Methods, apparatus, equipment and storage medium for density prediction of molten salt thermal storage materials

Abstract

This application discloses a method, apparatus, device, and storage medium for predicting the density of molten salt thermal storage materials. The method includes: determining a candidate linear mapping model between the density of molten salt and temperature in the target energy storage material based on the mole fraction data and density data of each sub-component material in a sample material corresponding to the target energy storage material; determining candidate mapping relationship sub-models for each target temperature range based on at least two target temperature ranges; optimizing the model parameters of the candidate mapping relationship sub-models using a particle swarm optimization algorithm to determine a target mapping relationship sub-model; and determining a target linear mapping model based on the target mapping relationship sub-models corresponding to each target temperature range. This technical solution improves the accuracy and applicability of mixed molten salt density prediction.

Description

Technical Field

[0001] This application relates to the field of mixed molten salt thermal storage materials technology, specifically to a density prediction method, apparatus, equipment, and storage medium for molten salt thermal storage materials. Background Technology

[0002] Hybrid molten salt thermal storage materials, as the core carrier of energy storage in oil pipeline stations, play a crucial role in ensuring the stable operation of oil transportation systems due to their excellent thermal storage performance. Density, as a core physical parameter of hybrid molten salt, is directly related to the equipment selection, operating energy consumption, and safety management of the thermal storage system, and is an important basis for the design and optimization of thermal storage schemes in oil pipeline stations.

[0003] However, the existing methods for obtaining the density of mixed molten salts rely on traditional experimental measurements, which are cumbersome, costly, and limited by experimental conditions, making it difficult to cover the complex temperature ranges and component ratios in the actual operation of oil pumping stations. This results in insufficient prediction accuracy and fails to meet the high-precision density parameter requirements of oil pumping stations. Summary of the Invention

[0004] This application provides a method, apparatus, equipment, and storage medium for predicting the density of molten salt thermal storage materials, so as to improve the accuracy of density prediction for molten salt thermal storage materials.

[0005] According to one aspect of this application, a method for predicting the density of molten salt thermal storage materials is provided, the method comprising: Based on the mole fraction data and density data of each sub-component material in the sample material corresponding to the target energy storage material, a candidate linear mapping model between molten salt density and temperature in the target energy storage material is determined; wherein, the target energy storage material is a mixed lava material composed of at least two sub-component materials; Based on at least two target temperature ranges, determine the candidate mapping relationship sub-model corresponding to the candidate linear mapping model in each target temperature range; For the candidate mapping relationship sub-models, the particle swarm optimization algorithm is used to optimize the model parameters in the candidate mapping relationship sub-models to determine the target mapping relationship sub-model; Based on the target mapping relationship sub-model corresponding to each target temperature range, a target linear mapping model is determined; wherein, the target linear mapping model is used to predict the mixed molten salt density of the target energy storage material.

[0006] According to another aspect of this application, a density prediction device for molten salt thermal storage materials is provided, the device comprising: The candidate model determination module is used to determine a candidate linear mapping model between molten salt density and temperature in the target energy storage material based on the mole fraction data and density data of each sub-component material in the sample material corresponding to the target energy storage material; wherein, the target energy storage material is a mixed lava material composed of at least two sub-component materials; The candidate sub-model determination module is used to determine the candidate mapping relationship sub-model corresponding to the candidate linear mapping model in each target temperature range based on at least two target temperature ranges. The target sub-model determination module is used to optimize the model parameters in the candidate mapping relationship sub-models using a particle swarm optimization algorithm to determine the target mapping relationship sub-model. The target model determination module is used to determine the target linear mapping model based on the target mapping relationship sub-model corresponding to each target temperature range; wherein, the target linear mapping model is used to predict the mixed molten salt density of the target energy storage material.

[0007] According to another aspect of this application, an electronic device is provided, the electronic device comprising: One or more processors; Memory, used to store one or more programs; When the one or more programs are executed by the one or more processors, the one or more processors implement any of the density prediction methods for molten salt thermal storage materials provided in the embodiments of this application.

[0008] According to another aspect of this application, a computer-readable storage medium is provided, on which a computer program is stored, which, when executed by a processor, implements any of the density prediction methods for molten salt thermal storage materials provided in the embodiments of this application.

[0009] According to another aspect of this application, a computer program product is provided, including a computer program that, when executed by a processor, implements any of the density prediction methods for molten salt thermal storage materials provided in the embodiments of this application.

