Crude oil molecular model driving-based atmospheric distillation dynamic mixing model construction method

Abstract

The invention belongs to the technical field of petrochemical engineering, and discloses a construction method of an atmospheric distillation dynamic mixing model based on crude oil molecular model driving. Calculating distillation physical property parameters related to molecular pure substances and a distillation process in the crude oil molecular model in a stable state, and calculating distillation related physical property parameters of the mixture according to a mixing rule; according to a material balance equation, a phase balance equation, a mole fraction normalization equation and a heat balance equation, establishing mechanism models for the whole primary distillation tower and the tower top and the tower bottom of the atmospheric distillation tower; establishing an agent model for the residual main body part of the normal-pressure rectifying tower according to the agent model; a crude oil atmospheric distillation process dynamic mixing model with a mechanism model-proxy model-mechanism model is built according to a sequence structure of a primary distillation tower, an atmospheric distillation tower main body part, an atmospheric distillation tower top and a tower bottom. And the constructed model can be used for simulating and calculating to obtain the specific molecular composition distribution of the product.

Description

Technical Field

[0001] The invention relates to the technical field of petrochemical engineering, and in particular to a method for constructing a dynamic mixing model of atmospheric distillation driven by a crude oil molecular model. Background Art

[0002] The rise of green energy has alleviated the pollution caused by traditional energy and has an impact on the cost of traditional energy. Therefore, the traditional oil refining industry faces the dual pressure of environmental protection and efficiency improvement, and urgently needs to upgrade and transform its process. As one of the crude oil refining technologies, distillation occupies an important position in the crude oil processing process, and with the assistance of computer modeling and simulation technology, its process technology continues to innovate and develop. Through modeling and simulation, engineers can evaluate the optimal operating parameters of the distillation process under different conditions with the correct principles, and optimize and adjust the process according to the real-time situation of the simulation, so as to achieve the purpose of improving product quality and saving energy and reducing consumption. The modeling of the distillation process is based on a comprehensive physical property library. The mechanism model of mathematically modeling the distillation process through material and energy balance equations can simulate steady-state, multi-component, and multi-stage distillation processes.

[0003] However, in actual situations, the distillation process is a dynamic process affected by many factors. In order to fully understand the dynamic changes of the distillation process caused by different variables, the time variable is introduced into the material by using differential equations, and the heat balance equation is used to establish a distillation dynamic model. At present, the commercial software Aspen Dynamics can also perform dynamic simulation of the distillation process. For the atmospheric distillation process of crude oil, in order to reduce the complexity of dynamic calculations, crude oil is usually divided into virtual components according to the real boiling point curve for dynamic simulation calculations. However, there are disputes about the estimation of the key properties of virtual components, and it is impossible to intuitively obtain the dynamic changes of specific substances in the distillation process. If real components are used for dynamic calculation of the crude oil distillation process, not only can the dynamic changes of all components be intuitively obtained, but also it is conducive to the subsequent process simulation of the distillation products. However, crude oil is composed of thousands of independent complex mixtures including heteroatoms, and there are many variables in the entire distillation process. Therefore, its dynamic mathematical model is a complex nonlinear equation, and the entire calculation process needs to be simplified. When facing models with strong nonlinearity, high complexity, and large solution scale, surrogate models are often used instead of mechanism models for solution, and polynomial response surface, radial basis function, Gaussian process model and artificial neural network are common surrogate models. Among them, artificial neural network can excellently handle complex nonlinear relationships and multidimensional data, has strong nonlinear mapping ability, and has been applied to solve various problems.

[0004] With the increasing complexity of models and the requirements for model accuracy, hybrid models make full use of process mechanisms, data and prior knowledge to show better global performance compared to single models. With the continuous development of computer level and mathematical models, many works have shown that hybrid models can effectively reduce the complexity of models related to nonlinearity, uncertainty and multi-scale, and play an important role in complex dynamic systems in the field of fossil fuel energy. Summary of the invention

[0005] In view of the shortcomings of the prior art, the purpose of the present invention is to construct the physical properties related to distillation of each molecule in the crude oil molecular model mentioned in CN118298937A, and then build a dynamic hybrid model of atmospheric distillation based on the crude oil molecular model through hybrid modeling of mechanism model and proxy model.

