Complex product assembly-oriented intelligent tool reference model construction method and engineering implementation method thereof

Abstract

The invention relates to the technical field of intelligent production, and discloses an intelligent tool reference model construction method for complex product assembly and an engineering implementation method thereof.The model construction method comprises the following specific steps that geometric features, tool parameters and external load working condition data of parts needing to be assembled are collected; establishing a database of the structured assembly scene; based on the database, constructing a multi-dimensional time sequence correlation model comprising an in-position-measurement-attitude adjustment-docking model, a dimension chain precision mapping model reflecting a mapping relation between a load condition and dimension chain precision, and a tool function module library of a standardized tool; and performing multi-model coupling on the time sequence correlation model, the precision mapping model and the tool function module library to form a tool reference model. The problem that an existing intelligent assembling technology is insufficient in application range is solved, and the beneficial effect that the assembling efficiency and flexibility can be improved is achieved.

Description

Technical Field

[0001] The present invention relates to the field of intelligent production technology, and more specifically, to a method for constructing an intelligent tooling reference model for complex product assembly and an engineering implementation method thereof. Background Art

[0002] In the manufacturing process of modern complex products, especially in precision assembly that needs to handle different types of loads (such as pressure and temperature changes), it is particularly important to ensure the size, shape and position accuracy of each part. Traditional methods are mainly aimed at large-scale production of a single product and cannot flexibly deal with various uncertainties, making it difficult to quickly adjust the assembly process to meet specific needs. In addition, the research on how load affects assembly accuracy is not in-depth enough, making it more difficult to control assembly quality. Traditional tooling design is also not flexible enough to effectively handle subtle differences between parts, limiting the adaptability and efficiency of the production line.

[0003] The prior art provides an intelligent assembly system for a gear pump, which relates to the technical field of assembly equipment and includes a frame on which are provided an automatic parts detection and matching module, a collaborative robot, an automatic assembly device for shell components, an automatic assembly device for end cover components, an automatic locking device, and a product transfer mechanism. The automatic parts detection and matching module includes an automatic detection module, a workpiece information recognition module, a detection result storage module, and a matching assembly module; the automatic assembly device for shell components is used for assembling the shell, pins, bearings, and gear components of the gear pump; the automatic assembly device for end cover components is used for assembling the end cover, oil seal, bearing, and retaining ring components of the gear pump; the automatic locking device is used for assembling screws of the gear pump; there are multiple product transfer mechanisms for transferring parts and semi-finished products of the gear pump between modules; the above modules are coordinated to achieve fully automated assembly and improve assembly efficiency.

[0004] However, existing technologies are only applicable to the assembly of specific parts and lack the ability to cope with parts assembly projects in multiple fields and scenarios. Therefore, how to invent an intelligent tooling reference model that can adapt to the assembly needs of different products is a technical problem that urgently needs to be solved in this technical field. Summary of the Invention

[0005] In order to solve the problem of insufficient application scope of existing intelligent assembly technology, the present invention provides an intelligent tooling reference model construction method for complex product assembly and an engineering implementation method thereof, which has the characteristics of being able to improve assembly efficiency and flexibility.

[0006] In order to achieve the above-mentioned purpose of the present invention, the technical solutions adopted are as follows:

[0007] A method for constructing an intelligent tooling reference model for complex product assembly includes the following specific steps:

[0008] Collect the geometric features, tooling parameters, and external load condition data of the parts to be assembled, and establish a database of structured assembly scenarios;

[0009] Based on the database, a multi-dimensional time series correlation model including the positioning-measurement-attitude adjustment-docking model, a dimensional chain accuracy mapping model reflecting the mapping relationship between load conditions and dimensional chain accuracy, and a tooling function module library for standardized tooling are constructed;

[0010] The timing correlation model, precision mapping model, and tooling function module library are multi-model coupled to form a tooling reference model.

[0011] Preferably, the specific steps of collecting geometric features, tooling parameters and external load condition data of the parts to be assembled and establishing a structured assembly scenario database are:

[0012] Set assembly task constraints, including efficiency and cost objectives, and uncertainty factors such as environmental loads and micro-differences in part structure;

[0013] Collect the geometric and physical properties of the parts to be assembled by the tooling, including size, shape, material, dynamic and static thermal stiffness; determine the functional requirements of the tooling, including positioning, clamping, and docking; determine the types of external loads during the assembly process, including force loads and thermal loads; and construct a structured assembly scenario description.

