Clean room air quality control method, device and equipment and storage medium

Abstract

The invention provides a clean room air quality control method, device and equipment and a storage medium, and relates to the technical field of clean room environment regulation. The method comprises the steps of establishing a clean room CFD simulation model based on a three-dimensional geometric model, a grid division result and a turbulence model of the clean room, obtaining an initial simulation result, and inputting the initial simulation result into a multi-objective optimization model to obtain an optimization control scheme; wherein the constraint conditions of the multi-objective optimization model comprise cleanliness constraint, airflow uniformity constraint and economical efficiency constraint; the optimization control scheme comprises an FFU arrangement position and an FFU arrangement density; determining a fitness evaluation index according to the optimization control scheme, and calculating the fitness according to the fitness evaluation index; wherein the fitness evaluation indexes comprise pollutant removal efficiency, a pollution source contribution rate coverage index and an airflow uniformity index; and when the fitness meets a set condition, adjusting the FFU distribution according to the optimization control scheme. According to the method, the number and energy consumption of the FFUs can be optimized while the cleanliness requirement is met.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of clean room environment regulation, and in particular to a clean room air quality control method, device, equipment and storage medium. BACKGROUND

[0002] A clean room is a key facility for controlling the concentration of pollutants in the air, and is widely used in industries such as semiconductors, pharmaceuticals, biological engineering, and precision manufacturing, which have strict requirements for environmental cleanliness. In order to maintain the cleanliness of the clean room, it is usually necessary to control particulate matter, chemical pollutants and microorganisms in the air through reasonable air flow organization and high-efficiency filtration systems. In the clean room, Fan Filter Units (FFU) as the main provider of clean air, through the built-in fan, the air is purified by the high-efficiency filter and then delivered to the clean room, thereby achieving strict control of air cleanliness. The reasonable arrangement of FFU directly affects the air flow characteristics and cleanliness level of the clean room, and is a key link in the design of the clean room.

[0003] At present, the arrangement design of FFU in the clean room mostly adopts an empirical method. Common designs include uniform arrangement on the ceiling, functional partition arrangement, and adjustment arrangement after operation, etc. However, the uniform arrangement method is simple and easy to implement, but it fails to optimize the characteristics of pollutant diffusion, which can easily cause excessive redundancy or local loss of control of cleanliness; the functional partition arrangement, although it designs the density difference according to the cleanliness requirements of the region, usually relies on the experience and rough estimation of the designer, and lacks scientific and systematic optimization strategies. Some studies introduce Computational Fluid Dynamics (CFD) simulation technology to assist in analyzing the air flow distribution, but most of them still focus on the simulation of air flow characteristics, without fully combining the characteristics of pollutant diffusion. An important challenge in clean room design is the complex and variable diffusion behavior of pollutants, which is influenced by air flow distribution, air supply and exhaust port position, pollutant source position and release characteristics. The existing FFU design scheme in the clean room is difficult to optimize the number of FFUs and energy consumption while meeting the cleanliness requirements. SUMMARY

[0004] The embodiments of the present application provide a clean room air quality control method, device, equipment and storage medium to solve the problem that the existing FFU design scheme in the clean room is difficult to optimize the number of FFUs and energy consumption while meeting the cleanliness requirements.

[0005] In a first aspect, the embodiments of the present application provide a clean room air quality control method, comprising: Based on a clean room three-dimensional geometric model, a meshing result and a turbulent flow model, a clean room CFD simulation model is established, and based on the clean room CFD simulation model, an initial simulation result is obtained; wherein the initial simulation result includes a pollutant concentration distribution, an air flow distribution, a high-risk area marking and a pollution source contribution rate; The initial simulation result is input into a multi-objective optimization model to obtain an optimized control scheme; wherein the multi-objective optimization model constraint conditions include a cleanliness constraint, an air flow uniformity constraint and an economic constraint; and the optimized control scheme includes an FFU arrangement position and an FFU arrangement density; According to the optimized control scheme, an adaptability evaluation index is determined, and an adaptability is calculated according to the adaptability evaluation index; wherein the adaptability evaluation index includes a pollutant removal efficiency, a pollution source contribution rate coverage index and an air flow uniformity index; When the adaptability meets a set condition, the optimized control scheme is output to adjust the FFU distribution according to the optimized control scheme.

[0006] In a possible implementation, the multi-objective optimization model takes the maximum cleanliness compliance rate, the optimal air flow distribution uniformity and the minimum FFU number and energy consumption as objective functions.

[0007] In a possible implementation, determining the adaptability evaluation index according to the optimized control scheme includes: Simulating the optimized control scheme by using the clean room CFD simulation model to obtain a pollutant concentration drop amount, an air flow distribution and a pollution source contribution rate after the FFU is updated and arranged; Determining a pollutant removal efficiency according to a ratio of the pollutant concentration drop amount to an original pollutant concentration drop amount, calculating a pollution source contribution rate coverage index according to the pollution source contribution rate and a weight of a pollution source to each area, and calculating an air flow uniformity index according to the air flow distribution.

[0008] In a possible implementation, the adaptability calculation formula is:

[0009] wherein, is the pollutant removal efficiency, is the pollution source contribution rate coverage index, is the air flow uniformity index, , , is a dynamic weight factor.

[0010] In a possible implementation, when the adaptability does not meet the set condition, the method further includes: According to the FFU arrangement position and the FFU arrangement density corresponding to the last optimization control scheme and the optimization control scheme, the FFU arrangement position and the FFU arrangement density after optimization updating are obtained as the updated optimization control scheme. The operation of determining the fitness evaluation index according to the optimization control scheme and the operation after that are performed.

