Design method for realizing air volume equalization of passenger train air duct air outlet

Abstract

The present application relates to the technical field of passenger car air conditioning system, and relates to a design method for realizing air volume equalization of air outlet of passenger car air duct. The design method comprises: obtaining basic parameters of target air duct; obtaining air volume data of each air outlet; calculating air volume equalization evaluation index of current air duct, if satisfied, outputting air outlet radius; otherwise, entering first stage optimization, comprising: fitting function relationship between air outlet radius and distance from air outlet to car head; calculating air volume equalization evaluation index of current air duct; if satisfied, outputting air outlet radius; if not satisfied, entering second stage optimization, comprising: using proxy model for prediction; calculating air volume equalization evaluation index of current air duct; if satisfied, obtaining optimal parameter set of flow guide structure, outputting air outlet radius and optimal parameter set of flow guide structure. The design target is converted into mathematical optimization problem, and is solved by two-stage optimization process, so as to complete optimal air volume equalization design of air outlet.

Description

Technical Field

[0001] This invention relates to the field of bus air conditioning system technology, and in particular to a design method for achieving uniform airflow at the air outlet of a bus duct. Background Technology

[0002] The comfort of a bus's air conditioning system largely depends on the uniformity of airflow from the duct outlets. Currently, most bus ducts use a design with a constant cross-section or a simple variable cross-section, resulting in uniformly sized outlets. Due to pressure loss during airflow within the duct, outlets closer to the fan outlet experience higher air pressure and volume, while outlets farther away have lower air pressure and volume. This significant difference in air velocity between near and far ends causes passengers in the front of the carriage to feel too cold, while those in the rear feel stuffy, severely impacting passenger comfort. Furthermore, to meet the cooling needs of rear passengers, it is often necessary to increase the fan power, thereby reducing the overall energy efficiency of the air conditioning system.

[0003] While existing technologies have attempted to address the issue by adding fixed deflectors or altering the duct cross-section, these methods largely rely on experience-based design and lack systematic optimization, often resulting in limited improvement and poor versatility. Therefore, a scientific and efficient design method is urgently needed to fundamentally solve the problem of uneven airflow distribution in bus ducts. Summary of the Invention

[0004] The main objective of this invention is to provide a design method for achieving uniform airflow at the air outlet of a bus duct, aiming to solve the problem of uneven airflow distribution in bus ducts.

[0005] A design method for achieving uniform airflow at the air outlet of a bus duct includes the following steps:

[0006] Step 1: Obtain the basic parameters of the target air duct; establish an initial CFD simulation model, conduct the first simulation, and obtain the airflow data for each air outlet; the basic parameters of the target air duct include the total length of the air duct. Number of air outlets Initial position of the air outlet and the radius of the air outlet ;

[0007] The second step is to calculate the airflow uniformity evaluation index of the current air duct based on the airflow data of each air outlet obtained in the first step, and make a judgment: if the requirements are met, proceed to the fifth step; if the requirements are not met, proceed to the next step.

[0008] The third step is to conduct the first phase of optimization, which specifically includes:

[0009] Step 3.1: Design at least one set of operating conditions based on the air volume data of each air outlet, where the radius varies with distance; extract the radius corresponding to the maximum air volume at each location in the corresponding operating condition;

[0010] Step 3.2: Fit an air outlet radius based on the radius corresponding to the maximum air volume at each location obtained in Step 3.1. Distance from air vent to front of the car The functional relationship between them was established, and a CFD model was built based on the functional relationship. The air volume of each air outlet was obtained through CFD model simulation calculation; the functional relationship is as follows:

[0011] ;

[0012] in: For polynomial coefficients, ; For constant terms;

[0013] Step 3.3: Calculate the airflow uniformity evaluation index of the current air duct based on the airflow volume of each air outlet obtained in Step 3.2, and make a judgment: if the requirements are met, proceed to Step 5; if the requirements are not met, proceed to the next step.