[0014] Collect interaction data between the assembly parts and the tooling, including position deviation, contact force, and temperature change, through sensors, vision systems, or past experimental data.

[0015] By integrating constraints, task objectives, uncertainty factors, assembly scenario descriptions, and interaction data, a database of structured assembly scenarios for tooling operations is constructed.

[0016] Furthermore, based on the database and the actual assembly environment, a multi-dimensional time series correlation model including the positioning-measurement-attitude adjustment-docking model, a dimensional chain accuracy mapping model reflecting the mapping relationship between load conditions and dimensional chain accuracy, and a tooling function module library for standardized tooling are constructed. The specific steps are as follows:

[0017] Considering the sequential steps of the parts to be assembled entering the tooling for assembly, a multi-dimensional sequential correlation model including positioning-measurement-posture adjustment-docking is constructed based on the database.

[0018] Based on the database, the effects of different loads on the accuracy of the dimensional chain components, including size, shape, and position, are studied through finite element simulation or physical experiments. Regression analysis, neural networks, and fuzzy logic are used to quantify the mapping relationship between the working load and the physical geometric characterization indicators of the components, including dynamic and static thermal stiffness and geometric envelope shape, and the accuracy of the component chains.

[0019] The tooling functions of positioning, clamping, jig, and docking are abstracted into modular components, standardized interfaces and functional descriptions are defined, and a reusable tooling functional module library is constructed.

[0020] Furthermore, the multi-dimensional temporal association model of the positioning-measurement-attitude adjustment-docking steps specifically includes a positioning deviation model, a geometric feature measurement model, a dynamic attitude adjustment model, and an optimal docking path model;

[0021] Place the component in the assembly position and establish a deviation model between the component's initial position and the tooling reference based on the positioning sensor data;

[0022] Build a geometric feature measurement model based on high-precision sensing and measurement components;

[0023] Combine support vector machines and deep learning algorithms to design dynamic posture adjustment strategies and build dynamic posture adjustment models;

[0024] An optimal docking path model is generated by selecting a path planning algorithm to generate the optimal docking path.

[0025] Furthermore, the timing correlation model, precision mapping model and tooling module are multi-model coupled to form a tooling reference model. Specifically, a virtual simulation environment for the assembly process is constructed using SIMIO, MATLAB, or Simulink. The timing correlation model, precision mapping model and tooling function module library are multi-model coupled to form a tooling reference model.

[0026] An engineering implementation method for an intelligent tooling reference model for complex product assembly includes the following specific steps:

[0027] Based on the tooling reference model, a flexible tooling design solution including positioning module, clamping module, jig module, and docking module is constructed;

[0028] The flexible chemical equipment design scheme based on the construction simulates the dynamic behavior in the actual assembly scene through 3D modeling and dynamic simulation platform;

[0029] Optimize the design of flexible chemical equipment based on simulation results;

[0030] The optimized flexible chemical equipment design scheme is applied to actual production and manufacturing.

[0031] Preferably, based on the tooling reference model, a flexible tooling design scheme including a positioning module, a clamping module, a jig module, and a docking module is constructed, and the specific steps are as follows:

[0032] Based on the time series correlation model and combined with the tooling reference parameters in the tooling function module library, a positioning module is constructed for dynamically matching the parts to be assembled;

[0033] Based on the association rules between load and deformation in the dimensional chain precision mapping model, a clamping module is constructed to adjust the clamping force threshold and adaptive compensation logic.

[0034] Based on the reconfigurable interface of the tooling function library, a parameterized jig module is constructed to adjust the jig's degrees of freedom and connection devices;

[0035] Based on the docking model of the time series association model and the dimensional chain accuracy constraint of the dimensional chain accuracy mapping model, a docking module for generating tolerance-compensated docking trajectories is constructed.

[0036] Furthermore, before the simulation, the flexible chemical equipment design scheme was pre-designed. The specific steps are as follows:

[0037] The positioning module corresponds to a digital flexible positioning system, in which the tooling positioning data is transmitted to the control system in digital form, and then transmitted to the actuator by the control system, and positioning is completed through digital motion;

[0038] The clamping module is matched with a digital flexible adaptive clamping device. According to the shape and type of different parts, the clamping parameters are dynamically adjusted based on real-time positioning data to be compatible with the assembly of different types of parts and ensure adaptive clamping during the assembly process.

