CN118278226B - Multi-objective optimized gas-solid two-phase flow heating system design method and system - Google Patents

Abstract

The invention discloses a multi-objective optimized gas-solid two-phase flow heating system design method and system, which relate to the technical field of gas-solid two-phase flow heating system design. The invention designs a design variable set of the gas-solid two-phase flow heating system by training a heat transfer coefficient prediction model and a slip velocity prediction model, and collecting a parameter value set of constant parameters of the heating system; collects a heat transfer coefficient fitting function corresponding to the heat transfer coefficient prediction model, and collects a slip velocity fitting function corresponding to the slip velocity prediction model; designs a system design optimization problem based on the design variable set, the parameter values of the constant parameters, the heat transfer coefficient fitting function and the slip velocity fitting function, solves the system design optimization problem, and performs parameter design on the gas-solid two-phase flow heating system; and completes system structure design and process optimization before the gas-solid two-phase flow heating system is constructed.

Description

A multi-objective optimization gas-solid two-phase flow heating system design method and system

Technical Field

The invention relates to the technical field of gas-solid two-phase flow heating system design, and in particular to a multi-objective optimized gas-solid two-phase flow heating system design method and system.

Background Art

Gas-solid two-phase flow heating systems are widely used in many industries such as chemical industry, energy, metallurgy, environmental protection, etc., and play an important role in fluidized bed reactors, tubular heating furnaces, thermal power plant boilers, drying equipment, etc. This type of system uses high-temperature gas (such as air, combustion flue gas, etc.) and solid particles (such as catalysts, mineral powder, biomass particles, etc.) to form gas-solid two-phase flow to achieve efficient heating of the solid phase and material transportation.

Compared with single-phase fluid, gas-solid two-phase flow presents more complex flow behaviors, such as gas-solid phase slip, particle collision, turbulence enhancement, etc., which will significantly affect the flow resistance, heat and mass transfer performance of the system. At the same time, the constitutive relationship, relative motion and interface exchange process of gas-solid two-phase flow also make the mathematical model and solution of the system more complicated.

In the design process of gas-solid two-phase flow heating system, engineers need to pre-design many key parameters, such as solid phase temperature, gas phase temperature, etc., in order to obtain smaller pressure drop, higher heat transfer efficiency and lower wear rate. However, the current design of key parameters is often based only on the relevant experience of engineers, lacking quantifiable guidance, and it is difficult to achieve the expected results.

To this end, the present invention proposes a multi-objective optimization gas-solid two-phase flow heating system design method and system.

Summary of the invention

The present invention aims to solve at least one of the technical problems existing in the prior art. To this end, the present invention proposes a multi-objective optimization gas-solid two-phase flow heating system design method and system, which can complete the system structure design and process optimization before the gas-solid two-phase flow heating system is constructed.

To achieve the above objectives, a multi-objective optimization design method for a gas-solid two-phase flow heating system is proposed, which includes the following steps:

Step 1: Collect heat transfer coefficient training sample data and slip velocity training sample data in advance;

Step 2: training a heat transfer coefficient prediction model based on the heat transfer coefficient training sample data, and training a slip velocity prediction model based on the slip velocity training sample data;

Step 3: Collect parameter value sets of constant parameters of the heating system;

Step 4: Design a set of design variables for the gas-solid two-phase flow heating system; collect the heat transfer coefficient fitting function corresponding to the heat transfer coefficient prediction model, and collect the slip velocity fitting function corresponding to the slip velocity prediction model;

Step 5: Design a system design optimization problem based on the design variable set, the parameter values of the constant parameters, the heat transfer coefficient fitting function and the slip velocity fitting function;

Step 6: Solve the system design optimization problem to obtain the solution set of design variables, and based on the solution set, perform parameter design on the gas-solid two-phase flow heating system;

The collection of the heat transfer coefficient training sample data comprises the following steps:

Step 11: Build an experimental environment for the gas-solid two-phase flow heating system, and conduct N1 sets of first gas-solid two-phase flow heating experiments in the experimental environment. The characteristic values in the heat transfer coefficient characteristic value set of each first gas-solid two-phase flow heating experiment are different from each other; N1 is the number of pre-selected first gas-solid two-phase flow heating experiments;

The heat transfer coefficient characteristics in the heat transfer coefficient characteristic value set include solid phase temperature, gas phase temperature, heat exchange area, gas phase velocity and solid phase velocity;

Step 12: For each first gas-solid two-phase flow heating experiment, when the fluctuations of various physical quantities in the experimental environment tend to converge, measure and record the heat transfer efficiency η;

Step 13: Calculate the heat transfer coefficient ; The heat transfer coefficient The calculation formula is ; Where A is the heat exchange area, T_s and T_g are the solid phase temperature and gas phase temperature respectively;

Step 14: The heat transfer coefficient characteristic value sets of all the first gas-solid two-phase flow heating experiments are combined into heat transfer coefficient sample characteristic data, and the heat transfer coefficients of all the first gas-solid two-phase flow heating experiments are combined into heat transfer coefficient sample label data; the heat transfer coefficient training sample data includes heat transfer coefficient sample characteristic data and heat transfer coefficient sample label data;

The collection of the slip speed training sample data comprises the following steps:

Step 21: construct an experimental environment for a gas-solid two-phase flow heating system, and conduct N2 sets of second gas-solid two-phase flow heating experiments in the experimental environment, wherein the characteristic values in the slip velocity characteristic value set of each second gas-solid two-phase flow heating experiment are different from each other; N2 is the number of pre-selected second gas-solid two-phase flow heating experiments;

