Parameter optimization method of vehicle door glass outer contour surface and electronic device

Abstract

The embodiment of the application provides a parameter optimization method for an outer contour surface of a door glass and an electronic device, the method comprising: obtaining initial control point position information, reference point position information and a target gap range, wherein the reference point position information is used to represent a space reference position corresponding to the outer contour surface of the door glass, and the target gap range is used to represent a gap constraint condition corresponding to the reference point position information; constructing an initial outer contour surface corresponding to the door glass based on the initial control point position information; performing evaluation processing on the initial outer contour surface by using the reference point position information and the target gap range to generate a modeling and engineering evaluation score; and performing iterative optimization on the initial control point position information based on the modeling and engineering evaluation score to obtain target control point position information, wherein the target control point position information is used to construct a target outer contour surface corresponding to the door glass. The application solves the technical problems of long development cycle and low optimization precision of related door glass large surface optimization methods.

Description

Technical Field

[0001] This application relates to the field of vehicle technology, and more specifically, to a method for optimizing the parameters of the outer contour surface of a vehicle door glass and an electronic device. Background Technology

[0002] In automotive design, the large glass panels of car doors must coordinate multiple engineering requirements, including aesthetics, ergonomics, motion trajectory, and manufacturing processes. Their curved shape directly impacts sealing performance, visibility, and assembly performance. Related technologies commonly employ parametric modeling methods based on geometric constraints, such as generating the glass panels through rotation, sweeping, or spirals, supplemented by manual adjustment of control parameters based on engineer experience. However, these methods rely on subjective trial and error, making it difficult to uniformly balance multiple constraints such as clearance accuracy, spatial interference, and process feasibility. This results in lengthy design processes, frequent iterations, poor consistency of solutions, long development cycles, and low optimization accuracy.

[0003] There is currently no good solution to the above problems. Summary of the Invention

[0004] This application provides a method and electronic device for optimizing the parameters of the outer contour surface of a car door glass, so as to at least solve the technical problems of long development cycle and low optimization accuracy of related large-area optimization methods for car door glass.

[0005] According to one aspect of the embodiments of this application, a method for parameter optimization of the outer contour surface of a vehicle door glass is provided, comprising: acquiring initial control point position information, reference point position information, and target gap range, wherein the reference point position information is used to represent the spatial reference position corresponding to the outer contour surface of the vehicle door glass, and the target gap range is used to represent the gap constraint condition corresponding to the reference point position information; constructing an initial outer contour surface corresponding to the vehicle door glass based on the initial control point position information; evaluating the initial outer contour surface using the reference point position information and the target gap range to generate a styling and engineering evaluation score; and iteratively optimizing the initial control point position information based on the styling and engineering evaluation score to obtain target control point position information, wherein the target control point position information is used to construct the target outer contour surface corresponding to the vehicle door glass.

[0006] Optionally, constructing the initial outer contour surface corresponding to the door glass based on the initial control point position information includes: obtaining the surface type information corresponding to the door glass; determining the fitting control points based on the surface type information and the initial control point position information; and constructing the initial outer contour surface based on the fitting control points.

[0007] Optionally, the initial outer contour surface is evaluated using reference point location information and target gap range to generate a design and engineering evaluation score, including: determining the gap evaluation score based on reference point location information and target gap range; determining the wind resistance evaluation score based on the estimated wind resistance contribution coefficient and preset wind resistance coefficient target value corresponding to the initial outer contour surface; and performing a weighted calculation based on the gap evaluation score and wind resistance evaluation score to obtain the design and engineering evaluation score.

[0008] Optionally, determining the gap evaluation score based on the reference point position information and the target gap range includes: determining the gap calculation distance based on the reference point position information and the initial outer contour surface, wherein the gap calculation distance is used to represent the spatial position distance between the reference point position information and the initial outer contour surface; and determining the gap evaluation score based on the gap calculation distance and the target gap range.

[0009] Optionally, determining the gap evaluation score based on the gap calculation distance and the target gap range includes: determining a first gap distance based on the upper limit of the gap calculation distance and the target gap range, and determining a second gap distance based on the lower limit of the gap calculation distance and the target gap range; determining a third gap distance based on the first gap distance and the second gap distance; and determining the gap evaluation score based on the third gap distance, a preset scaling factor, a preset attenuation factor, a preset total evaluation score, and the number of reference points.

[0010] Optionally, determining the third gap distance based on the first gap distance and the second gap distance includes: determining the first gap distance as the third gap distance in response to the first gap distance being less than the second gap distance; and determining the second gap distance as the third gap distance in response to the first gap distance being greater than the second gap distance.

[0011] Optionally, the initial control point location information is iteratively optimized based on the shape and engineering evaluation scores to obtain the target control point location information, including: in response to the shape and engineering evaluation scores being greater than a preset score threshold, the initial outer contour surface is determined as the first surface individual; the first surface individual is updated and iterated until a preset convergence condition is met to obtain the target surface individual; and the target control point location information is determined based on the target surface individual.

[0012] Optionally, the parameter optimization method for the outer contour surface of the door glass also includes: in response to the styling and engineering evaluation score being less than a preset score threshold, determining the initial outer contour surface as a second surface individual, and filtering the second surface individual.

[0013] According to another aspect of the embodiments of this application, a parameter optimization device for the outer contour surface of a vehicle door glass is also provided, comprising: an acquisition module, used to acquire initial control point position information, reference point position information, and a target gap range, wherein the reference point position information is used to represent the spatial reference position corresponding to the outer contour surface of the vehicle door glass, and the target gap range is used to represent the gap constraint condition corresponding to the reference point position information; a construction module, used to construct an initial outer contour surface corresponding to the vehicle door glass based on the initial control point position information; a processing module, used to evaluate the initial outer contour surface using the reference point position information and the target gap range to generate a styling and engineering evaluation score; and an optimization module, used to iteratively optimize the initial control point position information based on the styling and engineering evaluation score to obtain target control point position information, wherein the target control point position information is used to construct the target outer contour surface corresponding to the vehicle door glass.

[0014] Optionally, the construction module is also used to: obtain the surface type information corresponding to the door glass; determine the fitting control points based on the surface type information and the initial control point position information; and construct the initial outer contour surface based on the fitting control points.

[0015] Optionally, the processing module is also used to: determine the gap evaluation score based on the reference point location information and the target gap range; determine the wind resistance evaluation score based on the estimated wind resistance contribution coefficient and the preset wind resistance coefficient target value corresponding to the initial outer contour surface; and perform a weighted calculation based on the gap evaluation score and the wind resistance evaluation score to obtain the shape and engineering evaluation score.

[0016] Optionally, the processing module is further configured to: determine the gap calculation distance based on the reference point position information and the initial outer contour surface, wherein the gap calculation distance is used to represent the spatial position distance between the reference point position information and the initial outer contour surface; and determine the gap evaluation score based on the gap calculation distance and the target gap range.

[0017] Optionally, the processing module is further configured to: determine a first gap distance based on the gap calculation distance and the upper limit of the target gap range, and determine a second gap distance based on the gap calculation distance and the lower limit of the target gap range; determine a third gap distance based on the first gap distance and the second gap distance; and determine a gap evaluation score based on the third gap distance, a preset scaling factor, a preset attenuation factor, a preset total evaluation score, and the number of reference points.

[0018] Optionally, the processing module is further configured to: determine the first gap distance as the third gap distance in response to the first gap distance being less than the second gap distance; and determine the second gap distance as the third gap distance in response to the first gap distance being greater than the second gap distance.

[0019] Optionally, the optimization module is also used to: in response to the shape and engineering evaluation score being greater than a preset score threshold, determine the initial outer contour surface as the first surface individual; update and iterate based on the first surface individual until the preset convergence condition is met to obtain the target surface individual; and determine the target control point position information based on the target surface individual.

[0020] Optionally, the optimization module is also used to: determine the initial outer contour surface as the second surface individual in response to the shape and engineering evaluation score being less than a preset score threshold, and to perform filtering processing on the second surface individual.

[0021] According to another aspect of the embodiments of this application, an electronic device is also provided, including: a memory storing an executable program; and a processor for running the program, wherein the program executes the methods in various embodiments of this application when it runs.

