Digital training method and system based on safety production

Abstract

The invention belongs to the technical field of electric power safety production, and discloses a digital training method and system based on safety production, microcosmic-macroscopic double-domain mapping is constructed through quantum enhanced digital twinning units, students can visually observe microcosmic processes such as cable insulation layer molecular chain breakage and control cabinet arc discharge plasma evolution, and the training efficiency is improved. Associating to macroscopic fault performance; the problem that a traditional system can only present the surface state of the equipment is solved, the pre-judgment capability on the hidden danger of the high-voltage equipment is improved from the source, and operation omission caused by the fact that risk cognition is not deep is avoided; through the brain-computer collaborative cognitive training unit, the system can monitor the neural activity and operation characteristics of the trainee in real time, and precise regulation and control of cognitive load are realized by adjusting pressure parameters of a virtual scene; the problem of decision delay of students in real high-voltage operation can be effectively relieved, the training effect is closer to the actual working condition, and it is ensured that the students keep stable judgment and execution ability when facing high-risk operation.

Description

Technical Field

[0001] The present invention belongs to the technical field of electric power production safety, and in particular relates to a digital training method and system based on production safety. Background Art

[0002] In the field of intelligent power control equipment and cable manufacturing, production safety training is directly related to the operational standardization of high-voltage equipment, fault emergency handling capabilities and production efficiency. This field covers key links such as 35kV and above cable laying, intelligent control cabinet commissioning, and insulation material performance testing. The operation process involves risk factors such as high voltage and high tension, and requires extremely high skill proficiency and risk prediction capabilities of practitioners.

[0003] After searching, the invention patent with publication number CN119963375A discloses a digital training management system for safe production. Although it can push personalized training plans by analyzing students' learning time, test scores and other behavioral data, it still has significant technical limitations: First, the system can only evaluate the status of students based on macro behavioral data, and does not integrate physiological signals such as electroencephalogram (EEG) and electromyography to build a cognitive-action association model. It cannot capture the micro-cognitive states of students such as attention fluctuations and emotional tension in high-voltage operations in real time, resulting in insufficient matching between virtual training and the psychological state in a real high-voltage environment. Students are faced with the 35kV cable endurance test. First, there is still a decision delay in high-risk scenarios such as pressure testing; second, its digital twin module only simulates the macroscopic operating parameters of the equipment (such as temperature and pressure), and does not involve the visualization of microscopic mechanisms such as the breakage of the molecular chain of the cable insulation layer and the evolution of the arc discharge plasma in the control cabinet. The trainees' understanding of potential risks remains at the phenomenon level, and it is difficult to understand the fundamental mechanism of the failure; third, the fault scenario design relies on a preset case library, and does not build a cross-device correlation map through the graph neural network. It is impossible to reproduce the chain reaction of "poor cable joint sealing → partial discharge → insulation breakdown → control cabinet over-tripping", which is disconnected from the fault transmission mechanism of the equipment interconnection in actual production. Summary of the Invention

[0004] The purpose of the present invention is to provide a digital training method and system based on safe production to solve the problems raised in the above background technology.

[0005] In order to achieve the above object, the present invention provides the following technical solution: a digital training system based on safe production, the system comprising: Quantum-enhanced digital twin unit: Based on the physical properties of the device, it constructs a multi-scale digital twin. It uses quantum dot marking to track microscopic changes in the cable insulation layer and correlates the macroscopic behavior of the control cabinet with its microscopic mechanisms. Its high-speed interface synchronizes real-time parameters to the cross-domain fault chain generation unit, supporting dynamic scenario construction. It also receives updated data from the evolving knowledge base, continuously optimizing model accuracy and providing physical data support for the system. Brain-computer collaborative cognitive training unit: Integrates EEG and electromyography equipment to capture trainees' neural activity and operational characteristics, building a "cognition-action" model. When cognitive abnormalities are detected, it sends instructions to the holographic operation memory unit to trigger scenario adaptation, encrypts and transmits cognitive data to the self-evolving knowledge base unit, and also receives scenario parameters from the cross-domain fault chain unit to dynamically adjust the monitoring threshold to achieve collaborative training of cognition and operation. Cross-domain fault chain generation unit: Based on real-time parameters and historical cases of the self-evolving knowledge base unit, a graph neural network is used to build a device association map. Based on the trainee's operation data and virtual device status, a fault chain scenario is generated, synchronized to the holographic operation memory unit to drive rendering, and reversely output rules to the self-evolving knowledge base unit for iteration; The holographic operation memory unit records expert operations through light field imaging and generates a holographic template. After receiving the scenario parameters from the cross-domain fault chain generation unit, the trainee and the virtual expert can "operate on the same screen." The AR device compares operation deviations, and the exoskeleton device provides tactile guidance. The intensity and frequency are adjusted according to the trainee's status in the brain-computer collaborative cognitive training unit. Deviation data is uploaded to the evolutionary knowledge base unit. Self-evolving knowledge base unit: Integrates multi-source information including fault chains, holographic operations, and brain-computer collaboration, refines rules and models through federated learning, and synchronizes them to the quantum-enhanced digital twin unit to optimize the physical model after updating, providing the latest rules for the cross-domain fault chain generation unit and triggering expert template iteration.

[0006] Preferably, the quantum enhanced digital twin unit is used to: (1) Multi-scale modeling and micro-mechanism restoration: Based on the physical properties of intelligent power equipment, a multi-scale digital twin is constructed. The cable insulation layer modeling adopts the quantum dot labeling algorithm to track the trajectory of virtual quantum dots and dynamically present microscopic changes such as molecular chain breakage and crystal ablation under the action of temperature and stress. The intelligent control cabinet uses the electromagnetic simulation module to associate macroscopic behaviors such as circuit breaker action with microscopic mechanisms such as electron transitions to achieve multi-dimensional restoration of the equipment status, providing a physical basis for subsequent scenario construction. Quantum dot diffusion coefficient formula: ,

[0007] Where: represents the quantum dot diffusion coefficient, in units of , is a core indicator that describes the activity of virtual molecular motion in the cable insulation layer. In the digital twin scenario, its value directly corresponds to the looseness of the microstructure of the insulation material. A larger value indicates a higher risk of molecular chain breakage. Indicates the initial diffusion coefficient. The base value is determined by the type of cable insulation material, such as cross-linked polyethylene cable. , rubber insulated cable ,obtained through actual measurement in the material laboratory and pre-entered into the system; The activation energy of diffusion is expressed in eV, which characterizes the energy threshold required for the molecular chain of the insulating material to break. For 10kV cables, its value is usually between 0.3 and 0.5eV, and is dynamically adjusted with the degree of material aging (the value of aged cables is 15% to 20% lower than that of new cables). represents the Boltzmann constant , used to convert temperature parameters into energy units to ensure the consistency of formula dimensions; Indicates the virtual environment temperature in K, which is synchronized with the real-time temperature of the cable production line (range 293~353K) and is collected from the extruder temperature control module through the device data interaction unit; Represents mechanical stress in MPa, corresponding to the tension during cable laying. For example, 8-12 MPa is used for overhead cables, and 5-8 MPa is used for underground cables. This is calculated based on the laying angle in the virtual scene (for example, when the angle is ≥45°, the tension is increased by 20%) and the traction force parameters. It represents the stress sensitivity coefficient, dimensionless, and is calibrated by 1000 cable tensile tests (polyethylene material is taken as , reflecting the accelerating effect of mechanical force on molecular diffusion; Function: Quantify the coupling effect of temperature and mechanical stress on microscopic motion. The calculation results are used to drive the animation of electrical dendrite growth in the insulating layer of the digital twin unit ( The real-time data is pushed to the cross-domain fault chain generation unit as the starting condition for the "insulation failure → control cabinet trip" fault chain; (2) Data linkage and model iteration optimization: The unit has a built-in high-speed interface to synchronize real-time parameters such as cable insulation resistance and control cabinet temperature field to the cross-domain fault chain generation unit to support the construction of dynamic fault scenarios; at the same time, it receives device characteristic update data from the evolutionary knowledge base unit, continuously optimizes the physical accuracy of the twin model, and ensures that the virtual scenario is highly consistent with the actual device characteristics.

