Virtual-real linkage training system and method based on real-time data of production line

Abstract

The invention relates to the technical field of virtual training, and discloses a virtual-real linkage training system and method based on real-time data of a production line, and the method comprises the steps: constructing a multi-dimensional real-time collection model, carrying out the standardization processing of the state information of each physical device, building a consistency mapping relation between the states of virtual devices and physical devices, and carrying out the recognition of the state information of each physical device; the method comprises the following steps: monitoring synchronization delay in real time, identifying synchronization abnormity, setting an operation instruction and a control rule, carrying out legality verification on the operation instruction according to the current state of equipment, constructing a difference identification model by comparing state differences of virtual equipment and physical equipment, and carrying out abnormity early warning according to a set deviation threshold value. According to the method, a scoring mechanism is constructed in combination with legality and consistency of operation behaviors of trainees and system response conditions, the operation level is evaluated according to score grading, the whole practical training process is divided into multiple modules, sorting is performed based on error rates of the trainees in the modules, personalized recommendation paths are formed, and practical training efficiency and pertinence are improved.

Description

Technical Field

[0001] This invention relates to the field of virtual training technology, specifically to a virtual-real linkage training system and method based on real-time production line data. Background Technology

[0002] In the context of the current intelligent and digital transformation of manufacturing, production line training has become a crucial component in the cultivation of technical talent. Traditional training methods, which primarily focus on the operation of physical equipment, offer some practical experience but generally suffer from high resource consumption, high operational risks, and untimely evaluation, making them ill-suited to the demands of modern production environments for efficient, safe, and intelligent training systems. Furthermore, with the diversification of equipment types and the increasing complexity of control systems, it becomes increasingly difficult for trainees to grasp the equipment's status characteristics and control logic within a short period, thus impacting the effectiveness and efficiency of training.

[0003] In recent years, virtual simulation technology has developed rapidly. Introducing it into practical training scenarios allows for highly realistic operational training without relying on real equipment, reducing resource consumption and risks. However, virtual training systems often lack real-time perception and feedback of the real equipment's status, making it difficult to fully reflect the dynamic characteristics of the physical system, resulting in deviations between training content and actual work scenarios. Furthermore, most existing training systems still employ static evaluation methods, failing to provide personalized recommendations based on differences in student performance, and thus unable to effectively support differentiated teaching and precise training.

[0004] Meanwhile, by constructing a real-time acquisition model based on the physical device status, a comprehensive perception of the device's operating status can be achieved. This perception can then be used to drive the state synchronization and feedback control of virtual devices, thus forming a "virtual-real linkage" training mechanism. This mechanism not only enhances the training system's perception and response capabilities to real working conditions but also enables functions such as operation legality verification, system consistency judgment, difference early warning analysis, behavior scoring evaluation, and personalized recommended path planning, thereby comprehensively improving the scientific and intelligent level of training.

[0005] In summary, existing technologies still have significant shortcomings in terms of real-time performance, interactivity, and personalized support in training systems. There is an urgent need to propose an intelligent virtual-real linkage training method that integrates real-time data from physical equipment with virtual simulation capabilities. This method would achieve the organic integration of equipment status perception, virtual-real consistency mapping, operational behavior analysis, and personalized learning path planning, thereby comprehensively improving the adaptability, intelligence, and teaching effectiveness of the training system. Summary of the Invention

[0006] This invention provides a virtual-real linkage training system and method based on real-time production line data, which helps to solve the problems mentioned in the background art.

[0007] This invention provides the following technical solution: a virtual-real linkage training method based on real-time production line data, comprising: Construct a multi-dimensional real-time acquisition model and perform linear processing on the physical device status information; Establish a consistent mapping relationship between the virtual device state and the physical device state, and determine synchronization anomalies based on synchronization delay; Set operation instructions and control rules, verify their legality based on the current state of the equipment, and construct a set of legal operations; By comparing the status of virtual and physical devices, a difference identification model is established and anomaly warnings are issued based on deviation thresholds; A scoring mechanism is constructed by combining the legality and consistency of trainees' operational behavior with system response, and operational levels are assessed in a tiered manner. The training process is divided into multiple modules, and personalized recommended paths are generated by sorting the students' error rates in each module.