[0006] The technical solution of the present invention is as follows: A method for constructing a dynamic mixing model of atmospheric distillation driven by a crude oil molecular model, comprising the following steps:

[0007] Calculate the distillation physical property parameters related to the distillation process of molecular pure substances in the crude oil molecular model under steady state, and calculate the distillation-related physical property parameters of the mixture according to the mixing rules;

[0008] According to the material balance equation, phase balance equation, mole fraction normalization equation and heat balance equation, a mechanism model is established for the entire primary distillation tower and the top and bottom of the atmospheric distillation tower.

[0009] Establish a proxy model for the remaining main part of the atmospheric distillation tower according to the proxy model;

[0010] According to the sequential structure of primary distillation tower-main part of atmospheric distillation tower-top and bottom of atmospheric distillation tower, a dynamic hybrid model of crude oil atmospheric distillation process with the structure of mechanism model-proxy model-mechanism model is built.

[0011] The calculation process involved in the dynamic mixing model of crude oil atmospheric distillation includes:

[0012] The crude oil molecular model involves the calculation of distillation-related physical property parameters of molecular pure substances and mixtures, and the obtained data constitutes a basic database for the construction of the mechanism model; the distillation-related physical property parameters include vapor phase enthalpy, liquid phase enthalpy, activity coefficient, vapor-liquid phase equilibrium constant and bubble point temperature;

[0013] Establish dynamic mechanism models for the top and bottom of the primary distillation tower and atmospheric distillation tower, and construct them according to the traditional material balance equation, phase balance equation, molar fraction normalization equation and heat balance equation;

[0014] The proxy model is constructed as a BP neural network with a three-layer network structure consisting of an input layer, a hidden layer and an output layer; the molar flow rate, temperature and pressure of each component of the atmospheric distillation tower feed are used as input units of the BP neural network, and the flow rate of the product stream and the molar fraction of each molecular weight are output units of the BP neural network.

[0015] The calculation method of the vapor phase enthalpy, liquid phase enthalpy, activity coefficient, vapor-liquid phase equilibrium constant and bubble point temperature is as follows:

[0016] The vapor phase enthalpy and liquid phase enthalpy calculation of pure substances is obtained by using commercial software to obtain the vapor phase enthalpy and liquid phase enthalpy values ​​of each molecule at different temperatures, which are then fitted into a temperature-dependent formula to obtain the constant term in the formula; the vapor phase enthalpy and liquid phase enthalpy of the mixture are calculated by the mixing rule;

[0017] The activity coefficient of each molecule is calculated by correlating the activity coefficient with temperature through fitting. The constant term in the correlation equation is obtained based on the activity coefficient at different temperatures and is used to calculate the activity coefficient at different temperatures.

[0018] The gas phase used in the dynamic mixing model of the atmospheric distillation process of crude oil is an ideal gas, and the liquid phase is a non-ideal solution system; the vapor-liquid phase equilibrium constant is calculated by the activity coefficient, the saturated vapor pressure and the current plate pressure, where the saturated vapor pressure is calculated by the Antoine equation and the current plate pressure is a constant;

[0019] The bubble point temperature is calculated using the Richmond iteration method.

[0020] The vapor phase product flow rate of the primary distillation tower is obtained by multiplying the vapor phase fraction obtained by Newton iteration calculation using the Rachford-Rice equation by the feed flow rate; the vapor phase flow rate calculation formula at the top and bottom of the atmospheric distillation tower is obtained by combining the material balance equation with the heat balance equation.

[0021] The proxy model is constructed as follows:

[0022] The proxy model is constructed using a BP neural network with a three-layer network structure consisting of an input layer, a hidden layer and an output layer; the molar flow rate, temperature and pressure of each component of the atmospheric distillation tower feed are used as the input units of the BP neural network, and the convergent and effective vapor phase molar flow rates of each component of the second plate of the atmospheric distillation tower and the liquid phase molar flow rates of each component of the j-1th plate are used as the output units of the BP neural network. It is assumed that the crude oil distillation tower has a total of j plates, and each plate is numbered 1, 2, 3...j from top to bottom.

