Intelligent manufacturing factory simulation teaching system based on AI + VR and implementation method

Abstract

The invention belongs to the technical field of virtual intelligence, and particularly relates to an intelligent manufacturing factory simulation teaching system based on AI + VR and an implementation method. The system comprises a VR display module, an AI learning guiding module, a factory simulation module, an interaction control module and a data storage module, all the modules achieve data interaction and function cooperation through standardized interfaces, the AI learning guiding module obtains an operation instruction from the interaction control module and sends a visual prompt instruction to the VR display module, and the VR display module displays the visual prompt instruction. Interacting trainee ability data with the data storage module; the factory simulation module receives an operation instruction of the interaction control module and provides equipment state data for the AI learning guiding module; the interaction control module sends a control instruction to the factory simulation module; the data storage module interacts with the AI learning guiding module through an API interface. According to the invention, the problems of lack of intelligence and adaptivity in teaching and lack of deep fusion between a virtual environment and a real industrial control protocol are solved.

Description

TECHNICAL FIELD

[0001] The present application belongs to the technical field of virtual intelligence, and more particularly, to an AI+VR-based intelligent manufacturing factory simulation teaching system and implementation method. BACKGROUND

[0002] With the rapid development of intelligent manufacturing technology, industrial manufacturing enterprises have increasingly high requirements for employees' operation skills and system understanding ability. Traditional training methods are limited by high equipment cost, large site restrictions, significant safety risks, and lack of teaching resources, and are difficult to meet the efficient, safe, and accurate training needs under the modern intelligent manufacturing system.

[0003] Chinese invention patent CN117765783A discloses an intelligent interactive training system based on virtual reality technology. The system includes: a training environment virtual module for establishing a virtual training environment through a virtual reality device; an intelligent interaction design module for identifying the intent in the user's voice and generating targeted answers and suggestions through artificial intelligence; a virtual scene modeling and simulation module for constructing a virtual scene and performing scene simulation using computer graphics and a physics engine; a training content development module for developing corresponding training content according to the user's training requirements; and a training effect evaluation module for evaluating the user's performance in virtual training and providing customized training suggestions and optimization schemes for the user.

[0004] Existing virtual simulation training systems mostly focus on scene visualization and basic operation simulation, and generally have the following defects: first, there is a lack of intelligence and adaptability in teaching guidance, and personalized guidance cannot be provided according to the actual operation level of students; second, there is a lack of deep integration between virtual environment and real industrial control protocol in virtual-real interaction, resulting in a disconnection between operation experience and real production line; third, the feedback mechanism is relatively single, relying mainly on visual cues, and lacking multi-sensory coordinated teaching feedback, affecting the efficiency of skill transfer and immersion; fourth, the evaluation system is mostly based on rules or static indicators, making it difficult to dynamically capture the growth trajectory of students' ability and optimize the teaching path.

[0005] Therefore, there is an urgent need for a comprehensive simulation teaching system that integrates artificial intelligence and virtual reality technology, and has the capabilities of intelligent learning guidance, multi-modal interaction, virtual-real linkage, and dynamic evaluation, to improve training effectiveness and resource utilization efficiency. SUMMARY

[0006] The present application aims to overcome at least one of the above-mentioned defects of the prior art, and provides an AI+VR-based intelligent manufacturing factory simulation teaching system to solve the problems of lack of intelligence and adaptability in teaching guidance, and lack of deep integration between virtual environment and real industrial control protocol.

[0007] The detailed technical solutions of the present application are as follows: An intelligent manufacturing factory simulation teaching system based on AI+VR, the system comprises a VR display module, an AI learning module, a factory simulation module, an interactive control module and a data storage module, each module realizes data interaction and function cooperation through a standardized interface, forming a closed-loop teaching system; The VR display module realizes handle operation signal acquisition and feedback, completes real-time tracking of user position and posture, provides immersive three-dimensional visual scene rendering, and outputs spatialized audio to enhance immersion, and displays evaluation results in a visual manner; The AI learning module identifies and analyzes student voice instructions, generates personalized learning tasks and guidance plans, and then provides multi-modal feedback, and can generate evaluation reports based on a decision tree model; The factory simulation module constructs a highly realistic three-dimensional factory scene, simulates device physical motion and interaction, analyzes operation behavior and detects errors in real time, and simulates production processes and fault scenarios; The interactive control module recognizes natural gestures and maps them to operation instructions, provides an industrial protocol interface to connect real factory equipment, generates operation force feedback to enhance realism, and realizes precise control of virtual equipment; The data storage module stores student ability data and learning history, records operation details for review and analysis, manages intelligent manufacturing field knowledge graph, and supports data query and statistical analysis.

