A knowledge-based process inspection method and system based on feature recognition

Abstract

The present invention discloses a knowledge-based process inspection method and system based on feature recognition, belonging to the technical field of three-dimensional model process inspection. The method specifically comprises: establishing a DFX digital process rule library, combing and calibrating the digital knowledge library in multiple dimensions, storing the established DFX digital process rule library in a database, determining process characteristics and standards to be inspected, clarifying the purpose and requirements of the inspection, obtaining a three-dimensional model to be inspected, and performing feature recognition on the three-dimensional model to be inspected, including the characteristics, attributes, and three-dimensional annotations of the three-dimensional model, storing the identified three-dimensional model characteristics, attributes, and three-dimensional annotations in a database, comparing and analyzing the extracted three-dimensional model feature points, attributes, and three-dimensional annotations with the DFX digital process rule library in the database, quickly locating and highlighting error characteristics in an interactive interface graphic area, and automatically generating a process inspection report.

Description

Technical Field

[0001] The present invention belongs to the technical field of three-dimensional model process inspection, and specifically is a knowledge-based process inspection method and system based on feature recognition. Background Art

[0002] With the increasingly fierce market competition and the continuous improvement of user needs, the speed of product replacement is getting faster and faster. How manufacturing companies can produce products with the best quality and the best process at the lowest cost and respond to market demand at the fastest speed is the key to the survival and development of enterprises. This forces enterprises to change the traditional serial working mode and introduce the idea of ​​parallel engineering, which requires process personnel to fully consider the manufacturability of products in the process design stage, refine the internal process basic work, and avoid bringing these problems into the manufacturing stage.

[0003] Design processability assessment still mainly adopts traditional manual methods. Complex and tedious processability issues are easily overlooked, and many difficult-to-test and costly process problems are not easy to find. At the same time, due to the lack of clear product processability assessment standards and specifications, processability assessment work is often more centralized, the assessment cycle is seriously insufficient, the error rate is high, the design process is frequently repeated, and the process knowledge base cannot be effectively accumulated and solidified.

[0004] For example, the Chinese patent with the authorization announcement number CN111583394B discloses a knowledge-based process inspection method and system based on feature recognition, including determining the time of process inspection intervention based on the maturity of the design model, and managing the inspection knowledge in an itemized manner based on database technology; constructing an inspection rule library based on the inspection rule formula and feature parameter expression; extracting the design model features and feature parameters based on feature recognition; matching process inspection rules based on the similarity of component types and part features; reasoning of process inspection results based on the reasoning engine; and three-dimensional visualization of inspection results. In order to solve the problems of excessive reliance on manual experience, long inspection time, and easy omission of inspection points in traditional process inspection, a knowledge-based process inspection method is proposed, which mainly relies on feature recognition and automatically matches inspection rules based on features, and uses computers to calculate and reason out inspection results based on inspection rules, thereby improving the efficiency and quality of inspection and the readability of inspection results.

[0005] The defect of the above patent is that for assembly models with high complexity, many detailed structures inside the assembly cannot be completely inspected. Summary of the invention

[0006] In view of the deficiencies in the prior art, the present invention proposes a knowledge-based process inspection method and system based on feature recognition, establishes a DFX digital process rule library, performs multi-dimensional knowledge combing and calibration on the digital knowledge base, and stores the established DFX digital process rule library in a database, determines the process characteristics and standards to be inspected, clarifies the purpose and requirements of the inspection, obtains the three-dimensional model to be inspected, and performs feature recognition on the three-dimensional model to be inspected, including the characteristics, attributes, and three-dimensional annotations of the three-dimensional model, and stores the identified three-dimensional model characteristics, attributes, and three-dimensional annotations in a database, compares and analyzes the extracted three-dimensional model feature points, attributes, and three-dimensional annotations with the DFX digital process rule library in the database, quickly locates and highlights error features in the interactive interface graphic area, automatically generates a process inspection report, lists in detail the process inspection problems existing in the model, reminds users, and automatically analyzes error information and gives reasonable improvement suggestions, optimizes and improves the process flow according to the inspection results and improvement suggestions, and improves product quality and process performance.