[0014] Step four: Conduct the second phase of optimization, which specifically includes:

[0015] Step 4.1: Obtain the design variable set for the airflow guide structure; the design variable set for the airflow guide structure includes the tilt angle of the airflow guide plate. Length of the deflector Projected length of the deflector The position of the air deflector from the edge of the air outlet and the distance between the spoiler and the front of the car. ; Get the number of iterations =1;

[0016] Step 4.2: Use a surrogate model to make predictions and obtain the predicted air volume for each air outlet;

[0017] Step 4.3: Based on the predicted airflow volume of each outlet obtained in Step 4.2, calculate the airflow uniformity evaluation index of the current air duct and make a judgment: if the requirements are met, obtain the optimal parameter set of the guide structure and proceed to Step 5; if the requirements are not met, then... Return to step 4.2;

[0018] Step 5: Output the air outlet radius obtained in Step 3. Or the air vent radius obtained in the third step. Output and the optimal parameter set of the flow guiding structure obtained in step four.

[0019] Preferably, in step 3.2, three sets of operating conditions are designed, with the radius varying linearly, exponentially, and logarithmically with distance. CFD models for the three sets of operating conditions are established and simulation calculations are performed separately. The radius corresponding to the maximum air volume at each location in all operating conditions is extracted. Based on the obtained radius corresponding to the maximum air volume at each location, an air outlet radius is fitted. Distance from air vent to front of the car The functional relationship between them.

[0020] Preferably, in step 4.2, at least two surrogate models are used for prediction. By comparing the air volume uniformity evaluation index corresponding to the predicted air volume output by each surrogate model, the air volume predicted by each air outlet corresponding to the surrogate model with the best performance is selected.

[0021] Preferably, the surrogate model includes at least two of the following: regression model, neural network model, and statistical nonparametric model.

[0022] Preferably, the standard deviation is used as the evaluation index for air volume uniformity. The expression is as follows:

[0023] ;

[0024] in: For the first Predicted air volume for each air outlet This represents the total number of air outlets. This represents the average value of the predicted air volume at the air outlet.

[0025] Preferred, standard deviation If less than If so, then the requirement is met.

[0026] The effect of applying the technical solution of this invention is:

[0027] The design method for achieving uniform airflow at the air outlets of a bus duct disclosed in this invention includes: obtaining the basic parameters of the target duct; establishing an initial CFD simulation model, performing the first simulation, and obtaining airflow data for each air outlet; the basic parameters of the target duct include the total length of the duct. Number of air outlets Initial position of the air outlet and the radius of the air outlet Based on the obtained airflow data from each air outlet, calculate the airflow uniformity evaluation index of the current air duct and make a judgment: if the requirements are met, output the obtained air outlet radius. If the requirements are not met, proceed to the first stage of optimization, which includes: based on the air volume data of each air outlet; design at least one set of operating conditions where the radius varies with distance; extract the radius corresponding to the maximum air volume at each location in the corresponding operating condition; and fit an air outlet radius based on the radius corresponding to the maximum air volume at each location. Distance from air vent to front of the car The functional relationship between the two is determined, and the air volume of each outlet is obtained through CFD simulation based on the functional relationship. Based on the obtained air volume of each outlet, the air volume uniformity evaluation index of the current duct is calculated and judged. If the requirements are met, the obtained outlet radius is output. If the requirements are not met, the second stage of optimization is initiated, which includes: obtaining the design variable set of the airflow guiding structure; using a surrogate model for prediction to obtain the predicted airflow volume of each outlet; calculating the airflow uniformity evaluation index of the current duct based on the obtained predicted airflow volume of each outlet, and making a judgment: if the requirements are met, the optimal parameter set of the airflow guiding structure is obtained, and the obtained outlet radius is output. Output the optimal parameter set of the resulting airflow guiding structure; if the requirements are not met, return to iteration until the requirements are met. The design objective is transformed into a mathematical optimization problem, and solved progressively through a two-level optimization process to obtain the optimal outlet airflow uniformity design, i.e., output the outlet radius, or output the outlet radius... And the optimal parameter set for the flow guiding structure. Attached Figure Description

[0028] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on the structures shown in these drawings without creative effort.

