An extended reality-based power grid maintenance training system and method

Abstract

The application relates to the technical field of power system operation and maintenance training, and discloses a power grid maintenance training system and method based on extended reality, which comprises a cloud rendering and distribution system: the cloud rendering and distribution system is used for rendering an extended reality scene, generating real-time rendering output, and transmitting the real-time rendering output to a terminal device through an edge computing node and a content distribution network; the cloud rendering and distribution system is connected with a real-time dynamic content updating module and a data processing module, is used for receiving real-time state data and student operation behavior data of the device, and is responsible for embedding the data in a rendering scene. Through the cloud-based XR service, the performance requirement of the terminal device is significantly reduced, the cloud rendering and edge computing are combined with the content distribution network, real-time rendering and transmission of high-quality content are realized, in the case of network fluctuation, low delay and smooth experience can be maintained, the network adaptability of the system is improved, and the hardware cost is reduced.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of power system operation and maintenance training, in particular to a power grid maintenance training system and method based on extended reality. BACKGROUND

[0002] In the power industry, power grid maintenance is a complex and high-risk job. The traditional power grid maintenance training method uses field teaching and textbook training, which has limitations. Field teaching is high in cost and risk, especially in extreme weather or emergency operation training. In addition, textbook or video training cannot provide real operation experience and feedback, so that students cannot master the feel and details in actual operation. At the same time, the update speed of power grid equipment and technology is fast, and the traditional training method cannot update the content in time, resulting in that the knowledge and skills of students lag behind the latest technical state.

[0003] The existing XR training system relies on high-performance terminal devices to ensure rendering quality and smooth operation, resulting in high hardware cost. In addition, the real-time nature of XR content requires high network requirements, and network fluctuations can easily cause increased delay or screen freezing, affecting student experience.

[0004] In the traditional XR training system, the virtual device state and task setting are mostly preset static content, which cannot reflect the state change of the actual power grid equipment in time, and lacks real-time update. Students cannot obtain training content synchronized with the real power grid state, resulting in disconnection between training content and actual work, and reducing the authenticity of training effect.

[0005] The existing XR training system provides the same training path and task setting for students, which cannot dynamically adjust according to the actual operation level and learning progress of students, resulting in individualization, reduction, and then affecting learning effect.

[0006] The existing XR training system lacks precise physical simulation in terms of touch and force feedback, so that students cannot obtain similar touch feeling to real power grid equipment in the operation process. At the same time, complex environmental factors such as temperature, humidity, wind force cannot be simulated, and students lack training in complex environment, reducing the practicality and immersion of training.

[0007] Therefore, the present application provides a power grid maintenance training system and method based on extended reality to solve the above problems. SUMMARY

[0008] In view of the deficiencies of the prior art, the present application provides a power grid maintenance training system and method based on extended reality to solve the problems raised in the background.

[0009] To achieve the above object, the present application is realized by the following technical solutions: A power grid maintenance training system based on extended reality, comprising:

[0010] A cloud rendering and distribution system is used for rendering an extended reality scene, generating real-time rendering output, and transmitting to a terminal device through an edge computing node and a content distribution network, the cloud rendering and distribution system is connected with a real-time dynamic content updating module and a data processing module, used for receiving real-time state data and student operation behavior data of the device, and responsible for embedding the data in the rendering scene, so as to update the virtual device state and student interaction in the extended reality scene in real time, and ensure that the scene seen by the student on the terminal device reflects the actual state in real time and accurately;

[0011] A data processing module is used for collecting data of sensors in the Internet of Things of power grid equipment, cleaning, converting and filtering the data, and generating a real-time state data set of the power grid equipment, in addition, the data processing module receives and processes the operation behavior data of the student, and provides input data for an AI-driven intelligent evaluation and personalized learning path module;

[0012] A real-time dynamic content updating module includes a digital twin technology module, used for mapping the real-time state data set of the power grid equipment generated by the data processing module to the virtual device model in the extended reality scene, and updating the training tasks and fault cases through a content management system, the real-time dynamic content updating module is connected with the cloud rendering and distribution system, used for receiving real-time data of the device and embedding it in the extended reality scene, so as to realize real-time updating of the device state in the virtual scene, in addition, the real-time dynamic content updating module ensures the synchronous transmission of student operation and environment data, so that the content of the scene is consistent with the actual situation;

[0013] An AI-driven intelligent evaluation and personalized learning path module analyzes the operation behavior data and operation accuracy of the student, generates a personalized learning path, and adjusts the task difficulty, the AI-driven intelligent evaluation and personalized learning path module obtains the behavior data in the data processing module in real time, and recommends corresponding personalized training tasks through a task management module;

[0014] A task management module is responsible for creating, distributing and adjusting the difficulty of training tasks, connected with the real-time dynamic content updating module and the AI-driven intelligent evaluation and personalized learning path module, generates adaptive tasks according to the state of the power grid equipment and the performance of the student and transmits them to the student terminal device;

[0015] A virtual reality and physical simulation fusion module simulates the weight, friction and operation resistance of the device through a force feedback device and a physical engine, the virtual reality and physical simulation fusion module is connected with the cloud rendering and distribution system, used for receiving real-time rendering content and providing simulation data of the force feedback device.

