Part standard detection model construction method and computer equipment

Abstract

The invention discloses a part standard detection model construction method and computer equipment, and the method comprises the steps: taking a part design model as input, extracting a grading reference, classifying geometric features and dimensional form and location tolerances through structural analysis, and intelligently complementing missing tolerances in combination with part function requirements and industry specifications, so as to obtain a part standard detection model; binding of dimensional form and location tolerance and geometric features is achieved through a core-auxiliary element dynamic association mechanism, association rationality is automatically checked through a geometric constraint rule, a three-dimensional tolerance zone model is constructed based on an environment-equipment double-compensation algorithm, a tolerance domain with a working condition adaptation boundary is generated, and by means of an equipment-method library of working condition adaptation, a three-dimensional tolerance zone model is established. And according to the part material, the feature priority and the detection environment, automatically matching a measurement device and an evaluation method, integrating detection information through a three-layer verification structured storage architecture, and finally generating a part standard detection model. According to the invention, a function-oriented, working condition-adaptive and standard-unified detection model can be provided for digital transformation in the field of part detection.

Description

Technical Field

[0001] This invention pertains to digital inspection technology for parts, specifically involving a method for constructing a standard inspection model for parts and a computer device. Background Technology

[0002] In the context of modern manufacturing's relentless pursuit of high precision and efficiency, traditional methods of parts inspection and evaluation—relying on manual measurement and experience based on parts design models or drawings—are increasingly revealing numerous significant problems. This approach is not only inefficient and unable to meet the demands of large-scale production, but also suffers from large measurement errors due to the limitations of manual operation, severely impacting product quality stability. Furthermore, poor information flow between different inspection stages creates information silos, hindering collaborative optimization of the production process.

[0003] In key areas such as feature extraction, tolerance analysis, and detection model construction, the current state of technology faces severe challenges: The Dilemma of Tolerance-Surface Relationship: Due to the lack of standardized procedures for PMI (Product Manufacturing Information) annotation by part designers, the relationship between dimensional and geometric tolerance annotations and the constrained set of precise surfaces in the design model is not fully and explicitly expressed in a structured manner. This deficiency not only makes it difficult to accurately map tolerance information to specific geometric surfaces in actual inspection applications, increasing inspection difficulty and error risks, but also, the lack of standardized public interfaces and clear data models severely hinders data interaction and sharing between different systems, restricting the development of automated inspection.

[0004] The urgent need for standardization of inspection models: With the accelerated digital transformation of the manufacturing industry, the compatibility requirements for inspection models across different platforms and systems are increasing. However, the current lack of a unified method for constructing inspection models makes it impossible to effectively integrate design intent, tolerance requirements, and inspection methods. This leads to frequent data loss and format incompatibility issues during cross-platform data exchange, severely limiting the improvement of inspection efficiency and quality control capabilities.

[0005] In summary, how to efficiently and accurately extract the features and tolerance information required for inspection from the part design model, establish a precise correlation between dimensional tolerances and related surfaces, and then construct a standardized inspection model to achieve smooth interconnection between design and inspection information has become a core issue for improving the level of inspection automation and quality control capabilities, and innovative solutions are urgently needed. Summary of the Invention

[0006] The purpose of this invention is to address the problems in existing design models, such as loose correlation between form and position tolerances and geometric features, disconnect between inspection requirements and actual working conditions (environment / equipment), and poor cross-platform reusability of models. It provides a method for constructing a standard inspection model for parts, computer equipment, computer-readable storage media, and computer program products, providing a functionally oriented, working condition-adaptive, and standardized inspection model for the digital transformation of the parts inspection field.