[0007] To achieve the above object, the present invention provides the following technical solutions:

[0008] A knowledge-based process inspection method based on feature recognition includes the following specific steps:

[0009] Step S1: Establish a DFX digital process rule library, perform multi-dimensional knowledge sorting and calibration on the digital knowledge base, and store the established DFX digital process rule library in the database;

[0010] Step S2: Determine the process characteristics and standards to be inspected, and clarify the purpose and requirements of the inspection;

[0011] Step S3: obtaining a 3D model to be inspected, and performing feature recognition on the 3D model to be inspected, including features, attributes, and 3D annotations of the 3D model, and storing the recognized features, attributes, and 3D annotations of the 3D model in a database;

[0012] Step S4: Compare and analyze the extracted 3D model feature points, attributes, and 3D annotations with the DFX digital process rule library in the database, and quickly locate and highlight the error features in the interactive interface graphic area;

[0013] Step S5: generating a process inspection report, wherein the process inspection report is used to record abnormal information in the three-dimensional model after the processability inspection, and to form error information and correction information based on the abnormal information analysis;

[0014] Step S6: Based on the inspection results and improvement suggestions, optimize and improve the process flow to improve product quality and process performance.

[0015] Specifically, the DFX digital process rule library in step S1 includes the following process classification directions: machining, assembly, welding, sheet metal, casting, injection molding, piping and additive manufacturing.

[0016] Specifically, the specific steps of step S3 are:

[0017] Step S301: Obtain the 3D model to be checked, establish a spatial rectangular coordinate system with any point in the 3D model as the origin, set the coordinates of point P in the 3D model as (x, y, z), and remove noise from the adjacent points of point P in the neighborhood T;

[0018] Step S302: constructing a scale space K(x, y, μz) of the three-dimensional model according to the points in the denoised three-dimensional model, where μ represents a spatial coefficient of the scale space of the three-dimensional model;

[0019] Step S303: Establishing constraint conditions for extracting scale space feature points of the three-dimensional model. The specific formula of the constraint conditions is:

[0020]

[0021] Among them, YS represents the constraint condition for extracting the scale space feature points of the 3D model, (x s ,y s ,z s ) represents the coordinates of the sth point in the three-dimensional model, (x s-1 ,y s-1 ,z s-1 ) represents the coordinates of the s-1th point in the three-dimensional model, exp() represents an exponential function with e as the base, ∨ represents or, max() represents a maximum value function, and min() represents a minimum value function;

[0022] Step S304: extract all feature points of the three-dimensional model according to the constraint conditions for extracting the scale space feature points of the three-dimensional model, and use image recognition technology to identify the attributes and three-dimensional annotations of the feature points.

[0023] Specifically, the specific steps of removing noise from the neighboring points of point P in the neighborhood T in step S301 include:

[0024] Step S3011: Calculate the Euclidean distance between point P and the i-th point in the neighborhood of T. The calculation formula is:

[0025] Among them, d Pi represents the Euclidean distance between point P and the i-th point in the neighborhood of T, (x i ,y i ,z i ) represents the coordinates of the i-th point in the T neighborhood of point P;

[0026] Step S3012: Setting the noise threshold λ zs , noise threshold λ zs The calculation formula is:

[0027]

[0028] Among them, d Pj represents the Euclidean distance between point P and the jth point in the neighborhood of T, and n represents the number of all points in the neighborhood of T of point P;

[0029] Step S3013: When d Pi Greater than the noise threshold λ zs , determine the i-th point as a noise point, and delete the i-th point.

[0030] Specifically, the specific steps of step S4 are:

[0031] Step S401: Compare the extracted 3D model feature points, attributes, and 3D annotations with the DFX digital process rule library in the database, and calculate the angle error and position error between the 3D model feature points and the feature points in the DFX digital process rule library;

[0032] Step S402: The calculation formula of the angle error between the feature point of the 3D model and the feature point in the DFX digital process rule library is:

[0033]

[0034] Among them, W jd represents the angle error between the feature points of the 3D model and the feature points in the DFX digital process rule library, J Oq Indicates the angle between the plane where the feature point q is located and the origin in the 3D model, J OQ represents the angle between the plane where the feature point Q in the DFX digital process rule library is located and the origin, |·| represents the absolute value symbol, Indicates that the feature point q in the 3D model corresponds to the feature point Q in the DFX digital process rule library;

