Gas safety emergency training system based on VR

Abstract

The invention relates to the technical field of training simulation, and discloses a VR-based gas safety emergency training system, which comprises a three-dimensional scene construction module, an interactive data acquisition module, an interactive data processing module, an examination data analysis module and an examination evaluation module, entity drilling is replaced, the same scene can be repeatedly trained for infinite times, and the training cost is remarkably reduced; the VR technology provides multi-sensory stimulation, the intuitive cognition of students on danger is enhanced, the safety awareness and the emergency response capability are effectively improved, and no danger exists; by collecting operation data of students, the system automatically calculates key coefficients such as equipment operation precision, process compliance, disposal timeliness and path planning rationality, and scientific quantification and accurate scoring of training effects are achieved; and automatic grading evaluation is carried out according to a grading result, and a customized remedy module is triggered for students with insufficient abilities, so that a'training-assessment-intervention 'closed loop is formed, and the overall training efficiency is improved.

Description

Technical Field

[0001] The present invention relates to the field of training simulation technology, and more particularly to a VR-based gas safety emergency training system. Background Art

[0002] Traditional employee safety emergency training is limited by various objective conditions such as venue, faculty, capabilities, and time. Most of it is based on theoretical knowledge or video observation. To avoid the risks of emergency drills, they can only be simple simulations, which are far from the actual situation. Companies spend a lot of energy, time and investment costs, and the training process is boring and the training results are not satisfactory. Specifically, there are the following shortcomings: Physical drills must realistically simulate gas leaks or fires, posing risks of burns, explosions, and shock injuries, as well as equipment damage. Dedicated training venues need to be built, which consumes consumables such as gas and fire-fighting equipment. The cost of a single training session is high and cannot be reused. Traditional training relies on verbal explanations or graphic illustrations, lacking multi-sensory stimulation. Trainees' understanding of dangerous scenarios remains at a theoretical level, and their emergency response capabilities are limited. Relying on manual observation and scoring makes it difficult to quantify key indicators such as operational accuracy and timeliness, and is easily affected by the evaluator's subjective judgment; After traditional assessments, no personalized tutoring plan is formed, students with weak abilities cannot receive targeted intensive training, and the overall training efficiency is low.

[0003] Therefore, a method with no safety hazards, low cost, multi-dimensional perception, scientific evaluation and closed-loop improvement is needed to solve the above problems. Summary of the Invention

[0004] In order to overcome the above-mentioned defects of the prior art, the present invention provides a VR-based gas safety emergency training system to solve the problems existing in the above-mentioned background technology.

[0005] To achieve the above objectives, the present invention provides the following technical solutions: a VR-based gas safety emergency training system. The VR-based gas safety emergency training system of the present invention uses a three-dimensional scene construction module to create virtual scenes such as gas leaks and fire escapes, and supports multi-scene switching and parameter adjustment. The interactive data acquisition module records trainees' operational behavior in real time. The interactive data processing module analyzes key indicators such as operational accuracy, process compliance, timeliness, and path planning. The assessment data analysis module comprehensively calculates and generates training scores. The assessment evaluation module classifies the scores and implements intervention measures to form a closed-loop training system. Specifically, the system includes: 3D scene construction module: used to build virtual 3D scenes of gas leakage and fire escape, supporting intelligent switching of multiple scenes and real-time parameter adjustment; Interactive data acquisition module: used to collect multimodal data of trainees' interactions with 3D scenes during safety emergency training; Interaction data processing module: cleans and processes the collected interaction data, calculates the equipment operation accuracy coefficient, process compliance coefficient, disposal time efficiency coefficient and path planning coefficient; Assessment data analysis module: used to integrate and calculate the processed interaction coefficients to generate safety emergency training scores; Assessment and evaluation module: used to conduct graded assessment of safety emergency training scores and take training intervention measures for trainees with insufficient grades.

[0006] Technical effects and advantages of the present invention: 1. This invention simulates high-risk scenarios such as gas leaks, fires, and explosions in a virtual environment. Trainees can conduct emergency response training without actual danger, thus avoiding personal injury and equipment damage that might be caused by real-life drills.