[0011] In a possible implementation, the optimization updating formula corresponding to the FFU arrangement position is as follows:

[0012] wherein, is a path fusion coefficient; is the FFU arrangement position corresponding to the last optimization control scheme; is the optimization control scheme.

[0013] In a possible implementation, the set condition is that a fitness difference value corresponding to the optimization control scheme and the last optimization control scheme is less than a set threshold value.

[0014] In a possible implementation, after the operation of determining the fitness evaluation index according to the optimization control scheme, the operation further includes: a difference value of each index in the corresponding fitness evaluation index and each index in the last fitness evaluation index is calculated respectively; according to the difference value of each index and a corresponding threshold value, the weight of each index in the fitness evaluation index calculation formula is adjusted.

[0015] In a possible implementation, the operation of adjusting the weight of each index in the fitness evaluation index calculation formula according to the difference value of each index and the corresponding threshold value includes: when the index including the difference value less than the corresponding threshold value, the weight of the index including the difference value greater than or equal to the corresponding threshold value is increased.

[0016] In a second aspect, an embodiment of the present application provides a clean room air quality control device, including: a simulation module, configured to establish a clean room CFD simulation model based on a three-dimensional geometric model of the clean room, a grid division result and a turbulent flow model, and obtain an initial simulation result based on the clean room CFD simulation model; wherein the initial simulation result includes a pollutant concentration distribution, an air flow distribution, a high-risk area mark and a pollution source contribution rate; an optimization model, configured to input the initial simulation result into a multi-objective optimization model to obtain an optimization control scheme; wherein the multi-objective optimization model constraint condition includes a cleanliness constraint, an air flow uniformity constraint and an economy constraint; and the optimization control scheme includes an FFU arrangement position and an FFU arrangement density; The fitness calculation module is configured to determine a fitness evaluation index according to the optimized control scheme, and to calculate a fitness according to the fitness evaluation index; wherein the fitness evaluation index comprises a pollutant removal efficiency, a pollution source contribution rate coverage index, and an air flow uniformity index; The output module is configured to output the optimized control scheme to adjust the FFU distribution according to the optimized control scheme when the fitness meets a set condition.

[0017] In a third aspect, an electronic device is provided, which includes a memory and a processor. The memory stores a computer program. The processor implements the method in the first aspect or any possible implementation manner of the first aspect when executing the computer program.

[0018] In a fourth aspect, a computer readable storage medium is provided, which stores a computer program. The computer program is executed by a processor to implement the method in the first aspect or any possible implementation manner of the first aspect.

[0019] In the embodiments of the present application, the initial pollutant concentration, air flow distribution and other key data are obtained by establishing a clean room CFD simulation model, the FFU arrangement is optimized in combination with a multi-objective optimization model, the effect of the scheme is evaluated through the fitness indexes including the pollutant removal efficiency, the pollution source contribution rate coverage and the air flow uniformity, and finally the FFU distribution is adjusted according to the fitness. This process realizes the closed-loop control from simulation analysis to optimization decision, can accurately identify the pollution risk and air flow problem of the clean room, can balance the cleanliness, air flow uniformity and economy through multi-objective constraints, avoids the blindness of traditional empirical arrangement, makes the FFU arrangement more scientific and targeted, and effectively improves the accuracy and efficiency of clean room air quality control. BRIEF DESCRIPTION OF DRAWINGS

[0020] Figure 1 is an application scenario diagram of the clean room air quality control method provided by the embodiments of the present application; Figure 2 is an implementation flowchart of the clean room air quality control method provided by the embodiments of the present application; Figure 3 is a structural schematic diagram of the clean room air quality control device provided by the embodiments of the present application; Figure 4 is a schematic diagram of the electronic device provided by the embodiments of the present application. DETAILED DESCRIPTION

[0021] Traditional design methods usually ignore the pollutant tracing analysis, i.e. the dynamic diffusion path and influence range of pollutants from the release source to different areas. Therefore, in actual operation, the high-pollution risk areas are often not effectively covered, resulting in insufficient performance of the clean room. In addition, the existing design is difficult to optimize the number of FFUs and energy consumption while meeting the cleanliness requirements. Although uniform arrangement or blind increase of FFU density can improve cleanliness to a certain extent, it will greatly increase the operation cost and energy consumption, and the zoned arrangement method is difficult to accurately control the diffusion of pollution sources.

[0022] In view of the above problems, there is an urgent need for a scientific and systematic FFU arrangement design method to determine the optimal FFU arrangement scheme by simulating the diffusion path of pollutants and combining dynamic optimization technology at the design stage of the clean room. In this way, not only can the targeted cleanliness control be achieved in high-risk areas, but also the waste of resources caused by overdesign can be avoided, thereby balancing the performance and economy of the clean room. Based on the above problems, the embodiments of the present application propose an FFU arrangement method combining pollutant tracing analysis and simulation optimization, which provides a new solution for the design of the clean room.

[0023] The embodiments of the present application will be described in detail below with reference to the accompanying drawings.

[0024] Figure 1 is the application scenario diagram of the clean room air quality control method provided by the embodiments of the present application.

[0025] As shown in Figure 1 , the terminal device is equipped with a CFD simulation model. Before the FFU system is built, the CFD simulation model will carry out simulation work on the clean room, and generate an optimized control scheme for FFU arrangement according to the simulation results, so as to realize reasonable arrangement of FFUs and maintain the air flow characteristics and cleanliness level of the clean room.