[0008] The VR display module communicates with the host computer through USB 3.0 and HDMI interfaces and displays; The AI learning module obtains operation instructions from the interactive control module, sends visual prompt instructions to the VR display module, and interacts with the data storage module to obtain student ability data; The factory simulation module and the VR display module share a rendering pipeline, receive operation instructions from the interactive control module, and provide device state data to the AI learning module; The interactive control module is in the form of a handle hardware connected to the host computer through USB / Bluetooth, the industrial protocol interface communicates through Ethernet, and sends control instructions to the factory simulation module, the industrial protocol interface is part of the standardized interface; The data storage module interacts with the AI learning module through an API interface, provides data support for evaluation, and supports data query through a Web-based management interface.

[0009] Further, the VR display module comprises a head-mounted display unit, a handle control unit, a positioning tracking unit and an audio output unit; The head-mounted display unit communicates with the host computer through USB 3.0 and HDMI interfaces, provides immersive three-dimensional visual scene rendering and display; The handle control unit is connected with the head-mounted display unit through Bluetooth to realize handle operation signal acquisition and feedback; The positioning tracking unit completes real-time tracking of user position and posture through a Wi-Fi synchronization clock signal; The audio output unit outputs spatialized audio to enhance immersion.

[0010] Further, the AI learning guide module comprises a voice interaction sub-module and a feedback generation sub-module; The voice interaction sub-module identifies and analyzes the student voice instructions and generates personalized learning tasks and guidance schemes; The feedback generation sub-module provides multi-modal feedback including voice, text and graphics according to the personalized learning tasks and guidance schemes.

[0011] The voice interaction sub-module comprises an ASR voice recognition unit and an NLP semantic understanding unit; The ASR voice recognition unit adopts a Kaldi framework + RNN-CNN model, and the NLP semantic understanding unit adopts a BERT pre-training model + knowledge graph.

[0012] The feedback generation sub-module comprises a voice synthesis unit and a visual prompt generator; The voice synthesis unit adopts a Tacotron2 model, and the visual prompt generator adopts a Unity particle system.

[0013] Further, the factory simulation module comprises a device model library, a scene editing sub-module, a process simulation sub-module and a behavior analysis sub-module; The device model library is used to construct a highly realistic factory three-dimensional scene and simulate device physical motion and interaction; The process simulation sub-module simulates production processes and fault scenarios; The behavior analysis sub-module analyzes operation behavior in real time and detects errors; The scene editing sub-module supports production line custom layout and parameter configuration; Further, the device model library comprises a 1:1 scale three-dimensional device model, a component-level detachable structure and a physical engine sub-module; The 1:1 scale three-dimensional device model comprises N types of industrial equipment, such as CNC machine tools, robot arms and AGV trolleys; The component-level detachable structure is realized through joint constraints; The physical engine sub-module is a PhysX 4.2 or Bullet physical engine.

[0014] The scene editing submodule includes: a production line layout editor and a process parameter configuration panel; the production line layout editor supports drag-and-drop modeling; the process parameter configuration panel includes the actual required physical parameters, such as: rotation speed, temperature, etc.

[0015] The process simulation submodule includes a production process state machine and a fault injector; the production process state machine is used to support work order flow simulation; the fault injector can simulate abnormal equipment operating conditions.

[0016] The behavior analysis submodule includes an operation sequence detector and an error detector; the operation sequence detector uses an LSTM neural network; and the error detector uses a decision tree classification model.

[0017] Furthermore, the interactive control module includes: a gesture recognition submodule, a device control interface, and a force feedback submodule; The gesture recognition submodule is used to recognize natural gestures and map them to device operations. The device control interface is used to provide an industrial protocol interface to connect with real devices. The force feedback submodule generates operational force feedback to enhance realism and achieve precise control of virtual devices.