The slip velocity characteristics in the slip velocity characteristic value set include gas-solid flow ratio, gas phase velocity and solid phase velocity;

Step 22: using a high-speed camera or a laser velocimeter to measure the average slip velocities of the gas phase and the solid phase in the heating pipeline of each group of the second gas-solid two-phase flow heating experiment;

Step 23: The slip velocity characteristic value sets of all the second gas-solid two-phase flow heating experiments are composed of slip velocity sample characteristic data, and the average slip velocity of all the second gas-solid two-phase flow heating experiments are composed of slip velocity label data; the slip velocity training sample data includes slip velocity sample characteristic data and slip velocity label data;

The method of training the heat transfer coefficient prediction model is:

Each heat transfer coefficient characteristic value set in the heat transfer coefficient training sample data is used as the input of the heat transfer coefficient prediction model, the heat transfer coefficient prediction model uses the predicted value of the heat transfer coefficient of the first gas-solid two-phase flow heating experiment corresponding to the heat transfer coefficient characteristic value set as the output, uses the heat transfer coefficient of the first gas-solid two-phase flow heating experiment as the prediction target, uses the difference between the predicted value of the heat transfer coefficient and the heat transfer coefficient as the first prediction error, and uses minimizing the sum of the first prediction errors as the training target; the heat transfer coefficient prediction model is trained until the sum of the first prediction errors reaches convergence, and the training is stopped; the heat transfer coefficient prediction model is a polynomial regression model; the sum of the first prediction errors is a mean square error;

The method of training the slip velocity prediction model is:

Each slip speed characteristic value set in the slip speed training sample data is used as the input of the slip speed prediction model, the slip speed prediction model uses the predicted value of the slip speed of the second gas-solid two-phase flow heating experiment corresponding to the slip speed characteristic value set as the output, uses the average slip speed of the second gas-solid two-phase flow heating experiment as the prediction target, uses the difference between the predicted value of the slip speed and the average slip speed as the second prediction error, and uses minimizing the sum of the second prediction errors as the training target; the slip speed prediction model is trained until the sum of the second prediction errors reaches convergence and the training is stopped; the slip speed prediction model is a polynomial regression model; the sum of the second prediction errors is a mean square error;

The method of collecting the parameter value set of the constant parameters of the heating system is:

The fixed values of various known constant parameters in the gas-solid two-phase flow heating system to be designed are collected in advance to form a parameter value set of constant parameters, wherein the constant parameters include the wear empirical constant K_s, the solid phase density , solid phase viscosity coefficient , gas phase viscosity coefficient , friction coefficient f inside the pipeline, pipeline length L, pipeline diameter D, volume fraction α, gas phase density , the pressure drop empirical index n and the known power of the heater ;

The method of designing the design variable set of the gas-solid two-phase flow heating system is:

Set the solid phase temperature variable T_s, gas phase temperature variable T_g, solid phase velocity vector variable u_s, gas phase velocity vector variable u_g, heat exchange area variable A and gas-solid flow ratio variable B to form a design variable set;

The method of collecting the heat transfer coefficient fitting function corresponding to the heat transfer coefficient prediction model and collecting the slip velocity fitting function corresponding to the slip velocity prediction model is:

Obtaining a polynomial function relationship expression between a heat transfer coefficient characteristic value set of a trained heat transfer coefficient prediction model and a predicted value of the heat transfer coefficient as a heat transfer coefficient fitting function;

Obtaining a polynomial function relationship expression between a set of slip speed characteristic values corresponding to the trained slip speed prediction model and a predicted value of the slip speed as a slip speed fitting function;

The heat transfer coefficient fitting function is labeled as γ(A, T_s, T_g, u_s, u_g), and the slip velocity fitting function is labeled as v_slip(B, u_s, u_g);

The design system design optimization problem is as follows:

Design optimization objective function G(T_s,T_g,u_s,u_g,A,B);

The optimization objective function is: G(T_s,T_g,u_s,u_g,A,B)=k1 η(T_s,T_g,u_s,u_g,A)+k2 W(u_s,u_g,B)+k3 ΔP(u_g); where k1, k2 and k3 are preset proportional coefficients respectively;

in, ,

η(T_s,T_g,u_s,u_g,A) represents the heat transfer efficiency;

in, ; Among them, Re_s is the solid phase Reynolds number, and the calculation formula of Re_s is ; W(u_s,u_g,B) represents the wear rate;

Where, ΔP(u_g)= ; ΔP(u_g) represents the pressure drop in the pipeline;

Design a set of constraint conditions S, the constraint conditions contained in the constraint condition set S are:

Limitation 1: ;in, represents the divergence operator;

Limitation 2: ;

Limitation 3: ;

Limitation 4: ;

Limitation 5: ;

The system design optimization problem is a convex optimization problem with maximizing the optimization objective function as the optimization objective, each design variable in the design variable set as the variable set, and a constraint condition set S as the constraint condition;

The system design optimization problem is solved to obtain a solution set of design variables. Based on the solution set, the method for parameter design of the gas-solid two-phase flow heating system is as follows:

By using genetic algorithms or ant colony algorithms to solve the system design optimization problem, the solutions corresponding to each design variable are obtained to form a solution set;

The solid phase temperature, gas phase temperature, solid phase velocity vector, gas phase velocity vector, heat exchange area and gas-solid flow ratio in the gas-solid two-phase flow heating system to be designed are set to the variable value of the solid phase temperature variable T_s, the variable value of the gas phase temperature variable T_g, the variable value of the solid phase velocity vector variable u_s, the variable value of the gas phase velocity vector variable u_g, the variable value of the heat exchange area variable A and the variable value of the gas-solid flow ratio variable B in the solution set respectively.