[0029] Figure 1 This is a schematic diagram illustrating the design method for achieving uniform airflow at the air outlet of a bus duct in this embodiment of the invention.

[0030] Figure 2 This is a schematic diagram of the overall structure of the bus air duct in an embodiment of the present invention;

[0031] Figure 3 This is a schematic diagram of the flow guiding structure in an embodiment of the present invention;

[0032] Figure 4This is a schematic diagram of the final bus air duct in an embodiment of the present invention, wherein: (a) represents a three-dimensional schematic diagram of the bus air duct (the fan air outlet is located at the top, and the air outlet is located at the bottom opposite to the fan air outlet); (b) represents a top view of the bottom plate of (a) without showing the air guide structure; (c) represents a top view of the bottom plate with showing the air guide structure; and (d) represents a schematic diagram of the angle between the air guide structure and the bottom plate of (c).

[0033] Explanation of icon numbers:

[0034] 1. Main duct; 2. Flow guiding structure; 3. Fan air outlet; 4. Air outlet.

[0035] The realization of the objective, functional features and advantages of the present invention will be further explained in conjunction with the embodiments and with reference to the accompanying drawings. Detailed Implementation

[0036] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative effort are within the scope of protection of the present invention.

[0037] It should be noted that all directional indications (such as up, down, left, right, front, back, etc.) in the embodiments of the present invention are only used to explain the relative positional relationship and movement of each component in a certain specific posture (as shown in the figure). If the specific posture changes, the directional indication will also change accordingly.

[0038] Furthermore, in this invention, descriptions involving "first," "second," etc., are for descriptive purposes only and should not be construed as indicating or implying their relative importance or implicitly specifying the number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include at least one of that feature. In the description of this invention, "a plurality of" means at least two, such as two, three, etc., unless otherwise explicitly specified.

[0039] In this invention, unless otherwise explicitly specified and limited, the terms "connection," "fixed," etc., should be interpreted broadly. For example, "fixed" can mean a fixed connection, a detachable connection, or an integral part; it can mean a mechanical connection or an electrical connection; it can mean a direct connection or an indirect connection through an intermediate medium; it can mean the internal communication of two components or the interaction between two components, unless otherwise explicitly limited. Those skilled in the art can understand the specific meaning of the above terms in this invention according to the specific circumstances.

[0040] Furthermore, the technical solutions of the various embodiments of the present invention can be combined with each other, but only if they are feasible for those skilled in the art. If the combination of technical solutions is contradictory or cannot be implemented, it should be considered that such combination of technical solutions does not exist and is not within the scope of protection claimed by the present invention.

[0041] A design method for achieving uniform airflow at the air outlet of a bus duct, used in the design of bus ducts, see details. Figure 1 A CAD model of the bus duct was established; CFD simulation was performed based on the division of the computational grid and the setting of simulation parameters; the standard deviation of the air volume at each outlet was calculated, the simulation results were analyzed, and the air volume variation law was summarized; multiple sets of "radius-distance" working conditions were set and simulated, the simulation data were analyzed to determine the radius corresponding to the maximum air volume, and the data was processed by methods such as fitting and regression analysis to obtain the radius formula; the parameters were optimized using neural networks and other optimization models, and the guide vane scheme was designed using the optimization model based on the radius formula and guide vane parameters; the original bus duct CFD model was modified and simulated, and the uniformity of the air volume was checked to determine whether the uniformity met the standard. If it met the standard, the optimal design scheme was output; if it did not meet the standard, the process of designing the guide vane scheme using the optimization model based on the radius formula and guide vane parameters was returned to redesign.

