An Automatic Annotation Method for Engineering Data Based on Feature Orientation Matching

Abstract

This invention discloses an automatic engineering data annotation method based on feature direction matching, belonging to the field of intelligent engineering annotation technology. It includes constructing a three-dimensional machining restricted area mesh model, generating an optimized annotation space coordinate set through composite feature direction vectors, and generating multi-field interconnected engineering diagrams through virtual machining simulation. Based on a dynamic response system for engineering data, it obtains updated annotation content, drives the annotation content to respond in real-time to changes in the physical field, and constrains the motion trajectory of the manufacturing equipment. Through the avoidance behavior of manufacturing constraints and the updated annotation content, an interlocking mechanism is formed for the real-time response behavior to changes in the physical field, enabling automatic annotation of engineering data. This invention, by establishing a dynamic response system for engineering data, an interlocking mechanism, and a three-dimensional machining restricted area mesh model, anticipates and avoids collision risks caused by dynamic changes in the workpiece, ensuring physical safety and dimensional accuracy of the final product during high-precision machining.

Description

Technical Field

[0001] This invention belongs to the field of intelligent engineering annotation technology, specifically relating to an automatic annotation method for engineering data based on feature direction matching. Background Technology

[0002] Automatic annotation technology for engineering data based on feature orientation matching plays a crucial role in the field of intelligent engineering annotation. In modern digital design and manufacturing, engineering data annotation is a core part of the product development process, responsible for transmitting key information such as geometric dimensions, geometric tolerances, and physical properties. Currently, existing technologies have achieved in-depth analysis of the geometric features of 3D models, enabling the automated generation and optimized layout of engineering drawing dimensions, effectively solving the problem of generating clear and accurate 2D drawings from static models.

[0003] However, in precision manufacturing scenarios such as CNC machining, which are closely coupled with the physical world, the limitations of the aforementioned static annotation methods are becoming increasingly apparent. During actual machining, the workpiece is affected by multiple physical field factors such as cutting heat and ambient temperature, resulting in real-time geometric deformation. This leads to a significant "data-to-object" deviation between the static CAD model generated during the design phase and the actual workpiece during physical machining. Traditional automated annotation systems generate key parameters such as toolpaths and safety boundaries based on static model data under ideal conditions, lacking a mechanism for perceiving and responding to dynamic changes in the physical machining environment, making it difficult to adapt to fluctuations in operating conditions during actual machining. Therefore, establishing an automated annotation method that can transform engineering drawings from static information carriers into dynamic manufacturing constraints, enabling them to respond in real-time to changes in the physical field and dynamically guide manufacturing equipment to avoid risks, is a critical technical bottleneck that urgently needs to be addressed in the field of intelligent manufacturing. Summary of the Invention

[0004] In view of the aforementioned existing problems, the present invention is proposed.

[0005] Therefore, this invention provides an automatic annotation method for engineering data based on feature direction matching, which solves the real-time coordination problem of manufacturing equipment avoidance after the dynamic change response of the workpiece's physical field.

[0006] To solve the above-mentioned technical problems, the present invention provides the following technical solution:

[0007] In a first aspect, the present invention provides an automatic annotation method for engineering data based on feature direction matching, comprising the following steps: S1. Extract the geometric normal vector of the target feature, combine it with multi-physics data, and generate a composite feature direction vector in the direction of physical field enhancement. S2. Construct a three-dimensional machining restricted area mesh model, generate an optimized set of labeled spatial coordinates through composite feature direction vectors, and generate multi-field interconnected engineering drawings through virtual machining simulation; S3. By activating the collaborative mechanism of physical field response rules and repulsive field optimization engine through multi-field interconnected engineering diagrams, a dynamic response system for engineering data is established. S4. Based on the dynamic response system of engineering data, drive the annotation content to respond to changes in the physical field in real time, obtain the updated annotation content, and constrain the motion trajectory of the manufacturing equipment. S5. Based on the spatial conflict feedback generated by the movement trajectory avoidance behavior of manufacturing equipment, the repulsion field algorithm is triggered to form the avoidance behavior of manufacturing constraints. S6. By creating constraint avoidance behavior and updated annotation content, an interlocking mechanism is formed for the real-time response behavior to changes in the physical field, and engineering data is automatically annotated.

[0008] Furthermore, S1 specifically refers to: Extract the geometric normal vector of the target feature using CAD software; Based on the functional requirements of the target characteristics in the project, the design intent direction is obtained, and multi-physics field-intent coupling weight coefficients are generated through the physical field contribution ratio quantification rule. By superimposing the multiphysics data with the target feature geometric normal vector through the multiphysics-intent coupling weight coefficient, a composite feature direction vector in the direction of physical field enhancement is generated.

