditions as input, and carrying out simulation output to obtain a three-dimensional multi-physical field simulation result under the plurality of snapshot working conditions; and outputting the three-dimensional multi-physical field simulation results under the plurality of snapshot working conditions in a Tecplot file format.
In the embodiment, based on ANSYS Fluent software, a user-defined function (UDF) is written by adopting C language, and variable input parameters of a plurality of snapshot working conditions are used as input, so that the solution of a coupling model of a three-dimensional multi-physical field of the fuel cell is realized; and analyzing the grid file to a file interface of the Tecplot software based on ANSYS Fluent software, and extracting a simulation result of the Tecplot software, namely obtaining a three-dimensional multi-physical field simulation result under a plurality of snapshot working conditions output in a Tecplot file format.
wherein: r is the number of the physical quantity or the three-dimensional physical field; f r A snapshot matrix which is the r three-dimensional physical field; m is the number of grid nodes; n is the number of snapshots; f. of r,i,j The value of the r physical quantity on the ith node in the jth snapshot is obtained; wherein i is 1 to m, and j is 1 to n.
Step 6, for each three-dimensional physical field, performing matrix decomposition and matrix transformation on the snapshot matrix under a plurality of snapshot working conditions based on a singular value decomposition method to obtain a plurality of three-dimensional basis functions; according to the singular value decomposition method, for each three-dimensional physical field, the snapshot matrix under a plurality of snapshot working conditions can be decomposed into the following formulas:
wherein: r is the number of the physical quantity; f r A snapshot matrix which is the r physical quantity; u shape r A left singular matrix formed by the left singular vectors of the r physical quantity; sigma-shaped r A singular value matrix of the r-th physical quantity; v r A right singular matrix formed by right singular vectors of the r-th physical quantity; a * Is the conjugate transpose of the matrix.
In the embodiment, a unilateral Jacobi algorithm is adopted to obtain a right singular matrix; the unilateral Jacobi algorithm is realized based on C + +; the specific process is as follows:
(1) Calculating an initial kernel matrix:
wherein: r is the number of the physical quantity; k is the Jacobi transformation times;
a kernel matrix after k times of Jacobi transformation of the r physical quantity is obtained; f r A snapshot matrix which is the r-th physical quantity; a * Is the conjugate transpose of the matrix.
(2) And (3) circulating all p and q combinations meeting the condition that p is more than or equal to 1 and less than or equal to q and more than or equal to n, and obtaining a second-order main sub-formula of the kernel matrix as follows, and executing the step (3) and the step (4):
wherein: r is the number of physical quantity; p is the line number of the second order major formula; q is the column number of the second-order main sub-formula;
the p row and the p column of the kernel matrix after the k time of Jacobi transformation of the r physical number;
the kth physical quantity is the p row and the q column of the kernel matrix after the kth Jacobi transformation;
the qth row and the pth column of the kernel matrix after the kth physical quantity and the Jacobi transformation are respectively;
and the qth row and the qth column of the kernel matrix after the kth Jacobi transformation of the r physical quantity are shown.
(3) Jacobi matrix J r,k And (3) calculating:
wherein: r is the number of the physical quantity; p is the line number of the second order major formula; q is the column number of the second-order major-minor type; theta r,k The rotation angle of the k-th Jacobi transform for the r-th physical quantity; j. the design is a square r,k A matrix representation of the k-th Jacobi transformation for the r-th physical quantity; sin is the sine of the angle; cos is the cosine of the angle; cot is the cotangent of the angle.
(4) Updating a core matrix:
wherein: r is the number of the physical quantity;
the kernel matrix is the k +1 th transformed Jacobi of the r physical number;
a kernel matrix which is obtained after k times of Jacobi transformation of the r physical quantity; j. the design is a square r,k A matrix representation of the k-th Jacobi transformation for the r-th physical quantity; a * Is the conjugate transpose of the matrix.
(5) And (3) continuously circulating the step (2) until the kernel matrix is converted into the diagonal matrix.
(6) Calculation of right singular vectors:
wherein: r is the number of the physical quantity; n is a radical of r Number of Jacobi transformations required to convert the kernel matrix into the diagonal matrix for the r-th physical quantityAn amount; j. the design is a square r,k (k is 1 to N) r ) The matrix representation of the k-th Jacobi transformation for the r-th physical quantity.