[0026] Figure 2 is the implementation flowchart of the clean room air quality control method provided by the embodiments of the present application, as shown in Figure 2 , comprising the following steps: S201, based on the three-dimensional geometric model of the clean room, the grid division result and the turbulent flow model, a clean room CFD simulation model is established, and based on the clean room CFD simulation model, an initial simulation result is obtained; wherein the initial simulation result includes pollutant concentration distribution, air flow distribution, high-risk area marking and pollution source contribution rate.

[0027] The execution subject of each embodiment of the present application can be a server, a processor, a microprocessor or other devices with data processing function. In the actual implementation process, the specific implementation mode of the execution subject can be selected according to actual needs, and the present embodiment does not make special limitation, as long as it is a device with data processing function.

[0028] In the embodiment, by combining the pollution traceability analysis and the CFD simulation technology in the clean room design stage, the diffusion path and distribution characteristics of the pollutants are dynamically simulated, so that the high-risk areas and airflow dead angles in the clean room are scientifically identified.

[0029] Before the FFU arrangement project is carried out in the initial stage of the clean room design, the effect of the FFU arrangement scheme on the air quality control of the clean room is simulated and simulated through the clean room CFD simulation model, so as to achieve the effect of meeting the cleanliness requirement while optimizing the number of FFUs and energy consumption. Specifically, by inputting the clean room design parameters, pollution source assumption and initial arrangement scheme, the clean room CFD simulation model is constructed to provide support for subsequent simulation and optimization.

[0030] Firstly, the clean room design parameters are determined according to the preliminary design drawings and functional requirements of the clean room, including: geometric structure parameters, functional area division and airflow design parameters.

[0031] In one possible implementation manner, the geometric structure parameters include: Clean room size (length, width, height): ; Air supply port and exhaust port position: , ; Area of air supply and exhaust port: , ; (2) The functional area division includes: High cleanliness area (such as photolithography area, key process equipment area); Medium cleanliness area (such as auxiliary equipment area, personnel activity area); Low cleanliness area (such as peripheral storage or buffer area); Wherein, each area is marked as and the cleanliness requirement (ISO level or maximum allowable concentration ) is attached.

[0032] (3) The airflow design parameters include: total air supply and exhaust rate: The calculation formula of the total air supply is:

[0033] Wherein, is the air change frequency per hour; is the volume of the clean room.

[0034] Exhaust rate .

[0035] Secondly, in the design stage, due to the actual pollution source position unknown, need to simulate possible pollution source distribution through reasonable assumption. Pollution source distribution includes: equipment pollution source, personnel activity pollution source and dynamic release model of pollution source. Corresponding equipment pollution source determines equipment pollution source position and pollution release amount; corresponding personnel activity pollution source determines activity path and release amount.

[0036] In a possible implementation, (1) equipment pollution source position: according to preliminary process equipment layout, assume pollution source point .

[0037] Equipment pollution source release amount calculation formula is:

[0038] Wherein, Maximum pollution release amount of equipment (determined by equipment type); Dynamic operation mode of equipment (such as intermittent release or constant release).

[0039] (2) Personnel activity pollution source activity path is the typical path of simulating personnel from entrance to process operation area.

[0040] Path is expressed by parameterized curve:

[0041] Release amount:

[0042] Wherein, Personnel number; Release amount per unit time per person.

[0043] (3) Dynamic release model of pollution source corresponding total pollution source release amount calculation formula is:

[0044] Wherein, Dynamic pollution generated by personnel activity; Three-dimensional product of Dirac Function takes nonzero value when space coordinates coincide with source point position; Function takes nonzero value when space coordinates coincide with source point position; ) is the spatial position coordinate of the th pollution source; Release amount of the th pollution source at time .

[0045] Then, the initial FFU arrangement scheme is determined, which lays the foundation for subsequent optimization. The initial FFU arrangement scheme includes the initial FFU arrangement density and the initial FFU operating parameters: (1) The initial FFU arrangement density is:

[0046] wherein, NFFU is the initial number of FFUs; A is the clean room ceiling area.

[0047] (2) The initial FFU operating parameters include the initial wind speed of each FFU and the FFU coverage area.

[0048] FFU coverage area:

[0049] wherein, NFFU is the initial number of FFUs; A is the clean room ceiling area.

[0050] Finally, after completing the above simulation process, the clean room CFD simulation model outputs the following data: Clean room geometry and airflow parameters:

[0051] Pollution source distribution and dynamic release amount:

[0052] Initial FFU arrangement scheme:

[0053] These data will be used as input conditions for subsequent pollutant diffusion simulation and FFU optimization.

[0054] Next, the CFD tool is used to simulate the pollutant diffusion path and concentration distribution in the clean room, identify high-risk areas, insufficient cleanliness areas, and diffusion paths, and provide a basis for subsequent FFU arrangement optimization.

[0055] wherein, the pollutant diffusion modeling includes determining the convection-diffusion equation, boundary conditions, and initial conditions.

[0056] (1) The pollutant concentration distribution is described by the convection-diffusion equation:

[0057] wherein, C is the pollutant concentration (unit: mg / m3); V is the airflow velocity (calculated by CFD simulation); Diffusion coefficient of the pollutant; Source term of the pollutant.

[0058] (2) Boundary conditions: Air supply: , ; the pollutant concentration of clean air is assumed to be zero.

[0059] Air exhaust: ; wall and obstacle: To pollutant concentration: no flux boundary condition .

[0060] To air flow: no slip boundary condition .

[0061] (3) Initial conditions: The initial pollutant concentration Assume zero, or assume there is a background concentration.

[0062] Air flow simulation includes: CFD simulation settings and simulation output.