[0008] Optionally, the step of constructing a multi-dimensional real-time acquisition model and performing linear processing on the physical device state information includes: Each physical device is assigned a number, denoted as: ; Construct the original state vector The details are as follows: ; in: T represents the timestamp; This represents the status code of the i-th physical device; This represents the real-time speed of the i-th physical device; This represents the surface temperature of the i-th physical device; This represents the driving frequency of the i-th physical device; Define standard sampling time series n is a natural number; If the timestamp of the original state vector is Then linear interpolation is performed, as follows: ; Where k is a natural number.

[0009] Optionally, establishing a consistency mapping relationship between the virtual device state and the physical device state, and determining synchronization anomalies based on synchronization delay, includes: In a virtual environment, each virtual device Includes the following parameters: ; in: This represents the virtual status code of the i-th virtual device; This represents the virtual speed of the i-th virtual device; This represents the virtual surface temperature of the i-th virtual device; This represents the virtual drive frequency of the i-th virtual device; The initial value is equivalent to the original state vector of the physical device. ,Right now ; Calculate the current synchronization delay as ,in For virtual device timestamps For the timestamp of the physical device; like If the data collection stops, a synchronization error will be displayed.

[0010] Optionally, the setting of operation instructions and control rules, based on the current state of the device, performs legality verification and constructs a set of legal operations, including: Configure the control commands as follows: ; in: The operating time of the physical equipment; Indicates the operation category; Indicates an operation action; Indicates the target value of the operation; Collect the appropriate control commands for all virtual devices under each virtual status code and enter them into the operation set; Each virtual status code corresponds to a set of operations; Define a validity verification function as follows: ; in: This indicates the result of the validity verification, where 1 represents valid and 0 represents invalid. This represents the validity verification function.

[0011] Optionally, the step of establishing a difference identification model by comparing the states of virtual and physical devices and issuing anomaly warnings based on deviation thresholds includes: Construct the virtual-real difference function as follows: ; in: Let be the difference between the virtual and real states of the i-th virtual device at time T; The specific calculation expressions for the predicted speed, temperature, and frequency values ​​based on historical data are as follows: ; Where key represents the length of the historical data window, and m is the index variable; Set deviation threshold ; when When this happens, an operational deviation warning will be issued.

[0012] Optionally, the step of constructing a scoring mechanism and grading operational levels by combining the legality and consistency of trainee operational behavior with system response includes: The behavior scoring algorithm is constructed as follows: ; in: Indicates the first Each student's performance score; Indicates the number of operations; Indicates the first The result of the legality verification of the l-th operation by each student; The expected response of the system is 1 if the system allows the current student's l-th operation, otherwise it is 0; The consistency function is as follows: ; Set the behavior rating level to Leave, as follows: ; when When the student's performance score is deemed unsatisfactory, the system will notify them. when When the student's performance score is passed, the system will notify them. when When the student's performance is rated as excellent, the system will notify them.

[0013] Optionally, the step of dividing the training process into multiple modules and generating personalized recommended paths based on the students' error rates in each module includes: The practical training is divided into M modules; An error rate table for each student is created, as follows: ; in, Indicates the first The error rate of each student in module q For the first The number of times each student completes the correct operation in module q. For the first Total number of operations performed by each student in module q; The recommendation priority for each module for each student is defined as the error rate of that module. ; in, Represents module q for the first Recommendation priority for each student; The learning paths are sorted from highest to lowest priority to form personalized learning paths, as follows: Sort in descending order; in, Indicates the first A list of personalized recommendation modules for each student. This indicates a sorting operation based on the recommended priority values ​​from module 1 to module M; like Error rate of any module in If so, skip the current module.