[0042] For details on bus ventilation ducts, please refer to Figures 2-4 This mainly includes a main duct 1, a fan air outlet 3, and air outlets 4 directly installed on the main duct. Initially, the radii of each air outlet 4 are usually the same. The main duct 1 is a constant cross-section duct. A flow guide structure 2 can be installed at each air outlet 4. Multiple air outlets 4 are evenly distributed side-by-side on one side of the main duct. Figure 2 The diagram illustrates three fan air outlets, numbered 3(1), 3(2), and 3(3); and 11 sets of air outlets, numbered 4(1), 4(2), 4(3), 4(4), 4(5), 4(6), 4(7), 4(8), 4(9), 4(10), and 4(11). The area occupied by the three fan air outlets on the top plate of the bus duct (i.e., the fan area) is... The total length of the air duct is The middle position of the three fan air outlets is located at one-third of the total length of the air duct, that is... .

[0043] The design method for achieving uniform airflow at the air outlet of a bus duct includes the following steps:

[0044] The first step is to obtain the basic parameters of the target air duct; establish an initial CFD simulation model, conduct the first simulation, and obtain the air volume data of each air outlet. The basic parameters of the target air duct include the total length of the air duct. Number of air outlets Initial position of the air outlet and the radius of the air outlet .

[0045] The second step involves analyzing the airflow data from each air outlet obtained in the first step. Calculate the airflow uniformity evaluation index of the current duct and make a judgment: if the requirements are met, proceed to step 5; if the requirements are not met, proceed to step 1.

[0046] The third step is to perform the first stage of optimization (i.e., parameterization of the air outlet area), which specifically includes:

[0047] Step 3.1: Based on the air volume data of each air outlet Design at least one set of operating conditions where the radius varies with distance; extract the radius corresponding to the maximum air volume at each location in the corresponding operating condition.

[0048] The preferred method here is based on the air volume data of each air outlet. Preliminary understanding of its windward location Based on the pattern of change, three sets of working conditions were designed where the radius changes linearly, exponentially, and logarithmically with distance. By establishing CFD models for the three sets of working conditions and performing simulation calculations respectively, the radius corresponding to the maximum air volume at each location in all working conditions was extracted. To determine the optimal radius of each air outlet, quadratic curve fitting was performed on the air volume data of each air outlet under the three working conditions to calculate the radius corresponding to its theoretical maximum air volume.

[0049] Step 3.2: Fit an air outlet radius based on the radius corresponding to the maximum air volume at each location obtained in Step 3.1. Distance from air vent to front of the car The functional relationship between them was determined, and a CFD model was established based on this relationship. The air volume of each outlet was obtained through CFD model simulation calculation. The functional relationship (i.e., the radius formula) is as follows:

[0050] ;

[0051] in: For polynomial coefficients, ; This is a constant term.

[0052] This function is typically a polynomial, and its specific form and coefficients are determined through a regression algorithm. Its purpose is to initially compensate for pressure loss by increasing the flow area at the far-end air outlet. Applying this functional relationship to the duct model generates the first-level optimization model.

[0053] Step 3.3: Calculate the airflow uniformity evaluation index of the current air duct based on the airflow volume of each air outlet obtained in Step 3.2, and make a judgment: if the requirements are met, proceed to Step 5; if the requirements are not met, proceed to the next step.

[0054] Step 4: Conduct the second stage of optimization (coordinated optimization, i.e., coordinated optimization of the air outlet radius and the airflow guiding structure), which specifically includes:

[0055] Step 4.1: Obtain the design variable set of the flow guide structure, that is, take the parameter set of flow guide structure 2 as input. The parameter set of the flow guide structure contains multiple variables for each flow guide plate. Specifically, the design variable set of the flow guide structure includes the tilt angle of the flow guide plate. Length of the deflector Projected length of the deflector The position of the air deflector from the edge of the air outlet and the distance between the spoiler and the front of the car. See details Figure 3 This section illustrates eight sets of airflow guiding structures, which are, in order, 2(1), 2(2), 2(3), 2(4), 2(5), 2(6), 2(7), and 2(8) corresponding to air outlets 4(1), 4(2), 4(3), 4(4), 4(5), 4(6), 4(7), and 4(8). Here, the design variable set... This is the set of all deflector parameters.