[0063] (1) CFD simulation settings Geometry model: establish a three-dimensional geometric model based on the structure of the clean room, including air supply, air exhaust, obstacles, FFU position, etc.

[0064] Meshing: to ensure simulation accuracy, use structured mesh or adaptive meshing, and encrypt the pollution source and key areas.

[0065] Turbulence model: use a turbulence model suitable for clean room airflow (such as Or LES model).

[0066] (2) Simulation output: Air flow velocity distribution ; pollutant concentration distribution .

[0067] Further, according to the CFD simulation results, analyze the pollutant diffusion path, and identify high-risk areas and airflow dead angles.

[0068] (1) High concentration area identification: define the area where the concentration exceeds the target value as a high-risk area:

[0069] Where, The concentration target value.

[0070] Calculate the volume of the high-risk area:

[0071] (2) Pollution source contribution analysis: trace the diffusion path of the pollution source, and analyze the pollution contribution rate of each pollution source to different areas.

[0072]

[0073] wherein, is the pollution source contribution rate to the target point; is the pollution source .

[0074] (3) Airflow dead angle identification: determine whether the airflow speed is lower than the set threshold :

[0075] Record the dead angle position and range.

[0076] Based on the analysis results, output the pollutant concentration distribution map, airflow distribution map, high-risk area data, and pollution source contribution rate. Among them, the pollutant concentration distribution map aims to output the pollutant concentration distribution map in the clean room, marking the high concentration area and its range. The airflow distribution map aims to output the airflow velocity field distribution, marking the airflow dead angle position. The high-risk area data includes: the volume of the high concentration area and the coordinate range of the high concentration area . The pollution source contribution rate aims to output the contribution rate of each pollution source to the high concentration area .

[0077] In the specific implementation process, the output data form is: pollutant concentration distribution: ; airflow distribution: ; high-risk area marking: ; pollution source contribution rate: .

[0078] S202, input the initial simulation results into a multi-objective optimization model to obtain an optimized control scheme; wherein the constraint conditions of the multi-objective optimization model include cleanliness constraints, airflow uniformity constraints, and economic constraints; the optimized control scheme includes: FFU arrangement position and FFU arrangement density.

[0079] In the specific implementation process, the initial simulation results including pollutant concentration distribution, airflow distribution, high-risk area marking, and pollution source contribution rate are used in combination with the high concentration area of pollutants and airflow distribution to design a multi-objective optimization model, and dynamically adjust the FFU position and density to obtain the optimized control scheme.

[0080] In the implementation process, the multi-objective optimization model takes the maximum cleanliness compliance rate, the optimal airflow distribution uniformity, and the minimum number of FFUs and energy consumption as the objective functions. The cleanliness constraint is: ; the airflow uniformity constraint is: ; and the economic constraint is: .

[0081] Among them, the cleanliness constraint corresponds to the concentration of pollutants in each region must be lower than the target value, the airflow uniformity constraint corresponds to the airflow velocity cannot be lower than the minimum threshold after the FFU is arranged, and the economic constraint corresponds to the number of FFUs cannot exceed the budget.

[0082] In the process of obtaining the optimized control scheme, the arrangement is adjusted according to the high-risk area, and the partition arrangement density is adjusted.

[0083] (1) The adjustment of the arrangement according to the high-risk area includes: In the area where the concentration of pollutants is higher than the target value , the FFU arrangement density is increased.

[0084] In the area where the airflow velocity is lower than the threshold value , the FFU is arranged to supplement the airflow circulation.

[0085] (2) The adjustment of the partition arrangement density includes setting different FFU arrangement densities according to the cleanliness requirements of the region.

[0086] The FFU arrangement density in the high-cleanliness area is:

[0087] Among them, is the area of the region; is the release amount of the pollution source; is the target airflow velocity.

[0088] The FFU arrangement density in the medium-cleanliness area is:

[0089] Among them, is the proportionality coefficient (usually 0.5-0.8).

[0090] The FFU arrangement density in the low-cleanliness area is:

[0091] Among them, is the minimum density of the system.

[0092] S203, determine the fitness evaluation index according to the optimization control scheme, and calculate the fitness according to the fitness evaluation index; wherein the fitness evaluation index includes: pollutant removal efficiency, pollution source contribution rate coverage index and airflow uniformity index.

[0093] In the embodiments of the present application, in order to ensure that cleanliness, airflow uniformity and economy meet the expected requirements, the optimization control scheme is further evaluated after being determined. In order to meet the evaluation needs of the optimization control scheme, fitness and corresponding evaluation indexes are set.

[0094] The traditional objective function only aims to minimize the concentration deviation and the number of FFUs. Unlike the traditional scheme, the embodiments of the present application introduce the pollutant removal efficiency, the pollution source contribution rate coverage index and the airflow uniformity index.

[0095] S204, when the fitness meets the set condition, output the optimization control scheme to adjust the FFU distribution according to the optimization control scheme.

[0096] In the specific implementation process, the optimization control scheme is iteratively updated based on the fitness to ensure that the FFU distribution scheme effectively improves the precision and efficiency of clean room air quality control. When the fitness meets the set condition, the corresponding optimization control scheme is output as the final scheme.

[0097] In the embodiments, the initial pollutant concentration, airflow distribution and other key data are obtained by establishing a clean room CFD simulation model, the FFU arrangement is optimized by combining a multi-objective optimization model, and the scheme effect is evaluated through the fitness indexes including the pollutant removal efficiency, the pollution source contribution rate coverage and the airflow uniformity. Finally, the FFU distribution is adjusted according to the fitness. This process realizes closed-loop control from simulation analysis to optimization decision, accurately identifies the pollution risk and airflow problem of the clean room, balances the cleanliness, airflow uniformity and economy through multi-objective constraints, avoids the blindness of traditional empirical arrangement, makes the FFU arrangement more scientific and targeted, and effectively improves the precision and efficiency of clean room air quality control.