[0009] Furthermore, in S2, a three-dimensional machining restricted area mesh model is constructed, and an optimized set of annotation space coordinates is generated through composite feature direction vectors, including: Based on the envelope parameters of machining tools and the thermal deformation characteristics of workpiece materials, a three-dimensional machining restricted area mesh model is generated by spatial discretization mesh generation to obtain the boundary of the machining restricted area. The initial position of the annotation located on the vertical projection plane of the composite feature direction vector is obtained through the repulsion field algorithm engine, and the dynamic distance between the initial position of the annotation and the boundary of the processing restricted area is detected in real time. When the dynamic spacing of the boundary collision avoidance is less than the safety threshold, the annotation position is dynamically adjusted to generate an optimized set of annotation space coordinates.

[0010] Furthermore, in S2, multi-field interconnected engineering diagrams are generated through virtual manufacturing simulation, including: Based on the optimized set of annotation space coordinates, annotation text is automatically generated in CAD, and the tool path is generated by triggering CAM software through API to perform virtual machining collision detection between workpiece and tool; During the virtual manufacturing collision detection process, the unavoidable areas are iteratively optimized, and multi-field interconnected engineering diagrams are output.

[0011] Furthermore, S3 specifically refers to: Based on the changes in the multi-physics field in the multi-field interconnected engineering diagram, the response rules of each physics field are triggered to execute the annotation attribute update and position correction. Based on the processing restricted area boundary in the multi-field interconnected engineering diagram, the optimal offset path of the annotation point under the constraint of the composite feature direction vector is dynamically obtained. A dynamic response system for engineering data is established based on the collaborative mechanism of physical field response rules and repulsive field optimization engine.

[0012] Furthermore, S4 specifically refers to: Through the dynamic response system of engineering data, the annotation content is driven to respond to changes in the physical field in real time, and the updated annotation content is obtained. By decoupling the feature directions, the spatial coordinates and direction components of the composite feature direction vector are analyzed. Combined with the equipment coordinate transformation matrix, the motion parameters of each axis of the manufacturing equipment are generated, and the motion control commands of the manufacturing equipment are obtained. By combining the updated annotations with the motion control commands of the manufacturing equipment, the motion trajectory of the manufacturing equipment is dynamically constrained.

[0013] Furthermore, S5 specifically refers to: By monitoring the movement trajectory of manufacturing equipment, the interference status of the processing restricted area boundary is monitored in real time, and spatial conflict feedback is generated; Based on spatial conflict feedback, the obstacle avoidance force field is obtained through a repulsive field algorithm; Based on the spatial vector data of the obstacle avoidance force field, a path offset correction value is generated using the principle of vector superposition. By correcting the path offset, the motion trajectory is reconstructed, an obstacle avoidance path is formed at the boundary of the processing restricted area, and the avoidance behavior of the initial manufacturing constraints is generated.

[0014] Furthermore, S6 specifically refers to: Based on the avoidance behavior of the initial manufacturing constraints and the updated annotation content, the key dynamic parameters of the physical field change response behavior are continuously monitored to generate interlock judgment signals that characterize the state anomaly. By combining interlock judgment signals, the process controller controls the automatic annotation of engineering data, performs real-time updates of annotation content and spatial repositioning operations, and obtains dynamic annotation content; By using the real-time update results of dynamically labeled content, the topological reconstruction calculation of the restricted area boundary is triggered to induce constraint avoidance behavior, and the spatial coordinates of the processing restricted area boundary are updated.

[0015] In a second aspect, the present invention provides a computer device, including a memory and a processor, wherein the memory stores a computer program, wherein: when the computer program is executed by the processor, it implements any step of the automatic annotation method for engineering data based on feature orientation matching as described in the first aspect of the present invention.

[0016] Thirdly, the present invention provides a computer-readable storage medium having a computer program stored thereon, wherein: when the computer program is executed by a processor, it implements any step of the automatic annotation method for engineering data based on feature orientation matching as described in the first aspect of the present invention.

[0017] The beneficial effects of this invention are as follows: By establishing a dynamic response system and interlocking mechanism for engineering data, this invention transforms engineering drawings into dynamic instructions that can respond in real time to changes in physical fields such as thermal deformation during processing. This directly guides and corrects the movement trajectory of the manufacturing equipment. On this basis, by constructing a three-dimensional processing restricted area mesh model that integrates the thermal deformation characteristics of materials and combining it with a repulsive field algorithm for real-time obstacle avoidance, this invention anticipates and avoids collision risks caused by dynamic changes in the workpiece, ensuring physical safety and dimensional accuracy of the final product during high-precision processing. Attached Figure Description

[0018] To more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings used in the following description of the embodiments will be briefly introduced. 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.

[0019] Figure 1 The flowchart shows a method for automatic annotation of engineering data based on feature orientation matching. Figure 2 Flowchart for generating composite feature direction vectors and multi-field interconnection engineering graphs; Figure 3 A flowchart for establishing a dynamic response system for engineering data and defining motion constraints; Figure 4 Flowchart for creating constraint avoidance and interlocking mechanisms. Detailed Implementation

[0020] To make the above-mentioned objects, features and advantages of the present invention more apparent and understandable, the specific embodiments of the present invention will be described in detail below with reference to the accompanying drawings.

