KR20240052175A - Method for recognizing machining feature and computing device for executing the method - Google Patents

Abstract

A machining feature recognition method and a computing device for performing the same are disclosed. A machining feature recognition method according to an embodiment disclosed is a method performed on a computing device having one or more processors and a memory storing one or more programs executed by the one or more processors, wherein the machining and Obtaining a related 3D model, selecting one target face among the faces constituting the 3D model, creating a descriptor including a plurality of items preset for the selected target face, and descriptors and techniques for the target face. It includes calculating the degree of similarity between technicians with respect to the reference surfaces of the set feature shape types.

Description

Machining feature recognition method and computing device for performing the same {METHOD FOR RECOGNIZING MACHINING FEATURE AND COMPUTING DEVICE FOR EXECUTING THE METHOD}

Embodiments of the present invention relate to machining feature recognition technology.

Machining features refer to specific shapes created by cutting by a machine tool in the process of manufacturing parts. Representative shapes include holes, pockets, slots, and fillets. Machining feature recognition refers to the act of recognizing features from a 3D (three dimensional) CAD (computer-aided design) model of a part. Machining feature recognition is used in many application fields such as product manufacturability evaluation, process planning, and tool path generation.

Common methods for recognizing machining features include graph-based methods, volume decomposition methods, and hint-based methods. However, existing methods have problems in that the recognition time takes a long time because the algorithm for recognizing machining features is complex, and the success rate in recognizing complex shapes or shapes that intersect each other even if not complex is low.

Domestic Registered Patent Publication No. 10-0567398 (2006.04.07)

The purpose of the present invention is to provide a machining feature recognition method that can improve the recognition performance of machining feature shapes and a computing device for performing the same.

Meanwhile, the technical problems to be achieved in the present invention are not limited to the technical problems mentioned above, and other technical problems not mentioned will be clearly apparent to those skilled in the art from the description below. It will be understandable.

A machining feature recognition method according to an embodiment disclosed is a method performed on a computing device having one or more processors and a memory storing one or more programs executed by the one or more processors, Obtaining a 3D model related to; selecting one target face among the faces constituting the 3D model and generating a descriptor including a plurality of preset items for the selected target face; and calculating similarities between descriptors for the target surface and descriptors for reference surfaces of preset feature shape types.

The descriptor includes face information, outer loop information, inner loop information, and auxiliary information, and the face information includes among face type items, curvature items, face-machining items, fillet-machining items, and chamfer-machining items. The outer loop information and the inner loop information include one or more of a convexity item, a continuity item, a parallel axis item, an acute angle item, a right angle item, and an obtuse angle item, and the auxiliary information includes a parallel plane item. , co-axial terms, and interference surface terms.

The items of the descriptor may include values subject to range constraints including one or more of a minimum constraint, a maximum constraint, and an equality constraint.

The minimum constraint condition refers to the lower limit of the value that the descriptor item can have, and the maximum constraint condition refers to the upper limit of the value that the descriptor item can have. The same constraint condition refers to the lower limit of the value that the descriptor item can have. It may mean a specific value that must be possessed.

The step of calculating the similarity includes calculating the similarity according to the minimum constraint condition, the similarity according to the maximum constraint condition, and the similarity according to the same constraint condition for each item of the descriptor for the target surface and the descriptor for the reference surface. It may include steps.

The calculating the similarity may include calculating the similarity for each descriptor item based on the similarity according to the minimum constraint condition, the similarity according to the maximum constraint condition, and the similarity according to the same constraint condition; And it may include calculating a final similarity between the technician for the target surface and the technician for the reference surface by adding up the similarities for each technician item for the target surface and the reference surface.

In the step of calculating the final similarity, weights may be assigned to each of the description items, and then the similarities of each of the description items may be summed.

The machining feature recognition method may further include determining that the selected target surface is a reference surface of the feature shape type to be compared when the calculated similarity is greater than or equal to a preset threshold value.