[0010] This application addresses the problem of insufficient prediction accuracy of a single model in a wide temperature range and multi-component systems by performing piecewise fitting of candidate linear mapping models based on differences in temperature characteristics, taking into account the influence of temperature range differences and component distribution ratios. It provides reliable density data support for the design, operation, and safety assessment of thermal storage systems at oil pipeline stations. Furthermore, it utilizes particle swarm optimization algorithm to optimize model parameters, effectively improving the accuracy and applicability of mixed molten salt density prediction. Attached Figure Description

[0011] Figure 1This is a flowchart of a density prediction method for molten salt thermal storage materials according to Embodiment 1 of this application; Figure 2 This is a flowchart of a density prediction method for molten salt thermal storage materials according to Embodiment 2 of this application; Figure 3 This is a flowchart of a density prediction method for molten salt thermal storage materials according to Embodiment 3 of this application; Figure 4 This is a schematic diagram of the structure of a density prediction device for molten salt thermal storage material according to Embodiment 4 of this application; Figure 5 This is a schematic diagram of the structure of an electronic device for implementing the density prediction method of molten salt thermal storage material according to Embodiment 5 of this application. Detailed Implementation

[0012] To enable those skilled in the art to better understand the present application, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present application, and not all embodiments. Based on the embodiments in the present application, all other embodiments obtained by those of ordinary skill in the art without creative effort should fall within the scope of protection of the present application.

[0013] It should be noted that the terms "first," "second," etc., in the specification, claims, and accompanying drawings of this application are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of this application described herein can be implemented in orders other than those illustrated or described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.

[0014] Example 1 Figure 1 This is a flowchart of a density prediction method for molten salt thermal storage materials according to Embodiment 1 of this application. This embodiment is applicable to the prediction of the density of a mixed molten salt for a target energy storage material. The prediction can be performed by a density prediction device for molten salt thermal storage materials, which can be implemented in hardware and / or software and can be configured in a computer device, such as a server. Figure 1 As shown, the method includes: S110. Based on the mole fraction data of each sub-component material in the sample material corresponding to the target energy storage material and the density data of the sample material, determine the candidate linear mapping model between the molten salt density and temperature in the target energy storage material.

[0015] The target energy storage material can be a mixed lava material composed of at least two sub-component materials.

[0016] Candidate linear mapping models can be used to characterize the linear mapping relationship between molten salt density and temperature in standard energy storage materials.

[0017] It should be noted that the mole fraction data of each sub-component material in the sample material can be obtained by chemical analysis methods to detect the sample material; the density data of each sub-component material can be collected by a high-temperature density meter.

[0018] In this embodiment of the invention, commonly used sub-component materials in oil pipeline stations can be selected as components of the mixed molten salt. Sample materials of target energy storage materials with different ratios are prepared by weighing the corresponding mass of each sub-component material and mixing them uniformly. Optionally, the sub-component materials can be sodium nitrate, potassium nitrate, and calcium nitrate, etc. For example, for any sample material with a single sub-component material ratio, a chemical analysis method is used to detect the mole fraction data of each sub-component material in the sample material to determine the mole fraction corresponding to each sub-component material, and the sum of the mole fractions of each sub-component material is 1. For any sample material with a single sub-component material ratio, multiple sampling temperature points are uniformly set within a preset operating temperature range corresponding to the sample material. A high-temperature density meter is used to repeatedly measure the molten salt density data corresponding to each sampling temperature point a preset number of times to obtain multiple molten salt density data corresponding to that sampling temperature point. Optionally, for each sample material, multiple molten salt density data obtained at sampling temperature points can be used to remove outliers using the Grubbs test for each sampling temperature point. The molten salt density data after outlier removal can then be processed by arithmetic mean, and the result of the arithmetic mean can be used as the molten salt density data corresponding to that sampling temperature point.

[0019] By repeatedly measuring the molten salt density of the sample material at each sampling temperature point within a preset operating temperature range, random errors in the measurement process are reduced, and the measurement accuracy of the results is improved. Furthermore, outlier removal and averaging are performed on the multiple molten salt density data corresponding to the sampling temperature points to reduce data fluctuations. This makes the processed data more reflective of the true density characteristics of the mixed molten salt at the corresponding temperature, providing more stable and accurate input data for model parameter fitting and improving the data quality of model construction.

[0020] S120. Based on at least two target temperature ranges, determine the candidate mapping relationship sub-models corresponding to the candidate linear mapping model in each target temperature range.

[0021] Different target temperature ranges can be used to characterize different operating temperature conditions of the target energy storage material.

[0022] Optionally, based on at least two target temperature ranges, candidate mapping relationship sub-models corresponding to the candidate linear mapping model in each target temperature range are determined, including: determining a first target temperature range, a second target temperature range, and a third target temperature range according to the operating conditions of the target energy storage material; and using the least squares method to fit the interval model parameters of the candidate linear mapping model based on the density data of the sub-component materials in each target temperature range, thereby determining the candidate mapping relationship sub-models corresponding to each target temperature range.

