Method, device and equipment for determining binary interaction parameters of thermodynamic model

Abstract

The invention discloses a method, a device and equipment for determining binary interaction parameters of a thermodynamic model, and relates to the field of chemical process simulation. The method comprises the following steps: in a chemical process simulation process, obtaining molecular structure data of any binary component, and inputting the molecular structure data and a plurality of simulation temperatures into a pre-trained activity coefficient prediction model to obtain first infinite dilution activity coefficients of the binary components corresponding to different simulation temperatures; for a thermodynamic model corresponding to the binary component, establishing an objective function based on the thermodynamic model and the first infinite dilution activity coefficient; the binary interaction parameters of the thermodynamic model are initialized, the minimum value of the target function is iteratively solved based on a preset optimization algorithm, and the target binary interaction parameters are determined under the condition that iteration stopping conditions are met. The problem of large deviation between simulation and reality caused by lack of binary interaction parameters in a thermodynamic model is solved, efficient estimation of the binary interaction parameters is achieved, and therefore the accuracy of chemical simulation is improved.

Description

Technical Field

[0001] The present invention relates to the field of chemical process simulation, and in particular to a method, device and equipment for determining binary interaction parameters of a thermodynamic model. Background Art

[0002] Chemical process simulation is to reproduce the actual production process on the computer by establishing a mathematical model to obtain detailed material balance and energy balance data for the entire process or unit process. It mainly includes important parameters such as raw material consumption, utility consumption, product composition and quality. Chemical process simulation is divided into steady-state simulation and dynamic simulation. Dynamic simulation refers to the change of all parameters over time during the simulation process. It is mainly used for the analysis of process dynamic characteristics, the formulation of control plans, the optimization of start-up and shutdown plans, and the development of operator training software.

[0003] Thermodynamic models affect physical parameters such as phase equilibrium and enthalpy and entropy, and are an important part of chemical simulation. However, many thermodynamic models lack binary interaction parameters, resulting in large deviations between simulation and reality.

[0004] Currently, experimental data are usually used to estimate binary interaction parameters. This method requires a large amount of data and is difficult to apply to most substances. Summary of the invention

[0005] The present invention provides a method, device and equipment for determining binary interaction parameters of a thermodynamic model to solve the problem of large deviation between simulation and reality due to lack of binary interaction parameters in the thermodynamic model, and realize efficient estimation of binary interaction parameters of the thermodynamic model.

[0006] According to one aspect of the present invention, a method for determining binary interaction parameters of a thermodynamic model is provided, comprising:

[0007] In a chemical process simulation, molecular structure data of any binary component is obtained, and the molecular structure data and a plurality of simulation temperatures are input into a pre-trained activity coefficient prediction model to obtain a first infinite dilution activity coefficient of the binary component corresponding to the plurality of simulation temperatures;

[0008] For the thermodynamic model corresponding to the binary component, establishing an objective function based on the thermodynamic model and the first infinite dilution activity coefficient, the objective function being used to measure the difference between the first infinite dilution activity coefficient and a second infinite dilution activity coefficient, the second infinite dilution activity coefficient being determined based on the thermodynamic model;

[0009] Initialize the binary interaction parameters of the thermodynamic model, iteratively optimize the binary interaction parameters based on a preset optimization algorithm to minimize the function value of the objective function, and determine the target binary interaction parameters of the thermodynamic model when an iteration stop condition is met.

[0010] According to another aspect of the present invention, there is provided a device for determining binary interaction parameters of a thermodynamic model, comprising:

[0011] A first infinite dilution activity coefficient prediction module, which obtains molecular structure data of any binary component during a chemical process simulation, inputs the molecular structure data and a plurality of simulation temperatures into a pre-trained activity coefficient prediction model, and obtains a first infinite dilution activity coefficient of the binary component corresponding to the plurality of simulation temperatures;

[0012] an objective function establishment module, for establishing an objective function for a thermodynamic model corresponding to the binary component based on the thermodynamic model and the first infinite dilution activity coefficient, wherein the objective function is used to measure the difference between the first infinite dilution activity coefficient and a second infinite dilution activity coefficient, wherein the second infinite dilution activity coefficient is determined based on the thermodynamic model;

[0013] The target binary interaction parameter determination module is used to initialize the binary interaction parameters of the thermodynamic model, iteratively optimize the binary interaction parameters based on a preset optimization algorithm to minimize the function value of the objective function, and determine the target binary interaction parameters of the thermodynamic model when the iteration stop condition is met.

[0014] According to another aspect of the present invention, an electronic device is provided, the electronic device comprising:

[0015] at least one processor; and

[0016] a memory communicatively connected to the at least one processor; wherein,

[0017] The memory stores a computer program executable by the at least one processor, and the computer program is executed by the at least one processor so that the at least one processor can execute the method for determining binary interaction parameters of a thermodynamic model described in any embodiment of the present invention.