[0022] According to another aspect of the embodiments of this application, a computer-readable storage medium is also provided, the computer-readable storage medium including a stored executable program, wherein, when the executable program is running, it controls the device where the computer-readable storage medium is located to perform the methods of various embodiments of this application.

[0023] According to another aspect of the embodiments of this application, a computer program product is also provided, including a computer program that, when executed by a processor, implements the methods of various embodiments of this application.

[0024] According to another aspect of the embodiments of this application, a computer program is also provided, which, when executed by a processor, implements the methods of the various embodiments of this application.

[0025] In this embodiment, a parametric surface modeling approach combined with an iterative optimization algorithm based on styling and engineering evaluation scores is employed. First, initial control point location information, reference point location information, and target gap range are obtained. The reference point location information represents the spatial reference position corresponding to the outer contour surface of the door glass, and the target gap range represents the gap constraint condition corresponding to the reference point location information. Then, an initial outer contour surface corresponding to the door glass is constructed based on the initial control point location information. Next, the initial outer contour surface is evaluated using the reference point location information and the target gap range to generate styling and engineering evaluation scores. Finally, the initial control point location information is iteratively optimized based on the styling and engineering evaluation scores to obtain target control point location information. This target control point location information is used to construct the target outer contour surface corresponding to the door glass, achieving the goal of automatically searching for the optimal large-area glass styling. This results in shortening the development cycle and improving optimization accuracy, thereby solving the technical problems of long development cycles and low optimization accuracy in related large-area optimization methods for door glass. Attached Figure Description

[0026] The accompanying drawings, which are included to provide a further understanding of this application and form part of this application, illustrate exemplary embodiments and are used to explain this application, but do not constitute an undue limitation of this application. In the drawings:

[0027] Figure 1 This is a flowchart of an optional parameter optimization method for the outer contour surface of a car door glass according to an embodiment of this application;

[0028] Figure 2 This is a schematic diagram of an optional olive-shaped pasta according to an embodiment of this application;

[0029] Figure 3 This is a schematic diagram of an optional annular surface according to an embodiment of this application;

[0030] Figure 4 This is a schematic diagram of an optional cylindrical surface according to an embodiment of this application;

[0031] Figure 5 This is a schematic diagram of an optional swarm intelligence optimization algorithm according to an embodiment of this application;

[0032] Figure 6 This is a schematic diagram of an optional parameter optimization method for the outer contour surface of a car door glass according to an embodiment of this application;

[0033] Figure 7 This is a schematic diagram of another optional parameter optimization method for the outer contour surface of a car door glass according to an embodiment of this application;

[0034] Figure 8 This is a structural block diagram of an optional parameter optimization device for the outer contour surface of a car door glass according to an embodiment of this application. Detailed Implementation

[0035] To enable those skilled in the art to better understand the present application, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present application, and not all embodiments. Based on the embodiments in the present application, all other embodiments obtained by those of ordinary skill in the art without creative effort should fall within the scope of protection of the present application.

[0036] It should be noted that the terms "first," "second," etc., in the specification, claims, and accompanying drawings of this application are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of this application described herein can be implemented in orders other than those illustrated or described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.

[0037] According to an embodiment of this application, a method embodiment for optimizing the parameters of the outer contour surface of a car door glass is provided. It should be noted that the steps shown in the flowchart in the accompanying drawings can be executed in a computer system such as a set of computer-executable instructions. Furthermore, although a logical order is shown in the flowchart, in some cases, the steps shown or described may be executed in a different order than that shown here.

[0038] This embodiment provides a method for optimizing the parameters of the outer contour surface of a car door glass. Figure 1 This is a flowchart of an optional parameter optimization method for the outer contour surface of a car door glass according to an embodiment of this application, such as... Figure 1 As shown, the process includes the following steps:

[0039] Step S11: Obtain initial control point position information, reference point position information, and target gap range. The reference point position information is used to represent the spatial reference position corresponding to the outer contour surface of the door glass, and the target gap range is used to represent the gap constraint conditions corresponding to the reference point position information.

[0040] Step S12: Construct the initial outer contour surface corresponding to the door glass based on the initial control point position information;

[0041] Step S13: Use the reference point position information and target gap range to evaluate the initial outer contour surface and generate a modeling and engineering evaluation score.

[0042] Step S14: Iteratively optimize the initial control point position information based on the styling and engineering evaluation scores to obtain the target control point position information, wherein the target control point position information is used to construct the target outer contour surface corresponding to the door glass.

[0043] The aforementioned initial control point location information represents the initial set of coordinates in a three-dimensional coordinate system for the control points of the non-uniform rational B-splines (NURBS) surface used to define the outer contour surface of the door glass. The initial control points are the underlying parameter variables that define the large-area geometry of the door glass, determining the surface's geometric shape.

[0044] The aforementioned reference point location information indicates the coordinates of key spatial feature points that the outer contour surface of the door glass needs to meet engineering constraints in the vehicle assembly environment, such as water tangent boundary points, head space envelope points, shoulder, elbow, and hip human-machine envelope points, door lock mounting surface contour points, or anti-collision beam interference boundary points, etc., which are used to characterize the relative spatial reference position of the door glass and surrounding components.

[0045] The aforementioned target gap range represents the interval consisting of the upper and lower limits of the allowable gap set for each reference point position information. It is used to quantitatively express the minimum and maximum distance constraints that must be met between the outer contour surface of the door glass and the reference object at each reference point.

[0046] The aforementioned initial outer contour surface represents the initial three-dimensional geometric surface model of the large surface of the car door glass, generated using a parametric modeling method based on the initial control point position information. In this embodiment, the initial outer contour surface can be a NURBS surface, whose shape is constructed by fitting the control point coordinates of basic surface types such as olive-shaped, toroidal, cylindrical, or spiral surfaces to the contour lines and trajectory lines, followed by rotation or sweeping operations. In this embodiment, the initial outer contour surface has not yet undergone gap constraint evaluation and optimization; it serves as the initial solution in the optimization process, representing the glass surface shape set in the early design phase based on engineering experience or conventional styling.

[0047] The above-mentioned design and engineering evaluation score represents a weighted total score that combines the gap evaluation score and the wind resistance evaluation score. It is used to quantify the overall quality of the initial outer contour surface under multi-dimensional engineering constraints such as manufacturing and assembly precision, ergonomic comfort, and aerodynamic efficiency.

[0048] The above iterative optimization refers to the process of using swarm intelligence optimization algorithms, with shape and engineering evaluation scores as fitness indicators, to repeatedly adjust, select, cross, and mutate the initial control point location information in order to search for a better solution.

[0049] The aforementioned target control point location information represents the set of control point coordinates obtained after iterative optimization that maximizes the styling and engineering evaluation scores. This set is used to ultimately construct the target outer contour surface of the door glass that satisfies all clearance constraints.

[0050] The aforementioned target outer contour surface represents the final design scheme of the large door glass surface, constructed from the target control point location information, which satisfies all engineering constraints and has the best performance.

[0051] During the initialization phase, the system first acquires the initial control point location information, reference point location information, and target gap range. Specifically, the system reads or generates the initial control point coordinate data used to construct the large surface of the door glass, and simultaneously receives the pre-set spatial coordinates of the reference points and their corresponding minimum and maximum gap constraint values, providing basic data input for subsequent surface construction and evaluation.

[0052] Then, based on the initial control point position information, an initial outer contour surface corresponding to the door glass is constructed. In this embodiment, based on the initial control point position information and according to the type of door glass, such as an olive-shaped, annular, cylindrical, or spiral surface, corresponding parametric modeling strategies, such as NURBS curve fitting and rotation or sweep operations, are adopted to generate an initial three-dimensional surface model of the door glass.

[0053] The initial outer contour surface is then evaluated using reference point location information and the target gap range. In this embodiment, the actual distance between the initial outer contour surface and each reference point is first calculated, and a gap evaluation score is calculated based on the target gap range. Simultaneously, the estimated wind resistance contribution coefficient is estimated based on the geometric characteristics of the initial outer contour surface, and compared with a preset wind resistance coefficient target value to calculate a wind resistance evaluation score. Finally, the gap evaluation score and the wind resistance evaluation score are weighted to obtain a comprehensive shape and engineering evaluation score, quantifying the overall engineering performance of the surface.

