Method, medium and system for establishing liquid flow model in reaction kettle

Abstract

The invention provides a method for establishing a liquid flow model in a reaction kettle, a medium and a system, and belongs to the technical field of computer models.The method for establishing the liquid flow model in the reaction kettle comprises the steps that firstly, a basic fluid dynamic model containing reaction kettle geometric parameters, fluid parameters and reaction parameters is established; establishing a mathematical model comprising a heat and mass transfer equation, a fluid motion equation, an energy conservation equation and a component conservation equation; by introducing a neural network module and a convolutional layer, a parameter contribution degree evaluation system is established, and dynamic optimization of model parameters is realized. And obtaining a convolution kernel initial parameter matrix based on the training data set, establishing an association relationship between a weight coefficient and various parameters, optimizing the model by verifying the data set, and finally obtaining the model capable of accurately predicting the flow characteristics of the liquid in the reaction kettle. The technical problem that in the prior art, a reaction kettle fluid dynamic model is difficult to accurately characterize fluid flow characteristics in the complex dynamic reaction process is solved.

Description

Technical Field

[0001] The present invention belongs to the technical field of computer models, and in particular, relates to a method, medium and system for establishing a liquid flow model in a reactor. Background Art

[0002] In the fields of chemical industry, materials, pharmaceuticals, etc., reactors are important equipment for realizing chemical reactions. The flow characteristics of the fluid in the reactor have a decisive influence on the heat transfer, mass transfer and reaction efficiency of the reaction process. The traditional reactor fluid flow model is mainly based on the computational fluid dynamics (CFD) method, which describes the fluid flow characteristics by solving basic control equations such as the Navier-Stokes equations, the continuity equation and the energy equation. These models are usually solved by numerical methods such as the finite volume method and the finite element method, and combined with turbulence models, multiphase flow models, etc. to deal with complex flow phenomena. In practical applications, researchers usually use commercial CFD software or self-developed programs to construct fluid flow models, and realize flow field calculations through steps such as meshing, boundary condition setting and solver parameter adjustment.

[0003] However, traditional fluid flow models have significant defects. First, these models are usually based on idealized assumptions and it is difficult to accurately describe the complex flow phenomena in the actual reaction process, such as local turbulence, secondary flow, dead zones, etc. Secondly, model parameters such as turbulent energy, dissipation rate, reaction rate, etc. usually use empirical values ​​or experimental fitting values, lacking accurate characterization of the dynamic changes of parameters. Thirdly, traditional models are difficult to effectively deal with the time-varying characteristics of parameters such as fluid properties and reaction conditions during the reaction process, resulting in a decrease in model prediction accuracy over time. In addition, existing models often separate processes such as fluid flow, heat and mass transfer, and chemical reactions, ignoring the coupling between the processes, making it difficult for the model to reflect the overall behavior of the actual reaction system.

[0004] Faced with increasingly complex chemical reaction processes and increasing process requirements, the limitations of traditional fluid flow models are becoming increasingly prominent. Especially when dealing with complex systems such as multiphase reactions and polymerization reactions, it is difficult for the model to accurately capture the dynamic changes in fluid flow characteristics, and it is also impossible to achieve real-time optimization and adjustment of model parameters. The lack of accuracy and poor adaptability of this model seriously restricts the process optimization and intelligent control of the reactor, and it is urgent to develop new modeling methods to break through this technical bottleneck. In other words, there is a technical problem in the prior art that the reactor fluid dynamics model is difficult to accurately characterize the fluid flow characteristics in complex dynamic reaction processes. Summary of the invention

[0005] In view of this, the present invention provides a method, medium and system for establishing a liquid flow model in a reactor, which can solve the technical problem in the prior art that the reactor fluid dynamics model is difficult to accurately characterize the fluid flow characteristics in a complex dynamic reaction process.

[0006] The present invention is implemented as follows: In a first aspect, the present invention provides a method for establishing a liquid flow model in a reactor, comprising the following steps: establishing a basic fluid dynamics model including reactor geometric parameters, fluid physical parameters and reaction process parameters; establishing a mathematical model of a reactor including a heat and mass transfer balance equation, a fluid motion balance equation, an energy conservation balance equation and a component conservation balance equation; constructing a deep neural network module to receive the calculation results of the basic fluid dynamics model and the reactor mathematical model; setting a flow feature convolution layer including multiple flow feature convolution kernels to calculate the contribution of the reaction process parameters to the process parameters of fluid flow; obtaining an initial parameter numerical matrix of the flow feature convolution kernel based on a model training data set, and establishing a mathematical association equation between the weight coefficient value of the flow feature convolution kernel and the reactor geometric parameters and the reaction process parameters; optimizing the parameter values ​​of the flow feature convolution kernel according to the mathematical association equation and establishing a final liquid flow model in the reactor.

[0007] Among them, the contribution of the process parameters is obtained through the following steps: calculating the partial derivative value of each reaction process parameter to the fluid velocity field distribution; calculating the partial derivative value of each reaction process parameter to the temperature field distribution; calculating the partial derivative value of each reaction process parameter to the concentration field distribution; normalizing the partial derivative values ​​to obtain the influence degree value of each reaction process parameter on the fluid flow state; and calculating the contribution coefficient value of each reaction process parameter based on the influence degree value.

[0008] Among them, the mathematical correlation equations include: linear correlation equations describing the mathematical relationship between the geometric parameters of the reactor and the numerical values ​​of the flow characteristic convolution kernel parameters; nonlinear correlation equations describing the mathematical relationship between the reaction process parameters and the numerical values ​​of the flow characteristic convolution kernel parameters; and coupled correlation equations describing the mathematical relationship between the contribution of the process parameters and the numerical values ​​of the flow characteristic convolution kernel parameters.

[0009] Among them, the geometric parameters of the reactor include the reactor diameter value, the reactor height value, the stirring paddle installation position value and the stirring paddle model parameter; the fluid physical parameters include the fluid density value, the fluid viscosity coefficient value, the fluid specific heat capacity value and the fluid thermal conductivity value; the reaction process parameters include the reaction temperature value, the reaction pressure value, the reaction conversion rate value and the reaction rate constant value.

[0010] Among them, the heat and mass transfer balance equation is used to calculate the temperature field distribution data inside the reactor; the fluid motion balance equation is used to calculate the fluid velocity field distribution data; the energy conservation balance equation is used to calculate the heat change data during the reaction process; and the component conservation balance equation is used to calculate the concentration field distribution data of each reactant.

[0011] Among them, before the step of establishing the final liquid flow model in the reactor, it also includes: collecting a model verification data set and calculating a model prediction result; comparing the error value between the model prediction result and the actual operation data, and when the error value is greater than a preset error threshold, returning to the step of recalculating the weight coefficient value of the flow feature convolution kernel.

[0012] Among them, the input parameters of the mathematical model of the reactor include: fluid temperature data, reactor wall temperature data and heat transfer coefficient value; fluid pressure data, fluid viscosity coefficient value and fluid density value; reaction heat value, stirring power value and heat dissipation value; reaction rate constant value, reactant initial concentration value and reaction conversion rate value.

[0013] The method further includes applying the final liquid flow model in the reactor to the reactor control system to achieve predictive control of the liquid flow in the reactor.

[0014] A second aspect of the present invention provides a computer-readable storage medium, wherein the computer-readable storage medium stores program instructions, and when the program instructions are run in a computer, they are used to execute the above-mentioned method for establishing a liquid flow model in a reactor.

[0015] The third aspect of the present invention provides a system for establishing a liquid flow model in a reactor, comprising the above-mentioned computer-readable storage medium, wherein the system is any one of a computer, a server, and a single-chip microcomputer, and the computer-readable storage medium is arranged in the system, and the system is provided with a microprocessor for executing program instructions stored in the computer-readable storage medium.