[0008] Preferably, the brain-computer collaborative cognitive training unit is used to: (1) Multi-dimensional state monitoring and model construction: Integrate EEG acquisition and electromyography sensing equipment to capture students' neural activity and operation characteristics in real time; the EEG module identifies cognitive states such as attention and emotion through prefrontal electrodes; the electromyography equipment determines the stability of hand operation, and the core algorithm integrates data to build a "cognition-action" association model to accurately identify abnormal cognitive load in high-voltage operations and provide a basis for scene control; Cognitive load index formula: ,

[0009] Where: It represents the cognitive load index, ranging from 0 to 1, with 0.7 as the critical value. In the high-voltage cable wiring training, This indicates that the trainees are at risk of operating errors, such as accidentally touching live terminals when wiring 35kV cables or incorrectly setting parameter thresholds when debugging control cabinets; Indicates brain waves The amplitude ratio of theta wave (4~8Hz) to beta wave (13~30Hz). The enhanced theta wave reflects the state of anxiety. For example, when facing a 35kV device, the enhanced beta wave reflects the concentration of attention. The EEG headset is used to collect the frontal electrode array (sampling rate ; Indicates the real-time myoelectric signal amplitude in μV, which is collected by the wrist myoelectric sensor and reflects the degree of hand operation tremor (during normal operation). , when nervous ; Indicates the maximum EMG signal amplitude in μV, obtained through the trainee's initial test, such as the EMG value when gripping a cable stripper with full force, and serves as a benchmark for individual operating limits; Represents the weight coefficient , calibrated based on 100 electrician training data, because neural signals have a more significant impact on operational safety, Higher weight; Function: Real-time assessment of students' physical and mental state, when When the value is greater than 0.7, the system sends a command to the holographic operation memory unit to reduce the sound and light intensity of the high-voltage arc in the virtual scene (reduced by 30%), and triggers the expert operation holographic prompt. Time series data is encrypted and uploaded to the self-evolving knowledge base to optimize the difficulty curve of personalized training programs; (2) Data interaction and dynamic control adaptation: When cognitive anomalies are detected, control instructions are generated and sent to the holographic operation memory unit to trigger scenario adaptation. At the same time, the encrypted student cognitive data is transmitted to the self-evolving knowledge base unit to support personalized solution optimization; the scenario complexity parameters of the cross-domain fault chain generation unit are received, and the cognitive monitoring threshold is dynamically adjusted to achieve accurate matching of the training scenario and the student status.

[0010] Preferably, the cross-domain fault chain generating unit is used to: (1) Association graph construction and scenario triggering: Based on the physical parameters of the quantum-enhanced digital twin unit and historical cases of the self-evolving knowledge base, a device association graph is constructed through a graph neural network; the graph includes cable production parameters and control cabinet components, and the node weights are dynamically adjusted according to the linkage relationship. When starting training, based on the trainee's operation data and the status of the virtual equipment, a chain failure scenario caused by cable laying deviation is triggered; Fault correlation weight formula: ,

[0011] Where: Represents a device node To Node The fault association weight, which ranges from 0 to 1, is used to quantify the probability of fault conduction (e.g. show After the failure 80% chance to trigger); Indicates historical data trigger The number of faults is derived from the fault case library of the self-evolving knowledge base, such as the number of records of "abnormal pressure of cable extruder (i) → insulation layer deflection (j)"; Representation node The physical parameters of For cable parameters, such as extruder pressure MPa, For control cabinet parameters, such as PLC temperature alarm threshold ; Indicates the parameter reference value, which is the rated parameter for normal operation of the equipment, such as the rated pressure of the extruder MPa, rated temperature of control cabinet ,determined by the equipment manual; Function: Calculate the device association strength through graph neural network, for example, when =0.75, the system prioritizes generating the fault chain of "extruder pressure exceeds the standard → cable resistance is abnormal → control cabinet overcurrent protection is activated". The weight matrix is ​​synchronized to the holographic operation memory unit to drive the linkage change of the device status in the virtual scene (for example, the control cabinet indicator light flashes with the fluctuation of cable parameters); (2) Data synchronization and rule iteration: The generated dynamic fault chain data is synchronized to the holographic operation memory unit to drive scene rendering, and the fault evolution rules are reversely output to the self-evolving knowledge base unit; by continuously receiving multi-source data to optimize the association map, the consistency and timeliness of the fault scenario are ensured, providing complex scenarios close to reality for training.

[0012] Preferably, the holographic operational memory unit is used for: (1) Expert template construction and on-screen operation: The expert operation data is recorded through light field imaging, and an interactive holographic template is formed through three-dimensional reconstruction. During training, the dynamic fault chain data of the cross-domain fault chain generation unit is received, the matching template is called, and the trainee and the virtual expert are "on-screen operation" using holographic projection. The AR device captures the trainee's movements in real time and compares them with the template to generate a deviation report; (2) Tactile guidance and data feedback: Based on the comparison results, the exoskeleton feedback device provides tactile guidance at key nodes such as cable crimping. Its intensity and frequency are dynamically adjusted according to the status of the trainees in the brain-computer collaborative cognitive training unit. The operation deviation data is packaged and uploaded to the self-evolving knowledge base unit to enrich the case library. Operational deviation formula: , where: Indicates the operation deviation in mm·s, which comprehensively reflects the temporal and spatial differences between trainees and experts. For example, in the cable connector crimping operation, To be qualified; The vector represents the student's operation trajectory, including the 3D position (unit: mm), the applied force (unit: N), and the tool angle (unit: °). It is collected in real time by the 6DoF sensor of the AR glasses and the force sensor of the exoskeleton glove with a sampling rate of 100Hz. Represents the expert holographic template trajectory vector, which is generated by recording the standard operation of senior electricians using a light field imaging system. For example, the force vector during cable crimping is (0,0,35)N (axial force); Respectively represent the operation start time and operation end time, the unit is seconds, which is automatically recognized by the system, such as the time interval from picking up the wire stripper to completing the insulation stripping; Indicates the weight of the key node, dimensionless, set according to the operation risk level, cable terminal installation ,Control cabinet wiring ,The higher the risk, the greater the weight; Function: Accurately quantify the operational standardization, when When the exoskeleton feedback device triggers a vibration reminder (frequency varies with At the same time, a deviation analysis report is generated, such as "crimping angle deviation 3°", and the data is uploaded to the self-evolving knowledge base unit to update the fault tolerance threshold of the expert template.

