Chemical reaction thermal fluid multi-field coupling reconstruction method and device based on deep learning

Abstract

The invention discloses a chemical reaction thermal fluid multi-field coupling reconstruction method and device based on deep learning, belongs to the technical field of chemical reaction thermal fluid forced convection heat transfer, and solves the problem of difficult flow field reconstruction caused by complex evolution of a flow field structure due to physical property and component changes of a chemical reaction thermal fluid. Comprising the following steps: constructing a three-dimensional numerical simulation model of a cooling channel, and obtaining numerical simulation steady-state data under various preset working conditions; preprocessing the numerical simulation steady-state data to obtain a preprocessed data set; constructing a multi-field coupling reconstruction network model, and training and optimizing the multi-field coupling reconstruction network model by adopting the preprocessed data set to obtain a trained multi-field coupling reconstruction network model; and based on the trained multi-field coupling reconstruction network model, reconstructing to obtain a temperature field, a physical property parameter field, a velocity field, a component field and a turbulence characteristic field of the chemical reaction thermal fluid. The device is suitable for research scenes of flow heat exchange characteristics of chemical reaction thermal fluid.

Description

Technical Field

[0001] This invention relates to the field of forced convection heat transfer technology for chemical reaction thermal fluids, and more specifically, to a method and apparatus for multi-field coupling reconstruction of chemical reaction thermal fluids based on deep learning. Background Technology

[0002] The dramatic changes in thermophysical properties of chemically reactive fluids within the critical region are accompanied by unique flow and heat transfer characteristics. Supercritical chemically reactive fluids, involving chemical reactions during flow and heat transfer, are influenced by both fluid dynamics and chemical reaction dynamics, resulting in strong coupling between heat transfer, mass transfer, turbulence, and chemical reaction, making their convective heat transfer and mass transfer behavior even more complex. Currently, research on the flow and heat transfer characteristics of chemically reactive fluids mainly relies on computational fluid dynamics (CFD). However, CFD simulations of complex systems often require abundant computational resources and a large number of computational samples, making it an expensive, time-consuming, and arduous task. Therefore, there is an urgent need to develop an efficient and accurate method that can obtain the flow field of chemically reactive fluids faster than traditional CFD. In recent years, the field of data science has developed rapidly, and deep learning (DL) technology for big data has demonstrated powerful capabilities in data-driven modeling using high-dimensional nonlinear flow fields, providing a new approach for the study of flow and heat transfer in chemically reactive fluids.

[0003] Existing deep learning studies on the heat transfer characteristics of fluids involved in chemical reactions utilize artificial neural networks (ANNs) to characterize heat transfer and flow behavior, aiming to quickly obtain more accurate empirical relationships between heat transfer and flow. However, ANNs can only predict zero-dimensional / one-dimensional parameters and cannot obtain flow field data with high-dimensional characteristics.

[0004] Avoiding time-consuming spatiotemporal discretization and numerical iterative calculations, reducing computational resource consumption, and shortening the time required to obtain accurate solutions for chemical reaction thermofluid flow fields are of great significance for improving the efficiency of design and optimization research of power cycles and thermodynamic systems using chemical reaction thermofluids as working fluids. Summary of the Invention

[0005] To address the existing technical problems, this invention provides a method, apparatus, electronic device, and computer-readable storage medium for multi-field coupling reconstruction of chemical reaction thermofluids based on deep learning.

[0006] In a first aspect, the present invention provides a deep learning-based method for reconstructing multi-field coupling of chemical reaction thermofluids, comprising: A three-dimensional numerical simulation model of the cooling channel is constructed, and steady-state numerical simulation data under various preset working conditions are obtained based on the three-dimensional numerical simulation model. The steady-state data from the numerical simulation are preprocessed to obtain the preprocessed dataset; A multi-field coupled reconstruction network model is constructed, and the preprocessed dataset is used to train and optimize the multi-field coupled reconstruction network model to obtain the trained multi-field coupled reconstruction network model. Based on the trained multi-field coupled reconstruction network model, the temperature field, physical property parameter field, velocity field, component field, and turbulence characteristic field of the chemical reaction thermofluid are reconstructed.

[0007] Optionally, the multiple preset operating conditions are combinations of different values ​​of at least two boundary condition parameters among heat flux density, operating pressure, and mass flow rate.

[0008] Optionally, the step of preprocessing the numerical simulation steady-state data includes: The steady-state data from the numerical simulation are extracted, and a data slice is taken at each preset interval in the cooling channel. The plane of each data slice is perpendicular to the fluid flow direction in the cooling channel. The data slices are calculated, with the outer wall temperature of the cooling channel as input and the physical and chemical fields of the chemical reaction heat fluid as output, to obtain the parameters used for training and generate a dataset.

[0009] Optionally, the preprocessed dataset includes: discrete temperature of the outer wall of the cooling channel, temperature field of supercritical hydrocarbon fuel, velocity field, composition field, turbulence characteristic field, and physical property parameter field.