[0018] According to another aspect of the present invention, a computer-readable storage medium is provided, wherein the computer-readable storage medium stores computer instructions, and the computer instructions are used to enable a processor to implement the method for determining binary interaction parameters of a thermodynamic model described in any embodiment of the present invention when executed.

[0019] The technical solution of the embodiment of the present invention is to obtain the molecular structure data of any binary component during the chemical process simulation, input the molecular structure data and multiple simulation temperatures into the pre-trained activity coefficient prediction model, and obtain the first infinite dilution activity coefficient of the binary component corresponding to the multiple simulation temperatures; for the thermodynamic model corresponding to the binary component, establish an objective function based on the thermodynamic model and the first infinite dilution activity coefficient, and the objective function is used to measure the difference between the first infinite dilution activity coefficient and the second infinite dilution activity coefficient, and the second infinite dilution activity coefficient is determined based on the thermodynamic model; initialize the binary interaction parameters of the thermodynamic model, iteratively optimize the binary interaction parameters based on a preset optimization algorithm to minimize the function value of the objective function, and determine the target binary interaction parameters of the thermodynamic model when the iteration stop condition is met. The problem of large deviation between simulation and reality due to the lack of binary interaction parameters in the thermodynamic model is solved, and efficient estimation of binary interaction parameters of the thermodynamic model is achieved, thereby improving the accuracy of chemical simulation.

[0020] It should be understood that the contents described in this section are not intended to identify the key or important features of the embodiments of the present invention, nor are they intended to limit the scope of the present invention. Other features of the present invention will become easily understood through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0021] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0022] Figure 1 It is a flow chart of a method for determining binary interaction parameters of a thermodynamic model provided in the first embodiment of the present invention;

[0023] Figure 2 It is a structural schematic diagram of a device for determining binary interaction parameters of a thermodynamic model provided in the second embodiment of the present invention;

[0024] Figure 3 It is a structural schematic diagram of an electronic device provided in Embodiment 3 of the present invention. DETAILED DESCRIPTION

[0025] In order to enable those skilled in the art to better understand the scheme of the present invention, the technical scheme in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work should fall within the scope of protection of the present invention.

[0026] It should be noted that the terms "first infinite dilution activity coefficient", "second infinite dilution activity coefficient", etc. in the specification and claims of the present invention and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchanged where appropriate, so that the embodiments of the present invention described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions, for example, a process, method, system, product or apparatus comprising a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or apparatus.

[0027] Embodiment 1

[0028] Figure 1 This is a flow chart of a method for determining binary interaction parameters of a thermodynamic model provided in the first embodiment of the present invention. This embodiment is applicable to the case of determining the required binary interaction parameters of a thermodynamic model in a chemical process simulation process. The method can be executed by a device for determining binary interaction parameters of a thermodynamic model. The device for determining binary interaction parameters of a thermodynamic model can be implemented in the form of hardware and / or software. The device for determining binary interaction parameters of a thermodynamic model can be configured in a computer. Figure 1 As shown, the method includes:

[0029] S110. During the chemical process simulation, the molecular structure data of any binary component is obtained, and the molecular structure data and a plurality of simulation temperatures are input into a pre-trained activity coefficient prediction model to obtain a first infinite dilution activity coefficient of the binary component corresponding to the plurality of simulation temperatures.

[0030] Among them, molecular structure data refers to the molecular structure data of any binary component. Specifically, the molecular structure data includes one or more of the molecular topological index, molecular connectivity index, molecular shape index, isotonic volume and eccentricity factor. The molecular graph is a topological expression of the molecular structure, and its vertices and edges correspond to atoms and chemical bonds in the molecular structure, respectively. Based on the theory of graph theory, the molecular graph properties such as the vertex degree, connectivity, and atom type of atoms can be described by calculating the molecular topological index. The molecular connectivity index is used to quantify the degree of branching of the alkane molecular structure and has a strong descriptive ability for the molecular skeleton. The molecular shape index describes the shape and flexibility of the molecule in the topological graph. Isotonic volume and eccentricity factor are used to characterize the local properties of the molecule.

[0031] Wherein, the simulation temperature refers to the temperature required for chemical process simulation, which is selected by a person skilled in the art within the temperature range of chemical process simulation according to the simulated chemical process, and is not limited here. In this embodiment, during the chemical process simulation, the molecular structure data of any binary component is obtained, and multiple groups of input parameters are formed based on the molecular structure data and multiple simulation temperatures, each group of input parameters includes molecular structure data and a simulation temperature, and the multiple input groups are respectively input into the pre-trained activity coefficient prediction model for prediction, and the first infinite dilution activity coefficient of the binary component corresponding to the multiple simulation temperatures is obtained. Wherein, the first infinite dilution activity coefficient refers to the infinite dilution activity coefficient predicted by the activity coefficient prediction model, and the first infinite dilution activity coefficient is used here as the accurate infinite dilution activity coefficient of the binary component. Specifically, the first infinite dilution activity coefficient includes the first infinite dilution activity coefficient of the first component and the first infinite dilution activity coefficient of the second component.