The machining feature recognition method may further include, when the 3D model includes a composite feature shape, recognizing the composite feature shape with priority over the single feature shape.

A computing device according to one disclosed embodiment includes one or more processors; Memory; and one or more programs, wherein the one or more programs are stored in the memory and configured to be executed by the one or more processors, wherein the one or more programs include: instructions for obtaining a 3D model related to machining; A command for selecting one target face among the faces constituting the 3D model and creating a descriptor including a plurality of preset items for the selected target face; and instructions for calculating the degree of similarity between descriptors for the target surface and descriptors for reference surfaces of preset feature shape types.

According to the disclosed embodiment, the descriptor is set for the reference surface of the feature, the descriptor is expanded by reflecting the range constraints, and the feature is recognized based on this descriptor, thereby speeding up the recognition of the feature and recognizing the feature. Performance can be improved.

Meanwhile, the effects that can be obtained from the present invention are not limited to the effects mentioned above, and other effects not mentioned will be clearly understood by those skilled in the art from the description below. You will be able to.

1 is a diagram showing a feature type according to an embodiment of the present invention,
Figure 2 is a diagram for explaining the process of calculating convexity in an embodiment of the present invention;
Figure 3 is a diagram showing a descriptor for the reference surface of the open island feature shape in one embodiment of the present invention,
Figure 4 is a diagram showing the types of values that a technician can have for each item regarding the reference surface of a feature shape in one embodiment of the present invention;
Figure 5 is a diagram showing a state in which a descriptor is expanded by applying a range constraint condition in one embodiment of the present invention;
6 is a block diagram illustrating and illustrating a computing environment including a computing device suitable for use in example embodiments;
Figure 7 is a flowchart showing a machining feature shape recognition method according to an embodiment of the present invention;
Figure 8 is a diagram showing the process of comparing a descriptor for a target surface of a 3D model and a descriptor for a reference surface of a feature shape type in one embodiment of the present invention;
Figure 9 is a diagram showing a complex feature shape in one embodiment of the present invention.

Hereinafter, embodiments of the present invention will be described in more detail with reference to the attached drawings. Embodiments of the present invention may be modified in various forms, and the scope of the present invention should not be construed as being limited to the following embodiments. This example is provided to more completely explain the present invention to those skilled in the art. Therefore, the shapes of elements in the drawings are exaggerated to emphasize clearer explanation.

The configuration of the invention to clarify the solution to the problem to be solved by the present invention will be described in detail with reference to the accompanying drawings based on preferred embodiments of the present invention, and the reference numbers to the components in the drawings will be the same. Components are given the same reference numbers even if they are in different drawings, and it is stated in advance that components of other drawings can be cited when necessary when explaining the relevant drawings.

In the disclosed embodiment, machining may include turning, milling, and drilling. And, the feature types used in such machining can be classified into 16 types as shown in FIG. 1. Referring to Figure 1, the feature shape types include 5 types of hole-related feature shapes (Simple hole, Counter sink hole, Counter bore hole, Counter drilled hole, Taper hole), 2 types of Slot-related feature shapes (Simple slot, Floorless slot), 3 types of Pocket-related feature shapes (Closed pocket, Opened pocket, Floorless pocket), 2 types of Island-related feature shapes (Closed island, Opened island), 2 types of Filet-related feature shapes (Inner fillet, Outer fillet), and Chamfer-related feature shapes. It may include 2 types (Inner chamfer, Outer chamfer).

In the disclosed embodiment, a base face may be defined for each feature type. The reference surface refers to the side that can best represent the characteristics of the machining feature among several surfaces that make up the machining feature. At this time, the characteristics of the machining features may include machining type, machining shape, and machining parameters.

In the case of a hole, the reference surface may vary depending on whether two or more different rotational shapes are combined. For example, for simple holes and taper holes consisting of only a single rotational shape, the side surface (cylindrical face or conical face) of the hole shape can be selected as the reference surface. For counter bore holes, counter sink holes, and counter drilled holes consisting of two or more different rotational shapes, any surface other than the cylindrical face can be selected as the reference surface.