[0021] Many specific details are set forth in the following description in order to provide a full understanding of the invention. However, the invention may also be practiced in other ways different from those described herein, and those skilled in the art can make similar extensions without departing from the spirit of the invention. Therefore, the invention is not limited to the specific embodiments disclosed below.

[0022] Secondly, the term "one embodiment" or "embodiment" as used herein refers to a specific feature, structure, or characteristic that may be included in at least one implementation of the present invention. The phrase "in one embodiment" appearing in different places in this specification does not necessarily refer to the same embodiment, nor is it a single or selective embodiment that is mutually exclusive with other embodiments.

[0023] Reference Figures 1-4 This is one embodiment of the present invention, which provides an automatic annotation method for engineering data based on feature direction matching, including the following steps:

[0024] S1. Extract the target feature geometric normal vector and combine it with multi-physics data to generate a composite feature direction vector in the direction of physical field enhancement.

[0025] In this embodiment, CAD software is used to perform topological boundary identification and parametric surface equation analysis on the target geometric entity. Based on the spatial surface normal vector components in the three-dimensional absolute coordinate system, the target feature geometric normal vector containing spatial position coordinates and direction cosine values ​​is obtained.

[0026] Based on the functional requirements of the target characteristics in the project, the design intent direction is obtained, and multi-physics field-intent coupling weight coefficients are generated through the physical field contribution ratio quantification rule. Among them, the workpiece being processed is defined as the target workpiece. The target features and functional requirements are derived from the analysis and processing results of product functional specification documents and manufacturing process requirement documents in the engineering scenario, such as the engineering requirement description of surface machining accuracy tolerance standards for mechanical parts or material strength bearing limit indicators. The physical field contribution ratio quantification rule is to calculate the absolute value ratio of the projection components of each physical field vector in the design intent direction in the multi-physics data, perform normalization mapping operations, and generate mathematical transformation rules for multi-physics-intent coupling weight coefficients. Based on the functional requirements of the target features in the engineering, key constraint parameters are defined, the directional reference value is calculated in the three-dimensional spatial coordinate system, and the design intention direction matching the functional requirements is obtained; the physical field contribution ratio quantification rule is applied to obtain the influence weight value of the multi-physics field, and a multi-physics field-intention coupling weight coefficient containing specific weight factor values ​​is generated. By superimposing the multiphysics data with the target feature geometric normal vector weighted by the multiphysics-intent coupling weight coefficient, a composite feature direction vector in the direction of physical field enhancement is generated. The multiphysics data includes electromagnetic field intensity distribution, fluid velocity vector, and thermodynamic temperature gradient field. The target feature geometric normal vector is scaled using a multiphysics-intent coupling weight coefficient, and the contribution weight scaling operation is performed on each physics vector in the multiphysics data. All scaled physics vectors are then added in a three-dimensional coordinate system to generate an intermediate superimposed vector. Finally, the intermediate superimposed vector is normalized to a normalized magnitude, and the output is a unitized direction vector as the composite feature direction vector in the physics enhancement direction.

[0027] S2. Construct a three-dimensional machining restricted area mesh model, generate an optimized set of labeled spatial coordinates through composite feature direction vectors, and generate multi-field interconnected engineering drawings through virtual machining simulation.

[0028] Based on the envelope parameters of machining tools and the thermal deformation characteristics of workpiece materials, a three-dimensional machining restricted area mesh model is generated by spatial discretization to obtain the boundary of the machining restricted area.

[0029] It should be noted that the envelope parameter refers to the dynamic vibration compensation amount obtained by superimposing the cutting edge radius of the tool through the radius of the tool volume envelope surface during end mill machining; the thermal deformation characteristics of the workpiece material are a set description of the linear expansion coefficient tensor, elastic modulus temperature gradient function, and yield strength temperature decay function of the material under machining temperature rise conditions. Based on the envelope parameters in machining tools, the spatial occupancy equation of the tool motion sweep volume is defined. At the same time, the thermal expansion strain tensor is obtained by combining the thermal deformation characteristics of the workpiece material. In the three-dimensional space of the workpiece and the tool, spatial discretization mesh is performed, and the partitioning operation generates a set of spatial voxels covering the thermal deformation offset field and the tool sweep envelope area. The spatial voxel set is subjected to isosurface extraction processing to obtain the spatial vertex coordinate set of the closed surface boundary, and the machining restricted area boundary containing the topological connection relationship is output.

[0030] The initial position of the annotation located on the vertical projection plane of the composite feature direction vector is obtained through the repulsion field algorithm engine, and the dynamic distance between the initial position of the annotation and the boundary of the processing restricted area is detected in real time. Furthermore, using the repulsive field algorithm engine, based on the labeled repulsive potential energy function, the coordinates of the zero potential energy point are calculated in the normal plane of the composite feature direction vector to generate the initial labeling position; at the same time, by accelerating the detection structure through spatial distance, the spatial coordinates of the initial labeling position are calculated with the vertex set of the triangular mesh of the processing restricted area boundary, and the dynamic anti-collision distance between the initial labeling position and the processing restricted area boundary is output in real time.