[0035] Step S403: The calculation formula for the position error between the feature point of the 3D model and the feature point in the DFX digital process rule library is:

[0036]

[0037] Among them, W wz represents the position error between the feature points of the 3D model and the feature points in the DFX digital process rule library, (x q ,y q ,z q ) represents the coordinates of the feature point q in the three-dimensional model, (x Q ,yQ ,z Q ) represents the coordinates of the feature point Q in the DFX digital process rule library;

[0038] Step S404: setting the angle error and position error thresholds. When any of the angle error and position error between the feature point of the 3D model and the feature point in the DFX digital process rule library exceeds the threshold, the error feature is quickly located and highlighted in the interactive interface graphic area.

[0039] Specifically, the process inspection report of step S5 includes information on the process inspection items that have been carried out and the items that have not passed the inspection, including text descriptions and error screenshots.

[0040] A knowledge-based process inspection system based on feature recognition, comprising: a rule base establishment and storage module, a process inspection preparation module, a feature recognition module, a comparison and analysis module, an inspection report automatic generation module and an improvement and suggestion module;

[0041] The rule base establishes a storage module, which is used to establish a DFX digital process rule base, perform multi-dimensional knowledge combing and calibration on the digital knowledge base, and store the established DFX digital process rule base in the database;

[0042] The processability inspection preparation module is used to determine the processability characteristics and standards to be inspected and to clarify the purpose and requirements of the inspection;

[0043] The feature recognition module is used to obtain the 3D model to be inspected, and perform feature recognition on the 3D model to be inspected, including features, attributes, and 3D annotations of the 3D model, and store the recognized 3D model features, attributes, and 3D annotations in a database;

[0044] The comparison and analysis module is used to compare and analyze the extracted 3D model feature points, attributes, and 3D annotations with the DFX digital process rule library in the database, and quickly locate and highlight the error features in the interactive interface graphic area;

[0045] The inspection report automatic generation module is used to automatically generate a process inspection report, list in detail the process inspection problems existing in the model, remind the user, and automatically analyze the error information and give reasonable improvement suggestions;

[0046] The improvement and suggestion module is used to optimize and improve the process flow according to the inspection results and improvement suggestions, so as to improve the product quality and process performance.

[0047] Specifically, the comparison and analysis module includes an angle error analysis unit and a position error analysis unit;

[0048] The angle error analysis unit is used to calculate the angle error between the feature points of the three-dimensional model and the feature points in the DFX digital process rule library;

[0049] The position error analysis unit is used to calculate the position error between the feature points of the three-dimensional model and the feature points in the DFX digital process rule library.

[0050] An electronic device includes a memory and a processor, wherein the memory stores a computer program, and the processor implements the steps of a knowledgeable process inspection method based on feature recognition when executing the computer program.

[0051] A storage medium stores computer instructions, which, when executed, execute the steps of a knowledgeable process inspection method based on feature recognition.

[0052] Compared with the prior art, the present invention has the following beneficial effects:

[0053] 1. The present invention proposes a knowledge-based process inspection method based on feature recognition, which supports the inspection of common process problems such as machining and assembly, ensures the process quality of products, reduces rework caused by process problems, can discover potential size and process problems in the early stage of the product process, guide the optimization of products and processes, and solve process defects before manufacturing actual parts and tooling. By optimizing the process plan, it can reduce product costs, shorten time to market, and improve corporate competitiveness.

[0054] 2. The present invention proposes a knowledge-based process inspection method based on feature recognition. The process inspection software provides automated inspection work based on three-dimensional models, freeing auditors from tedious and time-consuming manual inspection work, significantly improving process inspection efficiency, avoiding omissions, and improving the quality of process inspection.