[0032] On the basis of the above embodiments, optionally, the training method of the activity coefficient prediction model includes: establishing a training database, the training database including molecular structure data of multiple binary components, multiple simulation temperatures and infinite dilution activity coefficients of the multiple binary components corresponding to the multiple simulation temperatures respectively; determining a data set based on the training database, and training a neural network model based on the data set to obtain an activity coefficient prediction model.

[0033] In this embodiment, the molecular structure data and simulation temperature of the binary components are selected as the input parameters of the neural network model, and the infinite dilution activity coefficient is used as the output parameter to establish a training database. Among them, the training database includes the molecular structure data of multiple binary components, multiple simulation temperatures and the first infinite dilution activity coefficients of multiple binary components corresponding to the multiple simulation temperatures; specifically, for each binary component, multiple groups of input parameters are formed based on the molecular structure data of the binary component and multiple simulation temperatures, each group of input parameters includes molecular structure data and a simulation temperature, and each group of input parameters corresponds to an infinite dilution activity coefficient. It can be understood that the infinite dilution activity coefficient in the training database is a true infinite dilution activity coefficient. Further. Data is selected from the training database to establish a data set, and the data set includes a training set, a validation set and a prediction set. It should be noted that due to the different scales of the data, normalization is required, and the sliding window method is used to divide the data set into multiple samples. Further, the neural network model is trained based on the training set, and the internal parameters of the neural network model are adjusted to minimize the mean square error between the predicted infinite dilution activity coefficient and the true infinite dilution activity coefficient; the performance of the neural network model at different training stages is evaluated based on the validation set, so as to adjust the hyperparameters in the neural network model and obtain the activity coefficient model; the activity coefficient model after training is evaluated based on the prediction set. The neural network model can be a GA-BP neural network model.

[0034] The embodiment of the present invention uses a neural network model to use two-dimensional structural data of molecules to predict infinite dilution activity coefficients, which has higher prediction accuracy and helps to distinguish compounds with similar compositions.

[0035] S120. For the thermodynamic model corresponding to the binary component, establish an objective function based on the thermodynamic model and the first infinite dilution activity coefficient, wherein the objective function is used to measure the difference between the first infinite dilution activity coefficient and the second infinite dilution activity coefficient, and the second infinite dilution activity coefficient is determined based on the thermodynamic model.

[0036] Among them, the thermodynamic model is an activity coefficient model, such as the NRTL (non-random two liquid) model, the UNIQUAC model, etc. In this embodiment, the thermodynamic model corresponding to the binary component is selected for different binary components. It can be understood that the selection of the thermodynamic model of the binary component depends on many factors, including the composition of the binary component, the interaction between the components, the physical state of the binary component (solid, liquid or gaseous) and the required prediction accuracy, etc. Therefore, for different binary components, it is necessary to select the thermodynamic model corresponding to the binary component. Further, an objective function is established based on the thermodynamic model and the first infinite dilution activity coefficient, wherein the objective function is used to measure the difference between the first infinite dilution activity coefficient and the second infinite dilution activity coefficient determined based on the thermodynamic model.

[0037] On the basis of the above embodiment, optionally, establishing the objective function based on the thermodynamic model and the first infinite dilution activity coefficient includes: determining the second infinite dilution activity coefficient of the component based on the thermodynamic model; for any component in the binary components, determining the infinite dilution activity coefficient difference of the component based on the first infinite dilution activity coefficient and the second infinite dilution activity coefficient of the component; and determining the objective function based on the infinite dilution activity coefficient difference of the first component and the infinite dilution activity coefficient difference of the second component.

[0038] In this embodiment, the second infinite dilution activity coefficient is determined based on the thermodynamic model, wherein the second infinite dilution activity coefficient is determined by the thermodynamic model, and the second infinite dilution activity coefficient includes the second infinite dilution activity coefficient of the first component and the second infinite dilution activity coefficient of the second component. Exemplarily, taking the NRTL model as an example, the second infinite dilution activity coefficient is calculated as follows:

[0039] ;

[0040] ;

[0041] in, represents the second infinite dilution activity coefficient of the first component, represents the second infinite dilution activity coefficient of the second component, G and is an interaction parameter related to the thermodynamic properties of the binary components. τ and G are calculated using the NRTL binary interaction parameters as follows:

[0042] ;

[0043] ;

[0044] ;

[0045] ;

[0046] ;

[0047] ;

[0048] in, , , , , , , , , , , and is a binary interaction parameter, T represents the simulation temperature, is a non-random parameter, reflecting the non-randomness of the molecular interactions in the binary components. It should be noted that c is a constant and = , , , , , and Usually 0.