[0014] A system for implementing the virtual-real linkage training method based on real-time production line data includes: The data acquisition module is used to collect the operating status information of physical equipment in real time, form the original state vector, and perform linear interpolation on the equipment status data to generate a standardized data sequence. The virtual synchronization module is used to establish a consistent mapping between the virtual device state and the physical device state, and to determine the synchronization anomaly state based on the synchronization delay calculation result; The operation control module is used to set up a set of operation instructions for different device status codes, and to use a validity verification function to judge the validity of the student's operation instructions. The virtual-physical difference assessment module is used to compare the status of virtual and physical devices, calculate the status deviation, and trigger synchronous anomaly warnings based on the set deviation threshold. The behavior scoring module is used to count the legality of the operator's operation behavior and the consistency of the system response during the training process, calculate the scoring results, and evaluate the operation level based on the scoring level. The path generation module is used to divide the practical training tasks into multiple modules and generate personalized recommended learning paths based on the students' error rates in each module, thereby achieving targeted training optimization.

[0015] The present invention has the following beneficial effects: By constructing a multi-dimensional real-time acquisition model and linearly processing the status information of each physical device, and using a standard time series as a benchmark, the model uniformly models and interpolates parameters such as device status codes, real-time speeds, surface temperatures, and drive frequencies, thereby ensuring the time consistency and status accuracy of data acquisition. This technical solution assigns a unique number to each physical device and constructs a standard status vector after collecting multi-dimensional status data, accurately describing the current operating status of the device. Simultaneously, by standardizing sampling time intervals and performing linear interpolation on asynchronously acquired data, it ensures consistent correspondence of data across dimensions on the time axis, effectively eliminating time-series deviations caused by different sampling frequencies. Compared to traditional methods that only use real-time snapshot data, this method, through structured linear time correction, can more accurately and dynamically depict the fluctuation trends of device status, providing high-quality foundational data support for subsequent virtual-real mapping and synchronization judgment. The overall solution has significant advantages in improving the accuracy of status data and enhancing the stability of virtual-real synchronization, making it particularly suitable for industrial simulation and training scenarios with high requirements for time-series data.

[0016] By establishing a consistent mapping relationship between the state parameters of virtual and physical devices, and calculating the synchronization delay value using timestamp comparison, abnormal states during the synchronization process are further identified, ensuring the accuracy and real-time performance of virtual-physical linkage. In this scheme, the initial state of each virtual device is completely referenced to its physical counterpart, with status codes, speed, temperature, frequency, and other data achieving equivalent mapping. Simultaneously, by continuously comparing the data update times of virtual and physical devices, the synchronization delay is calculated. If it exceeds a set range, data synchronization is immediately terminated and a synchronization anomaly warning is issued. This mechanism effectively solves the inconsistency problem between virtual and physical systems caused by sensor latency, unstable network transmission, or slow system response in traditional virtual simulation systems. Especially during practical training, the system can automatically determine whether there is a synchronization offset between virtual and physical devices, thereby ensuring the timeliness and realism of trainees' operations in the virtual environment. This technology significantly enhances the fault tolerance and data synchronization stability of the simulation system, and is a key means to ensure the efficient operation of the virtual-physical linkage training platform.

[0017] By constructing device control rules and a validity verification function, the system enables real-time validity judgment of trainee operation commands, ensuring that each operation conforms to the operational logic of the current device state. This solution establishes an operation command model for each device, clearly defining specific elements such as operation time, operation category, action type, and target value, and records a set of valid control commands based on the virtual device's state. After a trainee issues an operation command, the system immediately uses the validity verification function to determine whether the operation is permitted under the specified state. If invalid, the system provides real-time feedback to prevent misoperation from damaging the device or affecting subsequent training processes. This mechanism achieves the dual goals of teaching guidance and risk control. On the one hand, it can standardize trainee operation behavior in real time, guiding them to develop good operating habits in real-world scenarios; on the other hand, it reduces the risk of device malfunction due to incorrect operation during training. The overall technical architecture is clear and logically rigorous, significantly improving the intelligent interaction capabilities and teaching quality of the training system.

[0018] A difference identification model between virtual and physical equipment is established, and a deviation threshold mechanism is introduced to compare and analyze multiple indicators such as speed, temperature, and frequency in both virtual and physical states, thereby achieving intelligent anomaly identification and early warning. This technical solution introduces a virtual-physical difference function between the virtual and physical equipment states and constructs a predictive value model based on historical data to measure the degree of matching between virtual operating trends and actual states. When the difference between virtual and physical equipment exceeds a preset deviation threshold, the system immediately determines it as an operational deviation and issues an anomaly warning, effectively guiding trainees to review their operational behavior or equipment status. This method has the advantages of strong dynamic identification capability and fast response speed, enabling early warning intervention before multi-dimensional parameter deviations affect the overall process, improving the safety and intelligence of the training system. Especially in complex operational tasks, the system's high sensitivity to minute state deviations makes it widely applicable to training simulations of high-requirement processes, significantly enhancing the reliability and stability of the simulation system in dynamic monitoring.