[0018] Preferably, the gesture recognition submodule includes: a Leap Motion controller or a visual gesture recognition algorithm and a gesture semantic mapping table.

[0019] The device control interface includes: an OPC UA industrial protocol adapter and a Modbus / TCP communication interface.

[0020] The force feedback submodule includes: a handle vibration feedback unit and a resistance simulation motor.

[0021] Furthermore, the data storage module includes: a student database, an operation record database, and a knowledge graph database; The student database is used to store student ability data and learning history; the operation record database is used to record operation details for review and analysis; and the knowledge graph database is used to manage knowledge graphs in the field of intelligent manufacturing, supporting data query and statistical analysis.

[0022] On the other hand, the present invention also includes a method for implementing an AI+VR-based intelligent manufacturing factory simulation teaching system, comprising: S1. Initialization Phase: The VR display module loads a factory scene; The AI-guided learning module generates an initial learning plan based on the student's profile. The data storage module creates training session records; S2, Interaction Phase: Trainees perform operations in a virtual factory using a VR display module; The interactive control module sends operation commands to the factory simulation module; The factory simulation module receives operation commands, updates equipment status, and provides feedback on physical effects. The AI-guided learning module analyzes the operations and generates feedback in real time. S3, Evaluation Phase: The data storage module records the complete operation sequence; The AI-guided learning module generates evaluation reports based on a decision tree model. The VR display module presents the evaluation results in a visual manner.

[0023] In another aspect of the invention, an electronic device is also provided, comprising: At least one processor; and, A memory that stores computer-executable instructions, which, when executed by the at least one processor, cause the at least one processor to execute the computer-executable instructions stored in the memory to implement the system.

[0024] In another aspect of the invention, a computer-readable storage medium is also provided, which stores executable instructions that, when executed by a processor, are used to implement the system.

[0025] Compared with the prior art, the beneficial effects of the present invention are as follows: (1) The AI+VR-based intelligent manufacturing factory simulation teaching system provided by the present invention adopts the dynamic knowledge graph fusion method to associate the NLP model of the AI ​​learning module with the equipment model of the factory simulation module to realize the linkage analysis of "operation-principle".

[0026] (2) The AI+VR-based intelligent manufacturing factory simulation teaching system provided by this invention establishes a two-way mapping between the physical engine and industrial protocols: the two-way conversion between virtual operation and real industrial protocols is realized through the interactive control module. At the same time, a multimodal feedback collaboration mechanism is specified: voice, visual and tactile feedback are integrated to provide differentiated guidance for different error types.

[0027] (3) The AI+VR-based intelligent manufacturing factory simulation teaching system provided by this invention establishes an incremental learning evaluation model, uses an LSTM neural network to construct a learner's ability growth curve, and supports personalized learning path planning. Attached Figure Description Figure 1 This is a diagram illustrating the structure of an AI+VR-based intelligent manufacturing factory simulation teaching system as described in this invention.

[0028] Figure 2It is a schematic flow diagram of the implementation method of an AI+VR-based intelligent manufacturing factory simulation teaching system in Embodiment 1 of the present invention. Detailed implementation manners

[0029] The present invention will be further described below in conjunction with the accompanying drawings and embodiments.

[0030] It should be noted that the following detailed descriptions are all exemplary and are intended to provide further descriptions of the present invention. Unless otherwise specified, all technical and scientific terms used herein have the same meaning as commonly understood by those of ordinary skill in the technical field to which the present invention belongs.

[0031] It should be noted that the terms used herein are only for describing specific implementation manners and are not intended to limit the exemplary embodiments according to the present invention. As used herein, unless the context clearly indicates otherwise, the singular form is also intended to include the plural form. In addition, it should be understood that when the terms "comprise" and / or "include" are used in this specification, they indicate the presence of features, steps, operations, devices, components, and / or combinations thereof.

[0032] In the case of no conflict, the embodiments in the present invention and the features in the embodiments can be combined with each other.

[0033] Embodiment 1 Refer Figure 1 , this embodiment provides an AI+VR-based intelligent manufacturing factory simulation teaching system, and the system includes: a VR display module, an AI tutoring module, a factory simulation module, an interaction control module, and a data storage module. Each module realizes data interaction and function collaboration through a standardized interface, forming a closed-loop teaching system.