A multi-objective optimization gas-solid two-phase flow heating system design system is proposed, which includes a training data collection module, a prediction model training module, a parameter collection module and a system design module; wherein each module is electrically connected;

A training data collection module, used for pre-collecting heat transfer coefficient training sample data and slip velocity training sample data, and sending the heat transfer coefficient training sample data and slip velocity training sample data to the prediction model training module;

A prediction model training module, which trains a heat transfer coefficient prediction model based on the heat transfer coefficient training sample data, and trains a slip velocity prediction model based on the slip velocity training sample data, and sends the heat transfer coefficient prediction model and the slip velocity prediction model to the system design module;

A parameter collection module collects the parameter value set of the constant parameters of the heating system and designs the design variable set of the gas-solid two-phase flow heating system; collects the heat transfer coefficient fitting function corresponding to the heat transfer coefficient prediction model and the slip velocity fitting function corresponding to the slip velocity prediction model, and sends the parameter value set of the constant parameters, the design variable set, the heat transfer coefficient fitting function and the slip velocity fitting function to the system design module;

The system design module designs the system design optimization problem based on the design variable set, the parameter values of the constant parameters, the heat transfer coefficient fitting function and the slip velocity fitting function, solves the system design optimization problem, obtains the solution set of the design variables, and performs parameter design on the gas-solid two-phase flow heating system based on the solution set.

An electronic device is proposed, comprising: a processor and a memory, wherein the memory stores a computer program that can be called by the processor;

The processor executes the above-mentioned multi-objective optimization gas-solid two-phase flow heating system design method by calling the computer program stored in the memory.

A computer-readable storage medium is provided, on which a rewritable computer program is stored;

When the computer program is executed on a computer device, the computer device is enabled to execute the above-mentioned multi-objective optimization method for designing a gas-solid two-phase flow heating system.

Compared with the prior art, the present invention has the following beneficial effects:

The present invention collects heat transfer coefficient training sample data and slip velocity training sample data in advance, trains a heat transfer coefficient prediction model based on the heat transfer coefficient training sample data, and trains a slip velocity prediction model based on the slip velocity training sample data, collects a parameter value set of constant parameters of the heating system, and designs a design variable set of the gas-solid two-phase flow heating system; collects a heat transfer coefficient fitting function corresponding to the heat transfer coefficient prediction model, and collects a slip velocity fitting function corresponding to the slip velocity prediction model, designs a system design optimization problem based on the design variable set, the parameter values of the constant parameters, the heat transfer coefficient fitting function and the slip velocity fitting function, solves the system design optimization problem, obtains a solution set of the design variables, and performs parameter design on the gas-solid two-phase flow heating system based on the solution set; comprehensively considers multiple optimization targets such as heat exchange efficiency, wear life, and flow resistance, establishes a mathematical model of the gas-solid two-phase flow heating system, and uses intelligent optimization technologies such as evolutionary algorithms and particle swarm optimization to search for the optimal design solution in the parameter space, thereby completing system structure design and process optimization before the gas-solid two-phase flow heating system is built.

BRIEF DESCRIPTION OF THE DRAWINGS

FIG1 is a flow chart of a multi-objective optimization method for designing a gas-solid two-phase flow heating system in Example 1 of the present invention;

FIG2 is a module connection relationship diagram of a multi-objective optimization gas-solid two-phase flow heating system design system in Example 2 of the present invention;

FIG3 is a schematic diagram of the structure of an electronic device in Embodiment 3 of the present invention;

FIG. 4 is a schematic diagram of the structure of a computer-readable storage medium in Embodiment 4 of the present invention.

DETAILED DESCRIPTION

The technical scheme of the present invention will be clearly and completely described below in conjunction with the embodiments. Obviously, the described embodiments are only part of the embodiments of the present invention, rather than all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

Example 1

As shown in FIG1 , a multi-objective optimization design method for a gas-solid two-phase flow heating system includes the following steps:

Step 1: Collect heat transfer coefficient training sample data and slip velocity training sample data in advance;

Step 2: training a heat transfer coefficient prediction model based on the heat transfer coefficient training sample data, and training a slip velocity prediction model based on the slip velocity training sample data;

Step 3: Collect parameter value sets of constant parameters of the heating system;

Step 4: Design a set of design variables for the gas-solid two-phase flow heating system; collect the heat transfer coefficient fitting function corresponding to the heat transfer coefficient prediction model, and collect the slip velocity fitting function corresponding to the slip velocity prediction model;

Step 5: Design a system design optimization problem based on the design variable set, the parameter values of the constant parameters, the heat transfer coefficient fitting function and the slip velocity fitting function;

Step 6: Solve the system design optimization problem to obtain the solution set of design variables, and based on the solution set, perform parameter design on the gas-solid two-phase flow heating system;

The collection of the heat transfer coefficient training sample data includes the following steps:

Step 11: Build an experimental environment for the gas-solid two-phase flow heating system, and conduct N1 sets of first gas-solid two-phase flow heating experiments in the experimental environment. The characteristic values in the heat transfer coefficient characteristic value set of each first gas-solid two-phase flow heating experiment are different from each other; N1 is the number of pre-selected first gas-solid two-phase flow heating experiments;