[0007] To achieve the above objectives, one aspect of the present invention provides a method for constructing a standard inspection model for a part, comprising: Step S1: Using the part design model as input, analyze the part design model, extract geometric features, dimensional tolerances and datums, and prioritize the geometric features according to their functional importance, and label them with priority tags; Step S2: Establish the relationship between dimensional and positional tolerances and geometric features and datum elements; verify the rationality of the relationship based on geometric constraint rules; and match the optimal equipment and method according to part attributes, measuring equipment parameters and measurement methods that include working condition constraints. Step S3: Construct a three-layer structured storage architecture consisting of a base layer, a constraint layer, and an execution layer. The base layer stores geometric feature IDs, basic parameters, and priority tags; the constraint layer stores tolerance values, datum relationships, and tolerance accuracy levels; and the execution layer stores measurement methods, equipment parameters, and operating condition constraints. Step S4: Calculate the thermal deformation compensation amount based on the detection environment parameters, calculate the equipment error compensation amount based on the equipment accuracy, generate a three-dimensional tolerance zone model with compensation coefficients, and perform working condition compensation for dimensional and positional tolerances. Step S5: Generate a scene-adaptive detection form and generate a unique identifier, which the device can use to automatically match the measured data; Step S6: Define a unified model pattern, interface protocol, and information access mechanism to ensure that the model can be called across platforms.

[0008] Another aspect of the present invention provides a computer device including a memory, a processor, and a computer program stored in the memory, wherein the processor executes the computer program to implement the steps of the method described above.

[0009] Another aspect of the present invention provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the steps of the method described above.

[0010] Another aspect of the present invention provides a computer program product including a computer program that, when executed by a processor, implements the steps of the method described above.

[0011] According to the part standard inspection model construction method, computer equipment, computer-readable storage medium and computer program product of the present invention, a function-oriented, working condition-adaptive and standard-unified inspection model is provided for the digital transformation of the part inspection field. Attached Figure Description

[0012] To more clearly illustrate the technical solutions of the present invention, the accompanying drawings used in the description of the embodiments of the present invention will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort: Figure 1 This is a flowchart of a method for constructing a standard inspection model for parts according to an embodiment of the present invention; Figure 2 This is a schematic diagram of the construction result of a standard inspection model for parts according to an embodiment of the present invention; Figure 3 This is a structural diagram of a computer device according to an embodiment of the present invention. Detailed Implementation

[0013] To make the objectives, technical solutions, and advantages of this invention clearer, the technical solutions of this invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this invention, and not all embodiments. Based on the embodiments of this invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this invention.

[0014] One embodiment of the present invention provides a method for constructing a standard inspection model for parts. The standard inspection model for parts defined in this embodiment is based on a parametric 3D CAD design model of the parts. Through information parsing driven by functional priority, tolerance-feature association adapted to working conditions, information storage of layered verification, and tolerance zone modeling with double compensation, it achieves deep integration of geometric entities, design intent (dimensional / geometric tolerances), and inspection execution requirements (equipment / methods). It has the characteristics of "machine readability, working condition adaptability, and cross-platform compatibility", and can directly drive automated inspection equipment to support the "design-inspection" data closed loop.

[0015] like Figure 1 As shown, the part standard inspection model construction method of this embodiment includes steps S1-S6.

[0016] Step S1: Analysis of model input and function-oriented information and tolerance refinement: Using the part design model (such as CATIA / UG format) as the basic input, the generated standard inspection model is set as the sole data source for the inspection process to ensure consistency of information transmission. The design model undergoes structured analysis driven by functional priorities. Extract geometric features and classify them according to "functional importance" (P1 level: critical functional features, such as mounting holes and sealing surfaces of aerospace parts; P2 level: general mating features, such as locating pin holes; P3 level: non-matting features, such as process bosses), and automatically label them with priority tags through the "feature-function mapping table". Extract the annotation set (coordinate system, datum, dimensions / geometric tolerances, roughness), general / technical annotations, and material information. Among them, the coordinate system needs to distinguish between the "design coordinate system" and the "inspection datum coordinate system" and clarify the conversion relationship between the two. If dimensional / geometric tolerances are missing or only refer to annotations (such as "unspecified tolerances are filled according to HB5800"), execute "Function-Tolerance Intelligent Matching": combine the part's functional priority (P1 level is filled first) and the industry standard library to automatically recommend tolerance values; for scenarios with multiple optional tolerances (such as hole tolerances H7 / H8), output a three-dimensional comparison suggestion of "tolerance - process cost - inspection accuracy", support manual confirmation and lock the filling result to ensure that the tolerance annotation is "complete and matches the functional requirements", and complete the automatic / interactive filling of tolerances.

