Mine self-rescuer simulation training effect monitoring method and system

Abstract

The invention relates to the technical field of mine self-rescuers, in particular to a mine self-rescuer simulation training effect monitoring method and system.The mine self-rescuer simulation training effect monitoring method comprises the following steps that data of physiological monitoring equipment worn by a trainee is collected, the heart rate value and the blood oxygen saturation degree are collected, and meanwhile the response time and the error rate of operation behaviors of the trainee are recorded; an equipment operation sequence and environment change information are extracted, and a physiological behavior integration data set is established. According to the method, the physiological data and the operation behavior data of the trainee are collected in real time, the environment change information is combined, and the multi-dimensional physiological behavior integration data set is created, so that the heart rate and blood oxygen changes of the trainee in simulation training are reflected, the response time and the error rate are integrated, a basis is provided for evaluating the emergency response capability of the trainee, and the training efficiency of the trainee is improved. The training difficulty adaptability index can dynamically reflect the physiological and behavior states of the trainee, so that the training content can be specifically adjusted in real time according to the situation of the trainee, and the training difficulty is optimized.

Description

Technical Field

[0001] The present invention relates to the technical field of mine self - rescuers, and particularly to a method and system for monitoring the simulation training effect of mine self - rescuers. Background Art

[0002] A mine self - rescuer is a safety device used to protect miners in the event of a mine accident. A self - rescuer usually includes an oxygen - supply device and a gas mask, which can provide life support when harmful gas leakage occurs in the mine internal environment due to fires, explosions or other accidents. The continuous progress of self - rescuer technology, including the lightening of materials, the extension of the use time and the improvement of wearing comfort, is aimed at enhancing the survival ability and escape efficiency of miners. In addition, modern mine self - rescuers also integrate communication and positioning systems for effective rescue operations in emergency situations.

[0003] Among them, the method for monitoring the simulation training effect of mine self - rescuers is how to improve the ability of miners to use self - rescuers through simulation training and ensure that the training effect can be monitored and evaluated in real time. Training usually adopts a simulated - scene method, allowing miners to experience real mine escape scenarios in a safe environment, so as to improve their response ability in emergency situations. The aim is to improve the training quality and effect through real - time feedback, ensure that miners can effectively use self - rescuers in real crises, and protect their own safety.

[0004] The prior art cannot monitor and feedback the individual physiological state and operation behavior of trainees in real time. The training process lacks the ability of real - time data analysis and dynamic adjustment of trainees' reactions, resulting in the inability to optimize in a timely manner according to the actual performance and training effect of trainees. For example, trainees fail to conduct specialized training for their own physiological and operation weaknesses in simulation training, making the training effect unable to be maximized. Once trainees face real mine accidents, they may operate improperly due to failure to adapt to the training mode of emergency situations, increasing risks. In addition, the prior art relies on static training programs, unable to adjust in real time according to the progress of trainees in training, reducing the adaptability and flexibility of training, without real - time correction of behavior deviations, and prone to making wrong decisions at critical moments, affecting the use effect of self - rescuers. Summary of the Invention

[0005] The purpose of the present invention is to solve the deficiencies existing in the prior art, and to propose a method and system for monitoring the simulation training effect of mine self - rescuers.

[0006] To achieve the above purpose, the present invention adopts the following technical solutions: A method for monitoring the simulation training effect of mine self - rescuers, including the following steps,

[0007] S1: Collect data from the physiological monitoring device worn by the trainer, acquire the heart rate value and blood oxygen saturation, record the reaction time and error rate of the trainer's operation behavior simultaneously, and extract the device operation sequence and environmental change information to establish a physiological-behavior integration dataset;

[0008] S2: Based on the physiological-behavior integration dataset, analyze the change data of heart rate and blood oxygen, compare with the safety benchmark values, evaluate the deviation degree of heart rate and the decline range of blood oxygen, calculate the deviation ratio and deviation rate, and judge the adaptability of training difficulty to obtain the difficulty adaptability index;

[0009] S3: Call the physiological-behavior integration dataset, perform time window segmentation on the operation behavior, extract operation features, compare the features with the standard operation process of the mine self-rescuer, identify the operation sequences with low similarity, and judge the key behavior deviations to obtain the behavior deviation overview;

[0010] S4: Based on the difficulty adaptability index, evaluate the current simulated difficulty requirement, dynamically adjust the environmental parameters of the simulated mine, including the gas leakage rate and temperature control parameters, match the training conditions with the trainer's ability, and generate environmental parameter adjustment information.

[0011] The improvement of the present invention is that the difficulty adaptability index includes a heart rate deviation index, a blood oxygen decline index, a deviation ratio index, and a deviation rate index; the behavior deviation overview includes operation feature differences and behavior deviation points; the environmental parameter adjustment information includes a gas leakage adjustment value, a temperature adjustment value, and a process rhythm optimization coefficient.

[0012] The improvement of the present invention is that the acquisition steps of the physiological-behavior integration dataset are specifically as follows:

[0013] S111: Collect data from the physiological monitoring device worn by the trainer, acquire the heart rate value and blood oxygen saturation, record the reaction time and error rate of the trainer's operation behavior simultaneously, and match the data using time stamps to obtain a time-matched dataset;

[0014] S112: Based on the time-matched dataset, analyze the change trends of the heart rate value and blood oxygen saturation, and according to the reaction time and error rate, use the formula:

[0015]

[0016] Calculate the physiological-behavior correlation intensity RC s , where HC i represents the heart rate value at the i-th moment, OC i represents the blood oxygen saturation at the i-th moment, TC i represents the behavior reaction time at the i-th moment, EC i represents the error rate at the i-th moment, and n rcis the total amount of data;

[0017] S113: Invoke the physiological behavior association intensity, extract the device operation sequence and environmental change information, calculate the behavior change rate at the difference moment, and compare the physiological data fluctuation trend to establish a physiological behavior integration data set.