[0019] By constructing a scoring mechanism that incorporates legality, consistency, and system response, this method quantifies and grades trainees' operational behaviors during practical training, thereby achieving individualized training effect feedback and competency assessment. In this method, the system records each trainee's every operational action in real time and compares the expected and actual responses. A scoring model is constructed using a legality judgment function and a consistency calculation function. The final score determines whether the trainee's operation meets the equipment's requirements, categorizing it into three levels: failing, passing, and excellent, thus achieving a scientific and reasonable skill level assessment. This mechanism breaks away from the traditional approach that uses task completion as the sole criterion for evaluation. It comprehensively assesses trainees' responsiveness, rule adherence, and operational proficiency in different operational scenarios, representing a significant innovative means to improve personalized teaching effectiveness and system evaluation accuracy. The scoring mechanism results can not only be used for current course evaluation but also provide data support for subsequent training path planning, achieving a fully intelligent teaching closed loop.

[0020] By dividing the overall training process into multiple functional modules and calculating the error rate of each learner in each module, a personalized learning recommendation path is generated based on the error rate, thus achieving a training management model that is tailored to individual needs. The solution first calculates the number of correct operations and the total number of operations performed by each learner in all modules, then constructs a priority list based on this, prioritizing modules with high error rates for repeated training. When the error rate of a module falls below a set threshold, the system automatically skips that module, ensuring that learning resources are concentrated on areas of weakness. This method generates targeted training suggestions based on real-world operational data, avoiding repetitive learning of already mastered content and improving learning efficiency. Simultaneously, its quantitative identification capability of errors enables the teaching system to have precise diagnostic and dynamic adjustment capabilities, fully reflecting the personalized and intelligent development direction of virtual-real integrated training systems. The overall solution effectively enhances the system's teaching flexibility to adapt to the different abilities of learners, improving training effectiveness while significantly reducing the redundant use of teaching resources. Attached Figure Description

[0021] Figure 1 This is a schematic diagram of the process of the present invention.

[0022] Figure 2 This is a schematic diagram of the system structure of the present invention. Detailed Implementation

[0023] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0024] Example 1, see Figure 1 A virtual-real linkage training method based on real-time production line data includes: Construct a multi-dimensional real-time acquisition model and perform linear processing on the physical device status information; Establish a consistent mapping relationship between the virtual device state and the physical device state, and determine synchronization anomalies based on synchronization delay; Set operation instructions and control rules, verify their legality based on the current state of the equipment, and construct a set of legal operations; By comparing the status of virtual and physical devices, a difference identification model is established and anomaly warnings are issued based on deviation thresholds; A scoring mechanism is constructed by combining the legality and consistency of trainees' operational behavior with system response, and operational levels are assessed in a tiered manner. The training process is divided into multiple modules, and personalized recommended paths are generated by sorting the students' error rates in each module.

[0025] The construction of a multi-dimensional real-time acquisition model and the linear processing of physical device status information include: Each physical device is assigned a number, denoted as: ; Construct the original state vector The details are as follows: ; in: T represents the timestamp; This represents the status code of the i-th physical device; This represents the real-time speed of the i-th physical device; This represents the surface temperature of the i-th physical device; This represents the driving frequency of the i-th physical device; Define standard sampling time series n is a natural number; If the timestamp of the original state vector is Then linear interpolation is performed, as follows: ; Where k is a natural number.