[0016] Preferably, the cloud rendering and distribution system comprises:

[0017] a rendering server, responsible for generating each frame of the extended reality scene, and encoding the rendering output, the rendering server sends the encoded rendering output to the content distribution network for caching and distribution;

[0018] a content distribution network, used for caching and distributing rendering content, the content distribution network receives encoded rendering content from the rendering server, caches it to quickly respond to terminal requests, and at the same time, the content distribution network is connected with the edge computing node to push the rendering content to the edge node close to the user to optimize the transmission delay;

[0019] an edge computing node, deployed close to the student terminal, used for processing low-delay tasks, the edge computing node obtains the rendering content of the content distribution network, and performs additional processing if necessary to ensure low-delay transmission, and finally transmits the rendering content to the student terminal.

[0020] Preferably, the data processing module comprises:

[0021] a data cleaning unit, which performs preliminary processing on the data collected by the sensor, filters outliers and fills in missing data, and provides reliable data input for subsequent data standardization processing;

[0022] a data conversion unit, which receives the data processed by the data cleaning unit, standardizes it into a unified format, ensures the consistency and comparability of the data, and provides the data integration unit with formatted data input;

[0023] a data integration unit, which receives standardized data from the data conversion unit, integrates data from different sensors into a unified power grid equipment state data set, and provides complete equipment state information for real-time updating of the extended reality scene.

[0024] Preferably, the content management system of the real-time dynamic content updating module comprises:

[0025] a training task database, used for storing preset fault cases and operation tasks;

[0026] a dynamic task updating unit, used for automatically generating corresponding training tasks according to the real-time state of the power grid equipment;

[0027] The real-time dynamic content updating module realizes real-time state mapping through a digital twin technology module.

[0028] Preferably, the AI-driven intelligent evaluation and personalized learning path module comprises:

[0029] a behavior analysis unit configured to calculate a behavior score S based on a sequence of operation behaviors of the trainee a real-time calculation of the behavior score S:

[0030] ,

[0031] wherein, is an evaluation value of a single operation, is the behavior score, and n is the total number of operations, is a specific operation performed by the trainee at the i-th step in the task;

[0032] when the operation meets the standard, = 1, and when it does not meet the standard = 0;

[0033] the behavior analysis unit transmits the calculated behavior score S to the personalized learning path generation unit for dynamic generation of a subsequent learning path;

[0034] a personalized learning path generation unit configured to generate a learning path based on the operation accuracy and the behavior score of the trainee : ,

[0035] wherein, is a path recommendation function, is a personalized learning path, is the behavior score;

[0036] the personalized learning path generation unit recommends a training task for the trainee based on the calculated behavior score S, and transmits the personalized learning path to a task management module so as to push the recommended task to the trainee terminal.

[0037] Preferably, the task management module comprises:

[0038] a task generation unit configured to generate a basic training task based on real-time state data of the power grid equipment and pre-set fault cases in the system;

[0039] a task difficulty adjustment unit configured to dynamically adjust a difficulty coefficient of the task based on the behavior score of the trainee and the learning path recommended by the task generation unit;

[0040] a task assignment unit configured to assign the task to the trainee terminal based on the personalized learning path and the adjusted task difficulty;

[0041] a task feedback and recording unit configured to collect feedback and performance data of the trainee during the execution of the task, and return the data to the AI-driven intelligent evaluation and personalized learning path module for further adjustment of the personalized learning path. ​​​

[0042] Preferably, the task generation unit generates tasks based on the device status data received by the real-time dynamic content update module. At that time, based on the equipment's real-time status data set D and fault case parameters Task creation content:

[0043] ,

[0044] in, For the generated task, Generate functions for the task. This is a collection of real-time status data for the device. The default fault case parameters for the system;

[0045] The task difficulty adjustment unit calculates the final difficulty of the task based on the student's behavioral score S. :

[0046] ,

[0047] in, This represents the base difficulty of the task. To adjust the coefficient, Rate the trainees' behavior;

[0048] If S decreases, the task difficulty d will automatically decrease, making the task more suitable for the current student's level.

[0049] If S increases, the task difficulty d increases to increase the challenge.

[0050] Preferably, the virtual reality and physics simulation fusion module includes:

[0051] Force feedback unit is used to simulate the real force and resistance feedback experienced by trainees during operation, so that the power grid equipment in virtual operation has real mechanical characteristics;

[0052] The tactile feedback unit is used to provide tactile feedback, allowing trainees to experience the surface characteristics and vibration feedback of the power grid equipment during virtual operation;

[0053] A high-precision physics engine unit is used to simulate the physical characteristics of power grid equipment, enabling the equipment in the virtual environment to exhibit realistic physical behavior.

[0054] The environmental condition simulation unit is used to simulate different environmental conditions, enabling trainees to operate power grid equipment in various scenarios.

[0055] Preferably, the force feedback unit simulates the feedback of resistance, tension, and thrust during operation through a force feedback glove or controller, based on the intensity of the operation. Adjusting feedback force , force feedback relationship formula:

[0056] ,

[0057] wherein, is the feedback force, is the feedback force coefficient, is the operation strength;

[0058] The high-precision physical engine unit makes the virtual device have real physical feedback when operating based on the friction, reaction force and gravity of the physical engine calculation device. In the simulation cable connection process, the friction of the device The calculation formula is:

[0059] ,

[0060] wherein, is the friction coefficient, is the weight of the device.

