Analog nucleation detection system and method

Abstract

The invention relates to the technical field of power supply systems, in particular to an analog nucleation detection system and method, and the system comprises a data collection module, an equipment detection module, a simulation adaptation module, an analog nucleation detection module, a cyclic feedback module, and a detection evaluation module. Through cooperative operation of all the modules, the problems of insufficient proficiency, low simulation training efficiency and low operation safety in existing nucleation detection personnel training are effectively solved, the professional skills, team cooperation ability and adaptive ability of nucleation detection personnel are comprehensively improved, the high efficiency of training and the safety of practical operation are guaranteed, and the practical training efficiency is improved. And more qualified talents are cultivated for coring detection work.

Description

Technical Field

[0001] This invention relates to the field of chemical analysis technology, and in particular to a simulation nuclear chemical detection system and method. Background Technology

[0002] Nuclear and chemical detection, as a crucial link in responding to threats from nuclear and chemical hazardous materials, demands extremely high levels of operator proficiency, emergency response capabilities, and teamwork. However, current training for nuclear and chemical detection personnel generally lacks a systematic simulation training system. On the one hand, it's difficult to improve personnel's practical operational experience through simulated scenarios, leading to insufficient proficiency. On the other hand, existing training does not fully consider the adaptive development and targeted correction of individual operating habits and skill differences, and also lacks scientific assessment of teamwork processes. This directly results in low training efficiency, and personnel are prone to safety risks due to skill deficiencies or collaborative errors in actual operation, failing to meet the high safety and reliability requirements of nuclear and chemical detection missions. Therefore, there is an urgent need to construct a simulation-based nuclear and chemical detection system and method that takes into account individual differences, individual difference correction, and teamwork assessment to improve training efficiency and operational safety.

[0003] Chinese Patent Publication No. CN115359690A discloses a simulation training method and device for detecting surface contamination. Due to the hazards of nuclear and chemical contamination to human health and the environment, realistic training in detecting nuclear and chemical contamination in daily environments is not feasible, necessitating a simulation training scheme. The simulation training method provided by this invention constructs simulation models of various surface contaminations. Trainees wear AR augmented reality helmets and realistically operate the simulation training device according to a real detection process, receiving timely feedback on the simulation results. This invention also provides a corresponding simulation training device, a semi-physical simulation simulator. By combining real operation with virtual simulation, this invention allows trainees to realistically practice the detection process of nuclear and chemical surface contamination, effectively improving their operational skills and avoiding the dangers of nuclear and chemical contamination. However, this scheme still suffers from problems such as insufficient proficiency among nuclear and chemical detection personnel due to the lack of simulation training, failure to consider individual differences in adaptation, correction, and teamwork assessment, low simulation training efficiency, and low operational safety. Summary of the Invention

[0004] To address these issues, the present invention provides a simulation-based nuclear chemical detection system and method to overcome the problems in the prior art, such as insufficient proficiency of nuclear chemical detection personnel, low efficiency of simulation-based training for nuclear chemical detection personnel, and low operational safety of nuclear chemical detection personnel due to the lack of simulation training for nuclear chemical detection personnel and the failure to consider individual differences in adaptation, correction of individual differences, and team collaboration assessment.

[0005] To achieve the above objectives, in one aspect, the present invention provides a simulation-based nuclear detection system, comprising: The data acquisition module is used to collect startup and running parameters; The equipment detection module is used to acquire equipment fault conditions based on startup and operation parameters, and send adaptive adjustment signals to the simulation adaptation module based on the equipment fault conditions; The simulation adaptation module is used to judge the deviation based on the adaptive adjustment signal and send command signals to the simulated nucleochemical detection module according to the deviation. The simulated nuclear detection module is used to select training items according to command signals, and to acquire single-person training result data based on the selection results. It is also used to select multiple people for multi-person collaborative projects based on the number of people who passed the single-person training, and to acquire multi-person assessment result data based on the multi-person selection results. The feedback module is used to logically correct the assessment results data of multiple people based on real-time operating parameters, to judge the individual deviation risk based on the deviation coefficient, to optimize the logical correction process based on the individual deviation risk, and to correct the deviation in the selection process of multiple people based on the individual deviation risk. The detection and evaluation module is used to push the individual exercise evaluation results and the multi-person assessment results based on the individual exercise result data and the multi-person assessment result data.

[0006] Furthermore, the equipment detection module inputs the startup operating parameters into the equipment fault detection model, obtains the equipment fault status output by the model, which includes both equipment faults and normal equipment operation, and sends an adaptive adjustment signal to the simulation adaptation module based on the fault status, wherein: When the equipment malfunction is identified as a fault, the equipment detection module does not send an adaptive adjustment signal to the simulation adaptation module, but instead sends an equipment maintenance signal to the staff. When the equipment malfunctions and the equipment is functioning normally, the equipment detection module sends an adaptive adjustment signal to the simulation adaptation module.

[0007] Furthermore, when the simulation adaptation module makes adaptive adjustments based on the adaptive adjustment signal, it acquires the student's actual behavior dataset A{A1,A2,...,An-1,An} and the simulation simulator feedback dataset F{F1,F2,...,Fn-1,Fn}, and calculates the current deviation r based on the student's actual behavior dataset A{A1,A2,...,An-1,An}, the simulation simulator feedback dataset F{F1,F2,...,Fn-1,Fn}, and the number of data points n, and sets... Ai represents the actual behavior data of the i-th data point in the actual behavior dataset, Fi represents the simulation simulator feedback data of the i-th data point in the simulation simulator feedback dataset, and i represents the order of the data points. The current deviation r is compared with the preset deviation r0, the deviation is judged based on the comparison result, and the simulation simulator is adaptively adjusted based on the judgment result. When r < r0, the simulation adaptation module determines that the deviation is not a deviation, does not perform adaptive debugging on the simulation simulator, and sends the start simulation as an instruction signal to the simulation nucleation detection module. When r≥r0, the simulation adaptation module determines the deviation as a deviation, performs adaptive debugging on the simulation simulator, and sends the command signal "do not start simulation" to the simulation nucleation probe until r<r0. The adaptive debugging method is as follows: input the actual behavior dataset of the trainees A{A1,A2,...,An-1,An} into the adaptive parameter model, obtain the adjustment parameters output by the adaptive parameter model, and adjust the parameters of the simulation simulator according to the adjustment parameters.