[0017] Preferably, the automatic / interactive filling of tolerances includes: Construct an industry feature-function-tolerance mapping database to store the correspondence between typical features of industry parts and functional requirements and default tolerance values; By parsing the functional descriptions in general / technical notes, the functional priority of missing tolerance features can be identified. By combining feature priority and tolerance values ​​recommended by the mapping database, the tolerance is automatically filled. If there are multiple optional values, the tolerance-process cost comparison suggestion is output, and the filling result can be locked after manual confirmation.

[0018] Step S2: Tolerance-feature dynamic association and detection information binding for working condition adaptation: A "core-auxiliary element dynamic association mechanism" is constructed between dimensional / geometric tolerances and geometric features (points, lines, surfaces, holes, shafts, etc.) and datum elements. This mechanism supports real-time linkage and multi-dimensional filtering of "tolerance-feature" relationships, avoiding the static and easily confused problems of existing technologies. Define the priority of element association: core control elements (such as the axis of a hole, the normal vector of a datum plane) are priority 1, auxiliary verification elements (such as the cylindrical surface of a hole, the adjacent positioning surface of a datum plane) are priority 2, and reference elements (such as non-mating surfaces) are priority 3. When associating, extract the core control elements of the features and bind them to priority 1, then identify the auxiliary verification elements and bind them to priority 2. Record the relationship through the "feature ID-priority" mapping table. When collecting detection data, prioritize collecting data of priority 1 elements. If the data of priority 1 is out of tolerance, then the data of priority 2 is called for auxiliary verification. Introducing intelligent verification of association rationality: Based on geometric constraint rules (e.g., diameter dimensions must be associated with cylindrical / spherical surfaces, not arcs; parallelism tolerances must be associated with planes / axis lines, not points), the validity of the association is automatically verified. If an unreasonable situation is found (e.g., associating hole position tolerance with an arc), a pop-up window will prompt "Error type + correction suggestion" (e.g., "Suggest associating hole axis line (ID: H001)"), which will ultimately be confirmed or adjusted by the inspection personnel. When binding inspection information, the system uses the "equipment-method matching library for working conditions" to store equipment parameters (accuracy, applicable materials, working condition range) and measurement methods (including working condition constraints). Based on the part material, feature priority, and inspection environment, the system automatically matches the optimal equipment and method and outputs a "method-accuracy-efficiency" matching report (e.g., "Recommended coordinate measuring machine + least squares method, inspection efficiency improved by 20%, accuracy meets IT6 level requirements").

[0019] In step S2, preferably, the “equipment-method matching library for working conditions” differs from the “matching only by feature type” logic of the prior art and establishes a five-dimensional mapping relationship of “feature priority-material-working condition-equipment-method”.

[0020] Preferably, in the actual association process, the association between tolerance and geometric features is for the scenario of "one tolerance associated with multiple entities" (such as the hole position degree associated with the axis and the cylindrical surface), and is implemented through the logic of "core element dominance and auxiliary element verification" - during the inspection, the core element (axis) data is collected first. If the core element is out of tolerance, the auxiliary element (cylindrical surface) data is called for secondary verification, thus avoiding the problem of "chaotic data of multiple entity association" in the prior art.

[0021] Step S3: Information storage and visualization of hierarchical verification A three-tier structured storage architecture is constructed to overcome the problems of lack of information verification and chaotic cross-layer access in existing technologies, achieving "hierarchical classification, dynamic verification, and visual traceability" of information. Base layer: Stores geometric feature IDs (format: part number-feature type-priority-serial number, such as AE001-Hole-P1-001) and basic parameters (such as hole diameter φ10mm, length 20mm). Set "ID uniqueness + parameter rationality" verification (geometric feature IDs must be unique, and basic parameters must conform to the geometric constraints of the design model, such as diameter > 0, length > depth). Constraint layer: Stores tolerance values ​​(e.g., P1 grade hole position tolerance 0.02mm), datum association relationships (e.g., position tolerance associated with datum A / B), tolerance accuracy level (e.g., IT6), and sets "tolerance value conforms to GPS standard + datum system integrity" verification (tolerance value must be within the national standard allowable range, and position tolerance must be associated with at least one primary datum). Execution layer: Stores the matching measurement equipment (e.g., coordinate measuring machine model XXX), measurement method (least square method), and operating condition constraints (temperature 20±0.5℃), and sets up "method-accuracy matching + equipment operating condition adaptation" verification (the measurement method must match the feature accuracy, and the equipment parameters must be within the rated range). Visual presentation: The left side of the interface displays a "dynamically associated BOM (Bill of Materials) tree" (node ​​colors correspond to priorities: P1 red, P2 blue, P3 gray). Clicking on any node (such as P1 level hole) automatically expands the entire chain of information "parameter-tolerance-equipment-method"; the right side synchronously displays a simplified view of geometric features, with associated elements highlighted in different colors (priority 1 red, priority 2 blue).