[0034] Specifically, the VR display module includes: a head-mounted display unit, a handle control unit, a positioning and tracking unit, and an audio output unit; the head-mounted display unit provides immersive three-dimensional visual scene rendering, the handle control unit realizes the acquisition and feedback of handle operation signals, and then the positioning and tracking unit completes the real-time tracking of the user's position and posture, and the head-mounted display unit performs immersive three-dimensional visual scene rendering and display, and then the audio output unit outputs spatialized audio to enhance the immersion. The head-mounted display unit communicates with the host through USB 3.0 and HDMI interfaces, the handle control unit is connected to the head-mounted display unit through Bluetooth, the positioning and tracking unit, that is, the base station, synchronizes the clock signal through Wi-Fi, and finally the audio output unit outputs spatialized audio.

[0035] Preferably, the head-mounted display unit is selected as: Oculus Quest 2, with a resolution of 1832×1920 / eye and a refresh rate of 90Hz, or HTC Vive Pro 2, with a resolution of 2448×2448 / eye; The controller control unit is selected as a 6DoF haptic feedback controller, supporting trigger button, joystick, and touchpad input; The positioning and tracking unit selected is either a SteamVR 2.0 base station with a positioning accuracy of ±1mm, or an inside-out visual tracking camera. The audio output unit is selected as: integrated 3D sound effect headphones, supporting spatial audio positioning.

[0036] Preferably, the VR display module uses the VR plugin system of Unity3D engine to realize display rendering, and connects to hardware devices such as head-mounted display unit, controller control unit, positioning and tracking unit and audio output unit through OpenVRAPI, and uses parallax rendering and asynchronous spatial distortion technology to reduce dizziness.

[0037] Specifically, the AI-guided learning module includes a voice interaction submodule and a feedback generation submodule.

[0038] The voice interaction submodule recognizes and parses the student's voice commands, and generates personalized learning tasks and guidance plans; the feedback generation submodule provides multimodal feedback, including voice, text and graphics, based on the personalized learning tasks and guidance plans.

[0039] Preferably, the voice interaction submodule includes: an ASR speech recognition unit and an NLP semantic understanding unit; the ASR speech recognition unit adopts the Kaldi framework + RNN-CNN model, and the NLP semantic understanding unit adopts the BERT pre-trained model + knowledge graph.

[0040] The feedback generation submodule includes a speech synthesis unit and a visual cue generator; the speech synthesis unit uses the Tacotron2 model, and the visual cue generator uses the Unity particle system.

[0041] Preferably, the AI-guided learning module uses the TensorFlow framework to build AI models, utilizes the Neo4j graph database to store intelligent manufacturing knowledge graphs, and optimizes the selected industry-specific models through transfer learning.

[0042] The AI-guided learning module obtains operation data from the interactive control module, sends visual prompts to the VR display module, and interacts with the data storage module to obtain student ability data.

[0043] Specifically, the factory simulation module includes: an equipment model library, a scene editing submodule, a process simulation submodule, and a behavior analysis submodule; The equipment model library includes: 1:1 scale 3D equipment models, including N types of industrial equipment and a physics engine submodule; N types of industrial equipment include CNC machine tools, robotic arms, AGV vehicles, and component-level detachable structures (achieved through joint constraints), and the physics engine submodule can be PhysX 4.2 or Bullet physics engine.

[0044] The scene editing submodule includes: a production line layout editor that supports drag-and-drop modeling; and a process parameter configuration panel, including physical parameters such as rotation speed and temperature.

[0045] The process simulation submodule includes: a production process state machine, used to support work order flow simulation; and a fault injector, which can simulate abnormal equipment operating conditions.

[0046] The behavior analysis submodule includes: an operation sequence detector, i.e., an LSTM neural network; and an error detector, i.e., a decision tree classification model.