[0016] Compared with the prior art, the present invention provides a method, medium and system for establishing a liquid flow model in a reactor. The method for establishing a liquid flow model in a reactor proposed by the present invention combines a neural network module with a traditional fluid dynamics model and introduces the concept of parameter contribution, thereby achieving an accurate description of the flow characteristics of a complex reaction system and dynamic optimization of model parameters. The method first establishes a mathematical model containing basic equations such as heat and mass transfer, fluid motion, energy conservation and component conservation, and then optimizes the model through a neural network module, using the mapping relationship between the convolution kernel and the reaction parameters to improve the adaptability and prediction accuracy of the model.

[0017] Compared with traditional methods, the technical solution of the present invention has significant advantages. By introducing the concept of parameter contribution, a quantitative evaluation system for the influence of reaction parameters on the fluid flow state is established, so that the model can accurately identify and process the dynamic changes of key parameters. Based on the parameter optimization mechanism of the convolution kernel, the dynamic correlation between the model parameters and the actual process parameters is realized, ensuring the adaptability of the model under different working conditions. In addition, the present invention uniformly processes processes such as fluid flow, heat and mass transfer, and reaction kinetics, captures the coupling effect between the processes through the neural network module, and improves the overall prediction accuracy of the model.

[0018] Through the above technical innovation, the present invention effectively solves the limitations of traditional models in dealing with complex reaction systems. Based on the dynamic optimization mechanism of parameter contribution, the model can accurately reflect the changes in flow characteristics during the reaction process, providing a reliable theoretical basis for process optimization and intelligent control of the reactor. Therefore, the present invention solves the technical problem that the reactor fluid dynamics model existing in the prior art is difficult to accurately characterize the fluid flow characteristics in complex dynamic reaction processes. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] Figure 1 is a flow chart of the method of the present invention.

[0020] Figure 2 This is the evolution curve of the loss function during the deep neural network training process in Example 2.

[0021] Figure 3 This is a radar chart showing the contribution of different process parameters in Example 2.

[0022] Figure 4 This is a diagram of the convergence process of genetic algorithm optimization in Example 2.

[0023] Figure 5 This is a comparison chart of the prediction errors of the model in Example 2 under different working conditions. DETAILED DESCRIPTION

[0024] In order to make the purpose, technical solution and advantages of the embodiments of the present invention more clear, the technical solution in the embodiments of the present invention will be clearly and completely described below in conjunction with the accompanying drawings in the embodiments of the present invention.

[0025] like Figure 1 FIG. 1 is a flow chart of a method for establishing a liquid flow model in a reactor provided by the first aspect of the present invention. The method comprises the following steps:

[0026] S01. Establishing a basic fluid dynamics model, wherein the basic fluid dynamics model includes reaction kettle geometric parameters, fluid physical parameters and reaction process parameters;

[0027] S02. Establishing a mathematical model of the reactor, wherein the mathematical model of the reactor includes a heat and mass transfer balance equation, a fluid motion balance equation, an energy conservation balance equation, and a component conservation balance equation;

[0028] S03, constructing a deep neural network module, wherein the deep neural network module comprises an input layer node, a hidden layer node and an output layer node, wherein the input layer node receives the calculation results of the basic fluid dynamics model and the reactor mathematical model;

[0029] S04. Setting a flow feature convolution layer in the deep neural network module, wherein the flow feature convolution layer comprises a plurality of flow feature convolution kernels, and each of the flow feature convolution kernels corresponds to a set of reaction process parameters;

[0030] S05. Calculate the contribution of each reaction process parameter to the process parameter of fluid flow;

[0031] S06. Collecting reactor operation data, obtaining fluid temperature data, fluid pressure data, fluid flow rate data and reactant concentration data, and forming a model training data set;

[0032] S07, inputting the model training data set into the deep neural network module to obtain the initial parameter numerical matrix of the flow feature convolution kernel;

[0033] S08, calculating the weight coefficient value of the flow characteristic convolution kernel based on the initial parameter numerical matrix and the process parameter contribution, and establishing a mathematical correlation equation between the weight coefficient value and the reactor geometric parameters and the reaction process parameters;

[0034] S09, optimizing the parameter values ​​of the flow characteristic convolution kernel according to the mathematical association equation to obtain optimized convolution kernel parameter values;

[0035] S10, modifying the basic fluid dynamics model based on the optimized convolution kernel parameter values ​​to obtain a modified fluid dynamics model;

[0036] S11, collecting a model verification data set, inputting the model verification data set into the modified fluid dynamics model, and calculating the model prediction result;

[0037] S12, comparing the error value between the model prediction result and the actual operation data, and when the error value is greater than a preset error threshold, returning to step S08;

[0038] S13. When the error value is less than the preset error threshold, a final liquid flow model in the reactor is obtained.

[0039] Optionally, the method further includes applying the final liquid flow model in the reactor to a reactor control system to achieve predictive control of the liquid flow in the reactor.

[0040] The process parameter contribution is obtained by the following steps:

[0041] (1) Calculate the partial derivative values ​​of each reaction process parameter with respect to the fluid velocity field distribution;

[0042] (2) Calculating the partial derivative values ​​of each reaction process parameter with respect to the temperature field distribution;

[0043] (3) Calculate the partial derivative values ​​of each reaction process parameter with respect to the concentration field distribution;

[0044] (4) normalizing the partial derivative values ​​to obtain the influence of each reaction process parameter on the fluid flow state;

[0045] (5) calculating the contribution coefficient value of each reaction process parameter based on the influence degree value;

[0046] in:

[0047] The heat and mass transfer balance equation is used to calculate the temperature field distribution data inside the reactor. The input parameters include fluid temperature data, reactor wall temperature data and heat transfer coefficient value. The output result is the temperature field distribution data.

[0048] The fluid motion balance equation is used to calculate the fluid velocity field distribution data, the input parameters include fluid pressure data, fluid viscosity coefficient value and fluid density value, and the output result is the velocity field distribution data;

[0049] The energy conservation balance equation is used to calculate the heat change data during the reaction process. The input parameters include the reaction heat value, the stirring power value and the heat dissipation value. The output result is the energy balance data.

[0050] The component conservation balance equation is used to calculate the concentration field distribution data of each reactant, the input parameters include the reaction rate constant value, the initial concentration value of the reactant and the reaction conversion rate value, and the output result is the concentration field distribution data;

[0051] The geometric parameters of the reactor include the reactor diameter value, the reactor height value, the stirring paddle installation position value and the stirring paddle model parameter;

[0052] The fluid physical parameters include fluid density value, fluid viscosity coefficient value, fluid specific heat capacity value and fluid thermal conductivity value;

[0053] The reaction process parameters include reaction temperature, reaction pressure, reaction conversion rate and reaction rate constant;

[0054] The mathematical correlation equation includes:

[0055] Linear correlation equation: describes the mathematical relationship between the geometric parameters of the reactor and the numerical values ​​of the convolution kernel parameters of the flow characteristics;

[0056] Nonlinear correlation equation: describes the mathematical relationship between reaction process parameters and flow characteristic convolution kernel parameters;

[0057] Coupling correlation equation: describes the mathematical relationship between the contribution of process parameters and the numerical value of the flow characteristic convolution kernel parameters.

[0058] The flow feature convolution kernel is specifically a convolution operation unit for extracting fluid flow features;

[0059] The process parameter contribution is specifically a quantitative value of the influence of the reaction process parameter on the fluid flow state;

[0060] The fluid flow state includes the velocity field distribution, temperature field distribution and concentration field distribution of the fluid;

[0061] The preset error threshold is a preset allowable error range value between the model calculation result and the actual data.

[0062] The specific implementation of the above steps is described in detail below.

[0063] The specific implementation of step S01 is to establish a basic dynamic model that describes the movement law of the fluid inside the reactor. First, the geometric parameters of the reactor are collected and sorted, including the reactor diameter value in the range of 0.5 to 5 meters, the reactor height value in the range of 1 to 10 meters, the stirring paddle installation position value is generally located at 1 / 3 to 1 / 2 of the reactor height, and the stirring paddle model parameters include the number of blades, blade angle and blade diameter. Then collect the fluid physical parameters, the fluid density value range is 800 to 2000 kilograms per cubic meter, the fluid viscosity coefficient value range is 0.001 to 0.1 Pascal seconds, the fluid specific heat capacity value range is 2000 to 5000 joules per kilogram Kelvin, and the fluid thermal conductivity value range is 0.1 to 0.5 watts per meter Kelvin. Finally, the reaction process parameters were collected, with the reaction temperature ranging from 20 to 200 degrees Celsius, the reaction pressure ranging from 0.1 to 1.0 MPa, the reaction conversion rate ranging from 0.8 to 0.99, and the reaction rate constant ranging from 0.001 to 0.1 per second. These parameters were input into the computational fluid dynamics software to establish a basic fluid dynamics model.