Specifically, the setting up of the experimental environment includes: setting up a gas-solid two-phase flow heating pipeline experimental device, preparing a high-precision temperature sensor (such as a thermocouple), preparing a heater with known power, and preparing the gas and solid particles required for the gas-solid two-phase flow experiment;

The heat transfer coefficient characteristics in the heat transfer coefficient characteristic value set include solid phase temperature, gas phase temperature, heat exchange area, gas phase velocity and solid phase velocity;

Step 12: For each first gas-solid two-phase flow heating experiment, when the fluctuations of various physical quantities in the experimental environment tend to converge, measure and record the heat transfer efficiency η;

The heat transfer efficiency η is calculated as follows: η= ;in , where Q_air is the air side energy of the gas-solid two-phase fluid inlet and outlet, and Q_solid is the solid particle side energy of the gas-solid two-phase fluid inlet and outlet; it can be understood that It expresses the actual electrical power used by the heating system in the first gas-solid two-phase flow heating experiment; is the known power of the heater;

Step 13: Calculate the heat transfer coefficient ; The heat transfer coefficient The calculation formula is ; Where A is the heat exchange area, T_s and T_g are the solid phase temperature and gas phase temperature respectively;

Step 14: The heat transfer coefficient characteristic value sets of all the first gas-solid two-phase flow heating experiments are combined into heat transfer coefficient sample characteristic data, and the heat transfer coefficients of all the first gas-solid two-phase flow heating experiments are combined into heat transfer coefficient sample label data; the heat transfer coefficient training sample data includes heat transfer coefficient sample characteristic data and heat transfer coefficient sample label data;

Furthermore, the collection of the slip speed training sample data includes the following steps:

Step 21: construct an experimental environment for a gas-solid two-phase flow heating system, and conduct N2 sets of second gas-solid two-phase flow heating experiments in the experimental environment, wherein the characteristic values in the slip velocity characteristic value set of each second gas-solid two-phase flow heating experiment are different from each other; N2 is the number of pre-selected second gas-solid two-phase flow heating experiments;

The slip velocity characteristics in the slip velocity characteristic value set include gas-solid flow ratio, gas phase velocity and solid phase velocity;

Step 22: using a high-speed camera or a laser velocimeter to measure the average slip velocities of the gas phase and the solid phase in the heating pipeline of each group of the second gas-solid two-phase flow heating experiment;

Step 23: The slip velocity characteristic value sets of all the second gas-solid two-phase flow heating experiments are composed of slip velocity sample characteristic data, and the average slip velocity of all the second gas-solid two-phase flow heating experiments are composed of slip velocity label data; the slip velocity training sample data includes slip velocity sample characteristic data and slip velocity label data;

Furthermore, the method of training the heat transfer coefficient prediction model based on the heat transfer coefficient training sample data is:

Each heat transfer coefficient characteristic value set in the heat transfer coefficient training sample data is used as the input of the heat transfer coefficient prediction model, the heat transfer coefficient prediction model uses the predicted value of the heat transfer coefficient of the first gas-solid two-phase flow heating experiment corresponding to the heat transfer coefficient characteristic value set as the output, uses the heat transfer coefficient of the first gas-solid two-phase flow heating experiment as the prediction target, uses the difference between the predicted value of the heat transfer coefficient and the heat transfer coefficient as the first prediction error, and uses minimizing the sum of the first prediction errors as the training target; the heat transfer coefficient prediction model is trained until the sum of the first prediction errors reaches convergence, and the training is stopped; the heat transfer coefficient prediction model is a polynomial regression model; the sum of the first prediction errors is a mean square error;

Furthermore, the method of training the slip speed prediction model based on the slip speed training sample data is:

Each slip speed characteristic value set in the slip speed training sample data is used as the input of the slip speed prediction model, the slip speed prediction model uses the predicted value of the slip speed of the second gas-solid two-phase flow heating experiment corresponding to the slip speed characteristic value set as the output, uses the average slip speed of the second gas-solid two-phase flow heating experiment as the prediction target, uses the difference between the predicted value of the slip speed and the average slip speed as the second prediction error, and uses minimizing the sum of the second prediction errors as the training target; the slip speed prediction model is trained until the sum of the second prediction errors reaches convergence and the training is stopped; the slip speed prediction model is a polynomial regression model; the sum of the second prediction errors is a mean square error;

Furthermore, the method of collecting the parameter value set of the constant parameters of the heating system is:

The fixed values of various known constant parameters in the gas-solid two-phase flow heating system to be designed are collected in advance to form a parameter value set of constant parameters, wherein the constant parameters include the wear empirical constant K_s, the solid phase density , solid phase viscosity coefficient , gas phase viscosity coefficient , friction coefficient f inside the pipeline, pipeline length L, pipeline diameter D, volume fraction α, gas phase density , the pressure drop empirical index n and the known power of the heater ; It can be understood that the wear empirical constant, the friction coefficient inside the pipeline, the pipeline length L and the pipeline diameter are constant parameters that can be determined after the pipeline is determined. The solid phase density, solid phase viscosity coefficient, gas phase viscosity coefficient, gas phase density and pressure drop empirical index can all be obtained by querying the basic properties of the substances corresponding to the gas phase and the solid phase, that is, by looking up the table; the volume fraction can be collected by the gamma ray method or the shutter method;

Furthermore, the design variable set of the gas-solid two-phase flow heating system is designed in the following manner:

Set the solid phase temperature variable T_s, gas phase temperature variable T_g, solid phase velocity vector variable u_s, gas phase velocity vector variable u_g, heat exchange area variable A and gas-solid flow ratio variable B to form a design variable set;