[0047] The equipment model library is used to build highly realistic 3D factory scenes and simulate the physical movement and interaction of equipment. The process simulation submodule simulates the production process and fault scenarios. The behavior analysis submodule analyzes the operation behavior in real time and detects errors. The scene editing submodule supports custom layout and parameter configuration of the production line. Preferably, the factory simulation module uses Blender / 3ds Max for model building and implements dynamic simulation through the Unity physics engine interface. At the same time, it uses a finite state machine (FSM) to manage the production process.

[0048] The factory simulation module shares a rendering pipeline with the VR display module, receives operation commands from the interactive control module, and provides equipment status data to the AI ​​learning module.

[0049] Specifically, the interactive control module includes: a gesture recognition submodule, a device control interface, and a force feedback submodule; The gesture recognition submodule includes: a Leap Motion controller (accuracy 0.1mm) or a visual gesture recognition algorithm and a gesture semantic mapping table, including 60+ gestures such as grasping, rotating, and clicking.

[0050] The device control interface includes: an OPC UA industrial protocol adapter and a Modbus / TCP communication interface.

[0051] The force feedback submodule includes: a handle vibration feedback unit and a resistance simulation motor; the handle vibration feedback unit supports vibrations of different frequencies, and the resistance simulation motor can be selected as an accessory according to actual needs.

[0052] The gesture recognition submodule is used to recognize natural gestures and map them to device operations. The device control interface is used to provide an industrial protocol interface to connect with real devices. The force feedback submodule generates operational force feedback to enhance realism and achieve precise control of virtual devices.

[0053] Preferably, the interactive control module uses computer vision algorithms (OpenCV) for gesture recognition, manages input devices through Unity's Input System, and uses force feedback API to achieve tactile simulation.

[0054] The handle hardware in the interactive control module is connected via USB / Bluetooth, and the industrial protocol interface communicates via Ethernet, sending control commands to the factory simulation module.

[0055] Specifically, the data storage module includes: a student database, an operation record database, and a knowledge graph database; The student database includes: a competency assessment table and a learning trajectory table; the competency assessment table includes dimensions such as knowledge mastery and operational proficiency, and the learning trajectory table includes task completion records and error type statistics.

[0056] The operation log library includes: time-series operation logs (operation records accurate to the frame level) and device status snapshots (historical curves of key parameters). The knowledge graph database includes: an intelligent manufacturing process knowledge base and a fault diagnosis rule base; the intelligent manufacturing process knowledge base contains 1000+ process nodes, and the fault diagnosis rule base is built based on expert experience.

[0057] The student database is used to store student ability data and learning history; the operation record database is used to record operation details for review and analysis; and the knowledge graph database is used to manage knowledge graphs in the field of intelligent manufacturing, supporting data query and statistical analysis.

[0058] Preferably, the data storage module uses a MySQL relational database to store structured data, uses Neo4j graph database to manage the knowledge graph, and uses ETL tools to achieve data cleaning and integration.

[0059] The data storage module interacts with the AI-guided learning module through an API interface, providing data support for the evaluation system and supporting data querying on the web-based management interface.

[0060] The following technical indicators can be achieved through this embodiment: Scene rendering frame rate: ≥90FPS; Operation delay: ≤50ms; In typical industrial scenarios, the knowledge graph coverage is ≥95%. Error identification accuracy: ≥92%; Student immersion rating: ≥4.5 / 5 (subjective evaluation).

[0061] Application scenarios include: pre-job training for new employees: simulating the operation of high-risk equipment and learning complex processes; practical teaching in colleges and universities: providing a low-cost, repeatable training environment; process optimization verification: testing new production line layout schemes in a virtual environment; and fault handling drills: injecting various equipment faults for emergency response training.

[0062] Example 2 This embodiment provides a method for implementing an AI+VR-based intelligent manufacturing factory simulation teaching system, such as... Figure 2 As shown, it includes: S1. Initialization Phase: The VR display module loads a factory scene; The AI-guided learning module generates an initial learning plan based on the student's profile. The data storage module creates training session records; S2, Interaction Phase: Trainees perform operations in a virtual factory using a VR display module; The interactive control module sends operation commands to the factory simulation module; The factory simulation module receives operation commands, updates equipment status, and provides feedback on physical effects. The AI-guided learning module analyzes the operations and generates feedback in real time. S3, Evaluation Phase: The data storage module records the complete operation sequence; The AI-guided learning module generates evaluation reports based on a decision tree model. The VR display module presents the evaluation results in a visual manner.