[0023] The temperature ranges corresponding to the first target temperature range, the second target temperature range, and the third target temperature range can increase sequentially.

[0024] Interval model parameters can include prefactor parameters and apparent activation energy parameters.

[0025] Specifically, based on the actual operating temperature conditions of the target energy storage material, three target temperature ranges can be generated: a low-temperature range, a medium-temperature range, and a high-temperature range, corresponding to the first, second, and third target temperature ranges, respectively. Based on the operating temperature of the sample material, the molten salt density data corresponding to the sample material is divided into their respective target temperature ranges. For the first, second, and third target temperature ranges, the molten salt density data of the sample material within each target temperature range, along with the sample material's operating temperature, can be input into a candidate linear mapping model. With the objective of minimizing the sum of squared residuals between the predicted and measured molten salt density values, the least squares method is used to minimize the sum of squared residuals between the predicted and measured molten salt density values ​​of the candidate linear mapping model. This determines the antecedent factor parameters and apparent activation energy parameters corresponding to the target temperature range, thereby determining the candidate mapping relationship sub-model.

[0026] For example, for a first target temperature range, a set of initial prefactor parameters and initial apparent activation energy parameters can be selected from the ranges of prefactor parameters and apparent activation energy parameters corresponding to the first target temperature range. These initial prefactor parameters and initial apparent activation energy parameters are then substituted into a candidate linear mapping model to predict the molten salt density at each sampling temperature point within the first target temperature range. Then, based on the sum of squared residuals between the predicted molten salt density at each sampling temperature point within the first target temperature range and the measured molten salt density data, if the sum of squared residuals is less than a preset residual threshold, the prefactor parameters and apparent activation energy parameters corresponding to the sum of squared residuals are used to construct a candidate mapping relationship sub-model corresponding to the first target temperature range. Otherwise, a parameter optimization algorithm (gradient descent method) is used to update the initial prefactor parameters and initial apparent activation energy parameters. Optionally, the preset residual threshold can be adaptively set according to those skilled in the art.

[0027] Optionally, the ranges of the pre-factor parameters and the apparent activation energy parameters can be determined based on the measured molten salt density data of the sampling temperature points within the target temperature range, the candidate linear mapping model, and the parameter error ranges of the pre-factor parameters and the apparent activation energy parameters. For example, the measured molten salt density data corresponding to the lowest temperature sampling temperature point within the first target temperature range is substituted into the candidate linear mapping model, and the range of the pre-factor parameters is determined in conjunction with the parameter error range of the pre-factor parameters; the measured molten salt density data corresponding to two sampling temperature points within the first target temperature range are substituted into the candidate linear mapping model respectively, compared, and then the logarithm is taken, and the range of the apparent activation energy parameters is determined in conjunction with the parameter error range of the apparent activation energy parameters.

[0028] Based on the differences in the characteristics of mixed molten salt in different temperature ranges, multiple target temperature ranges are generated. By fitting the model parameters to different target temperature ranges, candidate mapping relationship sub-models corresponding to each target temperature range are generated. This avoids the overall fitting deviation caused by the large temperature span, and makes the model parameters of each target temperature range more consistent with the density change law of the corresponding temperature range. This significantly improves the prediction accuracy of the model in each temperature range and ensures the accuracy of density prediction under different working conditions.

[0029] S130. For the candidate mapping relation sub-models, the particle swarm optimization algorithm is used to optimize the model parameters in the candidate mapping relation sub-models to determine the target mapping relation sub-model.

[0030] S140. Determine the target linear mapping model based on the target mapping relationship sub-model corresponding to each target temperature range.

[0031] Among them, the target linear mapping model can be used to predict the mixed molten salt density of the target energy storage material.

[0032] Optionally, in this embodiment of the invention, the process of predicting the mixed molten salt density of the target energy storage material using the target linear mapping model includes: determining the operating temperature of the target energy storage material based on its operating conditions, and determining the target temperature range within which the operating temperature is located as the operating temperature range; determining the target mapping relationship sub-model corresponding to the operating temperature range based on the operating temperature range; and inputting the mole fraction data of the sub-component materials corresponding to the target energy storage material and the operating temperature into the target mapping relationship sub-model to determine the predicted molten salt density corresponding to the target energy storage material.

[0033] This application's embodiments address the issue of insufficient prediction accuracy of a single model in a wide temperature range and multi-component systems by segmenting and fitting candidate linear mapping models based on differences in temperature characteristics. This approach considers the influence of temperature range differences and component group ratios, providing reliable density data support for the design, operation, and safety assessment of oilfield thermal storage systems. Furthermore, the application utilizes particle swarm optimization algorithms to optimize model parameters, effectively improving the accuracy and applicability of mixed molten salt density prediction.