[0031] When the dynamic spacing for boundary collision avoidance is less than the safety threshold, the annotation position is dynamically adjusted to generate an optimized set of annotation space coordinates. The safety threshold is derived from the empirical value of the maximum vibration amplitude of machining tools and the machine tool repeatability tolerance value. When the dynamic distance between the initial annotation position and the boundary of the processing restricted area is less than the safety threshold, the repulsive field gradient descent optimizer is activated. Position offset iteration is performed in the vertical projection plane of the composite feature direction vector. Based on the initial annotation position, a spatial gradient descent direction vector is constructed. The annotation point is moved along the negative potential energy gradient direction with an adaptive step size. After each movement, the minimum distance value with the processing restricted area boundary is re-acquired until the distance value meets the safety threshold requirement or the maximum number of iterations is reached. Finally, the set of coordinate values ​​of the convergence position is output as the optimized annotation spatial coordinate set.

[0032] Based on the optimized set of annotation space coordinates, annotation text is automatically generated in CAD, and the tool path is generated by triggering CAM software through API to perform virtual machining collision detection between workpiece and tool; Furthermore, based on the spatial vertex coordinate data of the optimized annotation space coordinate set, the geometric constraint matching interface of the CAD software is used to automatically associate the feature topology of the 3D model. The annotation text object instantiation operation is performed in the CAD software interface to generate annotation text objects containing tolerance symbols and dimension value information. At the same time, the tool path planning kernel of the CAM software is triggered through the inter-process communication API. Based on the feature positioning parameters of the optimized annotation space coordinate set, a set of five-axis machine tool center point paths is generated, the workpiece geometric mesh model is executed, and the virtual machining collision detection results of the non-contact area are output.

[0033] During the virtual manufacturing collision detection process, the unavoidable areas are iteratively optimized, and multi-field interconnected engineering diagrams are output. Furthermore, when the virtual machining collision detection results show the existence of unavoidable areas, the annotation position optimization calculator based on gradient backpropagation is activated. The set of vertex indices of the collision area is extracted based on the depth information field data of the workpiece-tool spatial interference area. The conflict coordinate points are marked in the optimized annotation space coordinate set based on the set of vertex indices of the collision area. The original annotation position coordinates are corrected by dynamic compensation parameters. Within the constraints of the 3D machining restricted area mesh model, iterative position updates are performed until the unavoidable areas in the virtual machining collision detection results are eliminated. Finally, the optimized annotation text object, the 3D model, and the machining restricted area boundary data are encapsulated into an engineering drawing document, and a multi-field interconnected engineering drawing is output.

[0034] S3. By using multi-field interconnected engineering diagrams, activate the collaborative mechanism of physical field response rules and repulsive field optimization engine to establish a dynamic response system for engineering data.

[0035] Based on the changes in the multi-physics field in the multi-field interconnected engineering diagram, the response rules of each physics field are triggered to execute the annotation attribute update and position correction. Based on the processing restricted area boundary in the multi-field interconnected engineering diagram, the optimal offset path of the annotation point under the constraint of the composite feature direction vector is dynamically obtained. It should be noted that the basic safety threshold is determined based on the physical limit parameters of the workpiece material, combined with material handbooks and experimental data. Multiphysics field change refers to determining the state of exceeding the safety threshold of physical field parameters by real-time calculation of the electromagnetic field intensity gradient, fluid velocity divergence, and thermodynamic temperature Laplace operator values ​​stored in the multiphysics interconnected engineering diagram, and activating the physical field response rule execution chain.

[0036] By analyzing the real-time data stream from multi-physics sensors in the multi-field interconnected engineering drawing, and based on the calibration feature index rule library of physical field entities, the physical field response rules bound to each physical field entity are triggered. Conditional instructions based on gradient matching according to field strength changes are executed, and tolerance values ​​are recalculated and dimensional reference point coordinates are updated for the labeled text objects. Simultaneously, based on the triangular mesh topology of the processing restricted area boundary in the multi-field interconnected engineering drawing, a three-dimensional obstacle avoidance path search calculation is performed in the vector constraint direction defined by the composite feature direction vector. Taking the labeled position as the starting point and the obstacle avoidance endpoint as the direction projection point, the continuous polyline segment path that avoids the processing restricted area boundary is output as the optimal offset path. A dynamic response system for engineering data is established based on the collaborative mechanism of physical field response rules and repulsive field optimization engine. Furthermore, based on the field strength gradient analysis module built into the physical field response rule, real-time monitoring of abnormal states in multi-physics data is performed. An event-triggered data channel is established between the physical field response rule and the labeled position of the repulsion field optimization engine. When the physical field response rule performs the labeled attribute update operation, the core of the repulsion field optimization algorithm is executed synchronously to generate the potential energy field gradient direction vector and the restricted area avoidance path at the labeled position. At the same time, the restricted area avoidance path is fed back to the dynamic feature compensator in the physical field response rule, constructing a coupled control mechanism with bidirectional data flow interaction logic. On the discrete-time grid sequence in three-dimensional space, the parallel execution flow data of the physical field response rule and the repulsion field optimization engine are integrated to construct a dynamic response system for engineering data that includes a dynamic parameter update channel, a real-time obstacle avoidance feedback loop, and multi-threaded synchronous control.