[0022] Step S4: 3D modeling and interactive display of dimensional and positional tolerances for working condition compensation: To address the shortcomings of existing tolerance zone models, which are "static and do not consider actual working conditions," a "dual-compensation tolerance zone modeling method based on environment and equipment" is proposed to achieve adaptation of the tolerance zone to actual testing conditions. Environmental compensation calculation: Input the detection environment parameters (temperature, humidity), and calculate the thermal deformation Δ based on the thermal expansion coefficient of the part material. L If the humidity is greater than 65%, an additional humidity compensation of 0.001 mm / mm will be applied to non-metallic features. H ; Equipment error compensation: The repeatability accuracy σ of the detection equipment is retrieved from the equipment library, and the equipment error compensation amount Δσ=2σ is calculated based on the 95% confidence interval; Tolerance zone boundary calculation: Upper boundary = original upper deviation + (Δ L +Δσ), lower boundary = original lower deviation - (Δσ) L +Δσ), generating a compensation coefficient K=Δ L +Δσ is a three-dimensional tolerance zone model (e.g., the cylindricity tolerance zone is "original upper and lower boundary diameter ± K (coaxial cylindrical surface); Interactive adjustment: Supports simulation of different temperature ranges and different equipment accuracies. The tolerance zone model and the solid geometry of the part are displayed on the same screen on the right side of the interface. Supports "operating condition simulation interaction" - drag the temperature slider or select different equipment to update the tolerance zone boundary and K value change curve in real time, which helps to judge the impact of operating conditions (environment / equipment) on the test results.

[0023] Step S5: Scene-adaptive detection form output and hierarchical lightweight processing: Overcoming the problems of "fixed format and lightweight, undifferentiated models" in existing technologies, this technology achieves "scenario-adaptive output and hierarchical retention of key information": 1) Scenario-adaptive form generation: Workshop on-site inspection form: includes "serial number, view, tolerance category, upper / lower tolerance, associated feature ID, quick judgment threshold (e.g., "the measured value is qualified if it is within 10±0.02mm"), simplified measurement steps (e.g., "1. locate datum A; 2. use a coordinate measuring machine to measure 3 points and take the average")", adapted for rapid on-site inspection; Laboratory precision testing form: Add "Number of repeated measurements (e.g., 3 times), data confidence requirements (e.g., R²≥0.99), and operating condition record column (temperature / humidity / equipment number)" to adapt to high-precision calibration; The form generates a unique identifier (format: detection model ID-form type-generation time, such as DM-AE001-Lab-20240915), which allows the detection equipment to automatically match and fill in the measured data (e.g., the coordinate measuring machine automatically fills in the "measured size" field with the measured aperture value of 10.005mm). 2) Tiered lightweighting process: P1 level features: Preserve high-precision geometric data (such as NURBS surface parameters and axis vectors) to ensure that the detection accuracy is not compromised; P2 level features: Simplify to a patch model (e.g., simplify a cylindrical surface to a 16-patch model), while retaining key parameters (diameter / length). P3 level features: Remove unnecessary geometric details (such as the chamfered arc of process bosses), and retain only the feature ID and basic attributes; The lightweight model reduces its size by more than 60%, and the integrity of the P1-level feature detection data reaches 100%, adapting to the loading requirements of different devices (workshop tablets / laboratory workstations).