[0026] By constructing a multi-dimensional real-time acquisition model and linearly processing the status information of each physical device, and using a standard time series as a benchmark, the model uniformly models and interpolates parameters such as device status codes, real-time speeds, surface temperatures, and drive frequencies, thereby ensuring the time consistency and status accuracy of data acquisition. This technical solution assigns a unique number to each physical device and constructs a standard status vector after collecting multi-dimensional status data, accurately describing the current operating status of the device. Simultaneously, by standardizing sampling time intervals and performing linear interpolation on asynchronously acquired data, it ensures consistent correspondence of data across dimensions on the time axis, effectively eliminating time-series deviations caused by different sampling frequencies. Compared to traditional methods that only use real-time snapshot data, this method, through structured linear time correction, can more accurately and dynamically depict the fluctuation trends of device status, providing high-quality foundational data support for subsequent virtual-real mapping and synchronization judgment. The overall solution has significant advantages in improving the accuracy of status data and enhancing the stability of virtual-real synchronization, making it particularly suitable for industrial simulation and training scenarios with high requirements for time-series data.

[0027] The process of establishing a consistent mapping between the virtual device state and the physical device state, and determining synchronization anomalies based on synchronization delay, includes: In a virtual environment, each virtual device Includes the following parameters: ; in: This represents the virtual status code of the i-th virtual device; This represents the virtual speed of the i-th virtual device; This represents the virtual surface temperature of the i-th virtual device; This represents the virtual drive frequency of the i-th virtual device; The initial value is equivalent to the original state vector of the physical device. ,Right now ; Calculate the current synchronization delay as ,in For virtual device timestamps For the timestamp of the physical device; like If the data collection stops, a synchronization error will be displayed.

[0028] By establishing a consistent mapping relationship between the state parameters of virtual and physical devices, and calculating the synchronization delay value using timestamp comparison, abnormal states during the synchronization process are further identified, ensuring the accuracy and real-time performance of virtual-physical linkage. In this scheme, the initial state of each virtual device is completely referenced to its physical counterpart, with status codes, speed, temperature, frequency, and other data achieving equivalent mapping. Simultaneously, by continuously comparing the data update times of virtual and physical devices, the synchronization delay is calculated. If it exceeds a set range, data synchronization is immediately terminated and a synchronization anomaly warning is issued. This mechanism effectively solves the inconsistency problem between virtual and physical systems caused by sensor latency, unstable network transmission, or slow system response in traditional virtual simulation systems. Especially during practical training, the system can automatically determine whether there is a synchronization offset between virtual and physical devices, thereby ensuring the timeliness and realism of trainees' operations in the virtual environment. This technology significantly enhances the fault tolerance and data synchronization stability of the simulation system, and is a key means to ensure the efficient operation of the virtual-physical linkage training platform.

[0029] The set operation instructions and control rules are validated for legality based on the current state of the device and a set of legal operations is constructed, including: Configure the control commands as follows: ; in: The operating time of the physical equipment; Indicates the type of operation, such as speed adjustment, restart, etc. Indicates operation actions, such as "+", "-", "set to 0", etc.; This indicates the target value for operation, such as setting the speed of the physical device to 1.5 meters per second; Collect the appropriate control commands for all virtual devices under each virtual status code and enter them into the operation set; Each virtual status code corresponds to a set of operations; Define a validity verification function as follows: ; in: This indicates the result of the validity verification, where 1 represents valid and 0 represents invalid. This represents the validity verification function.

[0030] By constructing device control rules and a validity verification function, the system enables real-time validity judgment of trainee operation commands, ensuring that each operation conforms to the operational logic of the current device state. This solution establishes an operation command model for each device, clearly defining specific elements such as operation time, operation category, action type, and target value, and records a set of valid control commands based on the virtual device's state. After a trainee issues an operation command, the system immediately uses the validity verification function to determine whether the operation is permitted under the specified state. If invalid, the system provides real-time feedback to prevent misoperation from damaging the device or affecting subsequent training processes. This mechanism achieves the dual goals of teaching guidance and risk control. On the one hand, it can standardize trainee operation behavior in real time, guiding them to develop good operating habits in real-world scenarios; on the other hand, it reduces the risk of device malfunction due to incorrect operation during training. The overall technical architecture is clear and logically rigorous, significantly improving the intelligent interaction capabilities and teaching quality of the training system.