[0064] The specific implementation method of step S02 is to establish a mathematical model of the reactor, which includes 4 main equilibrium equations. First, a heat and mass transfer equilibrium equation is established. The equation is based on Fourier's law of heat conduction, and the temperature field distribution inside the reactor is calculated. The input fluid temperature data range is 20 to 200 degrees Celsius, the reactor wall temperature data range is 15 to 180 degrees Celsius, and the heat transfer coefficient value range is 100 to 1000 watts per square meter Kelvin. Then a fluid motion equilibrium equation is established. The equation is based on the Navier-Stokes equation, and the fluid velocity field distribution is calculated. The input fluid pressure data range is 0.1 to 1.0 MPa, the fluid viscosity coefficient value range is 0.001 to 0.1 Pascal seconds, and the fluid density value range is 800 to 2000 kilograms per cubic meter. Then, the energy conservation balance equation is established. This equation is based on the first law of thermodynamics and calculates the heat change during the reaction process. The input reaction heat value ranges from -500 to 500 kilojoules per mole, the stirring power value ranges from 0.1 to 10 kilowatts, and the heat dissipation value ranges from 0.05 to 5 kilowatts. Finally, the component conservation balance equation is established. This equation is based on the law of conservation of mass and calculates the concentration field distribution of each reactant. The input reaction rate constant value ranges from 0.001 to 0.1 per second, the initial concentration of the reactant ranges from 0.1 to 10 moles per liter, and the reaction conversion rate ranges from 0.8 to 0.99.

[0065] The specific implementation of step S03 is to construct a deep neural network module, using a multi-layer perceptron network structure, the number of input layer nodes is the dimension of the calculation results of the basic fluid dynamics model and the reactor mathematical model, and 3 hidden layers are set. The number of nodes in each layer is 2 times, 1.5 times and 1 times the number of nodes in the input layer, respectively. The corrected linear unit activation function is used, and the number of output layer nodes is the predicted target dimension. The training adopts the stochastic gradient descent optimization algorithm, the learning rate is set to 0.001, the batch size is 32, and the number of training rounds is 1000 rounds.

[0066] The specific implementation method of step S04 is to set a flow feature convolution layer in the deep neural network module, adopt a three-dimensional convolutional neural network structure, set multiple flow feature convolution kernels, each convolution kernel size is 3×3×3, the step length is 1, and the filling method is the same filling. The number of convolution kernels is the same as the number of reaction process parameter groups, and each convolution kernel corresponds to a group of reaction process parameters, including reaction temperature value, reaction pressure value, reaction conversion rate value and reaction rate constant value. The batch normalization layer is used for data standardization, and the maximum pooling layer is used for feature dimensionality reduction. The pooling kernel size is 2×2×2, and the step length is 2.

[0067] The specific implementation method of step S05 is to calculate the process parameter contribution of each reaction process parameter to the fluid flow, first calculate the partial derivative value of each reaction process parameter to the fluid velocity field distribution, and use the central difference method to calculate the numerical differential. Then calculate the partial derivative value of each reaction process parameter to the temperature field distribution, also using the central difference method. Then calculate the partial derivative value of each reaction process parameter to the concentration field distribution. These partial derivative values ​​are subjected to minimum and maximum normalization processing to obtain the influence degree value of each reaction process parameter on the fluid flow state, ranging between 0 and 1. Finally, based on the influence degree value, the contribution coefficient value of each reaction process parameter is calculated using the weighted average method.

[0068] The specific implementation method of step S06 is to collect the operation data of the reactor, collect the fluid temperature data through the temperature sensor, the sampling frequency is 1 Hz, and the sampling time is 8 hours. Collect the fluid pressure data through the pressure sensor, the sampling frequency is 1 Hz, and the sampling time is 8 hours. Collect the fluid flow rate data through the flow meter, the sampling frequency is 1 Hz, and the sampling time is 8 hours. Collect the reactant concentration data through the concentration detector, the sampling frequency is 0.1 Hz, and the sampling time is 8 hours. The collected data is preprocessed, including outlier detection, missing value processing and data smoothing, to form a model training data set.

[0069] The specific implementation of step S07 is to input the model training data set into the deep neural network module, use the back propagation algorithm to perform network training, use the mean square error function as the loss function, use the adaptive moment estimation algorithm as the optimization algorithm, the learning rate is 0.001, and the number of training rounds is 1000. The initial parameter numerical matrix of the flow feature convolution kernel is obtained through training.

[0070] The specific implementation method of step S08 is to calculate the weight coefficient value of the flow characteristic convolution kernel based on the initial parameter value matrix and the process parameter contribution, and use the linear regression method to establish the linear correlation equation between the geometric parameters of the reactor and the flow characteristic convolution kernel parameter values. The polynomial regression method is used to establish the nonlinear correlation equation between the reaction process parameters and the flow characteristic convolution kernel parameter values, and the polynomial order is 3. The neural network method is used to establish the coupling correlation equation between the process parameter contribution and the flow characteristic convolution kernel parameter values.

[0071] The specific implementation method of step S09 is to optimize the parameter values ​​of the flow feature convolution kernel according to the mathematical association equation, and use the genetic algorithm for global optimization, with the population size set to 100, the evolutionary number of generations to 500, the crossover probability to 0.8, and the mutation probability to 0.1. The particle swarm optimization algorithm is used for local optimization, with the number of particles to 50, the maximum number of iterations to 200, the inertia weight to 0.7, and the acceleration coefficient to 2.

[0072] The specific implementation of step S10 is to modify the basic fluid dynamics model based on the optimized convolution kernel parameter value, extract the fluid flow characteristics by convolution operation, and modify the calculation results of the fluid velocity field distribution, temperature field distribution and concentration field distribution. The residual network structure is used to add the correction term to the calculation results of the basic model to obtain the modified fluid dynamics model.

[0073] The specific implementation of step S11 is to collect a model verification data set, using the same method as step S06 to collect data, and the sampling time is 4 hours. The model verification data set is input into the modified fluid dynamics model to calculate the model prediction results, including the fluid velocity field distribution, temperature field distribution and concentration field distribution.

[0074] The specific implementation of step S12 is to compare the error value between the model prediction result and the actual operation data, and use the relative error index for evaluation, and the preset error threshold is set to 5%. When the relative error of the velocity field distribution is greater than 5%, or the relative error of the temperature field distribution is greater than 5%, or the relative error of the concentration field distribution is greater than 5%, return to step S08 to re-optimize the convolution kernel parameters.

[0075] The specific implementation of step S13 is to determine the final liquid flow model in the reactor when the relative errors of all prediction results are less than the preset error threshold. The model includes the optimized flow characteristic convolution kernel parameter values ​​and the corrected fluid dynamics calculation equations. The model can be used to predict the fluid flow state under different reaction process conditions and provide a decision basis for the reactor control system.

[0076] The specific implementation method of optional step S14 is to apply the final liquid flow model in the reactor to the reactor control system to realize the predictive control of the liquid flow in the reactor. First, the model is deployed to the computing unit of the reactor control system, and the real-time data stream processing framework is used for online calculation. Then, based on the model prediction results, the model predictive control algorithm is used to optimize and adjust the operating parameters of the reactor, the prediction time domain is set to 60 minutes, the control time domain is set to 10 minutes, and the sampling period is 1 minute. Finally, the optimized operating parameters are sent to the actuator through the control system execution unit to realize the closed-loop control of the liquid flow in the reactor.

[0077] The equations or calculation processes involved in the present invention are described in detail below.