[0054] Finally, the initial control point location information is iteratively optimized based on the design and engineering evaluation scores to obtain the target control point location information. In this embodiment, the design and engineering evaluation scores are used as a fitness function to initiate a swarm intelligence optimization algorithm. This algorithm performs multiple rounds of iterative search on the initial control point location information, eliminating low-scoring individuals and retaining and evolving high-scoring individuals, continuously adjusting the control point coordinates until the convergence condition is met. Ultimately, the target control point location information that maximizes the design and engineering evaluation scores is output.

[0055] Based on the above steps S11 to S14, this embodiment of the application adopts a parametric surface modeling and iterative optimization algorithm that combines styling and engineering evaluation scores. First, it obtains initial control point position information, reference point position information, and target gap range. The reference point position information represents the spatial reference position corresponding to the outer contour surface of the door glass, and the target gap range represents the gap constraint condition corresponding to the reference point position information. Then, based on the initial control point position information, it constructs the initial outer contour surface corresponding to the door glass. Next, it evaluates the initial outer contour surface using the reference point position information and the target gap range to generate styling and engineering evaluation scores. Finally, iteratively optimizes the initial control point position information based on the styling and engineering evaluation scores to obtain the target control point position information. The target control point position information is used to construct the target outer contour surface corresponding to the door glass, achieving the goal of automatically searching for the optimal large-area glass styling. This results in shortening the development cycle and improving optimization accuracy, thus solving the technical problems of long development cycles and low optimization accuracy in related large-area optimization methods for door glass.

[0056] Optionally, constructing the initial outer contour surface corresponding to the door glass based on the initial control point position information includes: obtaining the surface type information corresponding to the door glass; determining the fitting control points based on the surface type information and the initial control point position information; and constructing the initial outer contour surface based on the fitting control points.

[0057] The above surface type information indicates the geometric category of the outer contour surface of the door glass, including four basic types: olive surface, toroidal surface, cylindrical surface, or spiral surface. This information is used to determine the parametric modeling strategy and geometric construction rules used for surface generation.

[0058] The aforementioned fitting control points represent a subset of control points selected from the initial control point position information based on the surface type information, used to define contour lines, trajectory lines, or rotation axes. Fitting control points are direct input nodes for NURBS curve fitting. Different surface types correspond to different fitting control point allocation rules. Specifically: in an olive-shaped surface, some control points are used to fit the contour line arc, and the rest are used to define the rotation axis; in a toroidal surface, some control points are used to fit the contour line, and the rest are used to fit the trajectory line; in a cylindrical surface, some control points are used to fit the contour line, and two control points are used to fit a straight trajectory line; in a spiral surface, two sets of olive-shaped surfaces are fitted independently, and the surface difference at the B-pillar junction must be minimized. The B-pillar is a vertical pillar structure in the automotive body structure, located between the front and rear doors, connecting the roof and the chassis frame. In the side view of the vehicle, it is located between the front and rear door frames and is one of the main supporting components of the vehicle side.

[0059] In this embodiment of the application, when constructing the initial outer contour surface corresponding to the door glass, the surface type information corresponding to the door glass is first obtained, that is, the geometric category to which the surface belongs is determined, such as an olive-shaped surface, a toroidal surface, a cylindrical surface, or a spiral surface. This acquisition step can guide subsequent parametric modeling to ensure the selection of matching geometric construction rules and control point allocation strategies.

[0060] Then, fitting control points are determined based on surface type information and initial control point location information. For example, embodiments of this application can select a subset of control points from the initial control point location information to construct contour lines, trajectory lines, or rotation axes, based on the determined surface type. For instance, in an olive-shaped surface, three control points are used to fit the contour line arc, and two control points are used to define the rotation axis. In a toroidal surface, some control points are used to fit the contour line, and the rest are used to fit the trajectory line. In a cylindrical surface, some control points are used to fit the contour line, and two control points are used to fit a linear trajectory line. In a helical surface, two independent olive-shaped surfaces correspond to their respective contour lines and rotation axes. The above steps for determining fitting control points simplify the complex parameter system of high-dimensional NURBS surfaces into a low-dimensional set of control points for three basic geometric elements through the classification and reuse of control points, achieving compression of modeling dimensions and clarification of engineering semantics.

[0061] Specifically, the profile line represents a planar curve that defines the cross-sectional shape of the outer profile surface of the door glass in a direction perpendicular to the motion or sweeping direction. It is generated by NURBS curve fitting and determined by a set of fitting control points to control the width, curvature, and local morphology of the surface. For example, in an olive-shaped surface, the profile line is an arc segment rotating about the axis of rotation; in a toroidal surface, the profile line is a cross-sectional curve swept along the trajectory line; and in a cylindrical surface, the profile line is an arc or straight line segment perpendicular to the straight trajectory line.

[0062] The trajectory line represents a spatial curve defining the path of the outer contour surface of the car door glass during sweeping or movement. It is generated through NURBS curve fitting and determined by a set of fitting control points to control the extension direction and spatial distribution of the surface. For example, in a toroidal surface, the trajectory line is a closed or open curve surrounding the car door; in a cylindrical surface, the trajectory line is a straight line; and in a helical surface, the trajectory line represents a helical path along the B-pillar direction.

[0063] The axis of rotation represents the axis of symmetry that defines the outer contour surface of the car door glass when generated through a rotation operation. It is a straight line in space, uniquely determined by two control points, and used to constrain the rotation direction and center position of the surface. The axis of rotation is only used on the olive-shaped surface, determining the tilt angle and spatial orientation of the olive-shaped surface, ensuring that the surface meets the spatial alignment requirements of styling and ergonomics during rotation.

[0064] In this embodiment, after obtaining the fitting control points, an initial outer contour surface is constructed based on these control points. Specifically, based on the determined fitting control points, the NURBS curve fitting method is used to generate the contour line, trajectory line, and rotation axis, and operations are performed according to the geometric operation rules specified by the surface type: for an olive-shaped surface, the contour line is rotated around the rotation axis to generate a surface of revolution; for a toroidal surface, the contour line is swept along the trajectory line to generate a surface; for a cylindrical surface, the contour line is swept along the straight trajectory line to generate a cylindrical surface; for a helical surface, two independent olive-shaped surfaces are joined at the intersection of the B-pillar while ensuring minimal surface difference. The above steps transform the discrete control point coordinates into a continuous, smooth, and computable three-dimensional NURBS outer contour surface, providing a stable and differentiable geometric basis for subsequent gap calculation and optimization.

[0065] Based on the above optional embodiments, the embodiments of this application realize the structured, parameterized, and low-dimensional generation of the initial outer contour surface of the car door glass. The complex process of directly optimizing the parameters of high-order NURBS surfaces is transformed into the fitting and combination operation of control points of three basic geometric elements: contour lines, trajectory lines, and rotation axes. This significantly reduces the scale of optimization variables, enhances the engineering interpretability and computational stability of the model, and makes the surface generation process not only in line with the manufacturing preference for regular geometric shapes in automotive engineering, but also provide an efficient and convergent search space for subsequent intelligent optimization algorithms.

[0066] For example, determining the fitting control points based on surface type information and initial control point position information includes: in response to the surface type information being an olive surface, determining the contour line fitting control points and rotation axis fitting control points corresponding to the olive surface based on the initial control point position information; in response to the surface type information being a toroidal surface, determining the contour line fitting control points and trajectory line fitting control points corresponding to the toroidal surface based on the initial control point position information; in response to the surface type information being a cylindrical surface, determining the contour line fitting control points and trajectory line fitting control points corresponding to the cylindrical surface based on the initial control point position information; and in response to the surface type information being a helical surface, determining the contour line fitting control points and rotation axis fitting control points corresponding to the helical surface based on the initial control point position information.

[0067] The aforementioned olive-shaped surface is a geometric type of the outer contour surface of a car door glass. It is generated by rotating a closed NURBS contour line around a straight line in space, forming a surface of revolution that is wide in the middle and narrows at both ends, resembling a rugby ball. It is commonly used in car door glass design for the upper curved surface of independent front or rear door glass. The rotation axis of the olive-shaped surface is uniquely determined by two control points, and the contour line is fitted by three control points, ensuring symmetry and a smooth curvature transition during rotation; that is, five control points can determine one olive-shaped surface. In a spatial coordinate system, a point is determined by the coordinates in the X, Y, and Z axes. When the contour line is a regular arc segment, only 15 parameters are needed to control the shape of the olive-shaped surface. An olive-shaped surface created using the above method is shown below. Figure 2 As shown, Figure 2 This is a schematic diagram of an optional olive pastry according to an embodiment of this application.

