CN115600309A

CN115600309A - Method and device for designing molded surface of automobile windshield mold based on curved surface reconstruction

Info

Publication number: CN115600309A
Application number: CN202211071158.9A
Authority: CN
Inventors: 张明; 张儒; 路明标; 郭震; 孙自飞; 金云峰; 李作东; 安旭
Original assignee: Nanjing Tianfu Software Co ltd
Current assignee: Nanjing Tianfu Software Co ltd
Priority date: 2022-09-02
Filing date: 2022-09-02
Publication date: 2023-01-13
Anticipated expiration: 2042-09-02
Also published as: CN115600309B

Abstract

The invention provides a method and a device for designing a mold surface of an automobile windshield mold based on curved surface reconstruction. And establishing a mapping model according to the geometrical characteristic data of the discrete points and the distance from the discrete points to the corresponding mould profile. And extracting discrete points of the required glass surface and geometrical characteristic data of the discrete points. And predicting the distance from each discrete point on the required glass molded surface to the required mold molded surface according to the geometric characteristic data and the mapping model of the discrete points of the required glass molded surface. And acquiring the coordinates of the discrete points of the required mould profile according to the geometric characteristic data of the discrete points and the distance from the discrete points to the required mould profile. And acquiring a plurality of reconstruction lines by using the coordinates of the discrete points, and establishing the molded surface of the required mold by using a geometric modeling engine based on the plurality of reconstruction lines.

Description

Method and device for designing molded surface of automobile windshield mold based on curved surface reconstruction

Technical Field

The invention belongs to the technical field of glass mold design, and particularly relates to a method and a device for designing a molded surface of an automobile windshield mold based on curved surface reconstruction.

Background

The production process of the automobile windshield comprises the following steps: first, a glass sheet is cut, edged, cleaned, dried, heated, and then conveyed to a forming chamber. Then, the molding chamber is attracted to the mold suction surface of the molding machine, and is lowered with the mold suction surface and abutted against the glass mold below. When the glass sheet reaches the softening point, the glass sheet is bent downwards under the influence of gravity and is attached to the glass mold, so that the set molded surface curvature of the glass mold is achieved. Finally, the glass sheet formed by hot bending is cooled and subjected to subsequent steps to form the automobile windshield meeting the production requirements.

Among them, the glass mold plays an important role in molding a glass original sheet. However, the original glass sheet can rebound in the forming process, so that the geometric characteristics of the molded surface of the glass mold are not completely consistent with the designed curved surface of the automobile windshield.

At present, the design of the molded surface of the automobile windshield glass mold mostly adopts a trial and error method, and the general flow of the method is as follows: (1) determining a desired glass profile; (2) preliminarily designing a molded surface of a glass mold according to the molded surface of the glass; (3) trial-producing a glass finished product according to the molded surface of the glass mold; (4) Checking the deviation between the trial-produced glass finished product and the required glass molded surface; (5) And (3) if the deviation is not qualified, returning to the step (2) to adjust the molded surface of the glass mold. However, the trial and error method requires repeated correction of the molded surface of the glass mold, and the method has the disadvantages of long design period, large workload and high cost, which results in low efficiency of producing the automobile windshield.

With the continuous development of the automobile industry, the styles of automobile windshields are more and more, and the design of the glass mold profile faces new requirements and challenges. The trial and error approach has been difficult to meet the trend in the automotive windshield manufacturing industry due to its high design cost and long design cycle.

Disclosure of Invention

The embodiment of the invention provides a method and a device for designing a molded surface of an automobile windshield mold based on curved surface reconstruction, and aims to solve the problems of high design cost and long design period in the prior art.

One aspect of the invention provides a method for designing a profile of an automobile windshield mold based on curved surface reconstruction, which is applied to generate a required mold profile according to the required glass profile and comprises the following steps:

acquiring a plurality of groups of molded surfaces from a historical design scheme, wherein each group of molded surfaces comprises a glass molded surface and a corresponding mold molded surface;

respectively extracting discrete points of each glass profile, and acquiring geometric feature data of each discrete point;

obtaining the distance from each discrete point to the molded surface of the corresponding mold;

establishing a mapping model according to the geometric characteristic data of all discrete points and the distance from the discrete points to the corresponding mould profiles, wherein the input variable of the mapping model is the geometric characteristic of the discrete points, and the output variable is the distance from the discrete points to the corresponding mould profiles;

extracting discrete points of a required glass profile, and acquiring geometric feature data of each discrete point;

predicting the distance from each discrete point on the required glass molded surface to the required mold molded surface according to the geometric characteristic data of the discrete points of the required glass molded surface and the mapping model;

acquiring coordinates of discrete points of the required mold surface according to the geometric characteristic data of the discrete points of the required glass mold surface and the predicted distance from the discrete points of the required glass mold surface to the required mold surface;

obtaining a plurality of reconstruction lines by using the coordinates of the discrete points of the profile of the required mould, wherein the average distance between each reconstruction line and the discrete point of the profile of the corresponding required mould is the minimum;

and establishing the molded surface of the required mold by adopting a geometric modeling engine based on the plurality of reconstruction lines.

Optionally, the respectively extracting discrete points of each glass profile and acquiring geometric feature data of each discrete point includes:

for each glass profile, discrete points are extracted as follows:

determining a minimum bounding box of the glass profile;

establishing a three-dimensional coordinate system of the glass molded surface by taking the central point of the minimum bounding box as an origin, wherein the x axis of the coordinate system is parallel to the longest edge of the minimum bounding box, and the z axis of the coordinate system is parallel to the shortest edge of the minimum bounding box;

respectively taking two longest boundary lines on the glass molded surface as an upper boundary line and a lower boundary line of the glass molded surface;

respectively dividing the upper boundary line and the lower boundary line by p +1 equally, and connecting corresponding equally dividing points on the upper boundary line and the lower boundary line to obtain p equally dividing lines;

obtaining p planes which are vertical to the XOY plane and pass through any one of p bisectors, wherein the planes are in one-to-one correspondence with the bisectors;

obtaining p intersecting lines which intersect with p planes on the glass molded surface;

dividing each intersection line into q +1 equal parts; sequentially connecting equant points in corresponding sequence on the p intersecting lines to obtain q connecting lines; the intersections of the p intersecting lines and the q connecting lines are discrete points of the glass profile.

Optionally, the respectively extracting discrete points of each glass profile and obtaining geometric feature data of each discrete point further includes:

(1) Acquiring the coordinates of each discrete point under the coordinate system corresponding to the glass molded surface;

(2) For each discrete point, obtaining a normal vector N according to the following method:

obtaining a tangent vector S of the discrete point parallel to the x axis _x And, a tangent vector S of the discrete point parallel to the y-axis _y ；

Obtaining a normal vector N by cross multiplication of tangent vectors: n = S _x ×S _y ；

(3) For each discrete point, the average curvature H is obtained as follows:

wherein k is ₁ Is the maximum radius of curvature through the discrete point; k is a radical of ₂ Is the minimum radius of curvature through the discrete point;

(4) For each discrete point, a gaussian curvature K is obtained as follows:

K＝k ₁ *k ₂

(5) Aiming at each discrete point, acquiring the arch height AH according to the following method;

the arch height is the distance from the discrete point to the corresponding bisector:

AH＝Dist(P,l _i ),P∈l' _i ,i＝1,2,…p

wherein the discrete points P are on the intersecting line l' _i Upper, l _i Is of l' _i Corresponding bisector.