[0010] Optionally, the multi-field coupled reconstruction network model includes a multilayer perceptron in the first layer and an adversarial generative neural network in the second layer; The first layer of the multilayer perceptron includes an input layer, a hidden layer, and an output layer; the second layer of the generative adversarial neural network includes a generator and a discriminator.

[0011] Optionally, the input of the multilayer perceptron in the first layer is the discrete temperature of the outer wall of the cooling channel, and the output is a temperature field and a physical property parameter field; the input of the generator is the temperature field and physical property parameter field output by the multilayer perceptron in the first layer, and the output is a sample with the same dimension as the real data.

[0012] Optionally, the steps of training and optimizing the multi-field coupled reconstruction network model using the preprocessed dataset include: The preprocessed dataset was used to train and validate the multi-field coupled reconstruction network model multiple times. Based on the training and validation loss values, the number of hidden layers, the number of neurons in the fully connected layers, the activation function, the number of convolution and deconvolution layers, the convolution kernel size, the convolution stride, the learning rate, and the batch size in the network structure were continuously adjusted to obtain and save the optimal network model and hyperparameter settings.

[0013] Secondly, the present invention also provides a deep learning-based chemical reaction thermofluid multi-field coupling reconstruction device, the device being implemented based on the deep learning-based chemical reaction thermofluid multi-field coupling reconstruction method as described in any one or more of the above schemes, the device comprising: a simulation module, a preprocessing module, a training module, and a reconstruction module.

[0014] The simulation module is used to construct a three-dimensional numerical simulation model of the cooling channel and obtain steady-state numerical simulation data under various preset working conditions based on the three-dimensional numerical simulation model. The preprocessing module is used to preprocess the steady-state data of numerical simulation to obtain a preprocessed dataset; The training module is used to construct an initial multi-field coupled reconstruction network model. The preprocessed dataset is used to train and optimize the initial multi-field coupled reconstruction network model to obtain the trained multi-field coupled reconstruction network model. The reconstruction module is used to reconstruct the temperature field, physical property parameter field, velocity field, component field, and turbulence characteristic field of the chemical reaction thermofluid based on the trained multi-field coupled reconstruction network model.

[0015] Thirdly, the present invention provides an electronic device, including a processor and a memory, wherein the memory stores a computer program, the processor executes the computer program stored in the memory, and the computer program, when executed by the processor, implements the deep learning-based chemical reaction thermofluid multi-field coupling reconstruction method described in the first aspect.

[0016] Fourthly, the present invention also provides a computer-readable storage medium having a computer program stored thereon, wherein the computer program, when executed by a processor, implements the deep learning-based chemical reaction thermofluid multi-field coupling reconstruction method described in the first aspect.

[0017] Compared with the prior art, the advantages of the present invention are: This invention provides a deep learning-based method, apparatus, electronic device, and computer-readable storage medium for multi-field coupling reconstruction of chemical reaction thermofluids. By constructing a mapping function between discrete temperature data at the outer wall of a cooling channel and the internal flow field, it reconstructs the multi-physics and chemical fields (including temperature field, physical properties, parameter field, velocity field, thermal decomposition product component concentration field, and turbulence characteristic field) of the chemical reaction thermofluid. This method solves the problem of difficult flow field reconstruction caused by the complex evolution of the flow field structure due to drastic changes in the physical properties and composition of the chemical reaction thermofluid, and directly extends deep learning work on chemical reaction thermofluids to the reconstruction of sliced ​​flow fields. This method establishes a mapping relationship between the discrete temperature vector at the outer wall of the channel and the multi-dimensional flow field matrix information, enabling rapid and accurate reconstruction of the multi-physics and chemical fields.

[0018] This invention is applicable to the study of the flow and heat transfer characteristics of chemical reaction thermal fluids. Attached Figure Description

[0019] To more clearly illustrate the technical solutions in the embodiments of the present invention or the background art, the accompanying drawings used in the embodiments of the present invention or the background art will be described below.

[0020] Figure 1 A flowchart of a deep learning-based chemical reaction thermofluid multi-field coupling reconstruction method provided by an embodiment of the present invention is shown. Figure 2 The diagram illustrates a geometric model of the computational domain for cooling channels considering symmetric boundary conditions in the deep learning-based chemical reaction thermofluid multi-field coupling reconstruction method provided by an embodiment of the present invention. Figure 3 The diagram shows the structure of the multi-field coupling reconstruction network model in the deep learning-based chemical reaction thermofluid multi-field coupling reconstruction method provided by the embodiments of the present invention. Figure 4 A schematic diagram of a deep learning-based chemical reaction thermofluid multi-field coupling reconstruction device is shown in an embodiment of the present invention. Figure 5 The diagram shows a schematic of an electronic device for performing a deep learning-based chemical reaction thermofluid multi-field coupling reconstruction method, according to an embodiment of the present invention. Detailed Implementation

[0021] The technical solutions in the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only a part of the embodiments of this application, and not all of them. Based on the embodiments in this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0022] Implementation Method 1: In this embodiment, the chemical reaction thermal fluid studied is hydrocarbon fuel.