In the case of slots and pockets, the bottom surface or the side surface can be selected as the reference surface depending on the presence or absence of the bottom surface. In the case of an island, the bottom surface can be selected as the reference surface. For fillets and chamfers, a cylindrical surface or a flat surface can be selected as the reference surface. In Figure 1, the base face for each feature type is indicated by arrows and pink.

Meanwhile, each face that makes up the 3D model contains information about the face itself, information about the edges that make up the face, information about the vertices that make up the edge, and relationship information about adjacent faces. It can be included.

Here, information about the face itself may include the type of the face (eg, planar type, cylindrical face, toroidal face, etc.), normal vector, and loop (inner loop or outer loop, etc.) information. Edge information may include information about the type of line (linear type, curved type, etc.) and the length of the line. Information about a vertex may include coordinate information about the vertex. Relationship information about adjacent faces may include angle, convexity, and continuity between the face and the face adjacent to the face. Continuity can be divided into several grades (e.g., C0, G1, C1, G2, C2) depending on the tangency and curvature between two adjacent faces.

In the disclosed embodiment, a descriptor may be defined to recognize machining features. The descriptor may refer to a data structure that expresses information about the target surface to be recognized and relationship information between the target surface and adjacent elements. The information expressed by the technician may largely include target surface information, outer loop information, inner loop information, and auxiliary information.

Target surface information may include surface type items, curvature items, face-machining items, fillet-machining items, and chamfer-machining items. Surface type items can be divided into planar, cylindrical, conical, spherical, and toroidal. The name of each side type can be expressed as PLAN, CYLI, CONI, SPHE, and TORO by taking the previous four letters. If the type of face is not specified, it can be expressed as ANY.

Curvature items can be classified as convex, flat, or concave depending on the curvature of the relevant surface. These can be expressed as Positive, Flat, and Negative, respectively.

The Face-machining item is for distinguishing between Slot and Pocket. The face-machining item refers to a pair of parallel faces (F ₁ and After extracting F ₂ ) and finding the width of F ₁ and F _{2 ,} it can be compared to the value entered by the user. If it is longer than the value entered by the user, it can be expressed as Longer, and if it is shorter than the value entered by the user, it can be expressed as Shorter. . If there is no parallel surface among the adjacent surfaces in contact with the outer loop of the relevant surface, it can be expressed as Longer.

The Fillet-machining item is an item to distinguish fillet from other feature shapes. The chamfer-machining item is an item to distinguish chamfer from other feature shapes. Fillet-machining and chamfer-machining items can be expressed as Longer if they are longer than the value entered by the user after finding the shortest width on the target surface, and expressed as Shorter if it is shorter than the value entered by the user. there is. If the type of target surface is a rotational surface such as cylindrical, spherical, and toroidal, this value can be set to the radius of the target surface.

Among the information included in the descriptor, loop information such as outer loop information and inner loop information may include convexity items, continuity items, parallel axis items, acute angle items, right angle items, and obtuse angle items.

Here, the convexity item may refer to the convexity between the relevant surface (target surface) and the adjacent surface. Figure 2 is a diagram for explaining the process of calculating convexity in an embodiment of the present invention. Referring to Figure 2, when F _a and F _b are considered the corresponding surface and the adjacent surface, respectively, the normal vector of F _a and the normal vector of F _b Cross product the direction vector get And the coedge of F _a that touches F _b and By dot product, if the calculated value is a positive number, it is called convex, and if the calculated value is negative, it is called convex. After calculating convexity, the convexity item can be expressed by adding the type of face and the number of faces.

The continuity item may refer to the continuity between the relevant face and adjacent faces. Continuity can be divided into C0 and other continuities. Additionally, continuity items can be expressed only for adjacent surfaces whose continuity is not CO.

The parallel axis item may indicate whether the reference vector (V1) of the target surface and the reference vector (V2) of the adjacent surface are parallel. Here, the reference vector can be an axis vector if the target surface is a rotating surface, and can be a normal vector at the center of the surface if the target surface is a non-rotating surface.

