Virtual-real fusion intelligent manufacturing teaching system based on digital twinning

Abstract

The invention relates to the technical field of intelligent manufacturing education, in particular to a virtual-real fusion intelligent manufacturing teaching system based on digital twinning. According to the method, the multi-dimensional digital twin model is constructed and synchronized with the physical manufacturing equipment in real time, the virtual simulation operation is verified by the programmable logic controller and then issued to the physical equipment to be executed to form a safe closed loop, and dynamic binding and flexible combination control of the reconfigurable production line is achieved based on the EtherCAT protocol. Data linkage visualization is performed by adopting a Websocket and HTTP fusion protocol, and personalized simulation tasks are dispatched according to learning records, so that the problems of high cost, high security risk, insufficient virtual-real interaction precision and lack of personalization due to the fact that traditional teaching depends on real equipment are solved; the intelligent manufacturing teaching environment virtuality and reality fusion depth, the resource configuration flexibility and the personalized teaching ability are improved.

Description

Technical Field

[0001] This invention relates to the field of intelligent manufacturing education technology, and in particular to a virtual-real integrated intelligent manufacturing teaching system based on digital twins. Background Technology

[0002] With the deepening development of Industry 4.0 and intelligent manufacturing technologies, traditional engineering education models face significant challenges. Current teaching practices primarily rely on real industrial equipment, but this equipment is expensive to purchase, complex to maintain, and poses significant operational safety risks, making large-scale deployment in academic settings difficult. This limits students' hands-on opportunities and increases the risk of accidents. Meanwhile, while simple virtual simulation software can build basic experimental environments, it lacks real-time data interaction capabilities with physical equipment, resulting in limited simulation accuracy and dynamic response performance. It cannot achieve a precise one-to-one mapping and synchronous control between virtual and real spaces, preventing students from receiving realistic operational feedback and an immersive learning experience, significantly diminishing the teaching effectiveness. Furthermore, early digital twin systems were largely designed for industrial production rather than educational scenarios, with teaching content lagging behind the pace of industrial technology development. The system architecture lacks modular reconstruction and flexible configuration capabilities, failing to provide personalized learning paths and differentiated training programs based on students' different knowledge bases and skill levels. These problems lead to a long-term disconnect between theoretical teaching and engineering practice. Students struggle to develop a systematic understanding of the entire intelligent manufacturing process and lack the hands-on skills to handle complex engineering scenarios, severely hindering the efficiency and quality of cultivating high-quality engineering and technical personnel. Summary of the Invention

[0003] To address the aforementioned technical problems, this invention provides a virtual-real fusion intelligent manufacturing teaching system based on digital twins. The technical solution of this system is as follows: The physical data acquisition and digital twin model construction module is used to acquire the operating data of physical manufacturing equipment in real time based on a unified architecture industrial communication protocol, and to construct and dynamically update a digital twin model corresponding to the physical manufacturing equipment, covering geometric, information, motion, control, communication and physical dimensions, and maintain the real-time synchronization between the digital twin model and the physical manufacturing equipment. The virtual simulation and closed-loop control module receives user operation commands and drives the corresponding simulation operations in the digital twin model. It sends the simulation operation commands to the programmable logic controller for logic verification and collision detection, and generates control commands based on the verification results to send to the corresponding physical manufacturing equipment, forming a safety control closed loop consisting of virtual simulation, program verification, and physical execution. The reconfigurable production line collaborative control module includes an open controller based on the EtherCAT protocol and multiple hardware slave device modules that can be accessed as nodes. The open controller is used to dynamically load and bind the driver model of the selected hardware slave device module according to the teaching task, and generate the corresponding logic control program to flexibly combine and coordinate a group of physical manufacturing equipment in real time. The data fusion visualization and teaching management module is used to acquire the running status of the digital twin model, the production process data of physical equipment, and user learning records in real time using a combination of Websocket and HTTP protocols. It uses the Echarts chart library to trigger rendering and dynamic display of multi-source data, and combines a modular teaching content library and a personalized learning path planning algorithm to assign simulation teaching tasks to users based on their learning records.

[0004] Furthermore, the unified architecture industrial communication protocol is the OPC UA unified architecture.

[0005] Furthermore, data exchange between the virtual simulation and closed-loop control module and the programmable logic controller is achieved through a dedicated communication unit.