[0013] Preferably, the self-evolving knowledge base unit is used to: (1) Multi-source data integration and collaborative training: A distributed architecture is used to integrate multi-source information such as cross-domain fault chain cases, holographic operation deviation data, and brain-computer cognitive maps; through a federated learning framework, data is collaboratively trained while protecting privacy, to refine operation specification update rules and fault pattern recognition models; Federated learning framework aggregation formula: , where: Indicates global update of model parameters, including fault identification threshold, operation scoring standard, etc. For example, the qualified threshold of cable insulation resistance changes from Updated to 800 ; Indicates the The local model parameters of each plant are generated by independent training based on the training data of each plant. For example, the insulation resistance threshold of Plant A is lowered by 15% due to the humid environment. Indicates the The sample size weight of a factory is positively correlated with the number of trained people and the number of equipment types in the factory. For example, a factory with 5 cable production lines , a factory with only one production line ; The number of factories participating in federated learning will be 5 in the initial pilot phase, and will be gradually expanded to the entire industry. Data privacy protection will be achieved through encryption protocols. Function: Aggregate industry experience without sharing original data, and update Synchronize to the quantum-enhanced digital twin unit to correct insulation material aging models, such as the humidity impact coefficient in coastal plant areas, and provide the latest fault association rules for cross-domain fault chain generation units, such as the protection logic of new intelligent control cabinets; (2) Knowledge synchronization and template iteration: The updated knowledge base is synchronized to the quantum enhanced digital twin unit to optimize the physical model, providing the latest association rules for the cross-domain fault chain generation unit; according to the expert data update frequency of the holographic operation memory unit, the expert template iteration is automatically triggered to ensure that the training content always matches the industry best practices.

[0014] The present invention also provides a digital training method based on safe production. Based on the above system, the specific steps of the method are as follows: S1. Neural-Device Collaborative Modeling: Microscopic modeling generates digital samples of cables and control cabinets, which are then imported into the quantum-enhanced digital twin unit. Neural baseline calibration collects expert data to establish cognitive models, which are stored in the brain-computer collaborative cognitive training unit. Virtual and real parameters are bound to correlate physical indicators (such as cable insulation resistance and control cabinet temperature) with cognitive indicators (such as attention span and operating tremor frequency), forming adaptation rules that are synchronized to the cross-domain fault chain generation unit, providing a data and rule foundation for subsequent training scenarios. S2. Fault chain immersion training: The cross-domain fault chain generation unit calls the real-time parameters of the quantum-enhanced digital twin unit and the case generation scenario of the self-evolving knowledge base unit. The complexity is set according to the initial evaluation of the brain-computer collaborative cognitive training unit. During training, the brain-computer collaborative cognitive training unit monitors the cognitive state and regulates the holographic operation memory unit or the cross-domain fault chain generation unit to adjust the scenario. S3. Memory enhancement and continuous optimization: The holographic operation memory unit retrieves expert templates, combines the fault chain scenario characteristics, and strengthens muscle memory through the exoskeleton; the self-evolving knowledge base unit summarizes data and updates the model through federated learning, which is synchronized to the quantum-enhanced digital twin unit and the cross-domain fault chain generation unit. The neural adaptation test results are fed back to step S1, forming a process from training to system iteration.

[0015] Preferably, the specific steps of the neural-device collaborative modeling in step S1 are as follows: S11. Basic model construction and feature extraction: Data fusion is completed in stages: In the microscopic modeling stage, molecular dynamics simulation is used to generate digital sample sets of cable insulation materials and control cabinet components, which are then imported into the quantum-enhanced digital twin unit to build the physical model. In the neural baseline calibration stage, EEG and motion data of senior technicians are collected during operation, neural activity characteristics are extracted, and a cognitive baseline model is established and stored in the brain-computer collaborative cognitive training unit. S12. Parameter association and scenario constraint setting: Associate and map key parameters of the physical model (such as insulation strength threshold) with cognitive benchmark indicators (such as attention fluctuation range) to form dynamic adaptation rules. Relevant data is synchronized to the cross-domain fault chain generation unit and used as constraints for scenario construction, achieving deep coupling between the physical model and the cognitive model. The formula for virtual and real parameter mapping coefficients: , where: It represents the mapping coefficient, ranging from -1 to 1. The larger the absolute value, the stronger the correlation. For example, K=0.85 indicates that the cable temperature is strongly positively correlated with the student's attention. Represents physical parameters and cognitive indicators The covariance of is the cable insulation resistance (unit: MΩ) or the control cabinet current (unit: A), is the trainee's attention span (unit: s) or the number of incorrect operations; Represents physical parameters The variance reflects the degree of fluctuation in the equipment status. For example, the insulation resistance variance of an old cable is 30% higher than that of a new cable. Represents cognitive indicators The variance reflects the differences in operational stability among different trainees. For example, the variance of the number of errors made by novices is twice as high as that of experienced trainees. Function: To establish a correlation model between equipment status and trainee cognition, for example, =−0.7 (negative correlation), the system automatically extends the trainee's attention assessment period when the insulation resistance decreases. The associated data is used to dynamically adjust the scenario difficulty of the cross-domain fault chain generation unit, such as matching high-risk scenarios with low cognitive load.

[0016] Preferably, the specific steps of the fault chain immersion training in step S2 are as follows: S21. Scenario Generation and Complexity Adaptation: Based on the basic model constructed in step S1, the cross-domain fault chain generation unit calls the real-time parameters of the quantum-enhanced digital twin unit and, combined with the cases of the self-evolving knowledge base, constructs a multi-linked virtual scenario. The scenario complexity is set based on the initial cognitive assessment results of the trainees fed back by the brain-computer collaborative cognitive training unit to ensure that the training difficulty matches the trainees' abilities. S22, real-time control and review analysis: The brain-computer collaborative cognitive training unit continuously monitors the trainee's status and triggers control when cognition deviates from the baseline: excessive tension is achieved by reducing scene stimulation and superimposing prompts through the holographic operation memory unit; when attention is distracted, the cross-domain fault chain generation unit adds fault branches; after training, the holographic review integrates the fault chain, operation trajectory and neural curve to provide targeted direction for memory enhancement. Preferably, the specific steps of memory enhancement and continuous optimization in step S3 are as follows: S31. Operation reinforcement and data iteration: Based on the training results of step S2, the holographic operation memory unit uses expert templates to guide trainees to repeat training using the exoskeleton device according to the weaknesses identified during the review. Force feedback parameters are adjusted based on the characteristics of the cross-domain fault chain scenario. The self-evolving knowledge base unit summarizes the operation data and updates the fault rules and specifications through federated learning. Feedback intensity adjustment formula: ,

[0017] Where: Indicates the exoskeleton feedback strength in N, which is applied through the built-in air pressure module of the glove (range 5~30N) to ensure that students can clearly perceive the difference in operating force.

[0018] Indicates the baseline feedback strength, which is the average strength of expert operation, such as the strength of cable connector crimping. ,Extracted by expert templates of holographic operational memory units; Indicates the operation deviation (unit: mm·s), directly using the calculation result of the holographic operation memory unit. The greater the deviation, the higher the feedback intensity. Indicates the complexity of the scenario, which is the number of nodes included in the fault chain, such as "cable breakage → partial discharge → control cabinet tripping". ,output in real time by the cross-domain fault chain generation unit.

[0019] Represents the scene sensitivity coefficient ,Through experimental calibration, ensure that the feedback intensity increase in complex scenarios is reasonable (avoid exceeding the students' tolerance limit); Role: Dynamically match feedback intensity to training needs, e.g. and In the difficult scenes, It will reach 1.5 times the baseline value, strengthening the muscle memory training effect. Feedback data will be used in the neural adaptation test phase to optimize the stress adaptation threshold of the cognitive baseline model; S32. Adaptation testing and system iteration: Introduce random interference factors, such as fluctuations in virtual device parameters, to conduct neural adaptation tests and evaluate the trainees' operational stability in complex environments; the test results are fed back to step S1 to optimize the cognitive benchmark model and parameter binding rules, forming a closed-loop process from training implementation to system iteration to improve training effectiveness.