[0007] 2. This invention replaces the venues, equipment, and consumables required for physical drills, significantly reducing training costs. The same scenario can be repeated an unlimited number of times, supporting standardized assessments for large-scale personnel.

[0008] 3. The VR technology of this invention provides multi-sensory stimulation of vision, hearing, and touch, enhancing students' intuitive understanding of danger and effectively improving their safety awareness and emergency response capabilities.

[0009] 4. By collecting trainees' operation data, the system automatically calculates key coefficients such as equipment operation accuracy, process compliance, disposal timeliness and path planning rationality, thereby achieving scientific quantification and accurate scoring of training effects.

[0010] 5. The present invention automatically conducts graded assessments based on the scoring results and triggers customized tutoring modules for students with insufficient abilities, forming a closed loop of "training-assessment-intervention" to improve overall training efficiency. BRIEF DESCRIPTION OF THE DRAWINGS

[0011] Figure 1 It is a structural block diagram of the present invention.

[0012] Figure 2 Flowchart of the present invention. DETAILED DESCRIPTION

[0013] The technical solutions of the present invention will be described clearly and completely below in conjunction with the drawings in the present invention. In addition, the forms of the various structures described in the following embodiments are merely examples. The automatic unloading device for a rotary kiln with a self-cooling function involved in the present invention is not limited to the various structures described in the following embodiments. All other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of the present invention.

[0014] Reference Figure 1 The present invention provides a VR-based gas safety emergency training system, which includes a three-dimensional scene construction module, an interactive data acquisition module, an interactive data processing module, an assessment data analysis module and an assessment evaluation module.

[0015] Reference Figure 2 The specific implementation steps of the present invention include the following steps: S1. Build virtual 3D scenes of gas leakage and fire escape, supporting intelligent switching of multiple scenes and real-time parameter adjustment.

[0016] It should be noted that the 3D scene construction module uses existing 3D modeling tools to create detailed models of gas leaks and fire escape virtual environments, simulating the dynamic effects of smoke diffusion and fire spread. It also supports intelligent switching of multiple scenes and real-time adjustment of wind direction and temperature parameters, and conducts panoramic digital virtual simulation training around risk identification, hidden danger investigation, dangerous operation management, and emergency rescue operations in the gas industry. S2. Collect multimodal data of trainees’ interactions with 3D scenes during safety emergency training.

[0017] It should be noted that based on the VR head-mounted display device and touch interactive system, the interactive data acquisition module captures the trainees' multi-modal operation data of equipment operation, protective wear, decision path, action sequence and position coordinates in the virtual scene in real time, providing raw input data for subsequent analysis. S3. Clean and process the collected interaction data, and calculate the equipment operation accuracy coefficient, process compliance coefficient, disposal time efficiency coefficient and path planning coefficient.

[0018] It should be noted that the calculation of the equipment operation accuracy coefficient is as follows: ; Among them, S is the equipment operation accuracy coefficient, which quantitatively evaluates the accuracy and standardization of trainees' operation of key equipment valves, fire extinguishers and pipeline tools in a virtual environment. The value range is 0-1, where 1 indicates perfect compliance with the standard.

[0019] F is the valve operation accuracy coefficient, which evaluates the standardization of the valve closing operation and is the weighted sum of the rotation angle score and the switching timing score.

[0020] The rotation angle score = 1 - |actual number of rotations - standard number of rotations| / standard number of rotations, which indicates the degree of match between the actual number of rotations and the standard number of rotations. It should be noted that the number of rotations here can be a decimal. The rotation angle error directly affects the sealing of the valve. The angle deviation leads to an increased gas leakage risk index, so it is given a higher weight, ranging from 0.55 to 0.6.

[0021] The switching timing score is based on whether the valve closing operation is completed within the specified time. If it is completed on time, the full score is 1 point, and the closing delay is deducted proportionally; the timing error can be remedied through subsequent emergency steps, and the weight range is between 0.4-0.45.

[0022] Valve operation errors are the main cause of gas leaks and household gas accidents. Gas valves must strictly follow specifications such as "rotate three times to confirm locking." Otherwise, the system cannot trigger safety confirmation. Therefore, they are given the highest weight, and the weight ωf ranges from 0.45 to 0.5.

