Clean air conditioning unit operation parameter optimization method and system based on numerical simulation

Abstract

The present invention discloses a method and system for optimizing the operating parameters of a clean air conditioning unit based on numerical simulation, including meshing according to a three-dimensional model of an operating room and determining sampling points in key areas; defining boundary conditions, using numerical simulation to analyze the airflow distribution of the operating room under the constraints of the boundary conditions, obtaining the airflow parameters of all grid nodes, and predicting the pollutant concentration distribution of all grid nodes according to the pollutant concentration of the sampling points and the airflow parameters of all grid nodes; judging whether there is a pollutant concentration of a certain grid node greater than a preset threshold; if so, triggering an alarm prompt and generating an air purification instruction; if not, establishing an objective function with the goal of minimizing the pollutant concentration, solving the objective function using the gradient descent method, and optimizing the operating parameters of the clean air conditioning unit. The present invention can optimize and control the operating parameters of the clean air conditioning unit according to the airflow distribution and pollutant concentration, thereby improving the air quality of the operating room.

Description

Technical Field

[0001] The present invention relates to the technical field of air conditioning control, and in particular to a method and system for optimizing operating parameters of a clean air conditioning unit based on numerical simulation. Background Art

[0002] In modern medical environments, especially in operating rooms, the requirements for air quality and airflow distribution are extremely strict. Traditional clean air conditioning systems usually rely on fixed airflow design and manual adjustment to maintain the cleanliness of the operating room. However, with the complexity of the internal environment of the operating room and the higher requirements for surgical safety, traditional methods have obvious shortcomings in the following aspects: First, traditional systems are often based on static design principles and cannot flexibly respond to dynamically changing environmental conditions in the operating room, such as the instantaneous increase of pollutants generated during surgery; second, there is a lack of real-time monitoring and feedback functions, and it is impossible to promptly detect and deal with situations where pollutant concentrations exceed the standard; third, in the process of air conditioning operation control, it usually relies on experience and simple manual adjustments, lacks scientific optimization algorithm support, and is difficult to achieve global optimal airflow distribution and purification effects. Summary of the invention

[0003] In order to solve at least one of the above-mentioned technical problems, the present invention provides a method and system for optimizing operating parameters of a clean air-conditioning unit based on numerical simulation.

[0004] In a first aspect, the present invention provides a method for optimizing operating parameters of a clean air conditioning unit based on numerical simulation, the method comprising:

[0005] A three-dimensional model of the operating room where the clean air conditioning unit is located is established, and the three-dimensional model is meshed to obtain multiple grid nodes. The key areas are determined according to the location of the operating table and the activity trajectory of the medical staff, and the grid nodes located in the key areas are used as sampling points.

[0006] Define boundary conditions, use numerical simulation to analyze the airflow distribution in the operating room under the constraint of boundary conditions, and obtain the airflow parameters of all grid nodes, wherein the airflow parameters include velocity field, pressure field and temperature field;

[0007] Detect the pollutant concentration at the sampling point, and predict the pollutant concentration distribution of all grid nodes based on the pollutant concentration at the sampling point and the airflow parameters of all grid nodes;

[0008] According to the predicted results of pollutant concentration distribution, determine whether there is a grid node with a pollutant concentration greater than a preset threshold;

[0009] If so, an alarm is triggered and an air purification instruction is generated;

[0010] If not, according to the pollutant concentration distribution and airflow parameters of each grid node, an objective function is established with the goal of minimizing the pollutant concentration. The objective function is solved using the gradient descent method, and the air inlet direction and speed, as well as the air outlet direction and speed of the clean air-conditioning unit are optimized based on the solution results.

[0011] Preferably, establishing an objective function with the goal of minimizing pollutant concentration includes:

[0012] Define the objective function: Assume C i is the pollutant concentration of the i-th grid node, then the objective function J is:

[0013]

[0014] Where N is the total number of grid nodes, w i is the weight factor of each grid node;

[0015] Determine the optimization variable: There are m air inlets and n exhaust ports, each of which has three directions, forming coordinates (x, y, z) and a speed value U; determine the optimization variable X as:

[0016] X=[x1,y1,z1,U1,...x m ,y m , z m , U m , x m+1 ,y m+1 , z m+1 , U m+1 ,...x m+n ,y m+n , z m+n , U m+n ]

[0017] In the formula, (x m ,y m , z m ), U m represents the coordinates and velocity value of the mth air inlet, (x m+1 ,y m+1 , z m+1 ) represents the coordinates of the first exhaust port, (x m+n ,y m+n , z m+n ) represents the coordinates of the nth exhaust port, U m+1 , U m+n Indicates the velocity value of the 1st and nth exhaust ports;

[0018] Create constraints:

[0019] l0≤x i ≤u0

[0020] l1≤y i ≤u1

[0021] l2≤z i ≤u2

[0022] v min ≤U i ≤v max

[0023] In the formula, l0, l1, l2 are x i ,y i , z i The corresponding lower limits, u0, u1, and u2 are x i ,y i , z i The corresponding upper limit, v min 、v max are the minimum speed and maximum speed respectively.