[0055] 3. The present invention proposes a knowledge-based process inspection method based on feature recognition, which uses digital means and key technologies such as feature recognition and feature comparison to achieve the transformation of process review from manual to automated methods. BRIEF DESCRIPTION OF THE DRAWINGS

[0056] Figure 1 This is a flow chart of a knowledge-based process inspection method based on feature recognition of the present invention;

[0057] Figure 2 This is an architecture diagram of a knowledge-based process inspection system based on feature recognition according to the present invention;

[0058] Figure 3 An electronic device diagram of a knowledgeable process inspection method based on feature recognition according to the present invention;

[0059] Figure 4 This is a storage medium diagram of a knowledge-based process inspection method based on feature recognition according to the present invention. DETAILED DESCRIPTION

[0060] In order to make the technical means, creative features, objectives and effects achieved by the present invention easy to understand, in the description of the present invention, it should be noted that the terms "center", "up", "down", "left", "right", "vertical", "horizontal", "inside", "outside" and the like indicate the orientation or position relationship based on the orientation or position relationship shown in the accompanying drawings, which is only for the convenience of describing the present invention and simplifying the description, and does not indicate or imply that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and therefore cannot be understood as a limitation on the present invention. In addition, the terms "No. 1", "No. 2" and "No. 3" are only used for descriptive purposes and cannot be understood as indicating or implying relative importance. The present invention is further explained below in conjunction with specific embodiments.

[0061] Example 1

[0062] See also Figure 1 The present invention provides an embodiment: a knowledge-based process inspection method based on feature recognition, comprising the following specific steps:

[0063] Step S1: Establish a DFX digital process rule library, perform multi-dimensional knowledge sorting and calibration on the digital knowledge base, and store the established DFX digital process rule library in the database;

[0064] The DFX digital process rule library in step S1 includes the following process classification directions: machining, assembly, welding, sheet metal, casting, injection molding, piping and additive manufacturing.

[0065] Step S2: Determine the process characteristics and standards to be inspected, and clarify the purpose and requirements of the inspection;

[0066] Step S3: obtaining a 3D model to be inspected, and performing feature recognition on the 3D model to be inspected, including features, attributes, and 3D annotations of the 3D model, and storing the recognized features, attributes, and 3D annotations of the 3D model in a database;

[0067] The specific steps of step S3 are:

[0068] Step S301: Obtain the 3D model to be checked, establish a spatial rectangular coordinate system with any point in the 3D model as the origin, set the coordinates of point P in the 3D model as (x, y, z), and remove noise from the adjacent points of point P in the neighborhood T;

[0069] Step S302: constructing a scale space K(x, y, μz) of the three-dimensional model according to the points in the denoised three-dimensional model, where μ represents a spatial coefficient of the scale space of the three-dimensional model;

[0070] Step S303: Establishing constraint conditions for extracting scale space feature points of the three-dimensional model. The specific formula of the constraint conditions is:

[0071]

[0072] Among them, YS represents the constraint condition for extracting the scale space feature points of the 3D model, (x s ,y s ,z s ) represents the coordinates of the sth point in the three-dimensional model, (x s-1 ,y s-1 ,z s-1 ) represents the coordinates of the s-1th point in the three-dimensional model, exp() represents an exponential function with e as the base, ∨ represents or, max() represents a maximum value function, and min() represents a minimum value function;

[0073] For the third constraint, it is mainly to control the sth point and the s-1th point to be in the same plane;

[0074] Step S304: extract all feature points of the three-dimensional model according to the constraint conditions for extracting the scale space feature points of the three-dimensional model, and use image recognition technology to identify the attributes and three-dimensional annotations of the feature points.

[0075] The image recognition technology is the existing text recognition technology;

[0076] In step S301, the specific steps of removing noise from the adjacent points of point P in the neighborhood T include:

[0077] Step S3011: Calculate the Euclidean distance between point P and the i-th point in the neighborhood of T. The calculation formula is:

[0078] Among them, d Pi represents the Euclidean distance between point P and the i-th point in the neighborhood of T, (x i ,y i ,z i ) represents the coordinates of the i-th point in the T neighborhood of point P;

[0079] Step S3012: Setting the noise threshold λ zs , noise threshold λ zs The calculation formula is:

[0080]

[0081] Among them, d Pjrepresents the Euclidean distance between point P and the jth point in the neighborhood of T, and n represents the number of all points in the neighborhood of T of point P;

[0082] Step S3013: When d Pi Greater than the noise threshold λ zs , determine the i-th point as a noise point, and delete the i-th point.