[0006] Furthermore, the personalized learning path planning algorithm uses an adaptive dynamic recommendation formula to calculate the recommendation priority score of the simulated teaching task. The adaptive dynamic recommendation formula integrates multiple factors, including time-decayed student skill assessment, similar user success records, matching degree between student ability and task difficulty, and weight of the inherent teaching value of the task.

[0007] Furthermore, the open controller dynamically loads the driver model based on the XML device description file generated from the hardware slave device module.

[0008] Furthermore, when the data fusion visualization and teaching management module triggers rendering of multi-source data in a linked manner, the associated 3D models, charts, and list components are synchronously redrawn when the status of any data source is updated.

[0009] Furthermore, the system is deployed on a cloud server and supports remote terminal access.

[0010] Furthermore, the safety control closed loop consisting of virtual simulation, program verification, and physical execution specifically includes: completing the simulation operation path planning in the digital twin model, sending the path control logic to the programmable logic controller for virtual debugging and collision detection, and only after the verification is passed can the corresponding G-code motion command be sent to the physical manufacturing equipment for execution.

[0011] Furthermore, the adaptive dynamic recommendation formula is as follows: in, Indicates time Task For students Recommendation priority score; , , , For dynamic adjustment coefficients; Indicates task Required core skill set; Students Skill Points The most recent assessment score; Indicates the time of the assessment; The time decay factor; Represents a set of users with similar learning features; Indicates user With students Similarity; For indicator functions; Students Current overall ability level; Indicates task Preset difficulty level; Indicates task Inherent teaching value weight.

[0012] Furthermore, the reconfigurable production line collaborative control module can quickly switch and reassemble different processes on the same group of physical manufacturing equipment by reconfiguring the logic control program in the open controller and the binding relationship between the hardware slave device module, according to different teaching tasks.

[0013] The technical solution of the present invention has significant beneficial effects compared with the prior art, specifically: 1) By constructing a multi-dimensional digital twin model covering geometry, information, motion, control, communication and physical dimensions and synchronizing it with physical devices in real time, the problem of single dimension and insufficient accuracy of virtual-real mapping in traditional virtual simulation models is solved, and more comprehensive virtual-real fusion and high-precision synchronization are achieved.

[0014] 2) By introducing a safety control closed loop consisting of virtual simulation, program verification and physical execution, virtual operation instructions must be logically verified and collision detected by a programmable logic controller before they can be issued for execution. Compared with existing technologies that directly perform virtual-real interaction or lack systematic verification, this fundamentally eliminates the risk of equipment damage and personal safety caused by misoperation, and significantly improves the inherent safety of the teaching system.

[0015] 3) By adopting an open controller based on the EtherCAT protocol and hardware slave device modules that can be accessed by nodes, and dynamically loading the driver model according to the XML device description file to generate the control program, compared with the traditional training system with fixed hardware configuration or loose hardware and software binding, the system realizes flexible and rapid reconfiguration and collaborative control of physical production line equipment, which greatly improves the flexibility of teaching resource allocation and the diversity of scenarios.

[0016] 4) By adopting the Websocket and HTTP fusion protocol to obtain multi-source data in real time and using the Echarts chart library for linked trigger rendering, compared with static or one-way data display methods, it realizes real-time, dynamic and related visualization of data throughout the teaching process, enhancing state awareness and immersive experience.

[0017] 5) By combining a modular teaching content library with an adaptive dynamic recommendation formula that integrates multiple factors for personalized learning path planning, compared with matching fixed teaching content or simple historical records, it achieves precise quantitative matching and dynamic adjustment of students' ability progress and the value of teaching tasks, effectively improving the personalization and adaptability of teaching.

[0018] The technical features of this invention are interconnected and work synergistically to solve the pain points of traditional intelligent manufacturing teaching, such as high cost, high risk, poor interaction, and rigid content. This invention achieves a systematic improvement in the teaching environment in terms of the depth of virtual-real integration, the flexibility of resource allocation, and the ability to provide personalized teaching.