[0018] The improvement of the present invention is that the acquisition step of the difficulty adaptability index is specifically as follows:

[0019] S211: Based on the physiological behavior integration data set, analyze the change data of heart rate and blood oxygen, calculate the mean values (benchmark values) of heart rate and blood oxygen saturation at each measurement moment, and compare the deviation amplitudes between the heart rate value and blood oxygen saturation value and the corresponding mean values to obtain the deviation data of heart rate and blood oxygen;

[0020] S212: Based on the deviation data of heart rate and blood oxygen, combined with the behavior reaction time and error rate, use the formula:

[0021]

[0022] Calculate the offset ratio PD at each measurement moment s , where HC i represents the heart rate value at the i-th moment, HC b represents the benchmark heart rate, OC i represents the blood oxygen saturation at the i-th moment, OC b represents the benchmark blood oxygen saturation, TC i represents the behavior reaction time at the i-th moment, EC i represents the error rate at the i-th moment, n rc is the total amount of data;

[0023] S213: According to the offset ratio, perform normalization processing, analyze the change amplitude between measurement moments, and compare the upper and lower floating intervals of the offset ratio to judge the adaptability of training difficulty and obtain the difficulty adaptability index.

[0024] The improvement of the present invention is that the acquisition step of the behavior deviation overview is specifically as follows:

[0025] S311: Invoke the physiological behavior integration data set, perform time window segmentation on the operation behavior, extract the operation behavior characteristics within each time window, including operation trajectory, movement amplitude, and time persistence, and screen the behavior segments with abnormal changes in the feature vector to obtain the operation behavior feature deviation value;

[0026] S312: Based on the operation behavior feature deviation value, compare the extracted features with the standard operation process features of the mine self-rescuer, using the formula:

[0027]

[0028] Calculate the average feature deviation DZ to obtain a low-similarity operation sequence, where FZ m represents the m-th operation behavior feature value, and SZ m represents the corresponding standard operation process feature value, and n dz represents the dimension of the feature vector;

[0029] S313: Based on the low-similarity operation sequence, analyze the key behavior deviations of each behavior segment, identify the abnormal change trend and deviation direction of the operation features, determine the key behavior deviation areas that have an impact, and obtain a behavior deviation overview.

[0030] The improvement of the present invention is that the step of obtaining the environmental parameter adjustment information is specifically:

[0031] S411: Based on the difficulty adaptability index, monitor the gas leakage rate and temperature control parameters of the current simulated mine, analyze the matching degree between the training conditions and the trainer's ability, eliminate the samples with low matching degree, and obtain a matching degree screening result;

[0032] S412: According to the matching degree screening result, dynamically adjust the gas leakage rate and temperature control parameters, using the formula:

[0033]

[0034] to obtain the adjusted training environment parameter Pl new , where Rl represents the value of the current environmental parameter, and AL avg represents the average adaptability index obtained from the matching degree screening result, and AL target represents the target adaptability index;

[0035] S413: Based on the adjusted training environment parameter, optimize the operation process rhythm, match the training conditions with the trainer's ability, and generate environmental parameter adjustment information.

[0036] The improvement of the present invention is that the step further includes:

[0037] S5: According to the behavior deviation overview, analyze the frequently occurring deviation operation behaviors, combine the environmental parameter adjustment information, evaluate the impact of the training environment change on the trainer, and adjust the difficulty adaptation parameter according to the evaluation result to obtain a training simulation optimization result;

[0038] The training simulation optimization result includes environmental adaptability parameters and feedback rule adjustment information.

[0039] The improvement of the present invention is that the step of obtaining the training simulation optimization result is specifically:

[0040] S511: Analyze the frequently occurring deviation operation behaviors according to the behavior deviation overview, calculate the deviation amplitude of each operation behavior, compare it with the deviation benchmark, and count the operation behaviors with the deviation amplitude exceeding the benchmark to obtain the deviation behavior statistical parameters;

[0041] S512: Based on the deviation behavior statistical parameters and the environmental parameter adjustment information, evaluate the impact of the training environment change on the trainer, analyze the operation behavior change rate after the environmental parameter adjustment, and use the formula:

[0042]

[0043] Obtain the training environment impact factor IG and establish the training environment impact evaluation value, where BG h represents the deviation amplitude of the h-th deviation behavior, BG avg represents the deviation mean in the deviation behavior statistical parameters, BG std represents the deviation variance, n Ig represents the total number of deviation behaviors, and Eq represents the operation behavior change rate after the environmental parameter adjustment;

[0044] S513: Invoke the training environment impact evaluation value, adjust the difficulty adaptation parameter, and update the training feedback rule to obtain the training simulation optimization result.

[0045] A monitoring system for the simulation training effect of a mine self-rescuer, the system includes:

[0046] The physiological data integration module collects the data of the physiological monitoring equipment worn by the trainer, acquires the heart rate value and blood oxygen saturation, records the reaction time and error rate of the trainer's operation behavior at the same time, extracts the equipment operation sequence and environmental change information, and establishes a physiological behavior integration data set;

[0047] The training difficulty evaluation module analyzes the change data of the heart rate and blood oxygen based on the physiological behavior integration data set, compares with the safety benchmark value, evaluates the deviation degree of the heart rate and the decline amplitude of the blood oxygen, and combines the behavior reaction time and error rate to calculate the deviation ratio and deviation rate to obtain the difficulty adaptability index;

[0048] The behavior deviation identification module invokes the physiological behavior integration data set, divides the operation behavior into time windows, compares the features with the standard operation process of the mine self-rescuer, identifies the operation sequences with low similarity, and judges the key behavior deviations to obtain the behavior deviation overview;

[0049] The training environment regulation module evaluates the current simulation difficulty requirement based on the difficulty adaptability index, dynamically adjusts the environmental parameters of the simulated mine, matches the training conditions with the trainer's ability, optimizes the operation process rhythm, and generates environmental parameter adjustment information;

[0050] The training optimization module analyzes the frequently occurring deviation operation behaviors according to the behavior deviation overview, combines the environmental parameter adjustment information, evaluates the impact of the training environment change on the trainer, and adjusts the difficulty adaptation parameter based on the evaluation result to obtain the training simulation optimization result.