It can be understood that the design variable set is the parameters that need to be designed when constructing the gas-solid two-phase flow heating system. After determining the parameter values that need to be designed, the parameters corresponding to the gas-solid two-phase flow heating system are set to the corresponding determined parameter values. For example, after obtaining the parameter value of the solid phase temperature variable T_s, the solid phase temperature corresponding to the gas-solid two-phase flow heating system is set to the parameter value;

Furthermore, the method of collecting the heat transfer coefficient fitting function corresponding to the heat transfer coefficient prediction model and collecting the slip velocity fitting function corresponding to the slip velocity prediction model is:

Obtaining a polynomial function relationship expression between a heat transfer coefficient characteristic value set of a trained heat transfer coefficient prediction model and a predicted value of the heat transfer coefficient as a heat transfer coefficient fitting function;

Obtaining a polynomial function relationship expression between a set of slip speed characteristic values corresponding to the trained slip speed prediction model and a predicted value of the slip speed as a slip speed fitting function;

The heat transfer coefficient fitting function is labeled as γ(A, T_s, T_g, u_s, u_g), and the slip velocity fitting function is labeled as v_slip(B, u_s, u_g);

Furthermore, the method of designing the system design optimization problem based on the design variable set, the parameter value of the constant parameter, the heat transfer coefficient fitting function and the slip velocity fitting function is:

Design optimization objective function G(T_s,T_g,u_s,u_g,A,B);

The optimization objective function is:

The optimization objective function is: G(T_s,T_g,u_s,u_g,A,B)=k1 η(T_s,T_g,u_s,u_g,A)+k2 W(u_s,u_g,B)+k3 ΔP(u_g); where k1, k2 and k3 are preset proportional coefficients respectively;

in, ,

η(T_s,T_g,u_s,u_g,A) represents the heat transfer efficiency. For the heat transfer efficiency, the optimization goal is to maximize the heat transfer efficiency as much as possible;

Where W(u_s,u_g,B)=K ; Among them, Re_s is the solid phase Reynolds number, and the calculation formula of Re_s is ; W(u_s,u_g,B) represents the wear rate. For the wear rate, the optimization goal is to minimize the wear rate as much as possible;

Where, ΔP(u_g)= ; ΔP(u_g) represents the pressure drop in the pipeline, which refers to the pressure loss caused by gas flow resistance when the gas phase flows through the pipeline or equipment; for the pressure drop, the optimization goal is to minimize the pressure drop as much as possible;

Design a set of constraint conditions S, the constraint conditions contained in the constraint condition set S are:

Limitation 1: ;in, Represents the divergence operator; restriction 1 ensures that the mass of the entire gas-solid two-phase flow system is conserved, that is, the total amount of mass does not increase or decrease. The terms on the left side of the equation describe the divergence of the gas and solid mass flows, and their sum is 0, which means that the net mass flow in and out of the control volume per unit time is 0. This restriction ensures the conservation of mass of the entire system;

Specifically, the divergence operator for any vector field A1 is defined as:

;

Where A1_x, A1_y, A1_z are the components of vector A1 in the x, y, z directions respectively;

Divergence describes the behavior of a vector field spreading outward from a certain point. Its essence is the summation of the partial derivatives of the vector field in all directions;

Limitation 2: ; Constraint 2 describes the conservation of momentum in the gas phase. The left side term is the convection term of the gas phase momentum; the right side is the pressure gradient term, the viscous force term, and the mutual coupling term with the solid phase. This constraint ensures that the net rate of change of momentum of the gas phase under the action of external forces (pressure, viscous shear stress, and solid phase resistance) is equal to the sum of the forces;

Limitation 3: ; Constraint 3 describes the conservation of momentum in the solid phase. The physical meaning of the term is similar to that of the gas phase, except that there is an additional term of solid phase pressure gradient ∇P_s, which describes the interaction force between particles. This equation ensures that the net change in momentum of the solid phase under the action of external forces (pressure, viscous shear and gas phase resistance) is equal to the sum of the forces;

Limitation 4: ; Restriction 4 describes the energy conservation of the gas phase. The left-hand term is the convection term of the gas phase energy (enthalpy); the first term on the right is the gas phase heat conduction term, and the second term is the convection heat transfer source term between the gas and the solid. This restriction ensures that the net change in total energy during the flow and heat transfer of the gas phase is equal to the net inflow of heat;

Limitation 5: ; Restriction 5 describes the energy conservation of the solid phase. The physical meaning of the term is similar to that of the gas phase energy equation, except that the sign of the convective heat transfer source term is opposite, indicating that heat is transferred from the solid phase to the gas phase. This restriction ensures that the net change in total energy during the flow and heat transfer of the solid phase is equal to the net outflow of heat;

The system design optimization problem is a convex optimization problem with maximizing the optimization objective function as the optimization objective, each design variable in the design variable set as the variable set, and a constraint condition set S as the constraint condition;

Furthermore, the system design optimization problem is solved to obtain a solution set of design variables. Based on the solution set, the parameter design method of the gas-solid two-phase flow heating system is as follows:

By using genetic algorithms or ant colony algorithms to solve the system design optimization problem, the solutions corresponding to each design variable are obtained to form a solution set;

The solid phase temperature, gas phase temperature, solid phase velocity vector, gas phase velocity vector, heat exchange area and gas-solid flow ratio in the gas-solid two-phase flow heating system to be designed are set to the variable value of the solid phase temperature variable T_s, the variable value of the gas phase temperature variable T_g, the variable value of the solid phase velocity vector variable u_s, the variable value of the gas phase velocity vector variable u_g, the variable value of the heat exchange area variable A and the variable value of the gas-solid flow ratio variable B in the solution set respectively.