[0019] The above description is merely an overview of the technical solution of the present invention. In order to better understand the technical means of the present invention and to implement it in accordance with the contents of the specification, and to make the above and other objects, features and advantages of the present invention more apparent and understandable, specific embodiments of the present invention are described below. Attached Figure Description

[0020] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0021] The accompanying drawings are for illustrative purposes only and are not intended to limit the invention. Furthermore, the same reference numerals denote the same parts throughout the drawings. In the drawings: Figure 1 This is a schematic diagram of an embodiment of a digital twin-based virtual-real integrated intelligent manufacturing teaching system according to the present invention. Detailed Implementation

[0022] Exemplary embodiments of the invention will now be described in more detail with reference to the accompanying drawings. While exemplary embodiments of the invention are shown in the drawings, it should be understood that the invention can be implemented in various forms and should not be limited to the embodiments set forth herein.

[0023] Figure 1 This diagram illustrates a structural schematic of an embodiment of a digital twin-based intelligent manufacturing teaching system that integrates virtual and real elements, provided by the present invention. Figure 1 As shown, the system includes: The physical data acquisition and twin model construction module 110 is used to acquire the operating data of physical manufacturing equipment in real time based on a unified architecture industrial communication protocol, and to construct and dynamically update a digital twin model corresponding to the physical manufacturing equipment, covering geometric, information, motion, control, communication and physical dimensions, and maintain the real-time synchronization between the digital twin model and the physical manufacturing equipment.

[0024] Among them, a unified architecture industrial communication protocol refers to a communication specification that provides standardized rules and interface models for data exchange between industrial automation equipment and control systems. For example, in a mobile phone casing polishing production line, the OPCUA protocol is used as a unified architecture industrial communication protocol, enabling the upper-level teaching system to read the coordinate and status data of the six-axis robot in a unified format. Physical manufacturing equipment refers to physical mechanical equipment used to perform specific manufacturing, processing, or assembly tasks in a real industrial production or training environment. For example, the physical manufacturing equipment in a mobile phone casing polishing production line includes a feeding conveyor belt, a six-axis polishing robot, a polishing worktable, and a unloading robotic arm. Operational data refers to a set of data generated in real time by the physical manufacturing equipment during operation, characterizing its working status, performance parameters, and environmental conditions. For example, the operational data of a six-axis polishing robot includes the real-time current, speed, and temperature of each joint motor, as well as the precise position coordinates of the end effector in three-dimensional space. A digital twin model refers to a digital mirror model constructed in virtual space based on the physical characteristics and operating mechanism of physical manufacturing equipment, encompassing multiple dimensions such as geometry, information, motion, control, communication, and physics. For example, a digital twin model constructed for a six-axis grinding robot includes a three-dimensional appearance, kinematic equations, control logic addresses, communication parameters, and mass and inertial properties, and maintains motion synchronization with the real robot.

[0025] The virtual simulation and closed-loop control module 120 is used to receive user operation instructions and drive the corresponding simulation operations in the digital twin model. It sends the simulation operation instructions to the programmable logic controller for logic verification and collision detection, and generates control instructions based on the verification results to send to the corresponding physical manufacturing equipment, forming a safety control closed loop consisting of virtual simulation, program verification and physical execution.

[0026] User operation instructions refer to commands issued by users to the system through a human-computer interaction interface, intended to trigger specific equipment actions or processes; for example, a student clicking the virtual "Start Polishing" button on the touchscreen of a virtual teaching platform generates a user operation instruction. Simulation operation refers to the digital twin model simulating the execution of corresponding action sequences or processes in a virtual environment based on received user operation instructions; for example, after receiving the "Start Polishing" instruction, the virtual polishing machine in the digital twin model begins to simulate the complete process of moving to the processing position, starting the grinding head, and moving along a preset trajectory. A programmable logic controller (PLC) is a computer control device specifically designed for industrial environments, which executes stored logic instructions to achieve sequential control, motion control, and process monitoring; for example, in a grinding and polishing production line, a PLC is responsible for receiving signals from various sensors and controlling the start and stop of the conveyor belt and the robot's action sequence according to its internal program logic. Logic verification and collision detection refer to the process of reviewing the correctness of program logic and checking for spatial interference of simulated operation instructions or planned paths in a virtual environment. For example, when a grinding trajectory planned by a virtual robot is sent to a programmable logic controller (PLC) simulation environment, the control logic is first checked to ensure it complies with safety interlocks, and then the risk of spatial collision between the tool path and the workpiece fixture is calculated. Verification results refer to the conclusions regarding operational safety and logical correctness reached after the logic verification and collision detection process is completed. For example, if the system outputs a logically correct path with no collision risk after verification, this is the verification result. Control instructions refer to the low-level control signals or codes generated after system verification that can directly drive physical manufacturing equipment to perform specific actions. For example, after successful verification, a series of G-code motion instructions generated and issued by the system to the real grinding robot are the control instructions.

