CFD-based greenhouse environment optimization method and device, medium and product

Abstract

The invention discloses a CFD-based greenhouse environment optimization method and device, a medium and a product, and relates to the technical field of greenhouse environment optimizing.The method comprises the steps that multiple sets of environment parameters of a greenhouse are initialized, and multiple sets of initial parameters are obtained; the environment parameters comprise the air speed of each fan and the temperature of a wet curtain in the greenhouse; constructing a target function; the objective functions comprise a temperature suitability function, a CO2 uniformity function and an operation energy consumption function; optimizing each initial parameter by using a multi-target particle swarm optimization algorithm to obtain a plurality of groups of optimized environmental parameters; determining control variable values of the environmental parameters based on the objective function and the plurality of groups of optimized environmental parameters by using CFD (Computational Fluid Dynamics); and controlling the greenhouse by using the control variable values of the environmental parameters. Uniformity and economical efficiency regulation and control of the greenhouse environment are achieved.

Description

Technical Field

[0001] The present application relates to the technical field of greenhouse environment optimization, and in particular to a greenhouse environment optimization method, device, medium and product based on CFD. Background Art

[0002] In the context of insufficient per capita arable land in China, facility agriculture uses artificial technology to improve and create environmental factors suitable for crop growth to promote crop growth and increase crop yields. On the one hand, it can reduce and get rid of the constraints and dependence of traditional agriculture on the external environment. On the other hand, due to the semi-closed ecosystem, the self-regulation ability of the internal environment is limited, and the quality of its factors has a significant impact on crop growth and energy conservation and emission reduction. Due to the relatively backward regulation technology, greenhouses generally have low regulation levels, high energy consumption, and high operating costs, which seriously restricts the digitalization and intelligentization of facility cultivation.

[0003] Computational Fluid Dynamics (CFD) technology uses computers to qualitatively analyze and quantitatively describe the physical characteristics of fluid flow. In the field of agricultural facilities, it is often used to simulate and study the indoor microenvironment climate of greenhouses. Combining CFD simulation technology to simulate the movement of airflow inside the greenhouse, the distribution of airflow and temperature fields can be grasped and analyzed, and then the optimal layout point with spatial representativeness in the greenhouse environment can be obtained, and research on sensor layout based on three-dimensional space can be carried out.

[0004] With the development of intelligent information and cloud data, facility agriculture has spawned a large number of intelligent control system equipment, and greenhouse environmental control technology mostly uses sensor feedback adjustment methods. Through real-time monitoring and uploading of environmental monitoring data to the cloud, the control background can set the greenhouse environmental control timing program based on expert experience and crop growth models, and mechanically execute the operation mode and operation time of environmental control equipment, which saves labor costs to a certain extent, avoids subjective errors, and makes greenhouse environmental control develop in the direction of automation and intelligence.

[0005] However, in the current control methods for greenhouse environments, most environmental factors are assumed to be uniformly distributed in space, and lumped parameters are used to evaluate the growth environment of crops. In fact, the greenhouse environment is a complex system with multiple variables, nonlinearity, and high coupling. The environmental factors in the crop planting area show obvious distributed parameter characteristics, which are significantly different from the monitoring data of limited sensor locations. The current environmental control strategy based on sensor feedback cannot accurately reflect the spatiotemporal variation characteristics of environmental factors inside the greenhouse. The crop growth conditions in different areas are different, which leads to low crop quality and yield. In addition, in order to achieve the required environmental parameter settings, the controller will programmatically execute the control plan based on the sensor feedback data. The control requirements can be met locally, but the overall environment may pay a greater control cost and consume too much energy. Summary of the invention

[0006] The purpose of this application is to provide a greenhouse environment optimization method, device, medium and product based on CFD to solve the problems of poor uniformity and economy of greenhouse environment regulation.

[0007] To achieve the above objectives, this application provides the following solutions.