[0051] Compared with the prior art, the advantages and positive effects of the present invention are as follows:

[0052] In the present invention, by collecting the physiological data and operation behavior data of the trainer in real time, combining the environmental change information, a multi-dimensional physiological behavior integration data set is created, which not only reflects the heart rate and blood oxygen changes of the trainer in the simulation training, but also comprehensively considers the reaction time and error rate, providing a basis for evaluating the emergency response ability of the trainer. Using this data, the training difficulty adaptability index can dynamically reflect the physiological and behavioral states of the trainer, enabling the training content to be adjusted in a targeted manner according to the actual situation of the trainer in real time, optimizing the training difficulty, ensuring that the trainer can complete the training in the best state. By using the time window segmentation technology to conduct a detailed analysis of the operation behavior, behavior deviations can be effectively identified, ensuring that the trainer can correct key errors during the training process and improving the accuracy of the emergency response. The dynamic adjustment of the simulation environment further enhances the reality of the training, enabling the trainer to train in an environment close to the real situation, thereby improving the training effect and survival ability and reducing wrong decisions. BRIEF DESCRIPTION OF THE DRAWINGS

[0053] Figure 1 It is a flowchart of a method for monitoring the simulation training effect of a mine self-rescuer proposed by the present invention;

[0054] Figure 2 It is a flowchart for obtaining the physiological behavior integration data set in the present invention;

[0055] Figure 3 It is a flowchart for obtaining the difficulty adaptability index in the present invention;

[0056] Figure 4 It is a flowchart for obtaining the behavior deviation overview in the present invention;

[0057] Figure 5 It is a flowchart for obtaining the environmental parameter adjustment information in the present invention;

[0058] Figure 6 It is a flowchart for obtaining the training simulation optimization result in the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0059] In order to make the objectives, technical solutions and advantages of the present invention clearer and more understandable, the present invention will be further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not used to limit the present invention.

[0060] In the description of the present invention, it should be understood that the orientation or positional relationship indicated by the terms "length", "width", "upper", "lower", "front", "rear", "left", "right", "vertical", "horizontal", "top", "bottom", "inner", "outer", etc. is based on the orientation or positional relationship shown in the drawings. It is only for the convenience of describing the present invention and simplifying the description, rather than indicating or implying that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and therefore should not be construed as a limitation to the present invention. In addition, in the description of the present invention, the meaning of "a plurality of" is two or more, unless otherwise specifically defined.

[0061] Embodiment

[0062] Please refer to Figure 1 , the present invention provides a technical solution: a method for monitoring the simulation training effect of a mine self-rescuer, including the following steps:

[0063] S1: Collect the data of the physiological monitoring equipment worn by the trainer, collect the heart rate value and blood oxygen saturation, record the reaction time and error rate of the trainer's operation behavior at the same time, extract the equipment operation sequence and environmental change information, match the data through the time stamp, and establish a physiological behavior integration data set;

[0064] S2: Based on the physiological behavior integration data set, analyze the change data of the heart rate and blood oxygen, compare with the safety benchmark value, evaluate the deviation degree of the heart rate and the decrease amplitude of the blood oxygen, and combine the behavior reaction time and error rate to calculate the deviation ratio and deviation rate, judge the adaptability of the training difficulty, and obtain the difficulty adaptability index;

[0065] S3: Call the physiological behavior integration data set, perform time window segmentation on the operation behavior, extract operation features, compare the features with the standard operation process of the mine self-rescuer, identify the operation sequences with low similarity, judge the key behavior deviations, and obtain the behavior deviation overview;

[0066] S4: Based on the difficulty adaptability index, evaluate the current simulation difficulty requirements, dynamically adjust the environmental parameters of the simulated mine, including the gas leakage rate and temperature control parameters, match the training conditions with the trainer's ability, optimize the operation process rhythm, and generate environmental parameter adjustment information;

[0067] S5: According to the behavior deviation overview, analyze the frequently occurring deviation operation behaviors, combine the environmental parameter adjustment information, evaluate the impact of the training environment change on the trainer, adjust the difficulty adaptation parameters according to the evaluation results, and update the training feedback rules to obtain the training simulation optimization result.

[0068] The training feedback rules refer to the guiding principles and operation specifications used to evaluate and adjust the training process. For example:

[0069] The rules illustrate how to evaluate the performance of the trainer through the collected physiological and behavioral data;

[0070] The rules will set the circumstances under which feedback should be provided and the specific form of the feedback. If the trainer's heart rate continuously exceeds the safe value, it will automatically prompt or adjust the training difficulty;

[0071] Dynamically adjust the difficulty of the simulation environment according to the trainer's performance and physiological responses;

[0072] Identify and handle deviant behaviors during the training process. When behaviors inconsistent with the standard operation procedures are detected, the trainer will be prompted;

[0073] Use long-term data to track the training effect.

[0074] The difficulty adaptability index includes the heart rate deviation index, the blood oxygen decline index, the deviation ratio index, and the deviation rate index. The behavior deviation overview includes operation characteristic differences and behavior deviation points. The environmental parameter adjustment information includes the gas leakage adjustment value, the temperature adjustment value, and the process rhythm optimization coefficient. The training simulation optimization result includes environmental adaptability parameters and feedback rule adjustment information.

[0075] Please refer to Figure 2 , and the specific steps for obtaining the physiological and behavioral integration data set are as follows:

[0076] S111: Collect the data of the physiological monitoring equipment worn by the trainer, collect the heart rate value and blood oxygen saturation, and at the same time record the reaction time and error rate of the trainer's operation behavior, and use the time stamp to match the data to obtain a time-matched data set;

[0077] Data is collected from the trainee through a physiological monitoring device. During the collection process, the device needs to be fixed on the trainee's wrist or fingertip to ensure that the photoelectric sensor can stably detect the pulse signal and blood oxygen saturation. At the same time, the internal data storage unit of the device should be able to record the detection results per second and attach a timestamp for subsequent matching. While the data is being collected, the operation behavior monitoring system will record each operation of the trainee. The system uses a timing module to record the time length from the appearance of the task prompt to the actual completion of the trainee's operation and automatically analyze the operation result. If the trainee's operation is correct, the correctness of this operation will be recorded. If an error occurs, such as pressing the wrong button or omitting an operation, the system will record the corresponding error type and error ratio. In addition, the timestamp module will synchronously record the current time in all data entries for subsequent data matching. During the data collection process, a trainee completed 50 operations within 10 minutes, including 40 correct operations and 10 incorrect operations. The heart rate data collected by the device fluctuated between 80 - 120 beats per minute, and the blood oxygen saturation changed between 95% - 98%. The system will attach a timestamp to each piece of data to form a complete time-matched data set.