[0020] The beneficial effects of the present invention are as follows: 1. The present invention constructs a micro-macro dual-domain mapping through quantum-enhanced digital twin units, allowing trainees to intuitively observe microscopic processes such as the breakage of molecular chains in cable insulation layers and the evolution of arc discharge plasma in control cabinets, and correlate them with macroscopic fault manifestations. This multi-scale visualization training solves the problem that traditional systems can only present the surface status of equipment, helping trainees understand the formation mechanism of potential risks, fundamentally improving the ability to predict hidden dangers of high-voltage equipment, and avoiding operational omissions due to a lack of in-depth risk awareness.

[0021] 2. Through the brain-computer collaborative cognitive training unit, the present invention can monitor the trainees' neural activities and operational characteristics in real time, and achieve precise regulation of cognitive load by adjusting the pressure parameters of the virtual scene (such as the intensity of the sound and light warnings of high-voltage equipment). Compared with traditional standardized training, this mechanism can effectively alleviate the decision-making delay problem of trainees in real high-voltage operations, making the training effect closer to actual working conditions, and ensuring that trainees maintain stable judgment and execution capabilities when facing high-risk operations such as 35kV cable withstand voltage testing.

[0022] 3. The present invention constructs a fault correlation map based on a graph neural network through a cross-domain fault chain generation unit, which can automatically generate chain reaction scenarios such as "cable joint defect → partial discharge → insulation breakdown → control cabinet protection malfunction"; this dynamically evolving training content makes up for the defects of isolated fault scenarios in traditional systems, enabling trainees to master the transmission laws of faults in actual production, improve the ability to analyze and deal with multi-link linkage faults, and reduce the risk of expanded accidents caused by insufficient understanding of fault correlation. BRIEF DESCRIPTION OF THE DRAWINGS

[0023] Figure 1 This is a flow chart of the digital training system based on safe production of the present invention; Figure 2 This is a flow chart of the digital training method based on safe production of the present invention. DETAILED DESCRIPTION

[0024] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of the present invention.

[0025] like Figure 1-Figure 2 As shown, an embodiment of the present invention provides a digital training system based on safe production, which includes: Quantum-enhanced digital twin unit: Based on the physical properties of the device, it builds a multi-scale digital twin, ranging from the nanometer level (cable insulation molecular chains) to the meter level (control cabinet overall structure). It uses quantum dot marking to track microscopic changes in the cable insulation layer and correlate the macroscopic behavior of the control cabinet with its microscopic mechanisms. Its high-speed interface synchronizes real-time parameters to the cross-domain fault chain generation unit, supporting dynamic scenario construction. It also receives updated data from the evolving knowledge base, continuously optimizing model accuracy and providing physical data support for the system. Brain-computer collaborative cognitive training unit: Integrates EEG and electromyography equipment to capture trainees' neural activity and operational characteristics, building a "cognition-action" model. When cognitive abnormalities are detected, it sends instructions to the holographic operation memory unit to trigger scenario adaptation, encrypts and transmits cognitive data to the self-evolving knowledge base unit, and also receives scenario parameters from the cross-domain fault chain unit to dynamically adjust the monitoring threshold to achieve collaborative training of cognition and operation. Cross-domain fault chain generation unit: Based on real-time parameters and historical cases of the self-evolving knowledge base unit, a graph neural network is used to build a device association map. Based on the trainee's operation data and virtual device status, a fault chain scenario is generated, synchronized to the holographic operation memory unit to drive rendering, and reversely output rules to the self-evolving knowledge base unit for iteration; The holographic operation memory unit uses light field imaging to record expert operations and generate holographic templates. After receiving scenario parameters from the cross-domain fault chain generation unit, the trainee and the virtual expert can "operate on the same screen." The AR device compares operation deviations, and the exoskeleton glove provides tactile guidance (vibration frequency 5-20Hz) where the thumb and index finger contact the cable crimping tool. The intensity and frequency are dynamically adjusted based on the trainee's status in the brain-computer collaborative cognitive training unit. Deviation data is uploaded to the evolutionary knowledge base unit. Self-evolving knowledge base unit: Integrates multi-source information including fault chains, holographic operations, and brain-computer collaboration, refines rules and models through federated learning, and synchronizes them to the quantum-enhanced digital twin unit to optimize the physical model after updating, providing the latest rules for the cross-domain fault chain generation unit and triggering expert template iteration.

[0026] Among them, the quantum-enhanced digital twin unit is used for: (1) Multi-scale modeling and micro-mechanism restoration: Based on the physical properties of intelligent power equipment, a multi-scale digital twin is constructed. The cable insulation layer modeling adopts the quantum dot labeling algorithm to track the trajectory of virtual quantum dots and dynamically present microscopic changes such as molecular chain breakage and crystal ablation under the action of temperature and stress. The intelligent control cabinet uses the electromagnetic simulation module to associate macroscopic behaviors such as circuit breaker action with microscopic mechanisms such as electron transitions to achieve multi-dimensional restoration of the equipment status, providing a physical basis for subsequent scenario construction. The quantum dot labeling algorithm involves implanting 1-5 nm virtual quantum dots in the digital twin model based on the molecular structure of the cable insulation material. Molecular dynamics simulation is used to calculate the binding energy between the quantum dots and the molecular chain (threshold ≥ 0.2 eV). The three-dimensional coordinates of the quantum dots are sampled at a frequency of 10 kHz, and the trajectory is smoothed using a Kalman filter to identify molecular chain breaks (trajectory mutations ≥ 5 μm / s). In the quantum dot labeling algorithm, the Kalman filter parameters are set as follows: filter gain K = 0.3, number of iterations N = 50, and trajectory mutation threshold ≥ 5 μm / s is considered as molecular chain breakage; Quantum dot diffusion coefficient formula: ,

[0027] Where: represents the quantum dot diffusion coefficient, in units of , is a core indicator that describes the activity of virtual molecular motion in the cable insulation layer. In the digital twin scenario, its value directly corresponds to the looseness of the microstructure of the insulation material. A larger value indicates a higher risk of molecular chain breakage. Indicates the initial diffusion coefficient. The base value is determined by the type of cable insulation material, such as cross-linked polyethylene cable. , rubber insulated cable ,obtained through actual measurement in the material laboratory and pre-entered into the system; The activation energy of diffusion is expressed in eV, which characterizes the energy threshold required for the molecular chain of the insulating material to break. For 10kV cables, its value is usually between 0.3 and 0.5eV, and is dynamically adjusted with the degree of material aging (the value of aged cables is 15% to 20% lower than that of new cables). represents the Boltzmann constant , used to convert temperature parameters into energy units to ensure the consistency of formula dimensions; Indicates the virtual environment temperature in K, which is synchronized with the real-time temperature of the cable production line (range 293~353K) and is collected from the extruder temperature control module through the device data interaction unit; Represents mechanical stress in MPa, corresponding to the tension during cable laying. For example, 8-12 MPa is used for overhead cables and 5-8 MPa is used for underground cables. It is calculated from the laying angle and traction force parameters in the virtual scene. It represents the stress sensitivity coefficient, dimensionless, and is calibrated by 1000 cable tensile tests (polyethylene material is taken as , reflecting the accelerating effect of mechanical force on molecular diffusion; Function: Quantify the coupling effect of temperature and mechanical stress on microscopic motion. The calculation results are used to drive the animation of electrical dendrite growth in the insulating layer of the digital twin unit ( The system triggers a partial discharge simulation (visual: AR device renders blue arc dynamics; auditory: headphones play a 1000-2000Hz buzzing sound; tactile: exoskeleton wrist provides weak electrical stimulation feedback) and pushes real-time data to the cross-domain fault chain generation unit as the starting condition for the "insulation failure → control cabinet trip" fault chain. (2) Data linkage and model iteration optimization: The unit has a built-in high-speed interface to synchronize real-time parameters such as cable insulation resistance and control cabinet temperature field to the cross-domain fault chain generation unit to support the construction of dynamic fault scenarios; at the same time, it receives device characteristic update data from the evolutionary knowledge base unit, continuously optimizes the physical accuracy of the twin model, and ensures that the virtual scenario is highly consistent with the actual device characteristics.