[0008] Furthermore, the simulated nucleochemical detection module selects training items based on command signals, and conducts simulated nucleochemical detection exercises based on the selected items, wherein: When the command signal is to start the simulation, the simulated nuclear detection module selects the training items, selects the individual training items from the project database, and conducts nuclear detection training for the trainees according to each individual training sub-item in the individual training items, obtains individual training result data, and sends the individual training result data to the detection evaluation module. When the command signal is "Do not start simulation", the simulated nuclear detection module does not select any exercise items until the command signal is switched to "Start simulation".

[0009] Furthermore, the simulated nuclear detection module acquires the number of participants (m) passing the single-person exercise, compares this number with a preset number (m0) passing the single-person exercise, selects multiple participants for multi-person collaborative projects based on the comparison results, and conducts simulated nuclear detection assessments on these projects based on the selection results. When m > m0, the simulated nuclear detection module selects multiple people for the multi-person collaborative project, selects a multi-person collaborative project from the project database, conducts a multi-person collaborative nuclear detection assessment on the m trainees according to each multi-person collaborative sub-project in the multi-person collaborative project, obtains the multi-person assessment result data, sends the multi-person assessment result data to the detection evaluation module, resets the number of people who passed the single-person exercise m to 0, and recounts the number of people who passed the single-person exercise m. When m≤m0, the simulated nucleation detection module does not select multiple users for multi-user collaborative projects until m>m0.

[0010] Furthermore, the cyclic feedback module acquires real-time operating parameters and inputs them into the real-time fault analysis model. It then obtains the fault status and cause output by the model, including whether a fault exists or not. Based on the fault cause, it acquires logically deducible judgment results and performs logical corrections on the multi-person assessment data based on these results. When the fault condition is "fault present," the logically deducible judgment result is obtained. The fault cause and concurrent behavioral parameters are input into the logically deducible judgment model. The logically deducible judgment result and the inferred multi-person assessment result data output by the logically deducible judgment model are obtained, wherein: If the logical deduction judgment result is that there is logical deduction, then the data of multiple assessment results will be logically corrected. The correction is to replace the content of the data of multiple assessment results with the content of the inferred data of multiple assessment results. If the logical deduction result is that there is no logical deduction, then the multi-person assessment result data is logically corrected. The correction is as follows: the multi-person collaborative nuclear detection assessment is re-conducted for the m students based on each multi-person collaborative sub-project in the multi-person collaborative project to obtain the updated multi-person assessment result data, and the content of the multi-person assessment result data is replaced with the updated multi-person assessment result data. When the fault condition is no fault, the logically deducible judgment result is not obtained.

[0011] Furthermore, the feedback module acquires the number of adaptive adjustments k for the trainee, calculates the individual behavior deviation coefficient Y based on the number of adaptive adjustments k, the first deviation coefficient α1, the first deviation degree r1, and the second deviation coefficient α2, and sets Y = k × α1 + r1 × α2. The individual behavior deviation coefficient Y is compared with the preset deviation coefficient Y0, and the risk of individual deviation is judged based on the comparison result. Based on the judgment result, the logic correction process is optimized for deviation, wherein: When Y≤Y0, the circuit feedback module determines that the individual deviation risk is not dangerous and does not perform deviation optimization in the logic correction process; When Y > Y0, the cyclic feedback module determines that the individual deviation risk is dangerous and optimizes the deviation in the logical correction process. The deviation optimization method is to replace the logical deducible judgment result of "there is logical deducible" with the logical deducible judgment result of "there is no logical deducible".

[0012] Furthermore, the roving feedback module also compares the individual behavior deviation coefficient Y with the preset deviation coefficient Y0, judges the risk of individual deviation based on the comparison result, and corrects the deviation in the process of multiple selections based on the judgment result, wherein: When Y≤Y0, the circuit feedback module determines that the individual deviation risk is not dangerous and does not perform deviation correction in the process of multiple selections; When Y > Y0, the circuit feedback module determines that the individual deviation risk is dangerous and performs deviation correction on the process of multiple selections. The deviation correction method is as follows: before the trainees with individual deviation risk of danger take the multi-person collaborative nuclear detection assessment, select a single correction training project from the project database, and add single correction training for trainees with individual deviation risk of danger according to each sub-project of the single correction training project.

[0013] Furthermore, the detection and evaluation module inputs the single-person exercise result data into the exercise evaluation model, obtains the single-person exercise evaluation result output by the single-person exercise evaluation model, and pushes the single-person exercise evaluation result to the terminal of the simulated nuclear detection device. It also inputs the multi-person assessment result data into the multi-person assessment evaluation model, obtains the multi-person assessment evaluation result output by the multi-person assessment evaluation model, and pushes the multi-person assessment evaluation result to the terminal of the simulated nuclear detection device.

[0014] On the other hand, the present invention also provides a method for simulating a nuclear detection system, comprising: Step S1: Collect startup and running parameters; Step S2: Obtain the equipment fault status based on the startup and operation parameters, and send an adaptive adjustment signal to the simulation adaptation module based on the equipment fault status; Step S3: Determine the deviation based on the adaptive adjustment signal, and send a command signal to the simulated nucleochemical detection module based on the deviation. Step S4: Select training items according to the instruction signal, and obtain individual training result data based on the selection results. Also, select multiple people for multi-person collaborative projects based on the number of people who passed the individual training, and obtain multi-person assessment result data based on the selection results. Step S5: Logically correct the multi-person assessment results data based on real-time operating parameters, judge the individual deviation risk based on the deviation coefficient, optimize the logical correction process based on the individual deviation risk, and correct the deviation of the multi-person selection process based on the individual deviation risk. Step S6: Push the individual exercise evaluation results and the multi-person assessment evaluation results based on the individual exercise result data and the multi-person assessment result data.

