Intelligent wearing simulation evaluation system and method for mining self-rescuer

Abstract

The invention relates to the technical field of mining self-rescue use training, and discloses an intelligent simulated wearing evaluation system and method for a mining self-rescuer, and the system simulates the whole process of wearing the self-rescuer by a miner in an actual working environment, and comprises the steps of wearing, use, respiratory resistance simulation, separation and the like. The objective and accurate quantitative evaluation of the operation skill of the wearer is realized. The system integrates a data acquisition module, an intelligent evaluation module, a control module, a feedback training module, a man-machine interaction module, a data storage module and the like, various data in the wearing simulation process can be acquired in real time, quantitative scoring is performed according to a preset evaluation standard, and a detailed evaluation report is output. Meanwhile, the system can also generate targeted training suggestions according to the evaluation report, and provide a simulated training scene for the wearer to practice repeatedly. According to the method, the training efficiency and effect are improved, the training cost is reduced, powerful support is provided for safety training of miners, and the method is of great significance in guaranteeing life safety of the miners.

Description

Technical Field

[0001] The present invention relates to the technical field of mine self-rescue training equipment, and in particular to an intelligent simulation wearing assessment system and method for mine self-rescue equipment. Background Art

[0002] In the mining industry, the safety of miners is of vital importance. As an important life-saving device for miners in emergencies underground, the correct wearing and use of mining self-rescuers is of vital importance to the life safety of miners. However, the traditional training method of wearing self-rescuers often relies on manual guidance and field exercises, which has many limitations.

[0003] Traditional training methods make it difficult to conduct objective and accurate quantitative evaluation of the wearer's operating skills. Training instructors can usually only judge the wearer's operation based on experience or subjective feelings. The lack of unified and scientific evaluation standards has led to doubts about the accuracy and fairness of the evaluation results.

[0004] Traditional training methods are difficult to simulate the complex situations in the actual working environment. When miners work underground, they may face various complex environmental factors, such as high temperature, high humidity, breathing resistance, etc. These factors will affect the wearing and use of self-rescuers. However, traditional training methods can often only be carried out in a relatively simple environment, and cannot fully simulate the actual working scene, thus affecting the training effect. Traditional training methods also have the problems of high training costs and low efficiency. Due to the need for on-site drills and manual guidance, a lot of manpower, material resources and time costs are consumed in the training process. At the same time, since the training effect is difficult to quantify and evaluate, trainers often find it difficult to accurately grasp the skill level of the wearer, resulting in low training efficiency. Summary of the invention

[0005] The purpose of the present invention is to provide an intelligent simulation wearing assessment system and method for a mining self-rescuer to solve the problems raised in the above-mentioned background technology.

[0006] To achieve the above-mentioned purpose, the present invention provides the following technical solution: an intelligent simulation wearing assessment system for a mining self-rescuer, the system comprising:

[0007] The simulation wearing module is used to simulate the whole process of miners wearing the self-rescuer in the actual working environment, including the wearing, use, breathing resistance simulation and removal of the self-rescuer;

[0008] The data acquisition module is connected to the simulated wearing module and is used to collect various data in the simulated wearing process in real time, including wearing time, wearing correctness, breathing rate, breathing resistance, self-rescuer pressure and ambient temperature;

[0009] The intelligent evaluation module is connected to the data acquisition module, and is used to receive and process the collected data, quantitatively score the wearer's operating skills according to the preset evaluation criteria, and output an evaluation report;

[0010] A control module, connected to the simulated wearing module and the intelligent evaluation module, for controlling the start, pause, and end of the simulated wearing process and adjusting the simulated environment parameters;

[0011] The feedback training module is connected to the intelligent evaluation module to generate targeted training suggestions based on the evaluation report and provide simulated training scenarios for the wearer to practice repeatedly;

[0012] A human-computer interaction interface, connected to the control module and the intelligent evaluation module, is used to display real-time data, evaluation reports and training suggestions during the simulated wearing process, and receive the wearer's operating instructions;

[0013] The data storage module is connected to the data acquisition module, the intelligent evaluation module and the feedback training module, and is used to store all data, evaluation criteria, evaluation reports and training records during the simulated wearing process.