[0061] A power grid maintenance training method based on extended reality, comprising the following steps:

[0062] Step 1, the cloud rendering and distribution system generates a high-quality rendering output of the power grid maintenance scene, and transmits the content to the terminal device of the student through the edge computing node and the content distribution network. In this process, the real-time dynamic content update module embeds the real-time data of the device into the extended reality scene, providing a real simulation environment for the student;

[0063] Step 2, the data processing module collects data in the Internet of Things sensor of the power grid device, cleans, converts and integrates, and generates a real-time state data set of the device;

[0064] Step 3, through the real-time dynamic content update module, the system uses digital twin technology to map the real-time state of the power grid device to the virtual device model. At the same time, the content management system calls the fault cases and operation tasks in the preset database, or generates corresponding training tasks according to the state of the device;

[0065] Step 4, the AI-driven intelligent evaluation and personalized learning path module analyzes the operation behavior and operation precision of the student, and generates a personalized learning path for the student. According to the performance of the student, the difficulty of the task is dynamically adjusted, and adaptive tasks are recommended;

[0066] Step 5, the task management module creates, distributes and adjusts tasks according to the personalized learning path of the student, dynamically generates adaptive tasks according to the real-time state of the device and the performance of the student, and pushes the tasks to the terminal device of the student;

[0067] Step 6, during the training process, the virtual reality and physical simulation fusion module provides real tactile feedback to the trainee through force feedback devices and a physics engine, at the same time, the haptic feedback and environmental condition simulation enable the trainee to experience the operation of power grid equipment in various situations;

[0068] Step 7, during the task execution process, the task management module collects the feedback and operation data of the trainee, and transmits the data to the AI-driven intelligent evaluation module, and based on the real-time operation performance of the trainee, the system dynamically adjusts the learning path and task difficulty;

[0069] Step 8, the virtual reality and physical simulation fusion module provides force feedback according to the operation strength of the trainee during the operation of the trainee, so that the virtual operation has real physical feedback;

[0070] Step 9, according to the behavior score and feedback of the trainee, the system continuously optimizes the personalized learning path and task difficulty, so that the trainee gradually adapts to more challenging tasks, and realizes the goal of personalized training.

[0071] The present application provides a kind of power grid maintenance training system and method based on extended reality.There are the following beneficial effects:

[0072] 1, the present application significantly reduces the performance requirements of terminal device by cloud-based XR service, uses cloud rendering and edge computing in combination with content distribution network, realizes the real-time rendering and transmission of high-quality content, in the case of network fluctuation, can maintain low delay and smooth experience, and improves the network adaptability of system, reduces hardware cost.

[0073] 2, the present application realizes the real-time synchronization of the state of power grid equipment in virtual environment by the real-time data of power grid equipment collected by Internet of Things device, in combination with data processing and digital twin technology, dynamically updates training task and fault case, ensures that the training content of trainee is consistent with actual equipment state, greatly improves the real-time and authenticity of training, so that trainee can access the latest power grid operation status and fault situation in virtual environment.

[0074] 3, the AI-driven module in the present application calculates behavior score by real-time analysis of the operation behavior of trainee, and generates personalized learning path and dynamically adjusts task difficulty according to the performance of trainee, so that the training content of trainee is adapted to its current skill level, realizes targeted training, improves learning efficiency, and ensures that trainee continuously improves under appropriate challenge level.

[0075] 4、The application reproduces the real physical properties and operating tactile feeling of power grid equipment through high-precision physical engines, force feedback and tactile feedback devices, so that the trainees obtain force, friction and vibration feedback similar to actual operation in the virtual environment, and the operation training under various complex situations is provided through environment condition simulation, thereby effectively improving the operation stability and the ability to cope with complex environment of the trainees, and enhancing the practicality and immersion of the training. BRIEF DESCRIPTION OF DRAWINGS

[0076] Figure 1 is a system framework diagram of the application;

[0077] Figure 2 is a flowchart of the application;

[0078] Figure 3 is a step schematic diagram of real-time state mapping realized by the real-time dynamic content updating module of the application through the digital twin technology module. DETAILED DESCRIPTION

[0079] In order for those skilled in the art to understand the application scheme, the technical solutions in the embodiments of the application will be described clearly and completely below in conjunction with the drawings in the embodiments of the application. Obviously, the described embodiments are part of the embodiments of the application, rather than all the embodiments. Based on the embodiments in the application, other embodiments obtained by those skilled in the art without creative labor should be within the scope of the application.

[0080] The application will be described in detail below in conjunction with the drawings:

[0081] Embodiment:

[0082] Please refer to the accompanying Figure 1 -Appendix Figure 3 The embodiment of the application provides an extended reality-based power grid maintenance training system, which comprises:

[0083] The cloud rendering and distribution system is used for rendering the extended reality scene, generating real-time rendering output, and transmitting the real-time rendering output to the terminal device through the edge computing node and the content distribution network. The cloud rendering and distribution system is connected with the real-time dynamic content updating module and the data processing module, is used for receiving the real-time state data of the device and the operation behavior data of the trainee, and is responsible for embedding the data in the rendering scene, so as to update the virtual device state in the extended reality scene and the trainee interaction in real time, and ensure that the scene seen by the trainee on the terminal device reflects the actual state in real time and accurately.