[0023] The method for obtaining the training database and setting the training parameters in the proxy model are as follows:

[0024] To ensure the diversity and randomness of the training data set, 200 sample points were selected within the parameter-related range through Latin hypercube sampling, and Latin hypercube sampling was repeated every time the feed composition of the primary distillation tower was changed;

[0025] Through random division, 70% of the data set is set as the training sample set, and 30% is set as the verification sample set; the activation function of the hidden layer in the BP neural network is selected as the logarithmic function in the S-type function: logsing; the transfer function from the hidden layer to the output layer is the Purelin linear function; the BP neural network uses the Levenberg-Marquardt algorithm for training.

[0026] Furthermore, the maximum number of training iterations is set to 1000. The target value of the mean square error is 0.0003, the network learning rate is 0.002, the number of validation checks is 12, and the number of hidden layer nodes is determined by an empirical formula.

[0027] Since the construction of the mechanism model of the atmospheric distillation tower is mainly based on equilibrium equations such as material balance, energy balance and vapor-liquid phase equilibrium, in order to ensure the effectiveness of the constructed mechanism model and reduce the complexity of its calculation structure, the following assumptions are made for the mechanism model of the atmospheric distillation tower:

[0028] (1) The vapor and liquid phases on each theoretical plate are completely mixed;

[0029] (2) Ignore the heat loss inside the tower and the heat exchange with the outside;

[0030] (3) The temperature and pressure of the vapor and liquid phases in the distillation tower are consistent;

[0031] (4) The vapor phase storage on each theoretical plate is ignored;

[0032] (5) The pressure drop on each theoretical plate is the same.

[0033] Through the mechanism model and proxy model of the atmospheric distillation process of crude oil described in the present invention, the atmospheric distillation process of crude oil is simulated and its product composition is dynamically predicted. The feed of the model is a mixture of 152 real components consisting of the predetermined molecular model of crude oil including saturated fraction (S), aromatic fraction (A), resin (R) and asphaltene (As) and water molecules constructed in previous work. After calculating the relevant properties of each real component and the mixture, MATLAB / Simulink is used to establish a mechanism model for the top and bottom of the pre-flash tower (PF) and atmospheric distillation tower (ADU) based on certain assumptions. The proxy model constructed by the BP neural network is used to replace the remaining main body of the atmospheric distillation tower. The hybrid model constructed by the mechanism model and the proxy model can quickly and effectively predict the dynamic changes of molecules involved in the crude oil molecular model during the atmospheric distillation process.

[0034] Beneficial effects of the present invention: The dynamic mixing model of atmospheric distillation driven by the crude oil molecular model of the present invention performs dynamic modeling of atmospheric distillation based on the original molecular model mentioned in CN118298937A. While obtaining the specific molecular composition of the product, it can predict the dynamic changes of the molecules during the distillation process. The specific molecular composition distribution of the product is obtained through simulation and calculation of the dynamic mixing model of atmospheric distillation of crude oil, which can more conveniently carry out modeling simulation and product property evaluation of the subsequent production process, and the dynamic change trend of each molecule during the distillation process can also better guide the change of production operation parameters. When changing the type of raw oil produced, this model can also be used to predict its production results and guide how the operating parameters should be changed in the specific production process. BRIEF DESCRIPTION OF THE DRAWINGS

[0035] Figure 1 It is a structural composition diagram of a dynamic mixing model of a crude oil atmospheric distillation process constructed by the present invention;

[0036] Figure 2 It is a calculation flow chart of the hybrid model in the present invention; (a) is a schematic diagram of the overall process; (b) is a schematic diagram of the mechanism model of the primary distillation tower; (c) is a schematic diagram of the mechanism model of the top of the atmospheric distillation tower; (d) is a schematic diagram of the mechanism model of the bottom of the atmospheric distillation tower.