[0023] Since the pressure within the regenerative cooling channel of a scramjet engine is typically between 3.5 and 7.0 MPa, exceeding the critical pressure of hydrocarbon fuels (2.0 to 3.0 MPa), the hydrocarbon fuel rapidly heats up during the flow and heat exchange process within the channel, transitioning to a supercritical state. Simultaneously, as the temperature of the hydrocarbon fuel continues to rise during this flow and heat exchange process, complex endothermic thermal cracking reactions will occur. Therefore, the supercritical hydrocarbon fuel studied in this embodiment is a standard chemical reaction thermofluid.

[0024] The embodiments of the present invention will now be described with reference to the accompanying drawings.

[0025] S101: Construct a three-dimensional numerical simulation model of the cooling channel, and obtain steady-state numerical simulation data under various preset working conditions based on the three-dimensional numerical simulation model.

[0026] In this embodiment, the model used is referred to [reference needed]. Figure 2 As shown, the cooling channel has an outer diameter of 2×2 mm and an inner diameter of 1×1 mm. The constant heat flux heating section has a length L = 1000 mm, and the heat flux is applied only to the bottom surface of the cooling channel. Sections of length L are installed before and after the heating section. in =L out An adiabatic section of 150 mm is included to ensure sufficient fuel flow development and eliminate boundary effects at the mass inlet and pressure outlet. Wherein, L in L represents the length of the insulation section preceding the heating section. out This indicates the length of the insulation section following the heating section. In this embodiment, computational fluid dynamics (CFD) software is used to perform steady-state numerical calculations, thereby obtaining simulation steady-state data under various preset operating conditions.

[0027] Optionally, multiple preset operating conditions are combinations of different heat flux densities, operating pressures, and mass flow inlet conditions.

[0028] In this embodiment, computational fluid dynamics (CFD) software is used to perform steady-state numerical calculations, thereby obtaining simulation steady-state data under various preset operating conditions. These preset operating conditions are combinations of different heat flux densities, operating pressures, and mass flow rate inlet conditions.

[0029] S102: Preprocess the steady-state data from the numerical simulation to obtain a preprocessed dataset containing discrete temperatures of the outer wall of the cooling channel, temperature field of the supercritical hydrocarbon fuel, velocity field, composition field, turbulence characteristic field, and physical property parameter field.

[0030] After obtaining the steady-state numerical simulation data of the cooling channel, a series of preprocessing operations were performed on these raw data to ensure their accuracy and usability. Specifically, the preprocessing process included data cleaning, interpolation, and format conversion. The preprocessed dataset was obtained through these operations. This dataset covers key information such as the discrete temperature distribution on the outer wall of the cooling channel, the temperature field of the supercritical hydrocarbon fuel, and the velocity field. This data can realistically reflect the flow, heat transfer, chemical reactions, and property changes of the hydrocarbon fuel under different operating conditions within the cooling channel.

[0031] The component field, turbulence characteristic field, and physical property parameter field can be selected as the mass fraction field of the cracking product methane, the turbulent kinetic energy field, and the density field.

[0032] Optionally, the above-mentioned S102 "preprocessing the numerical simulation steady-state data to obtain a preprocessed dataset including the discrete temperature of the outer wall of the cooling channel, the temperature field of the supercritical hydrocarbon fuel, the velocity field, the composition field, the turbulence characteristic field and the physical property parameter field" may include the following steps A1-A2.

[0033] Step A1: Extract steady-state data from numerical simulations under different preset operating conditions. Take a data slice at each preset interval in the cooling channel. The plane of the data slice is perpendicular to the fluid flow direction in the cooling channel.

[0034] For example, a data slice is taken every 4mm (preset interval) in the cooling channel, and 251 data slices can be extracted for each set of preset working conditions.

[0035] Step A2: Calculate the data slices, taking the outer wall temperature of the cooling channel as input and the physical and chemical fields of the chemical reaction heat fluid as output, to obtain the parameters used for training and generate the dataset.

[0036] Discrete temperatures on the outer wall of the cooling channel are extracted and transformed into one-dimensional vectors. The flow field information of the grid nodes on the data slice is interpolated using spatial coordinates to obtain 100×100 characteristic rectangles to represent the temperature field, velocity field, mass fraction field of the cracking product methane, turbulent kinetic energy field, and density field.

[0037] In this implementation, the dataset is divided into a training set and a validation set in an 8:2 ratio. The training set is used to train the network model to determine parameters such as weights and biases in the model; the validation set is used to evaluate the model's reconstruction performance during training and to fine-tune the parameters.

[0038] S103: Build an initial multi-field coupled reconstruction network model, and use the dataset to train and optimize the initial multi-field coupled reconstruction network model to obtain a trained multi-field coupled reconstruction network model.