[0084] Data processing module: used for collecting data from sensors in the Internet of Things of power grid equipment, cleaning, converting and filtering the data, generating real-time state data set of power grid equipment, in addition, the data processing module receives and processes the operation behavior data of the trainees, providing input data for the AI-driven intelligent evaluation and personalized learning path module;

[0085] Real-time dynamic content update module: contains a digital twin technology module for mapping the real-time state data set of power grid equipment generated by the data processing module to the virtual equipment model in the extended reality scene, and updating the training tasks and fault cases through the content management system, the real-time dynamic content update module is connected with the cloud rendering and distribution system for receiving real-time data of the equipment and embedding them in the extended reality scene to realize real-time update of the equipment state in the virtual scene, in addition, the real-time dynamic content update module ensures the synchronous transmission of the trainee's operation and environment data, so that the content of the scene remains consistent with the actual situation;

[0086] AI-driven intelligent evaluation and personalized learning path module: analyzes the operation behavior data and operation accuracy of the trainees, generates a personalized learning path, and adjusts the task difficulty, the AI-driven intelligent evaluation and personalized learning path module obtains the behavior data in the data processing module in real time, and recommends corresponding personalized training tasks through the task management module;

[0087] Task management module: responsible for managing the creation, distribution and difficulty adjustment of training tasks, connected with the real-time dynamic content update module and the AI-driven intelligent evaluation and personalized learning path module, generating adaptive tasks according to the state of power grid equipment and the performance of trainees and transmitting them to the trainee terminal equipment;

[0088] Virtual reality and physical simulation fusion module: simulates the weight, friction and operation resistance of the equipment through force feedback devices and physical engines, the virtual reality and physical simulation fusion module is connected with the cloud rendering and distribution system for receiving real-time rendering content and providing simulation data of force feedback devices.

[0089] The benefits of cloud rendering and distribution system reduce hardware cost and equipment maintenance complexity, ensure low latency of content transmission, improve network adaptability and user experience of the system, improve the real-time and practicality of training;

[0090] The benefits of data processing module ensure the accuracy and consistency of data, avoid misleading caused by noise or outliers, provide high-quality input data for subsequent real-time dynamic content update and AI intelligent evaluation, improve the overall performance of the system, provide basic support for real-time content update and personalized learning path generation, and ensure the real-time response of the system;

[0091] The benefits of the real-time dynamic content updating module enhance the authenticity of training, ensure that learners face the latest equipment status and scenarios, improve the relevance and effectiveness of learning, and enhance the practicality and emergency response capability of training.

[0092] The benefits of the AI-driven intelligent assessment and personalized learning path module enable learners to gradually improve their skills in the most suitable way, improve learning efficiency, avoid the impact of task difficulty or ease on learning effectiveness, and ensure the relevance and effectiveness of training.

[0093] The benefits of the task management module can generate adaptive tasks based on the status of power grid equipment and the operation performance of learners, ensure that the training content of learners meets their current ability and needs, reduce the need for manual intervention, ensure that learners continuously progress on the appropriate learning curve, and improve training effectiveness.

[0094] The benefits of the virtual reality and physical simulation fusion module enable learners to obtain a similar tactile experience to actual operation in a virtual environment, improve the realism and immersion of operation, and help apply skills learned in virtual training to actual work, improving the practicality of training.

[0095] The cloud rendering and distribution system includes:

[0096] The rendering server is responsible for generating each frame of the extended reality scene and encoding the rendering output, and the rendering server sends the encoded rendering output to the content distribution network for caching and distribution.

[0097] The content distribution network is used for caching and distributing rendering content, and the content distribution network receives encoded rendering content from the rendering server, caches it to quickly respond to terminal requests, and at the same time, the content distribution network is connected with the edge computing node to push the rendering content to the edge node close to the user to optimize transmission delay.

[0098] The edge computing node is deployed near the learner's terminal and is used to handle low-latency tasks. The edge computing node obtains the rendering content from the content distribution network and performs additional processing if necessary to ensure low-latency transmission, and finally transmits the rendering content to the learner's terminal.

[0099] The benefits of the rendering server reduce the performance requirements of the terminal device, ensure the visual quality and rendering efficiency of XR content, and enable learners to obtain high-quality immersive experience on low-performance devices.

[0100] The benefits of the content distribution network reduce the dependence on long-distance data transmission, effectively reduce transmission delay, enable learners in different regions to obtain fast access speed, reduce the bandwidth pressure of the rendering server, and improve the overall stability and user experience of the system.

[0101] The edge computing node reduces the network transmission time from the cloud to the terminal and the total rendering delay, so that the students can obtain a smooth and instant interactive experience, and the network adaptability of the system is improved, and the experience of the students is not limited by the network environment.

[0102] The data processing module comprises:

[0103] The data cleaning unit performs preliminary processing on the data collected by the sensor, filters abnormal values and fills in missing data, and provides reliable data input for subsequent data standardization processing;

[0104] The data conversion unit receives the data processed by the data cleaning unit, standardizes it into a unified format, ensures the consistency and comparability of the data, and provides the data integration unit with formatted data input;

[0105] The data integration unit receives the standardized data from the data conversion unit, integrates the data of different sensors into a unified power grid equipment state data set, and provides complete equipment state information for real-time updating of the extended reality scene.

[0106] The data cleaning unit removes error data caused by sensor failure or noise interference, ensures the accuracy and reliability of the data set, avoids misleading training content caused by inaccurate data, avoids interruption or display abnormalities of the equipment state in the XR scene caused by data loss, and ensures a smooth operation experience and complete training information for the students;

[0107] The data conversion unit enables the subsequent processing module to perform consistent operations on the data, eliminates data compatibility problems caused by inconsistent data formats, and provides more diverse data support for XR training content;

[0108] The data integration unit enables the system to accurately simulate the operation of the equipment in the XR scene, ensures that each module of the system obtains accurate equipment state information, and improves the reliability and real-time performance of the training.