Optionally, the obtaining a distance from each discrete point to the corresponding mold surface includes:

and aiming at each glass molded surface, respectively obtaining the distance from each discrete point on the glass molded surface to the corresponding mold molded surface in the z-axis direction.

Optionally, the establishing a mapping model according to the geometric feature data of all the discrete points and the distance from the discrete points to the corresponding mold surface includes:

preprocessing the coordinates of all discrete points by adopting a MinMax (maximum and minimum) normalization mode;

preprocessing normal vectors, average curvatures, gaussian curvatures and arch heights of all discrete points by adopting a Robust Normalization mode;

constructing a data set by utilizing the preprocessed geometrical characteristic data of the discrete points and the distance from the discrete points to the corresponding mould surface in the z-axis direction, wherein the coordinates, normal vectors, average curvature, gaussian curvature and arch height of the discrete points are used as input variables of the data set, and the distance from the discrete points to the corresponding mould surface in the z-axis direction is used as an output variable of the data set;

a mapping model between the input variables and the output variables is obtained using all data in the dataset.

Optionally, the preprocessing the coordinates of all the discrete points by using a MinMax normalization method includes:

the coordinates of each discrete point are preprocessed according to the following method:

wherein f _ max is the maximum value of all the discrete point coordinates; f _ min is the minimum value of all discrete point coordinates, and f is the original discrete point coordinate; f' is the coordinates of the discrete points after preprocessing.

Optionally, the preprocessing the normal vectors, the average curvatures, the gaussian curvatures, and the arch heights of all the discrete points by using a Robust normalization method includes:

the normal vector, the average curvature, the Gaussian curvature and the arch height of each discrete point are preprocessed according to the following modes:

wherein, f is an original geometric characteristic data value, and the geometric characteristic data value is a data value of one of the geometric characteristics of the normal vector, the average curvature, the Gaussian curvature and the arch height of the discrete point; f' is a preprocessed geometric characteristic data value corresponding to f; f _ mean is the median of the geometric characteristic data values corresponding to all discrete points and f on the glass molded surface to which the discrete points belong; and IQR is the interval length between the 1 st quartile and the 3 rd quartile in the geometric characteristic data values corresponding to all discrete points and f on the glass molded surface to which the discrete points belong.

Optionally, the establishing a mapping model according to the geometric feature data of all the discrete points and the distances from the discrete points to the corresponding mold surfaces includes:

selecting any one of all the glass molded surfaces as a test glass molded surface, and taking the rest glass molded surfaces as training glass molded surfaces;

constructing a test data set by using the geometrical characteristic data of the discrete points preprocessed by the test glass molded surface and the distance from the discrete points on the test glass molded surface to the corresponding mold molded surface in the z-axis direction, wherein the coordinates, normal vectors, average curvatures, gaussian curvatures and arch heights of the discrete points are used as input variables, and the distance from the discrete points to the corresponding mold molded surface in the z-axis direction is used as an output variable;

constructing a training data set by using the geometrical characteristic data of discrete points preprocessed by the training glass molded surface and the distance from the discrete points on the training glass molded surface to the corresponding mold molded surface in the z-axis direction, wherein the coordinates, normal vectors, average curvatures, gaussian curvatures and arch heights of the discrete points are used as input variables, and the distance from the discrete points to the corresponding mold molded surface in the z-axis direction is used as an output variable;

and establishing a regression model between the geometric characteristic data of the discrete points of the glass molded surface and the distance from the discrete points to the corresponding mold molded surface in the z-axis direction by adopting a random forest training algorithm according to the training data set and the testing data set.

Optionally, the extracting discrete points of the required glass profile and acquiring geometric feature data of each discrete point include:

determining a minimum bounding box of the required glass profile;

establishing a three-dimensional coordinate system of the required glass molded surface by taking the central point of the minimum bounding box as an origin, wherein the x axis of the coordinate system is parallel to the longest edge of the minimum bounding box, and the z axis of the coordinate system is parallel to the shortest edge of the minimum bounding box;

respectively taking two longest boundary lines on the required glass profile as an upper boundary line and a lower boundary line of the required glass profile;

obtaining p intersecting lines which intersect with the p planes on the required glass molded surface;

dividing each intersection line into q +1 equal parts; sequentially connecting equant points in corresponding sequence on the p intersecting lines to obtain q connecting lines; the intersection points of the p intersecting lines and the q connecting lines are discrete points of the required glass profile.

Optionally, the predicting the distance from each discrete point on the required glass profile to the required mold profile according to the geometric feature data of the discrete points of the required glass profile and the mapping model includes:

preprocessing the coordinates of all discrete points on the required glass molded surface by adopting a MinMax normalization mode;

preprocessing normal vectors, average curvatures, gaussian curvatures and arch heights of all discrete points on a required glass profile by adopting a Robust normalization mode;

substituting the geometrical characteristic data of all discrete points on the preprocessed required glass molded surface into the regression model, and calculating to obtain a predicted value of the distance from each discrete point on the required glass molded surface to the required mold molded surface in the z-axis direction;

judging whether discrete points with a plurality of predicted values exist on the required glass molded surface or not,

and if so, taking the maximum value in the plurality of predicted values as the final predicted value of the corresponding discrete point.

Optionally, the obtaining the coordinates of the discrete points of the required mold surface according to the geometric feature data of the discrete points of the required glass mold surface and the predicted distance from the discrete points of the required glass mold surface to the required mold surface includes:

the coordinates of each discrete point of the required mould surface are obtained according to the following modes:

x′ _i ＝x _i

y′ _i ＝y _i

z′ _i ＝z _i +d _i

wherein: (x' _i ,y' _i ,z' _i ) Coordinates of discrete points of the required mould surface are obtained; (x) _i ,y _i ,z _i ) The coordinates of the corresponding discrete points on the required glass molded surface are obtained; d _i The distance in the z-axis direction from the corresponding discrete point on the predicted desired glass profile to the desired mold profile.