[0078] 1. Heat and mass transfer balance equation (the first equation in step S02):

[0079] The heat and mass transfer balance equation is specifically expressed as follows:

[0080]

[0081] Where T is the temperature field, unit is K; t is the time, unit is s; α is the temperature diffusion coefficient, Unit: m 2 / s; k is thermal conductivity, unit is W / (m·K); ρ is density, unit is kg / m 3 ;c p is the specific heat capacity, the unit is J / (kg·K); q v is the volume heat source term, in W / m 3 ; ε T is the error term for temperature field calculation; x, y, z are spatial coordinates, and the unit is m.

[0082] Boundary conditions:

[0083]

[0084] Where n is the wall normal vector; h is the convective heat transfer coefficient, the unit is W / (m 2 ·K); T w is the wall temperature in K; T f is the fluid temperature in K.

[0085] 2. Fluid motion balance equation (the second equation in step S02):

[0086] The fluid motion balance equation is specifically expressed as follows:

[0087]

[0088] In the formula, is the velocity vector, in m / s; p is the pressure, in Pa; μ is the dynamic viscosity, in Pa·s; is the acceleration due to gravity, in m / s 2 ; ε v Compute the error term for the velocity field.

[0089] 3. Energy conservation balance equation (the third equation in step S02):

[0090] The energy conservation balance equation is specifically expressed as follows:

[0091]

[0092] Where Φ is the viscosity dissipation function, the unit is W / m 3 ;q r is the reaction heat, in W / m 3 ;P s is the stirring power, in W; q l is the heat loss, in W; ε e The error term for energy calculations.

[0093] 4. Component conservation balance equation (the fourth equation in step S02):

[0094] The component conservation balance equation is specifically expressed as follows:

[0095]

[0096] In the formula, c i is the concentration of component i, in mol / m 3 ;D i is the diffusion coefficient of component i, in m 2 / s; R i is the reaction rate of component i, in mol / (m 3 ·s); ε c Compute the error term for the concentration field.

[0097] 5. Partial derivative calculation (calculation process in step S05):

[0098] The partial derivative calculation is specifically expressed as follows:

[0099]

[0100] In the formula, p j is the jth process parameter; Δp j is the parameter perturbation; ε p1 , ε p2 , ε p3 Compute the error term for the partial derivatives.

[0101] 6. Calculation of process parameter contribution (calculation process in step S05):

[0102] The process parameter contribution calculation is specifically expressed as follows:

[0103]

[0104] In the formula, S j is the contribution of the jth process parameter; w1, w2, w3 are weight coefficients, and satisfy w1+w2+w3=1; ε s Calculate the error term for the contribution.

[0105] 7. Deep neural network structure (network structure in step S03):

[0106] The forward propagation calculation of the deep neural network is specifically expressed as follows:

[0107] h1=f1(W1x+b1);

[0108] h2=f2(W2h1+b2);

[0109] h3=f3(W3h2+b3);

[0110] y=W4h3+b4+ε n ;

[0111] Where x is the input vector; h1, h2, h3 are the hidden layer outputs; y is the output vector; W1, W2, W3, W4 are weight matrices; b1, b2, b3, b4 are bias vectors; f1, f2, f3 are activation functions; ε n is the neural network prediction error term.

[0112] 8. Flow feature convolution kernel calculation (convolution calculation in step S04):

[0113] The flow feature convolution kernel calculation is specifically expressed as follows:

[0114]

[0115] In the formula, F i，j，k is the convolution output feature; K l，m，n is the convolution kernel parameter; I i，j，k is the input feature; k Compute the error term for the convolution.

[0116] 9. Mathematical correlation equation (correlation equation in step S08):

[0117] The linear correlation equation is specifically expressed as follows:

[0118] K p =A1d+A2h+A3h s +A4n b +ε l ;

[0119] In the formula, K p is the convolution kernel parameter; d is the reactor diameter; h is the reactor height; h s The installation position of the stirring paddle; n b is the number of impeller blades; A1, A2, A3, A4 are linear coefficients; ε l is the linear correlation error term.

[0120] The nonlinear correlation equation is specifically expressed as follows:

[0121] K p =B1T 3 +B2T 2 +B3T+B4p 3 +B5p 2 +B6P+B7X 3 +B8X 2+B9X+B 10 k 3 +B 11 k 2 +B 12 k+ε n ;

[0122] Wherein, T is the reaction temperature; P is the reaction pressure; X is the reaction conversion rate; k is the reaction rate constant; B1, B2, . . . , B 12 is the nonlinear coefficient; ε n is the nonlinear correlation error term.

[0123] The coupling correlation equation is specifically expressed as follows:

[0124]

[0125] In the formula, C j is the coupling coefficient; S j is the contribution of process parameters; φ j (p j ) is the parameter mapping function; ε c is the coupling correlation error term.

[0126] 10. Loss function calculation (training process in step S07):

[0127] The loss function calculation is specifically expressed as follows:

[0128]

[0129] Where N is the number of samples; y i is the true value; is the predicted value; λ is the regularization coefficient; W l is the network weight of the lth layer; ||·|| F is the Frobenius norm; ε l Calculate the error term for the loss.

[0130] 11. Genetic algorithm optimization (optimization process in step S09):

[0131] The fitness function calculation is specifically expressed as follows:

[0132]

[0133] Where MSE(x) is the mean square error; β is the balance coefficient; ψ j (x j ) is the parameter penalty function; ε g Calculate the error term for the fitness.

[0134] 12. Particle swarm optimization (optimization process in step S09):

[0135] The speed update equation is specifically expressed as follows:

[0136]

[0137] The position update equation is specifically expressed as follows:

[0138]

[0139] In the formula, is the velocity of the i-th particle at the k-th iteration; for location; is the optimal position of an individual; is the global optimal position; w is the inertia weight; c1, c2 are acceleration coefficients; r1, r2 are random numbers; ε v , ε p is the updated error term.

[0140] 13. Model predictive control (control process in step S14):

[0141] The predictive control objective function is specifically expressed as follows:

[0142]

[0143] Where N p is the prediction time domain; N c is the control time domain; y(t+k|t) is the k-step prediction output; r(t+k) is the reference trajectory; Δu(t+k|t) is the control increment; Q, R are weight matrices; ε c is the control error term.

[0144] Control constraints:

[0145] u min ≤u(t)≤u max ;

[0146] Δu min ≤Δu(t)≤Δu max ;

[0147] y min ≤y(t)≤y max ;

[0148] In the formula, u min ,u max is the control variable constraint; Δu min , Δu max To control the incremental constraint; y min ,y max is the output variable constraint.

[0149] Now let's explain the principle and meaning of each equation:

[0150] 1. Heat and mass transfer balance equation:

[0151] The equation is constructed based on Fourier's law of heat conduction and the principle of energy conservation. The term represents the rate of change of temperature over time, reflecting the transient characteristics of the system; The term represents heat conduction, and the second-order derivative form is used to describe the diffusion process of heat in space; the term is used to compensate for the error caused by model simplification. The boundary condition uses the third type of boundary condition to describe the wall of the reactor. The term represents the contribution of volume heat source, including reaction heat, stirring heat, etc.; ε T is the error convection heat transfer process.

[0152] 2. Fluid motion equilibrium equation:

[0153] This equation is based on the Navier-Stokes equations and describes the motion of the fluid. The term represents the inertial force of the fluid, including local acceleration and convection acceleration; The term represents the pressure gradient force; The term represents the viscous force; The term represents gravity; ε v is the error term. Continuity equation Reflects the conservation of mass.

[0154] 3. Energy conservation balance equation:

[0155] This equation comprehensively considers various energy transfer processes in the reactor. The term represents the change in energy carried by the fluid; The term represents heat conduction; the term Φ represents the contribution of mechanical energy converted into thermal energy; q r The term indicates that the chemical reaction releases or absorbs heat; P s The term represents the stirring power input; q l The term represents the heat loss of the system; ε e is the error term.

[0156] 4. Component conservation balance equation:

[0157] This equation is based on the law of conservation of mass and describes the concentration distribution of reactants. The term represents the change of concentration with time; The term represents convective mass transfer; The term represents molecular diffusion; R i The term represents the chemical reaction rate; ε c is the error term.