[0109] The content management system of the real-time dynamic content updating module comprises:

[0110] The training task database is used to store pre-set fault cases and operation tasks;

[0111] The dynamic task updating unit is used to automatically generate corresponding training tasks according to the real-time state of the power grid equipment;

[0112] The real-time dynamic content updating module realizes real-time state mapping through the digital twin technology module.

[0113] The real-time dynamic content updating module of the application ensures real-time updating of device state and dynamic generation of task content in the XR training environment through the combination of the content management system and the digital twin technology module. The training task database and the dynamic task updating unit in the content management system realize rich task reserves and real-time task generation, making the training content more comprehensive and flexible. The digital twin technology module maps the actual device state to the virtual device model through the state mapping step and dynamically displays it in the XR scene, providing real device state feedback to the trainees and enhancing the real-time, authenticity and practicality of the training, so that the trainees can obtain similar experience and skill improvement in the virtual environment as in real operation.

[0114] The AI-driven intelligent evaluation and personalized learning path module includes:

[0115] a behavior analysis unit for calculating a behavior score S according to the operation behavior sequence of the trainee in real time:

[0116] ,

[0117] wherein, is the evaluation value of a single operation, is the behavior score, and n is the total number of operations, is the specific operation of the i-th step performed by the trainee in the task;

[0118] when the operation meets the standard, =1, and when it does not meet the standard, =0;

[0119] The behavior analysis unit transmits the calculated behavior score S to the personalized learning path generation unit for dynamic generation of the subsequent learning path.

[0120] The personalized learning path generation unit generates a learning path P according to the operation accuracy and the behavior score of the trainee : ,

[0121] wherein, is the path recommendation function, is the personalized learning path, is the behavior score;

[0122] The personalized learning path generation unit recommends the training task of the trainee according to the calculated behavior score S, and transmits the personalized learning path P to the task management module, so as to push the recommended task to the trainee terminal.

[0123] The real-time feedback mechanism of the behavior analysis unit helps the trainee to correct errors in time and enhances the effectiveness of learning.​​​

[0124] According to the actual performance of the students, personalized learning paths and task recommendations are generated, so that students can train at a suitable challenge level, avoiding the "one-size-fits-all" training method, and greatly improving learning efficiency;

[0125] The system can adjust the task difficulty in real time according to the learning progress and operation performance of the students, ensure that the learning path of the students meets their current operation level, and help the students to steadily progress;

[0126] Quantitative behavior scores and dynamic recommendation paths enable the system to make personalized recommendations based on data, ensuring that the training content received by the students meets their actual level and improving the effectiveness and relevance of training.

[0127] The task management module includes:

[0128] The task generation unit generates basic training tasks according to real-time state data of power grid equipment and pre-set fault cases in the system;

[0129] The task difficulty adjustment unit dynamically adjusts the difficulty coefficient of the task according to the behavior score of the student and the learning path recommended by the task generation unit;

[0130] The task assignment unit assigns tasks to the student terminal according to the personalized learning path and the adjusted task difficulty;

[0131] The task feedback and recording unit is used to collect feedback and performance data of the students during task execution, and returns the data to the AI-driven intelligent assessment and personalized learning path module for further adjustment of the personalized learning path.

[0132] The units of the task management module form an intelligent and automated task management process through task generation, difficulty adjustment, task assignment, and feedback recording, ensuring that the training content of the power grid maintenance training system can be adjusted in real time according to the student's level and equipment state:

[0133] The task management module realizes the automatic generation, assignment, and adjustment of tasks, reduces manual intervention, improves the operating efficiency of the system, and makes the training more smooth and efficient;

[0134] According to the operation level and personalized learning path of the students, the task management module can dynamically adjust the task difficulty and content, so that the training tasks of each student match their actual level, improving the personalization and relevance of training;

[0135] By collecting operation feedback and performance data of the students, the system can further optimize the personalized learning path, achieve more accurate task recommendations, and enhance the gradual progress and learning efficiency of the students in the training process;

[0136] The task generation unit dynamically provides adaptive tasks based on actual power grid equipment states and preset fault cases, helps trainees continuously practice in real situations, and improves their actual operation skills and emergency handling capabilities.

[0137] In summary, the task management module provides efficient and intelligent task management functions for the power grid maintenance training system through its multi-level task management process, makes the training more targeted and adaptive, and ensures that trainees can continuously improve their operation level in a dynamically adjusted task environment.

[0138] The task generation unit generates tasks based on the equipment state data received by the real-time dynamic content update module At this time, the real-time state data set D of the equipment and the fault case parameters Create task content:

[0139] ,

[0140] Among them, The generated task, Task generation function, Real-time state data set of equipment, System preset fault case parameters;

[0141] The task difficulty adjustment unit calculates the final difficulty of the task based on the behavior score S of the trainee :

[0142] ,

[0143] Among them, The base difficulty of the task, Adjustment coefficient, Behavior score of trainee;

[0144] If S decreases, the task difficulty d automatically decreases, making the task more suitable for the current trainee level;

[0145] If S increases, the task difficulty d increases to increase the challenge.

