Computational methods and systems for non-fluid phase change molten salt heat transfer

Abstract

This invention provides a calculation method and system for non-fluid phase change molten salt heat transfer. An adaptive thermodynamic model is constructed using a Bayesian optimization algorithm. Based on this model, a description of the thermodynamic characteristics of the molten salt system is obtained. Multi-scale modeling, discrete element method, finite volume method, and implicit time integration scheme are applied to analyze the thermodynamic characteristic description, generating a target description of the heat transfer path under non-fluid conditions. Based on this target description, surrogate modeling and deep neural networks are used to determine the pattern recognition results. Based on these results, the optimal heat transfer performance configuration is determined. Based on real-time molten salt temperature response data and the optimal heat transfer performance configuration, an evolutionary algorithm and a cooperative competition mechanism within a game theory framework are applied to generate a target operation strategy to achieve the calculation of non-fluid phase change molten salt heat transfer. This invention improves the accuracy, efficiency, and adaptability of molten salt heat transfer calculation, meeting the needs of efficient energy storage and conversion.

Description

Technical Field

[0001] The present invention relates to the field of computer simulation technology, and in particular to a calculation method and system for non-fluid phase change molten salt heat transfer. Background Technology

[0002] With the increasing demand for efficient energy storage and conversion in renewable energy and industrial processes, non-fluid phase change molten salt heat transfer technology has shown great potential in multiple fields. Particularly in applications such as solar thermal power generation, industrial waste heat recovery, and power peak regulation, molten salt, as a highly efficient heat storage medium, can store large amounts of thermal energy under high-temperature conditions and release it for power generation or heating when needed. However, these applications require precise heat transfer calculation methods to ensure the efficient operation and long-term stability of the system.

[0003] Currently, computational methods for molten salt heat transfer mainly include those based on empirical formulas and traditional numerical simulations. Existing empirical formula-based methods rely on laboratory test data and engineering experience, and cannot accurately describe the dynamic behavior of molten salt under different temperature conditions. In addition, existing methods generally lack computational accuracy, and their computational efficiency is low, with excessively long calculation times, making them difficult to adapt to the needs of real-time monitoring and rapid adjustment. These methods are usually based on fixed parameter sets and assumptions, lacking adaptability and flexibility. Summary of the Invention

[0004] This invention provides a calculation method and system for non-fluid phase change molten salt heat transfer, which solves the problems of insufficient calculation accuracy, low efficiency, difficulty in adapting to the needs of real-time monitoring and rapid adjustment, and lack of adaptability and flexibility in the prior art.

[0005] In a first aspect, embodiments of the present invention provide a method for calculating non-fluid phase change molten salt heat transfer, comprising:

[0006] A target state equation is selected using a Bayesian optimization algorithm. Based on the target state equation, the composition of the molten salt, and the temperature conditions, an adaptive thermodynamic model is constructed. Based on the adaptive thermodynamic model, the set of physical property parameters, latent heat change, and thermodynamic behavior of the molten salt at different temperatures are determined to obtain a description of the thermodynamic characteristics of the molten salt system.

[0007] Based on the thermodynamic property description, a multi-scale modeling method is applied to extract spatial distribution features. Based on these features, the discrete element method is used to generate a kinetic behavior description at the molten salt particle level. Simultaneously, the finite volume method is used to handle the heat transfer problem to determine the temperature field distribution. Combining phase field theory and the thermodynamic property description, an implicit time integration scheme is used to process the temperature field evolution inside the molten salt and at the heat exchange interface between the molten salt and the outside world, obtaining the temperature field evolution result. Based on the spatial distribution features, the kinetic behavior description, the temperature field distribution, and the temperature field evolution result, a target description of the heat transfer path in a non-fluid state is generated.

[0008] Based on the target description, the influence of each phase change influencing factor is evaluated using surrogate model technology to obtain phase change influence evaluation results. Historical operating data is analyzed using deep neural networks to obtain historical data analysis results. Combining the historical data analysis results and the phase change influence evaluation results, the pattern recognition results are determined. Based on the pattern recognition results, the operating parameter configuration of the molten salt system is optimized to determine the optimal heat exchange performance configuration.

[0009] Based on real-time molten salt temperature response data and the optimal heat transfer performance configuration, an evolutionary algorithm is applied to determine the target operating parameter set. A topology is constructed based on the target operating parameter set. Based on the topology and the target operating parameter set, a cooperative competition mechanism in the game theory framework is used to generate a target operating strategy. The target operating strategy is used to guide the operation of the molten salt system to perform non-fluid phase change molten salt heat transfer calculations.

[0010] Optionally, based on the thermodynamic property description, a multi-scale modeling method is applied to extract spatial distribution features. Based on these spatial distribution features, the discrete element method is used to generate a kinetic behavior description at the molten salt particle level. Simultaneously, the finite volume method is used to handle the heat transfer problem to determine the temperature field distribution. Combining phase field theory and the thermodynamic property description, an implicit time integration scheme is used to process the temperature field evolution inside the molten salt and at the heat exchange interface between the molten salt and the outside environment, obtaining the temperature field evolution results, including:

[0011] Based on the thermodynamic properties described above, microscopic molecular dynamics, and macroscopic continuum mechanics, a multi-scale modeling method is applied to simulate and extract the spatial distribution characteristics of the molten salt system at different scales.

[0012] The material properties and contact mechanical behavior of molten salt particles are defined. Based on the material properties, contact mechanical behavior and thermodynamic characteristics, the discrete element method is applied to simulate the interaction between molten salt particles and the influence of the interaction between molten salt particles on the molten salt system. Based on the interaction between molten salt particles and the influence of the interaction between molten salt particles on the molten salt system, a dynamic behavior description at the molten salt particle level is generated.

[0013] Based on the spatial distribution characteristics, an optimized mesh is generated using adaptive mesh refinement technology and topology optimization algorithm, and boundary conditions are set. Based on the optimized mesh and the boundary conditions, the heat transfer problem is handled using the finite volume method to obtain simulation results. Based on the simulation results, the temperature field distribution in the molten salt system is finally determined. A graph neural network is introduced in the process of handling the heat transfer problem to optimize the simulation results. The boundary conditions include mesh boundary conditions and physical boundary conditions.

[0014] Combining phase field theory and the aforementioned thermodynamic characteristics, the temperature field evolution inside the molten salt and at the heat exchange interface between the molten salt and the outside world is processed by an implicit time integration scheme to obtain the temperature field evolution results. In the process of processing by the implicit time integration scheme, a nonlinear dynamic equation solver and an adaptive step size control mechanism are introduced to obtain the temperature field variation law with time.

[0015] Optionally, based on the spatial distribution characteristics, an optimized mesh is generated using adaptive mesh refinement technology and topology optimization algorithm, and boundary conditions are set. Based on the optimized mesh and the boundary conditions, the heat transfer problem is handled using the finite volume method to obtain simulation results. Based on the simulation results, the temperature field distribution within the molten salt system is finally determined. A graph neural network is introduced during the handling of the heat transfer problem to optimize the simulation results, including:

[0016] Based on the spatial distribution characteristics, the geometry and physical properties of the molten salt system are dynamically adjusted using adaptive mesh refinement technology to generate an initial mesh. A topology optimization algorithm is then introduced to optimize the shape and distribution of the initial mesh to generate an optimized mesh. Boundary conditions are then set based on the optimized mesh.

[0017] Based on the optimized mesh and the boundary conditions, the heat transfer problem is handled using the finite volume method to obtain simulation results, which include the temperature field distribution to be optimized.

[0018] Based on the optimized mesh, a graph neural network is constructed. Based on the graph neural network, the connection patterns between nodes in the optimized mesh are analyzed to identify the heat transfer paths in the molten salt system and the interactions between the heat transfer paths. Based on the heat transfer paths and the interactions between the heat transfer paths, a graph neural network model is generated.

[0019] Based on the graph neural network model, the heat transfer path and its heat transfer efficiency are predicted and optimized to obtain the heat transfer results. Based on the heat transfer results, the temperature field distribution to be optimized in the simulation results is optimized, and finally the temperature field distribution in the molten salt system is determined.

[0020] Optionally, based on the target description, a surrogate model technique is used to evaluate the impact of each phase change influencing factor to obtain a phase change impact assessment result. A deep neural network is used to analyze historical operating data to obtain historical data analysis results. Combining the historical data analysis results and the phase change impact assessment results, a pattern recognition result is determined. Based on the pattern recognition result, the operating parameter configuration of the molten salt system is optimized to determine the optimal heat exchange performance configuration, including:

[0021] A target surrogate model is selected using surrogate model technology. The global sensitivity analysis method in the target surrogate model is used to evaluate the impact of each phase change influencing factor on the overall heat exchange efficiency, and the phase change factor impact results are obtained. Based on the phase change factor impact results, the local sensitivity analysis method in the target surrogate model is used to identify the key factors affecting the overall heat exchange efficiency under specific operating conditions. Based on the phase change factor impact results and the key factors, the phase change impact assessment results are obtained. The phase change influencing factors include temperature change, latent heat release, and latent heat absorption. The specific operating conditions include high-temperature operation conditions and low-temperature start-up conditions. The key factors include latent heat release rate and latent heat absorption rate.

[0022] A hybrid physical data-driven model is constructed based on physical laws and deep neural networks. Historical operational data is analyzed based on the hybrid physical data-driven model to obtain historical data analysis results.

[0023] Based on the historical data analysis results and the phase transition impact assessment results, advanced pattern recognition technology is applied to identify the interrelationships between the phase transition influencing factors. Based on the key factors and the interrelationships between the phase transition influencing factors, the pattern recognition results are determined.

[0024] Based on the pattern recognition results, the operating parameter configuration of the molten salt system is adjusted using a Bayesian optimization algorithm to generate a preliminary optimized operating parameter configuration. A genetic algorithm is then introduced to optimize the preliminary optimized operating parameter configuration to generate a final optimized operating parameter configuration. Based on the final optimized operating parameter configuration, the optimal heat exchange performance configuration is determined.