[0158] 5. Calculation of process parameter contribution:

[0159] The calculation quantifies the influence of each process parameter on the fluid flow state through normalized partial derivatives. The three-term weighted sum is used to consider the influence on the velocity field, temperature field and concentration field respectively. The weight coefficients w1, w2 and w3 can be optimized and determined through experimental data.

[0160] 6. Deep Neural Network Structure:

[0161] The network adopts a multi-layer perceptron structure and introduces nonlinear mapping capabilities through nonlinear activation functions. The output of each layer is used as the input of the next layer, and features are extracted layer by layer. The network parameters are optimized through the back propagation algorithm to minimize the prediction error.

[0162] 7. Flow feature convolution kernel calculation:

[0163] The calculation is based on the principle of three-dimensional convolution operation, and uses the characteristics of local connection and weight sharing to extract flow features. The 3×3×3 convolution kernel can capture the flow pattern in the local area, and extract features of different scales by superimposing multiple convolution kernels. The advantage of this method is that it can adaptively learn flow features without the need to manually design feature extraction operators.

[0164] 8. Mathematical correlation equations:

[0165] The linear correlation equation describes the relationship between the geometric parameters of the reactor and the convolution kernel parameters. The linear combination form is based on engineering experience, and it is believed that the influence of geometric parameters on flow characteristics has linear superposition. The nonlinear correlation equation uses a cubic polynomial to describe the influence of process parameters. This is because the reaction process usually exhibits nonlinear characteristics and the cubic polynomial has sufficient expression ability. The coupled correlation equation introduces parameter contribution as a weight, which reflects the difference in importance of different process parameters.

[0166] 9. Loss function calculation:

[0167] The loss function consists of two parts: the first part is the mean square error between the predicted value and the true value, which reflects the prediction accuracy of the model; the second part is the Frobenius norm of the weight matrix, which plays a regularization role to prevent overfitting. The parameter λ is used to balance the importance of these two parts.

[0168] 10. Genetic algorithm optimization:

[0169] The fitness function design takes two aspects into consideration: one is the model prediction accuracy (expressed as the inverse of the mean square error), and the other is the penalty term for the weighted parameter contribution. This design can ensure the prediction accuracy while considering the physical constraints of the process parameters.

[0170] 11. Particle Swarm Optimization:

[0171] The velocity update equation contains three terms: inertia term Maintain the original movement trend of particles; cognitive items Guide particles to move to the individual optimal position; social item Guide the particles to move to the global optimal position. The choice of parameters w, c1, c2 affects the convergence performance of the algorithm.

[0172] 12. Model Predictive Control:

[0173] The objective function consists of two items: output tracking error and control increment The former guarantees the control performance, while the latter suppresses the drastic change of the control quantity. The constraint conditions ensure that the control is within the practical feasible range. p and control time domain N c The choice of necessitates a balance between control performance and computational burden.

[0174] The innovations of these equations are mainly reflected in:

[0175] 1. Combining deep learning methods with traditional fluid mechanics models improves the accuracy and generalization ability of the model;

[0176] 2. The concept of process parameter contribution is introduced to quantify the importance of different parameters;

[0177] 3. Adopt multi-level optimization strategy to ensure the global optimality of model parameters;

[0178] 4. Various constraints in actual engineering are taken into consideration to improve the practicability of the model.

[0179] A second aspect of the present invention provides a computer-readable storage medium, wherein the computer-readable storage medium stores program instructions, and when the program instructions are run in a computer, they are used to execute the above-mentioned method for establishing a liquid flow model in a reactor.

[0180] The third aspect of the present invention provides a system for establishing a liquid flow model in a reactor, comprising the above-mentioned computer-readable storage medium, wherein the system is any one of a computer, a server, and a single-chip microcomputer, and the computer-readable storage medium is arranged in the system, and the system is provided with a microprocessor for executing program instructions stored in the computer-readable storage medium.

[0181] Specifically, the principle of the present invention is: the technical solution of the present invention is based on fluid dynamics theory and deep learning principles, and realizes accurate description of fluid flow characteristics in the reactor by constructing a multi-level model framework. Its core principle is to optimize the traditional fluid dynamics model by using the nonlinear mapping ability of neural networks, and realize dynamic adjustment of model parameters by calculating parameter contribution. In the basic fluid dynamics model, the heat and mass transfer equations are used to describe the temperature field distribution, the fluid motion equations are used to characterize the velocity field characteristics, and the energy conservation and component conservation equations are used to characterize the material and energy changes in the reaction process.

[0182] The introduction of the neural network module enables the model to have adaptive learning capabilities. By setting up a multi-layer convolution kernel structure, each convolution kernel corresponds to a specific reaction parameter group, realizing the mapping relationship between reaction parameters and model features. The calculation of parameter contribution is based on the partial derivative of each parameter to the flow state, and the influence weights of different parameters are obtained through normalization. This gradient-based contribution evaluation method enables the model to accurately identify key parameters and perform targeted optimization.

[0183] The optimization process of the model follows the principle of feedback iteration. By comparing the error between the model prediction results and the actual data, the convolution kernel parameters and weight coefficients are continuously adjusted until the preset accuracy requirements are met. This dynamic optimization mechanism ensures the adaptability and reliability of the model in practical applications. At the same time, by establishing the correlation between physical parameters and convolution kernel parameters, the physical interpretability of the model parameters is achieved, providing a theoretical basis for process optimization and control.

[0184] A specific embodiment 1 of the present invention is provided below, and the specific implementation method of each step in this embodiment 1 is described in detail as follows.

[0185] The specific implementation method of step S01 is to achieve high-precision prediction of liquid flow in the reactor by establishing a basic fluid dynamics model. First, the geometric parameters of the reactor need to be collected, including the reactor diameter value in the range of 0.5 to 5 meters, the reactor height value in the range of 1 to 10 meters, the stirring paddle installation position value located at 1 / 3 to 1 / 2 of the reactor height, the number of stirring paddle blades in the range of 2 to 8, the blade angle range of 30 to 60 degrees, and the blade diameter of 0.3 to 0.6 times the reactor diameter. Then collect the fluid physical parameters, obtain the fluid density value by experimental measurement or consulting the relevant data manual, ranging from 800 to 2000 kilograms per cubic meter, use a rotational viscometer to measure the fluid viscosity coefficient value, ranging from 0.001 to 0.1 Pascal seconds, use differential scanning calorimetry to determine the fluid specific heat capacity value, ranging from 2000 to 5000 joules per kilogram Kelvin, and use the transient hot wire method to measure the fluid thermal conductivity value, ranging from 0.1 to 0.5 watts per meter Kelvin. Finally, the reaction process parameters were collected. The reaction temperature range was determined to be 20 to 200 degrees Celsius through the process regulations, the reaction pressure range was 0.1 to 1.0 MPa, the reaction conversion rate range was 0.8 to 0.99 by gas chromatography, and the reaction rate constant range was 0.001 to 0.1 per second by the kinetic experimental method. These parameters were input into the computational fluid dynamics software, and the finite volume method was used for meshing. The number of meshes was not less than 1 million. The hexahedral structured mesh was used, and the mesh quality required orthogonality to be greater than 0.8 and skewness to be less than 0.3. The Reynolds-averaged Navier-Stokes equations were used to describe the fluid motion, the standard k-ε model was selected to simulate turbulence, and the wall function was used to process the near-wall area. Considering the motion of the stirring paddle, the sliding grid technology was used, the time step was set to 0.001 seconds, and the total calculation time was not less than 60 seconds. The established basic fluid dynamics model needs to meet the principles of conservation of mass, conservation of momentum, and conservation of energy.

