Aircraft thin-walled mouth frame type part rapid identification method

Abstract

The application discloses a kind of aircraft thin-walled mouth frame class parts fast identification method, the size of the bounding box of part is calculated, the thickness of part is measured along the reference surface normal of maximum area reverse, whether the part model is thin-walled class part is judged by part thickness;Then further project in the projection direction of part model, to identify the inner closed loop structure and outer closed loop structure of part in projection face, the part model is initially screened by calculating the perimeter of closed loop structure and the relationship of perimeter threshold value, then the ratio of the area of outer closed loop structure and the area of inner closed loop, the shape consistency of outer closed loop structure and inner closed loop structure is calculated, and whether the part model is thin-walled mouth frame class part is further efficiently and accurately judged;The application uses image recognition, statistical method to identify the thickness of part model, projection image edge consistency and other typical features to realize the identification of part model, whether the part model is thin-walled mouth frame class part can be efficiently and accurately judged.

Description

TECHNICAL FIELD

[0001] The application belongs to the technical field of part identification, and particularly relates to a rapid identification method for an aircraft thin-wall mouth frame part. BACKGROUND

[0002] In the field of industrial design and manufacturing, the geometric shape of a part directly affects its manufacturing and assembly process. Thin-wall mouth frame parts have typical geometric characteristics of thin thickness, annular shape and hollow, and are usually used between the aircraft skin and the flap to assist in positioning the flap components with different shapes and functions, thereby realizing process design planning of the flap components. Traditional identification methods usually rely on manual judgment or simple keyword matching, which has the problems of low efficiency and large identification error. With the increasing complexity of aircraft design, the scale of three-dimensional models of parts is becoming larger and larger, and there is an urgent need for an efficient and accurate automatic identification method for thin-wall mouth frame parts.

[0003] For example, in the patent application "Aircraft skin part feature detection method (publication date: March 25, 2015, publication number: CN104462656A)", first, various skin processing features are defined, for each skin part, its ring characteristic graph and holographic attribute surface edge graph are constructed, and the seed surface of various features is searched. On this basis, based on the reverse surface identification surface, the seed surface and the expansion rule are searched, all set elements of various features are searched out, the skin processing features are constructed, and then the feature recognition result is obtained. However, this method needs to predefine the processing features, and can only identify the features such as milling processing features, and cannot effectively identify the global level geometric features such as thin-wall mouth frame parts.

[0004] Therefore, in view of the problems of low identification efficiency and insufficient identification accuracy in the existing technology for identifying thin-wall mouth frame parts, the application discloses a rapid identification method for an aircraft thin-wall mouth frame part. SUMMARY

[0005] The application discloses a rapid identification method for an aircraft thin-wall mouth frame part, which adopts image recognition and statistical method to identify the thickness, projection image edge consistency and other typical features of the part model, so as to identify the part model, and can efficiently and accurately judge whether the part model is a thin-wall mouth frame part.

[0006] The application is implemented by the following technical scheme:

[0007] A rapid identification method for an aircraft thin-wall mouth frame part, comprising the following steps:

[0008] Step 1, establishing an OBB bounding box of the part model, and extracting the length, width and height dimensions of the OBB bounding box;

[0009] Step 2, extracting the reference surface with the largest area on the part model, measuring the thickness of the part along the normal direction of the reference surface, judging whether the part is a thin-walled part, if it is judged as a thin-walled part, then go to step 3;

[0010] Step 3, projecting the part model according to the calibration direction, identifying the closed loop structure formed on the projection surface, and calculating the perimeters of all closed loop structures;

[0011] Step 4, setting a perimeter threshold, comparing the perimeter of the closed loop structure with the perimeter threshold, and performing a first screening on the part model according to the comparison result;

[0012] Step 5, dividing the closed loop structure into inner closed loop structure and outer closed loop structure, calculating the ratio between the area of the inner closed loop structure and the area of the outer closed loop structure, and performing a second screening on the part model based on the ratio;

[0013] Step 6, calculating the shape consistency degree of the inner closed loop structure and the outer closed loop structure on the projection view, and performing a third screening on the part model based on the consistency degree to obtain the thin-walled frame-like part.

[0014] In order to better realize the present application, further, in the step 5, the calculation formula of the ratio is:

[0015] ;

[0016] Wherein: The ratio between the area of the inner closed loop structure and the area of the outer closed loop structure is represented; The area of the i-th inner closed loop structure is represented; The area of the outer closed loop structure is represented; k represents the number of inner closed loop structures, and 1≤i≤k.