[0024] The scene adaptation form generation in step S5 also includes: Customizable field extension: Inspection process personnel can add a "Special Inspection Requirements" field and set input rules; Data association function: The form identifier is bound to the detection model ID. After the detection device collects data, the measured value is automatically filled into the corresponding field through the identifier. Archive and import adaptation: Supports exporting in PDF / A and XML formats. Exported files contain digital signatures, and PDF / A files automatically embed a lightweight view of the detection model.

[0025] Step S6: Standardization and normalization of construction methods: To address the issues of poor cross-platform compatibility and ambiguous interface protocols in existing technologies, a comprehensive standardization system is established based on the ISO10303-242 (STEPAP242) standard. Model pattern unification: Define "design-inspection" data mapping rules, such as the "datum plane" in the design model corresponding to the "P1 level datum feature" in the inspection model, and the "..." in the dimension annotation. φ "10H7" corresponds to "diameter tolerance (upper deviation +0.015mm, lower deviation 0mm, associated cylindrical surface ID: C001)" in the inspection model, ensuring that design models from different CAD platforms (CATIA / UG) can be parsed uniformly. Interface protocol definition: Clearly define the full-link interfaces for "model import - data interaction - detection feedback": Import interface: Supports CATIA V5 / V6 and UGNX12.0+ formats; Equipment Interface: Establish communication protocols with different coordinate measuring machines to support real-time uploading of test data; Information access mechanism: "SQL+XML hybrid storage" is adopted - structured data (such as feature IDs and tolerance values) are stored in an SQL database (MySQL 8.0+), and unstructured data (such as tolerance zone models and form templates) are stored as XML files. "Read and write permission levels" are set (such as inspection designers can modify execution layer data, while inspection personnel can only read it) to ensure data security and traceability.

[0026] The following example further illustrates the part standard inspection model construction method of this invention. The construction result is as follows: Figure 2 As shown.

[0027] Step S1: Import the part design model and analyze its features. Model Import: Import CATIA format part design models using the "Model Library Parsing Tool" and automatically extract geometric features. P1 grade: φ10H7 mounting hole (ID: H-P1-001~003), reference surface A (sealing surface, ID: D-P1-001). P2 grade: φ8f8 positioning hole (ID: H-P2-001~002), datum plane B (positioning plane, ID: D-P2-001). P3 grade: Process boss (ID: B-P3-001); Annotation set extraction: The design coordinate system is O-XYZ, and the detection reference coordinate system is established with reference plane A (Z=0) and reference plane B (X=0), constructing a transformation matrix; extracting... φ The 8F8 positioning hole does not specify the positional tolerance; it only notes "according to HB5800-2004". Tolerance intelligent filling: recognition φ 8F8 is a P2-level positioning hole. The HB5800-2004 library is used, and the recommended positional tolerance is 0.05mm (associated with datum A / B). At the same time, the "cost-accuracy suggestion" is output: "If 0.03mm is selected, coordinate measuring machine measurement is required (cost +20%); if 0.05mm is selected, gauge inspection can be used (efficiency +30%)". After the inspector confirms the selection of 0.05mm, the system automatically completes the tolerance annotation.

[0028] Step S2: Correlation between dimensional and geometrical tolerances 1) Dynamic association: φ The 10H7 mounting hole position accuracy (0.02mm) is associated with the core element "hole axis (ID: H-P1-001-Axis)" (priority 1) and the auxiliary element "cylindrical surface (ID: H-P1-001-Surf)" (priority 2); φ The positional accuracy of the 8F8 positioning hole (0.05mm) is associated with the core element "hole axis (ID: H-P2-001-Axis)" (priority 1); 2) Intelligent verification: The system detects " φ The initial association of the 8f8 positioning hole position to the arc (ID: Arc-001) was displayed. An error message appeared: "The positioning hole position needs to be associated with the axis / cylindrical surface. It is recommended to associate it with the axis H-P2-001-Axis." The association took effect after the inspection personnel confirmed the modification. 3) Inspection information binding: The "Working condition adaptation library" matches the coordinate measuring machine with the least squares method according to "P1 grade titanium alloy hole + 25℃", and outputs the adaptation report: "Measurement efficiency: 30s per hole, accuracy: ±0.001mm, meets IT7 level requirements"; the P2 grade positioning hole matches the digital caliper with the maximum entity requirement, and the report is: "Measurement efficiency: 10s per hole, accuracy: ±0.005mm, meets IT8 level requirements".