[0078] S112: Based on the time-matched data set, analyze the change trends of the heart rate value and blood oxygen saturation. According to the reaction time and error rate, use the formula:

[0079]

[0080] Calculate the physiological behavior correlation strength RC s , where HC i represents the heart rate value at the i-th moment, OC i represents the blood oxygen saturation at the i-th moment, TC i represents the behavioral reaction time at the i-th moment, reflecting the time length of the trainee's reaction to a certain task at the i-th measurement moment, EC i represents the error rate at the i-th moment, indicating the error ratio of the trainee during the task execution at the i-th measurement moment, n rc is the total amount of data, referring to the total number of measurement moments considered during the analysis;

[0081] Extract all data with timestamp matches, and sort out the heart rate values, blood oxygen saturation, reaction time, and error rate at each time point in chronological order. For the extraction of heart rate values, mean filtering needs to be performed on the original data of the sensor to remove abnormal fluctuations within a short period. For example, during continuous detection, if the heart rate value suddenly increases to 150 beats per minute at a certain moment, while the data before and after are both around 100 beats per minute, then this data is determined to be abnormal and interpolation correction is performed. The extraction method of blood oxygen saturation is similar, and correction needs to be performed at each time point. The reaction time is calculated by subtracting the time when the trainer finishes the operation from the task prompt time, and is recorded in seconds. The error rate is calculated as the number of incorrect operations within a unit time divided by the total number of operations. For example, within a time window, the trainer completes 3 operations, with 1 error, then the error rate is 1 / 3 ≈ 0.333. For the calculation of the physiological behavior correlation strength RC s Calculation;

[0082] Within a certain time period, there are 3 data points, with corresponding heart rate values of 98, 105, and 112 beats per minute, blood oxygen saturations of 97%, 96%, and 95% respectively, reaction times of 2.5, 2.8, and 3.1 seconds respectively, and error rates of 0.2, 0.25, and 0.3 respectively. Then calculate the numerator part:

[0083]

[0084] Calculate the denominator part:

[0085]

[0086] Obtain the physiological behavior correlation strength:

[0087]

[0088] This result indicates that within this time period, there is a certain degree of numerical correlation between the physiological indicators of the trainer and the operation performance.

[0089] S113: Call the physiological behavior correlation strength, extract the device operation sequence and environmental change information, calculate the behavior change rate at the difference moment, and compare the physiological data fluctuation trend to establish a physiological behavior integration dataset;

[0090] Sort the device operation sequences, arrange the time-matched data in chronological order, and analyze the operation habits of the trainer at different task stages. For example, if the pressing order of a specific button by the trainer changes within a certain time period, this operation change needs to be recorded. Calculate the behavior change rate at the moment of difference. The calculation method of the behavior change rate is to compare the operation modes at adjacent time points, extract the changed items, and calculate the proportion of the change. For example, if within the first minute, the operation mode executed by the trainer is [A, B, C], and in the second minute, the operation mode becomes [A, C, B], then calculate the change rate: Behavior change rate = Number of changed operations / Total number of operations = 2 / 3 = 0.67. Compare the physiological data fluctuation trends, and calculate the fluctuation amplitudes of the heart rate and blood oxygen saturation at the moment of change. For example, at a certain time point, the heart rate increases from 100 beats per minute to 120 beats per minute, and the blood oxygen saturation decreases from 97% to 94%. Then the fluctuation amplitudes are calculated as follows: Heart rate fluctuation amplitude = (120 - 100) / 100 = 0.2, Blood oxygen saturation fluctuation amplitude = (97 - 94) / 97 = 0.031. Finally, integrate all the data to establish a physiological behavior integrated data set.

[0091] Please refer to Figure 3 , and the specific steps for obtaining the difficulty adaptability index are as follows:

[0092] S211: Based on the physiological behavior integrated data set, analyze the change data of the heart rate and blood oxygen, calculate the mean values (benchmark values) of the heart rate and blood oxygen saturation at each measurement moment, and compare the deviation amplitudes between the heart rate values and blood oxygen saturation values and their corresponding means to obtain the deviation data of the heart rate and blood oxygen;

[0093] Extract the heart rate values and blood oxygen saturation data at each measurement moment, arrange all the measurement data in chronological order to ensure the data is complete and without missing values. If there are missing data, use linear interpolation method to supplement. Next, calculate the mean values of the heart rate and blood oxygen saturation at all measurement moments and define them as the benchmark heart rate and benchmark blood oxygen saturation respectively. The benchmark heart rate is a reference value used to measure the heart rate fluctuation range in an individual's normal state, and the benchmark blood oxygen saturation is used to judge the stability of the blood oxygen concentration. For example, if the measurement data of an individual's heart rate is 78, 80, 85, 82, and 79 beats per minute, then the benchmark heart rate is calculated as follows: Similarly, if the measurement data of blood oxygen saturation is 98%, 97%, 96%, 98%, and 97%, then the benchmark blood oxygen saturation is: Then, compare the difference between the heart rate value at each measurement moment and the reference heart rate to obtain heart rate deviation data. For example, for a heart rate value of 85 beats per minute at a measurement moment, its deviation is: |85 - 80.8| = 4.2 beats per minute. Similarly, calculate the deviation between the blood oxygen saturation and the reference blood oxygen saturation to obtain blood oxygen deviation data. For example, if the blood oxygen value at a certain measurement moment is 96%, then: |96 - 97.2| = 1.2%. Thus, the deviation data of heart rate and blood oxygen are obtained.