[0098] In a possible implementation manner, the fitness evaluation index is determined according to the optimization control scheme, including: The clean room CFD simulation model is used to simulate the optimization control scheme, and the pollutant concentration drop, airflow distribution and pollution source contribution rate after the FFU is updated and arranged are obtained. The pollutant removal efficiency is determined according to the ratio of the pollutant concentration drop to the original pollutant concentration drop, the pollution source contribution rate coverage index is calculated according to the pollution source contribution rate and the weight of the pollution source to each region, and the airflow uniformity index is calculated according to the airflow distribution.

[0099] Wherein, the pollutant removal efficiency is introduced, aiming to increase the fitness index of the FFU arrangement for interrupting the diffusion path of the pollutants:

[0100] Wherein, is the pollutant concentration drop after the FFU arrangement; is the removal efficiency, the higher the better.

[0101] The pollutant source contribution rate index is introduced, aiming to guide the FFU to preferentially cover the area with a high pollutant source contribution rate:

[0102] Wherein, is the pollutant source weight for a certain area. is the area coordinate; maximizing the FFU coverage density of the high-weight area ensures that the key pollution path is controlled.

[0103] The airflow distribution uniformity index is introduced, aiming to increase the airflow uniformity as part of the optimization target:

[0104] Wherein, : clean room airflow average speed.

[0105] In the specific implementation process, when determining the fitness evaluation index according to the optimization control scheme, the following data is first taken as input data: Pollutant concentration distribution: .

[0106] Airflow distribution: .

[0107] High-risk area marking: .

[0108] FFU initial arrangement scheme: .

[0109] Then, initialization is performed based on the pollutant tracing path, including: pollutant source path weight initialization and area layering initialization.

[0110] Wherein, the pollutant source path weight initialization aims to perform weight distribution on the diffusion path of each pollutant source:

[0111] Wherein, is the pollutant concentration change of a certain area; is the pollutant source weight for a certain area.

[0112] The higher the weight of the area, the more FFUs are initially arranged, thereby preferentially controlling the diffusion path of the main pollution source.

[0113] Wherein, the area layering initialization arrangement aims to divide the clean room into high, medium and low risk layers (combined with the high-risk area and airflow dead angle output in step two), and allocate the initial FFU arrangement density:

[0114] Wherein, is a risk adjustment coefficient, which takes a larger value for high-risk areas; is a pollution source weight of the area.

[0115] In this embodiment, the method obtains the pollutant concentration change, airflow distribution and pollution source contribution rate after the FFU is updated and arranged through CFD simulation, and then quantitatively calculates the pollutant removal efficiency, pollution source contribution rate coverage index and airflow uniformity index. This index calculation method based on simulation data ensures the objectivity and accuracy of the fitness evaluation index, and can truly reflect the inhibition effect of the FFU arrangement scheme on the diffusion of pollutants, the coverage degree of the high-risk pollution source and the optimization of the airflow distribution, providing a reliable basis for subsequent fitness calculation and scheme adjustment, and improving the scientificity of the optimization process.

[0116] In one possible implementation, the fitness calculation formula is:

[0117] Wherein, is the pollutant removal efficiency, is the pollution source contribution rate coverage index, is the airflow uniformity index, , , is a dynamic weight factor.

[0118] Wherein, , , is a dynamic weight factor, and the introduction of the dynamic weight factor can flexibly adjust the importance of each index according to the actual optimization requirements.

[0119] For example, the weight of the pollutant removal efficiency can be increased in the high-pollution-risk area, and the weight of the airflow uniformity index can be increased when the airflow dead angle is prominent, so that the fitness calculation is more in line with the actual control requirements of the clean room, and the optimization process is guided to develop in the direction of better comprehensive performance.

[0120] In the embodiment, the fitness calculation formula integrates the pollutant removal efficiency, the pollution source contribution rate coverage index and the airflow uniformity index through a dynamic weight factor, so that the three factors form a synergistic effect in the fitness evaluation.

[0121] In a possible implementation, when the fitness does not satisfy the set condition, the method further includes: According to the FFU arrangement position and the FFU arrangement density corresponding to the previous optimization control scheme, the FFU arrangement position and the FFU arrangement density are updated, to obtain the updated FFU arrangement position and the updated FFU arrangement density as the updated optimization control scheme. The fitness evaluation index and the subsequent operation are determined according to the optimization control scheme.

[0122] In the embodiment, when the fitness does not satisfy the set condition, a new scheme is generated by updating the FFU arrangement position and the FFU arrangement density of the current and previous optimization control schemes, and the fitness is recalculated, to form an iterative optimization mechanism. This updating method can combine the advantages of different schemes, avoid the limitations of a single scheme, gradually approach the optimal solution through iteration, effectively improve the optimization depth of the FFU arrangement scheme, and ensure that the final scheme achieves a better balance in cleanliness, airflow uniformity and economy.

[0123] In a possible implementation, the updating formula corresponding to the FFU arrangement position is:

[0124] wherein, is a path fusion coefficient; is the FFU arrangement position corresponding to the previous optimization control scheme; is the optimization control scheme.