[0027] The safety control closed loop refers to a protective control process consisting of three interconnected stages: virtual simulation, program verification, and physical execution. This ensures that instructions are verified correctly in the virtual environment before being sent to the physical device for execution. For example, when a student operates a polishing machine model in a virtual environment, the system converts this operation into control logic and sends it to the programmable logic controller for virtual debugging and collision detection. Only after confirming safety is the G-code sent to the real polishing machine for execution, thus forming a safety control closed loop.

[0028] The reconfigurable production line collaborative control module 130 includes an open controller based on the EtherCAT protocol and multiple hardware slave device modules that can be accessed by nodes. The open controller is used to dynamically load and bind the driver model of the selected hardware slave device module according to the teaching task, and generate the corresponding logic control program to flexibly combine and coordinate a group of physical manufacturing equipment in real time.

[0029] EtherCAT protocol refers to a high-performance real-time industrial fieldbus protocol based on Ethernet, used to achieve millisecond-level precise communication between industrial controllers and distributed I / O devices or drives. For example, in a reconfigurable production line, an open controller uses the EtherCAT protocol to exchange data at high speed with multiple servo drives, achieving multi-axis synchronous motion control. An open controller refers to an industrial control core device that adopts an open hardware and software architecture, supports multiple industrial bus protocols, and allows users to customize application logic. For example, an industrial PC equipped with EtherCAT master station functionality acts as an open controller, managing the communication and control of all slave devices. A node-accessible hardware slave device module refers to a hardware unit designed based on fieldbus protocols that can dynamically join or leave the control network as an independent node and execute specific I / O or motion control functions. For example, a newly added vision inspection camera, as an EtherCAT slave device module, can be recognized by the controller and integrated into the control system by connecting to the network via a network cable. A teaching task refers to a practical training project designed to achieve specific skill development goals, containing clearly defined operational steps, process requirements, and assessment standards; for example, completing the entire collaborative operation of a mobile phone casing, from loading, positioning, grinding to polishing and unloading, constitutes a teaching task. A driver model refers to a software object in the controller software that represents the functional characteristics and communication protocols of a hardware slave device module, typically generated based on a device description file; for example, when a new servo driver module connects to an EtherCAT network, the open controller dynamically loads the corresponding XML device description file, generating a driver model in the software containing all parameters and command interfaces of that driver. A logic control program refers to program code written according to production processes and safety requirements, used to coordinate a group of devices to work collaboratively in a predetermined order and under predetermined conditions; for example, to complete the grinding task of a mobile phone casing, the logic control program running in the open controller will sequentially trigger the loading signal, control the robot to grasp, start the grinding motor, and guide the robot to move along a trajectory. Flexible combination and real-time collaborative control refers to a control method that uses software configuration to quickly reassemble standardized equipment modules according to changes in production needs, and achieves high-precision synchronous operation between them. For example, when the teaching task changes from polishing mobile phone shells to polishing small metal parts, the equipment originally used for polishing can be quickly reassembled into the fine grinding station by reconfiguring the program, and achieve millisecond-level collaborative operation with the robot.

[0030] The data fusion visualization and teaching management module 140 is used to acquire the running status of the digital twin model, the production process data of the physical equipment, and the user's learning records in real time using a combination of Websocket and HTTP protocols. It uses the Echarts chart library to trigger and dynamically display multi-source data, and combines a modular teaching content library and a personalized learning path planning algorithm to assign simulation teaching tasks to users based on their learning records.