[0029] Step S3: Hierarchical and categorized storage and display of information 1) Tiered storage: Base layer: H-P1-001 ( φ (10mm, length 15mm), verification "diameter > 0, length > 0" passed; Constraint layer: H-P1-001 position accuracy 0.02mm, associated datum A / B, verification of "datum system integrity" passed; Execution layer: H-P1-001 Hexagon measuring device, calibration "device accuracy ≥ 0.002mm" passed; 2) Visualization: In the BOM tree on the left, node H-P1-001 is displayed in red; expanding it reveals… φ 10mm+0.015 / 0mm (Tolerance + Coordinate Measuring Tool (Equipment)); In the right view, the hole axis is highlighted in red, and the cylindrical surface is highlighted in blue. Clicking the axis node will automatically display "Measurement path: Hole opening → Hole middle → Hole bottom (2:3:2 sampling)".

[0030] Step S4: 3D expansion display of dimensional and geometric tolerances, double-compensated tolerance zone modeling 1) Compensation calculation: Environmental compensation: The coefficient of thermal expansion of titanium alloy is 23× / ℃, T =25℃, ΔL=10mm×23× ×(25-20)=0.00115mm; Equipment compensation: coordinate measuring machine σ =0.002mm, Δ σ =2×0.002=0.004mm; Total compensation K =0.00115+0.004≈0.005mm; 2) Tolerance zone modeling: φ The positional tolerance zone of the 10H7 mounting hole is "original upper deviation + 0.02mm + 0.005mm = 0.025mm, original lower deviation 0mm - 0.005mm = -0.005mm", which is displayed in the 3D model as "coaxial cylindrical surface of φ10.025mm / φ9.995mm". 3) Interactive simulation: Drag the temperature slider to 35℃, ΔL increases to 0.0023mm, K=0.0063mm, the upper boundary of the tolerance zone is updated to 0.0263mm, and the interface prompts "The temperature has risen to 35℃, it is recommended to recalibrate the equipment".

[0031] Step S5: Detect the form output 1) Form generation: Workshop Form: Serial Number 1, View "Main View", Tolerance Category "Position Degree", Upper Tolerance 0.025mm, Lower Tolerance -0.005mm, Associated Feature ID "H-P1-001", Quick Judgment Threshold "9.995mm≤Measured Diameter≤10.025mm"; Laboratory form: Add "3 repeated measurements, confidence level R² ≥ 0.99, operating conditions record: 25℃ / 50%"; 2) Lightweight: P1-level mounting holes retain NURBS surface parameters; The P2 level positioning hole is simplified to an 8-facet model; For P3 grade process bosses, remove the chamfered arc and only retain "ID+B-P3-001+size 10×5mm"; After lightweighting, the model size was reduced from 20MB to 8MB, and the loading time of the coordinate measuring machine was shortened from 15s to 5s.

[0032] Step S6: Standardization and Normalization Model mode: Map "CATIA Design Datum A" to "Detection P1 Level Datum Feature D-P1-001" according to STEPAP242 to ensure that the UG platform can parse it normally; Interface Protocol: The coordinate measuring machine reads the model via the TCP / IP protocol, with a data interaction delay of 80ms. The measured data is automatically uploaded to the "Measured Dimensions" field of the form. Information storage: The SQL database stores the ID / tolerance / equipment information of H-P1-001, and the XML file stores the tolerance zone model. The inspection designer has modification permission, and the inspection personnel can only read the data to ensure that the data cannot be tampered with.