Optionally, the obtaining a plurality of reconstruction lines by using the coordinates of discrete points of the required mold surface includes:

constructing a to-be-reconstructed molded surface of the required mold by adopting a geometric modeling engine according to the coordinates of each discrete point of the molded surface of the required mold;

selecting an optimized area on the profile to be reconstructed, wherein the optimized area does not comprise the edge of the profile to be reconstructed;

acquiring a projection area of the optimized area on a required glass molded surface;

according to the projection area, dividing a connecting line obtained when the discrete points of the required glass profile are extracted into an optimized line and an edge line, wherein the optimized line is a part of the connecting line positioned in the projection area, and the edge line is a part of the connecting line positioned outside the projection area;

for each optimized line in the projection area, determining a corresponding reconstruction line R according to the following steps:

obtaining the highest point x on the optimization line _mid The highest point is the point with the maximum numerical value of the optimization line in the z-axis direction; let peak x _mid A distance d from the corresponding reconstruction line R in the z-axis direction _mid ；

At the highest point x _mid As a center, highest point x on the optimization line _mid Evenly set up n position points x respectively in both sides, position point x is in proper order: x is the number of _{left_1} ，x _{left_2} ，…，x _{left_n} ，x _{right_1} ，x _{right_2} ，…，x _{right_n} (ii) a Let the distance between the position point x and the reconstruction line R in the z-axis direction be d _{left_1} ，d _{left_2} ，…，d _{left_n} ，d _{right_1} ，d _{right_2} ，…，d _{right_n} ；

Will d _{left_1} ，d _{left_2} ，…，d _{left_n} ，d _{right_1} ，d _{right_2} ，…，d _{right_n} As a design variable;

the following constraint conditions are set for the values of the design variables:

d _{left_i} -d _mid ≤0(i＝1,2,…,n)

d _{right_i} -d _mid ≤0(i＝1,2,…,n)

0<d _{left_i+1} -d _{left_i} <d _{left_i} -d _{left_i-1}

d _{right_i} -d _{right_i-1} <d _{right_i+1} -d _{right_i} <0

acquiring all discrete points on the optimization line;

obtaining discrete points corresponding to the discrete points on the required mould profile and the optimized line, and taking the discrete points as the optimized discrete points corresponding to the reconstruction line R;

acquiring an initial reconstruction line according to a constraint condition by using an NSGA3 algorithm and taking the minimum average distance between the reconstruction line R and the corresponding optimized discrete point as an optimization target;

and connecting the initial reconstruction line with the edge line corresponding to the optimization line to form a complete reconstruction line R.

Optionally, the obtaining a plurality of reconstruction lines by using the coordinates of discrete points of the required mold surface further includes:

when a first reconstruction line R is obtained, presetting a reconstruction line, and obtaining the first reconstruction line R according to a constraint condition and an NSGA3 algorithm on the basis of the preset reconstruction line;

and when other reconstruction lines R are reconstructed, respectively setting preset reconstruction lines according to the previous reconstruction line of the reconstruction lines R, and obtaining the reconstruction lines R based on the preset reconstruction lines according to constraint conditions and NSGA3 algorithm.

Another aspect of the present invention provides an apparatus for designing a mold surface of an automotive windshield mold based on curved surface reconstruction, which is applied to generate a required mold surface according to a required glass mold surface, and includes:

the device comprises a glass molded surface and mold molded surface acquisition unit, a storage unit and a control unit, wherein the glass molded surface and mold molded surface acquisition unit is used for acquiring a plurality of groups of molded surfaces from historical design schemes, and each group of molded surfaces comprises a glass molded surface and a corresponding mold molded surface;

the device comprises a glass profile discrete point data acquisition unit, a data acquisition unit and a data acquisition unit, wherein the glass profile discrete point data acquisition unit is used for respectively extracting discrete points of each glass profile and acquiring geometric characteristic data of each discrete point;

the distance acquisition unit is used for acquiring the distance from each discrete point to the molded surface of the corresponding mold;

the mapping model establishing unit is used for establishing a mapping model according to the geometric characteristic data of all the discrete points and the distance between the discrete points and the corresponding mould surface, the input variable of the mapping model is the geometric characteristic of the discrete points, and the output variable is the distance between the discrete points and the corresponding mould surface;

the glass profile discrete point data acquisition unit is also used for extracting discrete points of a required glass profile and acquiring geometric characteristic data of each discrete point;

the distance prediction unit is used for predicting the distance from each discrete point on the required glass molded surface to the required mold surface according to the geometric characteristic data of the discrete points of the required glass molded surface and the mapping model;

the discrete point coordinate acquisition unit is used for acquiring the coordinates of the discrete points of the required mold surface according to the geometric characteristic data of the discrete points of the required glass mold surface and the predicted distance from the discrete points of the required glass mold surface to the required mold surface;

the reconstruction line acquisition unit is used for acquiring a plurality of reconstruction lines by utilizing the coordinates of the discrete points of the profile of the required mould, and the average distance between each reconstruction line and the discrete point of the profile of the corresponding required mould is the minimum;

and the required mold profile establishing unit is used for establishing the profile of the required mold by adopting a geometric modeling engine based on the plurality of reconstruction lines.

According to the technical scheme, the method and the device for designing the molded surface of the automobile windshield mold based on the curved surface reconstruction are characterized in that firstly, a plurality of groups of corresponding glass molded surfaces and mold molded surfaces are obtained from a historical design scheme, discrete points of each glass molded surface are respectively extracted, the geometric characteristic data of each discrete point is obtained, and the distance between each discrete point and the corresponding mold molded surface is obtained.

And secondly, establishing a mapping model according to the geometric feature data of all the discrete points and the distances from the discrete points to the corresponding mould profiles. And thirdly, extracting discrete points of the required glass profile, and acquiring geometric characteristic data of each discrete point on the required glass profile.

And finally, predicting the distance from each discrete point on the required glass molded surface to the required mold surface according to the geometric characteristic data and the mapping model of the discrete points of the required glass molded surface. And acquiring the coordinates of the discrete points of the required mold surface according to the geometric characteristic data of the discrete points of the required glass mold surface and the predicted distance from the discrete points of the required glass mold surface to the required mold surface. And obtaining a plurality of reconstruction lines by using the coordinates of the discrete points of the required mould surface, wherein the average distance between each reconstruction line and the discrete point of the corresponding required mould surface is the minimum. And establishing the molded surface of the required mold by adopting a geometric modeling engine based on the plurality of reconstruction lines.

Therefore, the method and the device provided by the embodiment of the invention can greatly improve the design efficiency of the molded surface of the automobile windshield glass mold and effectively reduce the iteration cost in the design process.

Drawings

Fig. 1 is a schematic flow chart of a method for designing a molded surface of an automobile windshield mold based on curved surface reconstruction according to an embodiment of the present invention;

fig. 2 is a schematic flowchart illustrating an implementation of step S102 in fig. 1 according to an embodiment of the present invention;

FIG. 3 is a schematic structural diagram of a minimum enclosure for a windshield of an automobile according to an embodiment of the invention;

FIG. 4 is a schematic view of discrete points on a glass profile provided in accordance with one embodiment of the present invention;

fig. 5 is a schematic flowchart illustrating an implementation of step S104 in fig. 1 according to an embodiment of the present invention;

FIG. 6 is a schematic diagram of an optimization area according to an embodiment of the present invention;

FIG. 7 is a schematic diagram of a reconstruction line and corresponding discrete points according to an embodiment of the present invention;

fig. 8 is a schematic structural diagram of a device for designing a molded surface of an automobile windshield mold based on curved surface reconstruction according to an embodiment of the present invention.

Detailed Description

In order to make the technical solutions of the present invention better understood, the present invention will be described in further detail with reference to the accompanying drawings and specific embodiments.