[0037] S4. Based on the dynamic response system of engineering data, the annotation content is driven to respond to changes in the physical field in real time, obtain the updated annotation content, and constrain the motion trajectory of the manufacturing equipment.

[0038] Through a dynamic response system for engineering data, the annotation content is driven to respond in real time to changes in the physical field, obtaining updated annotation content. There are two ways to determine changes in the physical field. First, thermodynamic physical field changes can be used. When the gradient change rate of the temperature sensor exceeds the tolerance threshold of the material's linear expansion coefficient for three consecutive sampling periods, it is determined to be a thermodynamic physical field change. Second, electromagnetic physical field changes can be used. Based on the fact that the differential value of the magnetic flux density detected by the eddy current sensor exceeds the inflection point of the second derivative of the saturation curve of the ferromagnetic material, it is determined to be a critical electromagnetic physical field change. Furthermore, the real-time data bus within the dynamic response system for engineering data captures the time-series monitoring data streams of multi-physics sensors; after performing physical field change state matching calculations, the dynamic marker locator is activated to perform dimensional tolerance correction and reference point coordinate displacement operations on the annotation text objects in the multi-field interconnected engineering drawing, while simultaneously synchronizing the annotation update instructions to the CAM system through the cross-process communication channel; within the multi-physics collaborative update cycle, the annotation content is regenerated and the topology relationship is remapped to obtain the updated annotation content containing the corrected tolerance attributes and spatial pose matrix.

[0039] By decoupling the feature directions, the spatial coordinates and direction components of the composite feature direction vector are analyzed. Combined with the equipment coordinate transformation matrix, the motion parameters of each axis of the manufacturing equipment are generated, and the motion control commands of the manufacturing equipment are obtained. It should be noted that the motion parameters represent a set of values ​​for linear axis displacement distance and rotation axis rotation angle. The spatial position coordinate components are obtained by performing a rigid coordinate transformation mapping after decoupling the characteristic direction through the device coordinate transformation matrix. Furthermore, through the characteristic direction decoupling operation, the composite characteristic direction vector is subjected to orthogonal coordinate system projection decomposition calculation, separating the spatial coordinate components and the direction cosine value components in the three-dimensional absolute coordinate system; the decoupled spatial coordinate components are input into the homogeneous transformation calculation process of the equipment coordinate transformation matrix, performing rigid body transformation mapping from the design coordinate system to the equipment coordinate system, and outputting the linear axis displacement command of the manufacturing equipment; the velocity vector in the linear axis displacement command is received through the linear-rotation motion correlator, and the cooperative rotational angular velocity is calculated according to the spatial geometric relationship between the velocity vector and the direction cosine value component (tool normal vector), and the angular velocity components of each axis are allocated according to the angle relationship between each rotation axis and the tangential velocity component. At the same time, in order to determine the angle value of the rotation axis, the coordinate system rotation theory is used to calculate the rotation axis motion angle value θ: ; in, The value of the rotation angle of the manufacturing equipment's rotating shaft. The trace of the rotation matrix represents the sum of the main diagonal elements of the rotation matrix constructed from the direction cosine components.

[0040] By combining the updated annotations with the motion control commands of the manufacturing equipment, the motion trajectory of the manufacturing equipment is dynamically constrained; Furthermore, the updated annotation content is used as the annotation tolerance boundary value as the spatial constraint boundary condition. During the equipment motion control cycle, the coordinates of each trajectory point are dynamically verified. If the coordinates exceed the annotation tolerance boundary, the offset compensation amount is obtained through linear interpolation algorithm, and the coordinate point sequence in the G code instruction is reconstructed synchronously. Finally, the corrected trajectory point set is input into the motion controller to realize the real-time position constraint of the manufacturing equipment's motion trajectory within the annotation tolerance boundary.

[0041] S5. Based on the spatial conflict feedback generated by the movement trajectory avoidance behavior of manufacturing equipment, the repulsion field algorithm is triggered to form the avoidance behavior of manufacturing constraints.