[0024] Preferably, solving the objective function by using a gradient descent method comprises:

[0025] Initialize the optimization variables, assuming that X is randomly generated:

[0026] X=[x1,y1,z1,U1,x2,y2,z2,U2,x3,y3,z3,U3]

[0027] Calculate the gradient of the objective function J with respect to the optimization variable X and obtain the gradient vector for:

[0028]

[0029] Assume the number of iterations is T, the step size is α, and update the optimization variable:

[0030]

[0031] Iterate and update until the objective function converges or the maximum number of iterations is reached to generate the optimal solution.

[0032] Preferably, predicting the pollutant concentration distribution of all grid nodes according to the pollutant concentration of the sampling point and the airflow parameters of all grid nodes includes:

[0033] Construct a pollutant concentration variation model:

[0034]

[0035] In the formula, C i+1 , C i represents the pollutant concentration of the i+1th and ith grid nodes, is the gradient of pollutant concentration, represents the velocity vector of the air at the i-th grid node; C j represents the pollutant concentration of the grid node j adjacent to i, and Δd represents the distance between grid nodes i and j;

[0036] Set the initial value C j (0) =C i , the number of iterations is k, and the pollutant concentration change model is substituted to obtain:

[0037]

[0038] In the formula, C j (k+1) , C j (k) are the C of the k+1th and kth iterations respectively. j value,

[0039] The pollutant concentration variation model is solved iteratively until the model converges to obtain the pollutant concentration distribution of the grid nodes.

[0040] Preferably, the defining of the boundary conditions and the use of numerical simulation to analyze the airflow distribution in the operating room under the constraints of the boundary conditions include:

[0041] Define boundary conditions, including defining the air inlet to be located at the center of the operating room roof, defining the size of the air inlet and the air inlet velocity; defining the exhaust outlets to be located at the four corners of the bottom of the operating room, defining the size of the exhaust outlets and the air outlet velocity;

[0042] Determine the size of air density and aerodynamic viscosity, input boundary conditions, air density and aerodynamic viscosity into CFD software, and use finite volume method as solver to simulate airflow distribution.

[0043] In a second aspect, the present invention further provides a clean air conditioning unit operating parameter optimization system based on numerical simulation, the system comprising:

[0044] A grid division unit is used to establish a three-dimensional model of the operating room where the clean air conditioning unit is located, to grid the three-dimensional model to obtain multiple grid nodes, to determine the key area according to the position of the operating table and the activity trajectory of the medical staff, and to use the grid nodes located in the key area as sampling points;

[0045] A parameter acquisition unit is used to define boundary conditions, analyze the airflow distribution of the operating room under the constraint of boundary conditions by numerical simulation, and obtain the airflow parameters of all grid nodes, wherein the airflow parameters include velocity field, pressure field and temperature field;

[0046] The pollutant prediction unit is used to detect the pollutant concentration at the sampling point and predict the pollutant concentration distribution of all grid nodes according to the pollutant concentration at the sampling point and the airflow parameters of all grid nodes;

[0047] A judgment unit, used to judge whether there is a pollutant concentration of a certain grid node greater than a preset threshold value according to the prediction result of the pollutant concentration distribution;

[0048] A purification instruction generating unit, used to trigger an alarm and generate an air purification instruction when the pollutant concentration at a certain grid node is greater than a preset threshold;

[0049] The operating parameter optimization unit is used to establish an objective function with the goal of minimizing the pollutant concentration according to the pollutant concentration distribution and airflow parameters of each grid node when there is no pollutant concentration greater than a preset threshold at a certain grid node, solve the objective function using the gradient descent method, and optimize the air inlet direction and speed, and the air outlet direction and speed of the clean air-conditioning unit according to the solution results.

[0050] In a third aspect, the present invention further provides an electronic device comprising a processor and a memory, wherein the memory is used to store computer program code, and the computer program code comprises computer instructions. When the processor executes the computer instructions, the electronic device executes the method as described in the first aspect above and any possible implementation thereof.

[0051] In a fourth aspect, the present invention further provides a computer-readable storage medium, wherein a computer program is stored in the computer-readable storage medium, wherein the computer program includes program instructions, and when the program instructions are executed by a processor of an electronic device, the processor executes the method as described in the first aspect above and any possible implementation thereof.