[0039] Furthermore, a multi-field coupled reconstruction neural network model can be built using the open-source software framework PyTorch. Based on the strength of the correlation between the discrete temperature information of the outer wall and the flow field, the network model is divided into two layers: the first layer is a multilayer perceptron (MLP) used to reconstruct the temperature field and the physical property parameter field; the second layer is a generative adversarial neural network (GAN) used to reconstruct the velocity field, component field, and turbulence characteristic field. The first-layer MLP uses the discrete temperature of the cooling channel outer wall as the network input parameter, while the second-layer GAN uses the output parameters (temperature field and density field) of the first-layer network as the network input parameter, forming a complete coupled reconstruction process.

[0040] Optionally, see Figure 3As shown, the multi-field coupled reconstruction network model for chemical reaction thermofluids includes a first-layer multilayer perceptron (MLP) and a second-layer generative adversarial neural network (GAN). The first-layer MLP consists of an input layer, a hidden layer, and an output layer. The nonlinear activation function of the hidden layer is Leaky ReLU to improve the network's expressive power. The mean squared error (MSE) loss function is selected. This module is used to establish a nonlinear mapping relationship between the discrete temperature of the cooling channel outer wall and the corresponding supercritical hydrocarbon fuel temperature and density fields.

[0041] The second layer of the Generative Adversarial Network (GAN) consists of two main parts: a generator (G) and a discriminator (D). The generator's input is the temperature field and physical property parameter field output from the first layer's multilayer perceptron, and its output is a sample with the same dimensions as the real data. The generator's task is to learn a mapping function to transform the network input into a realistic sample. The discriminator's input is a sample, and its output is a probability value. The value between 0 and 1 represents the probability that a sample comes from real data. Since a very accurate Wasserstein distance is required when training WGAN, the generator does not need to be trained in each iteration. Therefore, the discriminator is updated once every 5 generator updates. This module is used to establish a mapping relationship between the temperature field, physical property parameter field, and the corresponding supercritical hydrocarbon fuel velocity field, turbulence characteristic field, and composition field.

[0042] Using the dataset obtained in S102 above, the initial multi-field coupled reconstruction network model is trained and validated multiple times. Based on the training and validation loss values, the number of hidden layers, the number of neurons in fully connected layers, the activation function, the number of convolution and deconvolution layers, the convolution kernel size, the convolution stride, the learning rate, and the batch size in the network structure are continuously adjusted to obtain and save the optimal network model and hyperparameter settings, and finally the trained multilayer perceptron and adversarial generative neural network models are obtained.

[0043] S104: Based on the trained multi-field coupled reconstruction network model, the temperature field, physical property parameter field, velocity field, component field, and turbulence characteristic field of the chemical reaction thermofluid are reconstructed.

[0044] The deep learning-based multi-field coupling reconstruction method for chemical reaction thermofluids provided in this embodiment reconstructs multiple sets of physical and chemical fields of the chemical reaction thermofluid by constructing a mapping function between discrete point temperature data on the outer wall of the cooling channel and the internal flow field. This method solves the problem of difficult flow field reconstruction caused by drastic changes in the physical properties of the chemical reaction thermofluid and the complex evolution of the flow field structure due to the chemical reaction, and directly extends deep learning work for simple supercritical fluids to the reconstruction of sliced ​​flow fields. This method establishes a mapping relationship between the discrete point temperature vector on the outer wall of the channel and the multidimensional flow field matrix information, enabling rapid and accurate reconstruction of several physical and chemical fields, avoiding the time-consuming and expensive spatial discretization and iterative solution process in traditional numerical calculations.

[0045] The foregoing described in detail the deep learning-based chemical reaction thermofluid multi-field coupling reconstruction method provided by the embodiments of the present invention. This method can also be implemented by a corresponding device. The following describes in detail the deep learning-based chemical reaction thermofluid multi-field coupling reconstruction device provided by the embodiments of the present invention.

[0046] Figure 4 A schematic diagram of a deep learning-based chemical reaction thermofluid multi-field coupling reconstruction device is shown in the embodiment of the present invention. Figure 4 As shown, the deep learning-based chemical reaction thermofluid multi-field coupling reconstruction device includes a processor. The processor includes: a simulation module 41, a preprocessing module 42, a training module 43, and a reconstruction module 44.

[0047] The simulation module 41 is used to construct a three-dimensional numerical simulation model of the cooling channel and obtain steady-state numerical simulation data under various preset working conditions based on the three-dimensional numerical simulation model.

[0048] The preprocessing module 42 is used to preprocess the steady-state data of numerical simulation to obtain a preprocessed dataset containing discrete temperatures of the outer wall of the cooling channel, temperature field of supercritical hydrocarbon fuel, velocity field, composition field, turbulence characteristic field and physical property parameter field.

[0049] Training module 43 is used to build an initial multi-field coupled reconstruction network model. The initial multi-field coupled reconstruction network model is trained and optimized using the dataset to obtain a trained multi-field coupled reconstruction network model.