[0049] In this embodiment, the infinite dilution activity coefficient difference of the first component is determined based on the first infinite dilution activity coefficient of the first component and the second infinite dilution activity coefficient of the first component; the infinite dilution activity coefficient difference of the second component is determined based on the first infinite dilution activity coefficient of the second component and the second infinite dilution activity coefficient of the second component; and the objective function is determined based on the infinite dilution activity coefficient difference of the first component and the infinite dilution activity coefficient difference of the second component.

[0050] For example, taking the NRTL model as an example, the objective function is as follows:

[0051] ;

[0052] Where n represents n sets of simulation temperatures and the first infinite dilution activity coefficient, represents the simulated temperature of the i-th group among n groups of simulated temperatures and the first infinite dilution activity coefficient, is the natural logarithm of the second infinite dilution activity coefficient of the first component corresponding to the simulation temperature of the i-th group, represents the natural logarithm of the first infinite dilution activity coefficient of the first component corresponding to the simulation temperature of the i-th group, represents the natural logarithm of the second infinite dilution activity coefficient of the second component corresponding to the simulation temperature of the i-th group, Represents the natural logarithm of the first infinite dilution activity coefficient of the second component corresponding to the simulation temperature of the i-th group.

[0053] In some embodiments, optionally, the method further includes: obtaining a range of binary interaction parameters; transforming the objective function based on the range of the binary interaction parameters to obtain a transformed objective function; the binary interaction parameters in the transformed objective function have the same order of magnitude.

[0054] It is understandable that due to the different orders of magnitude of the binary interaction parameters, it is easy for the value of the binary interaction parameter with a larger order of magnitude to be close to the initial value. Therefore, the orders of magnitude of the binary interaction parameters need to be unified so that the binary interaction parameters are at the same order of magnitude.

[0055] In this embodiment, the range of the binary interaction parameter is obtained, the order of magnitude of the binary interaction parameter is determined based on the range of the binary interaction parameter, and the benchmark function is transformed based on the order of magnitude of the binary interaction parameter to obtain a transformed objective function; wherein, the order of magnitude of the binary interaction parameters in the transformed objective function is the same.

[0056] For example, taking the NRTL model as an example, since the ranges of parameter a and parameter b are different, generally the range of a is -100 to 100, and the range of b is -30000 to 30000, directly using the above objective function for regression solution may easily lead to the value of parameter b, which is of a larger order of magnitude, being close to the initial value. Considering that the contributions of a and b / T to the NRTL model are similar, the above objective function is transformed so that parameter b and parameter a are in the same order of magnitude. The transformed objective function is as follows:

[0057] .

[0058] It should be noted that if the binary interaction parameters are solved by the transformed objective function, the solved binary interaction parameters need to be reversely transformed to obtain the actual binary interaction parameters. For example, taking the NRTL model as an example, the actual parameter b needs to be multiplied by 300.

[0059] S130, initializing the binary interaction parameters of the thermodynamic model, iteratively optimizing the binary interaction parameters based on a preset optimization algorithm to minimize the function value of the objective function, and determining the target binary interaction parameters of the thermodynamic model when an iteration stop condition is met.

[0060] In this embodiment, the binary interaction parameters in the thermodynamic model are initialized, and the binary interaction parameters are iteratively optimized based on a preset optimization algorithm to minimize the function value of the objective function. When the iteration stop condition is met, the target binary interaction parameters of the thermodynamic model of the binary interaction parameters that meet the iteration stop condition are set. The iteration stop condition may be when the change or gradient of the objective function is less than a preset tolerance, and the iteration stop condition may also be when the number of iterative solutions is greater than a preset maximum number of iterations. The preset optimization algorithm may be the BFGS method.

[0061] On the basis of the above embodiment, optionally, the binary interaction parameters are iteratively optimized based on a preset optimization algorithm to minimize the function value of the objective function, and when an iteration stop condition is met, the target binary interaction parameters of the thermodynamic model are determined, including: iteratively executing the following steps, and when the function value of the objective function and / or the number of iterations meet the iteration stop condition, the binary interaction parameters of the current round are determined as the target binary interaction parameters of the thermodynamic model: determining the function value of the objective function of the current iteration round based on multiple simulation temperatures, the first infinite dilution activity coefficients of the binary components corresponding to the multiple simulation temperatures, and the binary interaction parameters of the current iteration round; updating the binary interaction parameters based on the preset optimization algorithm; wherein the updated binary interaction parameters are used as the binary interaction parameters of the next iteration round.