Fig. 1 is a schematic flow chart of a method for designing a profile of an automobile windshield mold based on curved surface reconstruction, which is provided by an embodiment of the present invention and is applied to generate a required mold profile according to a required glass profile. As shown in fig. 1, the method comprises the steps of:

step S101: a plurality of sets of profiles are obtained from a historical design scheme, and each set of profiles comprises a glass profile and a corresponding mold profile.

The glass molded surface and the die molded surface in each group of molded surfaces correspond to each other, and each glass molded surface is manufactured by the corresponding die molded surface.

Step S102: and respectively extracting discrete points of each glass profile, and acquiring geometric characteristic data of each discrete point.

In one embodiment of the present disclosure, for each glass profile, as shown in fig. 2, discrete points are extracted in the following manner:

step S1021: a minimum bounding box of the glass profile is determined.

The minimum bounding box is the minimum bounding rectangle of the glass profile, and in the disclosed embodiment of the invention, the minimum bounding box of the glass profile can be obtained using existing algorithms.

Step S1022: and establishing a three-dimensional coordinate system of the glass molded surface by taking the central point of the minimum bounding box as an origin.

As shown in FIG. 3, the x-axis of the three-dimensional coordinate system is parallel to the longest side of the minimum bounding box, the z-axis of the coordinate system is parallel to the shortest side of the minimum bounding box, and the y-axis of the coordinate system is parallel to the middle length side on the minimum bounding box.

Step S1023: the two longest boundary lines on the glass molded surface are respectively used as the upper boundary line and the lower boundary line of the glass molded surface.

A typical glass profile is an irregular curved surface that is approximately rectangular, and the boundaries of the glass profile are formed by curves that curve outward. When the glass mold surface is upright, the boundary lines are divided into an upper boundary line, a lower boundary line, a left boundary line and a right boundary line. Wherein, two upper and lower borderlines of the glass profile are longest.

Step S1024: and respectively dividing the upper boundary line and the lower boundary line by p +1 equally, and connecting corresponding equally dividing points on the upper boundary line and the lower boundary line to obtain p equally dividing lines.

P +1 equally dividing the upper boundary line and the lower boundary line respectively to obtain p equally divided points up on the upper boundary line _i I =1,2, … p, and p bisector points lp on the lower boundary line _i ,i＝1,2,…p。

Connecting corresponding bisectors on upper and lower boundary lines, e.g. up ₁ Connection lp ₁ ，up ₂ Connection lp ₂ . After connecting the corresponding p equal division points on the upper and lower boundary lines, obtaining p equal division lines l _i ,i＝1,2,…p。

Step S1025: p planes are obtained that are perpendicular to the XOY plane and pass through any of the p bisectors.

By a bisector l ₁ For example, a bisector l is obtained ₁ And at the same time, perpendicular to the XOY plane on the three-dimensional coordinate system, which can intersect the glass profile. According to the method, p planes are obtained, and each plane passes through a bisector l _i And perpendicular to the XOY plane. Each plane passing through only one bisector l _i The planes correspond to the bisectors one to one.

Step S1026: p intersecting lines intersecting the p planes on the glass profile are obtained.

The obtained p planes all intersect the glass profile surface, so that p intersecting lines l 'on the glass profile surface can be obtained' _i I =1,2, … p, the intersection line is a curve.

Step S1027: dividing each intersection line into q +1 equal parts; sequentially connecting equant points in a corresponding sequence on the p intersecting lines to obtain q connecting lines; the intersection of p intersecting lines and q connecting lines are discrete points of the glass profile.

For each intersecting line l 'on the glass profile surface' _i I =1,2, … p are each q +1 equally divided to obtain each intersection l' _i I =1,2, … p.

Connecting bisector points of corresponding order on p intersecting lines in turn, e.g. connecting intersecting lines l' ₁ The first bisector point, the intersecting line l' ₂ The first bisector point on, in turn, until connected to the intersecting line l' _p To obtain a connecting line connecting the first bisector point on each intersecting line. After the connection has been completed for the q-th bisector point on each of the intersecting lines, q connecting lines on the glass profile are obtained.

As shown in fig. 4, the intersections of p intersecting lines with q connecting lines are taken as discrete points of the corresponding glass profile.

In the embodiment disclosed in the present invention, the geometric characteristics required to obtain the discrete points are the coordinates of the discrete points, normal vectors, mean curvature, gaussian curvature and arch height.

The reason for extracting the characteristic feature parameters is as follows:

combining the processes of glass hot bending forming and rebounding, after the glass sheet is heated at high temperature, the glass sheet is lifted and attached to the suction mold through the combined action of vacuum adsorption and blowing-up of the suction film; then the suction mould and the glass descend to extrude the glass together with the hot ring; after being pressed and formed, the glass falls on a cold ring and is quickly supported out to be sent to a quenching air grid area for quenching and tempering.

The glass sheet is pressed and formed by the surface of the suction mould and the hot ring surface, and then is dropped on the cold ring by gravity. The stress distribution conditions at each stage are as follows: when the glass sheet is pressed and formed, the surface of the suction mold firstly contacts the middle area of the glass sheet and is gradually attached to the boundary, and the stress is small and uneven. After the edge of the glass is extruded by the surface of the suction mold and the hot ring surface, the boundary stress is increased and is distributed more uniformly. When the mold is dropped, the glass has a certain speed and falls on the cold ring under the action of the gravity of the glass, so that impact load is generated, and the stress of the edge part of the glass is suddenly increased.

Therefore, stress distribution of the automobile windshield at different positions in the forming process has certain difference, which can cause that the deviation of different positions on the formed glass molded surface and the mold molded surface also has difference. Based on this, position information of discrete points on the glass profile, i.e. discrete point coordinates (x/y/z), is extracted.

During the hot bending forming process of the glass sheet, when the glass sheet is subjected to the action of an external bending moment, the shape of the glass sheet is changed. When the glass profile is bent, the original glass sheet on the inner layer of the deformation area is subjected to compression deformation by tangential compressive stress, the original glass sheet on the outer layer is subjected to tensile deformation by tangential tensile stress, and the tangential direction also influences the deformation of the glass profile, so that a unit normal vector (vector _ x/vector _ y/vector _ z) perpendicular to the tangential direction is extracted for representing the tangential characteristic of the glass profile.

Meanwhile, the curvature radius of the mold surface is a main factor for determining the glass surface, the bending degree of the glass surface depends on the shape of the mold surface, and the rebound degree is related to the curvature radius of the mold surface. This is because the smaller the radius of curvature of the die surface, the deeper the relative bending degree becomes, the greater the proportion of elastic deformation in the total deformation becomes, and the larger the spring back becomes after the external force is removed. Thus, the curvature characteristics of the glass profile, including the mean curvature H and the gaussian curvature K, are extracted.

In addition, to characterize the degree of curvature of the glass profile, the camber AH of the discrete points is also extracted.

Respectively acquiring the data value of each geometrical characteristic of the discrete points according to the following modes:

(1) The coordinates of each discrete point are acquired in the coordinate system of the glass profile.

obtaining a tangent vector S of the discrete point parallel to the x axis _x And, a tangent vector S of the discrete point parallel to the y-axis _y 。

Obtaining a normal vector N by cross multiplication of tangent vectors: n = S _x ×S _y 。

(3) For each discrete point, the average curvature H is obtained as follows:

wherein k is ₁ Is the maximum radius of curvature through the discrete point; k is a radical of ₂ Is the minimum radius of curvature through the discrete point.