[0017] In order to better realize the present application, further, the step 6 specifically includes:

[0018] Step 6.1, for the outer closed loop structure, a plurality of outer closed loop sampling points are randomly selected on the outer closed loop structure, and the minimum distance between each outer closed loop sampling point and all inner closed loop structures is calculated to obtain a minimum distance sampling set;

[0019] Step 6.2, calculating the normalized standard deviation of the minimum distance sampling set as the consistency degree;

[0020] Step 6.3, comparing the normalized standard deviation with the consistency threshold, and performing a third screening on the part model based on the comparison result to obtain the thin-walled frame-like part.

[0021] In order to better realize the present application, further, the formula for calculating the normalized standard deviation in step 6.2 is as follows:

[0022] ;

[0023] wherein: denotes the normalized standard deviation; m denotes the number of outer closed loop sampling points; denotes the minimum distance between the ith outer closed loop sampling point and all inner closed loop structures; denotes the average value of the minimum distances between the m outer closed loop sampling points and all inner closed loop structures.

[0024] In order to better realize the present application, further, the step 2 specifically comprises:

[0025] Step 2.1, traversing all geometric faces on the part model, calculating the area of each geometric face;

[0026] Step 2.2, extracting the geometric face with the largest area as a reference face, and performing discretization processing on the reference face to obtain a plurality of reference geometric points on the reference face;

[0027] Step 2.3, extracting the normal vector of the reference geometric point on the reference face, and measuring the part thickness at each reference geometric point along the normal vector direction;

[0028] Step 2.4, judging whether the part thicknesses at all reference geometric points are equal, if equal, turning to step 2.5;

[0029] Step 2.5, setting a thickness threshold value based on the size of the OBB bounding box, comparing the part thickness with the thickness threshold value, and judging whether the part is a thin-walled part.

[0030] In order to better realize the present application, further, in the step 2.5, the comparison of the part thickness with the thickness threshold value is specifically as follows:

[0031] If , it is judged that the part is a thin-walled part; if , it is judged that the part is a non-thin-walled part;

[0032] wherein: denotes the part thickness at the kth reference geometric point; denotes the thickness threshold value; max(R) denotes the maximum value of the length, width and height dimensions of the OBB bounding box.

[0033] In order to better realize the present application, further, in the step 4, the circumference of each closed loop structure is calculated, and if the circumference of the closed loop structure is less than a circumference threshold value, the current closed loop structure is filtered out.

[0034] For better implementation of the present application, further, the filtering exclusion step of the closed loop structure is repeated, if the number of the finally remaining closed loop structures is equal to 1, then it is directly judged that the current part model is a non-thin-walled mouth frame type part; if the number of the finally remaining closed loop structures is greater than 1, then it is transferred to step 5.

[0035] For better implementation of the present application, further, in the step 1, the OBB bounding box algorithm is adopted to establish the OBB bounding box of the part model.

[0036] For better implementation of the present application, further, in the step 3, the edge detection algorithm is adopted to identify the closed loop structure formed on the projection surface.

[0037] Compared with the prior art, the present application has the following advantages and beneficial effects:

[0038] The present application adopts the image recognition and statistical method to identify the thickness, projection image edge consistency and other typical features of the part model, efficiently and accurately identifies the part model, can effectively identify whether the part is a thin-walled mouth frame type part; compared with the existing identification technology, the present application can improve the identification efficiency, reduce the manual intervention, is also suitable for the rapid identification and classification of large-scale part library, and is helpful to improve the aircraft knowledge management and process design level. BRIEF DESCRIPTION OF DRAWINGS

[0039] Figure 1 The flow step schematic diagram of the present application is shown in the figure;

[0040] Figure 2 The schematic diagram of the first thin-walled mouth frame type part is shown in the figure;

[0041] Figure 3 The schematic diagram of the second thin-walled mouth frame type part is shown in the figure;

[0042] Figure 4 The schematic diagram of the non-thin-walled mouth frame type part is shown in the figure;

[0043] Figure 5 The schematic diagram of the closed loop structure is shown in the figure. DETAILED DESCRIPTION

[0044] Embodiment 1:

[0045] The rapid identification method of the thin-walled mouth frame type part of the present embodiment is shown in the figure, which includes the following steps: Figure 1

[0046] Step 1, establish the OBB bounding box of the part model, and extract the length, width and height dimensions of the OBB bounding box;

[0047] ​Step 2, extract the reference surface with the largest area on the part model, measure the thickness of the part along the normal direction of the reference surface, judge whether the part is a thin-walled part, if it is a thin-walled part, go to step 3;