[0025] Optionally, a hybrid physics data-driven model is constructed based on physical laws and deep neural networks. Historical operational data is analyzed based on this hybrid physics data-driven model to obtain historical data analysis results, including:

[0026] A neural network structure is selected, and based on the neural network structure, physical laws, and deep learning technology, a hybrid physics data-driven model that combines prior physical knowledge is constructed. Based on the hybrid physics data-driven model, historical operation data is analyzed to obtain preliminary historical data analysis results.

[0027] Based on the preliminary historical data analysis results, a long short-term memory network is used to perform time series prediction on the historical operating data to obtain the time series prediction results.

[0028] The isolated forest algorithm is used to detect anomalies in the preliminary historical data analysis results, generating anomaly detection results. Based on the time series prediction results and the anomaly detection results, the preliminary historical data analysis results are optimized to obtain the historical data analysis results.

[0029] Optionally, a target equation of state is selected using a Bayesian optimization algorithm. Based on the target equation of state, the composition of the molten salt, and the temperature conditions, an adaptive thermodynamic model is constructed. Based on the adaptive thermodynamic model, the set of physical property parameters, latent heat changes, and thermodynamic behavior of the molten salt at different temperatures are determined to obtain a thermodynamic characteristic description of the molten salt system, including:

[0030] Based on Bayesian optimization algorithm and Gaussian process regression, the performance of different equations of state is evaluated to obtain performance evaluation results. Based on the performance evaluation results, a target equation of state is selected. Based on the target equation of state, molten salt composition and temperature conditions, an adaptive thermodynamic model is constructed by applying physical information neural network.

[0031] Based on the adaptive thermodynamic model, the physical properties of molten salt at different temperatures are calculated to obtain a set of physical property parameters, including density, specific heat capacity, and thermal conductivity.

[0032] Based on the set of physical property parameters, the latent heat release and latent heat absorption of molten salt during the phase change process are simulated to calculate the change in latent heat.

[0033] By combining the set of physical property parameters and the latent heat change, the thermodynamic behavior of the molten salt system is analyzed, and a description of the thermodynamic behavior of the molten salt system is generated, including the phase transition point, phase transition rate, and energy conversion efficiency.

[0034] Optionally, by combining the set of physical property parameters and the latent heat change, the thermodynamic behavior of the molten salt system is analyzed to generate a description of the thermodynamic behavior of the molten salt system. This thermodynamic behavior includes the phase transition point, phase transition rate, and energy conversion efficiency, including:

[0035] Based on the set of physical property parameters and the latent heat change, the phase transition temperature point of the molten salt from solid to liquid or from liquid to solid is identified.

[0036] Based on the phase transition temperature point, the temperature change rate, and the latent heat change, the rate of state transition of the molten salt during the phase transition process is calculated to obtain the phase transition rate.

[0037] Based on the phase transition rate, the energy transfer path and loss mechanism of the molten salt system are evaluated using coupled fluid dynamics simulation and finite element analysis, and the energy transfer evaluation results are obtained.

[0038] Based on the energy transfer assessment results and the phase change rate, the energy conversion efficiency of the molten salt system during the heat exchange process is evaluated. Combining the phase change rate, the energy transfer assessment results, and the energy conversion efficiency, a description of the thermodynamic behavior of the molten salt system is generated.

[0039] Secondly, embodiments of the present invention provide a calculation system for non-fluid phase change molten salt heat transfer, comprising:

[0040] The module is used to select the target equation of state using a Bayesian optimization algorithm, and to construct an adaptive thermodynamic model based on the target equation of state, the composition of the molten salt and the temperature conditions. Based on the adaptive thermodynamic model, the physical property parameter set, latent heat change and thermodynamic behavior of the molten salt at different temperatures are determined to obtain a thermodynamic characteristic description of the molten salt system.

[0041] The determination module is used to extract spatial distribution features based on the thermodynamic property description, apply multi-scale modeling methods, and generate a kinetic behavior description of molten salt particles using the discrete element method based on the spatial distribution features. At the same time, the finite volume method is used to handle the heat transfer problem to determine the temperature field distribution. Combining phase field theory and the thermodynamic property description, the temperature field evolution inside the molten salt and at the heat exchange interface between the molten salt and the outside world is processed through an implicit time integration scheme to obtain the temperature field evolution result. Based on the spatial distribution features, the kinetic behavior description, the temperature field distribution, and the temperature field evolution result, a target description of the heat transfer path in the non-fluid state is generated.

[0042] The optimization module is used to evaluate the impact of each phase change influencing factor based on the target description using surrogate model technology, obtain phase change impact evaluation results, analyze historical operating data using deep neural networks to obtain historical data analysis results, combine the historical data analysis results and the phase change impact evaluation results to determine pattern recognition results, and optimize the operating parameter configuration of the molten salt system based on the pattern recognition results to determine the optimal heat exchange performance configuration.

[0043] The generation module is used to determine the target operating parameter set based on real-time molten salt temperature response data and the optimal heat transfer performance configuration by applying an evolutionary algorithm, constructing a topology based on the target operating parameter set, generating a target operating strategy based on the topology and the target operating parameter set by adopting a cooperative competition mechanism under the game theory framework, and realizing the calculation of non-fluid phase change molten salt heat transfer based on the target operating strategy.

[0044] Thirdly, embodiments of the present invention provide a computing device, including a processor and a memory, wherein the memory stores a computer program, and the processor is configured to run the computer program to perform a calculation method for non-fluid phase change molten salt heat transfer as described in any of the first aspects.

[0045] Fourthly, embodiments of the present invention provide a computer storage medium storing computer program instructions thereon, wherein the computer program instructions, when executed by a processor, implement a calculation method for non-fluid phase change molten salt heat transfer as described in any one of the first aspects.

[0046] In this embodiment of the invention, a target state equation is selected using a Bayesian optimization algorithm. Based on the target state equation, the molten salt composition, and temperature conditions, an adaptive thermodynamic model is constructed. Based on the adaptive thermodynamic model, the set of physical property parameters, latent heat change, and thermodynamic behavior of the molten salt at different temperatures are determined to obtain a thermodynamic characteristic description of the molten salt system. Based on the thermodynamic characteristic description, a multi-scale modeling method is applied to extract spatial distribution features. Based on the spatial distribution features, the discrete element method is used to generate a particle-level dynamic behavior description of the molten salt. Simultaneously, the finite volume method is used to handle the heat transfer problem to determine the temperature field distribution. Combining phase field theory and the thermodynamic characteristic description, an implicit time integration scheme is used to process the temperature field evolution inside the molten salt and at the heat exchange interface between the molten salt and the outside environment to obtain the temperature field evolution result. Based on the spatial distribution features, the dynamic behavior description, the temperature field distribution, and the... The temperature field evolution results generate a target description of the heat transfer path under non-fluid conditions. Based on the target description, a surrogate model technique is used to evaluate the impact of each phase change influencing factor, obtaining a phase change impact assessment result. A deep neural network is used to analyze historical operating data, obtaining historical data analysis results. Combining the historical data analysis results and the phase change impact assessment results, a pattern recognition result is determined. Based on the pattern recognition result, the operating parameter configuration of the molten salt system is optimized to determine the optimal heat transfer performance configuration. Based on real-time molten salt temperature response data and the optimal heat transfer performance configuration, an evolutionary algorithm is applied to determine the target operating parameter set. A topology is constructed based on the target operating parameter set. Based on the topology and the target operating parameter set, a cooperative competition mechanism within a game theory framework is used to generate a target operating strategy. This target operating strategy guides the operation of the molten salt system for non-fluid phase change molten salt heat transfer calculations. The technical solution provided by this invention significantly improves the accuracy, efficiency, and adaptability of molten salt heat transfer calculations. These technical effects not only meet the needs of efficient energy storage and conversion in practical applications but also provide strong support for future energy management and industrial process optimization.The prediction accuracy was improved by combining adaptive thermodynamic modeling, multi-scale modeling, and the discrete element method. The adaptive thermodynamic model can dynamically adjust to adapt to changes in temperature conditions and molten salt composition, and the generated kinetic behavior description ensures a comprehensive capture of complex microstructures and macroscopic heat transfer processes. The use of the finite volume method, implicit time integration scheme, and surrogate model technology not only improved the accuracy of the simulation but also significantly reduced the computation time, facilitating real-time monitoring and rapid energy adjustment. Deep neural network analysis, evolutionary algorithms, and game theory frameworks ensured the long-term stability and optimal performance of the system, while also possessing high adaptability to cope with complex dynamic environmental changes. Through the above comprehensive methods, the target operation strategy was finally generated, realizing precise control and efficient management of the molten salt system, ensuring that the system maintains optimal heat transfer performance under various conditions, and ensuring that the calculation method can accurately and efficiently simulate the heat transfer process of the molten salt system, providing reliable technical support for practical applications. In particular, by providing detailed descriptions of heat transfer paths, the understanding of the internal heat transfer mechanism of the molten salt system is enhanced, providing data support for optimizing heat transfer paths; by using graph neural network models to predict and optimize heat transfer paths and heat transfer efficiency, a more uniform and accurate temperature field distribution is finally determined, which significantly improves the accuracy of the simulation and the heat exchange efficiency of the system.

[0047] These or other aspects of the invention will become more apparent from the following description of the embodiments. Attached Figure Description

[0048] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0049] Figure 1 A flowchart illustrating a calculation method for non-fluid phase change molten salt heat transfer provided in an embodiment of the present invention;

[0050] Figure 2 A schematic diagram of the structure of a computational system for non-fluid phase change molten salt heat transfer provided in an embodiment of the present invention;

[0051] Figure 3 This is a schematic diagram of the structure of a computing device provided in an embodiment of the present invention. Detailed Implementation

[0052] To enable those skilled in the art to better understand the present invention, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings.