[0186] The specific implementation method of step S02 is to establish a mathematical model of the reactor, which contains four main equilibrium equations. First, the heat and mass transfer equilibrium equation is established, based on Fourier's heat conduction law, and the finite difference method is used for discretization and solution, and the specific form is:

[0187]

[0188] The parameter descriptions in the formula have been given in the previous article. The second-order central difference format is used for spatial discretization, and the first-order forward difference format is used for time discretization. The time step is 0.01 second and the spatial step is 0.01 meter. Then the fluid motion equilibrium equation is established based on the Navier Stokes equation:

[0189]

[0190] The pressure correction algorithm is used to solve the problem, and the iteration error is controlled within 0.0001. Then the energy conservation balance equation is established:

[0191]

[0192] The alternating direction implicit difference method is used to solve the problem, and the convergence criterion is that the maximum relative error of the temperature field between two adjacent iterations is less than 0.001. Finally, the component conservation equilibrium equation is established:

[0193]

[0194] The flux balance method was used to ensure mass conservation, and the convergence criterion was that the component mass balance error was less than 0.1%.

[0195] The specific implementation method of step S03 is to construct a deep neural network module, using a multi-layer perceptron network structure. The number of input layer nodes is determined by the dimensions of the calculation results of the basic fluid dynamics model and the mathematical model of the reactor, usually the sampling values ​​of physical quantities such as flow field, temperature field, concentration field at characteristic positions, and the number of nodes ranges from 100 to 1000. Three hidden layers are used, and the number of nodes in each layer is 2 times, 1.5 times and 1 times the number of nodes in the input layer, respectively. The activation function uses the corrected linear unit function: f(x)=max(0,x). To prevent overfitting, a batch normalization layer and a dropout layer are added after each hidden layer, and the dropout ratio is set to 0.2. The number of output layer nodes is the prediction target dimension, usually between 20 and 200. The network parameter initialization adopts the He Kaiming initialization method, and the bias term is initialized to 0. The training adopts the stochastic gradient descent optimization algorithm, the initial value of the learning rate is set to 0.001, and the cosine annealing strategy is used to dynamically adjust the learning rate, and the minimum learning rate is 0.00001. The batch size is 32, the number of training rounds is 1000, and the model parameters are saved every 100 rounds. The early stopping strategy is used to prevent overfitting, and the training is stopped if the validation set loss does not decrease for 10 consecutive rounds.

[0196] The specific implementation of step S04 is to set a flow feature convolution layer in the deep neural network module, using a three-dimensional convolutional neural network structure. Set multiple flow feature convolution kernels, and the calculation formula of each convolution kernel is:

[0197]

[0198] The convolution kernel size is 3×3×3, the step size is 1, and the padding method is the same padding. The number of convolution kernels is the same as the number of reaction process parameter groups, usually 4 to 8. The batch normalization layer is used for data normalization, and the normalization parameters are obtained by training data statistics. The maximum pooling layer is used for feature dimensionality reduction, and the pooling kernel size is 2×2×2 and the step size is 2. Residual connections are added after the convolution layer, and every 2 layers constitute a residual block. A total of 3 residual blocks are used, and finally the features are mapped to the prediction target space through the fully connected layer. In order to improve the feature extraction capability, the attention mechanism is used in each residual block to calculate the feature importance weights at different positions. The convolution kernel parameters are initialized using the xavier method, and the standard deviation is set to 0.01. L2 regularization is used during training to prevent overfitting, and the regularization coefficient is 0.0001.

[0199] The specific implementation method of step S05 is to calculate the contribution of each reaction process parameter to the process parameter of fluid flow, using a sensitivity analysis method. First, the partial derivative value of each reaction process parameter to the fluid velocity field distribution is calculated, and the specific formula is:

[0200]

[0201] The central difference method is used to calculate the numerical differential, and the parameter perturbation is set to 1% of the parameter reference value. 100 perturbation calculations are performed on each parameter, and the average value is taken as the final result. Then the partial derivative values ​​of each reaction process parameter to the temperature field distribution are calculated:

[0202]

[0203] The central difference method is also used. Then the partial derivative values ​​of each reaction process parameter to the concentration field distribution are calculated:

[0204]

[0205] These partial derivative values ​​are normalized to the minimum and maximum values:

[0206]

[0207] The influence of each reaction process parameter on the fluid flow state is obtained, ranging from 0 to 1. The weight coefficient is determined by the principal component analysis method, generally satisfying w1>w2>w3. Finally, the weighted average method is used to calculate the contribution coefficient value of each reaction process parameter, and the parameters with a contribution higher than 0.5 are considered to be key process parameters.

[0208] The specific implementation method of step S06 is to collect the operation data of the reactor and collect the fluid temperature data through the temperature sensor. A platinum resistance temperature sensor is used with an accuracy of ±0.1 degrees Celsius, a sampling frequency of 1 Hz, a sampling time of 8 hours, and 5 temperature measuring points are arranged at different heights of the reactor. Fluid pressure data is collected through a pressure sensor, a piezoresistive pressure sensor is used, the accuracy is ±0.1% of the full scale, the sampling frequency is 1 Hz, the sampling time is 8 hours, and 3 pressure measuring points are arranged at different positions of the reactor. Fluid flow rate data is collected through an electromagnetic flowmeter with an accuracy of ±0.5%, a sampling frequency of 1 Hz, and a sampling time of 8 hours. Reactant concentration data is collected through a concentration detector, an online gas chromatograph is used, the analysis cycle is 10 seconds, and the sampling time is 8 hours. The collected data is preprocessed, firstly outlier detection is performed, the 3σ criterion is used to identify outliers, and the outliers are corrected by the local polynomial regression method. Then, missing value processing is performed using the time series interpolation method. For data with no more than 10 consecutive missing points, cubic spline interpolation is used, and for data segments with more than 10 missing points, Kalman filter prediction is used. Finally, data smoothing is performed using the Savitzky-Golay filter method, with a window length of 11 and a polynomial order of 3. The preprocessed data is randomly divided into a training set and a validation set in a ratio of 8:2.

[0209] The specific implementation method of step S07 is to input the model training data set into the deep neural network module and use the back propagation algorithm to perform network training. The loss function uses the mean square error function:

[0210]

[0211] The regularization coefficient λ is set to 0.0001. The optimization algorithm uses the adaptive moment estimation algorithm, and the main parameters β1 are set to 0.9, β2 is set to 0.999, and ε is set to 10 -8 , the learning rate is 0.001, and the number of training rounds is 1000. After each round of training, the model performance is calculated on the validation set, and the model parameters when the validation set loss value is less than 0.01 are recorded. The initial parameter numerical matrix of the flow feature convolution kernel is obtained through training. The matrix dimension is determined by the convolution kernel size, which is generally 3×3×3.

[0212] The specific implementation of step S08 is to calculate the weight coefficient value of the flow characteristic convolution kernel based on the initial parameter value matrix and the process parameter contribution, and establish a set of mathematical correlation equations. First, a linear regression method is used to establish a linear correlation equation between the geometric parameters of the reactor and the flow characteristic convolution kernel parameter values:

[0213] K p =A1d+A2h+A3h s +A4n b +ε l ,

[0214] The coefficient matrix is ​​estimated using the least squares method, and the coefficient of determination R 2 The requirement is greater than 0.9. Then the polynomial regression method is used to establish the nonlinear correlation equation between the reaction process parameters and the flow characteristic convolution kernel parameter values:

[0215] K p =B1T 3 +B2T 2 +B3T+B4P 3 +B5P 2 +B6P+B7X 3 +B8X 2 +B9X+B 10 k 3 +B 11 k 2 +B 12 k+ε n ,

[0216] The Legendre polynomials are used as the basis functions, and the coefficients are determined by fitting optimization. Then the neural network method is used to establish the coupling correlation equation between the contribution of process parameters and the numerical value of the flow characteristic convolution kernel parameters:

[0217]

[0218] Among them, φ_j is the parameter mapping function, which is constructed using radial basis function. Finally, the three equations are combined to form a complete set of mathematical correlation equations to guide the optimization of convolution kernel parameters.