[0015] Compared with existing technologies, the beneficial effects of this invention are as follows: The system collects startup and operation parameters through a data acquisition module, providing accurate and timely startup and operation parameters for subsequent use. The system also acquires equipment fault information through an equipment detection module and sends adaptive adjustment signals to ensure the normal operation of the training equipment. Furthermore, the system judges deviations through a simulation adaptation module and sends command signals to a simulated nuclear detection module based on the deviations, improving the adaptability between trainees and the simulation simulator. The system also selects training projects and acquires individual and multi-person assessment data through a simulated nuclear detection module, comprehensively evaluating personnel's individual operational capabilities and teamwork abilities, providing comprehensive raw data for subsequent assessments, and accurately grasping personnel's skill levels. The system also uses a feedback module to logically correct, optimize, and rectify assessment results, improving the accuracy of assessment results and promoting standardized and safe personnel operations. Finally, the system pushes individual and multi-person assessment results through a detection and evaluation module, allowing trainees and managers to clearly understand the training effect, providing direction for targeted personnel improvement and training plan adjustments, and enhancing the effectiveness and purpose of training. Attached Figure Description

[0016] Figure 1 This is a schematic diagram of the simulated nuclear chemical detection system in this embodiment; Figure 2 This is a flowchart illustrating the method for simulating a nuclear detection system in this embodiment; Figure 3 This is a schematic diagram of the simulation device in this embodiment. Detailed Implementation

[0017] To make the objectives and advantages of the present invention clearer, the present invention will be further described below with reference to embodiments; it should be understood that the specific embodiments described herein are merely for explaining the present invention and are not intended to limit the present invention.

[0018] Preferred embodiments of the present invention will now be described with reference to the accompanying drawings. Those skilled in the art should understand that these embodiments are merely illustrative of the technical principles of the present invention and are not intended to limit the scope of protection of the present invention.

[0019] It should be noted that in the description of this invention, the terms "upper", "lower", "left", "right", "inner", "outer", etc., which indicate directions or positional relationships, are based on the directions or positional relationships shown in the accompanying drawings. This is only for the convenience of description and is not intended to indicate or imply that the device or element must have a specific orientation, or be constructed and operated in a specific orientation. Therefore, it should not be construed as a limitation of this invention.

[0020] Furthermore, it should be noted that, in the description of this invention, unless otherwise explicitly specified and limited, the terms "installation," "connection," and "linking" should be interpreted broadly. For example, they can refer to a fixed connection, a detachable connection, or an integral connection; they can refer to a mechanical connection or an electrical connection; they can refer to a direct connection or an indirect connection through an intermediate medium; and they can refer to the internal connection of two components. Those skilled in the art can understand the specific meaning of the above terms in this invention according to the specific circumstances.

[0021] Please see Figure 1 As shown, this is a schematic diagram of the simulated nuclear chemical detection system in this embodiment. The system includes: The data acquisition module is used to collect startup and running parameters; The equipment detection module is used to acquire equipment fault conditions based on startup and operation parameters, and send adaptive adjustment signals to the simulation adaptation module based on the equipment fault conditions; The simulation adaptation module is used to judge the deviation based on the adaptive adjustment signal and send command signals to the simulated nucleochemical detection module according to the deviation. The simulated nuclear detection module is used to select training items according to command signals, and to acquire single-person training result data based on the selection results. It is also used to select multiple people for multi-person collaborative projects based on the number of people who passed the single-person training, and to acquire multi-person assessment result data based on the multi-person selection results. The feedback module is used to logically correct the assessment results data of multiple people based on real-time operating parameters, to judge the individual deviation risk based on the deviation coefficient, to optimize the logical correction process based on the individual deviation risk, and to correct the deviation in the selection process of multiple people based on the individual deviation risk. The detection and evaluation module is used to push the individual exercise evaluation results and the multi-person assessment results based on the individual exercise result data and the multi-person assessment result data.

[0022] Specifically, the simulated nuclear chemical detection system is applied in a simulated nuclear chemical detection terminal. Through the coordinated operation of its modules, the system effectively addresses the problems of insufficient proficiency, low efficiency of simulation training, and low operational safety in existing nuclear chemical detection personnel training. It comprehensively improves the professional skills, teamwork ability, and adaptability of nuclear chemical detection personnel, ensuring both high training efficiency and safe practical operation, and cultivating more qualified personnel for nuclear chemical detection work. The system collects startup and operating parameters through a data acquisition module, providing accurate and timely startup and operating parameters for subsequent operations. The system also acquires equipment fault information through an equipment detection module and sends adaptive adjustment signals to ensure the normal operation of the training equipment. Furthermore, the system uses a simulation adaptation module to judge deviations and... The system sends command signals to the simulated nuclear detection module based on deviations, improving the adaptability of trainees to the simulation simulator. The system also selects training projects and acquires individual and multi-person assessment data through the simulated nuclear detection module, comprehensively evaluating individual operational skills and teamwork abilities. This provides comprehensive raw data for subsequent assessments, accurately grasping personnel skill levels. Furthermore, the system uses a feedback module to logically correct, optimize, and rectify assessment results, improving accuracy and promoting standardized and safe operations. Finally, the system pushes individual and multi-person assessment results through the detection and evaluation module, allowing trainees and managers to clearly understand the training effectiveness. This provides direction for targeted personnel improvement and training plan adjustments, enhancing the effectiveness and purpose of training.

[0023] Specifically, the data acquisition module is used to collect startup and running parameters. Specifically, the equipment detection module inputs the startup parameters into the equipment fault detection model, obtains the equipment fault status output by the model, which includes both equipment faults and normal operation, and sends an adaptive adjustment signal to the simulation adaptation module based on the fault status. When the equipment malfunction is identified as a fault, the equipment detection module does not send an adaptive adjustment signal to the simulation adaptation module, but instead sends an equipment maintenance signal to the staff. When the equipment malfunctions and the equipment is functioning normally, the equipment detection module sends an adaptive adjustment signal to the simulation adaptation module.

[0024] Specifically, the equipment fault detection model refers to a recurrent neural network model that takes startup and operation parameters as input and outputs equipment fault conditions. This embodiment does not limit the specific construction method of the equipment fault detection model. Those skilled in the art can set it according to the actual situation. For example, the recurrent neural network model can be trained using an equipment fault learning dataset to obtain the equipment fault detection model. The equipment fault learning dataset refers to the training dataset used to construct the equipment fault detection model. The equipment fault learning dataset includes historically acquired startup and operation parameters and the corresponding equipment fault conditions. This embodiment does not limit the specific implementation method of sending adaptive adjustment signals to the simulation adaptation module. Those skilled in the art can set it according to the actual situation. For example, adaptive adjustment signals can be sent to the simulation adaptation module via wireless signal transmission. This embodiment does not limit the specific implementation method of sending equipment maintenance signals to staff. Those skilled in the art can set it according to the actual situation. For example, maintenance information can be sent to staff's mobile devices via Bluetooth.