[0053] In some of the processes described in the specification, claims, and accompanying drawings of this invention, multiple operations appearing in a specific order are included. However, it should be clearly understood that these operations may not be executed in the order they appear herein, or may be executed in parallel. The operation numbers, such as 101, 102, etc., are merely used to distinguish different operations and do not represent any execution order. Furthermore, these processes may include more or fewer operations, and these operations may be executed sequentially or in parallel. It should be noted that the descriptions such as "first," "second," etc., in this document are used to distinguish different messages, devices, modules, etc., and do not represent a sequential order, nor do they limit "first" and "second" to different types.

[0054] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0055] Figure 1 A flowchart of a calculation method for non-fluid phase change molten salt heat transfer is provided in this embodiment of the invention, as shown below. Figure 1 As shown, the method includes:

[0056] In the field of non-fluid phase change molten salt heat transfer, existing technologies still have many shortcomings in terms of accurate simulation, real-time optimization, and adaptive adjustment. To overcome these limitations and provide a novel solution for the efficient operation of complex molten salt systems, this invention provides a calculation method for non-fluid phase change molten salt heat transfer, such as... Figure 1 ,include:

[0057] Step 101: Select the target equation of state using the Bayesian optimization algorithm. Based on the target equation of state, the composition of the molten salt, and the temperature conditions, construct an adaptive thermodynamic model. Based on the adaptive thermodynamic model, determine the set of physical property parameters, latent heat change, and thermodynamic behavior of the molten salt at different temperatures to obtain a description of the thermodynamic characteristics of the molten salt system.

[0058] In this step, the target equation of state refers to the mathematical expression describing the thermodynamic behavior of molten salt, such as the ideal gas equation of state or the van der Waals equation, which can reflect the physical properties of molten salt at different temperatures and pressures.

[0059] Suppose a solar thermal power generation system in which molten salt serves as the heat storage medium. Using a Bayesian optimization algorithm, the most suitable equation of state (ESO) is selected as the target ESO. First, a set of candidate ESOs is defined, such as the ideal gas equation, the van der Waals equation, and the Bonley-Amsterdam equation. These equations are evaluated based on experimental or historical operating data, iteratively selecting the optimal parameter combination to ultimately determine the most suitable ESO describing the molten salt system. Based on the selected target ESO, molten salt composition, and temperature conditions (e.g., a mixture of sodium nitrate and potassium nitrate, and temperatures ranging from 300°C to 800°C), an adaptive thermodynamic model is constructed. This model can dynamically adjust its internal parameters to adapt to different operating conditions. Using the adaptive thermodynamic model, the set of physical properties, latent heat changes, and thermodynamic behavior of the molten salt at different temperatures are calculated. Physical properties include density, specific heat capacity, and thermal conductivity; latent heat changes include latent heat of fusion; and thermodynamic behavior includes phase transition points. For example, the model can predict that the density of the molten salt at 400°C is 1.7 g / cm³. 3 The specific heat capacity is 1.2 J / g·K, and the latent heat of fusion is 200 J / g. Based on the above results, the thermodynamic characteristics of the molten salt system are determined.

[0060] Step 102: Based on the thermodynamic property description, a multi-scale modeling method is applied to extract spatial distribution features. Based on the spatial distribution features, the discrete element method is used to generate a kinetic behavior description of molten salt particles. At the same time, the finite volume method is used to handle the heat transfer problem to determine the temperature field distribution. Combining phase field theory and the thermodynamic property description, the temperature field evolution inside the molten salt and at the heat exchange interface between the molten salt and the outside world is processed through an implicit time integration scheme to obtain the temperature field evolution result. Based on the spatial distribution features, the kinetic behavior description, the temperature field distribution, and the temperature field evolution result, a target description of the heat transfer path in the non-fluid state is generated.

[0061] This step employs a multi-scale modeling approach, extracting spatial distribution characteristics within the molten salt system from both microscopic and macroscopic levels. Microscopic features include particle-level structure, while macroscopic features include the overall temperature field distribution. For example, it analyzes the arrangement of molten salt particles within the container and their impact on overall heat transfer. The discrete element method (DEM) is used to simulate the interactions between molten salt particles, generating a particle-level dynamic behavior description. For instance, it simulates how particles move and rearrange during heating, affecting the heat transfer path. The finite volume method is used to address heat transfer and determine the temperature field distribution. For example, it simulates the temperature changes of molten salt over time and location during heating. Combining phase-field theory and thermodynamic properties, an implicit time integration scheme is used to handle the temperature field evolution at the heat exchange interface inside and outside the molten salt. For example, it simulates the dynamic changes in the temperature field during the transition from solid to liquid state. Based on the above information, a target description of the heat transfer path in the non-fluid state is generated. For example, it determines which regions have the highest heat transfer efficiency and which regions require further optimization.

[0062] Step 103: Based on the target description, the influence of each phase change influencing factor is evaluated using surrogate model technology to obtain the phase change influence evaluation result. Historical operating data is analyzed using deep neural network to obtain historical data analysis results. The pattern recognition result is determined by combining the historical data analysis result and the phase change influence evaluation result. Based on the pattern recognition result, the operating parameter configuration of the molten salt system is optimized to determine the optimal heat exchange performance configuration.

[0063] In this step, the pattern recognition result refers to the operational parameter optimization suggestions obtained through comprehensive analysis of historical data analysis and phase transition impact assessment results.

[0064] This step employs surrogate modeling to assess the impact of various phase change influencing factors, such as temperature changes and latent heat release. For example, it evaluates the impact of latent heat release under different temperature conditions on overall heat exchange efficiency. Deep neural networks are used to analyze historical operating data to identify the interrelationships between phase change influencing factors. For instance, analyzing the operating data of the molten salt system under different operating conditions over the past year helps identify the optimal operating conditions. Combining the phase change impact assessment results with the historical data analysis results, pattern recognition results are determined. For example, determining which operating parameter configuration achieves optimal heat exchange performance within a specific temperature range. Based on the pattern recognition results, the operating parameter configuration of the molten salt system is optimized to determine the optimal heat exchange performance configuration. For example, adjusting parameters such as heating rate and cooling rate maximizes heat exchange efficiency.

[0065] Step 104: Based on the real-time molten salt temperature response data and the optimal heat transfer performance configuration, an evolutionary algorithm is applied to determine the target operating parameter set. A topology is constructed based on the target operating parameter set. Based on the topology and the target operating parameter set, a cooperative competition mechanism in the game theory framework is used to generate a target operating strategy. The target operating strategy is used to guide the operation of the molten salt system to perform non-fluid phase change molten salt heat transfer calculations.

[0066] This step uses real-time molten salt temperature response data and optimal heat transfer performance configuration to apply an evolutionary algorithm to determine the target operating parameter set. For example, based on the current molten salt temperature and historical optimal configuration, parameters such as heating power and cooling rate are adjusted. The topology of the molten salt system is constructed based on the target operating parameter set. For example, the optimal layout of the heater, cooler, and sensors is determined. Based on the topology and the target operating parameter set, a cooperative-competitive mechanism within a game theory framework is used to generate the target operating strategy. For example, a set of operating rules is formulated to ensure that the system maintains optimal performance under different operating conditions.

[0067] The beneficial effects achieved by the embodiments of the present invention through the above steps are as follows:

[0068] By using the Bayesian optimization algorithm to select the most suitable target state equation to describe a specific molten salt system, the accuracy and reliability of the basic data for subsequent model construction are ensured.

[0069] The adaptive thermodynamic model can dynamically adjust its internal parameters according to the composition and temperature conditions of the molten salt, providing a high-precision description of its thermodynamic properties and ensuring accurate prediction of the physical properties, latent heat changes and thermodynamic behavior of the molten salt at different temperatures.

[0070] The application of these methods has improved computational accuracy and efficiency;

[0071] By optimizing the heat transfer path and operating parameters, energy loss during transmission is reduced, the energy utilization rate of the entire system is improved, and a more environmentally friendly and economical operating mode is achieved.

[0072] The generated target operation strategy can flexibly adjust the operation parameters under different working conditions, adapt to complex dynamic environmental changes, and enhance the system's adaptability.

[0073] After constructing the thermodynamic characteristic description of the molten salt system, in order to further accurately simulate the complex heat transfer behavior in the non-fluid phase change process, this invention provides a specific embodiment. Step 102: Based on the thermodynamic characteristic description, a multi-scale modeling method is applied to extract spatial distribution features. Based on the spatial distribution features, the discrete element method is used to generate a kinetic behavior description at the molten salt particle level. At the same time, the finite volume method is used to handle the heat transfer problem to determine the temperature field distribution. Combining phase field theory and the thermodynamic characteristic description, the temperature field evolution inside the molten salt and at the heat exchange interface between the molten salt and the outside world is processed through an implicit time integration scheme to obtain the temperature field evolution result. Based on the spatial distribution features, the kinetic behavior description, the temperature field distribution, and the temperature field evolution result, a target description of the heat transfer path in the non-fluid state is generated, specifically including the following steps:

[0074] Step 210: Based on the thermodynamic property description, microscopic molecular dynamics, and macroscopic continuum mechanics, apply a multi-scale modeling method to simulate and extract the spatial distribution characteristics at different scales within the molten salt system;

[0075] This step uses microscopic molecular dynamics to simulate the interactions between molten salt particles and their contribution to the overall system. For example, it simulates the vibration and movement behavior of individual molten salt particles under high-temperature conditions. Macroscopic continuum mechanics is then used to analyze the heat transfer and flow characteristics of the molten salt system on a larger scale. For example, the temperature distribution and fluid flow within the entire molten salt tank are assessed. Combining thermodynamic descriptions, microscopic and macroscopic simulation results, the spatial distribution characteristics at different scales within the molten salt system are extracted. For example, the arrangement of molten salt particles within the container and their impact on overall heat transfer are determined.