[0056] Get the number of iterations =1;

[0057] Step 4.2: Use a surrogate model to make predictions and obtain the predicted air volume of each air outlet.

[0058] In this embodiment, the following three different proxy models are preferably used to perform parameter optimization:

[0059] a) Regression model:

[0060] This model is used to handle the complex nonlinear response of the flow field within a duct caused by structural changes. Its general form can be expressed as:

[0061] ;

[0062] in: It can be a linear or nonlinear function. These represent different design subspaces. This model can effectively capture the characteristic changes under different flow conditions.

[0063] b) Neural network model:

[0064] Using a feedforward neural network, the mapping relationship can be expressed as:

[0065] ;

[0066] in: and These are the weight matrices and bias vectors for each layer. This is the activation function. Neural networks learn a complex nonlinear mapping from design parameters to performance metrics through training.

[0067] c) Statistical nonparametric model (Gaussian process regression is used in this example):

[0068] The model assumes that the objective function value follows a multivariate Gaussian distribution, and its predicted distribution is:

[0069] ;

[0070] in: and These represent the predicted mean and covariance, respectively. This model not only provides predicted values ​​but also indicates the predicted uncertainty, guiding the balance between exploration and utilization during the optimization process.

[0071] Three surrogate models were simultaneously trained using CFD simulation data to establish a mapping relationship between design parameters and air volume. Subsequently, each surrogate model automatically adjusted its set of design variables based on its inherent mathematical mechanisms and prediction results. The set of parameters for the flow guiding structure in the middle:

[0072] ① The regression model identifies different regions within the design space and optimizes parameters independently within each subspace. Based on the changing trend of the local fitted function, the model determines the direction and magnitude of parameter adjustment; for example, it appropriately increases parameter values ​​in increasing regions and decreases them accordingly in decreasing regions.

[0073] ② The neural network model calculates the gradient direction using the backpropagation algorithm and adjusts the parameters based on the direction of the fastest descent of the loss function. Parameter updates follow the gradient descent rule, that is, adjusting parameter values ​​along the negative gradient direction to make the prediction result continuously approach the optimal solution.

[0074] ③ Statistical nonparametric models utilize their probabilistic prediction characteristics to determine the direction of parameter adjustment by maximizing acquisition functions such as the expected improvement function. This model samples in regions of high uncertainty and in regions of optimal prediction, thereby guiding parameter adjustment.

[0075] Step 4.3: Based on the predicted airflow volume of each outlet obtained in Step 4.2, calculate the airflow uniformity evaluation index of the current air duct and make a judgment: if the requirements are met, obtain the optimal parameter set of the guide structure and proceed to Step 5; if the requirements are not met, then... Return to step 4.2.

[0076] Step 5: Output the air outlet radius obtained in Step 3. Or the air vent radius obtained in the third step. Output and the optimal parameter set of the flow guiding structure obtained in step four.

[0077] In this embodiment, the preferred evaluation index for airflow uniformity is the standard deviation. The expression is as follows:

[0078] ;

[0079] in: For the first Predicted air volume for each air outlet This represents the total number of air outlets. This represents the average of the predicted airflow at the air outlet. Further optimization: Standard deviation. If less than If so, then the requirement is met.

[0080] The application example of this invention is a basic constant cross-section air duct. Its foundation design parameters are: total duct length 10.5m, 22 air outlets (11 groups along the duct direction, 2 outlets per group along the transverse direction), and the outlet positions... The specific values ​​are shown in Table 1 below. The initial radius of all air outlets is 27.75 mm (equal radius). The total length of the fan area accounts for 1 / 5 of the total length of the entire duct. Three sets of air supply outlets are distributed on it (two in each set). The center of all air supply outlet areas is located at 1 / 3 of the total duct length from the front of the vehicle. An initial CFD model of the duct was established and simulated to obtain the initial air volume data of each air outlet and calculate the uniformity evaluation index. The results are shown in Table 1 below.