[0025] Specifically, when the simulation adaptation module makes adaptive adjustments based on the adaptive adjustment signal, it acquires the student's actual behavior dataset A{A1,A2,...,An-1,An} and the simulation simulator feedback dataset F{F1,F2,...,Fn-1,Fn}, and calculates the current deviation r based on the student's actual behavior dataset A{A1,A2,...,An-1,An}, the simulation simulator feedback dataset F{F1,F2,...,Fn-1,Fn}, and the number of data points n, and sets... Ai represents the actual behavior data of the i-th data point in the actual behavior dataset, Fi represents the simulation simulator feedback data of the i-th data point in the simulation simulator feedback dataset, and i represents the order of the data points. The current deviation r is compared with the preset deviation r0, the deviation is judged based on the comparison result, and the simulation simulator is adaptively adjusted based on the judgment result. When r < r0, the simulation adaptation module determines that the deviation is not a deviation, does not perform adaptive debugging on the simulation simulator, and sends the start simulation as an instruction signal to the simulation nucleation detection module. When r≥r0, the simulation adaptation module determines the deviation as a deviation, performs adaptive debugging on the simulation simulator, and sends the command signal "do not start simulation" to the simulation nucleation probe until r<r0. The adaptive debugging method is as follows: input the actual behavior dataset of the trainees A{A1,A2,...,An-1,An} into the adaptive parameter model, obtain the adjustment parameters output by the adaptive parameter model, and adjust the parameters of the simulation simulator according to the adjustment parameters.

[0026] Specifically, the student actual behavior dataset refers to the collection of student's actual behavior data when debugging according to debugging instructions. A1 refers to the first collected student actual behavior data, A2 refers to the second collected student actual behavior data, An-1 refers to the An-1th collected student actual behavior data, and An refers to the nth collected student actual behavior data. The simulation simulator feedback dataset refers to the collection of simulation simulator behavior feedback data when the student debugs according to debugging instructions. F1 refers to the first collected simulation simulator feedback data, F2 refers to the second collected simulation simulator feedback data, Fn-1 refers to the Fn-1th collected simulation simulator feedback data, and Fn refers to the nth collected simulation simulator feedback data. The debugging instructions refer to the instructions given by the instructor to the student when using the simulation simulator for the first time, mainly used to debug the simulation simulator according to the student's behavioral habits, making the simulation simulator more adaptable to different students. The preset deviation degree refers to a preset value for judging deviation. This embodiment does not limit the specific value of the preset deviation. Those skilled in the art can limit it according to the actual situation. For example, if multiple experiments show that the deviation is greater than 0.6, then r0=0.6 is set. The deviation refers to whether the student's actual behavior deviates from the simulation simulator feedback data when the student is tested, based on the current deviation and the preset deviation. The deviation includes deviation and no deviation. The adaptive parameter model is a decision tree model that takes the student's actual behavior dataset as input and the adjustment parameters as output. This embodiment does not limit the specific construction method of the adaptive parameter model. Those skilled in the art can set it according to the actual situation. For example, the adaptive parameter model can be obtained by training the decision tree model with the adaptive parameter dataset. The adaptive parameter dataset is the training dataset for constructing the adaptive parameter model. The adaptive parameter dataset includes the historically acquired student actual behavior dataset and the adjustment parameters corresponding to the historically acquired student actual behavior dataset. The adjustment parameters are the parameter set output by the adaptive parameter model for adjusting the parameters of the simulation simulator.

[0027] Specifically, the simulation adaptation module judges deviations and adaptively adjusts the simulation simulator based on the judgment results, thereby making the simulation simulator more suitable for the users' habits, so as to obtain more accurate individual practice results data and multi-person assessment results data in the future.

[0028] Specifically, the simulated nucleochemical detection module selects training items based on command signals, and conducts simulated nucleochemical detection exercises based on the selected items, wherein: When the command signal is to start the simulation, the simulated nuclear detection module selects the training items, selects the individual training items from the project database, and conducts nuclear detection training for the trainees according to each individual training sub-item in the individual training items, obtains individual training result data, and sends the individual training result data to the detection evaluation module. When the command signal is "Do not start simulation", the simulated nuclear detection module does not select any exercise items until the command signal is switched to "Start simulation".

[0029] Specifically, the project database refers to a database used to store training projects. These training projects include single-person projects, multi-person projects, and correction projects. Single-person projects refer to nuclear chemical detection training projects conducted by a single trainee. Multi-person projects refer to nuclear chemical detection training projects conducted jointly by multiple trainees. Correction projects refer to nuclear chemical detection training projects designed to correct errors for trainees. This embodiment does not limit the specific construction method of the project database; those skilled in the art can set it up according to actual conditions. For example, domain experts can set up training projects based on their experience and store the set training projects in the project database. Domain experts refer to experts widely recognized in the field of nuclear chemical detection. This embodiment does not select single-person training projects from the project database and based on single-person... The specific implementation method for the individual training sub-projects in the training project to conduct nuclear and chemical detection exercises for trainees is limited. Those skilled in the art can set it according to the actual situation. For example, the individual projects preset in the project database are matched with the current training progress, and the matched individual projects are output as individual training projects. Trainees conduct nuclear and chemical detection exercises according to the individual training sub-projects in the individual training projects. For example, when the sub-project is "to conduct a gas detection", the trainee needs to conduct nuclear and chemical detection exercises alone according to the task instructions in the sub-project. This embodiment does not limit the specific implementation method of sending the individual training result data to the detection evaluation module. Those skilled in the art can set it according to the actual situation. For example, the individual training result data can be sent to the detection evaluation module through wireless signal transmission.

[0030] Specifically, the simulated nuclear and chemical detection module selects training items based on command signals and conducts simulated nuclear and chemical detection exercises based on the selection results. This allows for training of trainees after the simulation simulator is adapted to them, thereby improving the operational safety of nuclear and chemical detection personnel.