[0076] Step 211: Define the material properties and contact mechanical behavior of the molten salt particles. Based on the material properties, contact mechanical behavior, and thermodynamic characteristics, apply the discrete element method to simulate the interaction between molten salt particles and the influence of the interaction between molten salt particles on the molten salt system. Based on the interaction between molten salt particles and the influence of the interaction between molten salt particles on the molten salt system, generate a kinetic behavior description at the molten salt particle level.

[0077] This step, based on the molten salt composition and experimental data, determines the material properties and contact mechanical behavior of the molten salt particles, such as a density of 1.7 g / cm³. 3 The molten salt has an elastic modulus of 50 GPa and contact mechanical behavior, such as a friction coefficient of 0.3. The discrete element method (DEM) is used to simulate the interactions between molten salt particles, generating a dynamic behavior description. For example, the simulation shows how particles move and rearrange during heating and the impact of these changes on the heat transfer path. Combining the above information, a particle-level dynamic behavior description of the molten salt is generated. For example, it describes how particles change their position and state under different temperature conditions, affecting the overall heat transfer efficiency.

[0078] Step 212: Based on the spatial distribution characteristics, an optimized mesh is generated using adaptive mesh refinement technology and topology optimization algorithm, and boundary conditions are set. Based on the optimized mesh and the boundary conditions, the heat transfer problem is handled using the finite volume method to obtain simulation results. Based on the simulation results, the temperature field distribution within the molten salt system is finally determined. A graph neural network is introduced in the process of handling the heat transfer problem to optimize the simulation results. The boundary conditions include mesh boundary conditions and physical boundary conditions.

[0079] In this step, boundary conditions include mesh boundary conditions and physical boundary conditions. Mesh boundaries include fixed temperature or adiabatic boundaries, while physical boundaries include heater location and power.

[0080] This step uses adaptive mesh refinement techniques and topology optimization algorithms to generate an optimized mesh and sets boundary conditions. For example, fixed temperature boundary conditions are set at the inlet and outlet of the molten salt tank, and heating power boundary conditions are set at the heater location. Based on the optimized mesh and boundary conditions, the finite volume method is used to handle the heat transfer problem, obtaining simulation results. For example, the temperature change of molten salt during the heating process is simulated to determine the temperature field distribution. Graph neural networks are introduced into the process of handling the heat transfer problem to optimize the simulation results. For example, graph neural networks are used to capture the complex relationships between molten salt particles, improving the accuracy of temperature field distribution prediction.

[0081] Step 213: Combining phase field theory and the thermodynamic characteristics described above, the temperature field evolution inside the molten salt and at the heat exchange interface between the molten salt and the outside is processed by an implicit time integration scheme to obtain the temperature field evolution results. In the process of processing by the implicit time integration scheme, a nonlinear dynamic equation solver and an adaptive step size control mechanism are introduced to obtain the temperature field change law with time.

[0082] This step combines phase-field theory and thermodynamic properties to describe the temperature field evolution at the heat exchange interface inside and outside the molten salt using an implicit time integration scheme. For example, it simulates the dynamic changes in the temperature field during the transition of molten salt from solid to liquid. A nonlinear dynamic equation solver and an adaptive step-size control mechanism are introduced into the implicit time integration scheme to obtain the temperature field's variation over time. For instance, a smaller time step is used near the phase transition point to capture the rapidly changing temperature field.

[0083] The beneficial effects achieved by the embodiments of the present invention through the above steps are as follows:

[0084] By providing a particle-level description of the dynamic behavior, it is helpful to understand the complex microstructure inside the molten salt system and its impact on heat transfer;

[0085] The precise temperature field distribution was determined by adaptive mesh refinement technology and graph neural network algorithms, which improved the simulation accuracy and efficiency of heat transfer problems.

[0086] By processing the temperature field evolution, the variation law of the temperature field over time was obtained, ensuring the accurate simulation and prediction of the phase transition process.

[0087] After extracting the spatial distribution features at different scales within the molten salt system, in order to further accurately simulate the heat transfer process and optimize the calculation results, this invention provides a specific embodiment. Step 212 involves generating an optimized mesh using adaptive mesh refinement technology and a topology optimization algorithm based on the spatial distribution features, and setting boundary conditions. Based on the optimized mesh and the boundary conditions, the finite volume method is used to handle the heat transfer problem to obtain simulation results. Based on the simulation results, the temperature field distribution within the molten salt system is finally determined. A graph neural network is introduced in the process of handling the heat transfer problem to optimize the simulation results, specifically including the following steps:

[0088] Step 221: Based on the spatial distribution characteristics, the geometric structure and physical properties of the molten salt system are dynamically adjusted using adaptive mesh refinement technology to generate an initial mesh. A topology optimization algorithm is introduced to optimize the shape and distribution of the initial mesh to generate an optimized mesh. Boundary conditions are set based on the optimized mesh.

[0089] In this step, spatial distribution features refer to the physical and geometric features at different scales within the molten salt system extracted using multi-scale modeling methods. The initial mesh refers to the basic mesh generated based on the geometric structure and physical properties of the molten salt system.

[0090] This step, based on the aforementioned spatial distribution characteristics, dynamically adjusts the geometry and physical properties of the molten salt system using adaptive mesh refinement technology. For example, a finer mesh is used in critical areas of the molten salt tank, such as near the heater, while a coarser mesh is used in areas with smaller temperature variations, reducing computational load and improving accuracy. A topology optimization algorithm is introduced to optimize the shape and distribution of the initial mesh, generating an optimized mesh. For example, by adjusting the position and connection method of mesh nodes, high-quality mesh is maintained even in complex geometries, while minimizing computational resource consumption. Based on the optimized mesh, boundary conditions are set. For example, fixed temperature boundary conditions are set at the inlet and outlet of the molten salt tank, and heating power boundary conditions are set at the heater location to ensure the realism and reliability of the simulation.

[0091] Step 222: Based on the optimized mesh and the boundary conditions, the heat transfer problem is handled using the finite volume method to obtain simulation results, including the temperature field distribution to be optimized;

[0092] This step, based on the optimized mesh and the boundary conditions, uses the finite volume method to handle the heat transfer problem and obtain simulation results. These simulation results include the temperature field distribution to be optimized, i.e., the temperature field distribution obtained from the preliminary simulation, which needs further optimization to improve its accuracy. For example, simulating the temperature change of molten salt during heating initially determines the temperature field distribution to be optimized.

[0093] Step 223: Based on the optimized mesh, construct a graph neural network; based on the graph neural network, analyze the connection patterns between nodes in the optimized mesh to identify the heat transfer paths in the molten salt system and the interactions between the heat transfer paths; based on the heat transfer paths and the interactions between the heat transfer paths, generate a graph neural network model.

[0094] This step, based on the optimized mesh, constructs a graph neural network to analyze the connection patterns between nodes in the optimized mesh, in order to identify heat transfer paths within the molten salt system and the interactions between these paths. For example, it identifies which connections between nodes are the primary heat transfer paths and which paths have significant interactions. Based on these heat transfer paths and their interactions, a graph neural network model is generated. For example, a graph neural network model capable of predicting heat transfer paths and their interactions is constructed, ensuring that the model can capture complex heat transfer behavior.

[0095] Step 224: Based on the graph neural network model, predict the heat transfer path and the heat transfer efficiency of the heat transfer path, and optimize the heat transfer path and the heat transfer efficiency of the heat transfer path to obtain the heat transfer result. Based on the heat transfer result, optimize the temperature field distribution to be optimized in the simulation result, and finally determine the temperature field distribution in the molten salt system.

[0096] This step predicts the heat transfer paths and their heat transfer efficiency based on the graph neural network model. For example, it predicts which heat transfer paths have the highest efficiency and which require further optimization. The heat transfer paths and their heat transfer efficiency are then optimized based on the prediction results. For example, the geometry or material properties of certain heat transfer paths are adjusted to improve overall heat transfer efficiency. The temperature field distribution to be optimized in the simulation results is further optimized based on the heat transfer results, ultimately determining the temperature field distribution within the molten salt system. For example, optimizing the heat transfer paths makes the temperature field distribution more uniform and reduces localized overheating.

[0097] More specifically, this invention provides a formula for calculating the temperature field distribution to generate a target description of the heat transfer path in a non-fluid state. The specific calculation formula is as follows:

[0098] T final =OPT(T) pre Q pred);

[0099] Among them, T final This represents the final temperature field distribution after optimization; OPT represents the optimization function, used to adjust the temperature field distribution to conform to the optimized heat transfer path and heat transfer efficiency; T pre Q represents the temperature field distribution to be optimized; pred Indicates the result of heat transfer;

[0100] The temperature field distribution to be optimized may contain areas of unevenness or significant energy loss. The temperature field distribution formula described above, by incorporating the heat transfer path and efficiency provided by the heat transfer result formula, can specifically optimize these areas, improving overall energy utilization efficiency and effectively avoiding localized overheating or insufficient cooling. This formula ensures that heat is transferred along the optimal path, improving the overall system efficiency. The optimized temperature field distribution is more uniform, reducing stress concentration caused by temperature gradients and extending the equipment's lifespan.

[0101] The formula for calculating the heat transfer result is as follows:

[0102] Q pred =GNN model (G opt C n (,HTP,HTPI);

[0103] Among them, Q pred This represents the heat transfer results, used to optimize the temperature field distribution to be optimized; GNN model Represents a graph neural network model; G opt Indicates the optimized mesh; C n This indicates the connection mode between mesh nodes; HTP represents the heat transfer path; HTPI represents the interaction between heat transfer paths.

[0104] The heat transfer process within a molten salt system involves complex geometry and variable physical properties. Traditional numerical methods struggle to efficiently handle these complexities. Graph neural network models, however, can capture the nonlinear relationships between nodes and adapt to different mesh structures, providing more accurate simulations. By incorporating a graph neural network model, the aforementioned heat transfer formulas more accurately predict the heat transfer paths and their efficiency within the molten salt system, providing reliable foundational data for subsequent optimization.