[0062] In this embodiment, the process of iteratively solving the target binary interaction parameters of the thermodynamic model is as follows:

[0063] 1) Repeat the above steps 2)-3) to continuously iterate and update the binary interaction parameters until the iteration stop condition is met, and the binary interaction parameters of the current round are determined as the target binary interaction parameters of the thermodynamic model. The iteration stop conditions usually include two: one is when the change or gradient of the function value of the objective function is less than the preset tolerance; the other is when the number of iterations reaches the preset maximum number of iterations

[0064] 2) Substitute multiple simulation temperatures, the first infinite dilution activity coefficients of the binary components corresponding to the multiple simulation temperatures, and the binary interaction parameters of the current iteration round into the objective function for solving, and obtain the function value of the objective function of the current iteration round.

[0065] It can be understood that the function value of the objective function of the current iteration round represents the difference or error between the second infinite dilution activity coefficient and the first infinite dilution activity coefficient determined by the thermodynamic model under the binary interaction parameters of the current iteration round.

[0066] 3) Using a preset optimization algorithm to optimize and update the binary interaction parameters, so that the function value of the objective function is reduced as much as possible, so that the second infinite dilution activity coefficient is as close as possible to the first infinite dilution activity coefficient; it can be understood that in the present invention, the first infinite dilution activity coefficient is used as the accurate infinite dilution activity coefficient, and the closer the second infinite dilution activity coefficient is to the first infinite dilution activity coefficient, the smaller the error between the two, and the more accurate the binary interaction parameters. The updated binary interaction parameters will be used as the input of the next iteration round.

[0067] The technical solution of this embodiment is to obtain the molecular structure data of any binary component during the chemical process simulation, input the molecular structure data and multiple simulation temperatures into the pre-trained activity coefficient prediction model, and obtain the first infinite dilution activity coefficient of the binary component corresponding to the multiple simulation temperatures; for the thermodynamic model corresponding to the binary component, establish an objective function based on the thermodynamic model and the first infinite dilution activity coefficient, and the objective function is used to measure the difference between the first infinite dilution activity coefficient and the second infinite dilution activity coefficient, and the second infinite dilution activity coefficient is determined based on the thermodynamic model; initialize the binary interaction parameters of the thermodynamic model, iteratively optimize the binary interaction parameters based on the preset optimization algorithm to minimize the function value of the objective function, and determine the target binary interaction parameters of the thermodynamic model when the iteration stop condition is met. The problem of large deviation between simulation and reality due to the lack of binary interaction parameters in the thermodynamic model is solved, and efficient estimation of binary interaction parameters of the thermodynamic model is achieved, thereby improving the accuracy of chemical simulation.

[0068] Embodiment 2

[0069] Figure 2 Schematic diagram of a device for determining binary interaction parameters of a thermodynamic model provided by the second embodiment of the present invention. Figure 2 As shown, the device comprises:

[0070] The first infinite dilution activity coefficient prediction module 210 obtains molecular structure data of any binary component during the chemical process simulation, inputs the molecular structure data and a plurality of simulation temperatures into a pre-trained activity coefficient prediction model, and obtains a first infinite dilution activity coefficient of the binary component corresponding to the plurality of simulation temperatures;

[0071] An objective function establishing module 220 is used to establish an objective function for the thermodynamic model corresponding to the binary component based on the thermodynamic model and the first infinite dilution activity coefficient, wherein the objective function is used to measure the difference between the first infinite dilution activity coefficient and a second infinite dilution activity coefficient, wherein the second infinite dilution activity coefficient is determined based on the thermodynamic model;

[0072] The target binary interaction parameter determination module 230 is used to initialize the binary interaction parameters of the thermodynamic model, iteratively optimize the binary interaction parameters based on a preset optimization algorithm to minimize the function value of the objective function, and determine the target binary interaction parameters of the thermodynamic model when the iteration stop condition is met.

[0073] The technical solution of this embodiment is to obtain the molecular structure data of any binary component during the chemical process simulation, input the molecular structure data and multiple simulation temperatures into the pre-trained activity coefficient prediction model, and obtain the first infinite dilution activity coefficient of the binary component corresponding to the multiple simulation temperatures; for the thermodynamic model corresponding to the binary component, establish an objective function based on the thermodynamic model and the first infinite dilution activity coefficient, and the objective function is used to measure the difference between the first infinite dilution activity coefficient and the second infinite dilution activity coefficient, and the second infinite dilution activity coefficient is determined based on the thermodynamic model; initialize the binary interaction parameters of the thermodynamic model, iteratively optimize the binary interaction parameters based on the preset optimization algorithm to minimize the function value of the objective function, and determine the target binary interaction parameters of the thermodynamic model when the iteration stop condition is met. The problem of large deviation between simulation and reality due to the lack of binary interaction parameters in the thermodynamic model is solved, and efficient estimation of binary interaction parameters of the thermodynamic model is achieved, thereby improving the accuracy of chemical simulation.