[0037] Figure 3 The specific operation scheme adopted by the embodiment of the present invention;

[0038] Figure 4The following are the dynamic change curves of the product stream composition in the embodiment of the present invention and the absolute errors of each component under the steady state; (a) is the change trend of each component of the vapor phase product at the top of the crude oil atmospheric distillation tower under operation scheme Ⅰ; (b) is the change trend of each component of the liquid phase product at the top of the crude oil atmospheric distillation tower under operation scheme Ⅰ; (c) is the change trend of each component of the liquid phase product at the bottom of the crude oil atmospheric distillation tower under operation scheme Ⅰ; (d) is the absolute error of each component of the vapor phase product at the top of the crude oil atmospheric distillation tower under operation scheme Ⅰ and the results of the commercial software; (e) is the absolute error of each component of the liquid phase product at the top of the crude oil atmospheric distillation tower under operation scheme Ⅰ and the results of the commercial software; (f) is the absolute error of each component of the liquid phase product at the bottom of the crude oil atmospheric distillation tower under operation scheme Ⅰ and the results of the commercial software;

[0039] Figure 5 The following are the dynamic change curves of the product stream composition after the operating parameters are disturbed in the embodiment of the present invention and the absolute errors of each component under the steady state; (a) is the change trend of each component of the vapor phase product at the top of the crude oil atmospheric distillation tower when the operating scheme is changed from Ⅰ to Ⅱ; (b) is the change trend of each component of the liquid phase product at the top of the crude oil atmospheric distillation tower when the operating scheme is changed from Ⅰ to Ⅱ; (c) is the change trend of each component of the liquid phase product at the bottom of the crude oil atmospheric distillation tower when the operating scheme is changed from Ⅰ to Ⅱ; (d) is the absolute error of each component of the vapor phase product at the top of the crude oil atmospheric distillation tower when the operating scheme is changed from Ⅰ to Ⅱ and the commercial software results; (e) is the absolute error of each component of the liquid phase product at the top of the crude oil atmospheric distillation tower when the operating scheme is changed from Ⅰ to Ⅱ and the commercial software results; (f) is the absolute error of each component of the liquid phase product at the bottom of the crude oil atmospheric distillation tower when the operating scheme is changed from Ⅰ to Ⅱ and the commercial software results;

[0040] Figure 6 The following are the dynamic change curves of the product stream composition after the oil type is changed in the embodiment of the present invention and the absolute errors of each component under the steady state; (a) is the change trend of each component of the vapor phase product at the top of the crude oil atmospheric distillation tower when the operation scheme is changed from Ⅱ to Ⅲ; (b) is the change trend of each component of the liquid phase product at the top of the crude oil atmospheric distillation tower when the operation scheme is changed from Ⅱ to Ⅲ; (c) is the change trend of each component of the liquid phase product at the bottom of the crude oil atmospheric distillation tower when the operation scheme is changed from Ⅱ to Ⅲ; (d) is the absolute error of each component of the vapor phase product at the top of the crude oil atmospheric distillation tower when the operation scheme is changed from Ⅱ to Ⅲ and the commercial software results; (e) is the absolute error of each component of the liquid phase product at the top of the crude oil atmospheric distillation tower when the operation scheme is changed from Ⅱ to Ⅲ and the commercial software results; (f) is the absolute error of each component of the liquid phase product at the bottom of the crude oil atmospheric distillation tower when the operation scheme is changed from Ⅱ to Ⅲ and the commercial software results;

[0041] Figure 7The following are probability histograms of the absolute errors of all molecules involved in the product streams under the three operating schemes in the embodiments of the present invention; (a) is a probability histogram of the absolute errors of the molecular content of the vapor phase product at the top of the crude oil atmospheric distillation tower under operating scheme I and the results of the commercial software; (b) is a probability histogram of the absolute errors of the molecular content of the liquid phase product at the top of the crude oil atmospheric distillation tower under operating scheme I and the results of the commercial software; (c) is a probability histogram of the absolute errors of the molecular content of the liquid phase product at the bottom of the crude oil atmospheric distillation tower under operating scheme I and the results of the commercial software; (d) is a probability histogram of the absolute errors of the molecular content of the vapor phase product at the top of the crude oil atmospheric distillation tower under the operating scheme changed from I to II and the results of the commercial software; (e) is a probability histogram of the absolute errors of the molecular content of the vapor phase product at the top of the crude oil atmospheric distillation tower under the operating scheme changed from I to II (f) is the probability histogram of the absolute error between the molecular content of the liquid phase product at the top of the crude oil atmospheric distillation tower and the commercial software result; (g) is the probability histogram of the absolute error between the molecular content of the vapor phase product at the top of the crude oil atmospheric distillation tower and the commercial software result when the operation scheme is changed from Ⅱ to Ⅲ; (h) is the probability histogram of the absolute error between the molecular content of the liquid phase product at the top of the crude oil atmospheric distillation tower and the commercial software result when the operation scheme is changed from Ⅱ to Ⅲ; (i) is the probability histogram of the absolute error between the molecular content of the liquid phase product at the bottom of the crude oil atmospheric distillation tower and the commercial software result when the operation scheme is changed from Ⅱ to Ⅲ. DETAILED DESCRIPTION