[0094] S212: Based on the deviation data of heart rate and blood oxygen, combined with the behavioral reaction time and error rate, use the formula:

[0095]

[0096] Calculate the offset ratio PD at each measurement moment s , where HC i represents the heart rate value at the i-th moment, HC b represents the reference heart rate, OC i represents the blood oxygen saturation at the i-th moment, OC b represents the reference blood oxygen saturation, TC i represents the behavioral reaction time at the i-th moment, EC i represents the error rate at the i-th moment, n rc is the total amount of data;

[0097] If the heart rate deviations of an individual at 3 measurement moments are [3.5, 2.8, 4.2] beats per minute respectively, the blood oxygen deviations are [1.1, 0.9, 1.3]% respectively, the behavioral reaction times are [0.85, 0.90, 1.05] seconds respectively, and the error rates are [0.04, 0.05, 0.06] respectively, then the calculation is as follows:

[0098] The numerator part (sum of heart rate deviation + blood oxygen deviation):

[0099]

[0100] The denominator part (sum of behavioral reaction time × error rate):

[0101]

[0102] Calculate the offset ratio:

[0103]

[0104] The result shows that the offset ratio data is 97.18, which reflects the overall change trend of the deviation degree of heart rate and blood oxygen of an individual at 3 measurement moments relative to the behavioral reaction time and error rate. The higher the offset ratio, the relatively larger the fluctuation range of physiological parameters.

[0105] S213: According to the offset ratio, perform normalization processing, analyze the change amplitude between measurement times, compare the upper and lower floating ranges of the offset ratio, judge the adaptability of training difficulty, and obtain the difficulty adaptability index;

[0106] Call the offset ratio data, perform normalization processing, calculate the change amplitude between each measurement time, and map all offset ratios to the interval from 0 to 1 for further analysis. For example, if the range of the offset ratio data is 100, 250, the min-max normalization method can be used: Taking PD s = 126.2 as an example: Calculate the normalized offset ratio of each measurement time, and calculate the fluctuation amplitude between each measurement time. Define the fluctuation amplitude as the change amount of the offset ratio between adjacent times. For example: Suppose the normalized offset ratios of an individual at 5 measurement times are 0.175, 0.230, 0.195, 0.210, 0.225, then its change amplitude is as follows:

[0107] ΔPD′ s = [|0.230 - 0.175|, |0.195 - 0.230|, |0.210 - 0.195|, |0.225 - 0.210|];

[0108] = [0.055, 0.035, 0.015, 0.015];

[0109] Compare the fluctuation range to judge its stability. If the overall fluctuation value is low, the individual's adaptation difficulty is low, otherwise it is high, and obtain the difficulty adaptability index.

[0110] Please refer to Figure 4 , and the specific steps for obtaining the behavior deviation overview are as follows:

[0111] S311: Call the physiological behavior integration dataset, perform time window segmentation on the operation behavior, extract the operation behavior characteristics within each time window, including operation trajectory, movement amplitude, and time persistence, and screen out the behavior segments with abnormal changes in the feature vector to obtain the operation behavior feature deviation value;

[0112] The data is segmented according to fixed time windows (such as 1 second, 5 seconds, or 10 seconds). The selection of different time windows directly affects the granularity of the data. Taking 5 seconds as an example, a complete operation process is segmented into multiple windows, and each window corresponds to the operation data of a time segment. After the time window is divided, the operation behavior characteristics are extracted from each time window. The characteristics usually include the operation trajectory, movement amplitude, and time persistence. Specifically, the operation trajectory is obtained by calculating the hand movement path. For example, the Euclidean distance of the hand movement is calculated in a three-dimensional coordinate system, setting the starting point and the ending point, and calculating the total path length. If the operation trajectory shows a large deviation, it represents an incorrect operation. The movement amplitude is obtained by analyzing the changes in acceleration and angular velocity. For example, calculating the change range of acceleration in different axes. If the operation amplitude is too small, it represents an incomplete or insufficient action. The time persistence is used to evaluate whether the operation time meets the standard. For example, for the operation of pulling the oxygen supply valve of the mine self-rescuer, if it takes 2 - 3 seconds, the time ratio of this action needs to be counted in the time window. If it is less than 2 seconds or greater than 3 seconds, it indicates that there is a deviation in the operation. Then, the behavior segments with abnormal changes in the feature vectors are screened. This step usually involves calculating the change rate of the features, such as calculating the change amplitude of the feature values between adjacent time windows. For example, calculating the mean square error of the acceleration change within adjacent time windows. If the mean square error of a certain time window exceeds the set threshold (such as 1.5 times the standard deviation), it can be determined as an abnormal behavior segment, and the operation behavior feature deviation value is obtained.

[0113] S312: Based on the operation behavior feature deviation value, compare the extracted features with the standard operation process features of the mine self-rescuer, and use the formula:

[0114]

[0115] Calculate the average feature deviation DZ to obtain a low-similarity operation sequence, where FZ m represents the m-th operation behavior feature value, SZ m represents the corresponding standard operation process feature value, and n dz represents the dimension of the feature vector;

[0116] The 3 feature data of a certain operation process are as follows:

[0117] The actual feature value of the operator is FZ = [2.5, 1.8, 4.2];

[0118] The standard operation process feature value is SZ = [2.0, 2.0, 4.0];

[0119] Substitute into the calculation:

[0120]

[0121] If the set threshold is T dz= 0.3. Since DZ = 0.3 is equal to the threshold value, it is determined that this operation behavior belongs to a low - similarity operation sequence, and the start and end times, the involved feature dimensions, and the deviation amount of this sequence are recorded for subsequent analysis.

[0122] S313: Based on the low - similarity operation sequence, analyze the key behavior deviations of each behavior segment, identify the abnormal change trends and deviation directions of operation features, determine the key behavior deviation regions that have an impact, and obtain an overview of behavior deviations;

[0123] Parse each time segment in the low - similarity operation sequence, extract the feature dimensions with larger deviations. For example, if the hand acceleration deviation is large in a certain segment, mark this segment as a high - deviation region. Then, identify the abnormal change trends of operation features. For example, calculate the deviation change rate in the time series to determine whether the deviation is gradually increasing, remaining stable, or suddenly increasing. For example, calculate the change trend of the hand angular velocity. If the angular velocity increases from 0.2 to 1.5 within 3 seconds, it is determined as a sudden - increase trend. Further, analyze the deviation direction, that is, whether the main deviation feature of the operation behavior is lower than the standard value or higher than the standard value. For example, if the pulling force is lower than the standard value, it is an insufficient operation; if it exceeds the standard value, it is a misoperation. Through the above analysis, determine the key behavior deviation regions that have an impact and obtain an overview of behavior deviations.