[0074] Based on the above embodiment, optionally, the device includes a training module of an activity coefficient prediction model, which is used to:

[0075] Establishing a training database, the training database comprising molecular structure data of a plurality of binary components, a plurality of simulation temperatures, and infinite dilution activity coefficients of the plurality of binary components corresponding to the plurality of simulation temperatures respectively;

[0076] A data set is determined based on the training database, and a neural network model is trained based on the data set to obtain an activity coefficient prediction model.

[0077] Based on the above embodiment, optionally, the molecular structure data includes one or more of a molecular topology index, a molecular connectivity index, a molecular shape index, an isotonic volume and an eccentricity factor.

[0078] Based on the above embodiment, optionally, the objective function establishment module 220 is used to:

[0079] determining a second infinite dilution activity coefficient of the component based on the thermodynamic model;

[0080] For any one of the binary components, determining an infinite dilution activity coefficient difference of the component based on a first infinite dilution activity coefficient and a second infinite dilution activity coefficient of the component;

[0081] The objective function is determined based on the infinite dilution activity coefficient difference of the first component and the infinite dilution activity coefficient difference of the second component. Based on the above embodiment, optionally, the device also includes an objective function transformation module, which is used to:

[0082] Get the range of binary interaction parameters;

[0083] The objective function is transformed based on the range of the binary interaction parameter to obtain a transformed objective function; the binary interaction parameters in the transformed objective function have the same order of magnitude.

[0084] Based on the above embodiment, optionally, the target binary interaction parameter determination module 230 is used to:

[0085] The following steps are iteratively performed, and when the function value and / or the number of iterations of the objective function meet the iteration stop condition, the binary interaction parameter of the current round is determined as the target binary interaction parameter of the thermodynamic model:

[0086] Determine a function value of an objective function of a current iteration round based on a plurality of simulation temperatures, first infinite dilution activity coefficients of the binary components corresponding to the plurality of simulation temperatures, and a binary interaction parameter of a current iteration round;

[0087] The binary interaction parameters are updated based on the preset optimization algorithm; wherein the updated binary interaction parameters are used as the binary interaction parameters for the next iteration round.

[0088] Based on the above embodiment, optionally, the thermodynamic model is an activity coefficient model.

[0089] The device for determining binary interaction parameters of a thermodynamic model provided in an embodiment of the present invention can execute the method for determining binary interaction parameters of a thermodynamic model provided in any embodiment of the present invention, and has functional modules and beneficial effects corresponding to the execution method.

[0090] Embodiment 3

[0091] Figure 3 1 is a schematic diagram of the structure of an electronic device provided in Embodiment 3 of the present invention. The electronic device 10 is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, 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 processing, cellular phones, smart phones, 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 examples and are not intended to limit the implementation of the present invention described and / or required herein.

[0092] like Figure 3 As shown, the electronic device 10 includes at least one processor 11, and a memory connected to the at least one processor 11 in communication, such as a read-only memory (ROM) 12, a random access memory (RAM) 13, etc., wherein the memory stores a computer program that can be executed by at least one processor, and the processor 11 can perform various appropriate actions and processes according to the computer program stored in the read-only memory (ROM) 12 or the computer program loaded from the storage unit 18 to the random access memory (RAM) 13. In the RAM 13, various programs and data required for the operation of the electronic device 10 can also be stored. The processor 11, ROM 12 and RAM 13 are connected to each other through a bus 14. An input / output (I / O) interface 15 is also connected to the bus 14.

[0093] A number of components in the electronic device 10 are connected to the I / O interface 15, including: an input unit 16, such as a keyboard, a mouse, etc.; an output unit 17, such as various types of displays, speakers, etc.; a storage unit 18, such as a disk, an optical disk, etc.; and a communication unit 19, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 19 allows the electronic device 10 to exchange information / data with other devices through a computer network such as the Internet and / or various telecommunication networks.

[0094] The processor 11 may be a variety of general and / or special processing components with processing and computing capabilities. Some examples of the processor 11 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various special artificial intelligence (AI) computing chips, various processors running machine learning model algorithms, a digital signal processor (DSP), and any appropriate processor, controller, microcontroller, etc. The processor 11 executes the various methods and processes described above, such as a method for determining binary interaction parameters of a thermodynamic model.