[0008] In a first aspect, the present application provides a greenhouse environment optimization method based on CFD, comprising: Initializing multiple sets of environmental parameters of the greenhouse to obtain multiple sets of initial parameters; the environmental parameters include: wind speed of each fan in the greenhouse and temperature of the wet curtain; Constructing an objective function; the objective function includes: a temperature suitability function, a CO2 uniformity function and an operating energy consumption function; The multi-objective particle swarm optimization algorithm is used to optimize the initial parameters and obtain multiple groups of optimized environmental parameters; Determining control variable values ​​of environmental parameters based on the objective function and multiple sets of optimized environmental parameters using CFD; The greenhouse is controlled using the control variable values ​​of the environmental parameters.

[0009] Optionally, the temperature suitability function includes: ; in, is the temperature suitability value; For the greenhouse Tier The simulated temperature of each observation point; For the greenhouse The ideal temperature setting value of the layer; is the total number of observation points in the greenhouse.

[0010] Optionally, the CO2 uniformity function includes: ; in, is the CO2 uniformity value; For the greenhouse Tier Simulated CO2 concentration at each observation point; For the greenhouse The ideal CO2 concentration setting value for the layer.

[0011] Optionally, the running energy consumption function includes: ; in, is the operating energy consumption value; is the pressure change of the fan; The total volume flow rate of air supplied to the fan; The fan operating efficiency.

[0012] Optionally, a multi-objective particle swarm optimization algorithm is used to optimize each initial parameter to obtain multiple sets of optimized environmental parameters, including: Each group of initial parameters is used as the initial position of each particle in the multi-objective particle swarm optimization algorithm; The position of each particle is optimized for a preset number of iterations to obtain the optimized position of each particle in each iteration round; The optimized positions of each particle in each iteration round are determined as multiple sets of optimized environmental parameters.

[0013] Optionally, using CFD, based on the objective function and multiple sets of optimized environmental parameters, determining the control variable values ​​of the environmental parameters includes: Determine any set of optimized environmental parameters as current environmental parameters; Using CFD, according to the objective function, a simulation calculation is performed on the objective function corresponding to the current environmental parameters to obtain the objective function value corresponding to the current environmental parameters; The optimized environmental parameters whose objective function values ​​satisfy the non-dominated conditions are determined as the controlled variable values ​​of the environmental parameters.

[0014] Optionally, controlling the greenhouse using the control variable value of the environmental parameter includes: Fit the control variable values ​​of each environmental parameter to obtain the Pareto advantage surface of the control variable values; The greenhouse is controlled by the Pareto dominance surface of the control variable values.

[0015] In a second aspect, the present application provides a computer device, comprising: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement any of the CFD-based greenhouse environment optimization methods described above.

[0016] In a third aspect, the present application provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements any of the CFD-based greenhouse environment optimization methods described above.

[0017] In a fourth aspect, the present application provides a computer program product, including a computer program, which, when executed by a processor, implements any of the CFD-based greenhouse environment optimization methods described above.

[0018] According to the specific embodiments provided in this application, this application discloses the following technical effects: The present application discloses a greenhouse environment optimization method, device, medium and product based on CFD. First, multiple sets of greenhouse environmental parameters are initialized to obtain multiple sets of initial parameters; the environmental parameters include: wind speed of each fan in the greenhouse and temperature of wet curtain; secondly, an objective function is constructed; the objective function includes: temperature suitability function, CO2 uniformity function and operation energy consumption function; then, each initial parameter is optimized using a multi-objective particle swarm optimization algorithm to obtain multiple sets of optimized environmental parameters; thirdly, CFD is used to determine the control variable values ​​of the environmental parameters based on the objective function and multiple sets of optimized environmental parameters; finally, the greenhouse is controlled using the control variable values ​​of the environmental parameters. The present application constructs an objective function that takes into account time and space specificity, optimizes the environmental parameters through CFD and a multi-objective particle swarm optimization algorithm, and realizes the uniformity and economic regulation of the greenhouse environment. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0020] Figure 1 A schematic flow chart of a greenhouse environment optimization method based on CFD provided in one embodiment of the present application.

[0021] Figure 2 Schematic diagram of the observation surface distribution of greenhouse environmental parameters.