[0048] Step 3, project the part model according to the calibration direction, identify the closed loop structure formed on the projection surface, and calculate the perimeter of all closed loop structures;

[0049] Step 4, set a perimeter threshold, compare the perimeter of the closed loop structure with the perimeter threshold, and perform a first screening on the part model according to the comparison result;

[0050] Step 5, divide the closed loop structure into inner closed loop structure and outer closed loop structure, calculate the ratio between the area of the inner closed loop structure and the area of the outer closed loop structure, and perform a second screening on the part model based on the ratio;

[0051] Step 6, calculate the shape consistency degree of the inner closed loop structure and the outer closed loop structure on the projection view, and perform a third screening on the part model based on the consistency degree to obtain the thin-walled frame-like part.

[0052] In the step 1, the OBB bounding box algorithm is used to establish the OBB bounding box of the part model, and in the step 3, the edge detection algorithm is used to identify the closed loop structure formed on the projection surface.

[0053] The step 2 specifically includes:

[0054] Step 2.1, traverse all geometric surfaces on the part model, and calculate the area of each geometric surface;

[0055] Step 2.2, extract the geometric surface with the largest area as the reference surface, and perform discrete processing on the reference surface to obtain a plurality of reference geometric points on the reference surface;

[0056] Step 2.3, extract the normal vector of the reference geometric point on the reference surface, and measure the thickness of the part at each reference geometric point along the normal direction;

[0057] Step 2.4, judge whether the thickness of the part at all reference geometric points is equal, if it is equal, go to step 2.5;

[0058] Step 2.5, set a thickness threshold based on the size of the OBB bounding box, compare the thickness of the part with the thickness threshold, and judge whether the part is a thin-walled part.

[0059] In the step 2.5, the comparison between the thickness of the part and the thickness threshold is specifically as follows:

[0060] If , it is judged that the part is a thin-walled part; if , it is judged that the part is a non-thin-walled part;

[0061] wherein: represents the thickness of the part at the kth reference geometric point; represents the thickness threshold value; max(R) represents the maximum value of the length, width and height dimensions of the OBB bounding box.

[0062] In step 4, the perimeter of each closed loop structure is calculated, and if the perimeter of the closed loop structure is less than the perimeter threshold value, the current closed loop structure is filtered out. The filtering and exclusion step of the closed loop structure is repeated, and if the number of the finally remaining closed loop structures is equal to 1, it is directly judged that the current part number model is a non-thin-walled frame type part; if the number of the finally remaining closed loop structures is greater than 1, it is transferred to step 5.

[0063] In step 5, the calculation formula of the ratio is:

[0064] ;

[0065] wherein: represents the ratio between the area of the inner closed loop structure and the area of the outer closed loop structure; represents the area of the ith inner closed loop structure; represents the area of the outer closed loop structure; k represents the number of inner closed loop structures, and 1≤i≤k.

[0066] Step 6 specifically includes:

[0067] Step 6.1, for the outer closed loop structure, a plurality of outer closed loop sampling points are randomly selected on the outer closed loop structure, and the minimum distance between each outer closed loop sampling point and all inner closed loop structures is calculated to obtain a minimum distance sampling set;

[0068] Step 6.2, calculating the normalized standard deviation of the minimum distance sampling set as the consistency degree;

[0069] Step 6.3, comparing the normalized standard deviation with the consistency threshold value, and based on the comparison result, the part number model is screened three times to obtain the thin-walled frame type part.

[0070] The formula for calculating the normalized standard deviation in step 6.2 is as follows:

[0071] ;

[0072] wherein: represents the normalized standard deviation; m represents the number of outer closed loop sampling points; represents the minimum distance between the ith outer closed loop sampling point and all inner closed loop structures; represents the average value of the minimum distances between the m outer closed loop sampling points and all inner closed loop structures.

[0073] Example 2:

[0074] This embodiment discloses a method for quickly identifying thin-walled aircraft frame parts, which is further optimized based on the first embodiment. Specifically,

[0075] Given a part model to be identified, calculate the OBB bounding box of the part model ,in 、 、 are the length, width and height of the bounding box respectively, in mm; Figure 2 As an example, the OBB bounding box size is ;

[0076] Traverse all geometric faces of the part model , j represents the geometric face number. Loop and calculate each geometric face Area , traverse the areas of all the calculated geometric surfaces and find the geometric surface with the largest area as the reference surface , for the reference surface Discretize according to the set accuracy to obtain several reference geometric points on the reference surface , k represents the serial number of the reference geometry point. Get the reference geometry point On the reference surface The normal vector on the part is specified to point to the interior of the part model 3D entity, and the part thickness t at each reference geometric point in the direction of the normal vector is calculated. k , t k Represents the part thickness along the normal direction at the kth reference geometry point.