The acute angle item, the right angle item, and the obtuse angle item may refer to the angle formed between the reference vector (V1) of the target surface and the reference vector (V2) of the adjacent surface.

Among the information included in the descriptor, auxiliary information may include parallel plane items, co-axis items, and interference surface items. Here, the parallel plane item may indicate whether adjacent planes in contact with the outer loop of the plane are parallel. At this time, if a pair of adjacent surfaces parallel to each other exists, it can be expressed as True, otherwise, it can be expressed as False.

The same axis item indicates whether the adjacent face (F1) that is in contact with the outer loop of the face and the adjacent face (F2) that is in contact with the inner loop are rotation faces and whether the axes of the adjacent face (F1) and the adjacent face (F2) are the same. You can. If the axes of the adjacent surface (F1) and the adjacent surface (F2) are the same, it can be expressed as True; otherwise, it can be expressed as False.

The interference surface item can indicate whether another surface exists in the normal direction of the corresponding surface (target surface). To do this, you can shoot a ray in the normal direction of that face and check whether the ray intersects another face. At this time, if the ray intersects another surface, it can be expressed as True; otherwise, it can be expressed as False.

In the disclosed embodiment, a descriptor for a specific aspect of a 3D model can be expressed as shown in Table 1 below.

(Table 1)

Figure 3 is a diagram showing a descriptor for the reference surface of the open island feature shape in one embodiment of the present invention. Briefly, the face type (D _{f_facetype} ) of the reference surface of the open island feature shape is PLAN (Planar), and the curvature (D _{f_curve} ) can be expressed as FLAT. Additionally, the convexity item (D _{ol_convexity} ) in the outer loop is PLAN | CONCAVE: 3, PLAN | CONVEX: 1, CYLI | CONCAVE: Can be expressed in two ways. Additionally, looking at the parallel plane item (D _{ax_parallel} ), it can be expressed as the existence (True) of pairs parallel to each other on the plane adjacent to the reference plane.

Meanwhile, in the disclosed embodiment, the descriptor for the reference surface of the feature shape may have a range constraint condition. Figure 4 is a diagram showing the types of values that a technician can have for each item regarding the reference surface of a characteristic shape in an embodiment of the present invention. Referring to Figure 4, the technician has three cases of values (D _i , D _j , D _k ). The first is a case where the value of the descriptor, such as D _i, must be between the lower limit (V _min ) and the upper limit (V _max ). The second is a case where a descriptor must have a specific value, such as D _j . The third is a case where the descriptor must have a value above a certain value (or below a certain value), such as D _k .

In this way, to consider all three cases, it is necessary to be able to describe range constraints such as minimum constraints, maximum constraints, and equality constraints for each item of the descriptor for the feature reference surface. Here, the minimum constraint condition may mean the lower limit of the value that each item of the descriptor can have. The maximum constraint may refer to the upper limit of the value that each item of the descriptor can have. The same constraint may mean a value that each item of the descriptor must have.

For example, the descriptor item for the target surface and the descriptor item for auxiliary information have values corresponding to the same constraint conditions. And, descriptor items related to the outer loop and inner loop have values corresponding to the minimum and maximum constraints. Therefore, it is necessary to expand the descriptor by applying these range constraints to the descriptor. Figure 5 is a diagram showing a state in which a descriptor is expanded by applying a range constraint condition in one embodiment of the present invention. Figure 5 shows the state in which the descriptor is expanded by considering the range constraints (Minimum, Maximum, and Equal) for the reference surface of the arbitrary feature shape of the 3D model. .

FIG. 6 is a block diagram illustrating and illustrating a computing environment 10 including computing devices suitable for use in example embodiments. In the illustrated embodiment, each component may have different functions and capabilities in addition to those described below, and may include additional components in addition to those described below.

The illustrated computing environment 10 includes a computing device 12 . In one embodiment, computing device 12 may be a device for recognizing machining features.