[0014] Preferably, the wearing time includes the time from the start of wearing to the completion of wearing and the time from the start of using the self-rescuer to the detachment;

[0015] The correctness of wearing includes whether the position of the self-rescuer is correct, whether the wearing steps are standard, and whether the self-rescuer is fastened;

[0016] The respiratory rate includes the average respiratory rate and the maximum respiratory rate during the simulated wearing process;

[0017] The breathing resistance includes the breathing resistance value and its changing trend of the self-rescuer at different use stages;

[0018] The self-rescuer pressure includes the change of the internal pressure of the self-rescuer;

[0019] The ambient temperature includes the ambient temperature and its fluctuation range during the simulated wearing process.

[0020] Preferably, the intelligent evaluation module uses a decision tree algorithm to construct a scoring model, and the scoring model is used to quantitatively score the wearer's operating skills.

[0021] Preferably, the scoring model is constructed in the following steps:

[0022] S1: Obtain the training data set of the scoring model and perform data preprocessing;

[0023] S2: Select features that have an important impact on the evaluation target from the preprocessed training data set as input features of the decision tree algorithm; the input features include wearing time, wearing correctness, breathing rate, breathing resistance, self-rescuer pressure and ambient temperature;

[0024] S3: Using the selected features as independent variables and the preset evaluation criteria as dependent variables, a decision tree model is constructed using a decision tree algorithm; the decision tree algorithm uses the following formula for node splitting:

[0025]

[0026] Among them, G(D,A) represents the information gain of data set D on feature A, H(D) represents the entropy of data set D, Values(A) represents all possible values ​​of feature A, and D v represents the subset of feature A in dataset D whose value is v, |D| and |D v | respectively represent the dataset D and subset D v The number of samples;

[0027] S4: Use the preprocessed data set to train the decision tree model, recursively select the optimal features for node splitting, and obtain a trained decision tree model until the stopping condition is met;

[0028] S5: inputting the simulated wearing data to be evaluated into the trained decision tree model, and obtaining a quantitative score of the wearer's operating skills according to the branch paths and leaf node values ​​of the decision tree;

[0029] S6: Integrate the quantitative scores into an evaluation report and display it to the wearer through a human-computer interaction interface.

[0030] Preferably, the Pearson correlation coefficient is used to select features that have a significant impact on the evaluation target from the preprocessed data set, and the specific implementation steps include:

[0031] S201: For each pair of features in the preprocessed data set, calculate the Pearson correlation coefficient. The formula is as follows:

[0032]

[0033] Among them, r represents the Pearson correlation coefficient between feature x and feature y, X i and Y i Respectively represent the values ​​of feature x and feature y on the i-th sample, and They represent the mean of feature x and feature y respectively, and n represents the number of samples;

[0034] S202: According to the calculated Pearson correlation coefficient, select several candidate features with higher absolute values ​​of the correlation coefficient as features that have a significant impact on the evaluation target;

[0035] S203: Using the selected features as independent variables and the preset evaluation criteria as dependent variables, a decision tree model is constructed using a decision tree algorithm, and subsequent training and quantitative scoring are performed.

[0036] Preferably, the method for obtaining the training data set of the scoring model is:

[0037] S101: Organize miners to wear the self-rescuer in an actual working environment, and use the data acquisition module to collect various data in the wearing process in real time, including wearing time, wearing correctness, breathing frequency, breathing resistance, self-rescuer pressure and ambient temperature, as actual wearing data;

[0038] S102: In a simulation environment, a simulation wearing module is used to simulate the whole process of a miner wearing a self-rescuer, and a data collection module is also used to collect various data in the simulation wearing process in real time as simulation wearing data;

[0039] S103: annotating the actual wearing data and the simulated wearing data, and marking each set of data with a corresponding evaluation label according to a preset evaluation standard, wherein the evaluation label includes "excellent", "good", "qualified" or "unqualified", which serves as supervised learning information for the decision tree model;

[0040] S104: synthesize the actual wearing data and the simulated wearing data into a training data set, and divide it into a training set and a validation set according to a certain ratio; the training set is used to train the decision tree model, and the validation set is used to verify the performance of the model and adjust the model parameters.

[0041] Preferably, the control module further comprises:

[0042] The simulation environment parameter setting submodule is used to set the environmental parameters during the simulation wearing process, including temperature, humidity, air pressure and harmful gas concentration;

[0043] The process control submodule is used to control the start, pause and end of the simulated wearing process and monitor various data in the simulated wearing process in real time;

[0044] The emergency simulation submodule is used to trigger emergency situations randomly or according to a preset program during the simulated wearing process to evaluate the wearer's ability to deal with emergencies.