[0083] Step S4: Compare and analyze the extracted 3D model feature points, attributes, and 3D annotations with the DFX digital process rule library in the database, and quickly locate and highlight the error features in the interactive interface graphic area;

[0084] The specific steps of step S4 are:

[0085] Step S401: Compare the extracted 3D model feature points, attributes, and 3D annotations with the DFX digital process rule library in the database, and calculate the angle error and position error between the 3D model feature points and the feature points in the DFX digital process rule library;

[0086] Step S402: The calculation formula of the angle error between the feature point of the 3D model and the feature point in the DFX digital process rule library is:

[0087]

[0088] Among them, W jd represents the angle error between the feature points of the 3D model and the feature points in the DFX digital process rule library, J Oq Indicates the angle between the plane where the feature point q is located and the origin in the 3D model, J OQ represents the angle between the plane where the feature point Q in the DFX digital process rule library is located and the origin, |·| represents the absolute value symbol, Indicates that the feature point q in the 3D model corresponds to the feature point Q in the DFX digital process rule library;

[0089] Step S403: The calculation formula for the position error between the feature point of the 3D model and the feature point in the DFX digital process rule library is:

[0090]

[0091] Among them, W wz represents the position error between the feature points of the 3D model and the feature points in the DFX digital process rule library, (x q ,y q ,z q ) represents the coordinates of the feature point q in the three-dimensional model, (x Q ,y Q ,z Q ) represents the coordinates of the feature point Q in the DFX digital process rule library;

[0092] Step S404: setting the angle error and position error thresholds. When any of the angle error and position error between the feature point of the 3D model and the feature point in the DFX digital process rule library exceeds the threshold, the error feature is quickly located and highlighted in the interactive interface graphic area.

[0093] The comparison here also includes the attributes and 3D annotations of the feature points of the 3D model. Both the attributes and 3D annotations are text types and can be directly compared. When there are errors in the attributes and 3D annotations of the feature points, they are also highlighted.

[0094] Step S5: Generate a process inspection report, which is used to record abnormal information in the three-dimensional model after the processability inspection, and to form error information and correction information based on the abnormal information analysis;

[0095] Step S6: Based on the inspection results and improvement suggestions, optimize and improve the process flow to improve product quality and process performance.

[0096] The process inspection report in step S5 includes information on the process inspection items that have been carried out and the items that have not passed the inspection, including text descriptions and error screenshots.

[0097] The existing 3D model process inspection problems are mainly manifested in:

[0098] 1) The process review work of process personnel mainly relies on two-dimensional engineering drawings;

[0099] 2) The process review of process personnel is mainly manual review. If the review work is interrupted due to certain factors, it must be restarted, which is inefficient and has a high error rate;

[0100] 3) Some of the current process review specifications of enterprises cannot be directly connected and integrated with the digital process rule library, and require quantifiable screening and evaluation;

[0101] 4) The original process review report is mostly formed by manual review and entry into forms, which makes it difficult to ensure accuracy. There are too many human factors and the time cycle is too long, making it difficult to carry out the review work;

[0102] 5) For assembly models with higher complexity, manual review of many detailed structures within the assembly is almost impossible, and the comprehensiveness of the assembly design or process review cannot be guaranteed.

[0103] The standard rules of the process model are shown in Table 1.

[0104] Table 1 Process model standard rules table

[0105] Serial number Process rules Rule Description 1 Layer Category Check Check if layer categories match 2 Key attribute existence check Check if a property exists 3 Modeling Unit Check Modeling units are metric 4 Physical color inspection There are no entities in the model that do not match the color 5 Model View Submission Status Check if the model is submitted in standard view 6 Model fillet radius Check if the model chamfer is between the reference values 7 Standard Reference Set Checks whether the components in the assembly file use the standard reference set 8 Interference components Check assembly files for interfering components 9 Component Inhibition Checking an assembly for suppressed components 10 View Name Validity This checker checks whether the view name in PMI meets the standard 11 PMI text size Check whether the PMI annotation text style meets the standard 12 PMI Text Type Check PMI's annotation text type 13 Engineering drawing size The size of the engineering drawing is set to meet the system requirements 14 Empty drawing There is no empty drawing in the file 15 Engineering drawing annotation text style Annotation in engineering drawings conforms to the style