[0031] The process of establishing a difference recognition model by comparing the states of virtual and physical devices and issuing anomaly warnings based on deviation thresholds includes: Construct the virtual-real difference function as follows: ; in: Let be the difference between the virtual and real states of the i-th virtual device at time T; The specific calculation expressions for the predicted speed, temperature, and frequency values ​​based on historical data are as follows: ; Where key represents the length of the historical data window, and m is the index variable; Set deviation threshold ; Deviation threshold In this scheme, a value of 3 can be taken. In a large number of training systems, even students who have mastered the skills will have a 1-2% error fluctuation (such as operation delay, accidental touch, interface switching, etc.). Setting the threshold to 3 can effectively avoid "false positive" prompts caused by these irrelevant factors. If the threshold is set too small (such as 1 or 2), it will lead to a large number of meaningless prompts. Setting it to 3 can significantly reduce the false alarm rate and improve the credibility of the system's recommendations.

[0032] when When this happens, an operational deviation warning will be issued.

[0033] A difference identification model between virtual and physical equipment is established, and a deviation threshold mechanism is introduced to compare and analyze multiple indicators such as speed, temperature, and frequency in both virtual and physical states, thereby achieving intelligent anomaly identification and early warning. This technical solution introduces a virtual-physical difference function between the virtual and physical equipment states and constructs a predictive value model based on historical data to measure the degree of matching between virtual operating trends and actual states. When the difference between virtual and physical equipment exceeds a preset deviation threshold, the system immediately determines it as an operational deviation and issues an anomaly warning, effectively guiding trainees to review their operational behavior or equipment status. This method has the advantages of strong dynamic identification capability and fast response speed, enabling early warning intervention before multi-dimensional parameter deviations affect the overall process, improving the safety and intelligence of the training system. Especially in complex operational tasks, the system's high sensitivity to minute state deviations makes it widely applicable to training simulations of high-requirement processes, significantly enhancing the reliability and stability of the simulation system in dynamic monitoring.

[0034] The aforementioned scoring mechanism, which combines the legality and consistency of trainee actions with system response to construct a graded assessment of operational skills, includes: The behavior scoring algorithm is constructed as follows: ; in: Indicates the first Each student's performance score; Indicates the number of operations; Indicates the first The result of the legality verification of the l-th operation by each student; The expected response of the system is 1 if the system allows the current student's l-th operation, otherwise it is 0; Whether the system allows a student's operation is determined by professional standards developed by professionals and embedded into the system. The expected response value of the system is set by comparing the student's operation with the professional standards. The consistency function is as follows: ; For example: If the device is currently running (number 1), the student executes "Restart": Actual response Operation is prohibited; System expected response The system believes it should be allowed; result: The operation was unreasonable.

[0035] Set the behavior rating level to Leave, as follows: ; when When the student's performance score is deemed unsatisfactory, the system will notify them. when When the student's performance score is passed, the system will notify them. when When the student's performance is rated as excellent, the system will notify them.

[0036] By constructing a scoring mechanism that incorporates legality, consistency, and system response, this method quantifies and grades trainees' operational behaviors during practical training, thereby achieving individualized training effect feedback and competency assessment. In this method, the system records each trainee's every operational action in real time and compares the expected and actual responses. A scoring model is constructed using a legality judgment function and a consistency calculation function. The final score determines whether the trainee's operation meets the equipment's requirements, categorizing it into three levels: failing, passing, and excellent, thus achieving a scientific and reasonable skill level assessment. This mechanism breaks away from the traditional approach that uses task completion as the sole criterion for evaluation. It comprehensively assesses trainees' responsiveness, rule adherence, and operational proficiency in different operational scenarios, representing a significant innovative means to improve personalized teaching effectiveness and system evaluation accuracy. The scoring mechanism results can not only be used for current course evaluation but also provide data support for subsequent training path planning, achieving a fully intelligent teaching closed loop.

[0037] The training process is divided into multiple modules, and personalized recommended paths are generated based on the students' error rates in each module, including: The practical training is divided into M modules; An error rate table for each student is created, as follows: ; in, Indicates the first The error rate of each student in module q For the first The number of times each student completes the correct operation in module q. For the first Total number of operations performed by each student in module q; The recommendation priority for each module for each student is defined as the error rate of that module. ; in, Represents module q for the first Recommendation priority for each student; The learning paths are sorted from highest to lowest priority to form personalized learning paths, as follows: Sort in descending order; in, Indicates the first A list of personalized recommendation modules for each student. This indicates a sorting operation based on the recommended priority values ​​from module 1 to module M; like Error rate of any module in If so, skip the current module.