[0028] Among them, the brain-computer collaborative cognitive training unit is used for: (1) Multi-dimensional state monitoring and model construction: Integrate EEG acquisition and electromyography sensing equipment to capture students' neural activity and operation characteristics in real time; the EEG module identifies cognitive states such as attention and emotion through prefrontal electrodes; the electromyography equipment determines the stability of hand operation, and the core algorithm integrates data to build a "cognition-action" association model to accurately identify abnormal cognitive load in high-voltage operations and provide a basis for scene control; The EEG device uses an 8-channel frontal electrode array with a sampling frequency of 250Hz (in compliance with IEC60601-2-26 standard) and an electromyographic sensor sampling rate of 1kHz; Cognitive load index formula: ,

[0029] Where: It represents the cognitive load index, ranging from 0 to 1, with 0.7 as the critical value. In the high-voltage cable wiring training, This indicates that the trainee is at risk of operating errors, such as accidentally touching a live terminal; Indicates brain waves The amplitude ratio of theta wave (4~8Hz) to beta wave (13~30Hz). The enhanced theta wave reflects the state of anxiety. For example, when facing a 35kV device, the enhanced beta wave reflects the concentration of attention. The EEG headset is used to collect the frontal electrode array (sampling rate ; Indicates the real-time myoelectric signal amplitude in μV, which is collected by the wrist myoelectric sensor and reflects the degree of hand operation tremor (during normal operation). , when nervous ; Indicates the maximum EMG signal amplitude in μV, obtained through the trainee's initial test, such as the EMG value when gripping a cable stripper with full force, and serves as a benchmark for individual operating limits; Represents the weight coefficient , calibrated based on 100 electrician training data, because neural signals have a more significant impact on operational safety, Higher weight; Function: Real-time assessment of students' physical and mental state, when When the value is greater than 0.7, the system sends a command to the holographic operation memory unit to reduce the sound and light intensity of the high-voltage arc in the virtual scene (reduced by 30%), and triggers the expert operation holographic prompt. Time series data is encrypted and uploaded to the self-evolving knowledge base to optimize the difficulty curve of personalized training programs; (2) Data interaction and dynamic control adaptation: When cognitive anomalies are detected, a control instruction (format: [scenario ID, control type, intensity value], such as [FD-001, sound and light reduction, 30%]) is generated and sent to the holographic operation memory unit to trigger scenario adaptation. At the same time, the encrypted student cognitive data is transmitted to the self-evolving knowledge base unit to support personalized solution optimization; the scenario complexity parameters of the cross-domain fault chain generation unit are received, and the cognitive monitoring threshold is dynamically adjusted to achieve accurate matching of the training scenario and the student status.

[0030] The cross-domain fault chain generation unit is used to: (1) Association graph construction and scenario triggering: Based on the physical parameters of the quantum-enhanced digital twin unit and historical cases of the self-evolving knowledge base, a device association graph is constructed through a graph neural network; the graph includes cable production parameters and control cabinet components, and the node weights are dynamically adjusted according to the linkage relationship. When starting training, based on the trainee's operation data and the status of the virtual equipment, a chain failure scenario caused by cable laying deviation is triggered; Graph neural network node features, such as insulation resistance and temperature for cable nodes and current and circuit breaker status for control cabinet nodes; clarify the network structure: input layer (128-dimensional features) → 2-layer GCN (hidden layer 64 / 32 dimensions) → output layer (fault association weights); explain that the training data is 10,000 historical fault chains, and the loss function is cross entropy (convergence threshold ≤ 0.01); The hidden layer of the graph neural network uses the ReLU activation function, the cross entropy convergence threshold of the loss function is ≤ 0.01, and the training sample is 10,000 historical fault chain data; Fault correlation weight formula: ,

[0031] Where: Represents a device node To Node The fault association weight, which ranges from 0 to 1, is used to quantify the probability of fault conduction (e.g. show After the failure 80% chance to trigger); Indicates historical data trigger The number of faults is derived from the fault case library of the self-evolving knowledge base, such as the number of records of "abnormal pressure of cable extruder (i) → insulation layer deflection (j)"; Representation node The physical parameters of For cable parameters, such as extruder pressure MPa, For control cabinet parameters, such as PLC temperature alarm threshold ; Indicates the parameter reference value, which is the rated parameter for normal operation of the equipment, such as the rated pressure of the extruder MPa, rated temperature of control cabinet ,determined by the equipment manual; Function: Calculate the device association strength through graph neural network, for example, when =0.75, the system prioritizes generating the fault chain of "extruder pressure exceeds the standard → cable resistance is abnormal → control cabinet overcurrent protection is activated". The weight matrix is ​​synchronized to the holographic operation memory unit to drive the linkage change of the device status in the virtual scene (for example, the control cabinet indicator light flashes with the fluctuation of cable parameters); (2) Data synchronization and rule iteration: The generated dynamic fault chain data is synchronized to the holographic operation memory unit to drive scene rendering, and the fault evolution rules are reversely output to the self-evolution knowledge base unit. When the cumulative verification times of a single rule reaches 50 times and the accuracy rate is ≥90%, the rule iteration update is triggered; by continuously receiving multi-source data to optimize the association map, the consistency and timeliness of the fault scenario are ensured, and complex scenarios close to reality are provided for training.