[0146] The task generation unit and the task difficulty adjustment unit in the application realize automatic generation and difficulty adjustment of tasks through dynamic analysis of real-time equipment state data and trainee behavior scores:

[0147] The task generation unit dynamically generates tasks according to equipment states and fault cases, making the task content more in line with actual needs, enhancing the emergency handling capabilities of trainees and the practicality of training;

[0148] The task difficulty adjustment unit dynamically adjusts the task difficulty based on the performance of the trainee, ensuring that the task difficulty is always appropriate for the trainee's level, allowing the trainee to continuously progress at an appropriate difficulty level, improving learning effectiveness and training efficiency;

[0149] The dynamically adjusted task difficulty ensures that skilled trainees can undertake more challenging tasks, avoiding the repetition of simple tasks, allowing trainees to continuously progress in moderate challenges and strengthen their operational skills;

[0150] The task generation and difficulty adjustment unit enables automatic generation and dynamic adjustment of tasks, reducing the complexity of manual operations, significantly improving the automation level and operational efficiency of the system, and allowing trainees to have an efficient and personalized training experience.

[0151] The virtual reality and physical simulation fusion module includes:

[0152] The force feedback unit simulates the real force and resistance feedback experienced by the trainee during operation, allowing the power grid equipment in the virtual operation to have realistic mechanical properties;

[0153] The haptic feedback unit provides haptic feedback, allowing trainees to receive surface characteristics and vibration feedback from power grid equipment during virtual operation;

[0154] The high-precision physical engine unit simulates the physical properties of power grid equipment, allowing devices in the virtual environment to exhibit realistic physical behavior;

[0155] The environmental condition simulation unit simulates different environmental conditions, allowing trainees to operate power grid equipment in various scenarios.

[0156] The virtual reality and physical simulation fusion module provides a realistic operation experience for trainees through the coordinated action of force feedback, haptic feedback, high-precision physical engine, and environmental condition simulation, making the training effect more significant:

[0157] The feedback and haptic feedback simulate the physical touch and texture of real equipment, allowing trainees to experience the reality of operating equipment and improving the immersion of learning;

[0158] The high-precision physical engine ensures that trainees acquire realistic skills during training, which helps to apply learning outcomes to real operating environments;

[0159] The environmental condition simulation unit allows trainees to operate and train in complex environments, enhancing their operational stability and emergency response capabilities in extreme or adverse conditions, ensuring that trainees can adapt to various working environments;

[0160] The physical engine provides precise physical parameters for force feedback and haptic feedback, ensuring that the operation feedback matches the actual physical characteristics of the device, improving the operation accuracy and skill mastery of the trainees.

[0161] Through the above improvements, the virtual reality and physical simulation fusion module provides high-quality operation experience for the power grid maintenance training system, enabling trainees to accumulate real operation skills in a virtual environment and meet the demand for high-standard skill training in the power industry.

[0162] The force feedback unit simulates the feedback of resistance, pulling force and pushing force during operation through force feedback gloves or controllers, and adjusts the feedback force according to the operation intensity Adjust the feedback force The force feedback relationship formula is:

[0163] ,

[0164] Wherein, is the feedback force, is the feedback force coefficient, is the operation intensity;

[0165] The high-precision physical engine unit calculates the friction, reaction force and gravity of the device based on the physical engine, so that the virtual device has real physical feedback during operation. During the simulation of the cable connection process, the friction of the device The calculation formula is:

[0166] ,

[0167] Wherein, is the friction coefficient, is the weight of the device.

[0168] The combination of the force feedback unit and the high-precision physical engine unit provides highly immersive operation feedback for the power grid maintenance training system:

[0169] Through force feedback and high-precision physical engine, trainees can experience real operation force, friction and reaction force in a virtual environment, increasing the sense of immersion in learning;

[0170] The feedback force simulation of the force feedback unit and the friction calculation of the physical engine help trainees better master operation skills in a virtual environment and ensure that learning outcomes can be applied to actual work;

[0171] By simulating physical properties such as friction and gravity through the physical engine, trainees can understand the mechanical properties of the device during operation, which helps trainees handle various operation situations flexibly in reality and improves their practical operation level;

[0172] The physical parameters provided by the physical engine make the force feedback highly consistent with the actual physical characteristics of the device, ensuring the accuracy and stability of the feedback force, further improving the precision of the operation and the learner's control over the operation process.

[0173] An extended reality-based power grid maintenance training method, comprising the following steps:

[0174] Step 1, the cloud rendering and distribution system generates a high-quality rendering output of the power grid maintenance scene, and transmits the content to the learner's terminal device through the edge computing node and the content distribution network, in the process, the real-time dynamic content update module embeds the real-time data of the device into the extended reality scene, providing a real simulation environment for the learner;

[0175] Step 2, the data processing module collects data from the Internet of Things sensors of the power grid equipment, cleans, transforms and integrates the data to generate a real-time state data set of the equipment;

[0176] Step 3, through the real-time dynamic content update module, the system uses digital twin technology to map the real-time state of the power grid equipment to the virtual equipment model, at the same time, the content management system calls the fault cases and operation tasks in the preset database, or generates corresponding training tasks according to the state of the equipment;

[0177] Step 4, the AI-driven intelligent evaluation and personalized learning path module analyzes the learner's operation behavior and operation precision to evaluate the learner in real time, generates a personalized learning path, and dynamically adjusts the difficulty of the task according to the learner's performance, and recommends adaptive tasks;