[0031] The combination of WebSocket and HTTP protocols refers to a hybrid network communication scheme that uses WebSocket to maintain long-term connections for real-time bidirectional data push, while simultaneously using HTTP to handle regular requests and static resource transmission. For example, the system uses WebSocket connections to continuously push real-time robot pose data, while using HTTP to load 3D model files and theoretical courseware. This combination ensures data real-time performance and efficient loading of system resources. Operating status refers to the working mode or health condition of physical manufacturing equipment or digital twin models at a given moment. For example, a real polishing machine may be in operating, emergency stop, or fault alarm states, and the digital twin model synchronously displays the same status. Production process data refers to indicator data generated during product manufacturing or training operations that reflects production efficiency, quality, and resource consumption. For example, the single-piece processing cycle time, surface finish Ra value, and cumulative wear of the grinding head recorded during polishing are production process data. User learning records refer to the historical data set formed by the system's continuous tracking and storage of all user operations, task completion progress, assessment scores, and skill evaluation results within the platform. For example, the system database records the total practice time of students in the robot trajectory programming module, the trajectory error of each practice session, and the scores of each assessment. Echarts chart library refers to an open-source data visualization library based on JavaScript, providing rich chart types for graphical data display. For example, the system uses the Echarts library to plot real-time energy consumption data from multiple devices on the production line into a dynamically updated stacked area chart and display it on the teaching screen. Multi-source data refers to heterogeneous data sets from different modules, devices, or processes within the system. For example, motion data from digital twin models, current and voltage data from physical devices, user operation log data, and environmental temperature and humidity data together constitute multi-source data.

[0032] Among them, "linked trigger rendering and dynamic display" refers to the process where, when the state of a data source changes, all associated visualization components are automatically redrawn and updated. For example, when the alarm status data of a polishing robot is pushed to the front end via Websocket, the corresponding 3D model on the teaching screen immediately turns red, and the alarm list, historical statistics pie chart, and equipment status card in the sidebar are simultaneously refreshed. "Modular teaching content library" refers to a collection of teaching resources that are structured according to knowledge points or skill points and can be independently accessed and combined. For example, the system creates independent digital courseware and virtual training units for basic industrial robot operation, polishing process principles, and OPC UA communication configuration, storing them in the modular teaching content library. "Personalized learning path planning algorithm" refers to a calculation method that intelligently calculates and recommends the optimal sequence of subsequent learning content based on students' historical data and knowledge graphs. For example, the algorithm in the teaching management module analyzes the tasks students have completed and their knowledge weaknesses, automatically calculating the path where they should prioritize learning complex trajectory planning before learning multi-device collaborative debugging. Learning records refer to a subset of a user's learning history that relates to their current ability assessment and knowledge mastery, used as input for personalized recommendations. For example, a personalized learning path planning algorithm might use a student's scores on various skill points over the past three months as learning records to perform task recommendation calculations. Simulated teaching tasks refer to virtual practical training projects selected from a modular teaching content library and matched by a personalized learning path planning algorithm before being pushed to a specific student. For example, based on a student's learning records, the system might push a specialized simulated teaching task called "Precision Assembly Based on Visual Positioning" to that student.

[0033] The technical solution of this embodiment constructs a multi-dimensional digital twin model and synchronizes it with the physical manufacturing equipment in real time. After the virtual simulation operation is verified by the programmable logic controller, it is sent to the physical equipment for execution to form a safe closed loop. Based on the EtherCAT protocol, dynamic binding and flexible combination control of the reconfigurable production line are realized. The Websocket and HTTP fusion protocol is used for data linkage visualization and personalized simulation tasks are assigned according to learning records. This solves the problems of high cost, high safety risk, insufficient accuracy of virtual-real interaction, and rigid teaching content caused by the reliance on real equipment in traditional teaching. It realizes the improvement of the depth of virtual-real integration, resource allocation flexibility and personalized teaching capabilities of the intelligent manufacturing teaching environment.

[0034] In one alternative approach, the unified architecture industrial communication protocol is the OPC UA unified architecture.

[0035] Among them, the OPC UA unified architecture refers to the industrial communication architecture defined by the specific standard OPC UA, which has a unified information model and cross-platform secure communication mechanism; for example, the physical data acquisition module can securely read and write data from the robot controller through a server interface that conforms to the OPC UA unified architecture.

[0036] Among the above-mentioned optional methods, the OPC UA unified architecture is further adopted as the industrial communication protocol, which improves the level of communication standardization and cross-platform interoperability, realizes unified description of equipment models and semantic-level data interoperability, and enhances the access capability of multi-source heterogeneous equipment.