[0095] In some embodiments, the method for determining the binary interaction parameters of the thermodynamic model may be implemented as a computer program, which is tangibly contained in a computer-readable storage medium, such as a storage unit 18. In some embodiments, part or all of the computer program may be loaded and / or installed on the electronic device 10 via the ROM 12 and / or the communication unit 19. When the computer program is loaded into the RAM 13 and executed by the processor 11, one or more steps of the method for determining the binary interaction parameters of the thermodynamic model described above may be performed. Alternatively, in other embodiments, the processor 11 may be configured to execute the method for determining the binary interaction parameters of the thermodynamic model in any other appropriate manner (e.g., by means of firmware).

[0096] Various implementations of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), systems on chips (SOCs), load programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various implementations can include: being implemented in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which can be a special purpose or general purpose programmable processor that can receive data and instructions from a storage system, at least one input device, and at least one output device, and transmit data and instructions to the storage system, the at least one input device, and the at least one output device.

[0097] The computer program for implementing the method for determining the binary interaction parameters of the thermodynamic model of the present invention can be written in any combination of one or more programming languages. These computer programs can be provided to a processor of a general-purpose computer, a special-purpose computer or other programmable data processing device, so that when the computer program is executed by the processor, the functions / operations specified in the flow chart and / or the block diagram are implemented. The computer program can be executed entirely on the machine, partially on the machine, partially on the machine as an independent software package and partially on a remote machine, or completely on a remote machine or server.

[0098] Embodiment 4

[0099] Embodiment 4 of the present invention further provides a computer-readable storage medium, wherein the computer-readable storage medium stores computer instructions, and the computer instructions are used to enable a processor to execute a method for determining binary interaction parameters of a thermodynamic model, the method comprising:

[0100] In a chemical process simulation, molecular structure data of any binary component is obtained, and the molecular structure data and a plurality of simulation temperatures are input into a pre-trained activity coefficient prediction model to obtain a first infinite dilution activity coefficient of the binary component corresponding to the plurality of simulation temperatures;

[0101] For the thermodynamic model corresponding to the binary component, establishing an objective function based on the thermodynamic model and the first infinite dilution activity coefficient, the objective function being used to measure the difference between the first infinite dilution activity coefficient and a second infinite dilution activity coefficient, the second infinite dilution activity coefficient being determined based on the thermodynamic model;

[0102] Initialize the binary interaction parameters of the thermodynamic model, iteratively optimize the binary interaction parameters based on a preset optimization algorithm to minimize the function value of the objective function, and determine the target binary interaction parameters of the thermodynamic model when an iteration stop condition is met.

[0103] In the context of the present invention, a computer-readable storage medium may be a tangible medium that may contain or store a computer program for use by or in conjunction with an instruction execution system, device, or equipment. A computer-readable storage medium may include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, devices, or equipment, or any suitable combination of the foregoing. Alternatively, a computer-readable storage medium may be a machine-readable signal medium. A more specific example of a machine-readable storage medium may include an electrical connection based on one or more lines, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0104] To provide interaction with a user, the systems and techniques described herein may be implemented on an electronic device having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and a pointing device (e.g., a mouse or trackball) through which the user can provide input to the electronic device. Other types of devices may also be used to provide interaction with the user; for example, the feedback provided to the user may be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user may be received in any form (including acoustic input, voice input, or tactile input).

[0105] The systems and techniques described herein may be implemented in a computing system that includes backend components (e.g., as a data server), or a computing system that includes middleware components (e.g., an application server), or a computing system that includes frontend components (e.g., a user computer with a graphical user interface or a web browser through which a user can interact with implementations of the systems and techniques described herein), or a computing system that includes any combination of such backend components, middleware components, or frontend components. The components of the system may be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: a local area network (LAN), a wide area network (WAN), a blockchain network, and the Internet.

[0106] A computing system may include a client and a server. The client and the server are generally remote from each other and usually interact through a communication network. The client and server relationship is generated by computer programs running on the corresponding computers and having a client-server relationship with each other. The server may be a cloud server, also known as a cloud computing server or cloud host, which is a host product in the cloud computing service system to solve the defects of difficult management and weak business scalability in traditional physical hosts and VPS services.

[0107] It should be understood that the various forms of processes shown above can be used to reorder, add or delete steps. For example, the steps described in the present invention can be executed in parallel, sequentially or in different orders, as long as the desired results of the technical solution of the present invention can be achieved, and this document does not limit this.

[0108] The above specific implementations do not constitute a limitation on the protection scope of the present invention. It should be understood by those skilled in the art that various modifications, combinations, sub-combinations and substitutions can be made according to design requirements and other factors. Any modification, equivalent substitution and improvement made within the spirit and principle of the present invention should be included in the protection scope of the present invention.