[0052] Compared with the prior art, the present invention has the following beneficial effects:

[0053] 1) By building a three-dimensional model of the operating room and dividing the model into grids, the present invention can detect the concentration of pollutants in key areas in real time and dynamically adjust the airflow distribution according to the detection results. The real-time monitoring and dynamic adjustment mechanism significantly improves the response speed of the system, and measures can be taken quickly when the concentration of pollutants increases, effectively ensuring the air quality and surgical safety in the operating room.

[0054] 2) The present invention uses numerical simulation technology to analyze air flow distribution, and combines it with optimization algorithms such as the gradient descent method to automatically adjust the direction and speed of the air inlet and outlet to ensure that the air flow distribution reaches the optimal state. This can flexibly adapt to various complex environments in the operating room, significantly improve the air quality and safety of the operating room, and reduce the risk of infection.

[0055] 3) When performing pollutant detection, the present invention determines the sampling points through the grid nodes in the key areas. It only needs to monitor the local pollutant concentration and quickly and accurately predict the pollutant concentration in other areas in combination with the airflow distribution. Compared with configuring monitoring equipment at each grid node, there is no need to directly monitor the concentration of each node, which can greatly reduce the monitoring cost.

[0056] It is to be understood that both the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the disclosure. BRIEF DESCRIPTION OF THE DRAWINGS

[0057] In order to more clearly illustrate the technical solutions in the embodiments of the present invention or the background technology, the drawings required for use in the embodiments of the present invention or the background technology will be described below.

[0058] The drawings herein are incorporated into the specification and constitute a part of the specification. These drawings illustrate embodiments consistent with the present disclosure and are used to illustrate the technical solutions of the present disclosure together with the specification.

[0059] Figure 1 A schematic flow chart of a method for optimizing operating parameters of a clean air conditioning unit based on numerical simulation provided by an embodiment of the present invention;

[0060] Figure 2 A schematic structural diagram of a clean air conditioning unit operating parameter optimization system based on numerical simulation provided in an embodiment of the present invention. DETAILED DESCRIPTION

[0061] In order to enable those skilled in the art to better understand the scheme of the present invention, the technical scheme in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0062] Reference to "embodiments" herein means that a particular feature, structure, or characteristic described in conjunction with the embodiments may be included in at least one embodiment of the present invention. The appearance of the phrase in various places in the specification does not necessarily refer to the same embodiment, nor is it an independent or alternative embodiment that is mutually exclusive with other embodiments. It is explicitly and implicitly understood by those skilled in the art that the embodiments described herein may be combined with other embodiments.

[0063] In current operating rooms, clean air conditioning units are often based on static design principles, usually relying on experience and simple manual adjustments to control the operating parameters of the air conditioner, making it difficult to achieve the global optimal airflow distribution and purification effect, resulting in a decrease in air quality and surgical safety. To this end, the present invention provides a clean air conditioning unit operating parameter optimization method based on numerical simulation, which can optimize the air inlet direction and speed, the air outlet direction and speed of the air conditioning unit by modeling and analyzing the airflow distribution in the operating room, combined with the pollutant distribution of the grid nodes in the pollutant concentration prediction model, thereby greatly improving the air quality in the operating room and reducing the risk of surgical infection.

[0064] See also Figure 1 , Figure 1 The present invention provides a flow chart of a method for optimizing the operating parameters of a clean air conditioning unit based on numerical simulation. Figure 1 As shown, the method includes:

[0065] S10. Establish a three-dimensional model of the operating room where the clean air conditioning unit is located, mesh the three-dimensional model to obtain multiple mesh nodes, determine the key area according to the position of the operating table and the activity trajectory of the medical staff, and use the mesh nodes located in the key area as sampling points.

[0066] The specific implementation process of this step is as follows:

[0067] 11) Obtain the detailed dimensions and layout of the operating room: including measuring the actual dimensions of the operating room (length, width, height); recording the location of all fixed equipment in the operating room, such as the operating table, lighting equipment, wall sockets, etc. Then, combined with the design drawings of the operating room air conditioning system, determine the location of the air supply and exhaust vents.

[0068] 12) Build a 3D model: Use CAD software or other 3D modeling tools to build a 3D model of the operating room based on actual measurement data and design drawings. Accurately arrange the position of the operating table and other important equipment in the model.

[0069] 13) Meshing: Meshing the 3D model, usually CFD software can be used to perform meshing tasks. Meshing needs to take into account the characteristics of air flow and select the appropriate mesh size to ensure calculation accuracy while reducing the consumption of computing resources.