[0032] Among them, the holographic operational memory unit is used for: (1) Expert template construction and on-screen operation: The expert operation data is recorded through light field imaging, and an interactive holographic template is formed through three-dimensional reconstruction. During training, the dynamic fault chain data of the cross-domain fault chain generation unit is received, the matching template is called, and the trainee and the virtual expert are "on-screen operation" using holographic projection. The AR device captures the trainee's movements in real time and compares them with the template to generate a deviation report; (2) Tactile guidance and data feedback: Based on the comparison results, the exoskeleton feedback device provides tactile guidance at key nodes such as cable crimping. Its intensity and frequency are dynamically adjusted according to the status of the trainees in the brain-computer collaborative cognitive training unit. The operation deviation data is packaged and uploaded to the self-evolving knowledge base unit to enrich the case library. The tactile guidance intensity is based on the feedback intensity adjustment formula (F), and the air pressure pump is controlled by a PWM signal (range 0-100kPa). When the deviation δ>100mm·s, the vibration frequency is linearly increased from 5Hz to 20Hz (in steps of 1Hz / 10mm·s). Exoskeleton tactile guidance parameters: The initial frequency for cable crimping scenarios is 10 Hz, increasing by 2 Hz for every 20 mm / s increase in delta (to a maximum of 20 Hz); the initial frequency for control cabinet wiring scenarios is 8 Hz (to a maximum of 15 Hz). Operational deviation formula: , where: Indicates the operation deviation in mm·s, which comprehensively reflects the temporal and spatial differences between trainees and experts. For example, in the cable connector crimping operation, To be qualified; The vector represents the student's operation trajectory, including the 3D position (unit: mm), the applied force (unit: N), and the tool angle (unit: °). It is collected in real time by the 6DoF sensor of the AR glasses and the force sensor of the exoskeleton glove with a sampling rate of 100Hz. Represents the expert holographic template trajectory vector, which is generated by recording the standard operation of senior electricians using a light field imaging system. For example, the force vector during cable crimping is (0,0,35)N (axial force); Trajectory Vector and The three-dimensional position coordinates take the center point of the cable connector in the virtual scene as the origin, the Z axis is the cable axis, and the unit conversion accuracy is ±0.1mm; Respectively represent the operation start time and operation end time, the unit is seconds, which is automatically recognized by the system, such as the time interval from picking up the wire stripper to completing the insulation stripping; Indicates the weight of the key node, dimensionless, set according to the operation risk level, cable terminal installation ,Control cabinet wiring ,The higher the risk, the greater the weight; Function: Accurately quantify the operational standardization, when When the exoskeleton feedback device triggers a vibration reminder (frequency varies with At the same time, a deviation analysis report is generated, such as "crimping angle deviation 3°", and the data is uploaded to the self-evolving knowledge base unit to update the fault tolerance threshold of the expert template.

[0033] Among them, the self-evolving knowledge base unit is used for: (1) Multi-source data integration and collaborative training: A distributed architecture is used to integrate multi-source information such as cross-domain fault chain cases, holographic operation deviation data, and brain-computer cognitive maps; through a federated learning framework, data is collaboratively trained while protecting privacy, to refine operation specification update rules and fault pattern recognition models; The local model of the federated learning framework was trained with 5,000 data points (Adam optimizer, learning rate 0.001). The FedAvg algorithm was used, and model parameters were transmitted using homomorphic encryption. Aggregation was triggered every 100 new data points, and the convergence condition was that the difference between two consecutive global model parameters was ≤ 1e-5. Federated learning uses the Paillier homomorphic encryption protocol with a public key length of 2048 bits. Global model aggregation is triggered every time 100 new operation data are accumulated. Federated learning framework aggregation formula: , where: Indicates global update of model parameters, including fault identification threshold, operation scoring standard, etc. For example, the qualified threshold of cable insulation resistance changes from Updated to 800 ; Indicates the The local model parameters of each plant are generated by independent training based on the training data of each plant. For example, the insulation resistance threshold of Plant A is lowered by 15% due to the humid environment. Indicates the The sample size weight of a factory is positively correlated with the number of trained people and the number of equipment types in the factory. For example, a factory with 5 cable production lines , a factory with only one production line ; The number of factories participating in federated learning will be 5 in the initial pilot phase, and will be gradually expanded to the entire industry. Data privacy protection will be achieved through encryption protocols. Function: Aggregate industry experience without sharing original data, and update Synchronize to the quantum-enhanced digital twin unit to correct insulation material aging models, such as the humidity impact coefficient in coastal plant areas, and provide the latest fault association rules for cross-domain fault chain generation units, such as the protection logic of new intelligent control cabinets; (2) Knowledge synchronization and template iteration: The updated knowledge base is synchronized to the quantum enhanced digital twin unit to optimize the physical model, providing the latest association rules for the cross-domain fault chain generation unit; based on the expert data update frequency of the holographic operation memory unit, the expert template iteration is automatically triggered to ensure that the training content always matches the industry best practices; Expert template iteration triggering conditions: Iteration is automatically started when 50 new expert operation data are accumulated and δ is less than 30mm・s (10% better than the historical template).

[0034] The embodiment of the present invention further provides a digital training method based on safe production. Based on the above system, the specific steps of the method are as follows: S1. Neural-Device Collaborative Modeling: Microscopic modeling generates digital samples of cables and control cabinets, which are then imported into the quantum-enhanced digital twin unit. Neural baseline calibration collects expert data to establish cognitive models, which are stored in the brain-computer collaborative cognitive training unit. Virtual and real parameters are bound to correlate physical and cognitive indicators, forming adaptation rules that are synchronized to the cross-domain fault chain generation unit, providing a data and rule basis for subsequent training scenarios. S2. Fault chain immersion training: The cross-domain fault chain generation unit calls the real-time parameters of the quantum-enhanced digital twin unit and the case generation scenario of the self-evolving knowledge base unit. The complexity is set according to the initial evaluation of the brain-computer collaborative cognitive training unit. During training, the brain-computer collaborative cognitive training unit monitors the cognitive state and regulates the holographic operation memory unit or the cross-domain fault chain generation unit to adjust the scenario. S3. Memory enhancement and continuous optimization: The holographic operation memory unit retrieves expert templates, combines the fault chain scenario characteristics, and strengthens muscle memory through the exoskeleton; the self-evolving knowledge base unit summarizes data and updates the model through federated learning, which is synchronized to the quantum-enhanced digital twin unit and the cross-domain fault chain generation unit. The neural adaptation test results are fed back to step S1, forming a process from training to system iteration.

[0035] Example 1: Digital training scenario case of a 35kV cable failure caused by improper crimping operation S1: Neural-Device Co-Modeling The quantum-enhanced digital twin unit generates digital samples of a 35kV cable insulation layer (cross-linked polyethylene material) and a control cabinet, tracking the molecular chain state of the insulation layer through quantum dot markers (initial diffusion coefficient D0 = 1.2×10−3μm2 / s, stable molecular chain). The brain-computer collaborative cognitive training unit collects EEG (θ / β = 0.3 when focused) and EMG (EMG = 30μV during stable operation) data from expert crimping operations to establish a cognitive benchmark model (CLI = 0.32). After binding virtual and real parameters, the association rule between "cable crimping force and trainee attention" (K = −0.6, negative correlation) is synchronized to the cross-domain fault chain generation unit.

[0036] S2: Fault Chain Immersion Training The cross-domain fault chain generation unit calls the twin data and knowledge base cases to generate the fault chain of "insufficient crimping force → insulation layer damage → partial discharge → control cabinet alarm" (correlated weight improper crimping force → partial discharge → control cabinet alarm). discharge), the scene complexity was set to S=3 based on the trainees’ initial cognitive assessment (CLI=0.5).

[0037] During training, the trainee's crimping force was too weak, and the quantum-enhanced digital twin unit detected loosening of the insulating layer's molecular chains (D = 5.2 × 10−3 μm2 / s, triggering a partial discharge simulation (visual: AR device rendering blue arc dynamics; auditory: headphones playing a 1000-2000 Hz buzzing sound; tactile: weak electrical stimulation feedback at the exoskeleton wrist)). The brain-computer collaborative cognitive training unit discovered that the trainee was nervous due to the discharge sound and light stimulation (CLI = 0.75, supercritical value), and immediately instructed the holographic unit to reduce the sound and light by 30%, and projected an expert crimping holographic prompt. After the trainee's attention was distracted, the cross-domain fault chain generation unit added a "control cabinet malfunction" branch (S = 4) to strengthen the training.