[0022] Figure 3 Schematic diagram of the multi-objective particle swarm optimization algorithm flow.

[0023] Figure 4 Schematic diagram of the specific process of greenhouse environment optimization strategy based on CFD.

[0024] Figure 5 Schematic diagram of the Pareto advantage surface for the control variable value.

[0025] Figure 6 A schematic diagram of the structure of a computer device provided in one embodiment of the present application. DETAILED DESCRIPTION

[0026] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0027] The purpose of this application is to provide a greenhouse environment optimization method, device, medium and product based on CFD, aiming to achieve uniformity and economic regulation of the greenhouse environment.

[0028] In order to make the above-mentioned objects, features and advantages of the present application more obvious and easy to understand, the present application is further described in detail below in conjunction with the accompanying drawings and specific implementation methods.

[0029] In an exemplary embodiment, Figure 1 As shown, the greenhouse environment optimization method based on CFD in this embodiment includes the following steps.

[0030] Step 1: Initialize multiple sets of environmental parameters of the greenhouse to obtain multiple sets of initial parameters; the environmental parameters include: wind speed of each fan in the greenhouse and temperature of the wet curtain.

[0031] Specifically, multiple groups of initial parameters are randomly generated within a set fan speed range and wet curtain temperature range.

[0032] Step 2: Construct the objective function; the objective function includes: temperature suitability function, CO2 uniformity function and operation energy consumption function.

[0033] Specifically, Figure 2As shown in the figure, considering that there are crops cultivated in the greenhouse, the environmental parameters have an obvious gradient distribution in the vertical direction, so the observation points are recursively arranged in the greenhouse space: three observation surfaces (F1, F2, F3) are arranged from bottom to top, with positions of 1m (crop vine height), 2.5m (crop canopy height), and 4.5m (highest part of the greenhouse); 9 observation points are arranged in a 3×3 arrangement on each observation surface, for a total of 27 observation points. Fluent will calculate the simulated temperature and simulated CO2 concentration after each simulation, and use the root mean square error function to compare with the ideal set value to evaluate the optimization and control effect of the greenhouse.

[0034] As an optional implementation, the temperature suitability function includes: .

[0035] in, is the temperature suitability value; For the greenhouse Tier The simulated temperature of each observation point; For the greenhouse The ideal temperature setting value of the layer; is the total number of observation points in the greenhouse.

[0036] As an optional implementation, the CO2 uniformity function includes: .

[0037] in, is the CO2 uniformity value; For the greenhouse Tier Simulated CO2 concentration at each observation point; For the greenhouse The ideal CO2 concentration setting value for the layer.

[0038] As an optional implementation, running the energy consumption function includes: .

[0039] in, is the operating energy consumption value; is the pressure change of the fan; The total volume flow rate of air supplied to the fan; The fan operating efficiency.

[0040] Step 3: Use the multi-objective particle swarm optimization algorithm to optimize the initial parameters and obtain multiple groups of optimized environmental parameters.

[0041] Specifically, since the objective function to be optimized is a typical multi-objective control problem, this application selects the Multi-Objective Particle Swarm Optimization (MOPSO) algorithm based on Pareto dominance relationship for optimization. The algorithm is inspired by the collaborative foraging behavior of bird flocks. In MOPSO, each bird is abstracted as a particle, and its foraging behavior is abstracted as an optimization process.

[0042] The concept of Pareto dominance in multi-objective optimization problems can be precisely described as follows: and are any two different individuals in the evolutionary population, called Dominate , then it must satisfy: for all sub-goals, No Difference, that is ,.in, is the number of objectives in the objective function, The value is 3, which means the above temperature suitability, CO2 uniformity, and operating energy consumption); is the objective function value.

[0043] like Figure 3 As shown in Figure 2, the implementation process of MOPSO includes the following contents.

[0044] When the algorithm starts running, each particle will randomly have its own initial position and flight speed within the decision range. The real-time position of the particle is the decision variable of the optimization problem, and the flight speed is determined by the optimal solution (dominant position) searched by the particle so far. Together with the external repository REP, the update formulas for speed and position are as follows.