[0070] For example: Assume that the size of the operating room is 6m long, 4m wide, and 3m high; one way is to use a coarser grid, the grid size is: side length 0.5m; the total number of grids is: (6 / 0.5)×(4 / 0.5)×(3 / 0.5)=12×8×6=576 grids. If a finer grid is used, for example, the side length is 0.1m, then the total number of grids is: (6 / 0.1)×(4 / 0.1)×(3 / 0.1)=60×40×30=72000 grids. It can be understood that a coarser grid is suitable for preliminary simulation because it can provide basic flow characteristics at a lower computational cost. A finer grid can provide more detailed flow characteristics and is suitable for situations where higher precision analysis is required, but the computational cost is also increased accordingly. Therefore, how to determine the grid size in actual applications can be determined as needed, and this embodiment does not impose any restrictions.

[0071] Preferably, when dividing the mesh, the operating room model can also be divided in the form of a combination of meshes of different granularities. For example, in the key area around the operating table, local refined meshes (local encryption) can be used to improve accuracy, and relatively coarse meshes can be used in other locations. The mesh division needs to consider important structures in the operating room, such as the operating table, equipment, walls, etc., to ensure that these structures will not be cut by the mesh. Therefore, through such combined mesh division, the consumption of computing resources can be controlled while ensuring the calculation accuracy. When performing numerical analysis in specific CFD software, the mesh parameters can also be adjusted in combination with the computing power conditions of the CFD software.

[0072] 14) Determine the key area: Define the key area based on the location of the operating table and the activity trajectory of the medical staff. For example, the space within 1m around the operating table can be regarded as the key area, and the activity trajectory of the medical staff can be the local space where the medical staff moves most frequently as the key area.

[0073] 15) Select sampling points: Select grid nodes in the key area as sampling points. These points are usually representative of the air quality in the area. The number of sampling points depends on the required research accuracy of the scenario.

[0074] S20. Define boundary conditions, use numerical simulation to analyze the airflow distribution in the operating room under the constraints of the boundary conditions, and obtain the airflow parameters of all grid nodes, wherein the airflow parameters include velocity field, pressure field, and temperature field.

[0075] Specifically, the boundary conditions are defined, and numerical simulation is used to analyze the airflow distribution in the operating room under the constraints of the boundary conditions, including:

[0076] Define boundary conditions, including defining the air inlet at the center of the operating room roof, defining the size of the air inlet and the air inlet speed; define the exhaust outlet at the four corners of the bottom of the operating room, defining the size of the exhaust outlet and the air outlet speed.

[0077] Determine the size of air density and aerodynamic viscosity, input boundary conditions, air density and aerodynamic viscosity into CFD software, and use finite volume method as solver to simulate airflow distribution.

[0078] In this embodiment, the air inlet is located in the center of the top of the room, with a size of 0.5m × 0.5m, and a wind speed of 2m / s. The exhaust ports are located at the four corners of the bottom of the room, and each exhaust port has a size of 0.25m × 0.25m. The total exhaust volume is equal to the intake volume to maintain pressure balance. The density of air is about 1.225kg / m 3 (value under standard atmospheric pressure). The dynamic viscosity of air is about 1.81×10 -5 Pa·s (value at 20°C). Use CFD software to input the above data and perform simulation, using the finite volume method as the solver. Through simulation, the velocity field, pressure field and temperature field at each grid node can be obtained.

[0079] For example, at a grid point (3m, 2m, 2.5m) directly below the air inlet, the simulation results are:

[0080] Velocity field: velocity is 1.5 m / s, direction downward;

[0081] Pressure field: Approximate standard atmospheric pressure;

[0082] Temperature field: The simulated temperature is 20℃.

[0083] S30, detecting the pollutant concentration at the sampling point, and predicting the pollutant concentration distribution of all grid nodes according to the pollutant concentration at the sampling point and the airflow parameters of all grid nodes.

[0084] From the above content, it can be seen that no matter whether a finer grid or a coarser grid is used, more grid nodes will be obtained. If sensors are used to monitor the pollutant concentration of all grid nodes according to the number of grids, it is obviously unreasonable and will cost a lot of equipment costs. If the grid nodes are divided into regions, for example, the three-dimensional model is divided into 9 regions, and sensors are set up in each region to monitor the pollutant concentration, this method is usually only effective for the detection of grid nodes closer to the sensor, while the relatively farther grid nodes cannot be accurately calculated, and the deployment of 9 sensors also requires a lot of equipment costs.