[0081] Table 1 Initial air duct outlet location and air volume data

[0082]

[0083] Initial air volume standard deviation =7.44 much larger At 0.9 The following predetermined standards show extremely uneven airflow distribution, which does not meet the requirements. Therefore, we proceed to the next step of optimization.

[0084] With the goal of achieving uniform airflow, the radii of each air outlet were adjusted, resulting in three different radius variation conditions (condition 1, condition 2, and condition 3). Three CFD simulation models were then established and simulation calculations were performed accordingly. The three conditions and their corresponding airflow volumes are shown in Table 2 below.

[0085] Table 2. Operating conditions with different radii and corresponding air volume

[0086]

[0087] Through comparative analysis, to determine the optimal radius of each air outlet, quadratic curve fitting was performed on the airflow data of each outlet under three operating conditions to calculate its theoretical optimal radius. Then, through cubic polynomial fitting of the optimal radius and distance, the relationship between radius and distance was finally obtained as follows:

[0088] .

[0089] A first-level optimized CFD model was established based on the radius formula, and simulations were performed. Although the standard deviation of the airflow was significantly improved after optimization compared to the initial state, it still did not meet the target requirements. Therefore, the next optimization step was initiated.

[0090] Flow guiding structures are introduced for collaborative optimization. Several flow guiding structures are pre-set within the main pipeline, and their initial parameter set includes, but is not limited to, inclination angle. ,length Projection length The distance from the edge of the air outlet It is worth noting that the position of each deflector from the front of the vehicle can also be parameterized. For demonstration purposes, this invention only varies the tilt angle. ,length Projection length The distance from the edge of the air outlet ,like Figure 4 As shown, the radii corresponding to air outlets 4(1), 4(2), 4(3), 4(4), 4(5), 4(6), 4(7), 4(8), 4(9), 4(10), and 4(11) are respectively R 1 - R 11 The projected lengths corresponding to the flow guiding structures 2(1), 2(2), 2(3), 2(4), 2(5), 2(6), 2(7), and 2(8) are denoted as follows: - The corresponding distances from the edge of the air outlet are recorded as follows: - And the corresponding tilt angle is - The three different deflector parameter conditions shown in Table 3 were used as training inputs for three types of surrogate models (regression model, neural network model, and statistical nonparametric model).

[0091] Table 3. Operating conditions of three groups of deflector parameters

[0092]

[0093] After multiple rounds of iterative optimization, comparing the prediction results of the three types of surrogate models, the parameter combination output by the statistical nonparametric model showed the best prediction performance. Table 4 shows the final parameter combination.

[0094] Table 4 Optimal Parameter Combination for the Deflector Plate

[0095]

[0096] Based on the optimal baffle arrangement parameters and the optimal radius obtained from the first-stage parameter optimization, a CFD simulation model was established and simulation calculations were performed. The airflow data for each outlet is shown in Table 5.

[0097] Table 5 shows the air volume at each outlet of the optimized model.

[0098]

[0099] Calculate the new uniformity index, substitute the data to get 0.87 Meets standard deviation At 0.9 The following indicators demonstrate the effectiveness and advancement of the technical solution presented in this embodiment.

[0100] Applying the technical solution of this embodiment, the radius of the air outlet 4 is determined by its position. The distribution follows the optimal function, resulting in a gradually expanding pattern along both sides of the wind turbine, demonstrating the effect of the optimal parameter set. Details of the defined flow guide structure 2; parameters of each flow guide (e.g. The orientations are all optimal solutions obtained through global optimization calculations. Therefore, their distribution in the air duct is non-uniform in order to achieve the best airflow guiding effect.

[0101] The above description is merely a preferred embodiment of the present invention and does not limit the patent scope of the present invention. Any equivalent structural transformations made using the contents of the present invention's specification and drawings under the inventive concept of the present invention, or direct / indirect applications in other related technical fields, are included within the patent protection scope of the present invention.