[0077] Setting the thickness threshold , first determine several reference geometric points The corresponding part thickness t k Are they equal? ​​If the thickness of the parts at all reference geometric points is equal, then:

[0078] like , then the current part model is judged to be a non-thin-wall part; if , then the current part model is judged to be a thin-walled part. Figure 2 For example, the thickness of the part at each reference geometric point is 1.2 mm, and , then judge Figure 2 The parts shown in the figure are thin-walled parts.

[0079] The part model is projected along the main direction of the OBB bounding box, and all closed loop structures formed by the edges of the part model on the projection plane are identified. The outermost loop of the closed loop structure is taken as the outer closed loop structure, and the loops inside the outer closed loop structure are taken as the inner closed loop structures. Usually, there is only one outer closed loop structure, and there are at least one inner closed loop structure inside the outer closed loop structure. The perimeters of the outer closed loop structure and the inner closed loop structures are calculated. The perimeter threshold c = 10 mm is set, and the perimeter of each closed loop structure is calculated. If the perimeter of the closed loop structure is less than the perimeter threshold, the closed loop structure is filtered. If the number of closed loop structures after filtering is equal to 1, the part model is directly determined as a non-thin-wall frame part, otherwise the next step is executed. Figure 3 The part shown in FIG. 1 is taken as an example, and all the closed loop structures identified in the projection image are shown in FIG. 2, including one outer closed loop structure and three inner closed loop structures. Figure 5

[0080] The perimeter threshold c = 10 mm is set, and the perimeter of each closed loop structure is calculated. If the perimeter of the closed loop structure is less than the perimeter threshold, the closed loop structure is filtered. If the number of closed loop structures after filtering is equal to 1, the part model is directly determined as a non-thin-wall frame part, otherwise the next step is executed.

[0081] The ratio of the sum of the areas of all the inner closed loop structures to the area of the outer closed loop structure of the part model is calculated The smaller the ratio is, the larger the hollow area of the part is. The calculation method is as follows:

[0082]

[0083] wherein, represents the ratio between the area of the inner closed loop structure and the area of the outer closed loop structure; represents the area of the i-th inner closed loop structure; represents the area of the outer closed loop structure; k represents the number of inner closed loop structures, and 1≤i≤k.

[0084] The shape consistency of the outer closed loop structure and the inner closed loop structure on the projection view of the part is calculated by statistical method, which includes the following steps:

[0085] For the outer closed loop structure, 100 outer closed loop sampling points are randomly taken from the outer closed loop structure, and the minimum distance between each outer closed loop sampling point and all inner closed loop structures is calculated to obtain a minimum distance sampling set represents the minimum distance between the i-th outer closed loop sampling point and all inner closed loop structures, and 1≤i≤100.

[0086] The normalized standard deviation of the minimum distance sampling set is calculated as the consistency, The smaller the normalized standard deviation is, the more consistent the shape of the outer closed loop structure and the inner closed loop structure of the part is, and vice versa. The calculation method is as follows:

[0087] wherein m = 100.​​​​

[0088] wherein: denotes the normalized standard deviation; m denotes the number of outer closed loop sampling points; denotes the minimum distance between the ith outer closed loop sampling point and all inner closed loop structures; denotes the average value of the minimum distances between the m outer closed loop sampling points and all inner closed loop structures.

[0089] Set the ratio threshold and the consistency threshold If the following conditions are met , and , the part is considered as a thin-walled mouth frame type part. For the parts shown in Figures 2-4 , it is calculated that are 0.76, 0.81, 0.15, respectively, are 0.09, 0.01, 0.42, respectively, so Figure 2 and Figure 3 are thin-walled mouth frame type parts, Figure 4 is a non-thin-walled mouth frame type part.

[0090] This embodiment shows that the automatic recognition method of the thin-walled mouth frame type part proposed by the present application can be used for the rapid recognition of the flat plate parts in the three-dimensional model of the aircraft, and good results can be achieved.

[0091] The other parts of this embodiment are the same as those of Embodiment 1, and will not be described again.

[0092] The above is only a preferred embodiment of the present application, and does not limit the present application in any form. Any simple modification or equivalent change made according to the technical essence of the present application falls within the protection scope of the present application.