[0023] M is the fire extinguisher operation accuracy coefficient, which evaluates the standardization of fire extinguisher use and is the weighted sum of the tilt angle score and the spray coverage score.

[0024] The criterion for judging the tilt angle deviation score is whether the deviation angle exceeds the limit. If it is less than or equal to the set deviation, it will be scored as the full score of 1 point, and if it is greater than the set deviation, it will be directly scored as 0 point. That is, if the deviation exceeds the limit, it will be directly judged as an error in use. The spray coverage score judges the fire extinguishing effect according to the proportion of fire source covered. Coverage x*100% will get x points. It should be noted that if the coverage is less than 50%, it will directly get 0 points. The impact of angle error and insufficient coverage on the fire extinguishing result is equivalent, so equal weight distribution is adopted.

[0025] Fire extinguisher operation directly affects the initial fire control effect. Gas fire spreads quickly, and operational deviations can cause the fire to get out of control. The weight ωm ranges from 0.25 to 0.3.

[0026] G is the tool operation accuracy, which evaluates the standardization of pipeline maintenance operations and is the weighted sum of the torque error score and the disassembly sequence score.

[0027] The torque error score = 1-|actual torque-standard torque| / standard torque, which indicates the degree of match between the actual torque and the standard value. The torque accuracy of pipeline inspection tools directly affects the sealing performance. Insufficient torque can cause gas leakage, while excessive torque can damage the equipment threads or sealing surfaces, inducing explosion risks. Therefore, it has a high weight, with a value range of 0.65-0.7.

[0028] Disassembly sequence score: 1 point is awarded for correct steps, and points are deducted proportionally according to the number of incorrect steps. In certain scenarios, incorrect sequence can lead to chain risks, but such errors can usually be corrected in time through system prompts. The weight range is between 0.3-0.35.

[0029] Pipeline maintenance requires precise torque control to avoid equipment damage or seal failure. Incorrect disassembly sequence will cause secondary leakage risk. The value range of the weight ωg is between 0.2-0.25.

[0030] It should be noted that the calculation of process compliance coefficient is as follows: ; Where L is the process compliance coefficient, which reflects the trainees' mastery of the process by verifying their compliance with operating procedures and wearing of protective equipment.

[0031] B is the step accuracy coefficient. The standard process is "valve closing - ventilation - detection - alarm - evacuation". The step accuracy coefficient = Σ (step weight × operation accuracy rate). The weight is allocated according to the risk level.

[0032] The primary priority is to block the gas source to prevent continued leakage from causing combustion / explosion. Failure to do so doubles the risk of subsequent operational failure, and the probability of explosion increases if valves are not closed during the initial stages of a leak. Therefore, closing the valve has the highest weight, ranging from 0.3 to 0.35. Reduce gas concentration to below the lower explosion limit. The specification requires the ventilation system to be activated within 15 seconds after fire compartment confirmation. Delayed ventilation will lead to the accumulation of combustible gas, increasing the risk of reaching the explosion limit concentration. Ventilation has a weight of 0.25 to 0.3. Verifying environmental safety determines subsequent actions. Methane and oxygen concentrations must be tested. If they do not meet the standards, operations other than evacuation are prohibited. Errors in test data can lead to secondary accidents, so the weight is between 0.15 and 0.2. The specification requires a two-level alarm mechanism. Delayed alarms will delay external rescue and expand the scope of the accident. The weight is between 0.1 and 0.15. When the detected concentration exceeds the standard or the leak cannot be controlled, evacuation must be completed within 30 seconds. The weight is low because it is a passive risk avoidance action, but failure to perform the action will directly result in casualties. The weight is between 0.1 and 0.15.

[0033] Emergency operations directly affect the speed of accident spread. Statistics show that standardized operations can reduce accident losses, and the weight of the step accuracy coefficient ωb is between 0.6-0.7. W is the protective equipment coefficient, which is the weighted sum of the wearing integrity coefficient, the fit compliance rate and the wearing response time.