[0034] Example 2 Figure 2 This is a flowchart of a density prediction method for molten salt thermal storage materials according to Embodiment 2 of this application. Based on the technical solutions of the above embodiments, this embodiment further refines the step of "determining a candidate linear mapping model between the molten salt density and temperature in the target energy storage material based on the mole fraction data of each sub-component material in the sample material corresponding to the target energy storage material and the density data of the sample material." It should be noted that for parts not detailed in this embodiment, please refer to the relevant descriptions in other embodiments. Figure 2 As shown, the method includes: S210. Based on the Arrhenius equation, determine the standard linear mapping model between molten salt density and temperature in the target energy storage material.

[0035] Optionally, the standard linear mapping model can be represented by the following formula: ; in, Let A be the predicted molten salt density at temperature T, E be the pre-exponential factor, R be the apparent activation energy, and T be the absolute temperature.

[0036] It should be noted that, in this embodiment of the invention, the Arrhenius equation is originally used to describe the exponential relationship between the rate constant of a chemical reaction and temperature. However, the relationship between molten salt density and temperature can borrow its form because it shares commonalities in both physics and mathematics. From a physical perspective, the change in molten salt density with temperature (thermal expansion) can be considered a thermally driven process. Thermal energy (RT) needs to overcome the energy barrier (E) formed by the cohesive forces between molecules or ions. Increased temperature enhances thermal motion and increases the tendency to overcome cohesive forces, thus leading to a significant decrease in density. From a mathematical and parametric perspective, the exponential form of the Arrhenius equation is consistent with the characteristic of molten salt density decreasing monotonically and nonlinearly with increasing temperature. The pre-factor can be used to characterize the molten salt density when the temperature approaches absolute zero, and the apparent activation energy can be used to characterize the sensitivity of molten salt density to temperature changes.

[0037] S220. Perform multiple linear regression on the mole fraction and density data of the sub-component materials to determine the density influence coefficient of each sub-component material.

[0038] S230. Based on the density influence coefficient and mole fraction data of the sub-component materials, determine the mole fraction correction factor of the sub-component materials.

[0039] S240. Based on the standard linear mapping model and the mole fraction correction factor, determine the candidate linear mapping model between molten salt density and temperature in the target energy storage material.

[0040] Specifically, in this embodiment of the invention, for sample materials of target energy storage materials with different sub-component material ratios, multiple linear regression analysis can be performed based on the measured molten salt density data of different sample materials at a unified sampling temperature point, using the mole fraction data of the sub-component materials as independent variables and the measured molten salt density data of the sample materials as dependent variables. The density influence coefficient corresponding to each sub-component material is then obtained by fitting the data using the least squares method. A mole fraction correction factor is introduced into the standard linear mapping model to obtain a candidate linear mapping model. It should be noted that the mole fraction correction factor can be the sum of the products of the mole fraction of each sub-component material and its corresponding density influence coefficient.

[0041] Optionally, the candidate linear mapping model can be represented by the following formula: ; in, , as well as These are the density influence coefficients for the three sub-component materials, respectively. , as well as These are the mole fraction data for the three sub-component materials. It should be noted that... This is the mole fraction correction factor.

[0042] It should be noted that in the candidate linear mapping model under low-temperature operating conditions The value can be set to 1 by default.

[0043] S250. Based on at least two target temperature ranges, determine the candidate mapping relationship sub-models corresponding to the candidate linear mapping model in each target temperature range.

[0044] S260. For the candidate mapping relation sub-models, the particle swarm optimization algorithm is used to optimize the model parameters in the candidate mapping relation sub-models to determine the target mapping relation sub-model.

[0045] S270. Determine the target linear mapping model based on the target mapping relationship sub-model corresponding to each target temperature range.

[0046] The embodiments of this application obtain density influence coefficients corresponding to different sub-component materials through multiple linear regression fitting, quantify the contribution of different sub-component materials to the density of molten salt, and introduce component mole fraction correction factors into the standard linear mapping model, so that the candidate linear mapping model can adapt to mixed molten salt systems with different component ratios, effectively improving the universality of the model and solving the problem that traditional single models are difficult to take into account multiple component ratios.

[0047] Example 3 Figure 3 This is a flowchart of a density prediction method for molten salt thermal storage materials according to Embodiment 3 of this application. Based on the technical solutions of the above embodiments, this embodiment further refines the step of "using a particle swarm optimization algorithm to optimize the model parameters in the candidate mapping relationship sub-models to determine the target mapping relationship sub-model." It should be noted that for parts not detailed in this embodiment, please refer to the relevant descriptions in other embodiments. Figure 3 As shown, the method includes: S310. Based on the mole fraction data of each sub-component material in the sample material corresponding to the target energy storage material and the density data of the sample material, determine the candidate linear mapping model between the molten salt density and temperature in the target energy storage material.