[0039] The docking module is matched with a digital flexible equipment jig, and the module state is changed by adjusting the degree of freedom and connecting devices to meet the needs of similar products and realize the co-line assembly of multiple varieties of parts in small batches;

[0040] The docking module is matched with a digital and flexible automated docking device, which drives the docking mechanism based on precise positioning and stable clamping to ensure automated and precise coordination between components. Each module operates collaboratively through a data link to build a flexible solution suitable for multi-variety, small-batch assembly.

[0041] Furthermore, the flexible chemical equipment design scheme is optimized based on the simulation results. The specific steps are as follows:

[0042] Through 3D modeling and dynamic simulation platform, dynamic behavior in actual assembly scenarios is simulated:

[0043] Kinematic simulation is used to analyze the motion trajectories between the digital flexible positioning system, adaptive clamping device, equipment jig, and automated docking device to detect potential mechanical interference issues when the various devices work together. Finite element analysis is used to evaluate the stress distribution of key components to ensure that the structural strength meets long-term use requirements.

[0044] Control logic simulation is used to verify the coordination of the electromechanical system, and core indicators including positioning accuracy, clamping force stability and jig reconstruction efficiency are tested through real-time digital twin models;

[0045] In response to the interference, stress concentration, and control delay problems exposed in the simulation, parametric drive technology is used to iteratively optimize the tooling geometric topology and control system algorithm, ultimately forming an optimized flexible tooling design scheme that has been virtually verified, providing data support for physical prototype manufacturing.

[0046] Furthermore, the optimized flexible chemical equipment design was tested. The specific steps are as follows:

[0047] Implement the optimized flexible chemical equipment design scheme in actual assembly scenarios;

[0048] Physical tests are conducted on positioning accuracy, clamping force, jig stiffness, and docking repeatability. The system's long-term stability and anti-interference capabilities are tested under typical operating conditions, targeting the harsh conditions that may be encountered in actual production.

[0049] If the test is passed, the final intelligent assembly tooling system will be applied to actual production and manufacturing; if it fails, the flexible tooling design plan will be rebuilt.

[0050] The beneficial effects of the present invention are as follows:

[0051] The present invention proposes an intelligent assembly solution based on the "component-tooling" interaction context. By creating a personalized assembly process method, covering key steps such as "positioning", "measurement", "posture adjustment" and "docking", more precise control and optimization of the assembly process can be achieved. Based on a database, the present invention takes into account the changes in assembly accuracy under different load conditions by setting a dimensional chain accuracy mapping model that maps the dimensional chain accuracy and a tooling function module library of standardized tooling. It can also use data analysis and intelligent algorithms to quickly identify and adapt to assembly requirements under uncertain conditions, provide optimal process arrangements, and improve overall assembly quality. BRIEF DESCRIPTION OF THE DRAWINGS

[0052] Figure 1 It is a flow chart of a method for constructing an intelligent tooling reference model for complex product assembly according to the present invention.

[0053] Figure 2 This is a flow chart of an engineering implementation method of an intelligent tooling reference model for complex product assembly according to Example 2 of the present invention.

[0054] Figure 3 It is a schematic diagram of the complete construction and implementation process of an intelligent tooling reference model for complex product assembly in Example 3 of the present invention. DETAILED DESCRIPTION

[0055] The present invention is described in detail below with reference to the accompanying drawings and specific embodiments.

[0056] Example 1

[0057] like Figure 1 As shown in FIG, a method for constructing an intelligent tooling reference model for complex product assembly includes the following specific steps:

[0058] Collect the geometric features, tooling parameters, and external load condition data of the parts to be assembled, and establish a database of structured assembly scenarios;

[0059] Based on the database, a multi-dimensional time series correlation model including the positioning-measurement-attitude adjustment-docking model, a dimensional chain accuracy mapping model reflecting the mapping relationship between load conditions and dimensional chain accuracy, and a tooling function module library for standardized tooling are constructed;

[0060] The timing correlation model, precision mapping model, and tooling function module library are multi-model coupled to form a tooling reference model.