[0178] Step 5, the task management module creates, distributes and adjusts tasks according to the learner's personalized learning path, dynamically generates adaptive tasks based on the real-time state of the equipment and the learner's performance, and pushes the tasks to the learner's terminal device;

[0179] Step 6, during the training process, the virtual reality and physical simulation fusion module provides real tactile feedback to the learner through force feedback devices and physical engines, and the haptic feedback and environmental condition simulation enable the learner to experience the operation of the power grid equipment in various situations;

[0180] Step 7, during the task execution process, the task management module collects the learner's feedback and operation data, and transmits the data to the AI-driven intelligent evaluation module, and based on the learner's real-time operation performance, the system dynamically adjusts the learning path and task difficulty;

[0181] Step 8, the virtual reality and physical simulation fusion module provides force feedback according to the learner's operation intensity during the learner's operation process, making the virtual operation have real physical feedback;

[0182] Step 9, according to the behavior score and feedback of the students, the system continuously optimizes the personalized learning path and task difficulty, so that the students gradually adapt to more challenging tasks, and achieve the goal of personalized training.

[0183] While embodiments of the application have been shown and described, it is to be understood that the embodiments described are merely divergences of the principles and specific embodiments of the application and that numerous modifications, changes, substitutions, and alterations can be made thereto without departing from the spirit and scope of the application as defined by the appended claims and their equivalents.

Claims

1. An extended reality based power grid maintenance training system, characterized by, Comprise: Cloud rendering and distribution system: for rendering an extended reality scene, generating real-time rendering output, and transmitting to terminal equipment through edge computing node and content distribution network, the cloud rendering and distribution system is connected with real-time dynamic content update module and data processing module, for receiving real-time state data of equipment and student operation behavior data, and embedding data into rendering scene to update virtual equipment state and student interaction in extended reality scene in real time; Data processing module: for collecting data of sensors in power grid equipment Internet of Things, cleaning, converting and filtering data, generating real-time state data set of power grid equipment, the data processing module receives and processes operation behavior data of students, and provides input data for AI-driven intelligent evaluation and personalized learning path module; Real-time dynamic content update module: including digital twin technology module, for mapping real-time state data set of power grid equipment generated by data processing module to virtual equipment model in extended reality scene, and updating training tasks and fault cases through content management system, the real-time dynamic content update module is connected with cloud rendering and distribution system, for receiving real-time data of equipment and embedding it into extended reality scene to realize real-time update of equipment state in virtual scene, the real-time dynamic content update module ensures synchronous transmission of student operation and environment data, so that the content of the scene is consistent with the actual situation; AI-driven intelligent evaluation and personalized learning path module: according to the operation behavior data and operation precision of students, a personalized learning path is generated, and the difficulty of the task is adjusted, the AI-driven intelligent evaluation and personalized learning path module obtains the operation behavior data in the data processing module in real time, and recommends corresponding personalized training tasks through the task management module; Task management module: responsible for creating, distributing and adjusting the difficulty of training tasks, connected with real-time dynamic content update module and AI-driven intelligent evaluation and personalized learning path module, generating adaptive tasks according to power grid equipment state and student performance and transmitting them to student terminal equipment; Specifically: the device state data received by the real-time dynamic content update module generates a task When the device is in a fault state, the real-time state data set D of the device and the fault case parameters Create task content: ， wherein, a generated task, a task generation function, a real-time state data set of the device, a fault case parameter preset by the system; calculating a final difficulty of the task based on the behavior score S of the student : ， wherein, is the base difficulty of the task, is the adjustment coefficient, is the behavior score of the student; If S decreases, the task difficulty d automatically decreases, so that the task is more suitable for the current student level; If S increases, the task difficulty d increases to increase the challenge; Virtual reality and physical simulation fusion module: simulating the weight, friction and operation resistance of the equipment through force feedback device and physical engine, the virtual reality and physical simulation fusion module is connected with cloud rendering and distribution system, for receiving real-time rendering content and providing simulation data of force feedback device.

2. The extended reality-based power grid maintenance training system of claim 1, wherein, The cloud rendering and distribution system comprises: Rendering server: responsible for generating each frame of rendering output of extended reality scene, and video encoding the rendering output, the rendering server sends the encoded rendering output to the content distribution network for caching and distribution; Content distribution network: for caching and distributing rendering content, the content distribution network receives encoded rendering content from the rendering server, caches it to quickly respond to terminal requests, at the same time, the content distribution network is connected with edge computing node, and pushes the rendering content to the edge computing node close to the user to optimize transmission delay; Edge computing node: deployed near the learner terminal, used for processing low-latency tasks, the edge computing node obtains the rendered content of the content distribution network to ensure low-latency transmission, and finally transmits the rendered content to the learner terminal.

3. The power grid maintenance training system based on extended reality of claim 1, wherein, The data processing module comprises: A data cleaning unit performs preliminary processing on the data collected by the sensor, filters outliers, and fills in missing data, providing reliable data input for subsequent data standardization processing; A data conversion unit receives the data processed by the data cleaning unit, standardizes it into a unified format, and ensures data consistency and comparability, and the output of the data conversion unit provides formatted data input for the data integration unit; A data integration unit receives standardized data from the data conversion unit, integrates data from different sensors into a unified power grid equipment state data set, and provides complete equipment state information for real-time updating of the extended reality scene.