[0050] The reconstruction module 44 is used to reconstruct the temperature field, physical property parameter field, velocity field, component field, and turbulence characteristic field of the chemical reaction thermofluid based on the trained multi-field coupled reconstruction network model.

[0051] Optionally, the multiple preset operating conditions are combinations of different heat flux densities, operating pressures, and mass flow inlet conditions.

[0052] Optionally, the preprocessing module is used for: Numerical simulation steady-state data under different preset working conditions are extracted, and a data slice is taken at each preset interval in the cooling channel. The plane where the data slice is located is perpendicular to the fluid flow direction in the cooling channel. The data slices are calculated, with the outer wall temperature of the cooling channel as input and the multiphysics field and chemical field of the chemical reaction heat fluid as output, to obtain the parameters used for training and generate a dataset.

[0053] Optionally, the multi-field coupled reconstruction network model includes a multilayer perceptron in the first layer and an adversarial generative neural network in the second layer; The first layer of the multilayer perceptron includes an input layer, a hidden layer, and an output layer; the second layer of the generative adversarial neural network includes a generator and a discriminator.

[0054] Optionally, the generator's input is the temperature field and physical property parameter field output from the first layer of the multilayer perceptron, and the output is a sample with the same dimensions as the real data. The generator's task is to learn a mapping function to map the network input into a realistic sample.

[0055] The apparatus provided in this invention reconstructs the temperature field, velocity field, composition field, turbulence characteristic field, and physical property parameter field of a chemical reaction thermofluid by constructing a mapping function between discrete point temperature data on the outer wall of the cooling channel and the internal flow field. This apparatus solves the problem of difficult flow field reconstruction caused by the complex evolution of the flow field structure due to the drastic changes in the physical properties of the chemical reaction thermofluid and the significant impact of chemical mass transfer on the flow heat transfer process. Furthermore, it directly extends deep learning work on chemical reaction thermofluids to the reconstruction of two-dimensional flow fields. The apparatus establishes a mapping relationship between the discrete point temperature vector on the outer wall of the channel and the multidimensional flow field matrix information, enabling rapid and accurate reconstruction of several physical and chemical fields.

[0056] It should be noted that the deep learning-based chemical reaction thermofluid multi-field coupling reconstruction device provided in the above embodiments is only illustrated by the division of the above functional modules. In practical applications, the above functions can be assigned to different functional modules as needed, that is, the internal structure of the device can be divided into different functional modules to complete all or part of the functions described above. In addition, the deep learning-based chemical reaction thermofluid multi-field coupling reconstruction device and the chemical reaction thermofluid multi-field coupling reconstruction method provided in the above embodiments belong to the same concept. The specific implementation process is detailed in the method implementation, and will not be repeated here.

[0057] According to one aspect of this application, embodiments of the present invention also provide a computer program product comprising a computer program containing program code for performing the methods shown in the flowchart. In such an embodiment, the computer program can be downloaded and installed from a network via a communication component. When the computer program is executed by a processor, it performs the deep learning-based chemical reaction thermofluid multi-field coupling reconstruction method provided in embodiments of this application.

[0058] In addition, the present invention also provides an electronic device, including a bus, a transceiver, a memory, a processor, and a computer program stored in the memory and executable on the processor. The transceiver, the memory, and the processor are connected via the bus. When the computer program is executed by the processor, it implements the various processes of the above-described deep learning-based chemical reaction thermofluid multi-field coupling reconstruction method and achieves the same technical effect. To avoid repetition, it will not be described again here.

[0059] For details, see Figure 5 As shown, the electronic device includes a bus 1110, a processor 1120, a transceiver 1130, a bus interface 1140, a memory 1150, and a user interface 1160.

[0060] In an embodiment of the present invention, the electronic device further includes: a computer program stored in a memory 1150 and executable on a processor 1120, wherein the computer program, when executed by the processor 1120, implements the various processes of the above-described embodiment of the deep learning-based chemical reaction thermofluid multi-field coupling reconstruction method.

[0061] Transceiver 1130 is used to receive and send data under the control of processor 1120.

[0062] In this embodiment of the invention, a bus architecture (represented by bus 1110) is used. Bus 1110 may include any number of interconnected buses and bridges. Bus 1110 connects various circuits, including one or more processors represented by processor 1120 and memory represented by memory 1150.

[0063] Bus 1110 represents one or more of several types of bus architectures, including memory buses and memory controllers, peripheral buses, Accelerated Graphical Ports (AGP), processors, or local buses using any bus architecture from various bus architectures. As an example and not a limitation, such architectures include: Industry Standard Architecture (ISA) buses, MicroChannel Architecture (MCA) buses, Enhanced ISA (EISA) buses, Video Electronics Standards Association (VESA) buses, and Peripheral Component Interconnect (PCI) buses.