[0061] Preferably, the specific steps of collecting geometric features, tooling parameters and external load condition data of the parts to be assembled and establishing a structured assembly scenario database are:

[0062] Set assembly task constraints, including efficiency and cost objectives, and uncertainty factors such as environmental loads and micro-differences in part structure;

[0063] Collect the geometric and physical properties of the parts to be assembled by the tooling, including size, shape, material, dynamic and static thermal stiffness; determine the functional requirements of the tooling, including positioning, clamping, and docking; determine the types of external loads during the assembly process, including force loads and thermal loads; and construct a structured assembly scenario description.

[0064] Collect interaction data between the assembly parts and the tooling, including position deviation, contact force, and temperature change, through sensors, vision systems, or past experimental data.

[0065] By integrating constraints, task objectives, uncertainty factors, assembly scenario descriptions, and interaction data, a database of structured assembly scenarios for tooling operations is constructed.

[0066] In a specific embodiment, based on the database and the actual assembly environment, a multi-dimensional time series correlation model including the positioning-measurement-attitude adjustment-docking model, a dimensional chain accuracy mapping model reflecting the mapping relationship between load conditions and dimensional chain accuracy, and a tooling function module library of standardized tooling are constructed. The specific steps are as follows:

[0067] Considering the sequential steps of the parts to be assembled entering the tooling for assembly, a multi-dimensional sequential correlation model including positioning-measurement-posture adjustment-docking is constructed based on the database.

[0068] Based on the database, the effects of different loads on the accuracy of the dimensional chain components, including size, shape, and position, are studied through finite element simulation or physical experiments. Regression analysis, neural networks, and fuzzy logic are used to quantify the mapping relationship between the working load and the physical geometric characterization indicators of the components, including dynamic and static thermal stiffness and geometric envelope shape, and the accuracy of the component chains.

[0069] The tooling functions of positioning, clamping, jig, and docking are abstracted into modular components, standardized interfaces and functional descriptions are defined, and a reusable tooling functional module library is constructed.

[0070] In a specific embodiment, the multi-dimensional temporal association model of the positioning-measurement-attitude adjustment-docking steps specifically includes a positioning deviation model, a geometric feature measurement model, a dynamic attitude adjustment model, and an optimal docking path model;

[0071] Place the component in the assembly position and establish a deviation model between the component's initial position and the tooling reference based on the positioning sensor data;

[0072] Build a geometric feature measurement model based on high-precision sensing and measurement components;

[0073] Combine support vector machines and deep learning algorithms to design dynamic posture adjustment strategies and build dynamic posture adjustment models;

[0074] An optimal docking path model is generated by selecting a path planning algorithm to generate the optimal docking path.

[0075] In a specific embodiment, the timing correlation model, the precision mapping model and the tooling module are multi-model coupled to form a tooling reference model. Specifically, a virtual simulation environment of the assembly process is constructed using any of SIMIO, MATLAB, and Simulink. The timing correlation model, the precision mapping model, and the tooling function module library are multi-model coupled to form a tooling reference model.

[0076] Example 2

[0077] like Figure 2 As shown in FIG, an engineering implementation method of an intelligent tooling reference model for complex product assembly includes the following specific steps:

[0078] Based on the tooling reference model, a flexible tooling design solution including positioning module, clamping module, jig module, and docking module is constructed;

[0079] The flexible chemical equipment design scheme based on the construction simulates the dynamic behavior in the actual assembly scene through 3D modeling and dynamic simulation platform;

[0080] Optimize the design of flexible chemical equipment based on simulation results;

[0081] The optimized flexible chemical equipment design scheme is applied to actual production and manufacturing.

[0082] In a specific embodiment, based on the tooling reference model, a flexible tooling design scheme including a positioning module, a clamping module, a jig module, and a docking module is constructed. The specific steps are as follows:

[0083] Based on the time series correlation model and combined with the tooling reference parameters in the tooling function module library, a positioning module is constructed for dynamically matching the parts to be assembled;

[0084] Based on the association rules between load and deformation in the dimensional chain precision mapping model, a clamping module is constructed to adjust the clamping force threshold and adaptive compensation logic.

[0085] Based on the reconfigurable interface of the tooling function library, a parameterized jig module is constructed to adjust the jig's degrees of freedom and connection devices;

[0086] Based on the docking model of the time series association model and the dimensional chain accuracy constraint of the dimensional chain accuracy mapping model, a docking module for generating tolerance-compensated docking trajectories is constructed.