[0034] The wearing integrity coefficient = Σ (equipment weight × correct wearing rate). The equipment weight is determined by the importance of the equipment. The weight of respiratory protection equipment is between 0.25-0.35; the weight of head protection equipment is between 0.15-0.25; the weight of torso protection equipment is between 0.2-0.25; the weight of hand and foot protection equipment is between 0.15-0.2; the weight of eye and face protection equipment is between 0.05-0.15, and it is dynamically adjusted according to different scenarios. Wearing integrity is the main factor, and the weight of the wearing integrity coefficient is between 0.5-0.6.

[0035] For the quantitative detection of respirators, if the leakage rate is less than 5%, 1 point will be awarded; if it is between 5% and 10%, 0.5 point will be awarded; if it is more than 10%, 0 point will be awarded; the weight ratio is between 0.2 and 0.25.

[0036] If the time from the alarm to the completion of equipment donning is ≤ 60 seconds, 1 point will be awarded, and 0.1 point will be deducted for every 10 seconds exceeding the limit; the weight ratio is between 0.2-0.25.

[0037] Equipment integrity is a prerequisite for entering a hazardous area, but it is a basic capability item with a weight ωw between 0.3-0.4. The ωw weight can be increased when the leak is upgraded. It should be noted that the calculation of the disposal time efficiency coefficient is as follows: ; Where C is the timeliness coefficient of the response, which quantifies the effectiveness of the response action within the time window.

[0038] Y is the response delay compliance coefficient, specifically: ; Y is the response delay compliance coefficient, which evaluates whether the time from when the system alarm is triggered to when the user performs the first operation meets security regulations.

[0039] ts is the actual extended time, and tb is the standard delay time. The standard delay time is as follows: gas leakage scenario ≤ 10 seconds, the response time limit after the combustible gas alarm is triggered; emergency shut-off operation ≤ 3 seconds, such as valve closure, which must be activated within 3 seconds after the alarm is triggered; other scenarios are dynamically set according to the equipment type; 0.1 points will be deducted for every 1 second the actual delay exceeds the standard value, until 0 points are deducted.

[0040] Response delay compliance directly affects the initial risk control capability. A 10-second timeout in leakage response can double the explosion risk. It has the highest weight, and the weight ωy ranges from 0.35 to 0.4.

[0041] D is the process deviation compliance coefficient, specifically: ; Where D is the process deviation compliance coefficient, which quantifies the degree of deviation between the operation time of the entire process and the standard time.

[0042] Ts is the actual duration, the total time actually consumed by the operation process; Tb is the standard duration, the preset standard duration, which is dynamically set based on safety regulations or industry benchmarks; the standard duration setting is 180 seconds for the entire leakage treatment process, including valve closing, ventilation, and detection steps; the fire extinguishing operation is 60 seconds or less, which is the time requirement for the fire extinguisher spray coverage. |Actual duration − Standard duration| represents the absolute value of the duration error, ignoring the directionality of advance or delay. The deviation ratio converts the absolute deviation into a ratio relative to the standard duration, facilitating cross-scenario comparison. The min function limits the deviation ratio to 1, ensuring that D ≥ 0. When the deviation ratio is greater than 1, min outputs 1, and D = 0.

[0043] D=1 means that the actual duration is equal to the standard duration, with zero deviation and full compliance; D close to 0 means that the deviation is too large, the actual duration far exceeds the standard, and the compliance is low.

[0044] Overtime in the entire process will expand the scope of the accident, and it is necessary to balance efficiency and operational integrity. The value range of the weight ωd is between 0.25-0.3. E is the emergency correction coefficient, which evaluates the speed and effectiveness of corrections after erroneous operations during emergency response and quantifies the efficiency from error identification to complete safety recovery. A higher value indicates a stronger correction capability.

[0045] Emergency correction coefficient = correction quality coefficient * standard time correction / actual correction time. The standard correction time is the ideal time threshold preset based on the scenario. When the threshold is exceeded, the efficiency decreases. The actual correction time is the actual time from the user discovering the error to completing the correction. The correction quality coefficient is assigned according to the degree of residual risk. It is 1.0 for complete elimination of risk and 0.8 for partial control to ensure that the results include safety integrity assessment.