[0037] In one alternative approach, the virtual simulation and data exchange between the closed-loop control module and the programmable logic controller are achieved through a dedicated communication unit.

[0038] Among them, the dedicated communication unit refers to a functional component integrated inside the virtual simulation and closed-loop control module, which is dedicated to establishing a stable, real-time data channel with the programmable logic controller. For example, the dedicated communication unit in the virtual teaching platform establishes a periodic read-write connection with a specific data block of the programmable logic controller through the industrial Ethernet protocol.

[0039] In the above-mentioned optional methods, data exchange between virtual simulation and programmable logic controller is further realized through a dedicated communication unit, which enhances the real-time performance and reliability of data transmission, reduces network latency and packet loss rate, and ensures the synchronization accuracy of virtual control and physical execution.

[0040] In one alternative approach, the personalized learning path planning algorithm uses an adaptive dynamic recommendation formula to calculate the recommendation priority score of the simulated teaching task. The adaptive dynamic recommendation formula integrates multiple factors, including time-decayed student skill assessment, similar user success records, matching degree between student ability and task difficulty, and weight of the inherent teaching value of the task.

[0041] The recommendation priority score refers to a numerical value calculated by the personalized learning path planning algorithm to quantify the urgency of recommending a specific simulation teaching task to a specific student. For example, the algorithm calculates a recommendation priority score of 0.85 for the robot collision avoidance programming task, which is higher than other tasks, and therefore prioritizes it. Student skill assessment refers to a quantitative evaluation of a student's mastery of specific knowledge or skills. For example, based on the student's average accuracy and completion speed in the last five trajectory programming exercises, the system assesses their trajectory accuracy control skill point score as 0.72. Similar user success records refer to historical information on other users with similar learning characteristics to the target student who have successfully completed specific simulation teaching tasks. For example, the algorithm finds five users with similar learning patterns to the student who have all successfully completed the EtherCAT slave configuration task; this record will be used as one of the recommendation criteria. Student ability and task difficulty matching degree refers to a measure of the degree of fit between the student's current comprehensive ability level and the preset difficulty of the simulation teaching task. For example, if the student's current comprehensive ability level is L3 and the preset difficulty of the multi-robot collaborative welding task is D4, the algorithm calculates the matching degree between the two. The inherent teaching value weight of a task refers to a fixed weight coefficient assigned to a simulation teaching task based on the teaching syllabus or expert experience, reflecting its fundamental, important, or cutting-edge nature; for example, in the curriculum system, safety operating procedures are given a high inherent teaching value weight T=0.9 to ensure that they are given priority recommendation.

[0042] Among the above-mentioned optional methods, an adaptive dynamic recommendation formula that integrates time decay assessment, similar user records, ability difficulty matching, and task value weight is further adopted. This enables the teaching tasks to be accurately matched with students' ability levels, dynamically adjust the recommendation strategy, and improve the relevance of personalized learning.

[0043] In one alternative approach, the driver model dynamically loaded by the open controller is generated based on the XML device description file of the hardware slave device module.

[0044] Among them, the XML device description file refers to a standardized file written in XML format to describe the functions, parameters and communication interfaces of industrial field equipment; for example, each EtherCAT servo drive module comes with an XML device description file, which defines in detail the control parameters, status words and process data mapping relationships.

[0045] Among the above optional methods, a driver model is further generated based on the XML device description file of the hardware slave device module, which simplifies the device driver development process, improves the plug-and-play capability of the hardware module, and shortens the configuration time and maintenance cost of the reconfigurable production line.

[0046] In one alternative approach, when the data fusion visualization and teaching management module triggers rendering of multi-source data in a linked manner, the associated 3D model, chart, and list components are synchronously redrawn when the status of any data source is updated.

[0047] In the above-mentioned optional methods, multi-source data linkage triggering rendering is further implemented in the data fusion visualization module. When the status of any data source is updated, the associated 3D model, chart and list components are redrawn synchronously, which improves the system status awareness capability and interface response speed.

[0048] In one alternative approach, the system is deployed on a cloud server and supports remote terminal access.