[0045] .

[0046] .

[0047] in, For the The current speed of the particle; is the inertia weight coefficient; For the The leading speed of the particles; and All are learning factors; is the optimal solution (dominant position) that the particle has searched so far; For the The leading position of the particles; is the hth non-dominated particle; For the The current position of the particle. For the Memory item of particle front velocity; For the The decision vector of the particle at the historical memory position and the current position is identified as a self-cognition item; For the The correlation vector between the particle's historical non-dominated position and the current position is identified as the group cognition term. These three terms work together to update the The speed and position of the particle.

[0048] ① Selection: Determine the The dominant relationship between the particle's current position and its historical memory position is When the particle's current position is superior to (dominates) the position contained in its memory, use the formula To update; when When the position in the particle memory dominates the current position, the original ; If The current position of the particle and the original If they do not dominate each other, then randomly select one of them as the latest one. .

[0049] ② Selection: MOPSO defines an external repository REP to store the archive set Archive of non-dominated particle groups discovered cumulatively during the search process.

[0050] In the decision-making process, the position vector generated by each iteration of the population is compared with the non-dominated vector in the external repository REP. There are several situations: 1. When the external repository REP is an empty set, accept the current solution.

[0051] 2. The current solution is dominated by a solution in the external repository REP, and the current solution is removed.

[0052] 3. The current solution dominates some solutions in the external repository REP, and the dominated old solutions are removed.

[0053] 4. The current solution has no dominating relationship with any solution in the external repository REP, and the solution is stored in the external repository REP.

[0054] When selecting an index value When , the Archive hypercube containing multiple non-dominated particles is firstly divided into fitnesses; each hypercube after division is divided by the number of particles contained in it to obtain the shared fitness value; the inverse of these shared fitness values ​​is then applied to the roulette function to select the hypercube, and then one of the particles is randomly selected. The particle is ranked in the order of the entire non-dominated particle group. The index value , whose current position is , the entire speed and position update process of the particle can be completed as above.

[0055] As an optional implementation, step 3 includes the following steps.

[0056] Step 31: Use each group of initial parameters as the initial position of each particle in the multi-objective particle swarm optimization algorithm.

[0057] Step 32: Optimize the position of each particle for a preset number of iterations to obtain the optimized position of each particle in each iteration round.

[0058] Step 33: Determine the optimized positions of each particle in each iteration round as multiple sets of optimized environmental parameters.

[0059] Step 4: Using CFD, based on the objective function and multiple sets of optimized environmental parameters, determine the control variable values ​​of the environmental parameters.

[0060] As an optional implementation, step 4 includes the following steps.

[0061] Step 41: Determine any set of optimized environmental parameters as current environmental parameters.

[0062] Step 42: Using CFD, based on the objective function, simulate and calculate the objective function corresponding to the current environmental parameters to obtain the objective function value corresponding to the current environmental parameters.

[0063] Specifically, CFD is used for simulation to determine the simulated temperature and simulated CO2 concentration of each observation point corresponding to the current environmental parameters, the temperature suitability value is calculated using the simulated temperature, the CO2 uniformity value is calculated using the simulated CO2 concentration, and the operating energy consumption value is calculated using the pressure change of the fan, so as to obtain the objective function value corresponding to the current environmental parameters.

[0064] Step 43: All optimized environmental parameters whose objective function values ​​satisfy the non-dominated conditions are determined as the controlled variable values ​​of the environmental parameters.

[0065] Step 5: Use the control variable values ​​of environmental parameters to control the greenhouse.

[0066] As an optional implementation, step 5 includes the following steps.

[0067] Step 51: Fit the control variable values ​​of each environmental parameter to obtain the Pareto advantage surface of the control variable values.

[0068] Step 52: Control the greenhouse through the Pareto advantage surface of the control variable value.

[0069] Specifically, Figure 4 As shown, when the population size is 100 and the preset number of iterations is 10, the actual implementation process of the greenhouse environment optimization strategy based on CFD includes the following steps.