[0087] In a specific embodiment, before the simulation, the flexible chemical equipment design scheme is pre-designed, and the specific steps are as follows:

[0088] The positioning module corresponds to a digital flexible positioning system, in which the tooling positioning data is transmitted to the control system in digital form, and then transmitted to the actuator by the control system, and positioning is completed through digital motion;

[0089] The clamping module is matched with a digital flexible adaptive clamping device. According to the shape and type of different parts, the clamping parameters are dynamically adjusted based on real-time positioning data to be compatible with the assembly of different types of parts and ensure adaptive clamping during the assembly process.

[0090] The docking module is matched with a digital flexible equipment jig, and the module state is changed by adjusting the degree of freedom and connecting devices to meet the needs of similar products and realize the co-line assembly of multiple varieties of parts in small batches;

[0091] The docking module is matched with a digital and flexible automated docking device, which drives the docking mechanism based on precise positioning and stable clamping to ensure automated and precise coordination between components. Each module operates collaboratively through a data link to build a flexible solution suitable for multi-variety, small-batch assembly.

[0092] In a specific embodiment, the flexible chemical equipment design is optimized based on the simulation results, and the specific steps are as follows:

[0093] Through 3D modeling and dynamic simulation platform, dynamic behavior in actual assembly scenarios is simulated:

[0094] Kinematic simulation is used to analyze the motion trajectories between the digital flexible positioning system, adaptive clamping device, equipment jig, and automated docking device to detect potential mechanical interference issues when the various devices work together. Finite element analysis is used to evaluate the stress distribution of key components to ensure that the structural strength meets long-term use requirements.

[0095] Control logic simulation is used to verify the coordination of the electromechanical system, and core indicators including positioning accuracy, clamping force stability and jig reconstruction efficiency are tested through real-time digital twin models;

[0096] In response to the interference, stress concentration, and control delay problems exposed in the simulation, parametric drive technology is used to iteratively optimize the tooling geometric topology and control system algorithm, ultimately forming an optimized flexible tooling design scheme that has been virtually verified, providing data support for physical prototype manufacturing.

[0097] In a specific embodiment, the optimized flexible chemical equipment design was tested, and the specific steps were as follows:

[0098] We manufacture tooling components through precision machining processes including CNC machine tools and 3D printing, and procure standard actuators including servo motors and sensors to implement the optimized flexible tooling design in actual assembly scenarios.

[0099] CMMs are used to verify key indicators, performing physical tests on positioning accuracy, clamping force, jig stiffness, and docking repeatability. The system's long-term stability and anti-interference capabilities are tested under typical operating conditions, targeting harsh conditions that may be encountered in actual production, such as high-temperature environments, high-humidity areas, or workshops with electromagnetic interference.

[0100] If the test is passed, the final intelligent assembly tooling system will be applied to actual production and manufacturing; if it fails, the flexible tooling design plan will be rebuilt.

[0101] Therefore, this invention introduces flexible assembly technology to address subtle differences between parts. This innovation not only improves assembly quality and efficiency, but also enhances the system's flexibility and responsiveness, allowing companies to more flexibly respond to market changes and technological challenges.

[0102] Example 3

[0103] In this embodiment, Figure 3 As shown in the figure, after completing the integration of the tooling reference model and converting the model into a digital design scheme for flexible tooling, the final intelligent assembly tooling system is applied to actual production and manufacturing, and the tooling performance including positioning accuracy and clamping force stability is verified in real assembly scenarios. Actual data including temperature, vibration, and assembly errors are collected for model correction, and experience such as dimensional chain mapping rules and flexible tooling design templates is accumulated. Cross-project knowledge sharing is also achieved to continuously improve the engineering applicability and reuse efficiency of the model.

[0104] Compared with the existing technology, the present invention has the following advantages and outstanding effects: (1) Constructing a personalized "positioning-measurement-attitude adjustment-docking" multi-dimensional time series correlation model to accurately describe the key steps and their interrelationships in the assembly process of complex products, making the assembly process more efficient and accurate, and adapting to the specific needs of different products. (2) Using data analysis and heuristic algorithms, accurately identify key assembly features under uncertain situations, and quickly generate optimized process solution space for specific needs, significantly improving assembly efficiency and flexibility, and reducing errors caused by human intervention. (3) In-depth research on the changing laws of component ring accuracy under different types of load conditions, and establishing a mapping relationship between accuracy indicators and working loads, and physical geometric characteristics of parts, which can not only adapt to the needs of different levels of abstraction, but also promote the reuse of knowledge and realize the rapid generation of assembly plans. (4) Explore and apply flexible chemical assembly technology to effectively deal with minor differences in part structure, significantly improve the adaptability and flexibility of the production line, and is particularly suitable for scenarios of multi-variety small-batch co-production, enhancing the company's market response speed and technological competitiveness.