(7) Snapshot rotation:
ψ′ r ＝F r V r
wherein: r is the number of physical quantity; psi' r A matrix formed by the non-normalized basis function vectors of the r physical quantity; f r A snapshot matrix which is the r physical quantity; v r Is the right singular matrix of the r-th physical quantity.
(8) Will matrix psi' r Is calculated by its two-norm (i.e., singular value or contained information quantity) | | ψ' r,i || 2 Sorting from big to small, and obtaining a basis function after normalization:
wherein: r is the number of physical quantity; i is the number of the basis function; psi r,i An ith basis function being an r-th physical quantity; psi' r,i An ith unnormalized basis function for an r-th physical quantity; i | · | | is the two-norm of the vector.
Step 7, projecting the three-dimensional physical field under each snapshot working condition to each basis function direction aiming at each three-dimensional physical field, and reconstructing to obtain the weight coefficient of each basis function direction of each three-dimensional physical field under each snapshot working condition; the specific process is as follows:
projecting the three-dimensional physical field under each snapshot working condition to each basis function direction to obtain a weight coefficient corresponding to each snapshot working condition in each basis function direction; wherein, the weight coefficient corresponding to each snapshot working condition in each basis function direction is:
wherein: r is the number of physical quantity; b is a mixture of r,i,k Representing the weight coefficient of the projection of the r physical quantity on the i basis function in the k snapshot;
a conjugate transpose of the ith basis function of the r-th physics; f. of r,k The three-dimensional physical field of the r-th physical quantity in the k-th snapshot.
Step 8, taking the weight coefficient of each basis function direction of each three-dimensional physical field under each twin snapshot working condition as a sample set, and obtaining a digital twin model of the preset three-dimensional multi-physical field of the fuel cell based on a pre-selected machine learning algorithm, an interpolation algorithm or a regression algorithm; preferably, the pre-selected machine learning algorithm is an artificial neural network algorithm, a multivariate adaptive regression spline algorithm or a deep learning algorithm.
In this embodiment, a predetermined truncation error TE% is selected, if r First l satisfying the r-th physical quantity r The first l of the first r physical quantity of the basis function neglecting the information quantity less than TE% r 1 basis function neglects the amount of information over TE%, then l will be r The truncation order is called as the truncation order under the truncation error TE% of the r-th physical quantity; the preset digital twin model of the three-dimensional multi-physical field of the fuel cell is as follows:
wherein: r is the number of the physical quantity; f' r A three-dimensional physical field of an r-th physical quantity under variable input parameters of the fuel cell to be predicted; b' r,j The weight coefficient of the three-dimensional physical field of the r physical quantity in the j basic function direction; psi r,j A jth basis function being an r physical quantity; j is the number of the basis function; l. the r Is the truncation order of the r-th physical quantity.
Step 9, obtaining variable input parameters of the random working condition of the fuel cell to be predicted;
and 10, taking the variable input parameters of the random working condition of the fuel cell to be predicted as the input of a preset digital twin model of the three-dimensional multi-physical field of the fuel cell, and outputting to obtain a digital twin result of the three-dimensional multi-physical field, namely obtaining a prediction result of the three-dimensional multi-physical field of the fuel cell to be predicted.
And (3) test verification:
the following explains the prediction effect of the three-dimensional multi-physical-field digital twinning technique by taking twenty sets of randomly variable input parameters, TE% = 0.01%. The global relative error is defined in terms of a two-norm, as shown in the following equation:
wherein: r is the number of physical quantity;
the three-dimensional physical field refers to the r physical quantity in the three-dimensional digital twinning result; f. of r,j The method comprises the steps of (1) indicating a three-dimensional physical field of an r-th physical quantity in numerical simulation results under the same variable input parameters; delta. For the preparation of a coating r Is the global relative error of the r-th physical quantity.
As shown in fig. 2, fig. 2 shows a global relative error result diagram of an electronic potential field, a temperature field, a film state water content field and a liquid state water saturation field in each random working condition digital twin result in the embodiment; as can be seen from the attached figure 2, the global relative error of most working conditions is within 15%, and the reliability of the three-dimensional multi-physical-field digital twinning method provided by the embodiment is verified.
As shown in fig. 3-5, fig. 3 shows a comparison graph of a simulation result of a liquid water saturation field and a digital twin prediction result under a certain random working condition in an embodiment, fig. 4 shows a comparison graph of a simulation result of an electron potential field and a digital twin prediction result under a certain random working condition in an embodiment, and fig. 5 shows a comparison graph of a simulation result of a temperature field under a certain random working condition and a digital twin prediction result under a certain random working condition in an embodiment; as can be seen from fig. 3 to 5, the method for predicting a three-dimensional physical field of a fuel cell according to the embodiment can accurately capture the global features and the local features of each physical field, and has high prediction accuracy.