[0068] The aforementioned annular surface is a geometric type of the outer contour surface of a car door glass. It is generated by sweeping a NURBS contour line along a spatial curve, i.e., a trajectory line, to form a closed or open loop surface surrounding the car door structure. The contour line and the trajectory line of the annular surface are perpendicular to each other or at a fixed angle, and it is often used for the lower part of the car door glass or the transition area with the B-pillar. The contour line of the annular surface controls the cross-sectional shape, and the trajectory line controls the spatial envelope path of the surface, enabling continuous transitions under complex curves. Following the fitting method of an olive-shaped surface, the annular surface only requires 6 control points and 18 parameters to control its shape. The annular surface established according to the above method is shown below. Figure 3 As shown, Figure 3 This is a schematic diagram of an optional annular surface according to an embodiment of this application.

[0069] The cylindrical surface described above is a geometric type of the outer contour surface of a car door glass. It is generated by sweeping a NURBS contour line along a straight trajectory line, forming a cylindrical surface with a consistent cross-sectional shape and a straight extension direction. The trajectory line of the cylindrical surface is a straight line, and the contour line is perpendicular to this straight line. It is often used for the lower straight section of the glass or the curved surface in the area parallel to the door frame. The cylindrical surface requires only 5 control points and 15 parameters to control its shape. The cylindrical surface created according to the above method is shown below. Figure 4 As shown, Figure 4 This is a schematic diagram of an optional cylindrical surface according to an embodiment of this application.

[0070] The aforementioned spiral surface is a composite geometric type of the outer contour surface of the car door glass. It is formed by splicing two independent olive-shaped surfaces of the front and rear doors at the junction of the B-pillars. Each olive-shaped surface has an independent contour line and axis of rotation, and the surface difference at the junction needs to be minimized to ensure the continuity of the surface. The overall shape of the spiral surface presents a spiral feature that extends and rotates along the height of the car door, used to achieve a continuous glass surface transition from the A-pillar to the B-pillar and then to the C-pillar. It is a key geometric form in the design of double-curvature glass to meet the needs of coordinating complex shapes and motion trajectories. Among them, the A-pillar is located on both sides of the windshield, connecting the front of the roof and the front of the car. The C-pillar is located behind the rear door, connecting the rear of the roof and the rear of the car. Because the spiral surface is composed of two olive-shaped surfaces, its shape is controlled by 10 control points and 30 parameters.

[0071] The aforementioned contour fitting control points represent the set of control points used to fit the cross-sectional shape of the outer contour surface of the door glass, defining the cross-sectional profile of the surface perpendicular to the sweeping or rotation direction.

[0072] The aforementioned rotation axis fitting control points represent two control points used to define the rotational symmetry axis of the outer contour surface of the door glass, which determine the rotation center and spatial orientation of the surface.

[0073] The aforementioned trajectory fitting control points represent the set of control points used to fit the sweeping path of the outer contour surface of the car door glass, determining the extension direction and distribution of the surface in space.

[0074] When determining the fitting control points based on surface type information and initial control point position information, in response to the surface type information being an olive surface, the contour fitting control points and rotation axis fitting control points corresponding to the olive surface are determined based on the initial control point position information. This indicates that when the surface type is an olive surface, this embodiment selects control points from the initial control points for fitting the contour line of the rotating section, and two points for defining the rotational symmetry axis, to construct the surface of revolution.

[0075] In response to the surface type information being a toroidal surface, contour line fitting control points and trajectory line fitting control points corresponding to the toroidal surface are determined based on the initial control point position information. This indicates that when the surface type is a toroidal surface, this embodiment of the application separates contour line control points for defining the cross-sectional shape and trajectory line control points for defining the toroidal path from the initial control points to achieve the generation of a swept toroidal surface.

[0076] In response to the surface type information being cylindrical, the contour fitting control points and trajectory fitting control points corresponding to the cylindrical surface are determined based on the initial control point position information. This indicates that when the surface type is cylindrical, this embodiment selects control points from the initial control points to define the cross-sectional contour perpendicular to the straight path, and two control points to define the straight path trajectory, to generate a cylindrical surface.

[0077] In response to the surface type information being a helical surface, the contour fitting control points and rotation axis fitting control points corresponding to the helical surface are determined based on the initial control point position information. This indicates that when the surface type is a helical surface, this embodiment extracts two sets of contour control points and rotation axis control points required for the olive-shaped surface from the initial control points, ensuring minimal surface difference at the B-pillar intersection, thus achieving splicing and continuity control of the double-sided olive-shaped surface.

[0078] Based on the above optional embodiments, this application embodiment implements differentiated classification and allocation of fitting control points according to different surface types, accurately mapping the initial control point position information to a subset of three types of geometric elements: contour lines, trajectory lines, or rotation axes. This achieves structured modeling support for four basic surface types: olive surface, toroidal surface, cylindrical surface, and spiral surface. It avoids redundant calculations and semantic ambiguity caused by blindly optimizing high-dimensional NURBS surface parameters in traditional methods, significantly improving the rationality of control point allocation, modeling efficiency, and traceability of geometric expression.

[0079] Optionally, the initial outer contour surface is evaluated using reference point location information and target gap range to generate a design and engineering evaluation score, including: determining the gap evaluation score based on reference point location information and target gap range; determining the wind resistance evaluation score based on the estimated wind resistance contribution coefficient and preset wind resistance coefficient target value corresponding to the initial outer contour surface; and performing a weighted calculation based on the gap evaluation score and wind resistance evaluation score to obtain the design and engineering evaluation score.

[0080] The aforementioned gap evaluation score represents a numerical score obtained by calculating the deviation of the actual distance between the initial outer contour surface and each reference point relative to the target gap range, and quantifying the compliance of the surface in terms of manufacturing gap, ergonomics, and layout feasibility using an exponential decay function. express.

[0081] The aforementioned estimated drag contribution coefficient represents a quantitative indicator, calculated using a simplified estimation model based on the geometric characteristics of the initial outer contour surface, characterizing the contribution of this surface shape to the overall vehicle's aerodynamic drag. The simplified estimation model is as follows:

[0082]

[0083] in, To estimate the drag contribution coefficient, As a baseline wind resistance level, For the width of the side window, The angle between the side window and the vertical plane. The total length of the vehicle body is... The sum of the measurements of discontinuities in the form. and These are empirical coefficients calibrated based on Computational Fluid Dynamics (CFD) results or wind tunnel measurement data.

[0084] The aforementioned preset drag coefficient target value represents the ideal drag coefficient value set according to the vehicle model level, serving as a benchmark for evaluating aerodynamic performance. express.

[0085] The aforementioned drag rating score represents a numerical score used to quantify the aerodynamic performance of curved surfaces, calculated by substituting the deviation between the estimated drag contribution coefficient and the preset target drag coefficient value into the drag scoring formula. The drag scoring formula is as follows:

[0086]

[0087] in, The wind resistance score is used to evaluate the wind resistance. To estimate the wind resistance contribution factor, software such as Fluent (a computational fluid dynamics software) can be used for calculation. The target value for the wind resistance coefficient is preset, and k is the sensitivity coefficient. The larger the value of k, the more severe the penalty for wind resistance deviation.

[0088] The specific formulas for the above-mentioned design and engineering evaluation scores are as follows:

[0089]

[0090] in, The evaluation score is based on the design and engineering. A higher value indicates better performance. and These are the weighting coefficients for the gap score and the wind resistance score, respectively, and their sum is 1.

[0091] For example, when evaluating the initial outer contour surface using reference point location information and target gap range to generate a styling and engineering evaluation score, the system first determines the gap evaluation score based on the reference point location information and target gap range. Specifically, the system obtains the actual physical distance between the large surface of the door glass and each reference point, combines it with the preset minimum and maximum gaps allowed for each reference point, and substitutes them into the gap scoring formula to calculate and generate the gap evaluation score for the surface, thereby quantifying the compliance of the current surface in terms of manufacturing gaps, ergonomics, and layout feasibility.