(4) For each discrete point, a gaussian curvature K is obtained as follows:

K＝k ₁ *k ₂

(5) Aiming at each discrete point, the arch height AH from the discrete point P to the corresponding bisector l is obtained according to the following method _i The distance of (c):

AH＝Dist(P,l _i ),P∈l' _i ,i＝1,2,…p

wherein the discrete points P are on the intersecting line l' _i I =1,2, …, p upper, l _i Is l' _i Corresponding bisector.

Step S103: and acquiring the distance from each discrete point to the corresponding mould profile.

In one embodiment of the present disclosure of the present invention,

Step S104: and establishing a mapping model according to the geometric characteristic data of all the discrete points and the distance from the discrete points to the corresponding mould profile.

The input variable of the mapping model is the geometrical characteristic of the discrete point, and the output variable is the distance from the discrete point to the corresponding mould surface.

In one embodiment of the present disclosure, the geometric feature data of the discrete points is preprocessed before the mapping model is established. As shown in fig. 5, the mapping model may be built by the following steps:

step S1041: and preprocessing the coordinates of all discrete points by adopting a MinMax normalization mode.

In one embodiment of the present disclosure, the coordinates of each discrete point are preprocessed according to the following method:

Step S1042: and preprocessing normal vectors, average curvatures, gaussian curvatures and arch heights of all discrete points by adopting a Robust normalization mode.

In one embodiment of the present disclosure, the normal vector, mean curvature, gaussian curvature and arch height of each discrete point are preprocessed as follows:

wherein, f is an original geometric characteristic data value, and the geometric characteristic data value is a data value of one of the geometric characteristics of a normal vector, an average curvature, a Gaussian curvature and an arch height of a discrete point; f' is a preprocessed geometric characteristic data value corresponding to f; f _ mean is the median of the geometric characteristic data values corresponding to all discrete points and f on the glass molded surface to which the discrete points belong; the IQR is the interval length between the 1 st quartile and the 3 rd quartile in the geometric characteristic data values corresponding to all discrete points and f on the glass molded surface to which the discrete points belong. For example, f is the data value of the original camber height of the discrete point, f' is the data value of the pre-processed camber height of the discrete point, f _ mean is the median of all the data values of the camber height of the discrete point on the glass surface to which the discrete point belongs, and IQR is the interval length between the 1 st quartile and the 3 rd quartile of all the data values of the camber height of the discrete point on the glass surface to which the discrete point belongs.

Step S1043: and constructing a data set by using the preprocessed geometrical characteristic data of the discrete points and the distances from the discrete points to the corresponding mould surface in the z-axis direction.

The discrete point coordinates, the normal vector, the average curvature, the Gaussian curvature and the arch height are used as input variables in the data set, and the distance between the discrete point and the corresponding mould profile in the z-axis direction is used as an output variable in the data set.

Step S1044: a mapping model between the input variables and the output variables is obtained using all data in the dataset.

In the embodiment disclosed in the present invention, the mapping model may be a learning algorithm model such as a regression model, a convolutional neural network model, or the like. Step S1044 can be implemented as follows:

(1) Any one of all the glass profiles is selected as a test glass profile, and all the glass profiles except the test glass profile are used as training glass profiles.

(2) And constructing a test data set by using the geometrical characteristic data of the discrete points after the pretreatment of the test glass molded surface and the distance from the discrete points on the test glass molded surface to the corresponding mold molded surface in the z-axis direction. The coordinates, normal vectors, average curvatures, gaussian curvatures and arch heights of the discrete points are used as input variables, and the distances from the discrete points to the corresponding die profiles in the z-axis direction are used as output variables.

(3) And constructing a training data set by utilizing the geometrical characteristic data of the discrete points preprocessed by the training glass molded surface and the distance from the discrete points on the training glass molded surface to the corresponding mold molded surface in the z-axis direction. The coordinates, normal vectors, average curvatures, gaussian curvatures and arch heights of the discrete points are used as input variables, and the distances from the discrete points to the corresponding die profiles in the z-axis direction are used as output variables.

(4) And establishing a regression model by adopting a random forest algorithm according to the training data set and the test data set.

In one embodiment of the present disclosure, the regression model may be established in the following manner:

(1) And constructing a plurality of training data sets by utilizing different combination modes of the training glass molded surfaces.

The method comprises the steps that a plurality of training data sets are constructed, each training data set can be formed by data corresponding to different training glass molded surfaces, and the data corresponding to the training glass molded surfaces are discrete point geometric characteristic data after the glass molded surfaces are preprocessed and the distance between a discrete point and a corresponding mold molded surface. The test data set only contains data corresponding to the test glass profile.

In one embodiment of the present disclosure, there are 6 sets of glass profiles and data corresponding to the mold profiles, which are respectively set as a set, a set D, a set H, a set K, a set N and a set U, wherein the set U is used as a test set, the glass profile therein is used as a test glass profile, the set a, the set D, the set H, the set K, the set N are used as a training set, and the glass profile therein is used as a training glass profile.

5 training data sets in different combination forms are constructed by using 5 groups of training groups, wherein independent training data sets, namely an H training data set, an H + A + K training data set, an H + K + D training data set and an H + A + K + D + N training data set are respectively constructed according to 5 different combination forms of H, H + A, H + A + K, H + A + K + D, H + A + K + D + N. A test data set is constructed from the U groups.

(2) For each training data set, a regression model is established.

A plurality of regression models are established by respectively utilizing different training data sets and the same testing data set, and one training data set corresponds to one regression model.

For example, a regression model M1 is established using the H training dataset and the U set of test datasets; establishing a regression model M2 by using the H + A training data set and the U group of test data sets; establishing a regression model M3 by using the H + A + K training data set and the U group of test data sets; establishing a regression model M4 by using the H + A + K + D training data set and the U group of test data sets; and establishing a regression model M5 by using the H + A + K + D + N training data set and the U group of test data sets.

(3) And fusing different regression models into a new regression model.

And fusing the established regression model into a new regression model. For example, the regression models M1 and M2 are fused to obtain a regression model M6, and the regression models M1 to M5 are fused to obtain a regression model M7. The fusion method may be to take an average value of data values of output variables of each regression model in the fusion combination, that is, an average value of predicted values, as a data value of an output variable of the regression model after fusion, that is, a predicted value. For example, when the input variable data value of the same discrete point p is substituted into M1 and M2 to obtain predicted values M1-p and M2-p, and the input variable data value of the discrete point p is substituted into a regression model M6 formed by fusing M1 and M2 to obtain a predicted value M6-p, the predicted value M6-p = (M1-p + M2-p)/2 is output from M6.

(4) And carrying out error test on each regression model and the fused regression model by using the test data set.