[0038] S3: Memory Enhancement and Optimization The holographic operation memory unit compares the trainee's movements and calculates the operation deviation δ=110mm·s (exceeding the qualified threshold). The exoskeleton device provides 30N tactile guidance (stronger than the baseline force of 20N) according to the deviation and scene complexity; the self-evolving knowledge base unit summarizes the operation data, updates the fault rules through federated learning (the crimping force threshold is lowered by 5%), and synchronizes it to the quantum-enhanced digital twin unit to optimize the insulation layer model; after the neural adaptation test, the results are fed back to step S1 to fine-tune the cognitive baseline model.

[0039] The specific steps of neural-device collaborative modeling in step S1 are as follows: S11. Basic model construction and feature extraction: Data fusion is completed in stages: In the microscopic modeling stage, molecular dynamics simulation is used to generate digital sample sets of cable insulation materials and control cabinet components, which are then imported into the quantum-enhanced digital twin unit to build the physical model. In the neural baseline calibration stage, EEG and motion data of senior technicians are collected during operation, neural activity characteristics are extracted, and a cognitive baseline model is established and stored in the brain-computer collaborative cognitive training unit. S12. Parameter association and scenario constraint setting: Associate and map key parameters of the physical model (such as insulation strength threshold) with cognitive benchmark indicators (such as attention fluctuation range) to form dynamic adaptation rules. Relevant data is synchronized to the cross-domain fault chain generation unit and used as constraints for scenario construction, achieving deep coupling between the physical model and the cognitive model. The formula for virtual and real parameter mapping coefficients: , where: It represents the mapping coefficient, ranging from -1 to 1. The larger the absolute value, the stronger the correlation. For example, K=0.85 indicates that the cable temperature is strongly positively correlated with the student's attention. Represents physical parameters and cognitive indicators The covariance of is the cable insulation resistance (unit: MΩ) or the control cabinet current (unit: A), is the trainee's attention span (unit: s) or the number of incorrect operations; Represents physical parameters The variance reflects the degree of fluctuation in the equipment status. For example, the insulation resistance variance of an old cable is 30% higher than that of a new cable. Represents cognitive indicators The variance reflects the differences in operational stability among different trainees. For example, the variance of the number of errors made by novices is twice as high as that of experienced trainees. Function: To establish a correlation model between equipment status and trainee cognition, for example, =−0.7 (negative correlation), the system automatically extends the trainee's attention assessment period when the insulation resistance decreases. The associated data is used to dynamically adjust the scenario difficulty of the cross-domain fault chain generation unit, such as matching high-risk scenarios with low cognitive load.

[0040] The specific steps of the fault chain immersion training in step S2 are as follows: S21. Scenario Generation and Complexity Adaptation: Based on the basic model constructed in step S1, the cross-domain fault chain generation unit calls the real-time parameters of the quantum-enhanced digital twin unit and, combined with the cases of the self-evolving knowledge base, constructs a multi-linked virtual scenario. The scenario complexity is set based on the initial cognitive assessment results of the trainees fed back by the brain-computer collaborative cognitive training unit to ensure that the training difficulty matches the trainees' abilities. S22. Real-time control and review analysis: The brain-computer collaborative cognitive training unit continuously monitors the trainee's status and triggers control when cognition deviates from the baseline: in case of excessive tension, the holographic operation memory unit reduces scene stimulation and superimposes prompts; in case of distraction, the cross-domain fault chain generation unit adds fault branches; after training, the holographic review integrates the fault chain, operation trajectory and neural curve to provide targeted direction for memory enhancement.

[0041] The specific steps of memory enhancement and continuous optimization in step S3 are as follows: S31. Operation reinforcement and data iteration: Based on the training results of step S2, the holographic operation memory unit uses expert templates to guide trainees to repeat training using the exoskeleton device according to the weaknesses identified during the review. Force feedback parameters are adjusted based on the characteristics of the cross-domain fault chain scenario. The self-evolving knowledge base unit summarizes the operation data and updates the fault rules and specifications through federated learning. Feedback intensity adjustment formula: ,

[0042] Where: Indicates the exoskeleton feedback strength in N, which is applied through the built-in air pressure module of the glove (range 5~30N) to ensure that students can clearly perceive the difference in operating force.

[0043] Indicates the baseline feedback strength, which is the average strength of expert operation, such as the strength of cable connector crimping. ,Extracted by expert templates of holographic operational memory units; Indicates the operation deviation (unit: mm·s), directly using the calculation result of the holographic operation memory unit. The greater the deviation, the higher the feedback intensity. Indicates the complexity of the scenario, which is the number of nodes included in the fault chain, such as "cable breakage → partial discharge → control cabinet tripping". ,output in real time by the cross-domain fault chain generation unit.

[0044] Represents the scene sensitivity coefficient ,Through experimental calibration, ensure that the feedback intensity increase in complex scenarios is reasonable (avoid exceeding the students' tolerance limit); Role: Dynamically match feedback intensity to training needs, e.g. and In the difficult scenes, It will reach 1.5 times the baseline value, strengthening the muscle memory training effect. Feedback data will be used in the neural adaptation test phase to optimize the stress adaptation threshold of the cognitive baseline model; S32. Adaptation testing and system iteration: Introduce random interference factors, such as fluctuations in virtual device parameters, to conduct neural adaptation tests and evaluate the trainees' operational stability in complex environments; the test results are fed back to step S1 to optimize the cognitive benchmark model and parameter binding rules, forming a closed-loop process from training implementation to system iteration to improve training effectiveness.

[0045] It should be noted that, in this document, relational terms such as first and second, etc., are used only to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any actual relationship or order between these entities or operations. Moreover, the terms "comprises," "comprising," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that includes a list of elements includes not only those elements but also other elements not explicitly listed, or elements inherent to such process, method, article, or apparatus.

[0046] While embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that various changes, modifications, substitutions, and variations may be made to these embodiments without departing from the principles and spirit of the invention, and that the scope of the invention is defined by the appended claims and their equivalents.

Claims

1. A digital training system based on safe production, characterized by: The system includes: Quantum-enhanced digital twin unit: Builds a digital twin, tracks microscopic changes in cable insulation through quantum dot marking, correlates macroscopic behavior and microscopic mechanisms of the control cabinet, and synchronizes real-time parameters to the cross-domain fault chain generation unit; Brain-computer collaborative cognitive training unit: Integrates EEG and electromyography equipment to capture students' neural activity and operational characteristics, builds a cognitive-action model, and sends instructions to the holographic operation memory unit when cognitive abnormalities are detected. This encrypts and transmits cognitive data to the self-evolving knowledge base unit, dynamically adjusting the monitoring threshold. Cross-domain fault chain generation unit: Based on real-time parameters, a graph neural network is used to build a device association map. Based on the trainee's operation data and virtual device status, a fault chain scenario is generated. The scenario parameters are synchronized to the holographic operation memory unit, and the rules are output to the self-evolving knowledge base unit. Holographic Operation Memory Unit: This unit records expert operations through light field imaging and generates holographic templates. After receiving scenario parameters from the cross-domain fault chain generation unit, it enables students and virtual experts to operate on the same screen. AR equipment compares operation deviations, and the exoskeleton device provides tactile guidance. The intensity and frequency are adjusted according to the student's status in the brain-computer collaborative cognitive training unit. Self-evolving knowledge base unit: Integrates multi-source information including fault chains, holographic operations, and brain-computer collaboration, refines rules and models through federated learning, and after updating, synchronizes them to the quantum-enhanced digital twin unit to optimize the physical model and trigger expert template iteration.