[0106] Example 2

[0107] See also Figure 2 ,Another embodiment provided by the present invention: A knowledgeable processability inspection system based on feature recognition, comprising: a rule base establishment storage module, a processability inspection preparation module, a feature recognition module, a comparison analysis module, an inspection report automatic generation module and an improvement and suggestion module;

[0108] The rule base establishes a storage module, which is used to establish a DFX digital process rule base, perform multi-dimensional knowledge combing and calibration on the digital knowledge base, and store the established DFX digital process rule base in the database;

[0109] The processability inspection preparation module is used to determine the processability characteristics and standards to be inspected and to clarify the purpose and requirements of the inspection;

[0110] The feature recognition module is used to obtain the 3D model to be inspected, and perform feature recognition on the 3D model to be inspected, including features, attributes, and 3D annotations of the 3D model, and store the recognized 3D model features, attributes, and 3D annotations in a database;

[0111] The comparison and analysis module is used to compare and analyze the extracted 3D model feature points, attributes, and 3D annotations with the DFX digital process rule library in the database, and quickly locate and highlight the error features in the interactive interface graphic area;

[0112] The inspection report automatic generation module is used to automatically generate a process inspection report, list in detail the process inspection problems existing in the model, remind the user, and automatically analyze the error information and give reasonable improvement suggestions;

[0113] The improvement and suggestion module is used to optimize and improve the process flow according to the inspection results and improvement suggestions, so as to improve the product quality and process performance.

[0114] The comparison and analysis module includes an angle error analysis unit and a position error analysis unit;

[0115] The angle error analysis unit is used to calculate the angle error between the feature points of the three-dimensional model and the feature points in the DFX digital process rule library;

[0116] The position error analysis unit is used to calculate the position error between the feature points of the three-dimensional model and the feature points in the DFX digital process rule library.

[0117] Example 3

[0118] Figure 3 1 is a schematic diagram of the structure of an electronic device provided by an embodiment of the present application. Figure 3As shown, according to another aspect of the present application, an electronic device 500 is also provided. The electronic device 500 may include one or more processors and one or more memories. The memories store computer readable codes, and when the computer readable codes are executed by one or more processors, a knowledgeable process inspection method based on feature recognition can be executed.

[0119] The method or system according to the embodiment of the present application can also be used by Figure 3 The electronic device architecture shown in FIG. Figure 3 As shown, the electronic device 500 may include a bus 501, one or more CPUs 502, a ROM 503, a RAM 504, a communication port 505 connected to a network, an input / output component 506, a hard disk 507, etc. The storage device in the electronic device 500, such as the ROM 503 or the hard disk 507, may store a knowledgeable process inspection method based on feature recognition provided by the present application. A knowledge-based process inspection method based on feature recognition may, for example, include: establishing a DFX digital process rule library, combing and calibrating the digital knowledge base in multiple dimensions, and storing the established DFX digital process rule library in a database, determining the process characteristics and standards to be inspected, clarifying the purpose and requirements of the inspection, obtaining the three-dimensional model to be inspected, and performing feature recognition on the three-dimensional model to be inspected, including the characteristics, attributes, and three-dimensional annotations of the three-dimensional model, and storing the identified three-dimensional model characteristics, attributes, and three-dimensional annotations in a database, comparing and analyzing the extracted three-dimensional model feature points, attributes, and three-dimensional annotations with the DFX digital process rule library in the database, quickly locating and highlighting erroneous features in the interactive interface graphic area, automatically generating a process inspection report, listing in detail the process inspection problems existing in the model, reminding the user, and automatically analyzing error information and giving reasonable suggestions for improvement. Furthermore, the electronic device 500 may also include a user interface 508. Of course, Figure 3 The architecture shown is only exemplary and can be omitted according to actual needs when implementing different devices. Figure 3 One or more components of an electronic device are shown.