[0031] Specifically, the simulated nuclear detection module acquires the number of participants (m) passing the single-person drill, compares this number with a preset number (m0) passing the single-person drill, selects multiple participants for multi-person collaborative projects based on the comparison results, and conducts simulated nuclear detection assessments on these projects based on the selection results. When m > m0, the simulated nuclear detection module selects multiple people for the multi-person collaborative project, selects a multi-person collaborative project from the project database, conducts a multi-person collaborative nuclear detection assessment on the m trainees according to each multi-person collaborative sub-project in the multi-person collaborative project, obtains the multi-person assessment result data, sends the multi-person assessment result data to the detection evaluation module, resets the number of people who passed the single-person exercise m to 0, and recounts the number of people who passed the single-person exercise m. When m≤m0, the simulated nucleation detection module does not select multiple users for multi-user collaborative projects until m>m0.

[0032] Specifically, the number of participants who passed the individual training refers to the number of participants who completed the individual training project. This embodiment does not limit the method of obtaining the number of participants who passed the individual training; those skilled in the art can set it according to the actual situation. For example, by using a simulated nuclear detection module to count the number of participants who completed all sub-projects of the individual training project, one participant is counted as 1. The preset number of participants who passed the individual training refers to a preset value for selecting multiple participants in a multi-person collaborative project. This embodiment does not limit the specific number of participants who passed the individual training; those skilled in the art can set it according to the actual situation. For example, when the required number of participants for a multi-person collaborative project is 5, m0 is set to 5. This embodiment does not limit the specific implementation method of selecting a multi-person collaborative project from the project database and conducting a multi-person collaborative nuclear detection assessment on m participants based on each multi-person collaborative sub-project in the multi-person collaborative project. Those skilled in the art can set it according to the actual situation, such as by using a preset number of participants from the project database. The various multi-person projects are matched with the current training progress, and the matched multi-person projects are output as multi-person collaborative projects. Based on the multi-person collaborative sub-projects in the multi-person collaborative projects, the m trainees are assessed on multi-person collaborative nuclear detection. For example, when the sub-project is "detecting gas at a designated location", the m trainees need to conduct multi-person collaborative nuclear detection assessment according to the task instructions in the sub-project. This embodiment does not limit the specific implementation method of sending the multi-person assessment result data to the detection evaluation module. Those skilled in the art can set it according to the actual situation. For example, the multi-person assessment result data can be sent to the detection evaluation module through wireless signal transmission. This embodiment does not limit the specific implementation method of re-counting the number of trainees m in the single-person exercise. Those skilled in the art can set it according to the actual situation. For example, the simulated nuclear detection module can re-count all trainees who have completed all sub-projects of the single-person exercise project after m is reset to 0, and one trainee is counted as 1.

[0033] Specifically, the simulated nuclear and chemical detection module compares the number of people who pass the single-person exercise with the preset number of people who pass the single-person exercise. Based on the comparison results, multiple people are selected for multi-person collaborative projects, and simulated nuclear and chemical detection assessments are conducted on the multi-person collaborative projects based on the selection results. This achieves comprehensive training for trainees and improves the operational safety of nuclear and chemical detection personnel.

[0034] Specifically, the cyclic feedback module acquires real-time operating parameters and inputs them into a real-time fault analysis model. It then obtains the fault status and cause output by the model, including whether a fault exists or not. Based on the fault cause, it acquires logically deducible judgment results and performs logical corrections on the multi-person assessment data based on these results. When the fault condition is "fault present," the logically deducible judgment result is obtained. The fault cause and concurrent behavioral parameters are input into the logically deducible judgment model. The logically deducible judgment result and the inferred multi-person assessment result data output by the logically deducible judgment model are obtained, wherein: If the logical deduction judgment result is that there is logical deduction, then the data of multiple assessment results will be logically corrected. The correction is to replace the content of the data of multiple assessment results with the content of the inferred data of multiple assessment results. If the logical deduction result is that there is no logical deduction, then the multi-person assessment result data is logically corrected. The correction is as follows: the multi-person collaborative nuclear detection assessment is re-conducted for the m students based on each multi-person collaborative sub-project in the multi-person collaborative project to obtain the updated multi-person assessment result data, and the content of the multi-person assessment result data is replaced with the updated multi-person assessment result data. When the fault condition is no fault, the logically deducible judgment result is not obtained.

[0035] Specifically, the real-time operating parameters refer to the operating parameters generated by the simulation simulator during real-time operation, such as the inhalation rate. This embodiment does not limit the method of obtaining the real-time operating parameters; those skilled in the art can set them according to actual conditions. For example, the real-time operating parameters can be obtained by reading the task log of the simulation simulator. The real-time fault analysis model refers to a decision tree model that takes the real-time operating parameters as input and outputs the fault condition and fault cause. This embodiment does not limit the specific construction method of the real-time fault analysis model; those skilled in the art can set it according to actual conditions. For example, the real-time fault analysis model can be obtained by training the decision tree model through a real-time analysis dataset. The real-time analysis dataset refers to the training dataset used to construct the real-time fault analysis model. This dataset includes historically acquired real-time operating parameters and the corresponding fault causes and conditions. The concurrent behavioral parameters refer to the operating parameters of the other simulation simulators that jointly execute the collaborative project, excluding the faulty simulator. The logically inferable judgment model is a multilayer perceptron that takes the fault causes and concurrent behavioral parameters as input and infers the results of multiple participants' assessments as output. This embodiment does not limit the specific construction method of the logically inferable judgment model; those skilled in the art can implement the settings according to actual conditions, such as incorporating historical fault causes and concurrent behavioral parameters from the logical inference dataset. The data in the logical inference dataset, including behavioral parameters, historical fault causes, and corresponding multi-person assessment results for the same behavioral parameters, were examined to remove duplicate, erroneous, or incomplete records. The historical fault causes, corresponding behavioral parameters, and corresponding multi-person assessment results were then labeled. Features closely related to the historical fault causes and corresponding behavioral parameters were extracted from the multi-person assessment results. The most representative features were selected through statistical analysis or machine learning techniques to improve model performance. One-hot encoding was used to encode the categorical features. The logical inference dataset was split into 75% inference training set and 15% inference training set. The validation set and a 10% split are used to create an inference test set. Data augmentation techniques are employed to expand the inference training set. A multilayer perceptron is selected as the logically inferable judgment model. The weights and biases of the logically inferable judgment model are initialized. Data from the inference training set is input into the logically inferable judgment model, and its output is calculated. The loss function value is calculated based on the output and labels of the logically inferable judgment model. The gradient is calculated using the backpropagation algorithm, and the weights and biases of the logically inferable judgment model are updated. The process of forward propagation, loss function calculation, and backpropagation is repeated until the preset number of training rounds is reached. The performance of the multilayer perceptron is verified on the inference validation set, and the multilayer perceptron that meets the performance requirements is used as the logically inferable judgment model for output.