Claims

1. A design method for achieving uniform airflow at the air outlet of a bus duct, characterized in that, Includes the following steps: Step 1: Obtain the basic parameters of the target air duct; establish an initial CFD simulation model, conduct the first simulation, and obtain the airflow data for each air outlet; the basic parameters of the target air duct include the total length of the air duct. Number of air outlets Initial position of the air outlet and the radius of the air outlet ; The second step is to calculate the airflow uniformity evaluation index of the current air duct based on the airflow data of each air outlet obtained in the first step, and make a judgment: if the requirements are met, proceed to the fifth step. If the requirements are not met, proceed to the next step; The third step is to conduct the first phase of optimization, which specifically includes: Step 3.1: Design at least one set of operating conditions based on the air volume data of each air outlet, where the radius varies with distance; extract the radius corresponding to the maximum air volume at each location in the corresponding operating condition; Step 3.2: Fit an air outlet radius based on the radius corresponding to the maximum air volume at each location obtained in Step 3.

1. Distance from air vent to front of the car The functional relationship between them was determined, and a CFD model was established based on this relationship. The air volume of each air outlet was obtained through CFD simulation calculation. The functional relationship is as follows: ； in: For polynomial coefficients, ; For constant terms; Step 3.3: Calculate the airflow uniformity evaluation index of the current air duct based on the airflow volume of each air outlet obtained in Step 3.2, and make a judgment: if the requirements are met, proceed to Step 5; if the requirements are not met, proceed to the next step. Step four: Conduct the second phase of optimization, which specifically includes: Step 4.1: Obtain the design variable set for the airflow guide structure; the design variable set for the airflow guide structure includes the tilt angle of the airflow guide plate. Length of the deflector Projected length of the deflector The position of the air deflector from the edge of the air outlet and the distance between the spoiler and the front of the car. ; Get the number of iterations =1; Step 4.2: Use a surrogate model to make predictions and obtain the predicted air volume for each air outlet; Step 4.3: Based on the predicted airflow volume of each outlet obtained in Step 4.2, calculate the airflow uniformity evaluation index of the current air duct and make a judgment: if the requirements are met, obtain the optimal parameter set of the guide structure and proceed to Step 5; if the requirements are not met, then... Return to step 4.2; Step 5: Output the air outlet radius obtained in Step 3. Alternatively, output the vent radius obtained in step three. And the optimal parameter set of the flow guiding structure obtained in the fourth step.

2. The design method for achieving uniform airflow at the air outlet of a bus duct as described in claim 1, characterized in that, In step 3.2, three sets of operating conditions are designed, with the radius varying linearly, exponentially, and logarithmically with distance. CFD models for the three sets of operating conditions are established and simulations are performed separately. The radius corresponding to the maximum air volume at each location in all operating conditions is extracted. Based on the obtained radius corresponding to the maximum air volume at each location, an air outlet radius is fitted. Distance from air vent to front of the car The functional relationship between them.

3. The design method for achieving uniform airflow at the air outlet of a bus duct as described in claim 1 or 2, characterized in that, In step 4.2, at least two surrogate models are used for prediction. By comparing the air volume uniformity evaluation index corresponding to the predicted air volume output by each surrogate model, the air volume predicted by each air outlet corresponding to the surrogate model with the best performance is selected.

4. The design method for achieving uniform airflow at the air outlet of a bus duct as described in claim 3, characterized in that, The surrogate model includes at least two of the following: regression model, neural network model, and statistical nonparametric model.

5. The design method for achieving uniform airflow at the air outlet of a bus duct as described in claim 4, characterized in that, The standard deviation is used as the evaluation index for air volume uniformity. The expression is as follows: ； in: For the first Predicted air volume for each air outlet This refers to the total number of air outlets; This represents the average value of the predicted air volume at the air outlet.

6. The design method for achieving uniform airflow at the air outlet of a bus duct as described in claim 5, characterized in that, Standard deviation If less than 0.9 If so, then the requirement is met.

Images