The prediction method of the three-dimensional physical field of the fuel cell meets the requirements of realizing rapid and accurate prediction of three-dimensional multi-physical fields in the fuel cell based on a large number of off-line simulation results on the basis of a given fuel cell numerical model, and meeting the prediction requirements of the multi-physical fields in the fuel cell on-line control scene; the method comprises the steps of realizing rapid and accurate prediction of three-dimensional multi-physical fields in a fuel cell based on an intrinsic orthogonal decomposition technology, carrying out expansion prediction on weight coefficients under any random working condition by adopting a pre-selected machine learning algorithm, an interpolation algorithm or a regression algorithm, and rapidly and accurately obtaining multi-physical field prediction results under any random working condition through a modal superposition method on the weight coefficients and basis functions obtained by prediction.
It should be noted that the prediction method of the three-dimensional physical field of the fuel cell according to the present embodiment is also applicable to other geometric structures, other types of fuel cells, and other fuel cell models; for example: serpentine flow channels, solid oxide fuel cells, three-dimensional single-phase isothermal models, and the like.
For a description of relevant parts in the system, the device and the computer-readable storage medium for predicting a three-dimensional physical field of a fuel cell provided in this embodiment, reference may be made to the detailed description of the corresponding parts in the method for predicting a three-dimensional physical field of a fuel cell described in this embodiment, and details are not repeated here.
The method, the system, the equipment and the medium for predicting the three-dimensional physical field of the fuel cell can predict the three-dimensional multi-physical field in the fuel cell only in seconds, and verify that the method can be applied to the online prediction of the internal physical field of the fuel cell.
The above-described embodiment is only one of the embodiments that can implement the technical solution of the present invention, and the scope of the present invention is not limited by the embodiment, but includes any variations, substitutions and other embodiments that can be easily conceived by those skilled in the art within the technical scope of the present invention disclosed.
Claims (10)
1. A method for predicting a three-dimensional physical field of a fuel cell, comprising:
acquiring variable input parameters of random working conditions of the fuel cell to be predicted;
the variable input parameters of the random working condition of the fuel cell to be predicted are used as the input of a preset digital twin model of the three-dimensional multi-physical field of the fuel cell, and the digital twin result of the three-dimensional multi-physical field is output to obtain the prediction result of the three-dimensional multi-physical field of the fuel cell to be predicted;
the construction process of the digital twin model of the preset three-dimensional multi-physical field of the fuel cell comprises the following steps:
solving a coupling model of a pre-constructed three-dimensional multi-physical field of the fuel cell to obtain a plurality of twin snapshots;
aiming at each type of three-dimensional physical field in the fuel cell, constructing a plurality of basis functions by adopting an intrinsic orthogonal decomposition method according to a plurality of twin snapshots, and acquiring a weight coefficient of each basis function direction of each three-dimensional physical field under the working condition of each twin snapshot;
and taking the weight coefficient of each basis function direction of each three-dimensional physical field under each twin snapshot working condition as a sample set, and obtaining the preset digital twin model of the fuel cell three-dimensional multi-physical field based on a pre-selected machine learning algorithm, interpolation algorithm or regression algorithm.
2. The method as claimed in claim 1, wherein the variable input parameters of the random operating conditions of the fuel cell to be predicted comprise cathode pressure, anode pressure, cathode humidity, anode humidity, cathode stoichiometry, anode stoichiometry, and operating temperature of the fuel cell to be predicted.
3. The method for predicting the three-dimensional physical field of the fuel cell according to claim 1, wherein the preset process for constructing the digital twin model of the three-dimensional multi-physical field of the fuel cell is as follows:
constructing a three-dimensional multi-physical field coupling model of the fuel cell;
obtaining model parameters of the fuel cell according to the coupling model of the three-dimensional multi-physical field of the fuel cell;
selecting variable parameters from the model parameters of the fuel cell to obtain variable input parameters of a plurality of snapshot working conditions;
taking variable input parameters of a plurality of snapshot working conditions as the input of a coupling model of a three-dimensional multi-physical field of the fuel cell, and obtaining a plurality of twin snapshots through simulation;
generating a plurality of snapshot matrixes under snapshot working conditions according to a plurality of twin snapshots aiming at each type of three-dimensional physical field in the fuel cell;
aiming at each type of three-dimensional physical field in the fuel cell, matrix decomposition and matrix transformation processing are carried out on a snapshot matrix under a plurality of snapshot working conditions by using a singular value decomposition method to obtain a plurality of basis functions;
projecting a plurality of twin snapshots to each basis function direction, and reconstructing to obtain a weight coefficient of each basis function direction of each three-dimensional physical field under the working condition of each twin snapshot;
and taking the weight coefficient of each basis function direction of each three-dimensional physical field under each twin snapshot working condition as a sample set, and obtaining the preset digital twin model of the three-dimensional multi-physical field of the fuel cell based on a pre-selected machine learning algorithm, interpolation algorithm or regression algorithm.