[0036] Specifically, the cyclic feedback module obtains the fault status and fault cause, obtains the logically deducible judgment result based on the fault cause, and performs logical correction on the multi-person assessment result data based on the logically deducible judgment result, so as to avoid inaccurate assessment results caused by simulation simulator failure during the assessment process.

[0037] Specifically, the feedback module acquires the number of adaptive adjustments k made by the student, calculates the individual behavioral deviation coefficient Y based on the number of adaptive adjustments k, the first deviation coefficient α1, the first deviation degree r1, and the second deviation coefficient α2, and sets Y = k × α1 + r1 × α2. The individual behavioral deviation coefficient Y is compared with the preset deviation coefficient Y0, and the risk of individual deviation is judged based on the comparison result. Based on the judgment result, the logic correction process is optimized for deviation, wherein: When Y≤Y0, the circuit feedback module determines that the individual deviation risk is not dangerous and does not perform deviation optimization in the logic correction process; When Y > Y0, the cyclic feedback module determines that the individual deviation risk is dangerous and optimizes the deviation in the logical correction process. The deviation optimization method is to replace the logical deducible judgment result of "there is logical deducible" with the logical deducible judgment result of "there is no logical deducible".

[0038] Specifically, the number of adaptive debugging attempts for students refers to the number of adaptive debugging attempts performed by the simulation simulator in the simulation adaptation module for students whose deviation is considered to be indicative of deviation. In this embodiment, the simulation adaptation module counts the number of adaptive debugging attempts performed by the simulation simulator for students whose deviation is considered to be indicative of deviation to obtain the number of adaptive debugging attempts for students. The first deviation coefficient refers to the weighting coefficient corresponding to the number of adaptive debugging attempts for students during the calculation of the individual behavior deviation coefficient. The second deviation coefficient refers to the weighting coefficient corresponding to the first deviation degree during the calculation of the individual behavior deviation coefficient. This embodiment does not limit the specific values ​​of the first and second deviation coefficients. Those skilled in the art can set them according to the actual situation, as long as the calculation of the individual behavior deviation coefficient and the requirement of α1+α2=1 are met. Since the number of adaptive debugging attempts by trainees accounts for a high proportion in the calculation of individual behavior deviation coefficient, α1=0.7 and α2=0.3 can be set. The first deviation degree refers to the current deviation degree calculated when the trainee performs adaptive debugging for the first time. The preset deviation coefficient refers to the preset value for judging the risk of individual deviation. This embodiment does not limit the specific value of the preset deviation coefficient. Those skilled in the art can set it according to the actual situation. For example, according to multiple experiments, when the individual behavior deviation coefficient is greater than 0.6, the risk of individual behavior deviation is dangerous. Therefore, Y0=0.6 is set. The risk of individual deviation refers to whether the individual deviation of the trainee will bring danger to the multi-person collaborative project, as judged by the individual behavior deviation coefficient and the preset deviation coefficient. The risk of individual deviation includes dangerous and not dangerous.

[0039] Specifically, the cyclical feedback module assesses the risk of individual deviations and optimizes the logical correction process based on the assessment results to prevent individual deviations of trainees from posing a danger to multi-person collaborative projects.

[0040] Specifically, the feedback module also compares the individual behavior deviation coefficient Y with the preset deviation coefficient Y0, judges the risk of individual deviation based on the comparison result, and corrects the deviation in the process of multiple selections based on the judgment result, wherein: When Y≤Y0, the circuit feedback module determines that the individual deviation risk is not dangerous and does not perform deviation correction in the process of multiple selections; When Y > Y0, the circuit feedback module determines that the individual deviation risk is dangerous and performs deviation correction on the process of multiple selections. The deviation correction method is as follows: before the trainees with individual deviation risk of danger take the multi-person collaborative nuclear detection assessment, select a single correction training project from the project database, and add single correction training for trainees with individual deviation risk of danger according to each sub-project of the single correction training project.

[0041] Specifically, this embodiment does not limit the specific implementation method of selecting individual correction training projects from the project database and adding individual correction training for trainees with dangerous individual deviation risks based on each sub-project of the individual correction training project. Those skilled in the art can set it up according to the actual situation. For example, the correction projects preset in the project database are matched with the deviation causes of trainees with dangerous individual deviation risks, and the matched correction projects are output as individual correction training projects. Individual correction training is added for trainees with dangerous individual deviation risks based on each sub-project of the individual correction training project. For example, when the sub-project is "Demonstration Project of Correct Use of Simulation Simulator", the trainee needs to carry out individual correction training according to the correct use method of simulation simulator in the sub-project. The deviation cause refers to the reason why the trainee's individual deviation risk is dangerous, which is determined by the domain expert. The domain expert refers to an authoritative expert in the field of nuclear chemical detection.

[0042] Specifically, the feedback module judges the risk of individual deviation based on the comparison results, and corrects the deviation in the process of multiple selections based on the judgment results. This prevents students with a high risk of individual deviation from affecting the evaluation scores of others in multi-person collaborative projects. Furthermore, it improves the operational safety of students by providing individual correction training to them before multi-person collaborative projects.

[0043] Specifically, the detection and evaluation module inputs the single-person exercise result data into the exercise evaluation model, obtains the single-person exercise evaluation result output by the single-person exercise evaluation model, and pushes the single-person exercise evaluation result to the terminal of the simulated nuclear detection device. It also inputs the multi-person assessment result data into the multi-person assessment evaluation model, obtains the multi-person assessment evaluation result output by the multi-person assessment evaluation model, and pushes the multi-person assessment evaluation result to the terminal of the simulated nuclear detection device.