Example 2

As shown in FIG2 , a multi-objective optimization gas-solid two-phase flow heating system design system includes a training data collection module, a prediction model training module, a parameter collection module, and a system design module; wherein each module is electrically connected;

A training data collection module, used for pre-collecting heat transfer coefficient training sample data and slip velocity training sample data, and sending the heat transfer coefficient training sample data and slip velocity training sample data to the prediction model training module;

A prediction model training module, which trains a heat transfer coefficient prediction model based on the heat transfer coefficient training sample data, and trains a slip velocity prediction model based on the slip velocity training sample data, and sends the heat transfer coefficient prediction model and the slip velocity prediction model to the system design module;

A parameter collection module collects the parameter value set of the constant parameters of the heating system and designs the design variable set of the gas-solid two-phase flow heating system; collects the heat transfer coefficient fitting function corresponding to the heat transfer coefficient prediction model and the slip velocity fitting function corresponding to the slip velocity prediction model, and sends the parameter value set of the constant parameters, the design variable set, the heat transfer coefficient fitting function and the slip velocity fitting function to the system design module;

The system design module designs the system design optimization problem based on the design variable set, the parameter values of the constant parameters, the heat transfer coefficient fitting function and the slip velocity fitting function, solves the system design optimization problem, obtains the solution set of the design variables, and performs parameter design on the gas-solid two-phase flow heating system based on the solution set.

Example 3

FIG3 is a schematic diagram of the structure of an electronic device provided by an embodiment of the present application. As shown in FIG3, according to another aspect of the present application, an electronic device 100 is also provided. The electronic device 100 may include one or more processors and one or more memories. The memory stores a computer readable code, and when the computer readable code is executed by one or more processors, it can execute a multi-objective optimization gas-solid two-phase flow heating system design method as described above.

The method or device according to the embodiment of the present application can also be implemented with the aid of the architecture of the electronic device shown in FIG3. As shown in FIG3, the electronic device 100 may include a bus 101, one or more CPUs 102, a ROM 103, a RAM 104, a communication port 105 connected to a network, an input/output component 106, a hard disk 107, etc. The storage device in the electronic device 100, such as the ROM 103 or the hard disk 107, may store a multi-objective optimization gas-solid two-phase flow heating system design method provided in the present application.

Furthermore, the electronic device 100 may further include a user interface 108. Of course, the architecture shown in FIG3 is only exemplary, and when implementing different devices, one or more components in the electronic device shown in FIG3 may be omitted according to actual needs.

Example 4

FIG4 is a schematic diagram of the structure of a computer-readable storage medium provided by an embodiment of the present application. As shown in FIG4, it is a computer-readable storage medium 200 according to an embodiment of the present application. Computer-readable instructions are stored on the computer-readable storage medium 200. When the computer-readable instructions are executed by the processor, a multi-objective optimization gas-solid two-phase flow heating system design method according to an embodiment of the present application described with reference to the above figures can be executed. The computer-readable storage medium 200 includes, but is not limited to, for example, volatile memory and/or non-volatile memory. Volatile memory may include, for example, random access memory (RAM) and cache memory (cache), etc. Non-volatile memory may include, for example, read-only memory (ROM), hard disk, flash memory, etc.

In addition, according to the implementation of the present application, the process described above with reference to the flowchart can be implemented as a computer software program. For example, the present application provides a non-transitory machine-readable storage medium, the non-transitory machine-readable storage medium stores machine-readable instructions, the machine-readable instructions can be run by a processor to execute instructions corresponding to the method steps provided by the present application, and when the computer program is executed by a central processing unit (CPU), the above functions defined in the method of the present application are executed.

The method, apparatus, and device of the present application may be implemented in many ways. For example, the method, apparatus, and device of the present application may be implemented by software, hardware, firmware, or any combination of software, hardware, and firmware. The above order of steps for the method is for illustration only, and the steps of the method of the present application are not limited to the order specifically described above unless otherwise specified. In addition, in some embodiments, the present application may also be implemented as a program recorded in a recording medium, which includes machine-readable instructions for implementing the method according to the present application. Therefore, the present application also covers a recording medium storing a program for executing the method according to the present application.

In addition, the parts of the above-mentioned technical solutions provided in the embodiments of the present application that are consistent with the implementation principles of the corresponding technical solutions in the prior art are not described in detail to avoid excessive redundancy.

The specific implementation modes described above further describe the purpose, technical solutions and beneficial effects of the present invention. It should be understood that the above description is only a specific implementation mode of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention should be included in the protection scope of the present invention.

The above preset parameters or preset thresholds are all set by technicians in this field according to actual conditions or obtained by simulating a large amount of data.

The above embodiments are only used to illustrate the technical method of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical method of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical method of the present invention.