[0049] In this context, a cloud server refers to a remote, virtualized server resource deployed in an internet data center, providing computing, storage, and network services. For example, deploying the application software and database of a digital twin-based, virtual-real integrated intelligent manufacturing teaching system on a cloud-based elastic computing service instance constitutes a cloud server. A remote terminal refers to a client device that can access the application services provided by the cloud server via a network. For example, students using personal laptops or tablets to access the teaching system deployed on the cloud server through a browser are considered remote terminals.

[0050] Among the above-mentioned optional methods, further deploying the system on a cloud server and supporting remote terminal access breaks through geographical limitations to achieve the sharing of teaching resources, reduces the hardware investment threshold for colleges and universities, and supports multi-user concurrent online learning and collaborative training.

[0051] In one alternative approach, the safety control closed loop consisting of virtual simulation, program verification, and physical execution specifically includes: completing the simulation operation path planning in the digital twin model, sending the path control logic to the programmable logic controller for virtual debugging and collision detection, and only after the verification is passed can the corresponding G-code motion command be sent to the physical manufacturing equipment for execution.

[0052] Among them, simulation operation path planning refers to the process of calculating an optimized motion trajectory for a virtual device in the virtual environment where the digital twin model is located, from the starting point to the target point, and satisfying kinematic, dynamic and obstacle avoidance constraints; for example, planning a smooth and collision-free motion path for a polishing robot in a virtual scene, from the standby point around obstacles to the processing point.

[0053] Among the above-mentioned optional methods, the safety control closed loop is further defined to include simulation path planning, PLC virtual debugging and collision detection, and issuing G-code instructions after verification. This refines the safety verification process and ensures that physical devices only receive instructions that have undergone rigorous testing, thereby reducing the risk of misoperation.

[0054] In one alternative approach, the adaptive dynamic recommendation formula is: in, Indicates time Task For students Recommendation priority score; , , , For dynamic adjustment coefficients; Indicates task Required core skill set; Students Skill Points The most recent assessment score; Indicates the time of the assessment; The time decay factor; Represents a set of users with similar learning features; Indicates user With students Similarity; For indicator functions; Students Current overall ability level; Indicates task Preset difficulty level; Indicates task Inherent teaching value weight.

[0055] Among the above-mentioned optional methods, the mathematical expression of the adaptive dynamic recommendation formula is further clarified, the weight relationship of each dimension is quantified, the interpretability of recommendation results and the accuracy of parameter tuning are improved, and a standardized measurement basis is provided for teaching evaluation.

[0056] In one alternative approach, the reconfigurable production line collaborative control module can quickly switch and reassemble different processes on the same set of physical manufacturing equipment by reconfiguring the logic control program in the open controller and the binding relationship between the hardware slave device module and different teaching tasks.

[0057] In this context, "binding relationship" refers to the mapping and connection established between software control points in the logic control program and the physical I / O channels or drive parameters of a specific hardware slave device module in an open controller. For example, in the controller configuration software, the conveyor belt start output variable in the logic program is bound to the third digital output channel on a specific EtherCAT remote I / O module.

[0058] Among the above-mentioned optional methods, by further reconfiguring the binding relationship between the open controller logic program and the hardware slave module, different process flows can be quickly switched and recombined on the same group of physical devices, which enhances the flexible manufacturing capability of the teaching system and expands the coverage of teaching scenarios.

[0059] The above description is merely a preferred embodiment of the present invention and an explanation of the technical principles employed. Those skilled in the art should understand that the scope of disclosure in this invention is not limited to technical solutions formed by specific combinations of the above-described technical features, but should also cover other technical solutions formed by arbitrary combinations of the above-described technical features or their equivalents without departing from the above-disclosed concept. For example, technical solutions formed by substituting the above features with (but not limited to) technical features with similar functions disclosed in this invention.

[0060] It should be noted that the terms "first," "second," etc., used in the specification and claims of this application are used to distinguish similar objects and do not imply a limitation on a specific order or sequence. Where appropriate, the order of use for similar objects can be interchanged so that the embodiments of this application described herein can be implemented in an order other than that shown or described.

[0061] Although embodiments of the present invention have been shown and described above, it is understood that the above embodiments are exemplary and should not be construed as limiting the present invention. Those skilled in the art can make changes, modifications, substitutions and variations to the above embodiments within the scope of the present invention.