[0085] In order to solve this problem, this embodiment determines the sampling points according to the key areas obtained in the previous steps. It is only necessary to detect the pollutant concentration at the sampling points, and then predict the pollutant concentration distribution of all grid nodes based on the pollutant concentration at the sampling points and the airflow parameters of all grid nodes. In this way, it is only necessary to detect the local pollutant concentration in a small range to obtain the pollutant concentration distribution in the operating room, which greatly reduces the monitoring cost.

[0086] Assume that the operating table is located in the center of the operating room, with specific coordinates of (3 meters, 2 meters, 1.5 meters). Assume that the main activities of medical staff are concentrated within a radius of 1 meter around the operating table. Therefore, the coordinate range of the key area can be expressed as 2.0≤X≤4.0, 1.5≤Y≤2.5, 1.0≤Z≤2.0. Assuming that the grid size is 0.5m×0.5m×0.5m, the coordinates of the grid nodes in the key area can be expressed as X∈{2.0,2.5,3.0,3.5,4.0}; Y∈{1.5,2.0,2.5}; Z∈{1.0,1.5,2.0}. That is, there are 5×3×3=45 grid nodes in the key area. Therefore, it can be determined that the size of the key area is 5×3×3, and 8 vertices and one center point can be taken as sampling points. In this way, the pollutant concentrations of these 9 sampling points can be obtained, and the pollutant concentrations of all grid nodes can be predicted.

[0087] Specifically, predicting the pollutant concentration distribution of all grid nodes according to the pollutant concentration of the sampling point and the airflow parameters of all grid nodes includes:

[0088] Construct a pollutant concentration variation model:

[0089]

[0090] In the formula, C i+1 , C i represents the pollutant concentration of the i+1th and ith grid nodes, is the gradient of pollutant concentration, represents the velocity vector of the air at the i-th grid node; C j represents the pollutant concentration of the grid node j adjacent to i, and Δd represents the distance between grid nodes i and j;

[0091] Set the initial value C j (0) =C i , the number of iterations is k, and the pollutant concentration change model is substituted to obtain:

[0092]

[0093] In the formula, C j (k+1), C j (k) are the C of the k+1th and kth iterations respectively. j value.

[0094] The pollutant concentration variation model is solved iteratively until the model converges to obtain the pollutant concentration distribution of the grid nodes.

[0095] This embodiment uses the finite difference method to approximately solve the pollutant transport equation based on the continuous medium assumption. The transport of pollutants is mainly affected by two factors, namely diffusion and convection. In this model, the main focus is on the convection factor, that is, the phenomenon that pollutants move with the airflow. By iteratively updating the pollutant concentration of each grid node, the actual pollutant distribution state is gradually approached.

[0096] Therefore, through numerical simulation, by only detecting the pollutant concentrations at a limited number of sampling points, the pollutant concentration distribution at each grid node in the operating room can be accurately predicted, helping to identify potential high-incidence areas of pollution, reducing monitoring costs, and taking measures to reduce the concentration of pollutants in the air during surgery, thereby improving the safety and success rate of surgery.

[0097] S40, judging whether there is a grid node whose pollutant concentration is greater than a preset threshold value according to the predicted result of the pollutant concentration distribution;

[0098] S50: If yes, trigger an alarm and generate an air purification instruction;

[0099] S60. If not, establish an objective function based on the pollutant concentration distribution and airflow parameters of each grid node with the goal of minimizing the pollutant concentration, solve the objective function using the gradient descent method, and optimize the air inlet direction and speed, and the air outlet direction and speed of the clean air conditioning unit based on the solution results.

[0100] When the pollutant concentration distribution of all grid nodes is obtained, it is compared with the preset safety threshold. If it is found that the pollutant concentration of any grid node exceeds the preset safety threshold, step S50 is executed; otherwise, step S60 is executed.

[0101] Specifically, the alarm prompt in step S50 can use an acoustic signal or a light signal to remind medical staff to pay attention. When generating a purification instruction, according to the location and degree of the exceeding node, a corresponding air purification instruction is generated, such as starting an additional air purification device, increasing the number of ventilation times, etc.; finally, the purification instruction is sent to the relevant control system to immediately execute the air purification operation.

[0102] Therefore, through real-time monitoring and automated alarm mechanisms, situations where pollutant concentrations exceed the standard can be quickly detected and responded to, avoiding health threats to patients and medical staff.

[0103] If the pollutant concentration of all grid nodes is lower than the preset threshold, it means that it is temporarily within the safe range. However, in order to prevent the pollutant concentration from increasing or even exceeding the safety threshold, it is necessary to optimize the operating parameters of the current air-conditioning unit according to the pollutant concentration distribution and airflow parameters of each grid node to achieve the goal of minimizing the pollutant concentration.