[0033] In summary, the part standard inspection model construction method of this invention takes the parametric 3D CAD design model of the part as input. Through structured analysis, it extracts the design coordinate system, hierarchical datum, classification geometric features, and dimensional / geometric tolerances. It intelligently completes missing tolerances by combining part functional requirements and industry standards, and establishes a transformation relationship between the design coordinate system and the inspection datum coordinate system, solving the problem of loose datum association in existing technologies. A core-auxiliary element dynamic association mechanism is used to bind dimensional / geometric tolerances to geometric features, and geometric constraint rules are used to automatically verify the rationality of the association, overcoming problems such as confusion and lack of association verification in static associations. A 3D tolerance zone model is constructed based on an environment-equipment dual compensation algorithm, generating a tolerance domain with working condition adaptation boundaries. Using a working condition-adaptive equipment-method library, measurement equipment and evaluation methods are automatically matched according to part material, feature priority, and inspection environment to generate executable inspection instructions. Inspection information is integrated through a three-layer verification structured storage architecture, with independent verification rules set for each layer, avoiding problems such as unverified form outputs and unlayered information storage. The final generated standard inspection model for parts has the characteristics of "machine readability, working condition adaptability, and cross-platform compatibility". It effectively solves the shortcomings of loose correlation between tolerance and feature in existing design models and the disconnect between inspection requirements and actual working conditions. It provides a standardized data source for the digital inspection of high-precision parts such as typical aerospace parts and improves inspection efficiency.

[0034] Compared with traditional methods, the part standard inspection model construction method of this invention has the following advantages: 1. Driving the Digital Transformation of Inspection: It provides a tailor-made inspection model for the digital inspection of parts, effectively addressing the shortcomings of existing design models in terms of tolerance annotation and inspection requirements. By accurately linking dimensional tolerances with inspection features, it provides inspection personnel with clear inspection and evaluation methods, becoming a key bridge connecting the digital design definition of products with digital quality inspection, and powerfully promoting the digitalization process of aircraft parts inspection.

[0035] 2. Improved testing efficiency and accuracy: Automated information extraction, correlation, and modeling processes reduce manual intervention, minimize human error, and improve testing efficiency. Simultaneously, standardized data structures and well-defined testing methods ensure more accurate and reliable results, contributing to improved product quality stability.

[0036] 3. Enhanced system compatibility and interoperability: Standardized and normalized construction methods and unified interface protocols ensure that the model can be seamlessly connected and exchange data between different platforms and systems, improving the synergy of the entire detection process.

[0037] 4. Adapting to the Development Needs of Intelligent Manufacturing: The method of this invention provides strong support for closed-loop product quality control driven by digital twins and flexible production in intelligent manufacturing. By constructing a precise detection model, product quality information can be fed back in real time, enabling dynamic adjustment and optimization of the production process, thus meeting the requirements of intelligent manufacturing for precise product quality control and production flexibility.

[0038] Embodiments of the present invention also provide a computer device, which may be a server, and its internal structure diagram may be as follows: Figure 3 As shown. The computer device includes a processor, memory, and a network interface connected via a system bus. The processor provides computing and control capabilities. The memory includes a non-volatile storage medium and internal memory. The non-volatile storage medium stores an operating system, computer programs, and a database. The internal memory provides an environment for the operation of the operating system and computer programs in the non-volatile storage medium. The database stores operating parameter data for various components. The network interface communicates with external terminals via a network connection. When executed by the processor, the computer program implements the steps of the method according to embodiments of the present invention.

[0039] Those skilled in the art will understand that Figure 3The structure shown is merely a block diagram of a portion of the structure related to the present application and does not constitute a limitation on the computer device to which the present application is applied. Specific computer devices may include more or fewer components than those shown in the figure, or combine certain components, or have different component arrangements.

[0040] Embodiments of the present invention also provide a computer-readable storage medium having a computer program stored thereon, wherein the computer program, when executed by a processor, implements the steps of the method of the embodiments of the present invention.

[0041] Embodiments of the present invention also provide a computer program product, including a computer program that, when executed by a processor, implements the steps of the method of the embodiments of the present invention.

[0042] The foregoing has only described certain exemplary embodiments of the present invention by way of illustration. Undoubtedly, those skilled in the art can modify the described embodiments in various ways without departing from the spirit and scope of the present invention. Therefore, the foregoing drawings and descriptions are illustrative in nature and should not be construed as limiting the scope of protection of the claims of the present invention.