[0120] Example 4

[0121] Figure 4 Schematic diagram of a storage medium structure provided by an embodiment of the present application. Figure 4As shown, a storage medium 600 according to an embodiment of the present application is shown. Computer-readable instructions are stored on the storage medium 600. When the computer-readable instructions are executed by the processor, a knowledge-based process inspection method based on feature recognition according to an embodiment of the present application described with reference to the above figures can be executed. The storage medium 600 includes, but is not limited to, for example, volatile memory and / or non-volatile memory. Volatile memory may include, for example, random access memory (RAM) and cache memory (cache), etc. Non-volatile memory may include, for example, read-only memory (ROM), hard disk, flash memory, etc.

[0122] It should be understood that the methods, apparatuses, and devices of the present application can be implemented in many ways. For example, the methods, apparatuses, and devices of the present application can be implemented by software, hardware, firmware, or any combination of software, hardware, and firmware. The above order of steps for the method is only for illustration, and the steps of the method of the present application are not limited to the order specifically described above unless otherwise specified. In addition, in some embodiments, the present application can also be implemented as a program recorded in a recording medium, which includes machine-readable instructions for implementing the method according to the present application. Therefore, the present application also covers a recording medium storing a program for executing the method according to the present application.

[0123] In addition, the parts of the above-mentioned technical solutions provided in the embodiments of the present application that are consistent with the implementation principles of the corresponding technical solutions in the prior art are not described in detail to avoid excessive redundancy.

[0124] The specific implementation modes as described above further describe the purpose, technical solutions and beneficial effects of the present invention in detail. It should be understood that the above description is only a specific implementation mode of the present invention and is not intended to limit the present invention. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention shall be included in the protection scope of the present invention.

Claims

1. A knowledge-based process inspection method based on feature recognition, characterized in that: The specific steps include: Step S1: Establish a DFX digital process rule library, perform multi-dimensional knowledge sorting and calibration on the digital knowledge base, and store the established DFX digital process rule library in the database; Step S2: Determine the process characteristics and standards to be inspected, and clarify the purpose and requirements of the inspection; Step S3: obtaining a 3D model to be inspected, and performing feature recognition on the 3D model to be inspected, including feature points, attributes, and 3D annotations of the 3D model, and storing the recognized 3D model features, attributes, and 3D annotations in a database; Step S4: Compare and analyze the extracted 3D model feature points, attributes, and 3D annotations with the DFX digital process rule library in the database, and quickly locate and highlight the error features in the interactive interface graphic area; Step S5: generating a process inspection report, wherein the process inspection report is used to record abnormal information in the three-dimensional model after the processability inspection, and to form error information and correction information based on the abnormal information analysis; Step S6: Optimize and improve the process flow according to the inspection results and improvement suggestions to improve product quality and process performance; The specific steps of step S3 are: Step S301: Obtain the 3D model to be checked, establish a spatial rectangular coordinate system with any point in the 3D model as the origin, set the coordinates of point P in the 3D model as (x, y, z), and remove noise from the adjacent points of point P in the neighborhood T; Step S302: constructing a scale space K(x, y, μz) of the three-dimensional model according to the points in the denoised three-dimensional model, where μ represents a spatial coefficient of the scale space of the three-dimensional model; Step S303: Establishing constraint conditions for extracting scale space feature points of the three-dimensional model. The specific formula of the constraint conditions is: Among them, YS represents the constraint condition for extracting the scale space feature points of the 3D model, (x s ,y s ,z s ) represents the coordinates of the sth point in the three-dimensional model, (x s-1 ,y s-1 ,z s-1 ) represents the coordinates of the s-1th point in the three-dimensional model, exp() represents an exponential function with e as the base, ∨ represents or, max() represents a maximum value function, and min() represents a minimum value function; Step S304: extract all feature points of the three-dimensional model according to the constraint conditions for extracting the scale space feature points of the three-dimensional model, and use image recognition technology to identify the attributes and three-dimensional annotations of the feature points.

2. A knowledge-based process inspection method based on feature recognition as claimed in claim 1, characterized in that: The specific steps of removing noise from the adjacent points of point P in the neighborhood T in step S301 include: Step S3011: Calculate the Euclidean distance between point P and the i-th point in the neighborhood of T. The calculation formula is: Among them, d Pi represents the Euclidean distance between point P and the i-th point in the neighborhood of T, (x i ,y i ,z i ) represents the coordinates of the i-th point in the T neighborhood of point P; Step S3012: Setting the noise threshold λ zs , noise threshold λ zs The calculation formula is: Among them, d Pj represents the Euclidean distance between point P and the jth point in the neighborhood of T, and n represents the number of all points in the neighborhood of T of point P; Step S3013: When d Pi Greater than the noise threshold λ zs , determine the i-th point as a noise point, and delete the i-th point.