Claims

1. A virtual-real integrated intelligent manufacturing teaching system based on digital twins, characterized in that... ,include: The physical data acquisition and digital twin model construction module is used to acquire the operating data of physical manufacturing equipment in real time based on a unified architecture industrial communication protocol, and to construct and dynamically update a digital twin model corresponding to the physical manufacturing equipment, covering geometric, information, motion, control, communication and physical dimensions, and maintain the real-time synchronization between the digital twin model and the physical manufacturing equipment. The virtual simulation and closed-loop control module receives user operation commands and drives the corresponding simulation operations in the digital twin model. It sends the simulation operation commands to the programmable logic controller for logic verification and collision detection, and generates control commands based on the verification results to send to the corresponding physical manufacturing equipment, forming a safety control closed loop consisting of virtual simulation, program verification, and physical execution. The reconfigurable production line collaborative control module includes an open controller based on the EtherCAT protocol and multiple hardware slave device modules that can be accessed as nodes. The open controller is used to dynamically load and bind the driver model of the selected hardware slave device module according to the teaching task, and generate the corresponding logic control program to flexibly combine and coordinate a group of physical manufacturing equipment in real time. The data fusion visualization and teaching management module is used to acquire the running status of the digital twin model, the production process data of physical equipment, and user learning records in real time using a combination of Websocket and HTTP protocols. It uses the Echarts chart library to trigger rendering and dynamic display of multi-source data, and combines a modular teaching content library and a personalized learning path planning algorithm to assign simulation teaching tasks to users based on their learning records.

2. The virtual-real fusion intelligent manufacturing teaching system based on digital twins according to claim 1, characterized in that... The unified architecture industrial communication protocol is the OPC UA unified architecture.

3. The intelligent manufacturing teaching system based on digital twins and fusion of virtual and real worlds according to claim 1, characterized in that... In the virtual simulation and closed-loop control module, data exchange with the programmable logic controller is achieved through a dedicated communication unit.

4. The virtual-real fusion intelligent manufacturing teaching system based on digital twins according to claim 1, characterized in that... The personalized learning path planning algorithm uses an adaptive dynamic recommendation formula to calculate the recommendation priority score of the simulated teaching task. The adaptive dynamic recommendation formula integrates multiple factors, including time-decayed student skill assessment, similar user success records, matching degree between student ability and task difficulty, and weight of the inherent teaching value of the task.

5. The virtual-real fusion intelligent manufacturing teaching system based on digital twins according to claim 1, characterized in that... The open controller dynamically loads the driver model based on the XML device description file of the hardware slave device module.

6. The virtual-real fusion intelligent manufacturing teaching system based on digital twins according to claim 1, characterized in that... When the data fusion visualization and teaching management module triggers rendering of multi-source data, the associated 3D model, chart and list components are redrawn synchronously when the status of any data source is updated.

7. The virtual-real fusion intelligent manufacturing teaching system based on digital twins according to claim 1, characterized in that... The system is deployed on a cloud server and supports remote terminal access.

8. The virtual-real fusion intelligent manufacturing teaching system based on digital twins according to any one of claims 1 to 7, characterized in that... The safety control closed loop, consisting of virtual simulation, program verification, and physical execution, specifically includes: completing the simulation operation path planning in the digital twin model, sending the path control logic to the programmable logic controller for virtual debugging and collision detection, and only after the verification is passed can the corresponding G-code motion command be sent to the physical manufacturing equipment for execution.

9. The virtual-real fusion intelligent manufacturing teaching system based on digital twins according to claim 4, characterized in that... The adaptive dynamic recommendation formula is: in, Indicates time Task For students Recommendation priority score; , , , For dynamic adjustment coefficients; Indicates task Required core skill set; Students Skill Points The most recent assessment score; Indicates the time of the assessment; The time decay factor; Represents a set of users with similar learned features; Indicates user With students Similarity; For indicator functions; Students Current overall ability level; Indicates task Preset difficulty level; Indicates task Inherent teaching value weight.

10. The virtual-real fusion intelligent manufacturing teaching system based on digital twins according to claim 1, characterized in that... The reconfigurable production line collaborative control module, based on different teaching tasks, enables rapid switching and reorganization of different processes on the same group of physical manufacturing equipment by reconfiguring the logic control program in the open controller and the binding relationship between the hardware slave device module.

Images