[0092] Secondly, the drag evaluation score is determined based on the estimated drag contribution coefficient and the preset drag coefficient target value corresponding to the initial outer contour surface. The system calculates the estimated drag contribution coefficient of the surface using a simplified estimation model based on the geometric characteristics of the initial outer contour surface. Subsequently, the calculated estimated drag contribution coefficient is compared with the ideal drag coefficient target value set according to the vehicle model level, and substituted into the drag scoring formula for calculation, thereby quantifying the aerodynamic performance of the current surface and generating a drag evaluation score.

[0093] Then, a weighted calculation is performed based on the gap evaluation score and the wind resistance evaluation score to obtain the styling and engineering evaluation score. The system obtains the preset gap scoring weight and wind resistance scoring weight, multiplies the calculated gap evaluation score by the gap scoring weight, multiplies the wind resistance evaluation score by the wind resistance scoring weight, and adds the two together to obtain the final comprehensive score. This comprehensive score is the styling and engineering evaluation score, which is used to comprehensively characterize the overall quality of the initial outer contour surface under multi-dimensional engineering constraints such as manufacturing and assembly accuracy, ergonomic comfort, and aerodynamic efficiency.

[0094] Based on the above optional embodiments, this application embodiment constructs a multi-objective weighted evaluation system covering geometric clearance compliance and aerodynamic performance. It can automatically and quantitatively evaluate the impact of the large-area shape of the door glass on the overall vehicle drag while meeting engineering constraints. This enables the optimization algorithm to simultaneously consider manufacturing assembly, ergonomics, and aerodynamic efficiency during the search process, thereby significantly improving the comprehensive engineering value of the design scheme and the overall vehicle performance.

[0095] Optionally, determining the gap evaluation score based on the reference point location information and the target gap range includes: determining the gap calculation distance based on the reference point location information and the initial outer contour surface, wherein the gap calculation distance is used to represent the spatial distance between the reference point location information and the initial outer contour surface; and determining the gap evaluation score based on the gap calculation distance and the target gap range.

[0096] The aforementioned gap calculation distance represents the shortest spatial Euclidean distance between the reference point location information and the initial outer contour surface, determined by geometric calculation methods. It is used to quantify the physical proximity of the surface at the reference point to the engineering constraint target.

[0097] When determining the gap evaluation score based on the reference point location information and the target gap range, the embodiments of this application first determine the gap calculation distance based on the reference point location information and the initial outer contour surface. Specifically, through geometric calculation methods, the shortest vertical distance from the three-dimensional coordinate point corresponding to each reference point location information to the initial outer contour surface is calculated, and this distance is the gap calculation distance.

[0098] Then, the gap evaluation score is determined based on the calculated gap distance and the target gap range. For each reference point, the corresponding calculated gap distance is compared with its pre-set target gap range, which is the interval between the minimum and maximum allowable gap. When the calculated gap distance is within this range, the evaluation score is higher; when it exceeds this range, a penalty score is applied according to the degree of deviation using an exponential decay formula. The scores of all reference points are then weighted and averaged to obtain a comprehensive value reflecting the overall compliance of the design, i.e., the gap evaluation score.

[0099] Based on the above optional embodiments, the embodiments of this application realize the accurate quantitative evaluation of the large surface of the car door glass under static geometric constraints. It can automatically calculate and evaluate the gap deviation between the curved surface and key spatial points. By introducing a deviation penalty mechanism, it ensures that the optimization process prioritizes meeting hard constraints such as manufacturing gaps, ergonomics, and layout feasibility. It provides accurate and sensitive fitness feedback for multi-objective optimization algorithms, thereby guiding the curved surface shape to converge in the direction of meeting multiple engineering standards and improving the comprehensive value of the final car door glass outer contour curved surface design scheme.

[0100] Optionally, determining the gap evaluation score based on the gap calculation distance and the target gap range includes: determining a first gap distance based on the upper limit of the gap calculation distance and the target gap range, and determining a second gap distance based on the lower limit of the gap calculation distance and the target gap range; determining a third gap distance based on the first gap distance and the second gap distance; and determining the gap evaluation score based on the third gap distance, a preset scaling factor, a preset attenuation factor, a preset total evaluation score, and the number of reference points.

[0101] The upper limit of the target clearance range mentioned above represents the maximum allowable clearance value set for each reference point, denoted as . This represents the maximum safe distance that can exist between the outer contour surface of the door glass and the reference point.

[0102] The lower limit of the above target clearance range represents the minimum allowable clearance value set for each reference point, denoted as . This represents the minimum safe distance that must be met between the outer contour surface of the car door glass and the reference point to avoid interference.

[0103] The aforementioned first gap distance represents the difference between the calculated gap distance and the upper limit of the target gap range when the calculated gap distance is greater than the upper limit of the target gap range. It is used to measure the degree of deviation of a curved surface in the direction of excessive gap.

[0104] The aforementioned second gap distance represents the difference between the calculated gap distance and the lower limit of the target gap range when the calculated gap distance is less than the lower limit. It is used to measure the degree of deviation of a curved surface in the direction where the gap is too small.

[0105] The aforementioned third gap distance represents the smaller of the first gap distance and the second gap distance, i.e. It is used to characterize the nearest boundary deviation of the surface at the reference point from the target gap range, and only the most severe one-sided deviation is retained.

[0106] The aforementioned preset scaling factor represents a positive real-number parameter that controls the rate of score decay. It is used to adjust the sensitivity of the deviation to the influence of the score, and can be set to 0.5-1.0.

[0107] The aforementioned preset attenuation factor represents a positive real parameter that controls the nonlinear attenuation pattern of the deviation. This is used to adjust the curvature of the scoring curve, making small deviations have a gentler impact and large deviations have a steeper penalty. It can be set to 2.0.

[0108] The above-mentioned preset total score represents the highest possible score value S set for all reference points. As the benchmark weight of the scoring system, it can be set to 100 points.

[0109] The above number of reference points represents the total number of reference point location information items used in the evaluation. This is used to normalize the average of the scores for each point.

[0110] In this embodiment of the application, when determining the gap evaluation score based on the gap calculation distance and the target gap range, a first gap distance is first determined based on the upper limit of the gap calculation distance and the target gap range. That is, when the gap calculation distance is greater than the upper limit of the target gap range, the difference between the gap calculation distance and the upper limit is calculated, i.e., the first gap distance is... It is used to quantify the deviation of the outer contour surface of the door glass from the maximum allowable gap at the reference point, reflecting the "excessive gap" problem in the risk of interference between the surface and surrounding components.

[0111] Furthermore, a second gap distance is determined based on the calculated gap distance and the lower limit of the target gap range. When the calculated gap distance is less than the lower limit of the target gap range, the difference between the calculated gap distance and the lower limit is calculated, i.e., the second gap distance is... It is used to quantify the deviation of the outer contour surface of the door glass from the minimum allowable gap at the reference point, reflecting the "too small gap" problem in the risk of interference between the surface and surrounding components.

[0112] Then, based on the first and second gap distances, the third gap distance is determined, and the smaller value between the first and second gap distances is selected as the third gap distance. The aim is to retain the deviation on the side closest to the target gap range boundary at the reference point, eliminate interference from non-dominant directions, and ensure that the evaluation focuses on the nearest boundary conflict between the surface and the target area.

[0113] Finally, the gap evaluation score is determined based on the third gap distance, preset scaling factor, preset attenuation factor, preset total evaluation score, and number of reference points. Therefore, the formula for calculating the gap evaluation score is:

[0114]

[0115] in, For interval evaluation scores, Calculate the distance for the gap at the i-th reference point. and The upper and lower limits of the target gap range. S is the preset total evaluation score. For the preset scaling factor, As a preset attenuation factor, This represents the number of reference points. This is an optional, standardized denominator for the gap, used when the required range of reference points varies significantly. It can be set to... This makes the sensitivity of each component to gap deviation more fair and consistent. When the calculated gap distance is within the target gap range, the score approaches the maximum value S; if it exceeds the range, the score decreases exponentially with the degree of deviation.

[0116] Based on the above optional embodiments, this application embodiment constructs a gap evaluation score generation method driven by the most stringent one-sided deviation and with exponential decay as the mechanism. It unifies the two types of deviations, "gap too large" and "gap too small", into a symmetrical one-way deviation metric. It eliminates multi-objective conflict interference through the third gap distance and achieves precise control of the penalty intensity by combining preset scaling factors and preset decay factors. This enables the scoring system to have high inclusiveness for compliant areas and strong penalty for out-of-bounds areas, significantly improving the accuracy, stability and optimization guidance of the evaluation results.