[0105] The formula for calculating the heat transfer path is as follows:

[0106]

[0107] Where HTP represents the heat transfer path; argmin p This represents the choice among all possible heat transfer paths p that allows ∑i,j w ij (T i -T j ) 2 Minimize the p; ∑ i,j This represents summing over all relevant node pairs (i,j), where relevant nodes refer to node pairs that have a physical possibility of heat transfer; w ij T represents the weight coefficients from node i to node j. i T represents the temperature of node i; j The temperature of node j is indicated by "subject to p∈P". This means that the optimization process is subject to the constraint that the final selected heat transfer path p must belong to the set of heat transfer paths P.

[0108] Minimizing energy loss is one of the important goals of thermal management. The heat transfer path formula can be used to find the most efficient heat transfer path from one node to another, that is, the one with the least energy loss. By minimizing the sum of squares of the temperature difference between adjacent nodes, the formula ensures that heat flows in the direction of least resistance, which is in line with the laws of heat conduction in physics. The weighting coefficients can be used to represent the thermal conductivity of different materials or paths, so the formula can be adjusted according to actual physical conditions.

[0109] The formula for calculating the heat transfer path is as follows:

[0110] HTPI=∑ i,j (F ij ·n ij )exp(-α|T i -T j |);

[0111] Where HTPI represents the interaction between heat transfer paths; ∑ i,j This represents summing over all relevant node pairs (i,j), where relevant nodes refer to node pairs that have a physical possibility of heat transfer; F ij n represents the heat flux from node i to node j; ij Represents the unit normal vector between nodes; exp(-α|T) i -T j |T represents the exponential decay function, α represents the decay factor, and |T| represents the exponential decay function. i -T j | represents the absolute value of the temperature difference between node i and node j.

[0112] In practical applications, multiple heat transfer paths may influence each other, such as path intersections due to spatial constraints or changes in heat flow direction caused by temperature gradient variations. The heat transfer path formula above considers these factors to more accurately simulate real-world phenomena. This formula introduces an attenuation factor, reflecting the phenomenon that the product of heat flux and unit normal vector gradually decreases as the temperature difference increases; this not only simulates direct heat transfer effects but also captures indirect effects, such as thermal radiation or convective heat transfer.

[0113] The beneficial effects achieved by the embodiments of the present invention through the above steps are as follows:

[0114] It provides a high-quality and efficient initial mesh, laying the foundation for subsequent heat transfer problem processing and ensuring the accuracy and efficiency of the calculation;

[0115] The preliminary temperature field distribution was determined, providing basic data for subsequent optimization and improving the accuracy of the simulation;

[0116] It provides a detailed description of the heat transfer path, enhancing the understanding of the internal heat transfer mechanism of the molten salt system and providing data support for optimizing the heat transfer path;

[0117] By using a graph neural network model to predict and optimize heat transfer paths and heat transfer efficiency, the accurate temperature field distribution was ultimately determined, significantly improving the accuracy of the simulation and the heat exchange efficiency of the system.

[0118] After generating the target description of the heat transfer path under non-fluid conditions, this invention provides a specific embodiment to further optimize the heat transfer performance of the molten salt system. Step 103 involves using a surrogate model technique to evaluate the impact of each phase change influencing factor based on the target description, obtaining a phase change impact evaluation result, analyzing historical operating data using a deep neural network to obtain historical data analysis results, combining the historical data analysis results and the phase change impact evaluation results to determine the pattern recognition result, and optimizing the operating parameter configuration of the molten salt system based on the pattern recognition result to determine the optimal heat transfer performance configuration. This specifically includes the following steps:

[0119] Step 311: Select a target surrogate model using surrogate model technology, and use the global sensitivity analysis method in the target surrogate model to evaluate the degree of influence of each phase change influencing factor on the overall heat exchange efficiency, and obtain the phase change factor influence results. Based on the phase change factor influence results, use the local sensitivity analysis method in the target surrogate model to identify the key factors affecting the overall heat exchange efficiency under specific operating conditions. Based on the phase change factor influence results and the key factors, obtain the phase change influence assessment results. The phase change influencing factors include temperature change, latent heat release, and latent heat absorption. The specific operating conditions include high-temperature operation conditions and low-temperature start-up conditions. The key factors include latent heat release rate and latent heat absorption rate.

[0120] In this step, the phase change influencing factor refers to factors that affect the heat transfer performance of the molten salt system, such as temperature changes, latent heat release, and latent heat absorption.

[0121] This step employs surrogate modeling techniques to select a suitable target surrogate model for evaluating phase change influencing factors. For example, Gaussian process regression is chosen as the target surrogate model because it handles nonlinear relationships well and provides uncertainty estimation. The global sensitivity analysis method within the target surrogate model is used to assess the impact of each phase change influencing factor on overall heat transfer efficiency. For instance, global sensitivity analysis reveals that latent heat release has a significant impact on heat transfer efficiency under high-temperature operating conditions. Based on the results of the phase change factor impact assessment, the local sensitivity analysis method within the target surrogate model is used to identify key factors affecting overall heat transfer efficiency under specific operating conditions. For example, under high-temperature operating conditions, the latent heat release rate is a key factor; while under low-temperature start-up conditions, the latent heat absorption rate is more important. Combining the above analysis results, the phase change impact assessment results are obtained, clarifying which phase change influencing factors have the greatest impact on heat transfer efficiency under different operating conditions. For example, it is determined that the latent heat release rate should be the focus during high-temperature operation, while the latent heat absorption rate should be optimized during low-temperature start-up.

[0122] Step 312: Construct a hybrid physical data-driven model based on physical laws and deep neural networks, analyze historical operation data based on the hybrid physical data-driven model, and obtain historical data analysis results;

[0123] This step involves constructing a hybrid physics data-driven model based on physical laws and deep neural networks. For example, the heat conduction equation is used as the foundation of the model, and a deep neural network is used to capture nonlinear relationships in the data. This hybrid physics data-driven model is then used to analyze historical operating data of the molten salt system, yielding historical data analysis results. For instance, analyzing the operating data of the molten salt system under different operating conditions over the past year helps identify optimal operating conditions and potential problems.

[0124] Step 313: Based on the historical data analysis results and the phase transition impact assessment results, apply advanced pattern recognition technology to identify the interrelationships between the phase transition influencing factors, and determine the pattern recognition results based on the key factors and the interrelationships between the phase transition influencing factors.

[0125] This step, based on the historical data analysis results and the phase change impact assessment results, applies advanced pattern recognition technology to identify the relationships between the phase change influencing factors. For example, a significant negative correlation was found between the latent heat release rate and the latent heat absorption rate. Based on the key factors and the relationships between the phase change influencing factors, the pattern recognition results are determined. For example, it is confirmed that under high-temperature operating conditions, an increase in the latent heat release rate leads to a significant improvement in overall heat exchange efficiency, while under low-temperature start-up conditions, optimizing the latent heat absorption rate can effectively improve the system start-up speed.

[0126] Step 314: Based on the pattern recognition results, adjust the operating parameter configuration of the molten salt system using the Bayesian optimization algorithm to generate a preliminary optimized operating parameter configuration. Introduce a genetic algorithm to optimize the preliminary optimized operating parameter configuration to generate a final optimized operating parameter configuration. Based on the final optimized operating parameter configuration, determine the optimal heat exchange performance configuration.

[0127] This step, based on pattern recognition results, uses a Bayesian optimization algorithm to adjust the operating parameter configuration of the molten salt system, generating a preliminary optimized operating parameter configuration. For example, parameters such as heating power and cooling rate are adjusted to maximize heat exchange efficiency. A genetic algorithm is then introduced to optimize the preliminary optimized operating parameter configuration, generating a final optimized operating parameter configuration. For example, the genetic algorithm further optimizes the specific values ​​of heating power and cooling rate to ensure the system maintains optimal performance under various operating conditions. Based on the final optimized operating parameter configuration, the optimal heat exchange performance configuration is determined. For example, it is determined that under high-temperature operating conditions, a heating power of X kW and a cooling rate of Y ℃ / min can achieve the highest heat exchange efficiency.

[0128] The beneficial effects achieved by the embodiments of the present invention through the above steps are as follows:

[0129] The target proxy model provides detailed phase transition impact assessment results, which provides a scientific basis for subsequent optimization and ensures the rationality of operating parameter configuration;

[0130] Advanced pattern recognition technology provides comprehensive pattern recognition results, helping to understand the complex relationships between phase transition influencing factors and providing a scientific basis for optimizing operating parameter configurations.

[0131] Precise optimization of operating parameters was achieved, ensuring that the molten salt system can achieve optimal heat exchange performance under different operating conditions, thereby improving the overall efficiency and stability of the system.

[0132] After completing the assessment of phase transition influencing factors and the identification of key factors, in order to further improve the scientificity and accuracy of the molten salt system operating parameter configuration, this invention provides a specific embodiment. Step 312 involves constructing a hybrid physical data-driven model based on physical laws and deep neural networks, and analyzing historical operating data based on the hybrid physical data-driven model to obtain historical data analysis results. Specifically, this includes the following steps:

[0133] Step 321: Select a neural network structure, and based on the neural network structure, physical laws and deep learning technology, construct a hybrid physics data-driven model that combines prior physical knowledge. Analyze historical operating data based on the hybrid physics data-driven model to obtain preliminary historical data analysis results.

[0134] This step involves selecting a suitable neural network structure based on the characteristics of the molten salt system. For example, a convolutional neural network (CNN) or recurrent neural network (RNN) with multiple hidden layers is chosen to handle complex spatiotemporal data. Based on this neural network structure, physical laws, and deep learning techniques, a hybrid physics data-driven model incorporating prior physical knowledge is constructed. For instance, the heat conduction equation is embedded into the neural network, enabling the model to better understand physical processes. The hybrid physics data-driven model is then used to analyze historical operating data of the molten salt system, yielding preliminary historical data analysis results. For example, analyzing parameters such as temperature changes and latent heat release under different operating conditions over the past year helps identify key factors affecting heat transfer efficiency.