Claims

1. A method for determining binary interaction parameters of a thermodynamic model, characterized in that: include: In a chemical process simulation, molecular structure data of any binary component is obtained, and the molecular structure data and a plurality of simulation temperatures are input into a pre-trained activity coefficient prediction model to obtain a first infinite dilution activity coefficient of the binary component corresponding to the plurality of simulation temperatures; For the thermodynamic model corresponding to the binary component, establishing an objective function based on the thermodynamic model and the first infinite dilution activity coefficient, the objective function being used to measure the difference between the first infinite dilution activity coefficient and a second infinite dilution activity coefficient, the second infinite dilution activity coefficient being determined based on the thermodynamic model; Initialize the binary interaction parameters of the thermodynamic model, iteratively optimize the binary interaction parameters based on a preset optimization algorithm to minimize the function value of the objective function, and determine the target binary interaction parameters of the thermodynamic model when an iteration stop condition is met.

2. The method for determining binary interaction parameters of a thermodynamic model according to claim 1, characterized in that: The training method of the activity coefficient prediction model comprises: Establishing a training database, the training database comprising molecular structure data of a plurality of binary components, a plurality of simulation temperatures, and infinite dilution activity coefficients of the binary components corresponding to the plurality of simulation temperatures; A data set is determined based on the training database, and a neural network model is trained based on the data set to obtain an activity coefficient prediction model.

3. The method for determining binary interaction parameters of a thermodynamic model according to claim 2, characterized in that: The molecular structure data include one or more of a molecular topological index, a molecular connectivity index, a molecular shape index, an isotonic volume and an eccentricity factor.

4. The method for determining binary interaction parameters of a thermodynamic model according to claim 1, characterized in that: The establishing of an objective function based on the thermodynamic model and the first infinite dilution activity coefficient comprises: determining a second infinite dilution activity coefficient of the component based on the thermodynamic model; For any one of the binary components, determining an infinite dilution activity coefficient difference of the component based on a first infinite dilution activity coefficient and a second infinite dilution activity coefficient of the component; An objective function is determined based on the infinite dilution activity coefficient difference of the first component and the infinite dilution activity coefficient difference of the second component.

5. The method for determining binary interaction parameters of a thermodynamic model according to claim 4, characterized in that: The method further comprises: Get the range of binary interaction parameters; The objective function is transformed based on the range of the binary interaction parameter to obtain a transformed objective function; the binary interaction parameters in the transformed objective function have the same order of magnitude.

6. The method for determining binary interaction parameters of a thermodynamic model according to claim 1, characterized in that: The iterative optimization of the binary interaction parameters based on a preset optimization algorithm to minimize the function value of the objective function, and determining the target binary interaction parameters of the thermodynamic model when an iteration stop condition is met, includes: The following steps are iteratively performed, and when the function value and / or the number of iterations of the objective function meet the iteration stop condition, the binary interaction parameter of the current round is determined as the target binary interaction parameter of the thermodynamic model: Determining a function value of an objective function of a current iteration round based on first infinite dilution activity coefficients of the binary components corresponding to a plurality of simulation temperatures, the plurality of simulation temperatures, and a binary interaction parameter of a current iteration round; The binary interaction parameters are updated based on the preset optimization algorithm; wherein the updated binary interaction parameters are used as the binary interaction parameters for the next iteration round.

7. The method for determining binary interaction parameters of a thermodynamic model according to claim 1, characterized in that: The thermodynamic model is an activity coefficient model.

8. A device for determining binary interaction parameters of a thermodynamic model, characterized in that: include: A first infinite dilution activity coefficient prediction module, which obtains molecular structure data of any binary component during a chemical process simulation, inputs the molecular structure data and a plurality of simulation temperatures into a pre-trained activity coefficient prediction model, and obtains a first infinite dilution activity coefficient of the binary component corresponding to the plurality of simulation temperatures; an objective function establishment module, for establishing an objective function for a thermodynamic model corresponding to the binary component based on the thermodynamic model and the first infinite dilution activity coefficient, wherein the objective function is used to measure the difference between the first infinite dilution activity coefficient and a second infinite dilution activity coefficient, wherein the second infinite dilution activity coefficient is determined based on the thermodynamic model; The target binary interaction parameter determination module is used to initialize the binary interaction parameters of the thermodynamic model, iteratively optimize the binary interaction parameters based on a preset optimization algorithm to minimize the function value of the objective function, and determine the target binary interaction parameters of the thermodynamic model when the iteration stop condition is met.

9. An electronic device, characterized in that: The electronic device comprises: at least one processor; and a memory communicatively connected to the at least one processor; wherein, The memory stores a computer program executable by the at least one processor, and the computer program is executed by the at least one processor so that the at least one processor can perform the method for determining binary interaction parameters of a thermodynamic model according to any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer instructions, and the computer instructions are used to enable a processor to implement the method for determining binary interaction parameters of a thermodynamic model according to any one of claims 1 to 7 when executed.

Images