[0042] The embodiments of the present invention are described in detail below with reference to the accompanying drawings.

[0043] Figure 1 This is a structural composition diagram of the dynamic mixing model of the crude oil atmospheric distillation process constructed by the present invention. Figure 1 As shown in the figure, the feed is the crude oil that has been treated with electric desalting; the pre-flash tower PF is used as the crude oil primary distillation tower; the liquid product of the flash is changed in temperature and pressure by the heat exchanger HE, and then enters the atmospheric distillation tower ADU to complete the atmospheric distillation process of the crude oil, where P1 and P2 are the gas phase product and liquid phase product at the top of the ADU tower, respectively, P3 is the liquid phase product at the bottom of the ADU tower, and STEAM is the stripping steam. Therefore, a mechanism model is established for PF, an agent model is established for the main part of ADU, and a mechanism model is established for the top and bottom of ADU, thus forming a hybrid model with a structure of mechanism-agent-mechanism model as shown in the figure.

[0044] Figure 2 The calculation process sequence of the mixed model in the present invention is as follows. The liquid phase product at the bottom of the tower is calculated by the primary distillation tower mechanism model and flows to the crude oil atmospheric distillation tower proxy model. The vapor phase flow enters the tower top mechanism model, and the liquid phase flow enters the tower bottom mechanism model to complete the final calculation. Figure 2As shown in , the specific molecular composition distribution of crude oil is obtained through calculation of the crude oil molecular model, and then enters the mechanism model of the primary distillation tower, and calculates under the specified primary distillation temperature and pressure to obtain the liquid phase flow rate and specific molecular composition distribution at the bottom of the primary distillation tower. The feed temperature and pressure are set through the heat exchanger, and then the liquid phase product at the bottom of the primary distillation tower enters the proxy model of the main part of the crude oil atmospheric distillation tower under the conditions of this temperature and pressure and calculates to obtain the vapor phase flow rate and composition of the second plate of the crude oil atmospheric distillation tower and the liquid phase flow rate and composition of the j-1th plate, and enters the mechanism models of the top and bottom of the atmospheric distillation tower for calculation and simulation to obtain the final result.

[0045] Figure 3 The specific operation scheme adopted by the embodiment of the present invention. It mainly includes the crude oil type, flash temperature, feed temperature, feed pressure, cooling temperature, and the top pressure of the crude oil atmospheric distillation tower. When changing from operation scheme I to scheme II, the crude oil type does not change, and other conditions increase by 20. When changing from operation scheme II to scheme III, the crude oil type changes from OIL I to OIL II, and other conditions increase by 10.

[0046] Figure 4 It is the dynamic change curve of the composition of the product stream in the embodiment of the present invention, and the absolute error of each component in the steady state. It can be seen from Figures (a) to (c) that the molar fractions of the five components in the product stream reach a stable state after a period of time. Comparing the molar fractions of the five components in the product material under the stable state of the mixed model with the simulation results of Aspen Plus, it can be seen that under the same conditions, the absolute error of the molar fraction of each component is small, all within the range of ±5%, among which the smallest difference is the colloid in Figure P1 (d), which is 7.01×10-15%, and the largest difference is the saturation fraction in Figure P1 (d), which is -3.9%.