Claims

1. A method for quickly identifying aircraft thin-walled frame parts, characterized in that: The following steps are involved: Step 1: Create the OBB bounding box of the part digital model and extract the length, width and height of the OBB bounding box; Step 2: Extract the reference surface with the largest area on the part model, measure the thickness of the part along the normal direction of the reference surface, and determine whether the part is a thin-walled part. If it is a thin-walled part, proceed to step 3. Step 3: Project the part digital model according to the calibration direction, identify the closed-loop structure formed on the projection surface, and calculate the perimeter of all closed-loop structures; Step 4: Set a perimeter threshold, compare the perimeter of the closed-loop structure with the perimeter threshold, and screen the part digital model based on the comparison result; Step 5: Divide the closed-loop structure into an inner closed-loop structure and an outer closed-loop structure, calculate the ratio between the area of ​​the inner closed-loop structure and the area of ​​the outer closed-loop structure, and perform a secondary screening of the part digital model based on the ratio; Step 6: Calculate the shape consistency of the inner closed-loop structure and the outer closed-loop structure on the projection view, and screen the part digital model three times based on the consistency to obtain a thin-walled mouth frame part; The step 6 specifically includes: Step 6.1: For the outer closed-loop structure, randomly select several outer closed-loop sampling points on the outer closed-loop structure, and calculate the minimum distance between each outer closed-loop sampling point and all inner closed-loop structures to obtain the minimum distance sampling set; Step 6.2: Calculate the normalized standard deviation of the minimum distance sampling set as the consistency; Step 6.3: Compare the normalized standard deviation with the consistency threshold, and screen the part digital model three times based on the comparison results to obtain thin-walled mouth frame parts; The formula for calculating the normalized standard deviation in step 6.2 is as follows: ； in: represents the normalized standard deviation; m represents the number of outer closed-loop sampling points; represents the minimum distance between the i-th outer closed-loop sampling point and all inner closed-loop structures; It represents the average value of the minimum distance between m outer closed-loop sampling points and all inner closed-loop structures.

2. A method for quickly identifying aircraft thin-walled mouth frame parts according to claim 1, characterized in that: In step 5, the calculation formula of the ratio is: ； in: It represents the ratio between the area of ​​the inner closed loop structure and the area of ​​the outer closed loop structure; represents the area of ​​the i-th inner closed loop structure; represents the area of ​​the outer closed-loop structure; k represents the number of inner closed-loop structures, 1≤i≤k.

3. A method for quickly identifying aircraft thin-walled mouth frame parts according to claim 1 or 2, characterized in that: The step 2 specifically includes: Step 2.1, traverse all geometric faces on the part digital model and calculate the area of ​​each geometric face; Step 2.2, extracting the geometric surface with the largest area as the reference surface, and discretizing the reference surface to obtain a number of reference geometric points on the reference surface; Step 2.3, extract the normal vector of the reference geometric point on the reference surface, and measure the thickness of the part at each reference geometric point along the normal vector direction; Step 2.4: Determine whether the thickness of the part at all reference geometric points is equal. If so, proceed to step 2.

5. Step 2.5: Set a thickness threshold based on the size of the OBB bounding box, compare the part thickness with the thickness threshold, and determine whether the part is a thin-walled part.

4. A method for quickly identifying aircraft thin-walled mouth frame parts according to claim 3, characterized in that: In step 2.5, the part thickness is compared with the thickness threshold as follows: like , then the part is judged to be a thin-walled part; if , then the part is judged to be a non-thin-wall part; in: represents the thickness of the part at the kth reference geometric point; represents the thickness threshold; Indicates the maximum length, width, and height of the OBB bounding box.

5. A method for quickly identifying aircraft thin-walled mouth frame parts according to claim 1 or 2, characterized in that: In step 4, the perimeter of each closed-loop structure is calculated. If the perimeter of the closed-loop structure is less than a perimeter threshold, the current closed-loop structure is filtered out.

6. A method for quickly identifying aircraft thin-walled mouth frame parts according to claim 5, characterized in that: Repeat the filtering and exclusion steps for closed-loop structures. If the number of closed-loop structures remaining is equal to 1, directly determine that the current part model is a non-thin-walled mouth frame part; if the number of closed-loop structures remaining is greater than 1, proceed to step 5.

7. A method for quickly identifying aircraft thin-walled mouth frame parts according to claim 1 or 2, characterized in that: In step 1, an OBB bounding box algorithm is used to establish an OBB bounding box of the part digital model.

8. A method for quickly identifying aircraft thin-walled mouth frame parts according to claim 1 or 2, characterized in that: In step 3, an edge detection algorithm is used to identify the closed-loop structure formed on the projection surface.

Images