[0135] Step 322: Based on the preliminary historical data analysis results, use a long short-term memory network to perform time series prediction on the historical operating data to obtain the time series prediction results;

[0136] This step, based on the preliminary historical data analysis results, uses a Long Short-Term Memory (LSTM) network to perform time series prediction on the historical operating data, obtaining time series prediction results. For example, it predicts the temperature change trend of the molten salt system over the next week, helping to adjust operating parameters in advance to optimize performance.

[0137] Step 323: Use the Isolation Forest algorithm to perform anomaly detection on the preliminary historical data analysis results, generate anomaly detection results, optimize the preliminary historical data analysis results based on the time series prediction results and the anomaly detection results, and obtain the historical data analysis results;

[0138] This step uses the Isolation Forest algorithm to detect anomalies in the preliminary historical data analysis results, generating anomaly detection results. For example, it identifies anomalous fluctuations in the historical operating data, such as sudden temperature spikes or drops, which may be signs of equipment malfunction or operational errors. Based on the time series prediction results and the anomaly detection results, the preliminary historical data analysis results are optimized to obtain the final historical data analysis results. For example, after removing outlier data points, the historical operating data is re-evaluated to ensure the accuracy and reliability of the analysis results.

[0139] The beneficial effects achieved by the embodiments of the present invention through the above steps are as follows:

[0140] It provides an analytical framework that combines physical knowledge and data-driven approaches, ensuring that the model can not only capture complex data patterns but also maintain the accuracy of physical meaning.

[0141] Using long short-term memory networks improves the ability to predict future operating states, enhances the predictability and response speed of the system, and helps prevent potential problems.

[0142] Historical data analysis improves the accuracy of historical data analysis, removes the influence of outliers, and makes subsequent optimization and decision-making more reliable.

[0143] Having clarified the spatial distribution characteristics and heat transfer paths at different scales within the molten salt system, this invention provides a specific embodiment to further accurately describe the system's thermodynamic behavior. Step 101 involves selecting a target equation of state using a Bayesian optimization algorithm. Based on the target equation of state, the molten salt composition, and temperature conditions, an adaptive thermodynamic model is constructed. Based on this adaptive thermodynamic model, the set of physical property parameters, latent heat changes, and thermodynamic behavior of the molten salt at different temperatures are determined to obtain a description of the thermodynamic characteristics of the molten salt system. Specifically, this includes the following steps:

[0144] Step 111: Based on Bayesian optimization algorithm and Gaussian process regression, evaluate the performance of different equations of state and obtain performance evaluation results. Select the target equation of state based on the performance evaluation results. Based on the target equation of state, molten salt composition and temperature conditions, apply physical information neural network to construct an adaptive thermodynamic model.

[0145] In this step, the equation of state refers to the mathematical expression describing the physical properties of a substance under different temperature and pressure conditions. Performance evaluation results refer to the results obtained after evaluating different equations of state, including indicators such as prediction accuracy and computational efficiency.

[0146] This step uses Bayesian optimization and Gaussian process regression to evaluate the performance of multiple candidate equations of state. For example, for a mixed molten salt system containing sodium nitrate and potassium nitrate, the performance of different equations of state in simulating the physical properties of the molten salt is evaluated. Based on the performance evaluation results, the most suitable target equation of state is selected. For example, the evaluation found that the improved van der Waals equation most accurately describes the physical properties of the molten salt system, and therefore this equation is selected as the target equation of state. Based on the target equation of state, the molten salt composition, and the temperature conditions, an adaptive thermodynamic model is constructed using a physical information neural network. For example, the heat conduction equation is embedded in the neural network, enabling the adaptive thermodynamic model to better understand the physical processes and dynamically adjust its internal parameters according to actual operating conditions.

[0147] Step 112: Based on the adaptive thermodynamic model, calculate the physical properties of the molten salt at different temperatures to obtain a set of physical property parameters, including density, specific heat capacity, and thermal conductivity;

[0148] This step, based on the aforementioned adaptive thermodynamic model, calculates the physical properties of the molten salt at different temperatures, obtaining a set of physical property parameters. For example, the density of the molten salt at 400℃ is calculated to be 1.7 g / cm³. 3 Its specific heat capacity is 1.2 J / g·K, and its thermal conductivity is 0.5 W / m·K.

[0149] Step 113: Based on the set of physical property parameters, simulate the latent heat release and latent heat absorption of molten salt during the phase change process to calculate the change in latent heat;

[0150] This step, based on the aforementioned set of physical property parameters, simulates the latent heat release and absorption of molten salt during phase transition to calculate the change in latent heat. For example, simulating the transition of molten salt from solid to liquid, the latent heat absorbed per gram of molten salt is calculated to be 200 J / g.

[0151] Step 114: Combine the set of physical property parameters and the latent heat change to analyze the thermodynamic behavior of the molten salt system and generate a thermodynamic behavior description of the molten salt system, including the phase transition point, phase transition rate and energy conversion efficiency.

[0152] This step combines the set of physical property parameters and the latent heat change to analyze the thermodynamic behavior of the molten salt system and generate a description of its thermodynamic behavior. For example, it determines that the phase transition point of the molten salt is 450℃, the phase transition rate is 0.5℃ / min, and the energy conversion efficiency during the phase transition is 90%, thereby optimizing the system's operating parameters and ensuring efficient operation.

[0153] The beneficial effects achieved by the embodiments of the present invention through the above steps are as follows:

[0154] This ensured that the state equations most suitable for describing the molten salt system were selected, improving the accuracy of subsequent modeling and calculations;

[0155] A high-precision adaptive thermodynamic model is provided to ensure that the model can accurately reflect the behavior of the molten salt system under different conditions;

[0156] A detailed set of physical property parameters is provided to ensure the accuracy and reliability of the basic data for subsequent analysis;

[0157] It provides precise latent heat changes, which helps to understand the energy conversion mechanism in phase transition processes;

[0158] It provides a comprehensive description of thermodynamic behavior, helping to optimize the configuration of operating parameters for molten salt systems and improve the overall performance and stability of the system.

[0159] After calculating the set of physical property parameters of molten salt at different temperatures and simulating the latent heat change during the phase transition process, in order to further understand the overall thermodynamic behavior of the molten salt system, this invention provides a specific embodiment. Step 114: Combining the set of physical property parameters and the latent heat change, the thermodynamic behavior of the molten salt system is analyzed to generate a description of the thermodynamic behavior of the molten salt system. The thermodynamic behavior includes the phase transition point, phase transition rate, and energy conversion efficiency, specifically including the following steps:

[0160] Step 121: Based on the set of physical property parameters and the latent heat change, identify the phase transition temperature point of the molten salt from solid to liquid or from liquid to solid.

[0161] In this step, the latent heat change refers to the total amount of heat absorbed or released during the phase transition. The phase transition temperature is the temperature at which a substance undergoes a transition from solid to liquid or from liquid to solid.

[0162] This step, based on the set of physical property parameters and the latent heat change, identifies the phase transition temperature point of the molten salt from solid to liquid or from liquid to solid by analyzing the thermodynamic behavior of the molten salt at different temperatures. For example, for a mixed molten salt system containing sodium nitrate and potassium nitrate, a significant latent heat absorption phenomenon was observed at 450°C, and this temperature was determined to be the phase transition temperature point of the system.

[0163] Step 122: Based on the phase transition temperature point, temperature change rate, and latent heat change, calculate the rate of state transition of the molten salt during the phase transition process to obtain the phase transition rate;

[0164] In this step, the rate of temperature change refers to the rate at which the temperature changes over time.

[0165] This step calculates the rate of state transition of the molten salt during the phase transition process based on the phase transition temperature, the rate of temperature change, and the latent heat change, thus obtaining the phase transition rate. The rate of temperature change is similar to the heating or cooling rate. For example, assuming the molten salt system heats up at a rate of 0.5℃ / min near the phase transition temperature and each gram of molten salt absorbs 200 J / g of latent heat, the phase transition rate is calculated to be 0.1 g / s using thermodynamic formulas.

[0166] Step 122: Based on the phase transition rate, use coupled fluid dynamics simulation and finite element analysis to evaluate the energy transfer path and loss mechanism of the molten salt system, and obtain the energy transfer evaluation results;

[0167] This step, based on the phase change rate, utilizes coupled fluid dynamics simulation and finite element analysis to evaluate the energy transfer path and loss mechanism of the molten salt system, obtaining energy transfer assessment results. For example, simulations revealed that during the phase change process, the molten salt primarily transfers heat to the container wall through conduction and convection, with some heat loss occurring at the container wall. Further analysis shows that the choice of container wall material and its thickness significantly affect heat loss.

[0168] Step 122: Based on the energy transfer evaluation results and the phase change rate, evaluate the energy conversion efficiency of the molten salt system in the heat exchange process, and combine the phase change rate, the energy transfer evaluation results and the energy conversion efficiency to generate a description of the thermodynamic behavior of the molten salt system.

[0169] In this step, energy conversion efficiency refers to the effective utilization rate of energy during the phase transition process.

[0170] This step evaluates the energy conversion efficiency of the molten salt system during the heat exchange process based on the energy transfer assessment results and the phase change rate. For example, analysis of simulation results reveals that the energy conversion efficiency of the molten salt during the phase change process is 90%, meaning that 90% of the input energy is effectively used for the phase change, while the remaining 10% is dissipated due to heat loss and other factors. Combining the phase change rate, energy transfer assessment results, and energy conversion efficiency, a thermodynamic behavior description of the molten salt system is generated. For example, the final thermodynamic behavior description includes a phase change point of 450℃, a phase change rate of 0.1 g / s, and an energy conversion efficiency of 90%.

[0171] The beneficial effects achieved by the embodiments of the present invention through the above steps are as follows:

[0172] The phase transition temperature point of the molten salt system was accurately identified, providing crucial data support for subsequent calculations;

[0173] It provides accurate phase transition rates, which helps to understand the kinetic characteristics of phase transition processes and optimize operating conditions;

[0174] It provides detailed analysis of energy transfer paths and loss mechanisms to help optimize system design and reduce unnecessary energy loss;

[0175] It provides a comprehensive description of thermodynamic behavior, helping to optimize the configuration of operating parameters for molten salt systems and improve the overall performance and stability of the system.