[0117] Optionally, determining the third gap distance based on the first gap distance and the second gap distance includes: determining the first gap distance as the third gap distance in response to the first gap distance being less than the second gap distance; and determining the second gap distance as the third gap distance in response to the first gap distance being greater than the second gap distance.

[0118] In this embodiment, when determining the third gap distance, the first gap distance is determined as the third gap distance in response to the first gap distance being less than the second gap distance. This indicates that when the deviation of the curved surface in the "excessive gap" direction is less than the deviation in the "insufficient gap" direction, the system determines that the main design risk originates from the "excessive gap" state. Therefore, the first gap distance is selected as the primary evaluation criterion to ensure that the scoring system remains sensitive to sealing and appearance issues.

[0119] In response to the first gap distance being greater than the second gap distance, the second gap distance is determined as the third gap distance. This indicates that when the deviation of the surface in the "gap too small" direction is greater than the deviation in the "gap too large" direction, the system determines that the main design risk originates from the "gap too small" state. Therefore, the second gap distance is selected as the primary evaluation criterion to ensure that the scoring system remains sensitive to motion interference and assembly reliability issues.

[0120] Based on the above optional embodiments, this application embodiment constructs a third gap distance selection mechanism based on the priority of dominant deviation, which avoids the risk masking problem caused by the mutual cancellation of positive and negative deviations in traditional multi-objective evaluation, realizes independent identification and priority response to the two types of risks of "too tight" and "too loose", and significantly improves the evaluation system's accuracy in identifying design defects, engineering pertinence and reliability of optimization convergence.

[0121] Optionally, the initial control point location information is iteratively optimized based on the shape and engineering evaluation scores to obtain the target control point location information, including: in response to the shape and engineering evaluation scores being greater than a preset score threshold, the initial outer contour surface is determined as the first surface individual; the first surface individual is updated and iterated until a preset convergence condition is met to obtain the target surface individual; and the target control point location information is determined based on the target surface individual.

[0122] The aforementioned preset score threshold represents the minimum qualified score standard set during the optimization iteration process. It is used to screen out candidate surfaces that meet the basic engineering requirements. Only when the modeling and engineering evaluation scores are higher than this threshold will the surface be included in the optimization population.

[0123] The aforementioned first surface individual represents the current surface instance that is judged to have a shape and engineering evaluation score higher than a preset score threshold during the iterative optimization process, and it participates in the subsequent population evolution as a dominant solution.

[0124] The aforementioned update iteration represents the process of generating a new generation of candidate surface solutions through mutation, crossover, or selection operations, based on the first surface individual within the framework of swarm intelligence optimization algorithms. This aims to explore better surface morphologies while maintaining engineering compliance.

[0125] The aforementioned preset convergence conditions represent the set iteration termination criteria, including the maximum number of iterations, the rate of change of the optimal score being lower than a threshold for several consecutive generations, or the population diversity being lower than a set value, which are used to ensure that the optimization process reaches a stable solution within a reasonable computational cost.

[0126] The aforementioned target surface instance represents the final surface instance with the highest shape and engineering evaluation score that is retained when the preset convergence conditions are met. It represents the best geometric solution obtained by the current optimization process convergence.

[0127] In this embodiment, the initial control point location information is iteratively optimized based on the styling and engineering evaluation scores. When the target control point location information is obtained, in response to the styling and engineering evaluation scores being greater than a preset score threshold, the initial outer contour surface is determined as the first surface individual. Specifically, when the styling and engineering evaluation score of the outer contour surface of the car door glass calculated by the weighted scoring formula is higher than the preset minimum qualification standard, the surface is regarded as a candidate solution that satisfies the basic engineering constraints, and the system marks it as the "first surface individual" as the initial advantageous individual for subsequent optimization iterations.

[0128] Then, based on the first surface individual, updates and iterates until a preset convergence condition is met to obtain the target surface individual. For example, using the control point coordinates of the first surface individual as the genetic basis, a swarm intelligence optimization algorithm is used to perform mutation, crossover, or selection operations to generate a new generation of surface candidate solutions. The shape and engineering evaluation scores of each surface are calculated generation by generation, and the individual with the highest score is retained. This process is repeated until a preset termination condition is reached, and finally, the surface with the highest score is output as the "target surface individual." The termination condition can be the maximum number of iterations, a score change rate below a threshold, or the population stabilizing. The above steps realize the autonomous search and gradual optimization of the surface morphology, completing the evolutionary process from initial design to the optimal solution.

[0129] Then, based on the individual target surface, the position information of the target control points is determined. That is, the NURBS surface model corresponding to the finally converged target surface individual is used to extract all the coordinates of the three-dimensional control points required to define the surface shape through the parametric reverse extraction method, forming a set of accurate, unique parameters that can be directly used for engineering modeling and manufacturing, namely, "target control point position information".

[0130] Based on the above optional embodiments, this application embodiment constructs an automated design process driven by styling and engineering evaluation scores, optimized by control point coordinates, and searched by iterative evolution. This process achieves systematic optimization of the outer contour surface of the car door glass from the initial configuration to the optimal form, ensuring that the design results have high accuracy and engineering feasibility while meeting multidimensional constraints.

[0131] Optionally, the parameter optimization method for the outer contour surface of the door glass also includes: in response to the styling and engineering evaluation score being less than a preset score threshold, determining the initial outer contour surface as a second surface individual, and filtering the second surface individual.

[0132] The aforementioned second surface instance represents a surface instance whose shape and engineering evaluation score is determined to be lower than the preset score threshold during the optimization process, and it represents a poor solution that does not meet the engineering constraints.

[0133] The aforementioned filtering process refers to the exclusion, elimination, or non-participation of individuals on the second surface during the operation of the swarm intelligence optimization algorithm. Its purpose is to prevent low-quality surfaces from participating in subsequent population evolution and avoid them interfering with the optimization direction.

[0134] In this embodiment, in response to a styling and engineering evaluation score that is less than a preset score threshold, the initial outer contour surface is determined to be a second surface individual. Specifically, when the styling and engineering evaluation score of the outer contour surface of the car door glass, calculated based on reference point position information, target gap range, gap calculation distance, preset scaling factor, preset attenuation factor, and number of reference points, is lower than a preset minimum passing score standard, the surface is judged to not meet the basic engineering constraints. The system explicitly identifies it as a "second surface individual" to distinguish it from the candidate solutions that meet the requirements, thereby achieving automatic identification and classification of substandard design schemes.

[0135] After a surface is identified as a second surface individual, this second surface individual undergoes filtering. During the iterative operation of the swarm intelligence optimization algorithm, when filtering second surface individuals, all surfaces identified as "second surface individuals" are removed from the current population, prohibiting them from participating in subsequent selection, crossover, or mutation genetic operations. This avoids their control point location information negatively impacting the generation of the next generation of surfaces, ensuring that the optimization process evolves only based on high-scoring individuals, thereby maintaining the evolutionary quality and search efficiency of the population.

[0136] Based on the above optional embodiments, this application embodiment establishes a poor solution isolation mechanism based on shape and engineering evaluation scores, so that all surfaces that do not comply with engineering compliance are marked and removed in the early stage of optimization, effectively preventing low-quality solutions from polluting the optimization population, delaying the convergence speed or misleading the search direction, and ensuring that the entire iterative process is always efficiently promoted within a highly feasible design space.

[0137] Figure 5 This is a schematic diagram of an optional swarm intelligence optimization algorithm according to an embodiment of this application, such as... Figure 5As shown in the diagram, this schematic illustrates the iterative process of the swarm intelligence optimization algorithm in this embodiment of the application. Specifically, it employs an iterative search mechanism centered on control point location information as chromosome encoding, shape and engineering evaluation scores as fitness functions, and dynamic mutation rate and tournament selection strategy.

[0138] The swarm intelligence optimization algorithm starts with the initialization of the population, which consists of several sets of randomly generated control point coordinates. Each set of coordinates represents an independent individual of the outer contour surface of the car door glass, and its shape is uniquely defined by a parametric model of an olive-shaped surface, a toroidal surface, a cylindrical surface, or a spiral surface.