3. A knowledge-based process inspection method based on feature recognition as claimed in claim 2, characterized in that: The specific steps of step S4 are: Step S401: Compare the extracted 3D model feature points, attributes, and 3D annotations with the DFX digital process rule library in the database, and calculate the angle error and position error between the 3D model feature points and the feature points in the DFX digital process rule library; Step S402: The calculation formula of the angle error between the feature point of the 3D model and the feature point in the DFX digital process rule library is: Among them, W jd represents the angle error between the feature points of the 3D model and the feature points in the DFX digital process rule library, J Oq Indicates the angle between the plane where the feature point q is located and the origin in the 3D model, J OQ represents the angle between the plane where the feature point Q in the DFX digital process rule library is located and the origin, |·| represents the absolute value symbol, Indicates that the feature point q in the 3D model corresponds to the feature point Q in the DFX digital process rule library; Step S403: The calculation formula for the position error between the feature point of the 3D model and the feature point in the DFX digital process rule library is: Among them, W wz represents the position error between the feature points of the 3D model and the feature points in the DFX digital process rule library, (x q ,y q ,z q ) represents the coordinates of the feature point q in the three-dimensional model, (x Q ,y Q ,z Q ) represents the coordinates of the feature point Q in the DFX digital process rule library; Step S404: setting the angle error and position error thresholds. When any of the angle error and position error between the feature point of the 3D model and the feature point in the DFX digital process rule library exceeds the threshold, the error feature is quickly located and highlighted in the interactive interface graphic area.

4. The method for knowledgeable process inspection based on feature recognition as claimed in claim 3, characterized in that: The process inspection report in step S5 includes information on the process inspection items that have been carried out and the items that have not passed the inspection, including text descriptions and error screenshots.

5. A knowledgeable processability inspection system based on feature recognition, which is used to implement a knowledgeable processability inspection method based on feature recognition as claimed in any one of claims 1 to 4, characterized in that: include: Rule base establishment storage module, processability inspection preparation module, feature recognition module, comparison analysis module, inspection report automatic generation module and improvement and suggestion module; The rule base establishes a storage module, which is used to establish a DFX digital process rule base, perform multi-dimensional knowledge combing and calibration on the digital knowledge base, and store the established DFX digital process rule base in the database; The processability inspection preparation module is used to determine the processability characteristics and standards to be inspected and to clarify the purpose and requirements of the inspection; The feature recognition module is used to obtain the 3D model to be inspected, and perform feature recognition on the 3D model to be inspected, including features, attributes, and 3D annotations of the 3D model, and store the recognized 3D model features, attributes, and 3D annotations in a database; The comparison and analysis module is used to compare and analyze the extracted 3D model feature points, attributes, and 3D annotations with the DFX digital process rule library in the database, and quickly locate and highlight the error features in the interactive interface graphic area; The inspection report automatic generation module is used to automatically generate a process inspection report, list in detail the process inspection problems existing in the model, remind the user, and automatically analyze the error information and give reasonable improvement suggestions; The improvement and suggestion module is used to optimize and improve the process flow according to the inspection results and improvement suggestions, so as to improve the product quality and process performance.

6. A knowledge-based process inspection system based on feature recognition as claimed in claim 5, characterized in that: The comparison and analysis module includes an angle error analysis unit and a position error analysis unit; The angle error analysis unit is used to calculate the angle error between the feature points of the three-dimensional model and the feature points in the DFX digital process rule library; The position error analysis unit is used to calculate the position error between the feature points of the three-dimensional model and the feature points in the DFX digital process rule library.

7. An electronic device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the processor implements the steps of a knowledge-based process inspection method based on feature recognition as described in any one of claims 1-4.

8. A storage medium, characterized in that: Computer instructions are stored thereon, and when the computer instructions are executed, the steps of a knowledge-based process inspection method based on feature recognition described in any one of claims 1-4 are executed.

Images