[0176] Figure 2 This invention provides a schematic diagram of the structure of a computational system for non-fluid phase change molten salt heat transfer, as shown in the embodiment of the invention. Figure 2 As shown, the system includes:

[0177] Module 21 is used to select a target equation of state using a Bayesian optimization algorithm, and to construct an adaptive thermodynamic model based on the target equation of state, the composition of the molten salt and the temperature conditions. Based on the adaptive thermodynamic model, the set of physical property parameters, latent heat change and thermodynamic behavior of the molten salt at different temperatures are determined to obtain a thermodynamic characteristic description of the molten salt system.

[0178] The determination module 22 is used to extract spatial distribution features based on the thermodynamic property description by applying a multi-scale modeling method. Based on the spatial distribution features, it uses the discrete element method to generate a kinetic behavior description of molten salt particles. At the same time, it uses the finite volume method to handle the heat transfer problem to determine the temperature field distribution. Combining phase field theory and the thermodynamic property description, it uses an implicit time integration scheme to process the temperature field evolution inside the molten salt and at the heat exchange interface between the molten salt and the outside world to obtain the temperature field evolution result. Based on the spatial distribution features, the kinetic behavior description, the temperature field distribution, and the temperature field evolution result, it generates a target description of the heat transfer path in the non-fluid state.

[0179] Optimization module 23 is used to evaluate the impact of each phase change influencing factor based on the target description using surrogate model technology to obtain phase change impact evaluation results, analyze historical operating data using deep neural networks to obtain historical data analysis results, combine the historical data analysis results and the phase change impact evaluation results to determine pattern recognition results, and optimize the operating parameter configuration of the molten salt system based on the pattern recognition results to determine the optimal heat exchange performance configuration.

[0180] The generation module 24 is used to determine the target operating parameter set based on real-time molten salt temperature response data and the optimal heat transfer performance configuration by applying an evolutionary algorithm, constructing a topology based on the target operating parameter set, generating a target operating strategy based on the topology and the target operating parameter set by adopting a cooperative competition mechanism under the game theory framework, and realizing the calculation of non-fluid phase change molten salt heat transfer based on the target operating strategy.

[0181] Figure 2 The aforementioned computational system for non-fluid phase change molten salt heat transfer can perform... Figure 1 The implementation principle and technical effects of the non-fluid phase change molten salt heat transfer calculation method described in the illustrated embodiment will not be repeated here. The specific operation methods of each module and unit in the calculation system for non-fluid phase change molten salt heat transfer in the above embodiments have been described in detail in the embodiments related to this method, and will not be elaborated upon here.

[0182] In one possible design, Figure 2 The computational system for non-fluid phase change molten salt heat transfer in the illustrated embodiment can be implemented as a computing device, such as... Figure 3 As shown, the computing device may include a storage component 31 and a processing component 32;

[0183] The storage component 31 stores one or more computer instructions, wherein the one or more computer instructions are invoked and executed by the processing component 32.

[0184] The processing component 32 is used to: select a target equation of state using a Bayesian optimization algorithm; construct an adaptive thermodynamic model based on the target equation of state, molten salt composition, and temperature conditions; determine the set of physical property parameters, latent heat change, and thermodynamic behavior of the molten salt at different temperatures based on the adaptive thermodynamic model to obtain a thermodynamic characteristic description of the molten salt system; extract spatial distribution features using a multi-scale modeling method based on the thermodynamic characteristic description; generate a particle-level dynamic behavior description of the molten salt using the discrete element method based on the spatial distribution features; simultaneously use the finite volume method to handle heat transfer problems to determine the temperature field distribution; combine phase field theory and the thermodynamic characteristic description; process the temperature field evolution inside the molten salt and at the heat exchange interface between the molten salt and the outside environment using an implicit time integration scheme to obtain the temperature field evolution result; and, based on the spatial distribution features, the dynamic behavior description, and the temperature field distribution... Based on the temperature field evolution results, a target description of the heat transfer path under non-fluid conditions is generated. Based on this target description, a surrogate model technique is used to evaluate the impact of each phase change influencing factor, obtaining a phase change impact assessment result. A deep neural network is used to analyze historical operating data, obtaining historical data analysis results. Combining the historical data analysis results and the phase change impact assessment results, a pattern recognition result is determined. Based on the pattern recognition result, the operating parameter configuration of the molten salt system is optimized to determine the optimal heat transfer performance configuration. Based on real-time molten salt temperature response data and the optimal heat transfer performance configuration, an evolutionary algorithm is applied to determine the target operating parameter set. A topology is constructed based on the target operating parameter set. Based on the topology and the target operating parameter set, a cooperative competition mechanism within a game theory framework is used to generate a target operating strategy. This target operating strategy guides the operation of the molten salt system for calculating non-fluid phase change molten salt heat transfer.

[0185] The processing component 32 may include one or more processors to execute computer instructions to complete all or part of the steps in the above-described method. Alternatively, the processing component may be implemented as one or more application-specific integrated circuits (ASICs), digital signal processors (DSPs), digital signal processing devices (DSPDs), programmable logic devices (PLDs), field-programmable gate arrays (FPGAs), controllers, microcontrollers, microprocessors, or other electronic components to perform the above-described method.

[0186] Storage component 31 is configured to store various types of data to support operations at the terminal. The storage component can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic storage, flash memory, magnetic disk, or optical disk.

[0187] Of course, computing devices may also include other components, such as input / output interfaces, display components, communication components, etc.

[0188] Input / output interfaces provide interfaces between processing components and peripheral interface modules, which can be output devices, input devices, etc.

[0189] The communication components are configured to facilitate wired or wireless communication between computing devices and other devices.

[0190] The computing device can be a physical device or an elastic computing host provided by a cloud computing platform. In this case, the computing device can refer to a cloud server, and the aforementioned processing components, storage components, etc., can be basic server resources rented or purchased from the cloud computing platform.

[0191] This invention also provides a computer storage medium storing a computer program, which, when executed by a computer, can perform the above-described functions. Figure 1 The embodiment shown illustrates a calculation method for non-fluid phase change molten salt heat transfer.

[0192] Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the specific working processes of the systems, devices, and units described above can be referred to the corresponding processes in the foregoing method embodiments, and will not be repeated here.

[0193] The device embodiments described above are merely illustrative. 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; that is, they may be located in one place or distributed across multiple network units. Some or all of the modules can be selected to achieve the purpose of this embodiment according to actual needs. Those skilled in the art can understand and implement this without any creative effort.

[0194] Through the above description of the embodiments, those skilled in the art can clearly understand that each embodiment can be implemented by means of software plus necessary general-purpose hardware platforms, and of course, it can also be implemented by hardware. Based on this understanding, the above technical solutions, in essence or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, magnetic disk, optical disk, etc., and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute the methods described in the various embodiments or some parts of the embodiments.

[0195] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, and not to limit them; although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features; and these modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A calculation method for non-fluid phase change molten salt heat transfer, characterized in that, include: A target state equation is selected using a Bayesian optimization algorithm. Based on the target state equation, the composition of the molten salt, and the temperature conditions, an adaptive thermodynamic model is constructed. Based on the adaptive thermodynamic model, the set of physical property parameters, latent heat change, and thermodynamic behavior of the molten salt at different temperatures are determined to obtain a description of the thermodynamic characteristics of the molten salt system. Based on the thermodynamic property description, a multi-scale modeling method is applied to extract spatial distribution features. Based on these features, the discrete element method is used to generate a kinetic behavior description at the molten salt particle level. Simultaneously, the finite volume method is used to handle the heat transfer problem to determine the temperature field distribution. Combining phase field theory and the thermodynamic property description, an implicit time integration scheme is used to process the temperature field evolution inside the molten salt and at the heat exchange interface between the molten salt and the outside world, obtaining the temperature field evolution result. Based on the spatial distribution features, the kinetic behavior description, the temperature field distribution, and the temperature field evolution result, a target description of the heat transfer path in a non-fluid state is generated. Based on the target description, the influence of each phase change influencing factor is evaluated using surrogate model technology to obtain phase change influence evaluation results. Historical operating data is analyzed using deep neural networks to obtain historical data analysis results. Combining the historical data analysis results and the phase change influence evaluation results, the pattern recognition results are determined. Based on the pattern recognition results, the operating parameter configuration of the molten salt system is optimized to determine the optimal heat exchange performance configuration. Based on real-time molten salt temperature response data and the optimal heat transfer performance configuration, an evolutionary algorithm is applied to determine the target operating parameter set. A topology is constructed based on the target operating parameter set. Based on the topology and the target operating parameter set, a cooperative competition mechanism in the game theory framework is used to generate a target operating strategy. The target operating strategy is used to guide the operation of the molten salt system to perform non-fluid phase change molten salt heat transfer calculations.