[0070] ① Log creation: Write a Journal log in the text user interface of the Fluent software, which is used for Fluent to sequentially execute simulation commands and export the parameter results of the environment simulation.

[0071] ②Range setting: set the fan speed and wet curtain temperature; set the population size to 100, that is, randomly generate 100 particles within the range, and the current speed From current location and inertia weight coefficient Determination (inertia weight coefficient is set to 0.6); learning factor and In this strategy, they are all set to a constant of 0.4; the number of iterations is set to 10, that is, each particle completes 10 position and velocity updates.

[0072] ③ Calculation of objective function. , and The three objective functions are calculated and evaluated by CFD solution and the simulation parameters are read.

[0073] ④ Record the optimized control variable value (position) in this iteration round, run CFD simulation to calculate the corresponding objective function optimization value, and determine whether the non-dominated condition is met.

[0074] ⑤ When the non-dominated condition is met, the adapted solution is saved to the external repository REP, that is, the control variable value under this iteration round.

[0075] ⑥Select according to the formula and , complete the update of variable particle position and velocity.

[0076] ⑦ Determine whether the iteration is terminated; if not, repeat steps ②-⑥.

[0077] ⑧After the iteration is terminated, the Pareto advantage surface of the control variable value is fitted.

[0078] This application selects the temperature of each observation layer in the greenhouse, the ideal value of CO2 concentration distribution and energy consumption as the evaluation function; sets two control variables, namely the fan speed and the change range of the wet curtain inlet temperature (i.e., wet curtain temperature); sets the variable particle population size and the number of iterations; runs Fluent to initialize and optimize the above environmental parameters; after the particle swarm completes the iteration, the accumulated discrete optimal solution (dominant solution) is fitted to the Pareto frontier surface, and the optimal indicator range and the corresponding speed and temperature control range are obtained. The Pareto advantage surface of the obtained control variable value is as follows: Figure 5 shown.

[0079] This application combines CFD technology and MOPSO algorithm to reasonably optimize the distribution of greenhouse environmental parameters, balancing the contradictory relationship between environmental control level and energy consumption input. The simulation process fully considers the multivariable, nonlinear, and highly coupled distribution characteristics of the greenhouse environment, making up for the large difference between limited sensor monitoring and actual environmental conditions. At the same time, the writing of Journal logs and batch files realizes the closed-loop control of the environmental optimization process, reducing the subjective error and cost investment of manual environmental control. This strategy has reference value for the control and adjustment ideas of the greenhouse environment.

[0080] In an exemplary embodiment, a computer device is provided, including: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement a greenhouse environment optimization method based on CFD.

[0081] In an exemplary embodiment, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, a greenhouse environment optimization method based on CFD is implemented.

[0082] In an exemplary embodiment, a computer program product is provided, comprising a computer program, which implements a greenhouse environment optimization method based on CFD when executed by a processor.

[0083] In an exemplary embodiment, a computer device is provided. The computer device may be a server or a terminal. The internal structure diagram thereof may be as follows: Figure 6As shown. The computer device includes a processor, a memory, an input / output interface (Input / Output, referred to as I / O) and a communication interface. The processor, the memory and the input / output interface are connected through a system bus, and the communication interface is connected to the system bus through the input / output interface. The processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program and a database. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The input / output interface of the computer device is used to exchange information between the processor and an external device. The communication interface of the computer device is used to communicate with an external terminal through a network connection. When the computer program is executed by the processor, a greenhouse environment optimization method based on CFD is implemented.

[0084] Those skilled in the art will understand that Figure 6 The structure shown in the figure is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components.

[0085] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, stored data, displayed data, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of relevant data must comply with relevant regulations.

[0086] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to the memory, database or other medium used in the embodiments provided in this application can include at least one of non-volatile and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetoresistive random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. By way of illustration and not limitation, RAM may be in various forms, such as Static Random Access Memory (SRAM) or Dynamic Random Access Memory (DRAM).