[0064] The processor 1120 can be an integrated circuit chip with signal processing capabilities. In implementation, each step of the above-described method can be completed through integrated logic circuits in the processor hardware or instructions in software form. The processors described above include: general-purpose processors, central processing units (CPUs), network processors (NPs), digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), complex programmable logic devices (CPLDs), programmable logic arrays (PLAs), microcontroller units (MCUs) or other programmable logic devices, discrete gates, transistor logic devices, and discrete hardware components. They can implement or execute the methods, steps, and logic block diagrams disclosed in the embodiments of this invention. For example, the processor can be a single-core processor or a multi-core processor, and the processor can be integrated on a single chip or located on multiple different chips.

[0065] Processor 1120 can be a microprocessor or any conventional processor. The method steps disclosed in the embodiments of the present invention can be directly executed by a hardware decoding processor, or executed by a combination of hardware and software modules in the decoding processor. The software modules can reside in readable storage media known in the art, such as Random Access Memory (RAM), Flash Memory, Read-Only Memory (ROM), Programmable Read-Only Memory (PROM), Erasable Programmable Read-Only Memory (EPROM), registers, etc. The readable storage medium is located in the memory, and the processor reads the information in the memory and, in conjunction with its hardware, completes the steps of the above method.

[0066] Bus 1110 can also connect various other circuits, such as peripheral devices, voltage regulators, or power management circuits. Bus interface 1140 provides an interface between bus 1110 and transceiver 1130, all of which are well known in the art. Therefore, embodiments of the present invention will not be described further.

[0067] Transceiver 1130 can be a single element or multiple elements, such as multiple receivers and transmitters, providing a unit for communicating with various other devices over a transmission medium. For example, transceiver 1130 receives external data from other devices, and transceiver 1130 is used to send data processed by processor 1120 to other devices. Depending on the nature of the computer system, a user interface 1160 may also be provided, such as a touchscreen, physical keyboard, monitor, mouse, speaker, microphone, trackball, joystick, or stylus.

[0068] It should be understood that, in embodiments of the present invention, memory 1150 may further include memory remotely configured relative to processor 1120, and such remotely configured memory may be connected to a server via a network. One or more portions of the aforementioned network may be an ad hoc network, intranet, extranet, virtual private network (VPN), local area network (LAN), wireless local area network (WLAN), wide area network (WAN), wireless wide area network (WWAN), metropolitan area network (MAN), Internet, public switched telephone network (PSTN), ordinary old-style telephone service (POTS), cellular telephone network, wireless network, Wi-Fi network, and combinations of two or more of the aforementioned networks. For example, cellular telephone networks and wireless networks can be Global System for Mobile Communications (GSM), Code Division Multiple Access (CDMA), WiMAX, General Packet Radio Service (GPRS), Wideband Code Division Multiple Access (WCDMA), Long Term Evolution (LTE), LTE Frequency Division Duplex (FDD), LTE Time Division Duplex (TDD), Advanced Long Term Evolution (LTE-A), Universal Mobile Telecommunications System (UMTS), Enhanced Mobile Broadband (eMBB), Massive Machine Type Communication (mMTC), Ultra Reliable Low Latency Communications (uRLLC), etc.

[0069] It should be understood that the memory 1150 in the embodiments of the present invention may be volatile memory or non-volatile memory, or may include both volatile memory and non-volatile memory. Non-volatile memory includes: read-only memory (ROM), programmable read-only memory (PROM), erasable programmable read-only memory (EPROM), electrically erasable programmable read-only memory (EEPROM), or flash memory.

[0070] Volatile memory includes random access memory (RAM), which serves as an external cache. By way of example, but not limitation, many forms of RAM are available, such as static random access memory (SRAM), dynamic random access memory (DRAM), synchronous dynamic random access memory (SDRAM), double data rate synchronous dynamic random access memory (DDRSDRAM), enhanced synchronous dynamic random access memory (ESDRAM), synchronous linked dynamic random access memory (SLDRAM), and direct memory bus RAM (DRRAM). The memory 1150 of the electronic device described in this embodiment includes, but is not limited to, the above-described and any other suitable types of memory.

[0071] In this embodiment of the invention, the memory 1150 stores the following elements of the operating system 1141 and the application program 1142: executable modules, data structures, or subsets thereof, or extended sets thereof.

[0072] Specifically, the operating system 1141 includes various system programs, such as the framework layer, core library layer, and driver layer, used to implement various basic business functions and handle hardware-based tasks. The application program 1142 includes various applications, such as a media player and a browser, used to implement various application functions. Programs implementing the methods of this invention can be included in the application program 1142. The application program 1142 includes applets, objects, components, logic, data structures, and other computer system executable instructions that perform specific tasks or implement specific abstract data types.

[0073] Furthermore, this invention also provides a computer-readable storage medium storing a computer program thereon. When the computer program is executed by a processor, it implements the various processes of the above-described deep learning-based chemical reaction thermofluid multi-field coupling reconstruction method and achieves the same technical effect. To avoid repetition, it will not be described again here.