[0124] Please refer to Figure 5 , and the steps for obtaining the environmental parameter adjustment information are specifically as follows:

[0125] S411: Based on the difficulty adaptability index, monitor the gas leakage rate and temperature control parameters of the current simulated mine, analyze the matching degree between the training conditions and the trainer's ability, eliminate the samples with low matching degree, and obtain the matching - degree screening results;

[0126] Monitor the gas leakage rate and temperature control parameters of the current simulated mine. By deploying gas sensors and temperature monitoring devices in different regions inside the mine, regularly collect data and store it in the database, call the historical environmental parameter data, compare with the current monitoring values to identify the change trend of the environmental state, calculate the matching degree between the training conditions and the trainer's ability, cross - analyze the trainer's operation data (such as reaction time, accuracy, misoperation rate) and environmental parameters, and use the normalization processing method to calculate the adaptability index of each trainer under different environmental parameters. For example, if the operation correct rate of a certain trainer is 85% at a temperature of 30°C and a gas leakage rate of 5 ppm, and drops to 70% at 35°C and 8 ppm, then calculate the difficulty adaptability index of this environmental condition, set the adaptability index threshold (for example, 0.75), and eliminate the samples below this threshold to obtain the matching - degree screening results.

[0127] S412: According to the matching - degree screening results, dynamically adjust the gas leakage rate and temperature control parameters, using the formula:

[0128]

[0129] Obtain the adjusted training environment parameter Pl new , where Rl represents the value of the current environment parameter, which is the current gas leakage rate or the current temperature control parameter value, AL avg represents the average adaptability index obtained from the matching degree screening results, that is, the average of the adaptability indices of all selected samples, AL target represents the target adaptability index, which is the standard or desired adaptability level;

[0130] If the current gas leakage rate Rl gas = 5 ppm, the average adaptability index AL avg = 0.68, and the target adaptability index AL target = 0.75, substitute into the formula for calculation:

[0131]

[0132] The calculation results show that the gas leakage rate should be reduced to 4.53 ppm to optimize the adaptability of the trainer.

[0133] If the current temperature control parameter Rl temp = 35 °C, the average adaptability index AL avg = 0.72, and the target adaptability index AL target = 0.75;

[0134] Substitute into the formula for calculation:

[0135]

[0136] The calculation results show that the temperature should be adjusted to 33.6 °C to match the adaptability of the trainer.

[0137] S413: Based on the adjusted training environment parameters, optimize the operation process rhythm, match the training conditions with the trainer's ability, and generate environment parameter adjustment information;

[0138] Optimize the operation process rhythm, analyze the impact of the adjusted parameters on the trainer's operation behavior, such as monitoring the trainer's reaction time, error rate, and operation stability, collecting the trainer's operation records, and calculating the changes in training parameters before and after adjustment. For example, before adjustment, the average reaction time of the trainer at a gas leakage rate of 5 ppm was 1.2 s, and the error rate was 15%. After adjustment, at a gas leakage rate of 4.53 ppm, the reaction time was shortened to 1.1 s, and the error rate was reduced to 10%. This shows that the environmental adjustment optimized the trainer's operation stability, matched the training conditions with the trainer's ability, and generated environment parameter adjustment information.

[0139] Please refer to Figure 6 , the steps for obtaining the training simulation optimization results are specifically as follows:

[0140] S511: According to the behavior deviation overview, analyze the frequently occurring deviation operation behaviors, calculate the deviation magnitude of each operation behavior, compare it with the deviation benchmark, and count the operation behaviors with a deviation magnitude exceeding the benchmark to obtain the deviation behavior statistical parameters;

[0141] Extract the actual execution parameters of each operation behavior and compare them with the standard parameters, calculate their absolute difference or relative deviation rate. For example, assume that a trainer should perform operation A to the target value of 100 in a certain training task, and the actual execution result is 85, then the deviation magnitude can be expressed as |100 - 85| = 15. For operation behaviors involving continuity or dynamic adjustment, time series or difference methods can be used to calculate their deviation trends. For example, calculate the deviation change rate for multiple execution results (such as 95, 90, 85) of an operation behavior. After calculating the deviation magnitudes of multiple different operation behaviors, compare the calculation results with the deviation benchmark. The deviation benchmark can be set based on historical training data, industry standards, or preset reference values. For example, if the standard in a certain training scenario allows a deviation not exceeding ±10, then the operation behaviors exceeding this range are recorded as over-benchmark behaviors, and count the operation behaviors with a deviation magnitude exceeding the benchmark to obtain the deviation behavior statistical parameters. This parameter includes the occurrence times, mean value, variance of different deviation behaviors, and their distributions under different environmental conditions, so as to be used for subsequent evaluation of the trainer's adaptability and learning ability.

[0142] S512: Based on the deviation behavior statistical parameters and environmental parameter adjustment information, evaluate the impact of training environment changes on the trainer, analyze the operation behavior change rate after environmental parameter adjustment, and use the formula:

[0143]

[0144] Obtain the training environment impact factor IG and establish the training environment impact evaluation value, where BG h represents the deviation magnitude of the h-th deviation behavior, BG avg represents the deviation mean value in the deviation behavior statistical parameters, BG std represents the deviation variance, n Ig represents the total number of deviation behaviors, and Eq represents the operation behavior change rate after environmental parameter adjustment;

[0145] If BG1 = 7, BG2 = 11 (the deviation magnitudes of two deviation behaviors), BG avg (deviation mean value) is calculated as:

[0146]

[0147] BG std (The bias-variance) is calculated as:

[0148]

[0149] If Eq = 1.05 (the change rate of the operation behavior after adjusting the environmental parameters), calculate the IG value:

[0150]

[0151] The result shows that the influence factor IG of the training environment adjustment on the trainer is 1.05, indicating that the environmental change has a slight impact on the operation behavior of the trainer. The deviation range slightly increases in the adjusted training environment but remains within a relatively stable range. If this value is much greater than 1, it means that the environmental adjustment has a large interference on the operation behavior of the trainer, and it is necessary to further adjust the training tasks or training feedback rules to adapt to the new environmental conditions.