[0046] The speed of correction determines the probability of a secondary accident. Standard correction delays will significantly increase the chain reaction risk. The weight ωe ranges from 0.2 to 0.25. H is the interruption recovery coefficient, which quantifies the timeliness of recovery operations after a sudden interruption. The interruption scenarios include equipment failure and new risk emergencies. The recovery actions include resetting the safe state and restarting the operation process.

[0047] When the actual recovery time is ≤30 seconds, H is 1. The standard response time requirement for the gas emergency shut-off device is ≤30 seconds. If the operation can be restored within this time limit after the interruption, it is judged to be fully compliant. When the actual recovery time is greater than 30 seconds, the interruption recovery capability coefficient = 1-(actual recovery time-30) / 60. The deduction slope after the timeout is 1 / 60 points for each second exceeding the limit. This is based on the tolerance ratio of the total operation time standard of ≤180 seconds for the entire process. That is, the time consumed for interruption recovery does not exceed 1 / 3 of the total process.

[0048] Interruption recovery is a low-frequency event, but recovery timeout will aggravate secondary disasters. The value range of the weight ωh is between 0.1 and 0.15.

[0049] It should be noted that the calculation of the path planning coefficient is as follows: ; Where J is the path planning coefficient, which comprehensively evaluates the rationality of escape path selection and the accuracy of collaborative task execution. Its value range is between 0 and 1, where 1 represents the optimal value.

[0050] P is the path deviation compliance coefficient, specifically: ; Where P is the path deviation compliance coefficient, which quantifies the spatial deviation between the user's actual path and the optimal path.

[0051] Pa(t) represents the trainee's three-dimensional spatial coordinates at time t. The user's location information is collected in real time through the VR positioning device to form an actual path trajectory sequence. Po(t) is the three-dimensional coordinate corresponding to the optimal escape path pre-generated by the system at time t. It should be noted that the optimal escape path here is based on the algorithm in the existing technology, taking into account the path length, avoidance of dangerous sources such as gas leaks, and complex terrain factors. The numerator in the formula is the Euclidean norm, which calculates the straight-line distance between two points and quantifies the real-time spatial deviation between the user's position and the optimal path.

[0052] T is the total time of path tracking, ensuring that the deviation calculation covers the escape process and preventing partial path deviation from affecting the overall evaluation; Dmax is the maximum allowable deviation threshold, which serves as the standardized deviation value. When the threshold is exceeded, P is forced to 0, and the operation is directly judged as failed.

[0053] The degree of deviation from the escape path directly determines the emergency efficiency. Three-dimensional spatial coordinate tracking shows that deviation from the optimal path exceeding the threshold will significantly increase escape time and risk. The high weight reflects its fundamental impact on overall safety. The value range of the weight ωp is between 0.45 and 0.5.

[0054] X is the collaboration accuracy coefficient, specifically: ; Where X is the collaboration accuracy coefficient, which quantifies the consistency and accuracy of multi-user collaborative instruction execution, ensuring that team operations meet preset specifications.

[0055] R is the number of correctly executed instructions, representing the number of instructions correctly executed by the user team in the virtual environment. For example, after the main control trainee issued the "close the valve" instruction, other trainees completed the operation accurately. Z is the total number of instructions, representing the total number of all instructions issued by the system in the training scenario, including correct and incorrect executions. The ratio represents the accuracy of instruction execution, which directly reflects the team's ability to coordinate key operations. The higher the ratio, the better the team collaboration consistency.

[0056] △t is the average command response delay time, that is, the average time difference from the issuance of a command to the user's first operation; tmax is the maximum allowable delay time, which represents the maximum allowable delay time threshold, that is, the response time limit set by the system; the ratio is a dynamic correction for timeliness, identifying potential risks caused by communication lags and quantifying the severity of the delay, with a value range between 0 and 1; 1-△t / tmax is the delay penalty factor, with a value range between 0 and 1, close to 1 if the response is timely and close to 0 if the delay exceeds the limit.

[0057] In a multi-user scenario, the accuracy of instruction delivery affects the consistency of team responses, and incorrect execution leads to chain risks. The weight ωx is second because it relies on team collaboration rather than individual ability. The value range of the weight ωx is between 0.3 and 0.35.