[0045] Preferably, the feedback training module further comprises:

[0046] The training suggestion generation submodule is used to generate targeted training suggestions based on the deficiencies and improvement suggestions in the evaluation report;

[0047] The simulation training scenario submodule is used to generate simulation training scenarios based on training suggestions for the wearer to practice repeatedly;

[0048] The training effect evaluation submodule is used to evaluate the wearer's performance in the simulated training scenario and generate a training effect report.

[0049] Preferably, the human-computer interaction interface further comprises:

[0050] Data display area, used to display various data in the simulated wearing process in real time;

[0051] Evaluation report area, used to display the evaluation report and its detailed contents;

[0052] Training suggestion area, used to display targeted training suggestions and simulated training scenarios;

[0053] The operation instruction area is used to receive the wearer's operation instructions, including starting, pausing, and ending simulated wearing and adjusting simulated environment parameters.

[0054] Preferably, a method for intelligent simulation wearing assessment of a mining self-rescuer comprises the following steps:

[0055] Step 1: Send instructions to the control module through the human-computer interaction interface to start the intelligent simulation wearing assessment system for mining self-rescuers, and set the simulation environment parameters according to actual needs, including ambient temperature and breathing resistance simulation level; the control module controls the simulation wearing module to enter the preset simulation wearing state according to the received instructions and parameter settings;

[0056] Step 2: The wearer wears, uses, simulates breathing resistance and disengages the self-rescuer according to the instructions of the simulation wearing module; the data acquisition module collects various data in the simulation wearing process in real time, including wearing time, wearing correctness, breathing frequency, breathing resistance, self-rescuer pressure and ambient temperature, and transmits the collected data to the data storage module for storage;

[0057] Step 3: The intelligent evaluation module reads the collected data from the data storage module, pre-processes and analyzes the data; according to the preset evaluation criteria, the decision tree algorithm is used to quantitatively score the wearer's operating skills; an evaluation report including the wearer's operating skill score, various data indicators and evaluation conclusions is generated, and the evaluation report is stored in the data storage module;

[0058] Step 4: The human-computer interaction interface reads the evaluation report from the data storage module and displays it to the wearer; the feedback training module generates targeted training suggestions based on the evaluation report and provides simulated training scenarios for the wearer to practice repeatedly; the wearer views the evaluation report and training suggestions through the human-computer interaction interface and performs feedback training as needed;

[0059] Step 5: The control module controls the simulated wearing module to end the simulated wearing process according to preset conditions or the wearer's operating instructions; the data storage module stores all the data, evaluation criteria, evaluation reports and training records of this simulated wearing.

[0060] Compared with the prior art, the present invention has the following beneficial effects:

[0061] Through the intelligent evaluation module, this system can receive and process various data collected in real time by the data acquisition module during the simulated wearing process, including wearing time, wearing correctness, breathing frequency, breathing resistance, self-rescuer pressure and ambient temperature, etc. According to the preset unified and scientific evaluation standards, the system can objectively and accurately quantify the wearer's operating skills and output a detailed evaluation report, which effectively solves the problems of strong subjectivity, lack of accuracy and fairness in traditional training methods, and improves the scientificity and credibility of the evaluation.

[0062] The simulated wearing module can simulate the whole process of miners wearing the self-rescuer in the actual working environment, including the key links of wearing, using, simulating breathing resistance and detaching the self-rescuer. At the same time, the control module can flexibly adjust the simulated environmental parameters, such as temperature, humidity, breathing resistance, etc., to fully simulate the complex working environment underground, making the training closer to reality, improving the training effect, and helping the wearer better adapt to and deal with various situations in actual work.

[0063] This system adopts intelligent and automated training methods, reducing the need for manual guidance and field exercises, thereby significantly reducing the manpower, material and time costs of training. At the same time, since the training effect can be quantitatively evaluated through the intelligent evaluation module, the trainer can accurately grasp the wearer's skill level and conduct targeted training for weak links, thereby improving the training efficiency. The feedback training module can automatically generate targeted training suggestions based on the evaluation report generated by the intelligent evaluation module, and provide simulated training scenarios for the wearer to practice repeatedly. This personalized feedback and training method helps the wearer to quickly correct errors, improve operating skills, and achieve continuous improvement of skills.