Claims (9)

1. The design method of the multi-target optimized gas-solid two-phase flow heating system is characterized by comprising the following steps of:

step one: collecting heat transfer coefficient training sample data and slip speed training sample data in advance;

Step two: training a heat transfer coefficient prediction model based on the heat transfer coefficient training sample data, and training a slip speed prediction model based on the slip speed training sample data;

step three: collecting a parameter value set of constant parameters of the heating system;

step four: designing a design variable set of the gas-solid two-phase flow heating system; collecting a heat transfer coefficient fitting function corresponding to the heat transfer coefficient prediction model, and collecting a slip speed fitting function corresponding to the slip speed prediction model;

step five: designing a system design optimization problem based on the design variable set, parameter values of constant parameters, a heat transfer coefficient fitting function and a slip speed fitting function;

Step six: solving a system design optimization problem to obtain a solution set of design variables, and carrying out parameter design on the gas-solid two-phase flow heating system based on the solution set;

The method for collecting the parameter value set of the constant parameter of the heating system is as follows:

The method comprises the steps of collecting parameter value sets of constant parameters comprising wear empirical constants K_s and solid phase density of fixed values of known constant parameters in a gas-solid two-phase flow heating system to be designed in advance Coefficient of solid phase viscosityCoefficient of gas phase viscosityCoefficient of friction f in the pipe, pipe length L, pipe diameter D, volume fraction alpha, gas phase densityPressure drop empirical index n and heater known power；

The design variable set mode of the design gas-solid two-phase flow heating system is as follows:

setting a solid phase temperature variable T_s, a gas phase temperature variable T_g, a solid phase speed vector variable u_s, a gas phase speed vector variable u_g, a heat exchange area variable A and a gas-solid flow ratio variable B to form a design variable set;

The method for collecting the heat transfer coefficient fitting function corresponding to the heat transfer coefficient prediction model and collecting the slip speed fitting function corresponding to the slip speed prediction model comprises the following steps:

Acquiring a polynomial function relation expression between a heat transfer coefficient characteristic value set of the trained heat transfer coefficient prediction model and a predicted value of a heat transfer coefficient as a heat transfer coefficient fitting function;

Acquiring a polynomial function relation expression between a slip speed characteristic value set corresponding to the slip speed prediction model after training and a predicted value of the slip speed as a slip speed fitting function;

The heat transfer coefficient fitting function is labeled γ (a, t_s, t_g, u_s, u_g), and the slip velocity fitting function is labeled v_slip (B, u_s, u_g);

The design system design optimization problem is as follows:

designing optimization objective functions G (T_s, T_g, u_s, u_g, A, B);

the optimization objective function is as follows: g (t_s, t_g, u_s, u_g, a, B) =k1 η(T_s,T_g,u_s,u_g,A)+k2W(u_s,u_g,B)+k3Δp (u_g); wherein k1, k2 and k3 are respectively preset proportionality coefficients;

wherein η (t_s, t_g, u_s, u_g, a) = Η (t_s, t_g, u_s, u_g, a) represents the heat transfer efficiency;

wherein W (u_s, u_g, B) =k ; Wherein Re_s is the solid phase Reynolds number, and the calculation formula of Re_s is; W (u_s, u_g, B) represents the wear rate;

Wherein Δp (u_g) = ; ΔP (u_g) represents the pressure drop within the pipe;

designing a limiting condition set S, wherein the limiting conditions contained in the limiting condition set S are as follows:

Limit 1: ·(αρ_gu_g +(1-α)ρ_s u_s) =0; wherein, Representing a divergent operator;

limit 2: ·(αρ_g ) = -αΔP (u_g)+ ·(αμ_g) + α(u_s-u_g)；

Limit 3: ·((1-α)ρ_s ) = -(1-α)ΔP (u_g)+ ·((1-α)μ_s) - α(u_s-u_g)；

limit 4: ·(αρ_g) = ·(αu_gT_g) + γ(A,T_s,T_g,u_s,u_g)(T_s-T_g)；

limit 5: ·((1-α)ρ_s) = ·((1-α)u_sT_s) -γ(A,T_s,T_g，u_s,u_g)(T_s-T_g)；

The system design optimization problem is a convex optimization problem which takes a maximized optimization objective function as an optimization target, takes each design variable in a design variable set as a variable set and takes a constraint condition set S as a constraint condition.

2. The method for designing a multi-objective optimized gas-solid two-phase flow heating system according to claim 1, wherein the collection of the heat transfer coefficient training sample data comprises the steps of:

Step 11: setting up an experimental environment of a gas-solid two-phase flow heating system, and carrying out N1 groups of first gas-solid two-phase flow heating experiments in the experimental environment, wherein characteristic values in a heat transfer coefficient characteristic value set of each first gas-solid two-phase flow heating experiment are different; n1 is the number of times of a preselected first gas-solid two-phase flow heating experiment;

The heat transfer coefficient characteristics in the heat transfer coefficient characteristic value set comprise solid phase temperature, gas phase temperature, heat exchange area, gas phase speed and solid phase speed;

Step 12: for each first gas-solid two-phase flow heating experiment, when each physical quantity fluctuation in the experimental environment tends to converge, measuring and recording the heat transfer efficiency eta;

Step 13: calculating heat transfer coefficient ; The heat transfer coefficientThe calculation formula of (2) is; Wherein A is the heat exchange area, T_s and T_g are the solid phase temperature and the gas phase temperature respectively,Knowing the power for the heater;

Step 14: the heat transfer coefficient characteristic values of all the first gas-solid two-phase flow heating experiments are assembled to form heat transfer coefficient sample characteristic data, and the heat transfer coefficients of all the first gas-solid two-phase flow heating experiments are assembled to form heat transfer coefficient sample label data; the heat transfer coefficient training sample data includes heat transfer coefficient sample feature data and heat transfer coefficient sample tag data.