[0058] Q is the path safety compliance coefficient, specifically: ; Q is the path safety compliance coefficient, which means ensuring that the trainee's movement trajectory complies with preset safety specifications during path planning, and quantifying the degree of safety by real-time monitoring of the distance between the trainee and dangerous sources such as obstacles and leakage points.

[0059] d(t) is the real-time three-dimensional distance between the user and the nearest obstacle or hazard at time t; min(d(t)) represents the minimum distance between the user and the obstacle or hazard during the entire escape process, identifies the critical point on the path closest to the hazard, and reflects the global safety of the path; da represents the preset minimum safety distance threshold, which sets the safety boundary based on the scenario risk; the min function constrains the upper limit of Q to 1 to avoid inflated scores due to distances far exceeding the threshold. When the minimum distance ≥ da, Q = 1 indicates the optimal state, otherwise points are deducted proportionally.

[0060] Although the safe distance between the path and the source of danger is important, it can be predicted and avoided through the VR physics engine, and there is a large space for dynamic adjustment, so the weight is the lowest, and the value range of the weight ωq is between 0.2-0.25. S4. The processed interaction coefficients are integrated and calculated to generate a comprehensive score for safety emergency training.

[0061] The specific scoring of safety emergency training is as follows: ; A is the comprehensive score of emergency training, which comprehensively evaluates the emergency response capabilities of trainees through multi-dimensional coefficients.

[0062] S is the equipment operation accuracy coefficient, which directly determines the effectiveness of various equipment controls. Any mistakes will lead to escalation of accidents. Most accidents are directly caused by improper equipment operation, so it has the highest weight. The value range of weight α is between 0.35 and 0.4.

[0063] L is the process compliance coefficient. Omission of key steps or incorrect step sequence will lead to systemic risks. Standardized processes can reduce the probability of secondary accidents. Process errors can easily lead to chain failures, so the weight is second. The value range of weight β is between 0.25-0.3.

[0064] C is the disposal time efficiency coefficient. The response time directly affects the golden rescue window. Time delay in leakage accidents increases the risk of explosion. Time efficiency is exponentially related to risk, but it is not a direct cause. Therefore, the value range of the weight γ is between 0.15 and 0.2.

[0065] J is the path planning coefficient. If the path deviates from the optimal route or the safety distance is insufficient, the risk of casualties will be significantly increased. A reasonable path can improve evacuation efficiency. The weight focuses on optimizing the survival rate. The value range of the weight δ is between 0.15 and 0.2.

[0066] S5. Conduct a graded assessment of the comprehensive scores of safety emergency training and take training intervention measures for trainees with insufficient grades.

[0067] The comprehensive score of safety emergency training is graded and evaluated as follows: When a1<A≤100, it is an excellent grade; When a2<A≤a1, it is a good grade; When a3<A≤a2, it is a medium level; When a4<A≤a3, it is a passing grade; When 0<A≤a4, it is a failing grade; The value range of a1 is between 89-90, the value range of a2 is between 79-80, the value range of a3 is between 69-70, and the value range of a4 is between 59-60.

[0068] The specific training intervention measures for students with insufficient grades are as follows: Outstanding students will be given priority to participate in high-risk emergency response tasks, granted on-site command authority, and recommended to participate in national emergency rescuer qualification certification; Provide bonuses or training resources, such as advanced skills training opportunities, and include candidates in the annual core performance appraisal; Serve as an internal training instructor and record standardized operation videos for the team to learn.

[0069] We provide targeted reinforcement for students who perform well, and carry out VR simulation training to address weaknesses such as insufficient equipment operation accuracy. We conduct refresher training once a month until students meet the standards. Participate in actual combat and be assigned to secondary tasks, such as material dispatch, to gain experience in complex scenarios; Second-class bonuses will be awarded, and priority will be given to the qualification assessment of social emergency forces.

[0070] For mid-level trainees, mandatory refresher training is conducted, requiring them to leave their posts and participate in full-process closed-loop training, focusing on improving equipment operation accuracy and process compliance. Those who fail the assessment will be demoted. Reduce authority and suspend high-risk operation qualifications, such as gas valve operation, and only allow the execution of auxiliary tasks; Monthly performance deductions will be made and annual performance appraisal qualifications will be cancelled.