[0152] S513: Invoke the training environment impact evaluation value, adjust the difficulty adaptation parameter, and update the training feedback rule to obtain the optimized training simulation result;

[0153] Determine the adjustment range of the difficulty adaptation parameter according to the training environment impact evaluation value. If the influence factor IG caused by the environmental change is large, it is necessary to adjust the difficulty of the training task to ensure the adaptability of the trainer. For example, assuming the original difficulty adaptation parameter is 1.2, and the calculated influence factor IG = 1.5, then the difficulty adaptation parameter can be adjusted to 1.2 × 1.5 = 1.8. At the same time, according to the new difficulty adaptation parameter, reset the training feedback rule. For example, if the original feedback rule is that the deviation range is less than 5 is judged as qualified, then after adjustment, the qualified standard needs to be dynamically adjusted to 5 × 1.8 = 9 to adapt to the new training difficulty requirements and obtain the optimized training simulation result. This result includes the adjusted training task difficulty, feedback standard, and corresponding training adaptability evaluation data.

[0154] A monitoring system for the simulation training effect of a mine self-rescuer. The system includes:

[0155] The physiological data integration module collects the data of the physiological monitoring equipment worn by the trainer, acquires the heart rate value and blood oxygen saturation, and at the same time records the reaction time and error rate of the trainer's operation behavior, and extracts the equipment operation sequence and environmental change information to establish a physiological behavior integration data set;

[0156] The training difficulty evaluation module analyzes the change data of the heart rate and blood oxygen based on the physiological behavior integration data set, compares with the safety benchmark value, evaluates the deviation degree of the heart rate and the decline range of the blood oxygen, and combines the behavior reaction time and error rate to calculate the deviation ratio and deviation rate to obtain the difficulty adaptability index;

[0157] The behavior deviation identification module calls the physiological behavior integration dataset, performs time window segmentation on the operation behavior, compares the features with the standard operation process of the mine self-rescuer, identifies the operation sequences with low similarity, judges the key behavior deviations, and obtains an overview of the behavior deviations;

[0158] The training environment regulation module evaluates the current simulated difficulty requirements based on the difficulty adaptability index, dynamically adjusts the environmental parameters of the simulated mine, matches the training conditions with the capabilities of the trainees, optimizes the operation process rhythm, and generates information on environmental parameter adjustment;

[0159] The training optimization module analyzes the frequently occurring deviation operation behaviors according to the overview of the behavior deviations, combines the information on environmental parameter adjustment, evaluates the impact of the training environment change on the trainees, and adjusts the difficulty adaptation parameters according to the evaluation results to obtain the optimized result of the training simulation.

[0160] The above are only the preferred embodiments of the present invention, and do not limit the present invention in other forms. Any person skilled in the art may use the technical content disclosed above to make changes or modifications into equivalent embodiments with equivalent changes and apply them to other fields. However, as long as the technical solution content of the present invention is not departed from, any simple modification, equivalent change and modification made to the above embodiments according to the technical essence of the present invention still fall within the protection scope of the technical solution of the present invention.

Claims

1. A monitoring method for the simulation training effect of a mine self-rescuer, characterized in that, It includes the following steps: S1: Collect the data of the physiological monitoring device worn by the trainer, collect the heart rate value and blood oxygen saturation, record the reaction time and error rate of the trainer's operation behavior at the same time, extract the device operation sequence and environmental change information, and establish a physiological behavior integration dataset; S2: Based on the physiological behavior integration dataset, analyze the change data of heart rate and blood oxygen, compare with the safety reference value, evaluate the deviation degree of heart rate and the decline range of blood oxygen, calculate the deviation ratio and deviation rate, judge the adaptability of training difficulty, and obtain the difficulty adaptability index; S3: Call the physiological behavior integration dataset, perform time window segmentation on the operation behavior, extract operation features, compare the features with the standard operation process of the mine self-rescuer, identify the operation sequences with low similarity, judge the key behavior deviations, and obtain the behavior deviation overview; S4: Based on the difficulty adaptability index, evaluate the current simulated difficulty requirement, dynamically adjust the environmental parameters of the simulated mine, including the gas leakage rate and temperature control parameters, match the training conditions with the trainer's ability, and generate environmental parameter adjustment information.

2. The monitoring method for the simulation training effect of the mine self-rescuer according to claim 1, characterized in that, The difficulty adaptability index includes a heart rate deviation index, a blood oxygen decline index, a deviation ratio index, and a deviation rate index. The behavior deviation overview includes operation feature differences and behavior deviation points. The environmental parameter adjustment information includes a gas leakage adjustment value, a temperature adjustment value, and a process rhythm optimization coefficient.

3. The monitoring method for the simulation training effect of the mine self-rescuer according to claim 1, characterized in that, The specific steps for obtaining the physiological behavior integration dataset are as follows: S111: Collect the data of the physiological monitoring device worn by the trainer, collect the heart rate value and blood oxygen saturation, record the reaction time and error rate of the trainer's operation behavior at the same time, and match the data using a time stamp to obtain a time-matched dataset; S112: Based on the time-matched dataset, analyze the change trends of heart rate value and blood oxygen saturation, and according to the reaction time and error rate, use the formula: Calculate the physiological behavior correlation intensity RC s , where HC i represents the heart rate value at the i-th moment, OC i represents the blood oxygen saturation at the i-th moment, TC i represents the behavioral reaction time at the i-th moment, EC i represents the error rate at the i-th moment, and n rc is the total amount of data; S113: Call the physiological behavior association intensity, extract the device operation sequence and environmental change information, calculate the behavior change rate at the difference moment, and compare with the physiological data fluctuation trend to establish a physiological behavior integration dataset.