[0125] When the value of a is large, the new scheme retains more reasonable layout of the previous scheme; when the value of a is small, the new scheme absorbs more optimization ideas of the current scheme. This controllable fusion method makes the adjustment of the FFU arrangement position more targeted, which helps to gradually optimize the coverage effect of the high-risk area in the iteration process and improve the rationality of the scheme.

[0126] In the embodiment, the updating formula corresponding to the FFU arrangement position fuses the arrangement positions of the current and previous schemes through the path fusion coefficient, so that the new scheme can flexibly adjust the influence weight of the two schemes according to actual needs.

[0127] In a possible implementation, the updating formula corresponding to the FFU arrangement density is:

[0128] wherein, is the adjusted value calculated from the risk factor and removal efficiency; , is the risk factor, , calculated based on the proportion of pollutant concentration exceeding the standard in high-risk areas, is the target value of regional pollutant concentration, For removal efficiency, and is a dynamic weight factor, which is used to automatically adjust the relative weights of risk control and removal efficiency at different stages. and It can be determined based on actual process experience or simulation iteration.

[0129] in, It is the dynamic adjustment value of FFU arrangement density, which is used to modify FFU arrangement in real time according to pollution risk and removal efficiency during optimization iteration. 、 Data, computing and , and according to and calculate ,Will Used for the next round of FFU layout density calculation to achieve automatic generation optimization.

[0130] In a possible implementation, the set condition is that the fitness difference between the optimized control scheme and the last optimized control scheme is less than a set threshold.

[0131] In the specific implementation process, the conditions are set as

[0132] in, is the convergence judgment threshold; The fitness corresponding to the current optimization control scheme; It is the fitness corresponding to the last optimized control scheme.

[0133] In this embodiment, the set condition is defined as the fitness difference between the two previous optimization control schemes is less than the set threshold. This can not only avoid the scheme from not reaching the optimality due to insufficient number of iterations, but also prevent the waste of resources caused by excessive iterations, and ensure that the iteration is stopped in time when the fitness tends to be stable. While ensuring the optimization effect, the optimization efficiency is improved, so that the FFU layout scheme can achieve the expected performance at a reasonable computing cost.

[0134] In a possible implementation, after determining the fitness evaluation index according to the optimization control scheme, the following steps are further included: The difference between each index in the fitness evaluation index and the corresponding index in the last fitness evaluation index is calculated. According to the difference of each index and the corresponding threshold, the weight of each index in the fitness evaluation index calculation formula is adjusted.

[0135] Optionally, according to the difference of each index and the corresponding threshold, the weight of each index in the fitness evaluation index calculation formula is adjusted, including: When the index with a difference less than the corresponding threshold is included, the weight of the index with a difference greater than or equal to the corresponding threshold is increased.

[0136] For example, when the difference in pollutant removal efficiency is large and does not reach the threshold, the weight of the pollutant removal efficiency in the fitness calculation formula can be increased to guide the optimization process to prioritize improving the pollutant removal effect; when the airflow uniformity index has reached the standard, the weight of the airflow uniformity index can be reduced to reduce unnecessary optimization resource investment. This dynamic adjustment mechanism makes the optimization process more targeted, and can flexibly adjust the optimization focus according to the actual performance of each index to accelerate convergence to a scheme with better comprehensive performance.

[0137] In this embodiment, by calculating the difference between each index in the fitness evaluation index and the last one, and adjusting the weight of each index according to the difference and the corresponding threshold, the dynamic optimization of the weight is realized.

[0138] In order to ensure that the optimization control scheme output in step S204 meets the requirements, the optimization control scheme can be re-imported into the CFD model to verify the pollutant concentration and airflow distribution, and compare the FFU number, energy consumption and cleanliness improvement effect of the initial scheme and the optimal scheme. Specifically, whether the FFU arrangement position and the FFU arrangement density in the optimization control scheme meet the following requirements: The pollutant concentration in each area is lower than the target value; the airflow distribution is uniform and there is no obvious dead angle; the number of FFU running and the energy consumption meet the economic requirements.

[0139] It should be understood that the size of the serial number of each step in the above embodiments does not mean the order of execution, and the execution order of each process should be determined according to its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present application.

[0140] The following is a device embodiment of the present application, and for details not described in detail, reference can be made to the corresponding method embodiments described above.

[0141] Figure 3 The structure of the clean room air quality control device provided by the embodiment of the present application is shown, only the part related to the embodiment of the present application is shown for convenience of description, and the details are as follows: As Figure 3 shown, the clean room air quality control device 3 includes: The simulation module 301 is configured to establish a clean room CFD simulation model based on a three-dimensional geometric model of the clean room, a meshing result and a turbulence model, and obtain an initial simulation result based on the clean room CFD simulation model, wherein the initial simulation result comprises a pollutant concentration distribution, an airflow distribution, a high-risk area marking and a pollution source contribution rate; The optimization model 302 is configured to input the initial simulation result into a multi-objective optimization model to obtain an optimized control scheme, wherein constraint conditions of the multi-objective optimization model comprise a cleanliness constraint, an airflow uniformity constraint and an economic constraint, and the optimized control scheme comprises an FFU arrangement position and an FFU arrangement density; The fitness calculation module 303 is configured to determine a fitness evaluation index according to the optimized control scheme, and calculate a fitness according to the fitness evaluation index, wherein the fitness evaluation index comprises a pollutant removal efficiency, a pollution source contribution rate coverage index and an airflow uniformity index. The output module 304 is configured to output the optimized control scheme when the fitness satisfies a set condition, so as to adjust the FFU distribution according to the optimized control scheme.