[0071] For qualified students, they will be suspended for special training and participate in "one-on-one" corrective training, with 2 hours of additional training per day and submitting operation logs, which will be signed and confirmed by the instructor; Arrange emergency psychological stress resistance courses to eliminate hesitation or fear in operations; A warning will be given, and if the re-evaluation score is still ≤a3, the person will be transferred from the emergency post.

[0072] For those who fail the test, their positions will be frozen, all emergency-related duties will be suspended immediately, and they will be required to re-take pre-job qualification training; Individuals sign a commitment letter for improvement and submit weekly training reports; team instructors are held jointly responsible, and departmental emergency plans are re-filed; Those who fail the assessment for n consecutive times will have their labor contracts terminated or be transferred according to law. Through the description of the above embodiments, those skilled in the art can clearly understand that the various embodiments of the present application can be implemented by means of software or software combined with a necessary general hardware platform, and of course can also be implemented by hardware functions; based on such understanding, the technical solution of the present application can essentially be embodied in the form of a software product or the part that contributes to the prior art. The software product is stored in a storage medium and includes a number of instructions for enabling a computer device, such as but not limited to a personal computer, a server, or a network device, to execute all or part of the steps of the method described in any embodiment of the present application.

[0073] The above describes exemplary embodiments of the present application. It should be understood that the above exemplary embodiments are not restrictive but illustrative, and the scope of protection of the present application is not limited thereto. It should be understood that those skilled in the art can modify and vary the embodiments of the present application without departing from the spirit and scope of the present application, and these modifications and variations should be within the scope of protection of the present application.

Claims

1. A VR-based gas safety emergency training system, characterized in that: Specifically include: 3D scene construction module: used to build virtual 3D scenes of gas leakage and fire escape, supporting intelligent switching of multiple scenes and real-time parameter adjustment; Interactive data acquisition module: used to collect multimodal data of trainees' interactions with 3D scenes during safety emergency training; Interaction data processing module: cleans and processes the collected interaction data, calculates the equipment operation accuracy coefficient, process compliance coefficient, disposal time efficiency coefficient and path planning coefficient; Assessment data analysis module: used to integrate and calculate the processed interaction coefficients to generate safety emergency training scores; Assessment and evaluation module: used to conduct graded assessment of safety emergency training scores and take training intervention measures for trainees with insufficient grades.

2. The VR-based gas safety emergency training system according to claim 1 is characterized by: The calculation of equipment operation accuracy coefficient is as follows: ； Where S is the equipment operation accuracy coefficient, which ranges from 0 to 1, with 1 indicating perfect compliance with the standard; F is the valve operation accuracy coefficient, which is the weighted sum of the rotation angle score and the opening and closing timing score. The rotation angle score = 1 - |actual number of revolutions - standard number of revolutions| / standard number of revolutions. The opening and closing timing score is based on whether the valve closing operation is completed within the specified time. If the valve is completed on time, the full score is 1 point. If the closing operation is delayed, the points will be deducted proportionally. M is the fire extinguisher operation accuracy coefficient, which is the weighted sum of the tilt angle score and the spray coverage score. The tilt angle deviation score is determined by whether the deviation angle exceeds the limit. If it is less than or equal to the set deviation, it is scored as 1 point, and if it is greater than the set deviation, it is directly scored as 0 points. The spray coverage score determines the fire extinguishing effect based on the proportion of fire source covered. If the coverage is x*100%, it is scored as x points. If the coverage is less than 50%, it is directly scored as 0 points. G is the tool operation accuracy, which evaluates the standardization of pipeline maintenance operations and is the weighted sum of the torque error score and the disassembly sequence score. The torque error score = 1-|actual torque-standard torque| / standard torque. For the disassembly sequence score, 1 point is awarded for correct steps, and points are deducted proportionally based on the number of incorrect steps for errors or omissions.