Computing device 12 includes at least one processor 14, a computer-readable storage medium 16, and a communication bus 18. Processor 14 may cause computing device 12 to operate in accordance with the example embodiments noted above. For example, processor 14 may execute one or more programs stored on computer-readable storage medium 16. The one or more programs may include one or more computer-executable instructions, which, when executed by the processor 14, cause computing device 12 to perform operations according to example embodiments. It can be.

Computer-readable storage medium 16 is configured to store computer-executable instructions or program code, program data, and/or other suitable form of information. The program 20 stored in the computer-readable storage medium 16 includes a set of instructions executable by the processor 14. In one embodiment, computer-readable storage medium 16 includes memory (volatile memory, such as random access memory, non-volatile memory, or an appropriate combination thereof), one or more magnetic disk storage devices, optical disk storage devices, flash It may be memory devices, another form of storage medium that can be accessed by computing device 12 and store desired information, or a suitable combination thereof.

Communication bus 18 interconnects various other components of computing device 12, including processor 14 and computer-readable storage medium 16.

Computing device 12 may also include one or more input/output interfaces 22 and one or more network communication interfaces 26 that provide an interface for one or more input/output devices 24. The input/output interface 22 and the network communication interface 26 are connected to the communication bus 18. Input/output device 24 may be coupled to other components of computing device 12 through input/output interface 22. Exemplary input/output devices 24 include, but are not limited to, a pointing device (such as a mouse or trackpad), a keyboard, a touch input device (such as a touchpad or touch screen), a voice or sound input device, various types of sensor devices, and/or imaging devices. It may include input devices and/or output devices such as display devices, printers, speakers, and/or network cards. The exemplary input/output device 24 may be included within the computing device 12 as a component constituting the computing device 12, or may be connected to the computing device 12 as a separate device distinct from the computing device 12. It may be possible.

Figure 7 is a flowchart showing a machining feature shape recognition method according to an embodiment of the present invention. The machining feature shape recognition method may be performed by computing device 12 . In the illustrated flow chart, the method is divided into a plurality of steps, but at least some of the steps are performed in a different order, combined with other steps, omitted, divided into detailed steps, or not shown. One or more steps may be added and performed.

Referring to FIG. 7, the computing device 12 may acquire a 3D model for recognizing machining features (S 101). For example, computing device 12 may obtain a 3D model from a 3D CAD system, but is not limited thereto. The 3D model may be a 3D model in B-rep (Boundary representation) format.

Next, the computing device 12 may analyze the 3D model to obtain information on the surfaces constituting the 3D model (S 103). Information on the faces that make up the 3D model includes information on the face itself, information on the edges that make up the face, information on the vertices that make up the edge, and relationship information on adjacent faces. can do.

Next, the computing device 12 may select one target face among the faces constituting the 3D model and create a descriptor for the selected target face (S 105). Here, the descriptor for the target surface may include target surface information, outer loop information, inner loop information, and auxiliary information.

Target surface information included in the descriptor may include surface type items, curvature items, face-machining items, fillet-machining items, and chamfer-machining items. Loop information such as outer loop information and inner loop information included in the descriptor may include convexity terms, continuity terms, parallel axis terms, acute angle terms, right angle terms, and obtuse angle terms. Auxiliary information included in the descriptor may include parallel plane items, co-axial items, and interference surface items. The computing device 12 may generate a descriptor having the items shown in Table 1 for the selected target surface.

Next, the computing device 12 may compare the similarity between the descriptors for the selected target surface and the descriptors for the reference surfaces of preset feature shape types (S 107).

Here, the preset feature shape type may include 16 types as shown in FIG. 1. A reference surface may be set for each feature shape type. Additionally, a descriptor may be created and stored in advance on the reference surface of each feature shape type. A detailed description of the similarity comparison between the descriptor for the target surface and the descriptor for the reference surface of the preset feature shape type will be described later.