[0038] By dividing the overall training process into multiple functional modules and calculating the error rate of each learner in each module, a personalized learning recommendation path is generated based on the error rate, thus achieving a training management model that is tailored to individual needs. The solution first calculates the number of correct operations and the total number of operations performed by each learner in all modules, then constructs a priority list based on this, prioritizing modules with high error rates for repeated training. When the error rate of a module falls below a set threshold, the system automatically skips that module, ensuring that learning resources are concentrated on areas of weakness. This method generates targeted training suggestions based on real-world operational data, avoiding repetitive learning of already mastered content and improving learning efficiency. Simultaneously, its quantitative identification capability of errors enables the teaching system to have precise diagnostic and dynamic adjustment capabilities, fully reflecting the personalized and intelligent development direction of virtual-real integrated training systems. The overall solution effectively enhances the system's teaching flexibility to adapt to the different abilities of learners, improving training effectiveness while significantly reducing the redundant use of teaching resources.

[0039] Example 2, see Figure 2 A system for implementing the virtual-real linkage training method based on real-time production line data, comprising: The data acquisition module is used to collect the operating status information of physical equipment in real time, form the original state vector, and perform linear interpolation on the equipment status data to generate a standardized data sequence. The virtual synchronization module is used to establish a consistent mapping between the virtual device state and the physical device state, and to determine the synchronization anomaly state based on the synchronization delay calculation result; The operation control module is used to set up a set of operation instructions for different device status codes, and to use a validity verification function to judge the validity of the student's operation instructions. The virtual-physical difference assessment module is used to compare the status of virtual and physical devices, calculate the status deviation, and trigger synchronous anomaly warnings based on the set deviation threshold. The behavior scoring module is used to count the legality of the operator's operation behavior and the consistency of the system response during the training process, calculate the scoring results, and evaluate the operation level based on the scoring level. The path generation module is used to divide the practical training tasks into multiple modules and generate personalized recommended learning paths based on the students' error rates in each module, thereby achieving targeted training optimization.

[0040] It should be noted that, in this document, relational terms such as "first" and "second" are used only to distinguish one entity or operation from another, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Furthermore, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such process, method, article, or apparatus.

[0041] The above description is only a preferred embodiment of the present invention. It should be noted that for those skilled in the art, several improvements and modifications can be made without departing from the technical principles of the present invention, and these improvements and modifications should also be considered within the scope of protection of the present invention.

Claims

1. A virtual-real linkage training method based on real-time production line data, characterized in that, include: Construct a multi-dimensional real-time acquisition model and perform linear processing on the physical device status information; Establish a consistent mapping relationship between the virtual device state and the physical device state, and determine synchronization anomalies based on synchronization delay; Set operation instructions and control rules, verify their legality based on the current state of the equipment, and construct a set of legal operations; By comparing the status of virtual and physical devices, a difference identification model is established and anomaly warnings are issued based on deviation thresholds; A scoring mechanism is constructed by combining the legality and consistency of trainees' operational behavior with system response, and operational levels are assessed in a tiered manner. The training process is divided into multiple modules, and personalized recommended paths are generated by sorting the students' error rates in each module.

2. The virtual-real linkage training method based on real-time production line data according to claim 1, characterized in that, The construction of a multi-dimensional real-time acquisition model and the linear processing of physical device status information include: Each physical device is assigned a number, denoted as: ; Construct the original state vector The details are as follows: ； in: T represents the timestamp; This represents the status code of the i-th physical device; This represents the real-time speed of the i-th physical device; This represents the surface temperature of the i-th physical device; This represents the driving frequency of the i-th physical device; Define standard sampling time series n is a natural number; If the timestamp of the original state vector is Then linear interpolation is performed, as follows: ； Where k is a natural number.