In the embodiment disclosed by the invention, the single-point maximum error of each regression model and the fused regression model is calculated according to the following modes:

and substituting the geometric characteristic data of each discrete point in the test data set into a regression model, wherein the regression model can predict a predicted value corresponding to each discrete point, namely the distance from the discrete point to the corresponding mould surface. And obtaining the absolute value of the difference between the predicted value and the true value of each discrete point, and taking the maximum absolute value as the single-point maximum error of the regression model.

(5) And taking the regression model with the minimum error as the finally established regression model.

After the single-point maximum errors of all the regression models and the fused regression models are obtained respectively, the single-point maximum errors of the regression models are compared, and the regression model corresponding to the single-point maximum error with the minimum single-point maximum error is used as the finally established regression model.

For example, the single point maximum error for M1 is 4.19; the single point maximum error of M2 is 3.25; the single point maximum error of M3 is 3.41; the single point maximum error of M4 is 3.43; the single point maximum error of M5 is 2.18; the maximum error of a single point of M6 is 2.47; the single point maximum error for M7 is 2.04. Since the single-point maximum error value of M7 is the smallest, the regression model M7 is used as the final established regression model.

Step S105: discrete points of the required glass profile are extracted, and geometric characteristic data of each discrete point are obtained.

The required glass molded surface is a glass molded surface required to be designed corresponding to the molded surface of the mold and is a pre-designed glass molded surface.

Discrete points of the required glass profile are extracted in the following way:

(1) Determining a minimum bounding box of the required glass profile;

(2) Establishing a three-dimensional coordinate system of the required glass molded surface by taking the central point of the minimum bounding box as an origin, wherein the x axis of the coordinate system is parallel to the longest edge of the minimum bounding box, and the z axis of the coordinate system is parallel to the shortest edge of the minimum bounding box;

(3) Respectively taking two longest boundary lines on the required glass profile as an upper boundary line and a lower boundary line of the required glass profile;

(4) Respectively dividing the upper boundary line and the lower boundary line by p +1 equally, and connecting corresponding equally dividing points on the upper boundary line and the lower boundary line to obtain p equally dividing lines;

(5) Obtaining p planes which are vertical to the XOY plane and pass through any one of p bisectors, wherein the planes correspond to the bisectors one by one;

(6) Obtaining p intersecting lines which intersect with p planes on the required glass molded surface;

(7) Dividing each intersection line into q +1 equal parts; sequentially connecting equant points in corresponding sequence on the p intersecting lines to obtain q connecting lines; the intersection of p intersecting lines and q connecting lines are discrete points of the desired glass profile.

And acquiring the geometric characteristic data of each discrete point on the required glass profile according to the manner of acquiring the geometric characteristic data of each discrete point on the glass profile in the previous embodiment, which is not described herein again.

Step S106: and predicting the distance from each discrete point on the required glass molded surface to the required mold molded surface according to the geometric characteristic data and the mapping model of the discrete points of the required glass molded surface.

In one embodiment of the present disclosure, this step may be implemented by the following substeps:

(1) And preprocessing the coordinates of all discrete points on the required glass profile by adopting a MinMax normalization mode.

(2) And preprocessing normal vectors, average curvatures, gaussian curvatures and arch heights of all discrete points on the required glass profile by adopting a Robust normalization mode.

(3) And substituting the geometric characteristic data of all discrete points on the preprocessed required glass molded surface into the finally determined regression model, and calculating to obtain a predicted value of the distance from each discrete point on the required glass molded surface to the required mold molded surface in the z-axis direction.

(4) And judging whether the required glass molded surface has discrete points corresponding to a plurality of predicted values.

If yes, the one or more discrete points are explained to have more than two predicted values, and when the situation happens, the maximum value in the plurality of predicted values is taken as the final predicted value of the corresponding discrete point.

If not, the abnormal condition does not exist, and the unique predicted value corresponding to each discrete point is normally determined.

Step S107: and acquiring coordinates of the discrete points of the required glass profile according to the geometric characteristic data of the discrete points of the required glass profile and the predicted distance from the discrete points of the required glass profile to the required mould profile.

In one embodiment of the disclosure, the coordinates of each discrete point of the required mold surface are calculated by using the geometric feature data of the discrete point on the required glass mold surface and the distance from the discrete point of the required glass mold surface to the required mold surface in the z-axis direction, and the discrete points of the required mold surface correspond to the discrete points on the required glass mold surface one to one and are assumed discrete points on the required mold surface.

Obtaining the coordinates of each discrete point of the required mould surface according to the following modes:

x′ _i ＝x _i

y′ _i ＝y _i

z′ _i ＝z _i +d _i

wherein: (x' _i ,y' _i ,z' _i ) Coordinates of discrete points of the required mould surface are obtained; (x) _i ,y _i ,z _i ) The coordinates of corresponding discrete points on the required glass molded surface are obtained; d _i The distance in the z-axis direction from the corresponding discrete point on the predicted desired glass profile to the desired mold profile.

Step S108: and acquiring a plurality of reconstruction lines by using the coordinates of the discrete points of the required mould surface.

Wherein the average distance between each reconstruction line and the discrete point of the corresponding required mould profile is minimal.

In the embodiment disclosed by the invention, a plurality of reconstruction lines of the required mold surface are obtained by adopting the following modes:

(1) And constructing the to-be-reconstructed molded surface of the required mold by adopting a geometric modeling engine according to the coordinates of each discrete point of the molded surface of the required mold.

(2) And selecting an optimized region on the profile to be reconstructed, wherein the optimized region does not comprise the edge of the profile to be reconstructed.

In actual production, the edge regions of the glass profile and the mould profile are completely coincident, so that the edge portions of the profile to be reconstructed are ignored by the optimization region.

As shown in FIG. 6, the projections of the optimized region and the desired glass profile onto the XOY plane are project-1 and Pr, respectivelyObjection _2, the relative distance between the four boundary curves of the two projection areas is d ₁ ，d ₂ ，d ₃ ，d ₄ ，d _i ∈[0,0.5),i＝1,2,3,4。

In one embodiment of the present disclosure, d1 and d2 are each 4% of the length of the short side of the desired glass profile, and d3 and d4 are each 4% of the length of the long side of the desired glass profile.

(3) And acquiring a projection area of the optimized area on the required glass profile.

(4) And according to the projection area, dividing the connecting line obtained when the discrete points of the required glass profile are extracted into an optimized line and an edge line, wherein the optimized line is the part of the connecting line in the projection area, and the edge line is the part of the connecting line outside the projection area.

When discrete points of the required glass surface are extracted, q connecting lines are obtained and are divided into optimized lines and edge lines by using a projection area. Taking a connecting line as an example, the connecting line is divided into 3 parts by the projection area, wherein the part positioned in the projection area is an optimized line, and the two parts positioned outside the projection area are edge lines. In the above manner, each optimized line within the projection area is acquired.