[0047] Figure 5The dynamic change curve of the product stream composition after the operating parameters are disturbed in the embodiment of the present invention and the absolute error of each component in the steady state. It can be seen from the figure that with the change of operating conditions, in products P1 (Figure (a)), P2 (Figure (b)) and P3 (Figure (c)), except for the molar fraction of the saturated fraction, the molar separation of the other components increases to varying degrees, and then reaches a stable state again. Among them, the gas phase content of the components in product P1 (Figure (a)) suddenly decreases or increases when the operating scheme is changed. This is mainly because the equilibrium constant of each component changes with the change of external operating conditions. At the same time, the gas phase content of each component is determined according to the liquid phase content and the equilibrium constant. With the change of the liquid phase content and the equilibrium constant, the calculated initial value of the gas phase content of each component is affected, which leads to the occurrence of this phenomenon. Figures (d) to (f) show the absolute errors of the molar fractions of the five components after products P1 to P3 reach a stable state again. As can be seen from the figure, the prediction results of the mixing model still maintain good accuracy after the operating conditions of the same crude oil are changed, and the absolute error of each component remains between 2.92% and -3.04%. The minimum and maximum absolute errors are asphaltene (8.7×10-25%) and saturated fraction (-3.094%) in product P1 (Figure (d)), respectively.

[0048] Figure 6 It is the dynamic change curve of the product stream composition after the oil type is changed in the embodiment of the present invention, as well as the absolute error of each component in the steady state. When the external operating conditions change, the content of each component that has reached equilibrium in products P1 to P3 will fluctuate and then reach equilibrium again. From Figure (a), it can be seen that the content of each component in the gas phase product P1 at the top of the ADU tower changes with the change of the operating scheme. This is caused by the change in the equilibrium constant caused by the change in operating conditions. The difference is that the process of reaching equilibrium is not obvious. Combined with Figure (b), it can be seen that after the operating scheme is switched to Scheme III, the content of each component in the ADU tower top product (P1, P2) changes little, resulting in the process of the content of each component in P1 reaching equilibrium is not obvious. Figure (d)

[0049] (f) shows the absolute error of the content of each component when the product stream reaches equilibrium under Scheme III. As can be seen from the figure, the absolute error of all components is in the range of -0.5456–0.548%. Among them, the absolute error of asphaltene in product P1 (Figure d) is the smallest, which is 7.28×10-26, and the absolute error of the aromatic component of product P2 (Figure (e)) is the largest, which is 0.548%.

[0050] Figure 7The probability histogram of the absolute errors of all molecules involved in the product streams under the three operating schemes in the embodiment of the present invention. It can be seen from the figure that with the change of operating conditions, the probability that the absolute errors of all molecules in product P1 (Figures (a), (d), (g)) are within the range of ±1% is 97.62, 97.62 and 97.6% respectively; the probability that the absolute errors of all molecules in product P2 (Figures (b), (e), (h)) are within the range of ±1% is 96.62, 97.6 and 95.9% respectively; the probability that the absolute errors of all molecules in product P3 (Figures (c), (f), (i)) are within the range of ±0.1% is 88.2, 87.9 and 88% respectively, and all absolute errors are within the range of ±1%. The probability that the absolute errors of all molecules in all streams are within the range of -0.05 to 1.0% is above 90%, and the absolute errors of most molecules are within ±5%. This also illustrates the accuracy and stability of the prediction results of the hybrid model.

Claims

1. A method for constructing a dynamic mixing model for atmospheric distillation driven by a crude oil molecular model, characterized in that: The steps include: Calculate the distillation physical property parameters related to the distillation process of molecular pure substances in the crude oil molecular model under steady state, and calculate the distillation-related physical property parameters of the mixture according to the mixing rules; According to the material balance equation, phase balance equation, mole fraction normalization equation and heat balance equation, a mechanism model is established for the entire primary distillation tower and the top and bottom of the atmospheric distillation tower. Establish a proxy model for the remaining main part of the atmospheric distillation tower according to the proxy model; According to the sequential structure of primary distillation tower-main part of atmospheric distillation tower-top and bottom of atmospheric distillation tower, a dynamic hybrid model of crude oil atmospheric distillation process with the structure of mechanism model-proxy model-mechanism model is built.