[0048] S320. Based on at least two target temperature ranges, determine the candidate mapping relationship sub-models corresponding to the candidate linear mapping model in each target temperature range.

[0049] S330. Construct a fitness evaluation function based on the sum of squared residuals between the density prediction values ​​and density label values ​​corresponding to the candidate mapping relationship sub-models.

[0050] It should be noted that the density prediction value refers to the predicted molten salt density, while the density label value refers to the measured molten salt density data corresponding to the sample material.

[0051] S340. The particle swarm optimization algorithm is used to optimize the model parameters corresponding to the candidate mapping relationship sub-models.

[0052] The fitness evaluation function can be used as an evaluation criterion for parameter optimization. Optionally, the fitness evaluation function is defined as the sum of squared residuals between the measured molten salt density data and the predicted molten salt density values ​​corresponding to the current model parameters within a preset temperature range. The preset temperature range can refer to any target temperature range.

[0053] It should be noted that during each particle iteration optimization process, the velocity and position of each particle are updated, and the individual historical best position and the group historical best position of each particle are updated simultaneously. When the number of iterations reaches the preset maximum value or the rate of change of the group historical best fitness value is less than the preset threshold, the optimized parameters are obtained.

[0054] Optionally, the particle swarm optimization algorithm is used to optimize the model parameters corresponding to the candidate mapping relationship sub-model, and the method further includes: initializing the particle swarm corresponding to the candidate mapping relationship sub-model based on the model parameters in the candidate mapping relationship sub-model.

[0055] The particle swarm initialization process may include: randomly generating the initial positions of at least two particles for the model parameters in the candidate mapping relationship sub-model, and assigning each particle a corresponding initial velocity vector; and completing the particle swarm initialization process based on the individual historical best position and the group historical best position of each particle.

[0056] Specifically, the initial position vectors of multiple particles can be randomly generated within a preset neighborhood of each target temperature range, using the pre-factor parameters and apparent activation energy parameters corresponding to that range as the center point. Optionally, the preset neighborhood range can be adaptively set according to those skilled in the art.

[0057] By generating an initial population centered on the model parameters within the target temperature range, the particle swarm search begins near the potential optimal solution, significantly shortening the convergence time and effectively improving the reliability and stability of the optimized model parameters.

[0058] This invention employs a particle swarm optimization algorithm to optimize the model parameters in the candidate mapping relationship sub-model, effectively avoiding the predicament of traditional gradient descent methods easily getting trapped in local optima in complex nonlinear spaces. Through a population cooperative search mechanism, the probability of obtaining the globally optimal parameter solution is significantly improved, thereby ensuring the accuracy and reliability of density prediction.

[0059] Example 4 Figure 4 This is a schematic diagram of a density prediction device for molten salt thermal storage materials according to Embodiment 4 of this application. It is applicable to predicting the density of mixed molten salt for target energy storage materials. This density prediction device for molten salt thermal storage materials can be implemented in hardware and / or software, and can be configured in a computer device, such as a server. Figure 4 As shown, the device includes: The candidate model determination module 410 is used to determine a candidate linear mapping model between molten salt density and temperature in the target energy storage material based on the mole fraction data and density data of each sub-component material in the sample material corresponding to the target energy storage material; wherein, the target energy storage material is a mixed lava material composed of at least two sub-component materials; The candidate sub-model determination module 420 is used to determine, based on at least two target temperature ranges, the candidate mapping relationship sub-model corresponding to the candidate linear mapping model in each target temperature range; The target sub-model determination module 430 is used to optimize the model parameters in the candidate mapping relationship sub-models using a particle swarm optimization algorithm to determine the target mapping relationship sub-model. The target model determination module 440 is used to determine the target linear mapping model based on the target mapping relationship sub-model corresponding to each target temperature range; wherein, the target linear mapping model is used to predict the mixed molten salt density of the target energy storage material.

[0060] This application's embodiments address the issue of insufficient prediction accuracy of a single model in a wide temperature range and multi-component systems by segmenting and fitting candidate linear mapping models based on differences in temperature characteristics. This approach considers the influence of temperature range differences and component group ratios, providing reliable density data support for the design, operation, and safety assessment of oilfield thermal storage systems. Furthermore, the application utilizes particle swarm optimization algorithms to optimize model parameters, effectively improving the accuracy and applicability of mixed molten salt density prediction.

[0061] Optionally, the candidate model determination module 410 includes: The standard linear model determination unit is used to determine the standard linear mapping model between molten salt density and temperature in the target energy storage material based on the Arrhenius equation. The density influence coefficient determination unit is used to perform multiple linear regression processing on the mole fraction data and density data corresponding to the sub-component materials to determine the density influence coefficient corresponding to each sub-component material. The correction factor determination unit is used to determine the mole fraction correction factor corresponding to the sub-component material based on the density influence coefficient corresponding to the sub-component material and the mole fraction data corresponding to the sub-component material. The candidate model determination unit is used to determine the candidate linear mapping model between molten salt density and temperature in the target energy storage material based on the standard linear mapping model and the mole fraction correction factor.