Claims

1. A method for constructing a standard inspection model for parts, characterized in that, include: Step S1: Using the part design model as input, analyze the part design model, extract geometric features, dimensional tolerances and datums, and prioritize the geometric features according to their functional importance, and label them with priority tags; Step S2: Establish the relationship between dimensional and positional tolerances and geometric features and datum elements; verify the rationality of the relationship based on geometric constraint rules; and match the optimal equipment and method according to part attributes, measuring equipment parameters and measurement methods that include working condition constraints. Step S3: Construct a three-layer structured storage architecture consisting of a base layer, a constraint layer, and an execution layer. The base layer stores geometric feature IDs, basic parameters, and priority tags; the constraint layer stores tolerance values, datum relationships, and tolerance accuracy levels; and the execution layer stores measurement methods, equipment parameters, and operating condition constraints. Step S4: Calculate the thermal deformation compensation amount based on the detection environment parameters, calculate the equipment error compensation amount based on the equipment accuracy, generate a three-dimensional tolerance zone model with compensation coefficients, and perform working condition compensation for dimensional and positional tolerances. Step S5: Generate a scene-adaptive detection form and generate a unique identifier, which the device can use to automatically match the measured data; Step S6: Define a unified model pattern, interface protocol, and information access mechanism to ensure that the model can be called across platforms.

2. The method according to claim 1, characterized in that, In step S1, the geometric features are divided into key functional features, general compliant features and non-compliant features, and priority labels are marked by a feature-function mapping table.

3. The method according to claim 1 or 2, characterized in that, In step S1, if there are missing dimensional and positional tolerances, the tolerances are automatically or interactively filled in by combining the part's functional priority and the industry standard library.

4. The method according to claim 3, characterized in that, Automatic or interactive filling of tolerances includes: Construct an industry feature-function-tolerance mapping database to store the correspondence between typical features of industry parts and functional requirements and default tolerance values; By analyzing the functional descriptions in the part design model annotations, the functional priority of missing tolerance features can be identified. By combining feature priority and tolerance values ​​recommended by the mapping database, the tolerance is automatically filled. If there are multiple optional values, the tolerance-process cost comparison suggestion is output, and the filling result is locked after manual confirmation.

5. The method according to claim 1 or 2, characterized in that, In step S2, establishing the relationship between dimensional and positional tolerances and geometric features and datum elements includes: Define element priorities: core control elements are priority 1, auxiliary verification elements are priority 2, and reference elements are priority 3. When associating tolerances, first extract the core control elements of the features and bind them to the first priority, then identify the auxiliary verification elements and bind them to the second priority; When collecting detection data, priority is given to collecting data of the first priority element. If the data of the first priority element is out of tolerance, the data of the second priority element is then used for auxiliary verification.

6. The method according to claim 1 or 2, characterized in that, In step S3, the three-layer structure is verified: Base layer verification: Geometric feature IDs are unique, and basic parameters conform to the geometric constraints of the design model; Constraint layer verification: The tolerance value is within the allowable range of the national standard, and the positional tolerance is associated with at least one reference. Execution layer verification: The measurement method and feature accuracy are matched, and the equipment parameters are within the rated range.

7. The method according to claim 1 or 2, characterized in that, In step S4, different temperature ranges and different equipment accuracies are simulated, the tolerance zone model is updated in real time, and the K value change curve is displayed to help determine the impact of working conditions on the test results.

8. The method according to claim 1 or 2, characterized in that, In step S5, the scene-adapted testing forms include workshop field testing forms and laboratory precision testing forms. The workshop field testing forms include fields for quick determination thresholds and simplified measurement steps, while the laboratory precision testing forms add fields for the number of repeated measurements and data confidence requirements.

9. The method according to claim 1 or 2, characterized in that, In step S6, the data mapping relationship between the design model and the detection model is defined, the full-link interface of model import-data interaction-detection feedback is clarified, and SQL+XML hybrid storage is adopted, with structured data stored in the SQL database and unstructured data stored in XML files.

10. A computer device, comprising a memory, a processor, and a computer program stored in the memory, characterized in that, The processor executes the computer program to implement the steps of the method according to any one of claims 1-9.

Images