2. The method according to claim 1, characterized in that, Based on the aforementioned thermodynamic property description, a multi-scale modeling method is applied to extract spatial distribution features. Based on these features, the discrete element method is used to generate a kinetic behavior description at the molten salt particle level. Simultaneously, the finite volume method is used to handle heat transfer issues to determine the temperature field distribution. Combining phase field theory and the aforementioned thermodynamic property description, an implicit time integration scheme is used to process the temperature field evolution within the molten salt and at the heat exchange interface between the molten salt and the external environment, yielding the temperature field evolution results, including: Based on the thermodynamic properties described above, microscopic molecular dynamics, and macroscopic continuum mechanics, a multi-scale modeling method is applied to simulate and extract the spatial distribution characteristics of the molten salt system at different scales. The material properties and contact mechanical behavior of molten salt particles are defined. Based on the material properties, contact mechanical behavior and thermodynamic characteristics, the discrete element method is applied to simulate the interaction between molten salt particles and the influence of the interaction between molten salt particles on the molten salt system. Based on the interaction between molten salt particles and the influence of the interaction between molten salt particles on the molten salt system, a dynamic behavior description at the molten salt particle level is generated. Based on the spatial distribution characteristics, an optimized mesh is generated using adaptive mesh refinement technology and topology optimization algorithm, and boundary conditions are set. Based on the optimized mesh and the boundary conditions, the heat transfer problem is handled using the finite volume method to obtain simulation results. Based on the simulation results, the temperature field distribution in the molten salt system is finally determined. A graph neural network is introduced in the process of handling the heat transfer problem to optimize the simulation results. The boundary conditions include mesh boundary conditions and physical boundary conditions. Combining phase field theory and the aforementioned thermodynamic characteristics, the temperature field evolution inside the molten salt and at the heat exchange interface between the molten salt and the outside world is processed by an implicit time integration scheme to obtain the temperature field evolution results. In the process of processing by the implicit time integration scheme, a nonlinear dynamic equation solver and an adaptive step size control mechanism are introduced to obtain the temperature field variation law with time.

3. The method according to claim 2, characterized in that, Based on the spatial distribution characteristics, an optimized mesh is generated using adaptive mesh refinement technology and topology optimization algorithm, and boundary conditions are set. Based on the optimized mesh and the boundary conditions, the finite volume method is used to handle the heat transfer problem, and simulation results are obtained. Based on the simulation results, the temperature field distribution within the molten salt system is finally determined. A graph neural network is introduced in the process of handling the heat transfer problem to optimize the simulation results, including: Based on the spatial distribution characteristics, the geometry and physical properties of the molten salt system are dynamically adjusted using adaptive mesh refinement technology to generate an initial mesh. A topology optimization algorithm is then introduced to optimize the shape and distribution of the initial mesh to generate an optimized mesh. Boundary conditions are then set based on the optimized mesh. Based on the optimized mesh and the boundary conditions, the heat transfer problem is handled using the finite volume method to obtain simulation results, which include the temperature field distribution to be optimized. Based on the optimized mesh, a graph neural network is constructed. Based on the graph neural network, the connection patterns between nodes in the optimized mesh are analyzed to identify the heat transfer paths in the molten salt system and the interactions between the heat transfer paths. Based on the heat transfer paths and the interactions between the heat transfer paths, a graph neural network model is generated. Based on the graph neural network model, the heat transfer path and its heat transfer efficiency are predicted and optimized to obtain the heat transfer results. Based on the heat transfer results, the temperature field distribution to be optimized in the simulation results is optimized, and finally the temperature field distribution in the molten salt system is determined.

4. The method according to claim 1, characterized in that, Based on the target description, a surrogate model technique is used to evaluate the impact of each phase change influencing factor, obtaining phase change impact evaluation results. A deep neural network is used to analyze historical operating data, obtaining historical data analysis results. Combining the historical data analysis results and the phase change impact evaluation results, pattern recognition results are determined. Based on the pattern recognition results, the operating parameter configuration of the molten salt system is optimized to determine the optimal heat exchange performance configuration, including: A target surrogate model is selected using surrogate model technology. The global sensitivity analysis method in the target surrogate model is used to evaluate the impact of each phase change influencing factor on the overall heat exchange efficiency, and the phase change factor impact results are obtained. Based on the phase change factor impact results, the local sensitivity analysis method in the target surrogate model is used to identify the key factors affecting the overall heat exchange efficiency under specific operating conditions. Based on the phase change factor impact results and the key factors, the phase change impact assessment results are obtained. The phase change influencing factors include temperature change, latent heat release, and latent heat absorption. The specific operating conditions include high-temperature operation conditions and low-temperature start-up conditions. The key factors include latent heat release rate and latent heat absorption rate. A hybrid physical data-driven model is constructed based on physical laws and deep neural networks. Historical operational data is analyzed based on the hybrid physical data-driven model to obtain historical data analysis results. Based on the historical data analysis results and the phase transition impact assessment results, advanced pattern recognition technology is applied to identify the interrelationships between the phase transition influencing factors. Based on the key factors and the interrelationships between the phase transition influencing factors, the pattern recognition results are determined. Based on the pattern recognition results, the operating parameter configuration of the molten salt system is adjusted using a Bayesian optimization algorithm to generate a preliminary optimized operating parameter configuration. A genetic algorithm is then introduced to optimize the preliminary optimized operating parameter configuration to generate a final optimized operating parameter configuration. Based on the final optimized operating parameter configuration, the optimal heat exchange performance configuration is determined.

5. The method according to claim 4, characterized in that, A hybrid physics data-driven model is constructed based on physical laws and deep neural networks. Historical operational data is analyzed based on this model to obtain historical data analysis results, including: A neural network structure is selected, and based on the neural network structure, physical laws, and deep learning technology, a hybrid physics data-driven model that combines prior physical knowledge is constructed. Based on the hybrid physics data-driven model, historical operation data is analyzed to obtain preliminary historical data analysis results. Based on the preliminary historical data analysis results, a long short-term memory network is used to perform time series prediction on the historical operating data to obtain the time series prediction results. The isolated forest algorithm is used to detect anomalies in the preliminary historical data analysis results, generating anomaly detection results. Based on the time series prediction results and the anomaly detection results, the preliminary historical data analysis results are optimized to obtain the historical data analysis results.

6. The method according to claim 1, characterized in that, A target equation of state is selected using a Bayesian optimization algorithm. Based on the target equation of state, the composition of the molten salt, and the temperature conditions, an adaptive thermodynamic model is constructed. Based on the adaptive thermodynamic model, the set of physical property parameters, latent heat changes, and thermodynamic behavior of the molten salt at different temperatures are determined to obtain a thermodynamic characteristic description of the molten salt system, including: Based on Bayesian optimization algorithm and Gaussian process regression, the performance of different equations of state is evaluated to obtain performance evaluation results. Based on the performance evaluation results, a target equation of state is selected. Based on the target equation of state, molten salt composition and temperature conditions, an adaptive thermodynamic model is constructed by applying physical information neural network. Based on the adaptive thermodynamic model, the physical properties of molten salt at different temperatures are calculated to obtain a set of physical property parameters, including density, specific heat capacity, and thermal conductivity. Based on the set of physical property parameters, the latent heat release and latent heat absorption of molten salt during the phase change process are simulated to calculate the change in latent heat. By combining the set of physical property parameters and the latent heat change, the thermodynamic behavior of the molten salt system is analyzed, and a description of the thermodynamic behavior of the molten salt system is generated, including the phase transition point, phase transition rate, and energy conversion efficiency.

7. The method according to claim 6, characterized in that, By combining the aforementioned set of physical property parameters and the latent heat change, the thermodynamic behavior of the molten salt system is analyzed, and a description of the thermodynamic behavior of the molten salt system is generated. This thermodynamic behavior includes the phase transition point, phase transition rate, and energy conversion efficiency, including: Based on the set of physical property parameters and the latent heat change, the phase transition temperature point of the molten salt from solid to liquid or from liquid to solid is identified. Based on the phase transition temperature point, the temperature change rate, and the latent heat change, the rate of state transition of the molten salt during the phase transition process is calculated to obtain the phase transition rate. Based on the phase transition rate, the energy transfer path and loss mechanism of the molten salt system are evaluated using coupled fluid dynamics simulation and finite element analysis, and the energy transfer evaluation results are obtained. Based on the energy transfer assessment results and the phase change rate, the energy conversion efficiency of the molten salt system during the heat exchange process is evaluated. Combining the phase change rate, the energy transfer assessment results, and the energy conversion efficiency, a description of the thermodynamic behavior of the molten salt system is generated.

8. A computational system for non-fluid phase change molten salt heat transfer, characterized in that, include: The module is used to select the target equation of state using a Bayesian optimization algorithm, and to construct an adaptive thermodynamic model based on the target equation of state, the composition of the molten salt and the temperature conditions. Based on the adaptive thermodynamic model, the physical property parameter set, latent heat change and thermodynamic behavior of the molten salt at different temperatures are determined to obtain a thermodynamic characteristic description of the molten salt system. The determination module is used to extract spatial distribution features based on the thermodynamic property description, apply multi-scale modeling methods, and generate a kinetic behavior description of molten salt particles using the discrete element method based on the spatial distribution features. At the same time, the finite volume method is used to handle the heat transfer problem to determine the temperature field distribution. Combining phase field theory and the thermodynamic property description, the temperature field evolution inside the molten salt and at the heat exchange interface between the molten salt and the outside world is processed through an implicit time integration scheme to obtain the temperature field evolution result. Based on the spatial distribution features, the kinetic behavior description, the temperature field distribution, and the temperature field evolution result, a target description of the heat transfer path in the non-fluid state is generated. The optimization module is used to evaluate the impact of each phase change influencing factor based on the target description using surrogate model technology, obtain phase change impact evaluation results, analyze historical operating data using deep neural networks to obtain historical data analysis results, combine the historical data analysis results and the phase change impact evaluation results to determine pattern recognition results, and optimize the operating parameter configuration of the molten salt system based on the pattern recognition results to determine the optimal heat exchange performance configuration. The generation module is used to determine the target operating parameter set based on real-time molten salt temperature response data and the optimal heat transfer performance configuration by applying an evolutionary algorithm, constructing a topology based on the target operating parameter set, generating a target operating strategy based on the topology and the target operating parameter set by adopting a cooperative competition mechanism under the game theory framework, and realizing the calculation of non-fluid phase change molten salt heat transfer based on the target operating strategy.

9. A computing device, characterized in that, It includes a processing component and a storage component; the storage component stores one or more computer instructions; the one or more computer instructions are invoked and executed by the processing component to implement the calculation method for non-fluid phase change molten salt heat transfer as described in any one of claims 1 to 7.

10. A computer storage medium, characterized in that, The device contains a computer program that, when executed by a computer, implements a calculation method for non-fluid phase change molten salt heat transfer as described in any one of claims 1 to 7.

Images