(5) Aiming at each optimized line in the projection area, determining a corresponding reconstruction line R according to the following steps:

as shown in fig. 7, the solid curve is an optimized line on the required glass profile, the dotted curve is a reconstructed line R of the required mold profile, the square solid point is a predicted discrete point of the required mold profile, i.e., an optimized discrete point in the following description, and the straight line between the discrete point and the dotted curve is a distance between the discrete point and the reconstructed line R.

a. Obtaining the highest point x on the optimization line _mid The highest point is the point with the maximum value of the optimization line in the z-axis direction; let peak x _mid A distance d from the corresponding reconstruction line R in the z-axis direction _mid ；

b. With the highest point x _mid As a center, highest point x on the optimization line _mid Evenly set up n position points x respectively in both sides, position point x is in proper order: x is the number of _{left_1} ，x _{left_2} ，…，x _{left_n} ，x _{right_1} ，x _{right_2} ，…，x _{right_n} (ii) a Let the distance between the position point x and the reconstruction line R in the z-axis direction be d _{left_1} ，d _{left_2} ，…，d _{left_n} ，d _{right_1} ，d _{right_2} ，…，d _{right_n} ；

c. Will d _{left_1} ，d _{left_2} ，…，d _{left_n} ，d _{right_1} ，d _{right_2} ，…，d _{right_n}

As a design variable;

d. the following constraint conditions are set for the values of the design variables:

d _{left_i} -d _mid ≤0(i＝1,2,…,n)

d _{right_i} -d _mid ≤0(i＝1,2,…,n)

0<d _{left_i+1} -d _{left_i} <d _{left_i} -d _{left_i-1}

d _{right_i} -d _{right_i-1} <d _{right_i+1} -d _{right_i} <0

e. all discrete points on the optimization line are acquired.

f. And obtaining discrete points corresponding to the discrete points on the required mould profile and the optimized line, and using the discrete points as the optimized discrete points corresponding to the reconstruction line R.

g. Adopting NSGA3 algorithm, taking the minimum average distance between the reconstruction line R and the corresponding optimization discrete point as an optimization target, and calculating the final value of each design variable according to constraint conditions, namely the highest point x on the optimization line _mid And 2n distance between the position point x and the corresponding reconstruction line R in the z-axis direction.

Acquiring the highest point x under a coordinate system corresponding to the required glass molded surface _mid And the coordinates of 2n location points x.

Respectively putting the highest point x _mid And adding the z-direction value in the 2n position point coordinates and the corresponding design variable value to obtain the coordinates of 2n +1 points, taking the 2n +1 points as reconstruction points on a reconstruction line R, and generating an initial reconstruction line by using the coordinates of all the reconstruction points.

GA (genetic algorithm) in NSGA3 is a genetic algorithm, and its principle is to simulate the biological evolution, and the process of simulating the biological evolution has two important parameters, population size and iteration number: wherein the population scale is the number of organisms in the population, the number of schemes is in the optimization process of the practical problem, and the number of the schemes in each generation of the genetic algorithm is the population scale; the times of biological propagation evolution are iterative algebra, and in the optimization process of practical problems, the times of generating filial generation populations by genetic operation (crossing and mutation) of population species are obtained.

The population size and the number of iterations are set before solving the optimization problem, wherein the population size is set to 500 and the number of iterations is set to 150.

h. And connecting the initial reconstruction line with the edge line corresponding to the optimization line to form a complete reconstruction line R.

Each optimization line is provided with two corresponding edge lines, and the optimization lines and the corresponding edge lines form a complete connecting line. And connecting the initial reconstruction line with the two edge lines corresponding to the optimization line to form a complete reconstruction line R.

The edge lines on the left side and the right side of the required glass molded surface are connected with the initial reconstruction line in consideration of the spatial overall continuity, and because the edge area of the required glass molded surface is completely attached to the edge area of the required mold molded surface in the actual production, the edge lines on the required glass molded surface can be smoothly connected with the initial reconstruction line.

According to the steps, each optimization line can obtain a corresponding reconstruction line R.

In an embodiment of the disclosure, a reconstruction line is preset when the first reconstruction line R is obtained, and in a specific embodiment of the disclosure, a preset number of discrete points may be arbitrarily selected from all optimized discrete points corresponding to the first reconstruction line, and a curve is formed according to the preset number of discrete points, and the curve is used as the preset reconstruction line. On the basis of the preset reconstruction line, obtaining a first reconstruction line R according to a constraint condition by adopting an NSGA3 algorithm and taking the minimum average distance between the reconstruction line R and the corresponding optimized discrete point as an optimization target;

and when other reconstruction lines R are reconstructed, respectively setting preset reconstruction lines according to the previous reconstruction line of the reconstruction lines R, and obtaining the reconstruction lines R according to the constraint conditions and the NSGA3 algorithm on the basis of the preset reconstruction lines. For example, when reconstructing the second reconstruction line, the second reconstruction line is obtained by translating the first reconstruction line in the y-axis direction based on the already reconstructed first reconstruction line, and then using the translated first reconstruction line as a preset reconstruction line, where the distance of translation is the distance between the corresponding connection lines in the y-axis direction.

Step S109: and establishing the molded surface of the required mold by adopting a geometric modeling engine based on the plurality of reconstruction lines.

And (4) performing curved surface reconstruction on all reconstruction lines by using the existing geometric modeling engine to construct a final required mold profile.

Fig. 8 is a schematic structural diagram of a device for designing a profile of an automobile windshield mold, which is applied to generate a required mold profile according to a required glass profile. As shown in fig. 8, the apparatus includes the following units:

a glass-profile and mold-profile obtaining unit 11 configured to obtain a plurality of sets of profiles from a historical design plan, each set of profiles including one glass profile and a corresponding one mold profile;

a glass profile discrete point data obtaining unit 12 configured to extract discrete points of each glass profile, respectively, and obtain geometric feature data of each discrete point;

a distance acquisition unit 13 configured to acquire a distance of each discrete point to the corresponding mold profile;

the mapping model establishing unit 14 is configured to establish a mapping model according to the geometric characteristic data of all the discrete points and the distances from the discrete points to the corresponding mold surfaces, wherein the input variable of the mapping model is the geometric characteristic of the discrete points, and the output variable is the distance from the discrete points to the corresponding mold surfaces;

the glass profile discrete point data acquisition unit 12 is further configured to extract discrete points of a required glass profile and acquire geometric feature data of each discrete point;

a distance prediction unit 15 configured to predict a distance from each discrete point on the demand glass profile to the demand mold profile according to the geometric feature data of the discrete points of the demand glass profile and the mapping model;

a discrete point coordinate obtaining unit 16, configured to obtain the coordinates of the discrete points of the demand mold surface according to the geometric feature data of the discrete points of the demand glass surface and the predicted distance from the discrete points of the demand glass surface to the demand mold surface;

a reconstruction line obtaining unit 17 configured to obtain a plurality of reconstruction lines using the coordinates of the discrete points of the required mold surface, each reconstruction line having a minimum average distance from the discrete point of the corresponding required mold surface;

a demand mold profile establishing unit 18 configured to establish a profile of the demand mold using the geometry modeling engine based on the plurality of reconstruction lines.

It will be understood that the above embodiments are merely exemplary embodiments taken to illustrate the principles of the present invention, which is not limited thereto. It will be apparent to those skilled in the art that various modifications and improvements can be made without departing from the spirit and scope of the invention, and such modifications and improvements are also considered to be within the scope of the invention.