4. The extended reality-based power grid maintenance training system of claim 1, wherein, The content management system of the real-time dynamic content updating module comprises: A training task database for storing pre-set fault cases and operation tasks; A dynamic task updating unit for automatically generating corresponding training tasks according to the real-time state of the power grid equipment; The real-time state mapping is realized by the digital twin technology module of the real-time dynamic content updating module.

5. The extended reality-based power grid maintenance training system of claim 1, wherein, The AI-driven intelligent evaluation and personalized learning path module comprises: a behavior analysis unit configured to determine a behavior score S based on a sequence of actions performed by the student the behavior score S is calculated in real time ， wherein, is the evaluation value for a single operation, is the behavior score, n is the total number of operations, is the specific operation performed by the student in the i-th step of the task; = 1, when the operation is in accordance with the standard = 0; when the operation is not in accordance with the standard = 0; when the operation is not in accordance The behavior analysis unit will calculate the behavior score passed to the personalized learning path generation unit for the dynamic generation of subsequent learning paths; A personalized learning path generating unit generates a learning path according to the operation accuracy and the behavior score of the student : , wherein, is a path recommendation function, is a personalized learning path, is a behavior score; The personalized learning path generation unit generates a personalized learning path for the trainee based on the calculated behavior score The training tasks are recommended to the trainee, and the personalized learning path is passed to the task management module in order to push the recommended tasks to the trainee terminal.

6. The extended reality-based power grid maintenance training system of claim 1, wherein, The task management module comprises: A task generation unit generates basic training tasks according to the real-time state data of the power grid equipment and pre-set fault cases in the system; A task difficulty adjustment unit dynamically adjusts the difficulty coefficient of the task according to the behavior score of the learner and the learning path recommended by the task generation unit; A task assignment unit assigns tasks to learner terminals according to the personalized learning path and the adjusted task difficulty; A task feedback and recording unit is used to collect feedback and performance data of learners during task execution, and return the data to the AI-driven intelligent evaluation and personalized learning path module for further adjustment of the personalized learning path.

7. The power grid maintenance training system based on extended reality of claim 6, wherein, The virtual reality and physical simulation fusion module comprises: A force feedback unit for simulating the real force and resistance feedback received by the learner during operation, so that the power grid equipment in the virtual operation has real mechanical properties; A tactile feedback unit for providing tactile feedback, so that the learner can receive surface characteristics and vibration feedback from the power grid equipment in the virtual operation; A high-precision physical engine unit for simulating the physical properties of the power grid equipment, so that the equipment in the virtual environment exhibits actual physical behavior; An environmental condition simulation unit for simulating different environmental conditions, so that learners can operate power grid equipment in various situations.

8. The power grid maintenance training system based on extended reality of claim 7, wherein, The force feedback unit simulates the feedback of resistance, pulling force and pushing force during operation through a force feedback glove or a controller according to the operation intensity Adjusting the feedback force The force feedback relationship formula: ， wherein, is the feedback force, is the feedback force coefficient, is the operating strength; The high-precision physical engine unit makes the virtual device have real physical feedback when operating based on the friction, reaction force and gravity of the physical engine calculation device, and the friction of the device in the simulation cable connection process The calculation formula is: ， wherein, is the coefficient of friction, is the weight of the device.

9. A power grid maintenance training method based on extended reality, a power grid maintenance training system based on extended reality according to any one of claims 1 to 8, characterized in that, The method comprises the following steps: Step 1: The cloud rendering and distribution system generates a high-quality rendering output of the power grid maintenance scene, and transmits the content to the learner's terminal device through the edge computing node and the content distribution network, in the process, the real-time dynamic content updating module embeds the real-time data of the equipment into the extended reality scene, providing a real simulation environment for the learner; Step 2: The data processing module collects data from the Internet of Things sensors of the power grid equipment, cleans, converts and integrates the data to generate a real-time state data set of the equipment; Step 3: Through the real-time dynamic content update module, the system uses digital twin technology to map the real-time state of power grid equipment onto virtual device models. Meanwhile, the content management system retrieves fault cases and operation tasks from the preset database or generates corresponding training tasks based on the state of the equipment. Step 4: The AI-driven intelligent assessment and personalized learning path module analyzes the students' operation behavior and operation accuracy to conduct real-time assessment of the students, generates personalized learning paths, and dynamically adjusts the difficulty of tasks based on the students' performance and recommends adaptive tasks. Step 5: The task management module creates, distributes, and adjusts tasks based on the students' personalized learning paths, dynamically generates adaptive tasks based on the real-time state of the equipment and the performance of the students, and pushes the tasks to the students' terminal devices. Step 6: During the training process, the virtual reality and physical simulation fusion module provides real tactile feedback to students through force feedback devices and physical engines. At the same time, haptic feedback and environmental condition simulation enable students to experience the operation of power grid equipment in various scenarios. Step 7: During the task execution process, the task management module collects students' feedback and operation data and transmits the data to the AI-driven intelligent assessment module. Based on the students' real-time operation performance, the system dynamically adjusts the learning path and task difficulty. Step 8: The virtual reality and physical simulation fusion module provides force feedback based on the students' operation intensity during the students' operation process, making virtual operation have real physical feedback. Step 9: Based on the students' behavior scores and feedback, the system continuously optimizes the personalized learning path and task difficulty, enabling students to gradually adapt to more challenging tasks and achieving the goal of personalized training.

Images