4. The monitoring method for the simulation training effect of the mine self-rescuer according to claim 1, wherein, The specific steps for obtaining the difficulty adaptability index are as follows: S211: Based on the physiological behavior integration dataset, analyze the change data of heart rate and blood oxygen, calculate the mean value (reference value) of heart rate and blood oxygen saturation at each measurement moment, and compare the deviation amplitude between the heart rate value and blood oxygen saturation value and the corresponding mean value to obtain the deviation data of heart rate and blood oxygen; S212: Based on the deviation data of heart rate and blood oxygen, combined with the behavior reaction time and error rate, use the formula: Calculate the offset ratio PD at each measurement moment s , where HC i represents the heart rate value at the i-th moment, HC b represents the reference heart rate, OC i represents the blood oxygen saturation at the i-th moment, OC b represents the reference blood oxygen saturation, TC i represents the behavioral reaction time at the i-th moment, EC i represents the error rate at the i-th moment, n rc is the total amount of data; S213: According to the deviation ratio, perform normalization processing, analyze the change amplitude between measurement moments, and compare the upper and lower floating intervals of the deviation ratio to judge the adaptability of training difficulty and obtain the difficulty adaptability index.

5. The monitoring method for the simulation training effect of the mine self-rescuer according to claim 1, characterized in that The specific steps for obtaining the behavior deviation overview are as follows: S311: Call the physiological behavior integration dataset, perform time window segmentation on the operation behavior, extract the operation behavior features within each time window, including operation trajectory, movement amplitude, and time persistence, and screen out the behavior segments with abnormal changes in the feature vector to obtain the operation behavior feature deviation value; S312: Based on the operation behavior feature deviation value, compare the extracted features with the standard operation process features of the mine self-rescuer, using the formula: Calculate the average feature deviation DZ to obtain a low similarity operation sequence, where FZ m represents the m-th operation behavior feature value, SZ m represents the corresponding standard operation process feature value, n dz represents the dimension of the feature vector; S313: Based on the low similarity operation sequence, analyze the key behavior deviations of each behavior segment, identify the abnormal change trend and deviation direction of the operation features, determine the key behavior deviation area affecting the key, and obtain the behavior deviation overview.

6. The method for monitoring the simulation training effect of a mine self-rescuer according to claim 1, wherein The specific steps for obtaining the environmental parameter adjustment information are as follows: S411: Based on the difficulty adaptability index, monitor the gas leakage rate and temperature control parameters of the current simulated mine, analyze the matching degree between the training conditions and the trainer's ability, eliminate the samples with low matching degree, and obtain the matching degree screening result; S412: According to the matching degree screening result, dynamically adjust the gas leakage rate and temperature control parameters, using the formula: Obtain the adjusted training environment parameter Pl new , where Rl represents the value of the current environment parameter, and AL avg represents the average adaptability index obtained from the matching degree screening results, and AL target represents the target adaptability index; S413: Based on the adjusted training environment parameters, optimize the operation process rhythm, match the training conditions with the trainer's ability, and generate the environmental parameter adjustment information.

7. The monitoring method for the simulation training effect of the mine self-rescuer according to claim 1, characterized in that The steps further include: S5: According to the behavior deviation overview, analyze the frequently occurring deviation operation behaviors, combine the environmental parameter adjustment information, evaluate the impact of the training environment change on the trainer, and adjust the difficulty adaptation parameter according to the evaluation result to obtain the training simulation optimization result; The training simulation optimization result includes environmental adaptability parameters and feedback rule adjustment information.

8. The monitoring method for the simulation training effect of the mine self-rescuer according to claim 7, characterized in that, The specific steps for obtaining the training simulation optimization result are as follows: S511: According to the behavior deviation overview, analyze the frequently occurring deviation operation behaviors, calculate the deviation amplitude of each operation behavior, compare it with the deviation benchmark, and count the operation behaviors with the deviation amplitude exceeding the benchmark to obtain the deviation behavior statistical parameter; S512: Based on the deviation behavior statistical parameter and the environmental parameter adjustment information, evaluate the impact of the training environment change on the trainer, analyze the operation behavior change rate after the environmental parameter adjustment, using the formula: Obtain the training environment impact factor IG and establish the training environment impact assessment value, where BG h represents the deviation amplitude of the h-th deviation behavior, BG avg represents the deviation mean in the deviation behavior statistical parameters, BG std represents the deviation variance, n Ig represents the total number of deviation behaviors, and Eq represents the operation behavior change rate after environmental parameter adjustment; S513: Call the training environment impact evaluation value, adjust the difficulty adaptation parameter, and update the training feedback rule to obtain the training simulation optimization result.

9. A monitoring system for the simulation training effect of a mine self-rescuer, characterized in that, Executed according to the mine self-rescuer simulation training effect monitoring method described in any one of claims 1-8, the system includes: The physiological data integration module collects the data of the physiological monitoring device worn by the trainer, collects the heart rate value and blood oxygen saturation, records the reaction time and error rate of the trainer's operation behavior at the same time, and extracts the device operation sequence and environmental change information to establish a physiological behavior integration dataset; The training difficulty evaluation module analyzes the change data of the heart rate and blood oxygen based on the physiological behavior integration dataset, compares with the safety benchmark value, evaluates the deviation degree of the heart rate and the decline amplitude of the blood oxygen, and combines the behavior reaction time and error rate to calculate the deviation ratio and deviation rate to obtain the difficulty adaptability index; The behavior deviation identification module calls the physiological behavior integration dataset, performs time window segmentation on the operation behavior, compares the features with the standard operation process of the mine self-rescuer, identifies the operation sequences with low similarity, judges the key behavior deviations, and obtains the behavior deviation overview; The training environment regulation module evaluates the current simulated difficulty requirement based on the difficulty adaptability index, dynamically adjusts the environmental parameters of the simulated mine, matches the training conditions with the trainer's ability, optimizes the operation process rhythm, and generates the environmental parameter adjustment information; The training optimization module analyzes the frequently occurring deviation operation behaviors according to the behavior deviation overview, combines the environmental parameter adjustment information, evaluates the impact of the training environment change on the trainer, and adjusts the difficulty adaptation parameters according to the evaluation result to obtain the training simulation optimization result.

Images