Claims

1. The utility model provides an automobile windshield mould profile design method based on curved surface reconsitution, is applied to and generates demand mould profile according to demand glass profile, its characterized in that includes:

respectively extracting discrete points of each glass molded surface, and acquiring geometric characteristic data of each discrete point;

extracting discrete points of a required glass profile, and acquiring geometric characteristic data of each discrete point;

2. The method according to claim 1, wherein said separately extracting discrete points of each glass profile and obtaining geometric feature data for each of said discrete points comprises:

for each glass profile, discrete points are extracted as follows:

determining a minimum bounding box of the glass profile;

respectively carrying out p +1 equal division on the upper boundary line and the lower boundary line, and connecting corresponding equal division points on the upper boundary line and the lower boundary line to obtain p equal division lines;

3. The method of claim 2, wherein separately extracting discrete points of each glass profile and obtaining geometric feature data for each of the discrete points, further comprises:

And obtaining a normal vector N by cross multiplication of tangent vectors: n = S _x ×S _y ；

(3) For each discrete point, the average curvature H is obtained as follows:

(4) For each discrete point, a gaussian curvature K is obtained as follows:

K＝k ₁ *k ₂

AH＝Dist(P，l _i )，P∈l _i '，i＝1，2，…p

wherein the discrete points P are on the intersecting line l _i ' Upper, l _i Is a reaction of _i ' corresponding bisector.

4. The method of claim 3, wherein said obtaining a distance of each discrete point to a corresponding mold profile comprises:

5. The method of claim 4, wherein said creating a mapping model from the geometric feature data of all discrete points and the distances of the discrete points to the corresponding mold surface comprises:

preprocessing normal vectors, average curvatures, gaussian curvatures and arch heights of all discrete points by a Robust Normalization (robustnormalization);

constructing a data set by utilizing the preprocessed discrete point geometric characteristic data and the distance from the discrete point to the corresponding mould surface in the z-axis direction, wherein the coordinate, the normal vector, the average curvature, the Gaussian curvature and the arch height of the discrete point are used as input variables of the data set, and the distance from the discrete point to the corresponding mould surface in the z-axis direction is used as an output variable of the data set;

6. The method of claim 5, wherein the preprocessing of the coordinates of all the discrete points by MinMax normalization comprises:

7. The method according to claim 5, wherein the preprocessing of the normal vector, the mean curvature, the Gaussian curvature and the arch height of all discrete points is performed by using a Robust normalization method, and comprises:

8. The method of claim 5, wherein said creating a mapping model from the geometric feature data of all discrete points and the distances of the discrete points to the corresponding mold surface comprises:

constructing a training data set by using the geometrical characteristic data of the discrete points preprocessed by the training glass molded surface and the distance from the discrete points on the training glass molded surface to the corresponding mold molded surface in the z-axis direction, wherein the coordinates, normal vectors, average curvatures, gaussian curvatures and arch heights of the discrete points are used as input variables, and the distance from the discrete points to the corresponding mold molded surface in the z-axis direction is used as an output variable;

9. The method of claim 8, wherein said extracting discrete points of a desired glass profile and obtaining geometric feature data for each of said discrete points comprises:

determining a minimum bounding box of the required glass profile;

establishing a three-dimensional coordinate system of the required glass profile by taking the central point of the minimum bounding box as an origin, wherein the x axis of the coordinate system is parallel to the longest edge of the minimum bounding box, and the z axis of the coordinate system is parallel to the shortest edge of the minimum bounding box;

10. The method of claim 9, wherein predicting the distance of each discrete point on the desired glass profile from the desired mold profile based on the geometric characteristic data of the discrete points of the desired glass profile and the mapping model comprises:

preprocessing normal vectors, average curvatures, gaussian curvatures and arch heights of all discrete points on the required glass profile in a Robust normalization mode;

substituting the geometric characteristic data of all discrete points on the preprocessed required glass molded surface into the regression model, and calculating to obtain a predicted value of the distance from each discrete point on the required glass molded surface to the required mold molded surface in the z-axis direction;

11. The method according to claim 10, wherein obtaining the coordinates of the discrete points of the desired mold surface based on the geometric feature data of the discrete points of the desired glass surface and the predicted distance from the discrete points of the desired glass surface to the desired mold surface comprises:

x′ _i ＝x _i

y′ _i ＝y _i

z′ _i ＝z _i +d _i

wherein: (x) _i ，y _i ，z _i ) Coordinates of discrete points of the required mould surface are obtained; (x) _i ，y _i ，z _i ) The coordinates of the corresponding discrete points on the required glass molded surface are obtained; d _i The distance in the z-axis direction from the corresponding discrete point on the predicted desired glass profile to the desired mold profile.

12. The method of claim 11, wherein said obtaining a plurality of lines of reconstruction using coordinates of discrete points of a desired mold surface comprises:

acquiring a projection area of the optimization area on a required glass molded surface;

according to the projection area, dividing a connecting line obtained when the discrete point of the required glass profile is extracted into an optimized line and an edge line, wherein the optimized line is a part of the connecting line located in the projection area, and the edge line is a part of the connecting line located outside the projection area;

With the highest point x _mid Centered at the highest point x on the optimization line _mid Evenly set up n position points x respectively in both sides, position point x is in proper order: x is the number of _{left_1} ，x _{left_2} ，...，x _{left_n} ，x _{right_1} ，x _{right_2} ，...，x _{right_n} (ii) a Let the distance between the position point x and the reconstruction line R in the z-axis direction be d _{left_1} ，d _{ieft_2} ，...，d _{left_n} ，d _{right_1} ，d _{right_2} ，...，d _{right_n} ；

Will d _{left_1} ，d _{left_2} ，...，d _{left_n} ，d _{right_1} ，d _{right_2} ，...，d _{right_n} As a design variable;

d _{left_i} -d _mid ≤0(i＝1，2，...，n)

d _{right_i} -d _mid ≤0(i＝1，2，...，n)

0＜d _{left_i+1} -d _{left_i} ＜d _{left_i} -d _{left_i-1}

d _{right_i} -d _{right_i-1} ＜d _{right_i+1} -d _{right_i} ＜0

acquiring all discrete points on the optimization line;

obtaining discrete points of the required mould profile corresponding to the discrete points on the optimization line, and taking the discrete points as the optimized discrete points corresponding to the reconstruction line R;

13. The method of claim 12, wherein said obtaining a plurality of lines of reconstruction using coordinates of discrete points of a desired mold surface further comprises:

and when other reconstruction lines R are obtained, respectively setting a preset reconstruction line according to the previous reconstruction line of the reconstruction lines R, and obtaining the reconstruction lines R based on the preset reconstruction line according to a constraint condition and an NSGA3 algorithm.

14. The utility model provides an automobile windshield mould profile design device based on curved surface reconsitution, is applied to and generates demand mould profile according to demand glass profile, a serial communication port, includes:

the distance prediction unit is used for predicting the distance from each discrete point on the required glass molded surface to the required mold molded surface according to the geometric characteristic data of the discrete points of the required glass molded surface and the mapping model;