[0105] This invention enhances the intelligence of automated positioning, clamping, assembly, and docking processes, reducing reliance on manual operations and improving assembly efficiency and quality. This enables companies to more flexibly respond to market changes and technological challenges, providing more efficient and reliable assembly solutions with high practical value.

[0106] Obviously, the above embodiments of the present invention are merely examples for the purpose of illustrating the present invention, and are not intended to limit the embodiments of the present invention. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of the present invention shall be included within the scope of protection of the claims of the present invention.

Claims

1. A method for constructing an intelligent tooling reference model for complex product assembly, characterized by: The specific steps include: Collect the geometric features, tooling parameters, and external load condition data of the parts to be assembled, and establish a database of structured assembly scenarios; Based on the database, a multi-dimensional time series correlation model including the positioning-measurement-attitude adjustment-docking model, a dimensional chain accuracy mapping model reflecting the mapping relationship between load conditions and dimensional chain accuracy, and a tooling function module library for standardized tooling are constructed; The timing correlation model, precision mapping model, and tooling function module library are multi-model coupled to form a tooling reference model.

2. The method for constructing an intelligent tooling reference model for complex product assembly according to claim 1, characterized in that: The specific steps for collecting the geometric features, tooling parameters, and external load condition data of the parts to be assembled and establishing a structured assembly scenario database are as follows: Set assembly task constraints, including efficiency and cost objectives, and uncertainty factors such as environmental loads and micro-differences in part structure; Collect the geometric and physical characteristics of the parts to be assembled by the tooling, including size, shape, material, dynamic and static thermal stiffness; determine the functional requirements of the tooling, including positioning, clamping, and docking; determine the types of external loads during the assembly process, including mechanical loads and thermal loads; Construct a structured assembly scenario description; Collect interaction data between the assembly parts and the tooling, including position deviation, contact force, and temperature change, through sensors, vision systems, or past experimental data. By integrating constraints, task objectives, uncertainty factors, assembly scenario descriptions, and interaction data, a database of structured assembly scenarios for tooling operations is constructed.

3. The method for constructing an intelligent tooling reference model for complex product assembly according to claim 1, characterized in that: Based on the database and actual assembly environment, a multi-dimensional time series correlation model including the positioning-measurement-attitude adjustment-docking model, a dimensional chain accuracy mapping model reflecting the mapping relationship between load conditions and dimensional chain accuracy, and a tooling function module library for standardized tooling are constructed. The specific steps are as follows: Considering the sequential steps of the parts to be assembled entering the tooling for assembly, a multi-dimensional sequential correlation model including positioning-measurement-posture adjustment-docking is constructed based on the database. Based on the database, the effects of different loads on the accuracy of the dimensional chain components, including size, shape, and position, are studied through finite element simulation or physical experiments. Regression analysis, neural networks, and fuzzy logic are used to quantify the mapping relationship between the working load and the physical geometric characterization indicators of the components, including dynamic and static thermal stiffness and geometric envelope shape, and the accuracy of the component chains. The tooling functions of positioning, clamping, jig, and docking are abstracted into modular components, standardized interfaces and functional descriptions are defined, and a reusable tooling functional module library is constructed.

4. The method for constructing an intelligent tooling reference model for complex product assembly according to claim 3, characterized in that: The multi-dimensional temporal association model of the steps of positioning-measurement-attitude adjustment-docking specifically includes a positioning deviation model, a geometric feature measurement model, a dynamic attitude adjustment model, and an optimal docking path model; Place the component in the assembly position and establish a deviation model between the component's initial position and the tooling reference based on the positioning sensor data; Build a geometric feature measurement model based on high-precision sensing and measurement components; Combine support vector machines and deep learning algorithms to design dynamic posture adjustment strategies and build dynamic posture adjustment models; An optimal docking path model is generated by selecting a path planning algorithm to generate the optimal docking path.