[0062] Optionally, the candidate sub-model determination module 420 includes: The temperature range is divided into units to determine the first target temperature range, the second target temperature range, and the third target temperature range based on the operating conditions of the target energy storage material; wherein the temperature ranges corresponding to the first target temperature range, the second target temperature range, and the third target temperature range increase sequentially. The candidate sub-model determination unit is used to perform interval model parameter fitting on the candidate linear mapping model based on the density data of the sub-component material under each target temperature range, using the least squares method, to determine the candidate mapping relationship sub-model corresponding to each target temperature range; wherein, the interval model parameters include the pre-factor parameters and the apparent activation energy parameters.

[0063] Optionally, the target sub-model determination module 430 includes: The evaluation function determination unit is used to construct a fitness evaluation function based on the sum of squared residuals between the density prediction value and the density label value corresponding to the candidate mapping relationship sub-model. The parameter optimization unit is used to optimize the model parameters corresponding to the candidate mapping relationship sub-model using the particle swarm optimization algorithm. In each particle iteration optimization process, the velocity and position of each particle are updated, and the individual historical best position and the group historical best position of each particle are updated synchronously. When the number of iterations reaches a preset maximum value or the rate of change of the group historical best fitness value is less than a preset threshold, the optimized parameters are obtained.

[0064] Optionally, the parameter optimization unit may also include: The particle initialization subunit is used to initialize the particle swarm corresponding to the candidate mapping relationship submodel according to the model parameters in the candidate mapping relationship submodel. The particle swarm initialization process includes: randomly generating the initial positions of at least two particles for the model parameters in the candidate mapping relationship submodel, and assigning an initial velocity vector to each particle; and completing the particle swarm initialization process according to the individual historical best position and the group historical best position of each particle.

[0065] Optionally, the process of the target linear mapping model predicting the mixed molten salt density of the target energy storage material includes: determining the operating temperature of the target energy storage material based on its operating conditions, and determining the target temperature range within which the operating temperature is located as the operating temperature range; determining the target mapping relationship sub-model corresponding to the operating temperature range based on the operating temperature range; and inputting the mole fraction data of the sub-component materials corresponding to the target energy storage material and the operating temperature into the target mapping relationship sub-model to determine the predicted molten salt density corresponding to the target energy storage material.

[0066] The density prediction device for molten salt thermal storage materials provided in this application embodiment can execute the density prediction method for molten salt thermal storage materials provided in any embodiment of this application, and has the corresponding functional modules and beneficial effects for executing the density prediction method for each molten salt thermal storage material.

[0067] According to embodiments of this application, this application also provides an electronic device, a readable storage medium, and a computer program product.

[0068] Example 5 Figure 5 This is a schematic diagram of the structure of an electronic device 510 implementing the density prediction method for molten salt thermal storage materials according to embodiments of this application. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workbenches, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device may also represent various forms of mobile devices, such as personal digital processors, cellular phones, smartphones, wearable devices (such as helmets, glasses, watches, etc.), and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely illustrative and are not intended to limit the implementation of the present application described and / or claimed herein.

[0069] like Figure 5 As shown, the electronic device 510 includes at least one processor 511 and a memory, such as a read-only memory 512 or a random access memory 513, communicatively connected to the at least one processor 511. The memory stores computer programs executable by the at least one processor. The processor 511 can perform various appropriate actions and processes based on the computer program stored in the read-only memory 512 or loaded from storage unit 518 into the random access memory 513. The random access memory 513 can also store various programs and data required for the operation of the electronic device 510. The processor 511, read-only memory 512, and random access memory 513 are interconnected via a bus 514. An input / output interface 515 is also connected to the bus 514.

[0070] Multiple components in electronic device 510 are connected to input / output interface 515, including: input unit 516, such as keyboard, mouse, etc.; output unit 517, such as various types of monitors, speakers, etc.; storage unit 418, such as disk, optical disk, etc.; and communication unit 519, such as network card, modem, wireless transceiver, etc. Communication unit 519 allows electronic device 510 to exchange information / data with other devices through computer networks such as the Internet and / or various telecommunications networks.

[0071] Processor 511 can be a variety of general-purpose and / or special-purpose processing components with processing and computing capabilities. Some examples of processor 511 include, but are not limited to, central processing units, graphics processing units, various special-purpose artificial intelligence computing chips, various processors running machine learning model algorithms, digital signal processors, and any suitable processor, controller, microcontroller, etc. Processor 511 performs the various methods and processes described above, such as the density prediction method for molten salt thermal storage materials.