4. The method of claim 3, wherein the model parameters of the fuel cell comprise geometric parameters, physical parameters, electrochemical parameters and operational parameters of the fuel cell.
5. The method for predicting the three-dimensional physical field of the fuel cell according to claim 3, wherein the coupling model of the three-dimensional multi-physical field of the fuel cell is a three-dimensional two-phase non-isothermal numerical simulation model based on liquid pressure continuity.
6. The method for predicting the three-dimensional physical field of the fuel cell according to claim 3, wherein variable input parameters of a plurality of snapshot working conditions are used as input of a coupling model of the three-dimensional multi-physical field of the fuel cell, and a plurality of twin snapshots are obtained through simulation, specifically as follows:
compiling a three-dimensional multi-physical field coupling model of the fuel cell to be predicted into ANSYS Fluent software by adopting C language, taking variable input parameters of a plurality of snapshot working conditions as input, and performing simulation output to obtain a plurality of twin snapshots; wherein, a plurality of twin snapshots are output in a Tecplot file format.
7. The method for predicting the three-dimensional physical field of the fuel cell according to claim 3, wherein the preset digital twin model of the three-dimensional multi-physical field of the fuel cell is as follows:
wherein r is a number of a physical quantity; f. of r ' is a three-dimensional physical field of an r-th physical quantity under variable input parameters of the fuel cell to be predicted; b r ′ ,j The weight coefficient of the three-dimensional physical field of the r physical quantity in the j basic function direction; psi r,j A jth basis function being an r physical quantity; j is the number of the above-mentioned base function; l r Is the truncation order of the r-th physical quantity.
8. A system for predicting a three-dimensional physical field of a fuel cell, comprising:
the acquisition module is used for acquiring variable input parameters of random working conditions of the fuel cell to be predicted;
the prediction module is used for taking the variable input parameters of the random working conditions of the fuel cell to be predicted as the input of a preset digital twin model of the three-dimensional multi-physical field of the fuel cell and outputting the digital twin result of the three-dimensional multi-physical field to be obtained, namely the prediction result of the three-dimensional multi-physical field of the fuel cell to be predicted;
the construction process of the digital twin model of the preset three-dimensional multi-physical field of the fuel cell comprises the following steps:
solving a coupling model of a pre-constructed three-dimensional multi-physical field of the fuel cell to obtain a plurality of twin snapshots;
aiming at each type of three-dimensional physical field in the fuel cell, constructing a plurality of basis functions by adopting an intrinsic orthogonal decomposition method according to a plurality of twin snapshots, and acquiring weight coefficients of each basis function direction of each three-dimensional physical field under the working condition of each twin snapshot;
and taking the weight coefficient of each basis function direction of each three-dimensional physical field under each twin snapshot working condition as a sample set, and obtaining the preset digital twin model of the three-dimensional multi-physical field of the fuel cell based on a pre-selected machine learning algorithm, interpolation algorithm or regression algorithm.
9. A prediction device for a three-dimensional physical field of a fuel cell, comprising
A memory for storing a computer program;
a processor for implementing the steps of the method of predicting a three-dimensional physical field of a fuel cell according to any one of claims 1 to 7 when executing said computer program.