[0063] Example 3 This embodiment provides an electronic device, the electronic device comprising: At least one processor; and The memory stores instructions that, when executed by the at least one processor, cause the at least one processor to execute the AI+VR-based intelligent manufacturing factory simulation teaching system as described above.

[0064] In this embodiment, electronic devices include, but are not limited to: personal computers, server computers, workstations, desktop computers, laptop computers, notebook computers, mobile computing devices, smartphones, tablet computers, cellular phones, personal digital assistants (PDAs), handheld devices, messaging devices, wearable computing devices, consumer electronic devices, etc.

[0065] Example 4 This embodiment also provides a computer-readable storage medium storing executable instructions, which, when executed, cause the machine to perform the AI+VR-based intelligent manufacturing factory simulation teaching system as described above.

[0066] Specifically, a system or apparatus equipped with a readable storage medium may be provided, on which software program code implementing the functions of any of the embodiments described above is stored, and the computer or processor of the system or apparatus can read and execute the instructions stored in the readable storage medium.

[0067] In this case, the program code itself, which can be read from the readable medium, can perform the functions of any of the above embodiments, and therefore the computer-readable code and the readable storage medium storing the computer-readable code constitute a part of this specification.

[0068] Examples of readable storage media include floppy disks, hard disks, magneto-optical disks, optical disks (such as CD-ROM, CD-R, CD-RW, DVD-ROM, DVD-RAM, DVD-RW, DVD-RW), magnetic tapes, non-volatile memory cards, and ROMs. Alternatively, program code can be downloaded from a server computer or the cloud via a communication network.

[0069] Those skilled in the art will understand that embodiments of the present invention can be provided as methods, systems, or computer program products. Therefore, the present invention can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the present invention can take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0070] This invention is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the invention. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the flowchart illustrations and / or block diagrams. Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0071] Obviously, the above embodiments of the present invention are merely examples for clearly illustrating the technical solutions of the present invention, and are not intended to limit the specific implementation of the present invention. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of the claims of the present invention should be included within the protection scope of the claims of the present invention.

Claims

1. A smart manufacturing factory simulation teaching system based on AI+VR, characterized in that, The system includes: a VR display module, an AI-guided learning module, a factory simulation module, an interactive control module, and a data storage module. These modules interact and collaborate via standardized interfaces, forming a closed-loop teaching system. The VR display module enables the acquisition and feedback of controller operation signals, completes real-time tracking of user position and posture, provides immersive 3D visual scene rendering, and outputs spatial audio to enhance immersion, displaying evaluation results in a visual manner. The AI-guided learning module recognizes and parses students' voice commands, generates personalized learning tasks and guidance plans, provides multimodal feedback, and generates an evaluation report based on a decision tree model. The factory simulation module constructs a highly realistic 3D factory scene, simulates the physical movement and interaction of equipment, analyzes operational behavior and detects errors in real time, and simulates production processes and fault scenarios. The interactive control module recognizes natural gestures and maps them into operation commands, provides industrial protocol interfaces to connect with real factory equipment, generates operational force feedback to enhance realism, and achieves precise control of virtual equipment. The data storage module stores trainees' ability data and learning history, records operational details for review and analysis, manages knowledge graphs in the field of intelligent manufacturing, and supports data query and statistical analysis.

2. The AI+VR-based intelligent manufacturing factory simulation teaching system according to claim 1, characterized in that, The VR display module includes: a head-mounted display unit, a controller control unit, a positioning and tracking unit, and an audio output unit; The head-mounted display unit communicates with the host via USB 3.0 and HDMI interfaces, providing immersive 3D visual scene rendering and display; The handle control unit connects to the head-mounted display unit via Bluetooth to achieve handle operation signal acquisition and feedback; The positioning and tracking unit synchronizes the clock signal via Wi-Fi to achieve real-time tracking of the user's position and attitude; The audio output unit outputs spatialized audio to enhance immersion.