[0042] By monitoring the movement trajectory of manufacturing equipment, the interference status of the processing restricted area boundary is monitored in real time, and spatial conflict feedback is generated; It should be noted that spatial conflict feedback is a set of digital alarm signals that includes the three-dimensional coordinates, intrusion depth values, and timestamps of the interference between the movement trajectory points of the manufacturing equipment and the boundary of the processing restricted area. Furthermore, by acquiring the discrete trajectory point coordinate sequence of the manufacturing equipment's motion trajectory in real time, a convex hull acceleration detection structure for the motion trajectory point set is constructed in three-dimensional space; based on the triangular mesh topology data of the processing restricted area boundary, a ray intersection detection algorithm with continuous time steps is executed to obtain the minimum spatial distance value between the trajectory point and the triangular facet; when a trajectory point is detected to intrude into the restricted area mesh, the timestamp and intrusion depth of the intruding trajectory point are marked, generating structured data containing the conflict position vector, intrusion depth value and conflict time identifier, and generating spatial conflict feedback.

[0043] Based on spatial conflict feedback, the obstacle avoidance force field is obtained through a repulsive field algorithm; Furthermore, based on the conflict location coordinates, intrusion depth values, and timestamp data provided by the spatial conflict feedback, a repulsive potential energy peak point inversely proportional to the absolute value of the intrusion depth is set at the conflict location coordinates. A three-dimensional repulsive potential energy distribution field that decays exponentially with spatial distance is generated. A spatial gradient field transformation operation is performed on the potential energy distribution field to obtain the set of potential energy change rate vectors at each location point. The inverse direction of the potential energy change rate vector is mapped to the repulsive force direction, and the magnitude is associated with the potential energy change rate intensity. Finally, a vector-type force distribution field covering the entire boundary of the processing restricted area is generated as the obstacle avoidance force field. Based on the spatial vector data of the obstacle avoidance force field, a path offset correction value is generated using the principle of vector superposition. It should be noted that the principle of vector superposition refers to the fundamental mechanical rule of generating an equivalent resultant vector by performing algebraic summation of the magnitude components and synthesis of the direction components of multiple vectors acting at the same spatial point. Furthermore, based on the spatial vector data set provided by the obstacle avoidance force field, a spatial vector superposition operation is performed on the discrete motion trajectory points of the manufacturing equipment. The magnitude and direction of all associated force vectors acting on the trajectory points are orthogonally decomposed to generate the Cartesian component of the resultant force vector. The control cycle is set according to the physical limits of the equipment, the motion accuracy requirements, and the real-time performance of the communication architecture. Based on the directional component of the resultant force vector and the preset control cycle, the required position offset and correction direction angle value of the trajectory points within the control cycle are obtained. Finally, the linear displacement and rotation adjustment amount bound to the trajectory points are output as the path offset correction value. By correcting the path offset, the motion trajectory is reconstructed, an obstacle avoidance path is formed at the boundary of the processing restricted area, and the avoidance behavior of the initial manufacturing constraints is generated. Furthermore, based on the path offset correction value, spatial coordinate displacement operation is performed on the discrete trajectory points of the manufacturing equipment's motion trajectory. Through cubic B-spline curve mathematical interpolation, the corrected discrete trajectory point sequence is reconstructed into a continuous and smooth obstacle avoidance path curve. The minimum distance between the obstacle avoidance path curve and the triangular mesh of the processing restricted area boundary is verified in real time to ensure that it is greater than the safety threshold. If the distance in a local area is insufficient, fine-tuning iterative calculation based on repulsive field gradient optimization is triggered. Finally, the continuous path curve that meets the restricted area avoidance constraints is encapsulated into a G-code instruction segment containing time-space pose parameters, and the avoidance behavior of the initial manufacturing constraints is output.

[0044] S6. By creating constraint avoidance behavior and updated annotation content, an interlocking mechanism is formed for the real-time response behavior to changes in the physical field, and engineering data is automatically annotated.