[0072] In some embodiments, the density prediction method for molten salt thermal storage materials can be implemented as a computer program tangibly contained in a computer-readable storage medium, such as storage unit 518. In some embodiments, part or all of the computer program can be loaded and / or installed on electronic device 510 via read-only memory 512 and / or communication unit 519. When the computer program is loaded into random access memory 513 and executed by processor 511, one or more steps of the density prediction method for molten salt thermal storage materials described above can be performed. Alternatively, in other embodiments, processor 511 can be configured as the density prediction method for molten salt thermal storage materials by any other suitable means (e.g., by means of firmware).

[0073] Various embodiments of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field-programmable gate arrays, application-specific integrated circuits (ASICs), application-specific standard products (ASICs), systems-on-a-chip (SoCs), payload programmable logic devices, computer hardware, firmware, software, and / or combinations thereof. These various embodiments may include implementations in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which may be a dedicated or general-purpose programmable processor, capable of receiving data and instructions from a storage system, at least one input device, and at least one output device, and transmitting data and instructions to the storage system, the at least one input device, and the at least one output device.

[0074] Computer programs used to implement the methods of this application may be written in any combination of one or more programming languages. These computer programs may be provided to the processor of a general-purpose computer, a special-purpose computer, or other programmable density prediction device for molten salt thermal storage materials, such that when executed by the processor, the functions / operations specified in the flowcharts and / or block diagrams are implemented. The computer programs may be executed entirely on a machine, partially on a machine, or as a standalone software package, partially on a machine and partially on a remote machine, or entirely on a remote machine or server.

[0075] In the context of this application, a computer-readable storage medium can be a tangible medium that may contain or store a computer program for use by or in conjunction with an instruction execution system, apparatus, or device. A computer-readable storage medium can be, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination of the foregoing. Alternatively, a computer-readable storage medium can be a machine-readable signal medium. More specific examples of machine-readable storage media include electrical connections based on one or more wires, portable computer disks, hard disks, random access memory, read-only memory, erasable programmable read-only memory, optical fibers, portable compact disk read-only memory, optical storage devices, magnetic storage devices, or any suitable combination of the foregoing.

[0076] To provide interaction with a user, the systems and techniques described herein can be implemented on an electronic device having: a display device (e.g., a cathode ray tube or liquid crystal display monitor) for displaying information to the user; and a keyboard and pointing device (e.g., a mouse or trackball) through which the user provides input to the electronic device. Other types of devices can also be used to provide interaction with the user; for example, feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including sound input, voice input, or tactile input).

[0077] The systems and technologies described herein can be implemented in computing systems that include backend components (e.g., as data servers), or computing systems that include middleware components (e.g., application servers), or computing systems that include frontend components (e.g., user computers with graphical user interfaces or web browsers through which users can interact with implementations of the systems and technologies described herein), or any combination of such backend, middleware, or frontend components. The components of the system can be interconnected via digital data communication of any form or medium (e.g., communication networks). Examples of communication networks include local area networks (LANs), wide area networks (WANs), blockchain networks, and the Internet.

[0078] A computing system can include clients and servers. Clients and servers are generally geographically separated and typically interact via communication networks. The client-server relationship is created by computer programs running on the respective computers and having a client-server relationship with each other. The server can be a cloud server, also known as a cloud computing server or cloud host, which is a host product within the cloud computing service system to address the shortcomings of traditional physical hosts and virtual private servers, such as high management difficulty and weak business scalability.

[0079] It should be understood that the various forms of processes shown above can be used to rearrange, add, or delete steps. For example, the steps described in this application can be executed in parallel, sequentially, or in different orders, as long as the desired result of the technical solution of this application can be achieved, and this is not limited herein.

[0080] The specific embodiments described above do not constitute a limitation on the scope of protection of this application. Those skilled in the art should understand that various modifications, combinations, sub-combinations, and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of this application should be included within the scope of protection of this application.

Claims

1. A method for predicting the density of molten salt thermal storage materials, characterized in that, include: Based on the mole fraction data and density data of each sub-component material in the sample material corresponding to the target energy storage material, a candidate linear mapping model between molten salt density and temperature in the target energy storage material is determined; wherein, the target energy storage material is a mixed lava material composed of at least two sub-component materials; Based on at least two target temperature ranges, determine the candidate mapping relationship sub-model corresponding to the candidate linear mapping model in each target temperature range; For the candidate mapping relationship sub-models, the particle swarm optimization algorithm is used to optimize the model parameters in the candidate mapping relationship sub-models to determine the target mapping relationship sub-model; Based on the target mapping relationship sub-model corresponding to each target temperature range, a target linear mapping model is determined; wherein, the target linear mapping model is used to predict the mixed molten salt density of the target energy storage material.