10. A computer-readable storage medium, in which a computer program is stored which, when being executed by a processor, carries out the steps of the method for predicting a three-dimensional physical field of a fuel cell according to any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210929061.0A CN115270633A (en) | 2022-08-03 | 2022-08-03 | Prediction method, system, device and medium for three-dimensional physical field of fuel cell |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210929061.0A CN115270633A (en) | 2022-08-03 | 2022-08-03 | Prediction method, system, device and medium for three-dimensional physical field of fuel cell |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN115270633A true CN115270633A (en) | 2022-11-01 |
Family
ID=83748390
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210929061.0A Pending CN115270633A (en) | 2022-08-03 | 2022-08-03 | Prediction method, system, device and medium for three-dimensional physical field of fuel cell |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115270633A (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115762683A (en) * | 2022-11-25 | 2023-03-07 | 中国科学院宁波材料技术与工程研究所 | Method and device for processing fuel cell design data and electronic equipment |
| CN116404205A (en) * | 2023-06-02 | 2023-07-07 | 上海重塑能源科技有限公司 | Digital twin-based fuel cell low-temperature operation control system and method |
| CN118534332A (en) * | 2024-07-24 | 2024-08-23 | 深圳市菲尼基科技有限公司 | Battery monitoring method and system based on BMS system |
-
2022
- 2022-08-03 CN CN202210929061.0A patent/CN115270633A/en active Pending
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115762683A (en) * | 2022-11-25 | 2023-03-07 | 中国科学院宁波材料技术与工程研究所 | Method and device for processing fuel cell design data and electronic equipment |
| CN115762683B (en) * | 2022-11-25 | 2023-05-26 | 中国科学院宁波材料技术与工程研究所 | Method and device for processing fuel cell design data and electronic equipment |
| CN116404205A (en) * | 2023-06-02 | 2023-07-07 | 上海重塑能源科技有限公司 | Digital twin-based fuel cell low-temperature operation control system and method |
| CN116404205B (en) * | 2023-06-02 | 2023-09-08 | 上海重塑能源科技有限公司 | Digital twin-based fuel cell low-temperature operation control system and method |
| CN118534332A (en) * | 2024-07-24 | 2024-08-23 | 深圳市菲尼基科技有限公司 | Battery monitoring method and system based on BMS system |
| CN118534332B (en) * | 2024-07-24 | 2024-09-27 | 深圳市菲尼基科技有限公司 | Battery monitoring method and system based on BMS system |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN115270633A (en) | Prediction method, system, device and medium for three-dimensional physical field of fuel cell | |
| CN107609141B (en) | Method for performing rapid probabilistic modeling on large-scale renewable energy data | |
| Zhou et al. | GPU-accelerated algorithm for online probabilistic power flow | |
| CN116029464B (en) | Acceleration solving method for accurate box-type economic operation domain of power grid | |
| Astolfi et al. | Model reduction by moment matching: Beyond linearity a review of the last 10 years | |
| Hu et al. | Design of recurrent neural networks for solving constrained least absolute deviation problems | |
| CN109038592A (en) | A kind of method of sampling and the probability load flow calculation method using the method for sampling | |
| CN105608059A (en) | Module for solving triangular matrix decomposition based on improved bitwise substitution method | |
| Wang et al. | A data‐driven probabilistic power flow method based on convolutional neural networks | |
| Tang et al. | Application of ELM–Hammerstein model to the identification of solid oxide fuel cells | |
| CN115392029A (en) | Lithium battery thermal process space-time modeling method based on KWLSAT | |
| Tang et al. | Electrical power prediction of proton exchange membrane fuel cell by using support vector regression | |
| CN117613952B (en) | Matrix completion state estimation method and system for three-phase unbalanced distribution network | |
| CN117875241A (en) | Simulation calculation method, device and equipment for cascade H-bridge converter energy storage system | |
| CN113850298A (en) | Image identification method and device and related equipment | |
| CN112241580B (en) | Power system parameter determining method, device, computer equipment and storage medium | |
| CN116306030A (en) | New energy prediction dynamic scene generation method considering prediction error and fluctuation distribution | |
| CN113592361B (en) | Power flow calculation method, device, computer equipment and storage medium for power system | |
| CN113078335B (en) | Performance analysis method and device of proton exchange membrane fuel cell and terminal equipment | |
| CN112084710B (en) | Solid oxide fuel cell voltage prediction method, terminal device, and storage medium | |
| CN114237548A (en) | Method and system for complex dot product operation based on nonvolatile memory array | |
| Mitra et al. | Parameter Estimation of Proton Exchange Membrane Fuel Cell Model Using Chaotic Embedded Particle Swarm Optimization Technique | |
| Chen et al. | Study on Model Evolution Method Based on the Hybrid Modeling Technology With Support Vector Machine for an SOFC-GT System | |
| CN112308197B (en) | Compression method and device of convolutional neural network and electronic equipment | |
| CN110020501B (en) | Equipment structure improvement method and equipment based on multiphase computational fluid mechanics interpolation |
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 |