[0045] Based on the avoidance behavior of the initial manufacturing constraints and the updated annotation content, the key dynamic parameters of the physical field change response behavior are continuously monitored to generate interlock judgment signals that characterize the state anomaly. It should be noted that the key dynamic parameters are derived from the data stream of multi-physics field change response behavior output in real time collected by the engineering data dynamic response system, specifically including the instantaneous fluctuation parameters of temperature field gradient, electromagnetic field intensity and fluid pressure field. Furthermore, based on the real-time update records of the spatiotemporal trajectory data and annotation content of the G-code instruction segment in the initial manufacturing constraint avoidance behavior, a collaborative monitoring operation of dynamic changes in the physical field is performed. Through failure mode analysis, multi-physics field coupling simulation and equipment safety standards, the interlock threshold range is obtained. Through the real-time data stream interface of the engineering data dynamic response system, the temperature gradient field change rate, electromagnetic field intensity fluctuation, and flow field pressure fluctuation are captured and compared with the interlock threshold range in real time. If the parameters are detected to continuously exceed the interlock threshold range, the state abnormality flag bit flipping operation is triggered, and a digital alarm data packet carrying a timestamp, abnormal parameter type and deviation amplitude is generated as an interlock judgment signal characterizing the state abnormality. By combining interlock judgment signals, the process controller controls the automatic annotation of engineering data, performs real-time updates of annotation content and spatial repositioning operations, and obtains dynamic annotation content; Furthermore, by analyzing the abnormal type and deviation amplitude data in the interlock judgment signal through the process controller, the real-time state switching command of the automatic annotation process of engineering data is triggered. At the same time, based on the physical field response rules, the tolerance attribute is dynamically and adaptively corrected for the current annotation content, and the repulsive field optimization engine is called to search for the optimal spatial offset coordinates under the constraint of composite feature direction vector. The entire closed-loop process response of real-time updating of annotation content and spatial repositioning operation is completed simultaneously to obtain dynamic annotation content. By using the real-time update results of dynamically labeled content, the topological reconstruction calculation of the restricted area boundary is triggered to induce constraint avoidance behavior, and the spatial coordinates of the processing restricted area boundary are updated. Furthermore, based on the new tolerance attribute values ​​included in the real-time update results of the dynamically annotated content, a restricted area boundary reconstruction mechanism for manufacturing constraint avoidance behavior is triggered. The envelope parameters of the machining tool and the thermal deformation characteristic parameters of the workpiece material are called, and the thermal expansion strain tensor is re-acquired according to the new tolerance value. Under the constraint that the original topological connection relationship of the three-dimensional machining restricted area mesh model remains unchanged, an elastic displacement field mapping operation based on the strain tensor is performed on the vertex coordinates of the triangular mesh to generate a mesh structure with updated vertex spatial coordinates. Finally, the machining restricted area boundary dataset containing the new position coordinates is output.

[0046] This embodiment also provides a computer device applicable to the automatic annotation method for engineering data based on feature direction matching, comprising: a memory and a processor; the memory is used to store computer-executable instructions, and the processor is used to execute the computer-executable instructions to implement the automatic annotation method for engineering data based on feature direction matching as proposed in the above embodiment.

[0047] The computer device can be a terminal, comprising a processor, memory, communication interface, display screen, and input devices connected via a system bus. The processor provides computing and control capabilities. The memory includes non-volatile storage media and internal memory. The non-volatile storage media stores the operating system and computer programs. The internal memory provides an environment for the operation of the operating system and computer programs stored in the non-volatile storage media. The communication interface is used for wired or wireless communication with external terminals; wireless communication can be achieved through Wi-Fi, carrier networks, NFC (Near Field Communication), or other technologies. The display screen can be an LCD screen or an e-ink screen. The input devices can be a touch layer covering the display screen, buttons, a trackball, or a touchpad on the computer device's casing, or an external keyboard, touchpad, or mouse.

[0048] This embodiment also provides a storage medium storing a computer program that, when executed by a processor, implements the automatic annotation method for engineering data based on feature direction matching as proposed in the above embodiments. The storage medium can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as Static Random Access Memory (SRAM), Electrically Erasable Programmable Read-Only Memory (EEPROM), Erasable Programmable Read Only Memory (EPROM), Programmable Red-Only Memory (PROM), Read-Only Memory (ROM), magnetic storage, flash memory, magnetic disk, or optical disk.

[0049] In summary, this invention generates a composite feature direction vector in the direction of physical field enhancement, providing a guiding benchmark that couples the physical field with the design intent for engineering annotation. This enables adaptive optimization of the annotation direction in a multi-physics environment, eliminating annotation inaccuracies caused by human experience bias. By establishing a dynamic response system for engineering data, based on the collaborative mechanism of physical field response rules and repulsive field optimization engine, changes in the physical field in multi-field interconnected engineering drawings are mapped to annotation attributes in real time, updating and constraining the trajectory of manufacturing equipment.

[0050] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and are not intended to limit it. Although the present invention has been described in detail with reference to preferred embodiments, those skilled in the art should understand that modifications or equivalent substitutions can be made to the technical solutions of the present invention without departing from the spirit and scope of the technical solutions of the present invention, and all such modifications or substitutions should be covered within the scope of the claims of the present invention.

Claims

1. An automatic annotation method for engineering data based on feature direction matching, characterized in that, Includes the following steps: S1. Extract the geometric normal vector of the target feature, combine it with multi-physics data, and generate a composite feature direction vector in the direction of physical field enhancement. S2. Construct a three-dimensional machining restricted area mesh model, generate an optimized set of labeled spatial coordinates through composite feature direction vectors, and generate multi-field interconnected engineering drawings through virtual machining simulation; S3. By activating the collaborative mechanism of physical field response rules and repulsive field optimization engine through multi-field interconnected engineering diagrams, a dynamic response system for engineering data is established. S4. Based on the dynamic response system of engineering data, drive the annotation content to respond to changes in the physical field in real time, obtain the updated annotation content, and constrain the motion trajectory of the manufacturing equipment. S5. Based on the spatial conflict feedback generated by the movement trajectory avoidance behavior of manufacturing equipment, the repulsion field algorithm is triggered to form the avoidance behavior of manufacturing constraints. S6. By creating constraint avoidance behavior and updated annotation content, an interlocking mechanism is formed for the real-time response behavior to changes in the physical field, and engineering data is automatically annotated.