[0044] Specifically, the single-person training evaluation model refers to a recurrent neural network model that takes single-person training result data as input and outputs single-person training evaluation results. This embodiment does not limit the specific construction method of the single-person training evaluation model; those skilled in the art can set it according to actual conditions. For example, the recurrent neural network model can be trained using a single-person evaluation dataset to obtain the single-person training evaluation model. The single-person evaluation dataset refers to the training dataset used to construct the single-person training evaluation model. The single-person evaluation dataset includes historically acquired single-person training result data and the corresponding single-person training evaluation results. This embodiment does not limit the specific implementation method of pushing the single-person training evaluation results to the terminal of the simulated nuclear detection device; those skilled in the art can set it according to actual conditions. For example, the single-person training evaluation results can be pushed to the simulated nuclear detection device via wireless network transmission. The terminal, the multi-person assessment model, refers to a recurrent neural network model that takes multi-person assessment result data as input and multi-person assessment results as output. This embodiment does not limit the specific construction method of the multi-person assessment model. Those skilled in the art can set it according to the actual situation. For example, the recurrent neural network model can be trained through a multi-person assessment dataset to obtain the multi-person assessment model. The multi-person assessment dataset refers to the training dataset for constructing the multi-person assessment model. The multi-person assessment dataset includes historically acquired multi-person assessment result data and the multi-person assessment results corresponding to the historically acquired multi-person assessment result data. This embodiment does not limit the specific implementation method of pushing the multi-person assessment results to the terminal of the simulated nuclear and chemical detection device. Those skilled in the art can set it according to the actual situation. For example, the multi-person assessment results can be pushed to the terminal of the simulated nuclear and chemical detection device through wireless network transmission.

[0045] Please see Figure 2 As shown, this is a flowchart illustrating the method for simulating a nuclear detection system in this embodiment. The method includes: Step S1: Collect startup and running parameters; Step S2: Obtain the equipment fault status based on the startup and operation parameters, and send an adaptive adjustment signal to the simulation adaptation module based on the equipment fault status; Step S3: Determine the deviation based on the adaptive adjustment signal, and send a command signal to the simulated nucleochemical detection module based on the deviation. Step S4: Select training items according to the instruction signal, and obtain individual training result data based on the selection results. Also, select multiple people for multi-person collaborative projects based on the number of people who passed the individual training, and obtain multi-person assessment result data based on the selection results. Step S5: Logically correct the multi-person assessment results data based on real-time operating parameters, judge the individual deviation risk based on the deviation coefficient, optimize the logical correction process based on the individual deviation risk, and correct the deviation of the multi-person selection process based on the individual deviation risk. Step S6: Push the individual exercise evaluation results and the multi-person assessment evaluation results based on the individual exercise result data and the multi-person assessment result data.

[0046] Please see Figure 3 As shown, this is a schematic diagram of the simulation simulator in this embodiment. The simulation simulator includes: Simulator main body 1; Display screen 2, which is set on the main body of the simulator 1, is used to display the data collected by the simulation simulator; Filter 3, which is connected to the upper side of the simulator body 1, is used to filter out impurities absorbed by the air intake. The air intake 4 is connected to the filter 3 and is used to collect gas; Button panel 5 is located on the main body of the simulator 1; The first button 501 is located on the button panel 5; The second button 502 is located on the button panel 5; The third button 503 is located on the button panel 5; The fourth button, 504, is located on the button panel 5. The fifth button, 505, is located on button panel 5. Buzzer 6, which is mounted on the simulator body 1, is used to issue an alarm; The first LED light 7 is located on the simulator body 1 and is used to issue prompts; The second LED 8, which is located on the simulator body 1, is used to issue prompts.

[0047] The technical solution of the present invention has been described above with reference to the preferred embodiments shown in the accompanying drawings. However, it will be readily understood by those skilled in the art that the scope of protection of the present invention is obviously not limited to these specific embodiments. Without departing from the principles of the present invention, those skilled in the art can make equivalent changes or substitutions to the relevant technical features, and the technical solutions after these changes or substitutions will all fall within the scope of protection of the present invention.

Claims

1. A simulated nuclear detection system, characterized in that, include: The data acquisition module is used to collect startup and running parameters; The equipment detection module is used to acquire equipment fault conditions based on startup and operation parameters, and send adaptive adjustment signals to the simulation adaptation module based on the equipment fault conditions; The simulation adaptation module is used to judge the deviation based on the adaptive adjustment signal and send command signals to the simulated nucleochemical detection module according to the deviation. The simulated nuclear detection module is used to select training items according to command signals, and to acquire single-person training result data based on the selection results. It is also used to select multiple people for multi-person collaborative projects based on the number of people who passed the single-person training, and to acquire multi-person assessment result data based on the multi-person selection results. The feedback module is used to logically correct the assessment results data of multiple people based on real-time operating parameters, to judge the individual deviation risk based on the deviation coefficient, to optimize the logical correction process based on the individual deviation risk, and to correct the deviation in the selection process of multiple people based on the individual deviation risk. The detection and evaluation module is used to push the individual exercise evaluation results and the multi-person assessment results based on the individual exercise result data and the multi-person assessment result data.

2. The simulated nuclear detection system according to claim 1, characterized in that, The equipment detection module inputs the startup parameters into the equipment fault detection model, obtains the equipment fault status output by the model, including both equipment faults and normal operation, and sends an adaptive adjustment signal to the simulation adaptation module based on the fault status. When the equipment malfunction is identified as a fault, the equipment detection module does not send an adaptive adjustment signal to the simulation adaptation module, but instead sends an equipment maintenance signal to the staff. When the equipment malfunctions and the equipment is functioning normally, the equipment detection module sends an adaptive adjustment signal to the simulation adaptation module.

3. The simulation-based nuclear detection system according to claim 1, characterized in that, When the simulation adaptation module makes adaptive adjustments based on the adaptive adjustment signal, it acquires the student's actual behavior dataset A{A1,A2,...,An-1,An} and the simulation simulator feedback dataset F{F1,F2,...,Fn-1,Fn}, and calculates the current deviation r based on the student's actual behavior dataset A{A1,A2,...,An-1,An}, the simulation simulator feedback dataset F{F1,F2,...,Fn-1,Fn}, and the number of data points n, and sets... Ai represents the actual behavior data of the i-th data point in the actual behavior dataset, Fi represents the simulation simulator feedback data of the i-th data point in the simulation simulator feedback dataset, and i represents the order of the data points. The current deviation r is compared with the preset deviation r0, the deviation is judged based on the comparison result, and the simulation simulator is adaptively adjusted based on the judgment result. When r < r0, the simulation adaptation module determines that the deviation is not a deviation, does not perform adaptive debugging on the simulation simulator, and sends the start simulation as an instruction signal to the simulation nucleation detection module. When r≥r0, the simulation adaptation module determines the deviation as a deviation, performs adaptive debugging on the simulation simulator, and sends the command signal "do not start simulation" to the simulation nucleation probe until r<r0. The adaptive debugging method is as follows: input the actual behavior dataset of the trainees A{A1,A2,...,An-1,An} into the adaptive parameter model, obtain the adjustment parameters output by the adaptive parameter model, and adjust the parameters of the simulation simulator according to the adjustment parameters.