3. The method for designing a multi-objective optimized gas-solid two-phase flow heating system according to claim 2, wherein the collection of the slip velocity training sample data comprises the steps of:

step 21: establishing an experimental environment of a gas-solid two-phase flow heating system, and carrying out N2 groups of second gas-solid two-phase flow heating experiments in the experimental environment, wherein characteristic values in a slip speed characteristic value set of each second gas-solid two-phase flow heating experiment are different; n2 is the number of times of the preselected second gas-solid two-phase flow heating experiment;

The slip speed characteristics in the slip speed characteristic value set comprise a gas-solid flow ratio, a gas phase speed and a solid phase speed;

Step 22: measuring the average sliding speed of the gas phase and the solid phase in a heating pipeline of each group of second gas-solid two-phase flow heating experiments by using a high-speed camera or a laser velocimeter;

Step 23: assembling the characteristic values of the sliding speeds of all the second gas-solid two-phase flow heating experiments into characteristic data of sliding speed samples, and assembling the average sliding speeds of all the second gas-solid two-phase flow heating experiments into sliding speed label data; the slip speed training sample data comprises slip speed sample characteristic data and slip speed label data.

4. The method for designing a multi-objective optimized gas-solid two-phase flow heating system according to claim 3, wherein the mode of training the heat transfer coefficient prediction model is as follows:

Taking each heat transfer coefficient characteristic value set in the heat transfer coefficient training sample data as input of a heat transfer coefficient prediction model, wherein the heat transfer coefficient prediction model takes a predicted value of a heat transfer coefficient of a first gas-solid two-phase flow heating experiment corresponding to the heat transfer coefficient characteristic value set as output, takes the heat transfer coefficient of the first gas-solid two-phase flow heating experiment as a prediction target, takes a difference value between the predicted value of the heat transfer coefficient and the heat transfer coefficient as a first prediction error, and takes the sum of minimized first prediction errors as a training target; training the heat transfer coefficient prediction model until the sum of the first prediction errors reaches convergence; the heat transfer coefficient prediction model is a polynomial regression model; the sum of the first prediction errors is a mean square error.

5. The method for designing a multi-objective optimized gas-solid two-phase flow heating system according to claim 4, wherein the method for training the slip velocity prediction model is as follows:

Taking each sliding speed characteristic value set in sliding speed training sample data as input of a sliding speed prediction model, wherein the sliding speed prediction model takes a predicted value of the sliding speed of a second gas-solid two-phase flow heating experiment corresponding to the sliding speed characteristic value set as output, takes the average sliding speed of the second gas-solid two-phase flow heating experiment as a prediction target, takes a difference value between the predicted value of the sliding speed and the average sliding speed as a second prediction error, and takes the sum of minimized second prediction errors as a training target; training the slip speed prediction model until the sum of the second prediction errors reaches convergence, and stopping training; the sliding speed prediction model is a polynomial regression model; the sum of the second prediction errors is a mean square error.

6. The method for designing a multi-objective optimized gas-solid two-phase flow heating system according to claim 5, wherein the method for solving the system design optimization problem to obtain a solution set of design variables, and based on the solution set, performing parameter design on the gas-solid two-phase flow heating system is as follows:

Solving a system design optimization problem by using a genetic algorithm or an ant colony algorithm to obtain solutions corresponding to all design variables to form a solution set;

And setting the solid phase temperature, the gas phase temperature, the solid phase velocity vector, the gas phase velocity vector, the heat exchange area and the gas-solid flow ratio in the gas-solid two-phase flow heating system to be designed as the variable value of the solid phase temperature variable T_s, the variable value of the gas phase temperature variable T_g, the variable value of the solid phase velocity vector variable u_s, the variable value of the gas phase velocity vector variable u_g, the variable value of the heat exchange area variable A and the variable value of the gas-solid flow ratio variable B in the solution set respectively.

7. A multi-objective optimized gas-solid two-phase flow heating system design system for implementing the multi-objective optimized gas-solid two-phase flow heating system design method as set forth in any one of claims 1-6, characterized by comprising a training data collection module, a predictive model training module, a parameter collection module, and a system design module; wherein, each module is electrically connected;

the training data collection module is used for collecting heat transfer coefficient training sample data and slip speed training sample data in advance and sending the heat transfer coefficient training sample data and the slip speed training sample data to the prediction model training module;

The prediction model training module trains a heat transfer coefficient prediction model based on the heat transfer coefficient training sample data, trains a slip speed prediction model based on the slip speed training sample data, and sends the heat transfer coefficient prediction model and the slip speed prediction model to the system design module;

The parameter collection module is used for collecting parameter value sets of constant parameters of the heating system and designing a design variable set of the gas-solid two-phase flow heating system; collecting a heat transfer coefficient fitting function corresponding to the heat transfer coefficient prediction model, collecting a slip speed fitting function corresponding to the slip speed prediction model, and sending a parameter value set of constant parameters, a design variable set, the heat transfer coefficient fitting function and the slip speed fitting function to a system design module;

The system design module is used for designing a system design optimization problem based on the design variable set, parameter values of constant parameters, a heat transfer coefficient fitting function and a slip speed fitting function, solving the system design optimization problem to obtain a solution set of the design variables, and carrying out parameter design on the gas-solid two-phase flow heating system based on the solution set.

8. An electronic device, comprising: a processor and a memory, wherein:

The memory stores a computer program which can be called by the processor;

The processor executes a multi-objective optimized gas-solid two-phase flow heating system design method according to any one of claims 1-6 in the background by calling a computer program stored in the memory.

9. A computer readable storage medium having stored thereon a computer program that is erasable;

The computer program, when run on a computer device, causes the computer device to perform a multi-objective optimized gas-solid two-phase flow heating system design method as claimed in any one of claims 1-6 in the background.