[0104] In one embodiment, establishing an objective function with the goal of minimizing pollutant concentration includes:

[0105] Define the objective function: Assume C i is the pollutant concentration of the i-th grid node, then the objective function J is:

[0106]

[0107] Where N is the total number of grid nodes, w i is the weight factor of each grid node;

[0108] Determine the optimization variable: There are m air inlets and n exhaust ports, each of which has three directions, forming coordinates (x, y, z) and a speed value U; determine the optimization variable X as:

[0109] X=[x1,y1,z1,U1,...x m ,y m , Z m , U m , x m+1 ,y m+1 , z m+1 , U m+1 ,...x m+n ,y m+n , Z m+n , U m+n ]

[0110] In the formula, (x m ,y m , z m ), U m represents the coordinates and velocity value of the mth air inlet, (x m+1 ,y m+1 , z m+1 ) represents the coordinates of the first exhaust port, (x m+n ,y m+n , z m+n ) represents the coordinates of the nth exhaust port, U m+1 , U m+n Indicates the velocity value of the 1st and nth exhaust ports;

[0111] Create constraints:

[0112] l0≤x i ≤u0

[0113] l1≤y i ≤u1

[0114] l2≤z i ≤u2

[0115] v min ≤U i ≤v max

[0116] In the formula, l0, l1, l2 are x i ,y i , z i The corresponding lower limits, u0, u1, and u2 are x i ,y i , z i The corresponding upper limit, v min 、v max are the minimum speed and maximum speed respectively.

[0117] Since the goal is to minimize the pollutant concentration of all grid nodes, a weighted sum objective function is defined, which reflects the importance or sensitivity of each grid node by introducing a weight factor for each grid node, where the weight factor can be determined based on the distance from the critical area.

[0118] Furthermore, the use of the gradient descent method to solve the objective function includes:

[0119] Initialize the optimization variables, assuming that X is randomly generated:

[0120] X=[x1,y1,z1,U1,x2,y2,z2,U2,x3,y3,z3,U3]

[0121] Calculate the gradient of the objective function J with respect to the optimization variable X and obtain the gradient vector for:

[0122]

[0123] Assume the number of iterations is T, the step size is α, and update the optimization variable:

[0124]

[0125] Iterate and update until the objective function converges or the maximum number of iterations is reached to generate the optimal solution.

[0126] By adjusting the position and speed of the air inlet and exhaust port, the air flow pattern in the operating room can be optimized to ensure that the concentration of pollutants is as low as possible. Even if the concentration of pollutants has not exceeded the standard, the operating parameters of the air conditioning system can be optimized to prevent possible problems in the future and keep the air in the operating room in a safe state. This embodiment uses the objective function and optimization algorithm to dynamically adjust the air conditioning system according to actual conditions, making the system operation more efficient and economical. In addition, the ability to more effectively control the spread of pollutants reduces the need for human intervention, reduces the possibility of operational errors, and improves the overall safety of the operating room.

[0127] In summary, the method provided by the present invention can at least achieve the following beneficial effects:

[0128] 1) By building a three-dimensional model of the operating room and dividing the model into grids, the present invention can detect the concentration of pollutants in key areas in real time and dynamically adjust the airflow distribution according to the detection results. The real-time monitoring and dynamic adjustment mechanism significantly improves the response speed of the system, and measures can be taken quickly when the concentration of pollutants increases, effectively ensuring the air quality and surgical safety in the operating room.

[0129] 2) The present invention uses numerical simulation technology to analyze air flow distribution, and combines it with optimization algorithms such as the gradient descent method to automatically adjust the direction and speed of the air inlet and outlet to ensure that the air flow distribution reaches the optimal state. This can flexibly adapt to various complex environments in the operating room, significantly improve the air quality and safety of the operating room, and reduce the risk of infection.

[0130] 3) When performing pollutant detection, the present invention determines the sampling points through the grid nodes in the key areas. It only needs to monitor the local pollutant concentration and quickly and accurately predict the pollutant concentration in other areas in combination with the airflow distribution. Compared with configuring monitoring equipment at each grid node, there is no need to directly monitor the concentration of each node, which can greatly reduce the monitoring cost.