[0087] The database involved in each embodiment provided in this application may include at least one of a relational database and a non-relational database. The non-relational database may include a distributed database based on blockchain, etc., but is not limited thereto. The processor involved in each embodiment provided in this application may be a general-purpose processor, a central processing unit, a graphics processor, a digital signal processor, a programmable logic device, a data processing logic device based on quantum computing, etc., but is not limited thereto.

[0088] The technical features of the above embodiments may be combined arbitrarily. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0089] This article uses specific examples to illustrate the principles and implementation methods of this application. The description of the above embodiments is only used to help understand the method and core ideas of this application. At the same time, for those skilled in the art, according to the ideas of this application, there will be changes in the specific implementation methods and application scope. In summary, the content of this specification should not be understood as limiting this application.

Claims

1. A greenhouse environment optimization method based on CFD, characterized in that: The greenhouse environment optimization method based on CFD includes: Initializing multiple sets of environmental parameters of the greenhouse to obtain multiple sets of initial parameters; the environmental parameters include: wind speed of each fan in the greenhouse and temperature of the wet curtain; Constructing an objective function; the objective function includes: a temperature suitability function, a CO2 uniformity function and an operating energy consumption function; The multi-objective particle swarm optimization algorithm is used to optimize the initial parameters and obtain multiple groups of optimized environmental parameters; Determining control variable values ​​of environmental parameters based on the objective function and multiple sets of optimized environmental parameters using CFD; The greenhouse is controlled using the control variable values ​​of the environmental parameters.

2. The greenhouse environment optimization method based on CFD according to claim 1, characterized in that: The temperature suitability function includes: ； in, is the temperature suitability value; For the greenhouse Tier The simulated temperature of each observation point; For the greenhouse The ideal temperature setting value of the layer; is the total number of observation points in the greenhouse.

3. The greenhouse environment optimization method based on CFD according to claim 2, characterized in that: The CO2 uniformity function includes: ； in, is the CO2 uniformity value; For the greenhouse Tier Simulated CO2 concentration at each observation point; For the greenhouse The ideal CO2 concentration setting value for the layer.

4. The greenhouse environment optimization method based on CFD according to claim 3, characterized in that: The running energy consumption function includes: ； in, is the operating energy consumption value; is the pressure change of the fan; The total volume flow rate of air supplied to the fan; The fan operating efficiency.

5. The greenhouse environment optimization method based on CFD according to claim 1, characterized in that: The multi-objective particle swarm optimization algorithm is used to optimize the initial parameters and obtain multiple sets of optimized environmental parameters, including: Each group of initial parameters is used as the initial position of each particle in the multi-objective particle swarm optimization algorithm; The position of each particle is optimized for a preset number of iterations to obtain the optimized position of each particle in each iteration round; The optimized positions of each particle in each iteration round are determined as multiple sets of optimized environmental parameters.

6. The greenhouse environment optimization method based on CFD according to claim 5, characterized in that: Using CFD, based on the objective function and multiple sets of optimized environmental parameters, the control variable values ​​of the environmental parameters are determined, including: Determine any set of optimized environmental parameters as current environmental parameters; Using CFD, according to the objective function, a simulation calculation is performed on the objective function corresponding to the current environmental parameters to obtain the objective function value corresponding to the current environmental parameters; The optimized environmental parameters whose objective function values ​​satisfy the non-dominated conditions are determined as the controlled variable values ​​of the environmental parameters.

7. The greenhouse environment optimization method based on CFD according to claim 6, characterized in that: The greenhouse is controlled by using the control variable value of the environmental parameter, including: Fit the control variable values ​​of each environmental parameter to obtain the Pareto advantage surface of the control variable values; The greenhouse is controlled by the Pareto dominance surface of the control variable values.

8. A computer device comprising: A memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the greenhouse environment optimization method based on CFD as described in any one of claims 1 to 7.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the CFD-based greenhouse environment optimization method described in any one of claims 1 to 7 is implemented.

10. A computer program product, comprising a computer program, characterized in that When the computer program is executed by a processor, the CFD-based greenhouse environment optimization method described in any one of claims 1 to 7 is implemented.

Images