[0074] Computer-readable storage media include: permanent and non-permanent, removable and non-removable media, which are tangible devices capable of retaining and storing instructions for use by an instruction execution device. Computer-readable storage media include: electronic storage devices, magnetic storage devices, optical storage devices, electromagnetic storage devices, semiconductor storage devices, and any suitable combination thereof. Computer-readable storage media include: 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), non-volatile random access memory (NVRAM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technologies, optical disc read-only memory (CD-ROM), digital versatile optical disc (DVD) or other optical storage, magnetic tape storage, magnetic disk storage or other magnetic storage devices, memory sticks, mechanical encoding devices (such as punched cards or raised structures in grooves on which instructions are recorded), or any other non-transfer medium that can be used to store information accessible by a computing device. As defined in the embodiments of the present invention, a computer-readable storage medium does not include the temporary signal itself, such as radio waves or other freely propagating electromagnetic waves, electromagnetic waves propagating through waveguides or other transmission media (e.g., light pulses passing through optical fiber cables), or electrical signals transmitted through wires.

[0075] In the several embodiments provided in this application, it should be understood that the disclosed apparatus, electronic devices, and methods can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative. For instance, the division of modules or units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. In addition, the mutual coupling or direct coupling or communication connection shown or discussed may be indirect coupling or communication connection through some interfaces, devices, or units, or it may be an electrical, mechanical, or other form of connection.

[0076] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to solve the problems addressed by the embodiments of the present invention, depending on actual needs.

[0077] Furthermore, the functional units in the various embodiments of the present invention can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit.

[0078] If the integrated unit is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the embodiments of the present invention, in essence, or the part that contributes to the prior art, or all or part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause an electronic device (including: a personal computer, a server, a data center, or other network device) to execute all or part of the steps of the methods described in the various embodiments of the present invention. The aforementioned storage medium includes various media listed above that can store program code.

[0079] In the description of the embodiments of the present invention, those skilled in the art should understand that the embodiments of the present invention can be implemented as methods, apparatuses, electronic devices, and computer-readable storage media. Therefore, the embodiments of the present invention can be specifically implemented in the following forms: entirely hardware, entirely software (including firmware, resident software, microcode, etc.), or a combination of hardware and software. Furthermore, in some embodiments, the embodiments of the present invention can also be implemented as a computer program product contained in one or more computer-readable storage media, the computer-readable storage media containing computer program code.

[0080] The aforementioned computer-readable storage medium may be any combination of one or more computer-readable storage media. Computer-readable storage media include: electrical, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatuses, or devices, or any combination thereof. More specific examples of computer-readable storage media include: portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM), flash memory, optical fiber, optical disc read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any combination thereof. In embodiments of the present invention, the computer-readable storage medium may be any tangible medium containing or storing a program that can be used by or in conjunction with an instruction execution system, apparatus, or device.

[0081] The computer program code contained in the aforementioned computer-readable storage medium may be transmitted using any suitable medium, including wireless, wire, optical fiber, radio frequency (RF), or any suitable combination thereof.

[0082] Computer program code for performing the operations of embodiments of the present invention can be written in assembly instructions, instruction set architecture (ISA) instructions, machine instructions, machine-dependent instructions, microcode, firmware instructions, status setting data, integrated circuit configuration data, or in one or more programming languages ​​or combinations thereof. The programming languages ​​include object-oriented programming languages ​​such as Java, Smalltalk, and C++, as well as conventional procedural programming languages ​​such as C or similar languages. The computer program code can be executed entirely on the user's computer, partially on the user's computer, as a standalone software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In cases involving remote computers, the remote computer can be connected to the user's computer or an external computer via any type of network, including a local area network (LAN) or a wide area network (WAN).

[0083] The embodiments of the present invention describe the provided methods, apparatus, and electronic devices through flowcharts and / or block diagrams.

[0084] It should be understood that each block of a flowchart and / or block diagram, as well as combinations of blocks in a flowchart and / or block diagram, can be implemented by computer-readable program instructions. These computer-readable program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing apparatus to produce a machine that, when executed by a computer or other programmable data processing apparatus, creates means for implementing the functions / operations specified in the blocks of the flowchart and / or block diagram.

[0085] These computer-readable program instructions may also be stored in a computer-readable storage medium that enables a computer or other programmable data processing device to function in a particular manner. In this way, the instructions stored in the computer-readable storage medium produce an instruction apparatus product that includes the functions / operations specified in the blocks of a flowchart and / or block diagram.

[0086] Computer-readable program instructions may also be loaded onto a computer, other programmable data processing apparatus or other device to cause a series of operational steps to be performed on the computer, other programmable data processing apparatus or other device to produce a computer-implemented process, such that the instructions that execute on the computer or other programmable data processing apparatus provide a process for implementing the functions / operations specified in the blocks of the flowchart and / or block diagram.