[0131] See also Figure 2 In one embodiment, the present invention further provides a clean air conditioning unit operation parameter optimization system based on numerical simulation, the system comprising:

[0132] The grid division unit 100 is used to establish a three-dimensional model of the operating room where the clean air conditioning unit is located, to grid the three-dimensional model to obtain a plurality of grid nodes, to determine the key area according to the position of the operating table and the activity trajectory of the medical staff, and to use the grid nodes located in the key area as sampling points;

[0133] The parameter acquisition unit 200 is used to define boundary conditions, analyze the airflow distribution of the operating room under the constraint of the boundary conditions by numerical simulation, and obtain the airflow parameters of all grid nodes, wherein the airflow parameters include velocity field, pressure field and temperature field;

[0134] The pollutant prediction unit 300 is used to detect the pollutant concentration at the sampling point and predict the pollutant concentration distribution of all grid nodes according to the pollutant concentration at the sampling point and the airflow parameters of all grid nodes;

[0135] The judgment unit 400 is used to judge whether there is a grid node whose pollutant concentration is greater than a preset threshold value according to the prediction result of the pollutant concentration distribution;

[0136] A purification instruction generating unit 500 is used to trigger an alarm and generate an air purification instruction when the pollutant concentration of a certain grid node is greater than a preset threshold;

[0137] The operating parameter optimization unit 600 is used to establish an objective function with the goal of minimizing the pollutant concentration according to the pollutant concentration distribution and airflow parameters of each grid node when there is no grid node with a pollutant concentration greater than a preset threshold, solve the objective function using the gradient descent method, and optimize the air inlet direction and speed, and the air outlet direction and speed of the clean air-conditioning unit according to the solution results.

[0138] It can be understood that the functions or modules included in the clean air-conditioning unit operating parameter optimization system based on numerical simulation provided in this embodiment can be used to execute the method described in the above method embodiment. Its specific implementation can refer to the description of the above method embodiment. For the sake of brevity, it will not be repeated here.

[0139] The present invention also provides an electronic device, including a processor and a memory, wherein the memory is used to store computer program code, and the computer program code includes computer instructions. When the processor executes the computer instructions, the electronic device executes a method as described in any possible implementation manner.

[0140] The present invention also provides a computer-readable storage medium, in which a computer program is stored. The computer program includes program instructions. When the program instructions are executed by a processor of an electronic device, the processor executes a method as described in any possible implementation manner.

[0141] Those skilled in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of the present invention.

[0142] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices and units described above can refer to the corresponding processes in the aforementioned method embodiments, and will not be repeated here. Those skilled in the art can also clearly understand that the descriptions of the various embodiments of the present invention have different focuses. For the convenience and brevity of description, the same or similar parts may not be repeated in different embodiments. Therefore, for parts not described or not described in detail in a certain embodiment, refer to the records of other embodiments.

Claims

1. A method for optimizing operating parameters of a clean air conditioning unit based on numerical simulation, characterized in that: The method comprises: A three-dimensional model of the operating room where the clean air conditioning unit is located is established, and the three-dimensional model is meshed to obtain multiple grid nodes. The key areas are determined according to the location of the operating table and the activity trajectory of the medical staff, and the grid nodes located in the key areas are used as sampling points. Define boundary conditions, use numerical simulation to analyze the airflow distribution in the operating room under the constraint of boundary conditions, and obtain the airflow parameters of all grid nodes, wherein the airflow parameters include velocity field, pressure field and temperature field; Detect the pollutant concentration at the sampling point, and predict the pollutant concentration distribution of all grid nodes based on the pollutant concentration at the sampling point and the airflow parameters of all grid nodes; According to the predicted results of pollutant concentration distribution, determine whether there is a grid node with a pollutant concentration greater than a preset threshold; If so, an alarm is triggered and an air purification instruction is generated; If not, according to the pollutant concentration distribution and airflow parameters of each grid node, an objective function is established with the goal of minimizing the pollutant concentration. The objective function is solved using the gradient descent method, and the air inlet direction and speed, as well as the air outlet direction and speed of the clean air-conditioning unit are optimized based on the solution results.

2. The method for optimizing operating parameters of clean air conditioning units based on numerical simulation according to claim 1, characterized in that: The objective function is established with the goal of minimizing the pollutant concentration, including: Define the objective function: Assume C i is the pollutant concentration of the i-th grid node, then the objective function J is: Where N is the total number of grid nodes, w i is the weight factor of each grid node; Determine the optimization variable: There are m air inlets and n exhaust ports. Each air inlet and exhaust port has three directions, forming coordinates (x, y, z) and a speed value U. Determine the optimization variable X as: X=[x1,y1,z1,U1,...x m ,y m ,z m ,U m ,x m+1 ,y m+1 ,z m+1 ,U m+1 …x m+n ,y m+n ,z m+n ,U m+n ] In the formula, (x m ,y m ,z m ), U m represents the coordinates and velocity value of the mth air inlet, (x m+1 ,y m+1 ,z m+1 ) represents the coordinates of the first exhaust port, (x m+n ,y m+n ,z m+n ) represents the coordinates of the nth exhaust port, U m+1 , U m+n Indicates the velocity value of the 1st and nth exhaust ports; Create constraints: l0≤x i ≤u0 l1≤y i ≤u1 l2≤z i ≤u2 in min ≤U i ≤in max In the formula, l0, l1, l2 are x i ,y i , z i The corresponding lower limits, u0, u1, and u2 are x i , t i , z i The corresponding upper limit, v min 、v max are the minimum speed and maximum speed respectively.