3. The AI+VR-based intelligent manufacturing factory simulation teaching system according to claim 1, characterized in that, The AI-guided learning module includes: a voice interaction submodule and a feedback generation submodule; The voice interaction submodule recognizes and parses the student's voice commands, and generates personalized learning tasks and guidance plans. The feedback generation submodule provides multimodal feedback, including voice, text, and graphics, based on personalized learning tasks and guidance schemes; The voice interaction submodule includes: an ASR speech recognition unit and an NLP semantic understanding unit; The ASR speech recognition unit uses the Kaldi framework + RNN-CNN model for speech recognition, and the NLP semantic understanding unit uses the BERT pre-trained model + knowledge graph for semantic understanding. The feedback generation submodule includes: a speech synthesis unit and a visual cue generator; The speech synthesis unit uses the Tacotron2 model for speech synthesis, and the visual cue generator uses the Unity particle system to generate visual cues based on the synthesized speech.

4. The AI+VR-based intelligent manufacturing factory simulation teaching system according to claim 1, characterized in that, The factory simulation module includes: an equipment model library, a scene editing submodule, a process simulation submodule, and a behavior analysis submodule; The equipment model library is used to construct highly realistic 3D factory scenes and simulate the physical movement and interaction of equipment. The process simulation submodule simulates the production process and fault scenarios. The behavior analysis submodule analyzes operational behavior and detects errors in real time; The scene editing submodule supports custom layouts and parameter configurations for the production line.

5. The AI+VR-based intelligent manufacturing factory simulation teaching system according to claim 1, characterized in that, The interactive control module includes: a gesture recognition submodule, a device control interface, and a force feedback submodule; The gesture recognition submodule is used to recognize natural gestures and map them to device operations; The device control interface is used to provide an industrial protocol interface for interfacing with real devices; The force feedback submodule generates operational force feedback to enhance realism and enable precise control of virtual devices.

6. The AI+VR-based intelligent manufacturing factory simulation teaching system according to claim 1, characterized in that, The data storage module includes: a student database, an operation record database, and a knowledge graph database; The student database is used to store student ability data and learning history; The operation log library is used to record operation details for review and analysis. The knowledge graph library is used to manage knowledge graphs in the field of intelligent manufacturing and supports data querying and statistical analysis.

7. The AI+VR-based intelligent manufacturing factory simulation teaching system according to claim 4, characterized in that, The equipment model library includes: 1:1 scale 3D equipment models and a physics engine submodule; The 1:1 scale 3D equipment model includes N types of industrial equipment; The component-level detachable structure is achieved through joint constraints; The physics engine submodule is either PhysX 4.2 or Bullet physics engine; The scene editing submodule includes: a production line layout editor and a process parameter configuration panel; the production line layout editor supports drag-and-drop modeling, and the process parameter configuration panel includes the actual required physical parameters. The process simulation submodule includes a production process state machine and a fault injector; the production process state machine is used to support work order flow simulation, and the fault injector can simulate abnormal equipment operating conditions. The behavior analysis submodule includes an operation sequence detector and an error detector; the operation sequence detector uses an LSTM neural network, and the error detector uses a decision tree classification model.

8. A method for implementing an AI+VR-based intelligent manufacturing factory simulation teaching system, characterized in that, include: S1. Initialization Phase: The VR display module loads a factory scene; The AI-guided learning module generates an initial learning plan based on the student's profile. The data storage module creates training session records; S2, Interaction Phase: Trainees perform operations in a virtual factory using a VR display module; The interactive control module sends operation commands to the factory simulation module; The factory simulation module receives operation commands, updates equipment status, and provides feedback on physical effects. The AI-guided learning module analyzes the operations and generates feedback in real time. S3, Evaluation Phase: The data storage module records the complete operation sequence; The AI-guided learning module generates evaluation reports based on a decision tree model. The VR display module presents the evaluation results in a visual manner.

9. An electronic device, characterized in that, The electronic device includes: processor; The memory stores computer execution instructions, which, when executed by the at least one processor, cause the at least one processor to execute the computer execution instructions stored in the memory, thereby implementing an AI+VR-based intelligent manufacturing factory simulation teaching system as described in any one of claims 1-7.

10. A computer-readable storage medium storing a computer program, characterized in that, When the executable instructions are executed by the processor, they are used to implement an AI+VR-based intelligent manufacturing factory simulation teaching system as described in any one of claims 1-7.

Images