2. The method for constructing a dynamic mixing model for atmospheric distillation driven by a crude oil molecular model according to claim 1, characterized in that: The calculation process involved in the dynamic mixing model of crude oil atmospheric distillation includes: The crude oil molecular model involves the calculation of distillation-related physical property parameters of molecular pure substances and mixtures, and the obtained data constitutes a basic database for the construction of the mechanism model; the distillation-related physical property parameters include vapor phase enthalpy, liquid phase enthalpy, activity coefficient, vapor-liquid phase equilibrium constant and bubble point temperature; Establish dynamic mechanism models of the primary distillation tower, the top and bottom of the atmospheric distillation tower, and construct them according to the traditional material balance equation, phase balance equation, molar fraction normalization equation and heat balance equation; The proxy model is constructed as a BP neural network with a three-layer network structure consisting of an input layer, a hidden layer and an output layer; the molar flow rate, temperature and pressure of each component of the atmospheric distillation tower feed are used as input units of the BP neural network, and the flow rate of the product stream and the molar fraction of each molecular weight are output units of the BP neural network.

3. The method for constructing a dynamic mixing model for atmospheric distillation driven by a crude oil molecular model according to claim 2, characterized in that: The calculation method of the vapor phase enthalpy, liquid phase enthalpy, activity coefficient, vapor-liquid phase equilibrium constant and bubble point temperature is as follows: The vapor phase enthalpy and liquid phase enthalpy calculation of pure substances is obtained by using commercial software to obtain the vapor phase enthalpy and liquid phase enthalpy values ​​of each molecule at different temperatures, which are then fitted into a temperature-dependent formula to obtain the constant term in the formula; the vapor phase enthalpy and liquid phase enthalpy of the mixture are calculated by the mixing rule; The activity coefficient of each molecule is calculated by correlating the activity coefficient with temperature through fitting. The constant term in the correlation equation is obtained based on the activity coefficient at different temperatures and is used to calculate the activity coefficient at different temperatures. The gas phase used in the dynamic mixing model of the atmospheric distillation process of crude oil is an ideal gas, and the liquid phase is a non-ideal solution system; the vapor-liquid phase equilibrium constant is calculated by the activity coefficient, the saturated vapor pressure and the current plate pressure, where the saturated vapor pressure is calculated by the Antoine equation and the current plate pressure is a constant; The bubble point temperature is calculated using the Richmond iteration method.

4. The method for constructing a dynamic mixing model for atmospheric distillation driven by a crude oil molecular model according to claim 3, characterized in that: The vapor phase product flow rate of the primary distillation tower is obtained by multiplying the vapor phase fraction obtained by Newton iteration calculation using the Rachford-Rice equation by the feed flow rate; the vapor phase flow rate calculation formula at the top and bottom of the atmospheric distillation tower is obtained by combining the material balance equation with the heat balance equation.

5. The method for constructing a dynamic mixing model for atmospheric distillation driven by a crude oil molecular model according to claim 4, characterized in that: The proxy model is constructed as follows: The proxy model is constructed using a BP neural network with a three-layer network structure consisting of an input layer, a hidden layer and an output layer; the molar flow rate, temperature and pressure of each component of the atmospheric distillation tower feed are used as the input units of the BP neural network, and the convergent and effective vapor phase molar flow rates of each component of the second plate of the atmospheric distillation tower and the liquid phase molar flow rates of each component of the j-1th plate are used as the output units of the BP neural network. It is assumed that the crude oil distillation tower has a total of j plates, and each plate is numbered 1, 2, 3...j from top to bottom.

6. The method for constructing a dynamic mixing model for atmospheric distillation driven by a crude oil molecular model according to claim 5, characterized in that: The method for obtaining the training database and setting the training parameters in the proxy model are as follows: To ensure the diversity and randomness of the training data set, 200 sample points were selected within the parameter-related range through Latin hypercube sampling, and Latin hypercube sampling was repeated every time the feed composition of the primary distillation tower was changed; By randomly dividing the data set, 70% is set as the training sample set and 30% is set as the validation sample set; The activation function of the hidden layer in the BP neural network is the logarithmic function in the S-type function: logsing; the transfer function from the hidden layer to the output layer is the Purelin linear function; the BP neural network uses the Levenberg-Marquardt algorithm for training.

Images