[0219] The specific implementation method of step S09 is to optimize the parameter values ​​of the flow characteristic convolution kernel according to the mathematical association equation, and adopt a two-stage optimization strategy. In the first stage, a genetic algorithm is used for global optimization, the population size is set to 100, the chromosome length is equal to the number of parameters to be optimized, and a real number encoding method is used. The fitness function is:

[0220]

[0221] The mean square error threshold is set to 0.001, and the balance coefficient β is set to 0.1. The selection operation adopts the tournament selection method, and 3 individuals are selected for comparison each time. The crossover operation adopts arithmetic crossover with a crossover probability of 0.8. The mutation operation adopts Gaussian mutation with a mutation probability of 0.1, and the standard deviation decreases with the generation. The evolutionary generation is 500 generations, and the iteration is terminated when the optimal solution has not been improved for 50 consecutive generations. In the second stage, the particle swarm optimization algorithm is used for local optimization, with a particle number of 50 and a maximum number of iterations of 200. The speed update equation is:

[0222]

[0223] The position update equation is:

[0224]

[0225] The inertia weight w decreases linearly with the number of iterations, with an initial value of 0.9 and a final value of 0.4. The acceleration coefficients c1 and c2 are both set to 2.0. When the improvement of the optimal solution is less than 0.0001 for 30 consecutive iterations, the algorithm is considered to have converged.

[0226] The specific implementation method of step S10 is to correct the basic fluid dynamics model based on the optimized convolution kernel parameter values, using the residual learning method. First, the optimized convolution kernel is used to extract the features of the flow field data to obtain a flow feature map. The feature map is then mapped back to the physical space through a deconvolution operation to obtain a flow field correction term. The correction term is then added to the calculation results of the basic model to correct the fluid velocity field distribution, temperature field distribution and concentration field distribution. The velocity field correction adopts the momentum correction method and introduces the eddy viscosity correction term; the temperature field correction adopts the thermal diffusion correction method and introduces the turbulent Prandtl number correction term; the concentration field correction adopts the mass diffusion correction method and introduces the turbulent Schmidt number correction term. The correction coefficient is determined by optimizing the model verification data, and the relative error between the corrected prediction result and the experimental data must be controlled within 5%.

[0227] The specific implementation method of step S11 is to collect the model verification data set, and the data is collected using the same method as step S06, and the sampling time is 4 hours. The verification data set includes 5 groups of operating data of different working conditions, and the fluid temperature, pressure, flow rate and concentration data are recorded under each working condition. To ensure the representativeness of the data, the 5 groups of working conditions need to cover the typical operating range of the reactor: working condition 1 is a low temperature and low pressure working condition, the reaction temperature is 50 degrees Celsius, and the pressure is 0.2 MPa; working condition 2 is a low temperature and high pressure working condition, the reaction temperature is 50 degrees Celsius, and the pressure is 0.8 MPa; working condition 3 is a medium temperature and medium pressure working condition, the reaction temperature is 120 degrees Celsius, and the pressure is 0.5 MPa; working condition 4 is a high temperature and low pressure working condition, the reaction temperature is 180 degrees Celsius, and the pressure is 0.2 MPa; working condition 5 is a high temperature and high pressure working condition, the reaction temperature is 180 degrees Celsius, and the pressure is 0.8 MPa. The verification data set is input into the modified fluid dynamics model to calculate the flow field distribution prediction results under each working condition.

[0228] The specific implementation of step S12 is to compare the error value between the model prediction result and the actual operation data, using a multi-index evaluation system. The relative error calculation formula of the velocity field distribution is:

[0229]

[0230] The relative error calculation formula of temperature field distribution is:

[0231]

[0232] The relative error calculation formula of concentration field distribution is:

[0233]

[0234] The preset error threshold is set to 5%. When the relative error of any indicator exceeds the threshold, it is necessary to return to step S08 to re-optimize the convolution kernel parameters. In order to improve the optimization efficiency, the optimization target is dynamically adjusted according to the error analysis results, focusing on optimizing the prediction amount with larger error.

[0235] The specific implementation method of step S13 is to determine the final liquid flow model in the reactor when the relative errors of all prediction results are less than the preset error threshold. The model includes the optimized flow characteristic convolution kernel parameter numerical matrix and the modified fluid dynamics calculation equations. When the model is stored, the network structure information, model parameters, normalization parameters, etc. are saved at the same time, and a hierarchical storage structure is adopted to facilitate the call and update of the model. When the model is deployed, it is necessary to compress and quantize the model to reduce the computing resource usage. The final model can be used to predict the fluid flow state under different reaction process conditions, and the confidence interval of the prediction result is 95%. The model update cycle defaults to 3 months, and new operating data needs to be collected for model retraining during update.

[0236] In order to better understand and implement the present invention, Example 2 of a specific application scenario of the present invention is provided below: When a research team was studying the process control of a large polycarbonate synthesis reactor, they found that the traditional flow model was difficult to accurately predict the fluid flow state under complex reaction conditions, resulting in large fluctuations in product quality. The research team decided to use the method of the present invention to establish a high-precision liquid flow model in the reactor.

[0237] First, the research team collected the basic parameters of the reactor, as shown in Table 1:

[0238] Table 1 Basic parameters of reactor

[0239] Parameter Type Parameter name Parameter Value Geometric parameters Reactor diameter 2.5m Geometric parameters Reactor height 4.8m Geometric parameters Installation position of stirring paddle 1.8m Geometric parameters Number of stirring blades 6 pieces Geometric parameters Angle of stirring blade 45 degrees Geometric parameters Agitator paddle diameter 1.2m

[0240] The fluid physical parameters were obtained through experimental measurement, as shown in Table 2:

[0241] Table 2 Fluid physical parameters

[0242] Physical parameters Numerical range Measurement method Fluid Density <![CDATA[1150±50kg / m 3 ]]> Vibrating tube densitometer Fluid Viscosity 0.045±0.005Pa·s Rotational Viscometer Specific heat capacity of fluid 2850±150J / (kg·K) Differential Scanning Calorimetry Fluid thermal conductivity 0.28±0.02W / (m·K) Transient hot wire method

[0243] The setting of reaction process parameters is shown in Table 3:

[0244] Table 3 Reaction process parameters

[0245] Process parameters Setting range Control accuracy Reaction temperature 180～200℃ ±0.5℃ Reaction pressure 0.6~0.8MPa ±0.01MPa Reaction conversion rate 0.92～0.96 ±0.01 Reaction rate constant 0.025～0.035s-1 ±0.001s-1

[0246] The research team established a basic fluid dynamics model based on the above parameters and solved it using commercial computational fluid dynamics software. The meshing was done using a hexahedral structured grid, with a total of 1.25 million grids, a minimum grid size of 0.01 m, orthogonality of 0.85, and skewness of 0.25 in the grid quality evaluation index. The standard k-ε model was selected as the turbulence model, and the standard wall function was used for near-wall processing. + The value is controlled in the range of 30 to 300. The motion of the stirring paddle is realized by sliding grid technology, the time step is set to 0.001s, and the total calculation time is 180s.

[0247] The mathematical model of the reactor was established based on the heat and mass transfer balance equation, fluid motion balance equation, energy conservation balance equation and component conservation balance equation. The heat and mass transfer balance equation is:

[0248] The equilibrium equation of fluid motion is:

[0249] A deep neural network module with 4 hidden layers was constructed. The number of input layer nodes was 256, corresponding to the sampling values ​​of flow field, temperature field, pressure field and concentration field at 64 feature positions. The number of hidden layer nodes was 512, 384, 256 and 128 respectively, and the activation function used the rectified linear unit function. The dropout ratio was set to 0.2, the batch size was 32, and the number of training rounds was 1000. The evolution of the loss function of network training is shown in Table 4:

[0250] Table 4 Network training loss function evolution table

[0251] Number of training rounds Training set loss Validation set loss Learning Rate 100 0.0856 0.0921 0.001 300 0.0452 0.0487 0.0008 500 0.0287 0.0315 0.0005 700 0.0198 0.0225 0.0003 1000 0.0156 0.0182 0.0001

[0252] Figure 2 The evolution curve of the loss function during the deep neural network training process is shown. The figure contains three key indicators: the change of training set loss, validation set loss and learning rate. Through the design of double Y-axis, the change trend of these three parameters with the number of training rounds is intuitively shown. Eight flow feature convolution kernels are set in the deep neural network, each with a size of 3×3×3, corresponding to different combinations of reaction process parameters. The contribution of each process parameter is calculated by sensitivity analysis, as shown in Table 5:

[0253] Table 5 Process parameter contribution calculation results

[0254] Process parameters Velocity field contribution Temperature field contribution Concentration field contribution Comprehensive contribution Reaction temperature 0.385 0.452 0.325 0.412 Reaction pressure 0.278 0.215 0.245 0.246 Reaction conversion rate 0.156 0.185 0.285 0.198 Rate constant 0.181 0.148 0.145 0.144

[0255] Figure 3The contribution of different process parameters to the velocity field, temperature field and concentration field is shown in the form of a radar chart. The contribution distribution of the four process parameters (reaction temperature, reaction pressure, reaction conversion rate, rate constant) in the three fields is clearly shown through the polar coordinate system. The convolution kernel parameters are optimized using a two-stage optimization strategy. In the first stage, a genetic algorithm is used with a population size of 100 and an evolutionary generation of 500. The convergence process of the algorithm is shown in Table 6:

[0256] Table 6 Genetic algorithm optimization convergence process table

[0257] Evolutionary Algebra Optimal fitness Average fitness Parameter standard deviation 100 0.856 0.725 0.158 200 0.912 0.845 0.125 300 0.945 0.898 0.086 400 0.968 0.935 0.052 500 0.982 0.965 0.028

[0258] Figure 4 The convergence process of genetic algorithm optimization is shown, including the changing trends of the three indicators of optimal fitness, average fitness and parameter standard deviation. The double Y-axis design is used to intuitively show the changes of these indicators with the evolutionary generations. In the second stage, the particle swarm optimization algorithm is used for local optimization, with 50 particles and a maximum number of iterations of 200. The comparison between the model prediction results obtained by optimization and the experimental data is shown in Table 7:

[0259] Table 7 Comparison of model prediction results and experimental data

[0260] Evaluation indicators Relative error of velocity field Relative error of temperature field Relative error of concentration field Condition 1 3.25％ 2.85％ 3.56％ Condition 2 3.68％ 3.12％ 3.82％ Condition 3 3.45％ 2.98％ 3.65％ Condition 4 3.86％ 3.25％ 3.92％ Condition 5 3.92％ 3.35％ 4.15％

[0261] Figure 5 The grouped bar chart shows the comparison of the prediction errors of the model under different working conditions. The figure contains three relative errors of velocity field, temperature field and concentration field, which clearly shows the prediction accuracy of the model under different working conditions. The traditional reactor flow modeling method mainly uses computational fluid dynamics software to directly simulate or simplify the empirical model. The computational fluid dynamics method has a large amount of calculation, it is difficult to achieve real-time prediction, and the prediction error can reach more than 15% under complex working conditions. Although the empirical model has a fast calculation speed, it has low accuracy and the prediction error is usually more than 20%. The method of the present invention combines deep learning with the traditional fluid mechanics model, which significantly improves the prediction accuracy while ensuring the calculation efficiency, and the prediction error is controlled within 5%. In addition, the concept of process parameter contribution introduced in the present invention can quantitatively evaluate the influence of different parameters on the flow state, providing a theoretical basis for the optimization of process parameters. The two-stage optimization strategy is adopted to avoid the local optimal solution and ensure the global optimality of the model parameters.

[0262] It should be noted that the variables involved in the present invention are explained in detail as shown in Table 8 below.

[0263] Table 8 Variable explanation table

[0264]

[0265]

[0266] The above description is only a specific implementation mode of the present invention, but the protection scope of the present invention is not limited thereto. Any technician familiar with the technical field can easily think of changes or substitutions within the technical scope disclosed by the present invention, which should be covered by the protection scope of the present invention.

Claims

1. A method for establishing a liquid flow model in a reactor, characterized in that: The following steps are involved: A basic fluid dynamics model including the geometric parameters of the reactor, the physical parameters of the fluid and the reaction process parameters is established; a mathematical model of the reactor including the heat and mass transfer balance equation, the fluid motion balance equation, the energy conservation balance equation and the component conservation balance equation is established; a deep neural network module is constructed to receive the calculation results of the basic fluid dynamics model and the mathematical model of the reactor; a flow feature convolution layer including multiple flow feature convolution kernels is set to calculate the contribution of the reaction process parameters to the process parameters of the fluid flow; an initial parameter numerical matrix of the flow feature convolution kernel is obtained based on the model training data set, and a mathematical correlation equation between the weight coefficient value of the flow feature convolution kernel and the geometric parameters of the reactor and the reaction process parameters is established; according to the mathematical correlation equation, the parameter values ​​of the flow feature convolution kernel are optimized and a final liquid flow model in the reactor is established.

2. The method for establishing a liquid flow model in a reactor according to claim 1, characterized in that: The process parameter contribution is obtained by the following steps: calculating the partial derivative value of each reaction process parameter to the fluid velocity field distribution; calculating the partial derivative value of each reaction process parameter to the temperature field distribution; calculating the partial derivative value of each reaction process parameter to the concentration field distribution; normalizing the partial derivative values ​​to obtain the influence degree value of each reaction process parameter on the fluid flow state; The contribution coefficient value of each reaction process parameter is calculated based on the influence degree value.

3. The method for establishing a liquid flow model in a reactor according to claim 1, characterized in that: The mathematical correlation equations include: linear correlation equations describing the mathematical relationship between the geometric parameters of the reactor and the numerical values ​​of the flow characteristic convolution kernel parameters; nonlinear correlation equations describing the mathematical relationship between the reaction process parameters and the numerical values ​​of the flow characteristic convolution kernel parameters; and coupled correlation equations describing the mathematical relationship between the contribution of the process parameters and the numerical values ​​of the flow characteristic convolution kernel parameters.

4. The method for establishing a liquid flow model in a reactor according to claim 1, characterized in that: The geometric parameters of the reactor include the reactor diameter value, the reactor height value, the stirring paddle installation position value and the stirring paddle model parameter; the fluid physical parameters include the fluid density value, the fluid viscosity coefficient value, the fluid specific heat capacity value and the fluid thermal conductivity coefficient value; the reaction process parameters include the reaction temperature value, the reaction pressure value, the reaction conversion rate value and the reaction rate constant value.

5. The method for establishing a liquid flow model in a reactor according to claim 1, characterized in that: The heat and mass transfer balance equation is used to calculate the temperature field distribution data inside the reactor; the fluid motion balance equation is used to calculate the fluid velocity field distribution data; the energy conservation balance equation is used to calculate the heat change data during the reaction process; and the component conservation balance equation is used to calculate the concentration field distribution data of each reactant.

6. The method for establishing a liquid flow model in a reactor according to claim 1, characterized in that: Before the step of establishing the final liquid flow model in the reactor, it also includes: collecting a model verification data set and calculating a model prediction result; comparing the error value between the model prediction result and the actual operation data, and when the error value is greater than a preset error threshold, returning to the step of recalculating the weight coefficient value of the flow feature convolution kernel.

7. The method for establishing a liquid flow model in a reactor according to claim 1, characterized in that: The input parameters of the reactor mathematical model include: fluid temperature data, reactor wall temperature data and heat transfer coefficient value; fluid pressure data, fluid viscosity coefficient value and fluid density value; reaction heat value, stirring power value and heat dissipation value; reaction rate constant value, reactant initial concentration value and reaction conversion rate value.

8. The method for establishing a liquid flow model in a reactor according to claim 1, characterized in that: The method also includes applying the final liquid flow model in the reactor to the reactor control system to achieve predictive control of the liquid flow in the reactor.

9. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores program instructions, and when the program instructions are run in a computer, they are used to execute the method for establishing a liquid flow model in a reactor according to any one of claims 1 to 8.

10. A system for establishing a liquid flow model in a reactor, characterized in that: The system comprises the computer-readable storage medium as claimed in claim 9, wherein the system is any one of a computer, a server, and a single-chip microcomputer, the computer-readable storage medium is arranged in the system, and the system is provided with a microprocessor for executing program instructions stored in the computer-readable storage medium.

Images