5. The method for constructing an intelligent tooling reference model for complex product assembly according to claim 1, characterized in that: The timing association model, precision mapping model and tooling module are multi-model coupled to form a tooling reference model. Specifically, a virtual simulation environment for the assembly process is constructed using SIMIO, MATLAB, or Simulink. The timing association model, precision mapping model and tooling function module library are multi-model coupled to form a tooling reference model.

6. An engineering implementation method for an intelligent tooling reference model for complex product assembly, characterized by: The specific steps include: Based on the tooling reference model, a flexible tooling design solution including positioning module, clamping module, jig module, and docking module is constructed; The flexible chemical equipment design scheme based on the construction simulates the dynamic behavior in the actual assembly scene through 3D modeling and dynamic simulation platform; Optimize the design of flexible chemical equipment based on simulation results; The optimized flexible chemical equipment design scheme is applied to actual production and manufacturing.

7. The engineering implementation method of the intelligent tooling reference model for complex product assembly according to claim 6, characterized in that: Based on the tooling reference model, a flexible tooling design scheme including positioning module, clamping module, jig module, and docking module is constructed. The specific steps are as follows: Based on the time series correlation model and combined with the tooling reference parameters in the tooling function module library, a positioning module is constructed for dynamically matching the parts to be assembled; Based on the association rules between load and deformation in the dimensional chain precision mapping model, a clamping module is constructed to adjust the clamping force threshold and adaptive compensation logic. Based on the reconfigurable interface of the tooling function library, a parameterized jig module is constructed to adjust the jig's degrees of freedom and connection devices; Based on the docking model of the time series association model and the dimensional chain accuracy constraint of the dimensional chain accuracy mapping model, a docking module for generating tolerance-compensated docking trajectories is constructed.

8. The engineering implementation method of the intelligent tooling reference model for complex product assembly according to claim 7 is characterized by: Before the simulation, the flexible chemical equipment design scheme was pre-designed. The specific steps are as follows: The positioning module corresponds to a digital flexible positioning system, in which the tooling positioning data is transmitted to the control system in digital form, and then transmitted to the actuator by the control system, and positioning is completed through digital motion; The clamping module is matched with a digital flexible adaptive clamping device. According to the shape and type of different parts, the clamping parameters are dynamically adjusted based on real-time positioning data to be compatible with the assembly of different types of parts and ensure adaptive clamping during the assembly process. The docking module is matched with a digital flexible equipment jig, and the module state is changed by adjusting the degree of freedom and connecting devices to meet the needs of similar products and realize the co-line assembly of multiple varieties of parts in small batches; The docking module is matched with a digital and flexible automated docking device, which drives the docking mechanism based on precise positioning and stable clamping to ensure automated and precise coordination between components. Each module operates collaboratively through a data link to build a flexible solution suitable for multi-variety, small-batch assembly.

9. The engineering implementation method of the intelligent tooling reference model for complex product assembly according to claim 8, characterized in that: Optimize the flexible chemical equipment design scheme based on simulation results. The specific steps are as follows: Through 3D modeling and dynamic simulation platform, dynamic behavior in actual assembly scenarios is simulated: Kinematic simulation is used to analyze the motion trajectories between the digital flexible positioning system, adaptive clamping device, equipment jig, and automated docking device to detect potential mechanical interference issues when the various devices work together. Finite element analysis is used to evaluate the stress distribution of key components to ensure that the structural strength meets long-term use requirements. Control logic simulation is used to verify the coordination of the electromechanical system, and core indicators including positioning accuracy, clamping force stability and jig reconstruction efficiency are tested through real-time digital twin models; In response to the interference, stress concentration, and control delay problems exposed in the simulation, parametric drive technology is used to iteratively optimize the tooling geometric topology and control system algorithm, ultimately forming an optimized flexible tooling design scheme that has been virtually verified, providing data support for physical prototype manufacturing.

10. The engineering implementation method of the intelligent tooling reference model for complex product assembly according to claim 6, characterized in that: The optimized flexible chemical equipment design was also tested. The specific steps are as follows: Implement the optimized flexible chemical equipment design scheme in actual assembly scenarios; Physical tests are conducted on positioning accuracy, clamping force, jig stiffness, and docking repeatability. The system's long-term stability and anti-interference capabilities are tested under typical operating conditions, targeting the harsh conditions that may be encountered in actual production. If the test is passed, the final intelligent assembly tooling system will be applied to actual production and manufacturing; if it fails, the flexible tooling design plan will be rebuilt.

Images