4. The simulation-based nuclear detection system according to claim 1, characterized in that, The simulated nucleochemical detection module selects exercise items based on command signals and conducts simulated nucleochemical detection exercises based on the selected items, wherein: When the command signal is to start the simulation, the simulated nuclear detection module selects the training items, selects the individual training items from the project database, and conducts nuclear detection training for the trainees according to each individual training sub-item in the individual training items, obtains individual training result data, and sends the individual training result data to the detection evaluation module. When the command signal is "Do not start simulation", the simulated nuclear detection module does not select any exercise items until the command signal is switched to "Start simulation".

5. The simulated nuclear detection system according to claim 1, characterized in that, The simulated nuclear detection module acquires the number of participants (m) passing the single-person drill, compares this number with a preset number (m0) passing the single-person drill, selects multiple participants for multi-person collaborative projects based on the comparison results, and conducts simulated nuclear detection assessments on these projects based on the selection results. When m > m0, the simulated nuclear detection module selects multiple people for the multi-person collaborative project, selects a multi-person collaborative project from the project database, conducts a multi-person collaborative nuclear detection assessment on the m trainees according to each multi-person collaborative sub-project in the multi-person collaborative project, obtains the multi-person assessment result data, sends the multi-person assessment result data to the detection evaluation module, resets the number of people who passed the single-person exercise m to 0, and recounts the number of people who passed the single-person exercise m. When m≤m0, the simulated nucleation detection module does not select multiple users for multi-user collaborative projects until m>m0.

6. The simulation-based nuclear detection system according to claim 1, characterized in that, The cyclic feedback module acquires real-time operating parameters and inputs them into the real-time fault analysis model. It then obtains the fault status and cause output by the model, including whether a fault exists or not. Based on the fault cause, it acquires logically deducible judgment results and performs logical corrections on the multi-person assessment data based on these results. When the fault condition is "fault present," the logically deducible judgment result is obtained. The fault cause and concurrent behavioral parameters are input into the logically deducible judgment model. The logically deducible judgment result and the inferred multi-person assessment result data output by the logically deducible judgment model are obtained, wherein: If the logical deduction judgment result is that there is logical deduction, then the data of multiple assessment results will be logically corrected. The correction is to replace the content of the data of multiple assessment results with the content of the inferred data of multiple assessment results. If the logical deduction result is that there is no logical deduction, then the multi-person assessment result data is logically corrected. The correction is as follows: the multi-person collaborative nuclear detection assessment is re-conducted for the m students based on each multi-person collaborative sub-project in the multi-person collaborative project to obtain the updated multi-person assessment result data, and the content of the multi-person assessment result data is replaced with the updated multi-person assessment result data. When the fault condition is no fault, the logically deducible judgment result is not obtained.

7. The simulation-based nuclear detection system according to claim 1, characterized in that, The feedback module acquires the number of adaptive adjustments k made by the trainee, calculates the individual behavioral deviation coefficient Y based on the number of adaptive adjustments k, the first deviation coefficient α1, the first deviation degree r1, and the second deviation coefficient α2, and sets Y = k × α1 + r1 × α2. The individual behavioral deviation coefficient Y is compared with the preset deviation coefficient Y0, and the risk of individual deviation is judged based on the comparison result. Based on the judgment result, the logic correction process is optimized for deviation, wherein: When Y≤Y0, the circuit feedback module determines that the individual deviation risk is not dangerous and does not perform deviation optimization in the logic correction process; When Y > Y0, the cyclic feedback module determines that the individual deviation risk is dangerous and performs deviation optimization on the logical correction process. The deviation optimization method is to replace the logical deducible judgment result of "there is logical deducible" with the logical deducible judgment result of "there is no logical deducible".

8. The simulation-based nuclear detection system according to claim 1, characterized in that, The feedback module also compares the individual behavior deviation coefficient Y with the preset deviation coefficient Y0, judges the risk of individual deviation based on the comparison result, and corrects the deviation in the process of multiple selections based on the judgment result, wherein: When Y≤Y0, the circuit feedback module determines that the individual deviation risk is not dangerous and does not perform deviation correction in the process of multiple selections; When Y > Y0, the circuit feedback module determines that the individual deviation risk is dangerous and performs deviation correction on the process of multiple selections. The deviation correction method is as follows: before the trainees with individual deviation risk of danger take the multi-person collaborative nuclear detection assessment, select a single correction training project from the project database, and add single correction training for trainees with individual deviation risk of danger according to each sub-project of the single correction training project.

9. The simulation-based nuclear detection system according to claim 1, characterized in that, The detection and evaluation module inputs the single-person exercise result data into the exercise evaluation model, obtains the single-person exercise evaluation result output by the single-person exercise evaluation model, and pushes the single-person exercise evaluation result to the terminal of the simulated nuclear and chemical detection device. It also inputs the multi-person assessment result data into the multi-person assessment evaluation model, obtains the multi-person assessment evaluation result output by the multi-person assessment evaluation model, and pushes the multi-person assessment evaluation result to the terminal of the simulated nuclear and chemical detection device.

10. A method applied to a simulated nuclear detection system as described in claims 1-9, characterized in that, include: Step S1: Collect startup and running parameters; Step S2: Obtain the equipment fault status based on the startup and operation parameters, and send an adaptive adjustment signal to the simulation adaptation module based on the equipment fault status; Step S3: Determine the deviation based on the adaptive adjustment signal, and send a command signal to the simulated nucleochemical detection module based on the deviation. Step S4: Select training items according to the instruction signal, and obtain individual training result data based on the selection results. Also, select multiple people for multi-person collaborative projects based on the number of people who passed the individual training, and obtain multi-person assessment result data based on the selection results. Step S5: Logically correct the multi-person assessment results data based on real-time operating parameters, judge the individual deviation risk based on the deviation coefficient, optimize the logical correction process based on the individual deviation risk, and correct the deviation of the multi-person selection process based on the individual deviation risk. Step S6: Push the individual exercise evaluation results and the multi-person assessment evaluation results based on the individual exercise result data and the multi-person assessment result data.

Images