[0087] The above description is merely a specific embodiment of the present invention, but the protection scope of the present invention is not limited thereto. Any variations or substitutions that can be easily conceived by those skilled in the art within the technical scope disclosed in the embodiments of the present invention should be included within the protection scope of the present invention. Therefore, the protection scope of the embodiments of the present invention should be determined by the scope of the claims.

Claims

1. A deep learning based method for reconstructing multi-field coupling of chemical reaction thermal fluid, characterized in that, The method comprises the following steps: constructing a three-dimensional numerical simulation model of the cooling channel, and obtaining numerical simulation steady-state data under multiple preset working conditions based on the three-dimensional numerical simulation model; preprocessing the numerical simulation steady-state data to obtain a preprocessed data set; constructing a multi-field coupling reconstruction network model, and training and optimizing the multi-field coupling reconstruction network model using the preprocessed data set to obtain a trained multi-field coupling reconstruction network model; reconstructing the temperature field, the property parameter field, the velocity field, the component field, and the turbulent flow characteristic field of the chemical reaction hot fluid based on the trained multi-field coupling reconstruction network model.

2. The deep learning-based multi-field coupling reconstruction method for chemical reaction thermal fluid according to claim 1, wherein, The multiple preset working conditions are combinations of different values of at least two boundary condition parameters of heat flux density, operating pressure, and mass flow rate.

3. The deep learning-based multi-field coupling reconstruction method for chemical reaction thermal fluid according to claim 1, wherein, The preprocessing of the numerical simulation steady-state data comprises the following steps: extracting the numerical simulation steady-state data, and taking a data slice every preset interval in the cooling channel, wherein the plane of each data slice is perpendicular to the fluid flow direction in the cooling channel; calculating the data slice, taking the outer wall temperature of the cooling channel as input, and taking the physical field and the chemical field of the chemical reaction hot fluid as output, to obtain a parameter generation data set for training.

4. The deep learning-based multi-field coupling reconstruction method for chemical reaction thermal fluid according to claim 1, wherein, The preprocessed data set comprises the cooling channel outer wall discrete temperature, the supercritical hydrocarbon fuel temperature field, the velocity field, the component field, the turbulent flow characteristic field, and the property parameter field.

5. The deep learning based multi-field coupled reconstruction method of chemical reaction thermal fluid according to claim 1, wherein, The multi-field coupling reconstruction network model comprises a first layer of a multi-layer perceptron and a second layer of a generative adversarial network. The first layer of the multi-layer perceptron comprises an input layer, a hidden layer, and an output layer; and the second layer of the generative adversarial network comprises a generator and a discriminator.

6. The deep learning-based multi-field coupled reconstruction method of chemical reaction thermal fluid according to claim 5, characterized in that, The input of the first layer of the multi-layer perceptron is the cooling channel outer wall discrete temperature, and the output is the temperature field and the property parameter field; the input of the generator is the temperature field and the property parameter field output by the first layer of the multi-layer perceptron, and the output is a sample with the same dimension as the real data.

7. The deep learning based multi-field coupled reconstruction method of chemical reaction thermal fluid according to claim 1, characterized in that, The training and optimization of the multi-field coupling reconstruction network model using the preprocessed data set comprises the following steps: training and verifying the multi-field coupling reconstruction network model multiple times using the preprocessed data set, and continuously adjusting the number of hidden layers, the number of fully connected layer neurons, the activation function, the number of convolution and deconvolution layers, the convolution kernel size, the convolution step, the learning rate, and the batch size in the network structure to obtain and save the optimal network model and the hyperparameter setting.

8. A deep learning based chemical reaction thermal fluid multi-field coupling reconstruction device, characterized in that, The device is implemented based on the deep learning-based chemical reaction hot fluid multi-field coupling reconstruction method according to any one of claims 1-7, and comprises a simulation module, a preprocessing module, a training module, and a reconstruction module. The simulation module is configured to construct a three-dimensional numerical simulation model of the cooling channel, and obtain numerical simulation steady-state data under multiple preset working conditions based on the three-dimensional numerical simulation model. The preprocessing module is configured to preprocess the numerical simulation steady-state data to obtain a preprocessed data set. The training module is configured to construct an initial multi-field coupling reconstruction network model, and train and optimize the initial multi-field coupling reconstruction network model using the preprocessed data set to obtain a trained multi-field coupling reconstruction network model. The reconstruction module is configured to reconstruct the temperature field, the physical property parameter field, the velocity field, the component field and the turbulent flow characteristic field of the chemical reaction thermal fluid based on the trained multi-field coupling reconstruction network model.

9. An electronic device comprising a processor and a memory, the memory storing a computer program, characterized in that, The processor executes the computer program stored in the memory to implement the steps in the deep learning-based multi-field coupling reconstruction method of chemical reaction thermal fluid according to any one of claims 1 to 7.

10. A computer-readable storage medium having stored thereon a computer program, characterized in that, The computer program, when executed by the processor, implements the steps in the deep learning-based multi-field coupling reconstruction method of chemical reaction thermal fluid according to any one of claims 1 to 7.

Images