2. The digital training system based on safe production according to claim 1, characterized in that: The quantum-enhanced digital twin unit is used to: (1) Multi-scale modeling and micro-mechanism restoration: Based on the physical properties of intelligent power equipment, a multi-scale digital twin is constructed. The cable insulation layer modeling adopts the quantum dot labeling algorithm to track the trajectory of virtual quantum dots and dynamically present the microscopic changes including molecular chain breakage and crystal ablation under the action of temperature and stress. The intelligent control cabinet uses the electromagnetic simulation module to associate the macroscopic behavior of the circuit breaker action with the microscopic mechanism of electronic transition. (2) Data linkage and model iteration optimization: The unit has a built-in high-speed interface, which synchronizes the real-time parameters including cable insulation resistance and control cabinet temperature field to the cross-domain fault chain generation unit, and receives the device characteristic update data from the evolutionary knowledge base unit at the same time.

3. The digital training system based on safe production according to claim 2, characterized in that: The brain-computer collaborative cognitive training unit is used for: (1) Multi-dimensional state monitoring and model building: Integrate EEG acquisition and electromyography sensing equipment to capture students' neural activity and operational characteristics in real time. The EEG module uses frontal lobe electrodes to identify cognitive states including attention and emotion; the electromyography equipment determines the stability of hand operation, and the integrated data is used to build a cognitive-action association model. (2) Data interaction and dynamic control adaptation: When cognitive anomalies are detected, control instructions are generated and sent to the holographic operation memory unit to trigger scene adaptation. At the same time, the encrypted student cognitive data is transmitted to the self-evolving knowledge base unit, which receives the scene complexity parameters of the cross-domain fault chain generation unit and dynamically adjusts the cognitive monitoring threshold.

4. The digital training system based on safe production according to claim 3, characterized in that: The cross-domain fault chain generating unit is used to: (1) Association graph construction and scenario triggering: A device association graph is constructed through a graph neural network. The graph includes cable production parameters and control cabinet components. The node weights are dynamically adjusted according to the linkage relationship. When training is started, a chain failure scenario is triggered based on the trainee's operation data and virtual equipment status, such as a chain failure caused by cable laying deviation. (2) Data synchronization and rule iteration: The generated dynamic fault chain data is synchronized to the holographic operation memory unit to drive scene rendering, and the fault evolution rules are output in reverse to the self-evolution knowledge base unit.

5. The digital training system based on safe production according to claim 4, characterized in that: The holographic operational memory unit is used for: (1) Expert template construction and on-screen operation: The expert operation data is recorded through light field imaging, and an interactive holographic template is formed through three-dimensional reconstruction. During training, the dynamic fault chain data of the cross-domain fault chain generation unit is received, the matching template is called, and the trainee and the virtual expert are operated on the same screen using holographic projection. The AR device captures the trainee's movements in real time and compares them with the template to generate a deviation report; (2) Tactile guidance and data feedback: Based on the comparison results, the exoskeleton feedback device provides tactile guidance at key nodes including cable crimping. Its intensity and frequency are dynamically adjusted according to the status of the trainees in the brain-computer collaborative cognitive training unit.

6. The digital training system based on safe production according to claim 5, characterized in that: The self-evolving knowledge base unit is used to: (1) Multi-source data integration and collaborative training: A distributed architecture is used to integrate multi-source information including cross-domain fault chain cases, holographic operation deviation data, and brain-computer cognitive maps. Through a federated learning framework, collaborative training data is used to refine operation specification update rules and fault pattern recognition models. (2) Knowledge synchronization and template iteration: The updated knowledge base is synchronized to the quantum enhanced digital twin unit to optimize the physical model, and the expert template iteration is automatically triggered according to the expert data update frequency of the holographic operation memory unit.

7. A digital training method based on safe production, based on the system of claim 6, characterized in that: The specific steps of this method are as follows: S1. Neural-device collaborative modeling: Microscopic modeling generates digital samples of cables and control cabinets, which are then imported into the quantum-enhanced digital twin unit. Neural baseline calibration collects expert data to establish cognitive models that are stored in the brain-computer collaborative cognitive training unit. Virtual and real parameters are bound to correlate physical and cognitive indicators, forming adaptation rules that are synchronized to the cross-domain fault chain generation unit. S2. Fault chain immersion training: The cross-domain fault chain generation unit calls the real-time parameters of the quantum-enhanced digital twin unit and the case generation scenario of the self-evolving knowledge base unit. The complexity is set according to the initial evaluation of the brain-computer collaborative cognitive training unit. During training, the brain-computer collaborative cognitive training unit monitors the cognitive state and triggers regulation when the cognition deviates from the baseline; S3. Memory enhancement and continuous optimization: The holographic operation memory unit retrieves expert templates, combines the fault chain scenario characteristics, and strengthens muscle memory through the exoskeleton; the self-evolving knowledge base unit summarizes data and updates the model through federated learning, which is synchronized to the quantum enhanced digital twin unit and the cross-domain fault chain generation unit, and the neural adaptation test results are fed back to step S1.

8. The digital training method based on safe production according to claim 7, characterized in that: The specific steps of neural-device collaborative modeling in step S1 are as follows: S11. Basic model construction and feature extraction: Data fusion is completed in stages: in the microscopic modeling stage, molecular dynamics simulation is used to generate digital sample sets of cable insulation materials and control cabinet components, which are then imported into the quantum-enhanced digital twin unit to build the physical model; in the neural baseline calibration stage, EEG and motion data of the expert are collected during operation to establish a cognitive baseline model and store it in the brain-computer collaborative cognitive training unit; S12. Parameter association and scenario constraint setting: Associate and map the key parameters of the physical model with cognitive benchmark indicators to form dynamic adaptation rules; synchronize relevant data to the cross-domain fault chain generation unit as constraints for scenario construction.

9. The digital training method based on safe production according to claim 8, characterized in that: The specific steps of the fault chain immersion training in step S2 are as follows: S21. Scenario generation and complexity adaptation: Based on the basic model constructed in step S1, the cross-domain fault chain generation unit calls the real-time parameters of the quantum-enhanced digital twin unit and combines the cases of the self-evolving knowledge base to build a virtual scenario. The scenario complexity is set according to the initial cognitive assessment results of the trainees fed back by the brain-computer collaborative cognitive training unit; S22. Real-time control and review analysis: The brain-computer collaborative cognitive training unit continuously monitors the student's status and triggers control when cognition deviates from the baseline: in the case of excessive tension, the holographic operation memory unit reduces scene stimulation and superimposes prompts; in the case of distraction, the cross-domain fault chain generation unit adds fault branches.

10. The digital training method based on safe production according to claim 9, characterized in that: The specific steps of memory enhancement and continuous optimization in step S3 are as follows: S31, Operation reinforcement and data iteration: Based on the training results of step S2, the holographic operation memory unit calls the expert template to guide the trainee to repeat the training through the exoskeleton device, and the force feedback parameters are adjusted according to the characteristics of the cross-domain fault chain scenario; The self-evolving knowledge base unit aggregates operational data and updates fault rules and specifications through federated learning; S32, Adaptation test and system iteration: Introduce random interference factors, such as fluctuations in virtual device parameters, conduct neural adaptation tests, evaluate the trainees' operational stability in complex environments, and feed the test results back to step S1.

Images