3. The VR-based gas safety emergency training system according to claim 1 is characterized by: The specific calculation of process compliance coefficient is: ； Where L is the process compliance coefficient, B is the step accuracy coefficient, and the standard process is "valve closing - ventilation - detection - alarm - evacuation". The step accuracy coefficient = Σ (step weight × operation accuracy rate); W is the protective equipment coefficient, which is the weighted sum of the wearing completeness coefficient, the fit compliance rate and the wearing response time; the wearing completeness coefficient = Σ (equipment weight × correct wearing rate), the quantitative detection leakage rate of the respirator is <5% and gets 1 point, 5%-10% gets 0.5 points, and more than 10% gets 0 points; the time from the alarm to the completion of equipment donning is ≤ 60 seconds and gets 1 point, and 0.1 points will be deducted for every 10 seconds exceeding the limit.

4. The VR-based gas safety emergency training system according to claim 1 is characterized by: The calculation of disposal time efficiency coefficient is as follows: ； Where C is the disposal efficiency coefficient and Y is the response delay compliance coefficient, specifically: ； Where Y is the response delay compliance coefficient, t s is the actual extension time, t b The delay time is the standard delay time. For every second the actual delay exceeds the standard value, 0.1 points will be deducted, until the deduction reaches 0 points. D is the process deviation compliance coefficient, specifically: ； Where D is the process deviation compliance coefficient, T s is the actual duration, the total time actually consumed by the operation process; T b is the standard duration; The min function limits the deviation ratio to an upper limit of 1. When the deviation ratio is greater than 1, min outputs 1 and D = 0. D = 1 indicates that the actual duration is equal to the standard duration, with zero deviation and full compliance. D close to 0 indicates excessive deviation and low compliance. E is the emergency correction factor, which is the correction factor = correction quality factor * standard time correction / actual correction time; H is the interruption recovery capability coefficient. When the actual recovery time is ≤30 seconds, H is 1, indicating full compliance. When the actual recovery time is greater than 30 seconds, the interruption recovery capability coefficient = 1-(actual recovery time-30) / 60.

5. The VR-based gas safety emergency training system according to claim 1 is characterized by: The calculation of path planning coefficient is as follows: ； Where J is the path planning coefficient, which ranges from 0 to 1, with 1 indicating the optimal value; P is the path deviation compliance coefficient, specifically: ； Where P is the path deviation compliance coefficient, P a (t) represents the three-dimensional space coordinates of the student at time t, P o (t) is the three-dimensional coordinate of the optimal escape path pre-generated by the system at time t; T is the total time of path tracking, and Dmax is the maximum allowable deviation threshold. When the threshold is exceeded, P is forced to 0 and the operation is directly judged as failed; X is the collaboration accuracy coefficient, specifically: ； Where X is the collaboration accuracy coefficient, R is the number of correctly executed instructions, Z is the total number of instructions, △t is the average response delay time of the instruction, t max is the maximum allowable delay time, 1-△t / t max As a delay penalty factor, the value range is between 0 and 1, close to 1 if the response is timely, and close to 0 if the delay exceeds the limit; Q is the path safety compliance coefficient, specifically: ； Where Q is the path safety compliance coefficient, d(t) is the real-time three-dimensional distance between the user and the nearest obstacle or hazard at time t; min(d(t)) represents the minimum distance between the user and the obstacle or danger source during the entire escape process, d a Represents the preset minimum safety distance threshold. The min function constrains the upper limit of Q to 1. When the minimum distance ≥ d a When Q=1, it indicates the optimal state, otherwise points will be deducted proportionally.

6. The VR-based gas safety emergency training system according to claim 1 is characterized by: The specific scoring of safety emergency training is as follows: ； Among them, A is the comprehensive score of emergency training, S is the equipment operation accuracy coefficient, L is the process compliance coefficient, C is the disposal timeliness coefficient, and J is the path planning coefficient.

7. The VR-based gas safety emergency training system according to claim 1 is characterized by: The comprehensive score of safety emergency training is graded and evaluated as follows: When a1<A≤100, it is an excellent grade; When a2<A≤a1, it is a good grade; When a3<A≤a2, it is a medium level; When a4<A≤a3, it is a passing grade; When 0<A≤a4, it is a failing grade.

Images