3. The virtual-real linkage training method based on real-time production line data according to claim 1, characterized in that, The process of establishing a consistent mapping between the virtual device state and the physical device state, and determining synchronization anomalies based on synchronization delay, includes: In a virtual environment, each virtual device Includes the following parameters: ； in: This represents the virtual status code of the i-th virtual device; This represents the virtual speed of the i-th virtual device; This represents the virtual surface temperature of the i-th virtual device; This represents the virtual drive frequency of the i-th virtual device; The initial value is equivalent to the original state vector of the physical device. ,Right now ; Calculate the current synchronization delay as ,in For virtual device timestamps For the timestamp of the physical device; like If the data collection stops, a synchronization error will be displayed.

4. The virtual-real linkage training method based on real-time production line data according to claim 1, characterized in that, The set operation instructions and control rules are validated for legality based on the current state of the device and a set of legal operations is constructed, including: Configure the control commands as follows: ； in: The operating time of the physical equipment; Indicates the operation category; Indicates an operation action; Indicates the target value of the operation; Collect the appropriate control commands for all virtual devices under each virtual status code and enter them into the operation set; Each virtual status code corresponds to a set of operations; Define a validity verification function as follows: ； in: This indicates the result of the validity verification, where 1 represents valid and 0 represents invalid. This represents the validity verification function.

5. The virtual-real linkage training method based on real-time production line data according to claim 1, characterized in that, The process of establishing a difference recognition model by comparing the states of virtual and physical devices and issuing anomaly warnings based on deviation thresholds includes: Construct the virtual-real difference function as follows: ； in: Let be the difference between the virtual and real states of the i-th virtual device at time T; The specific calculation expressions for the predicted speed, temperature, and frequency values ​​based on historical data are as follows: ； Where key represents the length of the historical data window, and m is the index variable; Set deviation threshold ; when When this happens, an operational deviation warning will be issued.

6. The virtual-real linkage training method based on real-time production line data according to claim 1, characterized in that, The aforementioned scoring mechanism, which combines the legality and consistency of trainee actions with system response to construct a graded assessment of operational skills, includes: The behavior scoring algorithm is constructed as follows: ； in: Indicates the first Each student's performance score; Indicates the number of operations; Indicates the first The result of the legality verification of the l-th operation by each student; The expected response of the system is 1 if the system allows the current student's l-th operation, otherwise it is 0; The consistency function is as follows: ； Set the behavior rating level to Leave, as follows: ； when When the student's performance score is deemed unsatisfactory, the system will notify them. when When the student's performance score is passed, the system will notify them. when When the student's performance is rated as excellent, the system will notify them.

7. The virtual-real linkage training method based on real-time production line data according to claim 1, characterized in that, The training process is divided into multiple modules, and personalized recommended paths are generated based on the students' error rates in each module, including: The practical training is divided into M modules; An error rate table for each student is created, as follows: ； in, Indicates the first The error rate of each student in module q For the first The number of times each student completes the correct operation in module q. For the first Total number of operations performed by each student in module q; The recommendation priority for each module for each student is defined as the error rate of that module. ; in, Represents module q for the first Recommendation priority for each student; The learning paths are sorted from highest to lowest priority to form personalized learning paths, as follows: Sort in descending order; in, Indicates the first A list of personalized recommendation modules for each student. This indicates a sorting operation based on the recommended priority values ​​from module 1 to module M; like Error rate of any module in If so, skip the current module.

8. A system employing the virtual-real linkage training method based on real-time production line data as described in claim 1, characterized in that, include: The data acquisition module is used to collect the operating status information of physical equipment in real time, form the original state vector, and perform linear interpolation on the equipment status data to generate a standardized data sequence. The virtual synchronization module is used to establish a consistent mapping between the virtual device state and the physical device state, and to determine the synchronization anomaly state based on the synchronization delay calculation result; The operation control module is used to set up a set of operation instructions for different device status codes, and to use a validity verification function to judge the validity of the student's operation instructions. The virtual-physical difference assessment module is used to compare the status of virtual and physical devices, calculate the status deviation, and trigger synchronous anomaly warnings based on the set deviation threshold. The behavior scoring module is used to count the legality of the operator's operation behavior and the consistency of the system response during the training process, calculate the scoring results, and evaluate the operation level based on the scoring level. The path generation module is used to divide the practical training tasks into multiple modules and generate personalized recommended learning paths based on the students' error rates in each module, thereby achieving targeted training optimization.

Images