Next, as a result of the comparison in step S 107, if the similarity is greater than or equal to a preset threshold, the computing device 12 may determine the selected target surface as the reference surface for the feature shape (S 109).

That is, when comparing the similarity between the descriptor for the selected target surface and the descriptor for the reference surfaces of the preset feature shape types, if the similarity value is more than the preset threshold value, the selected target surface is compared to the reference surface of the feature type being compared. It can be judged that it is. In this case, recognition of the feature shape may be terminated.

As a result of the comparison in step S 107, if the similarity is less than a preset threshold, the computing device 12 selects another target surface from the 3D model to generate a descriptor and then compares the similarity with the descriptors for the reference surfaces of the preset feature shape types. The process of comparing can be repeated.

Hereinafter, a comparison of similarity between a descriptor for the target surface and a descriptor for a reference surface of a preset feature shape type will be described. The reference plane of the feature shape is , the target surface you want to compare and the descriptor item for the reference surface of the feature shape is , Enter the descriptive items for the target surface you wish to compare. It is said. Here, k may mean the descriptor item name defined in Table 1. And, the descriptor item of the reference plane According to three range constraints (minimum constraint, maximum constraint, and equality constraint) , , It can be further divided into

Computing device 12 has two sides ( , ), first, for each descriptor item (), the similarity ( ), similarity according to maximum constraints ( ), and similarity according to the same constraint ( ) can be calculated respectively. Table 2 is a table showing calculation of similarity for descriptor items according to range constraints in one embodiment of the present invention.

(Table 2)

The computing device 12 calculates the similarity according to the minimum constraints, as shown in Equation 1 ( ), similarity according to maximum constraints ( ), and similarity according to the same constraint ( ) to _obtain the similarity ( ) can be calculated.

(Equation 1)

The computing device 12 sums the similarities for each descriptor item and adds the two sides ( , ) can be calculated. At this time, the computing device 12 may assign a weight to each descriptor item. The sum of each weight can be 1. The computing device 12 has two sides ( , ) can be calculated.

(Equation 2)

W _k : weight for descriptor item k

If there is no value of a specific descriptor item in the descriptor for the reference surface of the feature shape type, the computing device 12 may exclude the corresponding descriptor item from the similarity calculation. At this time, the sum of the weights of the remaining descriptor items minus the excluded descriptor items can be set to 1.

Figure 8 is a diagram illustrating a process of comparing a descriptor for a target surface of a 3D model and a descriptor for a reference surface of a feature shape type in one embodiment of the present invention. Here, in order to search the reference surface of the counter hole included in the 3D model, a descriptor for the reference surface of the counter hole ( ) and a descriptor for the target surface ( ) shows the process of comparing. Descriptor for the reference surface of the counter hole ( ) has only 3, 1, and 3 descriptor items in the minimum constraint, maximum constraint, and identical constraints, respectively, so similarity can be calculated for a total of 7 descriptor items.

Figure 8 (a) shows descriptor items considering the range constraints for the reference surface of the counter hole, Figure 8 (b) shows descriptor items for the target surface of the 3D model, and Figure 8 (c) shows the similarity of each descriptor item according to the range constraints, and Figure 8 (d) shows the final similarity between the descriptor for the reference surface and the descriptor for the target surface.

Specifically, the feature reference plane of is PLAN and target plane of is PLAN. Since the values of the two descriptor items have the same value, the similarity becomes 1. however class Since no value is given, and becomes 1. Similarity according to each range constraint , , When multiplied by , the similarity of the corresponding descriptor item is becomes 1. in the same way Similarity according to each range constraint of the descriptor item of , , are each 1, and multiplying them gives the similarity of the corresponding descriptor item. becomes 1.

Descriptor item of loop information Looking at it, the feature shape reference plane of is ANY | CONCAVE: 1. And, the target surface of silver CYLI | CONCAVE: 2 and PLAN | CONVEX: 1. From here, go Because it contains the value of go You can see that it is bigger than . Therefore, the similarity becomes 1. however and Since no value is given, and becomes 1. Rest of the technician items in the same way , and Similarity of , , are each 1.