[0142] In a possible implementation, the multi-objective optimization model takes the maximum cleanliness compliance rate, the optimal airflow distribution uniformity and the minimum FFU number and energy consumption as objective functions.

[0143] In a possible implementation, the fitness calculation module 303 is specifically configured to: simulate the optimized control scheme by using the clean room CFD simulation model to obtain a pollutant concentration drop, an airflow distribution and a pollution source contribution rate after the FFU is updated and arranged; determine the pollutant removal efficiency according to a ratio of the pollutant concentration drop to an original pollutant concentration drop, calculate the pollution source contribution rate coverage index according to the pollution source contribution rate and a weight of the pollution source to each area, and calculate the airflow uniformity index according to the airflow distribution.

[0144] In a possible implementation, the fitness calculation formula is as follows:

[0145] wherein, is the pollutant removal efficiency, is the pollution source contribution rate coverage index, is the airflow uniformity index, , , is a dynamic weight factor.

[0146] In a possible implementation, when the fitness does not satisfy the set condition, the fitness calculation module 303 is further configured to: The FFU arrangement position and the FFU arrangement density corresponding to the previous optimization control scheme are updated according to the optimization control scheme to obtain updated FFU arrangement position and FFU arrangement density as the updated optimization control scheme.

[0147] The fitness calculation module 303 determines the fitness evaluation index according to the updated optimization control scheme, and calculates the fitness according to the fitness evaluation index; the output module 304 outputs the optimization control scheme when the fitness meets the set condition.

[0148] In a possible implementation, the updated formula corresponding to the FFU arrangement position is:

[0149] wherein, is a path fusion coefficient; is the FFU arrangement position corresponding to the previous optimization control scheme; is the optimization control scheme.

[0150] In a possible implementation, the set condition is that the difference between the fitness corresponding to the optimization control scheme and the fitness corresponding to the previous optimization control scheme is less than a set threshold.

[0151] In a possible implementation, the fitness calculation module 303 is further configured to, after determining the fitness evaluation index according to the optimization control scheme, calculate the difference between each index in the fitness evaluation index and each index in the previous fitness evaluation index, respectively; and adjust the weight of each index in the fitness evaluation index calculation formula according to the difference between each index and the corresponding threshold.

[0152] In a possible implementation, the fitness calculation module 303 is specifically configured to, when the index whose difference is less than the corresponding threshold is included, increase the weight of the index whose difference is greater than or equal to the corresponding threshold.

[0153] In the embodiment, the initial pollutant concentration, airflow distribution and other key data are obtained by establishing a clean room CFD simulation model, the FFU arrangement is optimized by combining a multi-objective optimization model, the effect of the scheme is evaluated by the fitness indexes including the pollutant removal efficiency, the pollution source contribution rate coverage and the airflow uniformity, and finally the FFU distribution is adjusted according to the fitness. This process realizes closed-loop control from simulation analysis to optimization decision, can accurately identify the pollution risk and airflow problem of the clean room, balances the cleanliness, airflow uniformity and economy through multi-objective constraints, avoids the blindness of traditional empirical arrangement, makes the FFU arrangement more scientific and targeted, and effectively improves the accuracy and efficiency of clean room air quality control.

[0154] Figure 4 is a schematic diagram of an electronic device provided by an embodiment of the present application. As shown inFigure 4 As shown, the electronic device 4 of this embodiment includes a processor 40 and a memory 41. The memory 41 stores a computer program 42. The processor 40 implements the steps in the above method embodiments when executing the computer program 42. Alternatively, the processor 40 implements the functions of the modules / units in the above apparatus embodiments when executing the computer program 42.

[0155] For example, the computer program 42 can be divided into one or more modules / units, which are stored in the memory 41 and executed by the processor 40 to complete the present application. The one or more modules / units can be a series of computer program instruction segments capable of completing a specific function, which are used to describe the execution process of the computer program 42 in the electronic device 4.

[0156] The electronic device 4 can include, but is not limited to, the processor 40 and the memory 41. Those skilled in the art can understand that the electronic device 4 can include more or less components, or combine certain components, or different components, for example, the electronic device 4 can also include an input / output device, a network access device, a bus, etc. Figure 4 The electronic device 4 is only an example and does not constitute a limitation on the electronic device 4, which can include more or less components than those shown, or combine certain components, or different components, for example, the electronic device 4 can also include an input / output device, a network access device, a bus, etc.

[0157] The processor 40 can be a central processing unit (CPU), and can also be other general-purpose processors, digital signal processors (DSP), application specific integrated circuits (ASIC), field programmable gate arrays (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor can be a microprocessor or the processor can also be any conventional processor.

[0158] The memory 41 can be an internal storage unit of the electronic device 4, such as a hard disk or a memory of the electronic device 4. The memory 41 can also be an external storage device of the electronic device 4, such as a plug-in hard disk, a Smart Media Card (SMC), a Secure Digital (SD) card, a Flash Card, etc. equipped on the electronic device 4. Further, the memory 41 can include both the internal storage unit and the external storage device of the electronic device 4. The memory 41 is used to store the computer program 42 and other programs and data required by the electronic device 4. The memory 41 can also be used to temporarily store data that has been output or will be output.

[0159] For the convenience and brevity of description, only the above-mentioned division of functional modules / units is exemplified, and in actual application, the above-mentioned functions can be completed by different functional modules / units according to needs. The above-mentioned modules / units can be realized in the form of hardware, software or a combination of hardware and software.

[0160] The embodiment of the present application also provides a computer readable storage medium, which stores a computer program. When the computer program is executed by a processor, the method in each method embodiment described above is implemented.