2. The automatic annotation method for engineering data based on feature direction matching as described in claim 1, characterized in that, S1 specifically refers to: Extract the geometric normal vector of the target feature using CAD software; Based on the functional requirements of the target characteristics in the project, the design intent direction is obtained, and multi-physics field-intent coupling weight coefficients are generated through the physical field contribution ratio quantification rule. By superimposing the multiphysics data with the target feature geometric normal vector through the multiphysics-intent coupling weight coefficient, a composite feature direction vector in the direction of physical field enhancement is generated.

3. The automatic annotation method for engineering data based on feature direction matching as described in claim 1, characterized in that, In S2, a 3D machining restricted area mesh model is constructed. An optimized set of labeled spatial coordinates is generated using composite feature direction vectors, including... Based on the envelope parameters of machining tools and the thermal deformation characteristics of workpiece materials, a three-dimensional machining restricted area mesh model is generated by spatial discretization mesh generation to obtain the boundary of the machining restricted area. The initial position of the annotation located on the vertical projection plane of the composite feature direction vector is obtained through the repulsion field algorithm engine, and the dynamic distance between the initial position of the annotation and the boundary of the processing restricted area is detected in real time. When the dynamic spacing of the boundary collision avoidance is less than the safety threshold, the annotation position is dynamically adjusted to generate an optimized set of annotation space coordinates.

4. The automatic annotation method for engineering data based on feature direction matching as described in claim 3, characterized in that, In S2, multi-field interconnected engineering diagrams are generated through virtual manufacturing simulation, including... Based on the optimized set of annotation space coordinates, annotation text is automatically generated in CAD, and the tool path is generated by triggering CAM software through API to perform virtual machining collision detection between workpiece and tool; During the virtual manufacturing collision detection process, the unavoidable areas are iteratively optimized, and multi-field interconnected engineering diagrams are output.

5. The automatic annotation method for engineering data based on feature direction matching as described in claim 1, characterized in that, S3 specifically refers to: Based on the changes in the multi-physics field in the multi-field interconnected engineering diagram, the response rules of each physics field are triggered to execute the annotation attribute update and position correction. Based on the processing restricted area boundary in the multi-field interconnected engineering diagram, the optimal offset path of the annotation point under the constraint of the composite feature direction vector is dynamically obtained. A dynamic response system for engineering data is established based on the collaborative mechanism of physical field response rules and repulsive field optimization engine.

6. The automatic annotation method for engineering data based on feature direction matching as described in claim 1, characterized in that, S4 specifically refers to: Through the dynamic response system of engineering data, the annotation content is driven to respond to changes in the physical field in real time, and the updated annotation content is obtained. By decoupling the feature directions, the spatial coordinates and direction components of the composite feature direction vector are analyzed. Combined with the equipment coordinate transformation matrix, the motion parameters of each axis of the manufacturing equipment are generated, and the motion control commands of the manufacturing equipment are obtained. By combining the updated annotations with the motion control commands of the manufacturing equipment, the motion trajectory of the manufacturing equipment is dynamically constrained.

7. The automatic annotation method for engineering data based on feature direction matching as described in claim 1, characterized in that, S5 specifically refers to: By monitoring the movement trajectory of manufacturing equipment, the interference status of the processing restricted area boundary is monitored in real time, and spatial conflict feedback is generated; Based on spatial conflict feedback, the obstacle avoidance force field is obtained through a repulsive field algorithm; Based on the spatial vector data of the obstacle avoidance force field, a path offset correction value is generated using the principle of vector superposition. By correcting the path offset, the motion trajectory is reconstructed, an obstacle avoidance path is formed at the boundary of the processing restricted area, and the avoidance behavior of the initial manufacturing constraints is generated.

8. The automatic annotation method for engineering data based on feature direction matching as described in claim 1, characterized in that, S6 specifically refers to: Based on the avoidance behavior of the initial manufacturing constraints and the updated annotation content, the key dynamic parameters of the physical field change response behavior are continuously monitored to generate interlock judgment signals that characterize the state anomaly. By combining interlock judgment signals, the process controller controls the automatic annotation of engineering data, performs real-time updates of annotation content and spatial repositioning operations, and obtains dynamic annotation content; By using the real-time update results of dynamically labeled content, the topological reconstruction calculation of the restricted area boundary is triggered to induce constraint avoidance behavior, and the spatial coordinates of the processing restricted area boundary are updated.

9. A computer device comprising a memory and a processor, wherein the memory stores a computer program, characterized in that, When the processor executes the computer program, it implements the steps of the automatic annotation method for engineering data based on feature direction matching as described in any one of claims 1 to 8.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by the processor, it implements the steps of the automatic annotation method for engineering data based on feature direction matching as described in any one of claims 1 to 8.

Images