3. The method for optimizing operating parameters of clean air conditioning units based on numerical simulation according to claim 2 is characterized in that: The method of solving the objective function by using the gradient descent method includes: Initialize the optimization variables, assuming that X is randomly generated: X=[x1,y1,z1,U1,x2,y2,z2,U2,x3,y3,z3,U3] Calculate the gradient of the objective function J with respect to the optimization variable X and obtain the gradient vector for: Assume the number of iterations is T, the step size is α, and update the optimization variable: Iterate and update until the objective function converges or the maximum number of iterations is reached to generate the optimal solution.

4. The method for optimizing operating parameters of clean air conditioning units based on numerical simulation according to claim 2, characterized in that: The method predicts the pollutant concentration distribution of all grid nodes according to the pollutant concentration of the sampling point and the airflow parameters of all grid nodes, including: Construct a pollutant concentration variation model: In the formula, C i+1 , C i represents the pollutant concentration of the i+1th and ith grid nodes, is the gradient of pollutant concentration, represents the velocity vector of the air at the i-th grid node; C j represents the pollutant concentration of the grid node j adjacent to i, and Δd represents the distance between grid nodes i and j; Set the initial value C j (0) =C i , the number of iterations is k, and the pollutant concentration change model is substituted to obtain: In the formula, C j (k+1) , C j (k) are the C of the k+1th and kth iterations respectively. j value, The pollutant concentration variation model is solved iteratively until the model converges to obtain the pollutant concentration distribution of the grid nodes.

5. The method for optimizing operating parameters of clean air conditioning units based on numerical simulation according to claim 1, characterized in that: The step of defining boundary conditions and analyzing the airflow distribution in the operating room under the constraint of the boundary conditions by numerical simulation includes: Define boundary conditions, including defining the air inlet to be located at the center of the operating room roof, defining the size of the air inlet and the air inlet velocity; defining the exhaust outlets to be located at the four corners of the bottom of the operating room, defining the size of the exhaust outlets and the air outlet velocity; Determine the size of air density and aerodynamic viscosity, input boundary conditions, air density and aerodynamic viscosity into CFD software, and use finite volume method as solver to simulate airflow distribution.

6. A clean air conditioning unit operating parameter optimization system based on numerical simulation, characterized in that: The system comprises: A grid division unit is used to establish a three-dimensional model of the operating room where the clean air conditioning unit is located, to grid the three-dimensional model to obtain multiple grid nodes, to determine the key area according to the position of the operating table and the activity trajectory of the medical staff, and to use the grid nodes located in the key area as sampling points; A parameter acquisition unit is used to define boundary conditions, analyze the airflow distribution of the operating room under the constraint of boundary conditions by numerical simulation, and obtain the airflow parameters of all grid nodes, wherein the airflow parameters include velocity field, pressure field and temperature field; The pollutant prediction unit is used to detect the pollutant concentration at the sampling point and predict the pollutant concentration distribution of all grid nodes according to the pollutant concentration at the sampling point and the airflow parameters of all grid nodes; A judgment unit, used to judge whether there is a pollutant concentration of a certain grid node greater than a preset threshold value according to the prediction result of the pollutant concentration distribution; A purification instruction generating unit, used to trigger an alarm and generate an air purification instruction when the pollutant concentration at a certain grid node is greater than a preset threshold; The operating parameter optimization unit is used to establish an objective function with the goal of minimizing the pollutant concentration according to the pollutant concentration distribution and airflow parameters of each grid node when there is no pollutant concentration greater than a preset threshold at a certain grid node, solve the objective function using the gradient descent method, and optimize the air inlet direction and speed, and the air outlet direction and speed of the clean air-conditioning unit according to the solution results.

7. An electronic device, characterized in that: include: A processor and a memory, wherein the memory is used to store computer program codes, wherein the computer program codes include computer instructions. When the processor executes the computer instructions, the electronic device executes the method for optimizing operating parameters of a clean air-conditioning unit based on numerical simulation as described in any one of claims 1 to 5.

8. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, which includes program instructions. When the program instructions are executed by a processor of an electronic device, the processor executes the method for optimizing operating parameters of a clean air-conditioning unit based on numerical simulation as described in any one of claims 1 to 5.

Images