[0139] In each iteration, the algorithm employs a tournament selection strategy to select parents for individuals in the current population. This strategy involves randomly selecting several individuals and comparing their modeling and engineering evaluation scores, selecting only the individuals with the highest scores as parents to participate in genetic operations, ensuring that the evolutionary direction always moves towards a higher fitness region, and avoiding low-quality solutions interfering with the optimization process.

[0140] Subsequently, the parent individuals generate new individuals through crossover operations, with their control point coordinates partially exchanged in the spatial dimension to integrate superior genetic traits.

[0141] After crossover, the algorithm performs mutation operations on the new individuals based on a dynamic mutation rate, which is adaptively adjusted according to the population convergence state. Specifically, a higher mutation rate is used in the early iteration phase to enhance global exploration capabilities, while the mutation rate is reduced in the later stages when convergence is near to strengthen local fine-tuning, thereby effectively balancing the breadth and accuracy of the search.

[0142] To ensure the geometric feasibility of the generated surfaces, the algorithm performs a geometric validity check on the control point coordinates after each generation of new individuals through crossover or mutation. Only surfaces whose coordinate set can construct a NURBS surface topology and form complete continuous circular arc segments or spiral trajectories are retained; otherwise, they are discarded. The new individuals generated through these operations constitute the next generation of the population, replacing the previous generation.

[0143] The above process continues to cycle until the preset iteration termination conditions are met, including reaching the maximum number of iterations, the rate of change of the optimal score being lower than the threshold for several consecutive generations, or the population diversity being lower than the set value.

[0144] Ultimately, the algorithm outputs the control point location information corresponding to the target surface individual with the highest fitness, realizing automated and high-precision optimization of the large surface of the car door glass under multi-dimensional engineering constraints.

[0145] The embodiments of this application transform the high-dimensional nonlinear search of design variables into a controllable population evolution process through the above-mentioned swarm intelligence optimization algorithm, which significantly improves design efficiency and solution reliability, and greatly reduces the reliance on traditional manual trial and error mode.

[0146] Figure 6 This is a schematic diagram of an optional parameter optimization method for the outer contour surface of a car door glass according to an embodiment of this application, as shown below. Figure 6 As shown in the diagram, this schematic illustrates the systematic design process of the method for optimizing the gaps in the large surfaces of the car door glass. Specifically, it includes: First, constructing the initial outer contour surface corresponding to the car door glass. Based on the structural characteristics of different vehicle models, the large surfaces of the car door glass are divided into basic surface types such as olive-shaped surfaces, annular surfaces, cylindrical surfaces, or spiral surfaces. A differentiated parametric modeling strategy is adopted to express these surfaces in the form of NURBS surfaces. Specifically, the olive-shaped surface is generated by rotating the contour line around a rotation axis, the annular surface is generated by sweeping the contour line around a trajectory line, the cylindrical surface is generated by sweeping the contour line around a straight trajectory line, and the spiral surface is formed by combining two olive-shaped surfaces, ensuring that the surface difference at the B-pillar junction is minimized. All surfaces are defined parametrically using control point coordinates to achieve precise control and efficient expression of the surface morphology.

[0147] Subsequently, the system inputs the coordinates of reference points and their corresponding target clearance ranges. Reference points include water tangents, key ergonomic points, and surrounding components. Key ergonomic points can include head, shoulder, elbow, and hip spaces, while surrounding components can include door locks, bumper beams, etc. Each reference point has a preset tolerance range consisting of a minimum clearance and a maximum clearance, serving as a constraint for subsequent styling evaluation.

[0148] After obtaining the surface model and reference point information, the system calculates the gap evaluation score and wind resistance evaluation score, and applies a weighted score to the initial outer contour surface. Based on the weighted scoring formula, and combined with the total score S and scaling factor, the system calculates the weighted score. Attenuation factor The modeling and engineering evaluation scores of the surface are generated based on the number of reference points n. These scores serve as the sole fitness index, quantifying the surface's overall compliance in terms of ergonomics, layout feasibility, and modeling consistency.

[0149] Subsequently, the system enters the swarm intelligence optimization algorithm module, using the control point coordinates as optimization variables and the modeling and engineering evaluation scores as fitness functions to initiate an iterative optimization process. The population undergoes selection, crossover, mutation, and filtering processes, eliminating second-surface individuals with scores below a preset score threshold and retaining and evolving first-surface individuals with scores above the threshold until the preset convergence condition is met.

[0150] Finally, the algorithm iterates and outputs the optimal parameter solution, that is, the target surface individual with the highest shape and engineering evaluation score. It also extracts the corresponding target control point position information from it, and outputs it as the final design parameters for the large surface of the door glass, thus completing the fully automated optimization process from the initial configuration to the optimal solution.

[0151] Figure 7 This is a schematic diagram of another optional parameter optimization method for the outer contour surface of a car door glass according to an embodiment of this application, as shown below. Figure 7 As shown. The method includes the following steps:

[0152] Step S701: Obtain initial control point position information, reference point position information, and target gap range. The reference point position information is used to represent the spatial reference position corresponding to the outer contour surface of the door glass, and the target gap range is used to represent the gap constraint conditions corresponding to the reference point position information.

[0153] Step S702: Obtain the surface type information corresponding to the door glass;

[0154] Step S703: Determine the fitting control points based on the surface type information and the initial control point position information;

[0155] Step S704: Construct the initial outer contour surface based on the fitted control points;

[0156] Step S705: Determine the gap calculation distance based on the reference point position information and the initial outer contour surface, wherein the gap calculation distance is used to represent the spatial position distance between the reference point position information and the initial outer contour surface;

[0157] Step S706: Determine the first gap distance based on the gap calculation distance and the upper limit of the target gap range, and determine the second gap distance based on the gap calculation distance and the lower limit of the target gap range;

[0158] Step S707: In response to the first gap distance being less than the second gap distance, the first gap distance is determined as the third gap distance;

[0159] Step S708: In response to the first gap distance being greater than the second gap distance, the second gap distance is determined as the third gap distance;

[0160] Step S709: Determine the gap evaluation score based on the third gap distance, preset scaling factor, preset attenuation factor, preset total evaluation score, and number of reference points;

[0161] Step S710: Determine the drag evaluation score based on the estimated drag contribution coefficient corresponding to the initial outer contour surface and the preset drag coefficient target value.

[0162] Step S711: Perform a weighted calculation based on the gap evaluation score and the wind resistance evaluation score to obtain the shape and engineering evaluation score;

[0163] Step S712: In response to the shape and engineering evaluation score being greater than a preset score threshold, the initial outer contour surface is determined as the first surface individual;

[0164] Step S713: Update and iterate based on the first surface individual until the preset convergence condition is met to obtain the target surface individual;

[0165] Step S714: Determine the target control point position information based on the individual target surface;

[0166] Step S715: In response to the shape and engineering evaluation score being less than a preset score threshold, the initial outer contour surface is determined as the second surface individual, and the second surface individual is filtered.

[0167] Based on the above steps S701 to S715, this embodiment of the application adopts a parametric surface modeling and iterative optimization algorithm that combines styling and engineering evaluation scores. First, it obtains initial control point position information, reference point position information, and target gap range. The reference point position information represents the spatial reference position corresponding to the outer contour surface of the door glass, and the target gap range represents the gap constraint condition corresponding to the reference point position information. Then, based on the initial control point position information, it constructs the initial outer contour surface corresponding to the door glass. Next, it evaluates the initial outer contour surface using the reference point position information and the target gap range to generate styling and engineering evaluation scores. Finally, iteratively optimizes the initial control point position information based on the styling and engineering evaluation scores to obtain the target control point position information. The target control point position information is used to construct the target outer contour surface corresponding to the door glass, achieving the goal of automatically searching for the optimal large-area glass styling. This results in shortening the development cycle and improving optimization accuracy, thus solving the technical problems of long development cycles and low optimization accuracy in related large-area optimization methods for door glass.

[0168] Figure 8 This is a structural block diagram of an optional parameter optimization device for the outer contour surface of a car door glass according to an embodiment of this application, such as... Figure 8As shown. It should be noted that this device can be used to execute the above-mentioned parameter optimization method for the outer contour surface of a car door glass. The device includes: an acquisition module 801, used to acquire initial control point position information, reference point position information, and a target gap range, wherein the reference point position information represents the spatial reference position corresponding to the outer contour surface of the car door glass, and the target gap range represents the gap constraint condition corresponding to the reference point position information; a construction module 802, used to construct the initial outer contour surface corresponding to the car door glass based on the initial control point position information; a processing module 803, used to evaluate the initial outer contour surface using the reference point position information and the target gap range, generating a styling and engineering evaluation score; and an optimization module 804, used to iteratively optimize the initial control point position information based on the styling and engineering evaluation score to obtain target control point position information, wherein the target control point position information is used to construct the target outer contour surface corresponding to the car door glass.