Looking at the description item in the auxiliary information, the feature reference plane of is TRUE. And, the target surface of is TRUE. Since the values of the two descriptors have the same value, the similarity becomes 1. however class Since no value is given, and becomes 1. Here, each similarity , , Multiplying the descriptor item similarity becomes 1. In this way, as the similarity calculation for all range constraints is completed, the similarity for each descriptor item Calculate . After that, the similarity for each descriptor item The final similarity R is calculated by reflecting the weights on the values.

Meanwhile, in order to accurately recognize a complex feature shape that can be expressed as a set of several feature shapes, it is necessary to apply priority to the recognition process. Figure 9 is a diagram showing a complex feature shape in one embodiment of the present invention. Referring to FIG. 9, complex feature shapes may include counterbore holes, counterdrilled holes, and countersink holes.

Referring to Figure 9, a counterbore hole is made up of a combination of two simple holes, a counterdrilled hole is made up of a combination of two simple holes and one taper hole, and a countersink hole is made up of one taper hole and one simple hole. It can be done in combination.

For example, since a counterbore hole is made up of a combination of two simple holes, when the feature shape is recognized through descriptor-based similarity comparison, not only the counterbore hole but also the simple hole may be recognized as duplicates at the same location. Accordingly, recognition priority may be applied to complex feature shapes before general feature shapes (i.e., single feature shapes).

According to the disclosed embodiment, the descriptor is set for the reference surface of the feature, the descriptor is expanded by reflecting the range constraints, and the feature is recognized based on this descriptor, thereby speeding up the recognition of the feature and recognizing the feature. Performance can be improved.

The above detailed description is illustrative of the present invention. Additionally, the foregoing is intended to illustrate preferred embodiments of the present invention, and the present invention can be used in various other combinations, modifications, and environments. That is, changes or modifications are possible within the scope of the inventive concept disclosed in this specification, the scope equivalent to the written disclosure, and/or the technology or knowledge in the art. The written examples illustrate the best state for implementing the technical idea of the present invention, and various changes required for specific application fields and uses of the present invention are also possible. Accordingly, the detailed description of the invention above is not intended to limit the invention to the disclosed embodiments. Additionally, the appended claims should be construed to include other embodiments as well.

10: Computing environment
12: Computing device
14: processor
16: computer-readable storage medium
18: communication bus
20: Program
22: input/output interface
24: input/output device
26: Network communication interface

Claims (19)