2. The method according to claim 1, characterized in that, Based on the mole fraction data and density data of each sub-component material in the sample material corresponding to the target energy storage material, a candidate linear mapping model between the molten salt density and temperature in the target energy storage material is determined, including: Based on the Arrhenius equation, a standard linear mapping model between molten salt density and temperature in the target energy storage material is determined. Multiple linear regression was performed on the mole fraction data and density data of the sub-component materials to determine the density influence coefficient of each sub-component material. Based on the density influence coefficient and the mole fraction data of the sub-component material, determine the mole fraction correction factor of the sub-component material; Based on the standard linear mapping model and the mole fraction correction factor, a candidate linear mapping model between molten salt density and temperature in the target energy storage material is determined.

3. The method according to claim 1, characterized in that, The step of determining the candidate mapping relationship sub-model corresponding to the candidate linear mapping model in each target temperature interval based on at least two target temperature intervals includes: Based on the operating conditions of the target energy storage material, a first target temperature range, a second target temperature range, and a third target temperature range are determined; wherein the temperature ranges corresponding to the first target temperature range, the second target temperature range, and the third target temperature range increase sequentially. Based on the density data of the sub-component materials in each target temperature range, the least squares method is used to fit the interval model parameters of the candidate linear mapping model to determine the candidate mapping relationship sub-model corresponding to each target temperature range; wherein, the interval model parameters include the pre-factor parameters and the apparent activation energy parameters.

4. The method according to claim 1, characterized in that, The step of optimizing the model parameters in the candidate mapping sub-model using a particle swarm optimization algorithm includes: Based on the sum of squared residuals between the density prediction values ​​and density label values ​​corresponding to the candidate mapping relationship sub-models, a fitness evaluation function is constructed. The particle swarm optimization algorithm is used to optimize the model parameters corresponding to the candidate mapping relationship sub-model. In each particle iteration optimization process, the velocity and position of each particle are updated, and the individual historical best position and the group historical best position of each particle are updated synchronously. When the number of iterations reaches a preset maximum value or the rate of change of the group historical best fitness value is less than a preset threshold, the optimized parameters are obtained.

5. The method according to claim 4, characterized in that, The step of using particle swarm optimization algorithm to optimize the model parameters corresponding to the candidate mapping relationship sub-models further includes: Based on the model parameters in the candidate mapping sub-model, the particle swarm corresponding to the candidate mapping sub-model is initialized. The particle swarm initialization process includes: randomly generating the initial positions of at least two particles for the model parameters in the candidate mapping relationship sub-model, and assigning each particle a corresponding initial velocity vector; and completing the particle swarm initialization process based on the individual historical best position and the group historical best position of each particle.

6. The method according to claim 1, characterized in that, The process by which the target linear mapping model predicts the mixed molten salt density of the target energy storage material includes: Based on the operating conditions of the target energy storage material, the operating temperature of the target energy storage material is determined, and the target temperature range in which the operating temperature is located is determined as the operating temperature range. Based on the operating temperature range, determine the target mapping relationship sub-model corresponding to the operating temperature range; The mole fraction data of the sub-component materials corresponding to the target energy storage material and the operating temperature are input into the target mapping relationship sub-model to determine the predicted molten salt density corresponding to the target energy storage material.

7. A density prediction device for molten salt thermal storage materials, characterized in that, include: The candidate model determination module is used to determine a candidate linear mapping model between molten salt density and temperature in the target energy storage material based on the mole fraction data and density data of each sub-component material in the sample material corresponding to the target energy storage material; wherein, the target energy storage material is a mixed lava material composed of at least two sub-component materials; The candidate sub-model determination module is used to determine the candidate mapping relationship sub-model corresponding to the candidate linear mapping model in each target temperature range based on at least two target temperature ranges. The target sub-model determination module is used to optimize the model parameters in the candidate mapping relationship sub-models using a particle swarm optimization algorithm to determine the target mapping relationship sub-model. The target model determination module is used to determine the target linear mapping model based on the target mapping relationship sub-model corresponding to each target temperature range; wherein, the target linear mapping model is used to predict the mixed molten salt density of the target energy storage material.

8. An electronic device, characterized in that, include: One or more processors; Memory, used to store one or more programs; When the one or more programs are executed by the one or more processors, the one or more processors implement the density prediction method for molten salt thermal storage materials as described in any one of claims 1-6.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that, When executed by a processor, the program implements the density prediction method for molten salt thermal storage materials as described in any one of claims 1-6.

10. A computer program product comprising a computer program that, when executed by a processor, implements the density prediction method for molten salt thermal storage materials according to any one of claims 1-6.

Images