[0169] Optionally, the construction module 802 is further configured to: obtain the surface type information corresponding to the door glass; determine the fitting control points based on the surface type information and the initial control point position information, wherein the fitting objects corresponding to the fitting control points include: the contour line, trajectory line and rotation axis corresponding to the initial outer contour surface; and construct the initial outer contour surface based on the fitting control points.

[0170] Optionally, the processing module 803 is also used to: determine the gap evaluation score based on the reference point position information and the target gap range; determine the wind resistance evaluation score based on the estimated wind resistance contribution coefficient corresponding to the initial outer contour surface and the preset wind resistance coefficient target value; and perform a weighted calculation based on the gap evaluation score and the wind resistance evaluation score to obtain the shape and engineering evaluation score.

[0171] Optionally, the processing module 803 is further configured to: determine the gap calculation distance based on the reference point position information and the initial outer contour surface, wherein the gap calculation distance is used to represent the spatial position distance between the reference point position information and the initial outer contour surface; and determine the gap evaluation score based on the gap calculation distance and the target gap range.

[0172] Optionally, the processing module 803 is further configured to: determine a first gap distance based on the gap calculation distance and the upper limit of the target gap range, and determine a second gap distance based on the gap calculation distance and the lower limit of the target gap range; determine a third gap distance based on the first gap distance and the second gap distance; and determine a gap evaluation score based on the third gap distance, a preset scaling factor, a preset attenuation factor, a preset total evaluation score, and the number of reference points.

[0173] Optionally, the processing module 803 is further configured to: determine the first gap distance as the third gap distance in response to the first gap distance being less than the second gap distance; and determine the second gap distance as the third gap distance in response to the first gap distance being greater than the second gap distance.

[0174] Optionally, the optimization module 804 is further configured to: determine the initial outer contour surface as the first surface individual in response to the modeling and engineering evaluation score being greater than a preset score threshold; update and iterate based on the first surface individual until a preset convergence condition is met to obtain the target surface individual; and determine the target control point position information based on the target surface individual.

[0175] Optionally, the optimization module 804 is also used to: determine the initial outer contour surface as the second surface individual in response to the shape and engineering evaluation score being less than a preset score threshold, and to perform filtering processing on the second surface individual.

[0176] Embodiments of this application also provide a vehicle, including: a memory storing an executable program; and a processor for running the program, wherein the program executes the methods described in various embodiments of this application when it runs.

[0177] Embodiments of this application also provide a computer-readable storage medium including a stored executable program, wherein, when the executable program is running, it controls the device where the computer-readable storage medium is located to perform the methods of various embodiments of this application.

[0178] Embodiments of this application also provide a computer program product, including a computer program that, when executed by a processor, implements the methods of various embodiments of this application.

[0179] Embodiments of this application also provide a computer program product, including a non-volatile computer-readable storage medium for storing a computer program that, when executed by a processor, implements the methods in various embodiments of this application.

[0180] Embodiments of this application also provide a computer program that, when executed by a processor, implements the methods described in the various embodiments of this application.

[0181] In the above embodiments of this application, the descriptions of each embodiment have different focuses. Parts not described in detail in a particular embodiment can be referred to in the relevant descriptions of other embodiments. It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, stored data, displayed data, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties. Furthermore, the collection, use, and processing of related data must comply with the relevant laws, regulations, and standards of the relevant countries and regions, and corresponding operation entry points are provided for users to choose to authorize or refuse.

[0182] In the several embodiments provided in this application, it should be understood that the disclosed technical content can be implemented in other ways. The device embodiments described above are merely illustrative; for example, the division of units can be a logical functional division, and in actual implementation, there may be other division methods. For instance, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the displayed or discussed mutual coupling, direct coupling, or communication connection may be through some interfaces; the indirect coupling or communication connection between units or modules may be electrical or other forms.

[0183] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0184] Furthermore, the functional units in the various embodiments of this application can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit.

[0185] If the integrated unit is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, or all or part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of this application. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, read-only memory (ROM), random access memory (RAM), portable hard drives, magnetic disks, or optical disks.

[0186] The above description is only a preferred embodiment of this application. It should be noted that for those skilled in the art, several improvements and modifications can be made without departing from the principle of this application, and these improvements and modifications should also be considered within the scope of protection of this application.

Claims

1. A method for optimizing the parameters of the outer contour surface of a car door glass, characterized in that, include: Acquire initial control point position information, reference point position information, and target gap range, wherein the reference point position information is used to represent the spatial reference position corresponding to the outer contour surface of the door glass, and the target gap range is used to represent the gap constraint condition corresponding to the reference point position information; The initial outer contour surface corresponding to the door glass is constructed based on the initial control point position information; The initial outer contour surface is evaluated using the reference point location information and the target gap range to generate a modeling and engineering evaluation score; Based on the styling and engineering evaluation scores, the initial control point position information is iteratively optimized to obtain the target control point position information, wherein the target control point position information is used to construct the target outer contour surface corresponding to the door glass.

2. The method according to claim 1, characterized in that, Constructing the initial outer contour surface corresponding to the door glass based on the initial control point position information includes: Obtain the surface type information corresponding to the door glass; The fitting control points are determined based on the surface type information and the initial control point position information; The initial outer contour surface is constructed based on the fitted control points.

3. The method according to claim 1, characterized in that, The initial outer contour surface is evaluated using the reference point location information and the target gap range to generate the shape and engineering evaluation score, including: The gap evaluation score is determined based on the reference point location information and the target gap range; The drag evaluation score is determined based on the estimated drag contribution coefficient corresponding to the initial outer contour surface and the preset drag coefficient target value. The design and engineering evaluation score is obtained by weighting the gap evaluation score and the wind resistance evaluation score.

4. The method according to claim 3, characterized in that, Determining the gap evaluation score based on the reference point location information and the target gap range includes: The gap calculation distance is determined based on the reference point position information and the initial outer contour surface, wherein the gap calculation distance is used to represent the spatial position distance between the reference point position information and the initial outer contour surface; The gap evaluation score is determined based on the gap calculation distance and the target gap range.

5. The method according to claim 4, characterized in that, Determining the gap evaluation score based on the gap calculation distance and the target gap range includes: A first gap distance is determined based on the gap calculation distance and the upper limit of the target gap range, and a second gap distance is determined based on the gap calculation distance and the lower limit of the target gap range; The third gap distance is determined based on the first gap distance and the second gap distance; The gap evaluation score is determined based on the third gap distance, the preset scaling factor, the preset attenuation factor, the preset total evaluation score, and the number of reference points.

6. The method according to claim 5, characterized in that, Determining the third gap distance based on the first gap distance and the second gap distance includes: In response to the first gap distance being less than the second gap distance, the first gap distance is determined as the third gap distance; In response to the first gap distance being greater than the second gap distance, the second gap distance is determined as the third gap distance.

7. The method according to claim 1, characterized in that, Based on the aforementioned shape and engineering evaluation scores, the initial control point location information is iteratively optimized to obtain the target control point location information, including: In response to the fact that the shape and engineering evaluation score is greater than a preset score threshold, the initial outer contour surface is determined to be the first surface individual; The first surface individual is updated and iterated until the preset convergence condition is met to obtain the target surface individual; The target control point position information is determined based on the target surface individual.

8. The method according to claim 7, characterized in that, The method further includes: In response to the fact that the shape and engineering evaluation score is less than the preset score threshold, the initial outer contour surface is determined to be a second surface individual, and the second surface individual is filtered.

9. An electronic device, characterized in that, include: Memory, which stores executable programs; A processor for running the program, wherein the program, when running, performs the method according to any one of claims 1 to 8.

10. A computer-readable storage medium, characterized in that, The computer-readable storage medium includes a stored executable program, wherein, when the executable program is executed, it controls the device on which the storage medium is located to perform the method according to any one of claims 1 to 8.

Images