[0161] The embodiment of the present application also provides a computer program product, which includes a computer program. When the computer program is executed by a processor, the method in each method embodiment described above is implemented.

[0162] The computer program includes computer program code, which can be in the form of source code, object code, executable files or some intermediate forms. The computer readable medium can include any entity or device capable of carrying computer program code, recording medium, U disk, mobile hard disk, magnetic disk, optical disk, computer memory, Read-Only Memory (ROM), Random Access Memory (RAM), electric carrier wave signal, telecommunication signal and software distribution medium, etc.

[0163] In the above embodiments, the description of each embodiment has its own emphasis, and the parts not described or recorded in detail in a certain embodiment can be referred to the relevant description of other embodiments. If there is no special description and no logical conflict, the terms and / or descriptions of different embodiments are consistent and can be mutually referenced. The technical features in different embodiments can be combined to form new embodiments according to their inherent logical relationship.

[0164] The above examples are only used to illustrate the technical solutions of the present application, but not limit the present application; although the present application has been described in detail with reference to the foregoing examples, those ordinarily skilled in the art should understand: the technical solutions recorded in the foregoing examples can still be modified, or some technical features can be replaced equivalently; and these modifications or replacements do not make the essence of the corresponding technical solutions deviate from the spirit and scope of the technical solutions of the embodiments of the present application, and should be included in the protection scope of the present application.

Claims

1. A clean room air quality control method, characterized by, The method comprises the following steps: Based on the three-dimensional geometric model, the grid division result and the turbulent flow model of the clean room, a clean room CFD simulation model is established, and an initial simulation result is obtained based on the clean room CFD simulation model; wherein the initial simulation result comprises a pollutant concentration distribution, an air flow distribution, a high-risk area marking and a pollution source contribution rate; The initial simulation result is input into a multi-objective optimization model to obtain an optimized control scheme; wherein the constraint conditions of the multi-objective optimization model comprise a cleanliness constraint, an air flow uniformity constraint and an economic constraint; the optimized control scheme comprises an FFU arrangement position and an FFU arrangement density; An adaptability evaluation index is determined according to the optimized control scheme, and an adaptability is calculated according to the adaptability evaluation index; wherein the adaptability evaluation index comprises a pollutant removal efficiency, a pollution source contribution rate coverage index and an air flow uniformity index; When the adaptability meets a set condition, the optimized control scheme is output to adjust the FFU distribution according to the optimized control scheme.

2. The method of claim 1, wherein, Determining the adaptability evaluation index according to the optimized control scheme comprises: The optimized control scheme is simulated by using the clean room CFD simulation model to obtain a pollutant concentration drop amount, an air flow distribution and a pollution source contribution rate after the FFU arrangement is updated; The pollutant removal efficiency is determined according to the ratio of the pollutant concentration drop amount to an original pollutant concentration drop amount, the pollution source contribution rate coverage index is calculated according to the pollution source contribution rate and the weight of the pollution source to each area, and the air flow uniformity index is calculated according to the air flow distribution.

3. The method of claim 2, wherein, The adaptability calculation formula is: wherein, is a pollutant removal efficiency, is a pollution source contribution rate coverage index, is an air flow uniformity index, , , is a dynamic weight factor.

4. The method of claim 1, wherein, When the adaptability does not meet the set condition, the method further comprises the following steps: The FFU arrangement position and the FFU arrangement density corresponding to the optimized control scheme and the last optimized control scheme are updated to obtain an updated FFU arrangement position and an updated FFU arrangement density as an updated optimized control scheme; The operation of determining the adaptability evaluation index according to the optimized control scheme and the subsequent operations are performed.

5. The method of claim 4, wherein, The updated formula corresponding to the FFU arrangement position is: wherein, is a path fusion coefficient; is a last time optimal control scheme corresponding FFU arrangement position; is the optimal control scheme.

6. The method of claim 4, wherein, The set condition is that the adaptability difference between the optimized control scheme and the last optimized control scheme is less than a set threshold.

7. The method of claim 4, wherein, After determining the adaptability evaluation index according to the optimized control scheme, the method further comprises the following steps: The difference between each index in the adaptability evaluation index and each index in the last adaptability evaluation index is calculated respectively; According to the difference of each index and the corresponding threshold, the weight of each index in the adaptability evaluation index calculation formula is adjusted.

8. A clean room air quality control device, comprising: The method comprises the following steps: A simulation module is configured to establish a clean room CFD simulation model based on a three-dimensional geometric model, a grid division result and a turbulent flow model of the clean room, and obtain an initial simulation result based on the clean room CFD simulation model; wherein the initial simulation result comprises a pollutant concentration distribution, an air flow distribution, a high-risk area marking and a pollution source contribution rate; An optimization model is used to input the initial simulation result into a multi-objective optimization model to obtain an optimized control scheme; wherein the constraint conditions of the multi-objective optimization model include cleanliness constraint, air flow uniformity constraint and economy constraint; and the optimized control scheme includes FFU arrangement position and FFU arrangement density; A fitness calculation module is used to determine a fitness evaluation index according to the optimized control scheme, and to calculate fitness according to the fitness evaluation index; wherein the fitness evaluation index includes pollutant removal efficiency, pollution source contribution rate coverage index and air flow uniformity index; An output module is used to output the optimized control scheme when the fitness satisfies a set condition, so as to adjust FFU distribution according to the optimized control scheme.

9. An electronic device, comprising: The computer readable storage medium stores a computer program, and the processor executes the computer program to implement the method in any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that, The computer readable storage medium stores a computer program, and the processor executes the computer program to implement the method in any one of claims 1 to 7.

Images