one or more processors, and
A method performed on a computing device having a memory storing one or more programs executed by the one or more processors, comprising:
Obtaining a 3D model related to machining;
selecting one target face among the faces constituting the 3D model and generating a descriptor including a plurality of preset items for the selected target face; and
A machining feature recognition method comprising calculating a degree of similarity between technicians for the target surface and technicians for reference surfaces of preset feature shape types.
In claim 1,
The technician said,
Contains face information, outer loop information, inner loop information, and auxiliary information,
The surface information includes one or more of a surface type item, a curvature item, a face-machining item, a fillet-machining item, and a chamfer-machining item,
The outer loop information and the inner loop information include one or more of a convexity term, a continuity term, a parallel axis term, an acute angle term, a right angle term, and an obtuse angle term,
The auxiliary information includes one or more of a parallel plane item, a co-axial item, and an interference surface item.
In claim 2,
The items of the above technician are:
A method for recognizing machining features, comprising values subject to range constraints including one or more of a minimum constraint, a maximum constraint, and an equality constraint.
In claim 3,
The minimum constraint condition refers to the lower limit of the value that the descriptor item can have,
The maximum constraint condition refers to the upper limit of the value that the descriptor item can have,
The same constraint condition refers to a specific value that the technician's item must necessarily have.
In claim 4,
The step of calculating the similarity is,
Machining, including the step of calculating similarity according to the minimum constraint condition, similarity according to the maximum constraint condition, and similarity according to the same constraint condition for each item of the technician for the target surface and the technician for the reference surface, respectively. Feature recognition method.
In claim 5,
The step of calculating the similarity is,
calculating a similarity for each descriptor item based on the similarity according to the minimum constraint condition, the similarity according to the maximum constraint condition, and the similarity according to the same constraint condition; and
A machining feature recognition method comprising calculating a final similarity between a technician for the target surface and a technician for the reference surface by adding up the similarities for each technician item for the target surface and the reference surface.
In claim 6,
The step of calculating the final similarity is,
A machining feature recognition method that assigns weights to each of the descriptor items and then adds up the similarities for each of the descriptor items.
In claim 1,
The machining feature recognition method is,
If the calculated similarity is greater than or equal to a preset threshold, the machining feature recognition method further includes determining that the selected target surface is a reference surface of the feature type to be compared.
In claim 1,
The machining feature recognition method is,
When the 3D model includes a complex feature shape, the machining feature recognition method further includes the step of recognizing the complex feature shape in priority over the single feature shape.
one or more processors;
Memory; and
Contains one or more programs,
The one or more programs are stored in the memory and configured to be executed by the one or more processors,
The one or more programs above include:
Commands for obtaining 3D models related to machining;
A command for selecting one target face among the faces constituting the 3D model and creating a descriptor including a plurality of preset items for the selected target face; and
A computing device comprising instructions for calculating a degree of similarity between descriptors for the target surface and descriptors for reference surfaces of preset feature shape types.
In claim 10,
The technician said,
Contains face information, outer loop information, inner loop information, and auxiliary information,
The surface information includes one or more of a surface type item, a curvature item, a face-machining item, a fillet-machining item, and a chamfer-machining item,
The outer loop information and the inner loop information include one or more of a convexity term, a continuity term, a parallel axis term, an acute angle term, a right angle term, and an obtuse angle term,
The auxiliary information includes one or more of a parallel plane term, a coaxial plane term, and an interference plane term.
In claim 11,
The items of the above technician are:
A computing device comprising a value subject to a range constraint that includes one or more of a minimum constraint, a maximum constraint, and an equality constraint.
In claim 12,
The minimum constraint condition refers to the lower limit of the value that the descriptor item can have,
The maximum constraint condition refers to the upper limit of the value that the descriptor item can have,
The same constraint condition refers to a specific value that an item of a descriptor must necessarily have.
In claim 13,
The command for calculating the similarity is:
Computing, including instructions for calculating similarity according to the minimum constraint condition, similarity according to the maximum constraint condition, and similarity according to the same constraint condition for each item of the descriptor for the target surface and the descriptor for the reference surface. Device.
In claim 14,
The command for calculating the similarity is:
Commands for calculating a similarity for each descriptor item based on the similarity according to the minimum constraint condition, the similarity according to the maximum constraint condition, and the similarity according to the same constraint condition; and
A computing device comprising instructions for calculating a final similarity between a descriptor for the target surface and a descriptor for the reference surface by summing the similarities for each descriptor item for the target surface and the reference surface.
In claim 15,
The command for calculating the final similarity is:
A computing device that assigns weights to each of the descriptor items and then adds up the similarities for each of the descriptor items.
In claim 10,
The one or more programs above include:
When the calculated similarity is greater than or equal to a preset threshold, the computing device further includes instructions for determining that the selected target surface is a reference surface of the feature shape type to be compared.
In claim 10,
The one or more programs above include:
When the 3D model includes a complex feature shape, the computing device further includes instructions for recognizing the complex feature shape in preference to the single feature shape.
A computer program stored on a non-transitory computer readable storage medium,
The computer program includes one or more instructions that, when executed by a computing device having one or more processors, cause the computing device to:
Obtaining a 3D model related to machining;
selecting one target face among the faces constituting the 3D model and generating a descriptor including a plurality of preset items for the selected target face; and
A computer program that performs a step of calculating the degree of similarity between descriptors for the target surface and descriptors for reference surfaces of preset feature shape types.