[0064] The data storage module can store all data, evaluation standards, evaluation reports and training records in the simulated wearing process, which facilitates subsequent data analysis, traceability and improvement, helps enterprises establish complete miner safety training files, and realizes the standardization and informatization of training management. BRIEF DESCRIPTION OF THE DRAWINGS

[0065] Figure 1 It is a working principle diagram of the intelligent simulation wearing evaluation system for mining self-rescuers of the present invention;

[0066] Figure 2 A flowchart for building a scoring model;

[0067] Figure 3 Diagram of the steps for feature selection using the Pearson correlation coefficient algorithm. DETAILED DESCRIPTION

[0068] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0069] See also Figure 1-3 The present invention provides a technical solution: an intelligent simulation wearing assessment system for a mining self-rescuer, the system comprising:

[0070] Simulation wearing module: The simulation wearing module is designed with a simulation self-rescuer that is highly similar to the appearance, weight and wearing method of the real self-rescuer, and an adjustable environmental chamber for simulating the complex environment underground. The environmental chamber can simulate high temperature, high humidity and different breathing resistance conditions to ensure that the wearer can wear, use, simulate breathing resistance and practice detachment of the self-rescuer in a close to actual working environment. The simulation self-rescuer has built-in sensors to detect the correctness and timing of wearing.

[0071] Data acquisition module: The data acquisition module is connected to the simulated wearing module by wired or wireless means, and uses high-precision sensors and data acquisition cards to capture and record key data in the wearing process in real time, including but not limited to wearing time, correctness of wearing steps (such as whether it is correctly fastened, whether it is operated in sequence, etc.), breathing frequency, the amount of resistance encountered during breathing, the internal pressure of the self-rescuer, and the temperature and humidity in the environmental chamber.

[0072] Intelligent evaluation module: After receiving the data transmitted by the data acquisition module, the intelligent evaluation module conducts a comprehensive analysis of the wearer's operating skills based on the preset evaluation standards (these standards are based on industry specifications and safety requirements), calculates a quantitative score, and automatically generates a report containing detailed evaluation content. The evaluation standards cover multiple dimensions such as wearing speed, accuracy, and the ability to cope with respiratory resistance.

[0073] Control module: The control module allows the training administrator to control the start, pause, and end of the simulated wearing process through the software interface, and adjust parameters such as temperature, humidity, and breathing resistance in the environmental chamber as needed to simulate different underground emergency conditions and enhance the pertinence and effectiveness of training.

[0074] Feedback training module: The feedback training module automatically analyzes the wearer's weaknesses and generates personalized training suggestions based on the evaluation report generated by the intelligent evaluation module. At the same time, the module provides virtual training scenarios, and the wearer can perform targeted repeated exercises in a simulated environment according to the suggestions until the skills meet the standard requirements.

[0075] Human-computer interaction interface: The human-computer interaction interface adopts an intuitive and easy-to-use graphical user interface to display real-time data, evaluation reports, training suggestions and other information during the simulated wearing process. At the same time, it receives operating instructions entered by the wearer through the touch screen or keyboard, such as starting training, selecting training mode, etc., to ensure convenient and efficient operation.

[0076] Data storage module: The data storage module uses a large-capacity storage device to safely and reliably store all simulated wearing process data, evaluation criteria, evaluation reports and training records.

[0077] The present invention will be further described below in conjunction with Examples 1 to 3:

[0078] Embodiment 1:

[0079] In the intelligent evaluation module, a decision tree algorithm is used to build a quantitative scoring model. This scoring model is designed to accurately evaluate the wearer's operating skills. The following is a detailed description of the scoring model construction steps:

[0080] S1. Obtain the training data set for the scoring model and perform data preprocessing.

[0081] S2. Select features that have an important impact on the evaluation target:

[0082] From the preprocessed training data set, select features that have an important impact on the evaluation target (i.e., the wearer's operating skills) as input features of the decision tree algorithm. The input features include at least:

[0083] Wearing time: includes the time from the beginning of wearing to the completion of wearing and the time from the beginning of using the self-rescuer to the time of detachment;

[0084] Correctness of wearing: quantitative scoring is performed based on the position of the self-rescuer, the standardization of the wearing steps and the tightness of the self-rescuer;

[0085] Respiratory rate: including the average respiratory rate and maximum respiratory rate during the simulated wearing process;

[0086] Respiratory resistance: The respiratory resistance value and its changing trend of the self-rescuer at different use stages;

[0087] Self-rescuer pressure: changes in the pressure inside the self-rescuer;

[0088] Ambient temperature: simulate the ambient temperature and its fluctuation range during wearing.

[0089] S3. Build a decision tree model:

[0090] The decision tree algorithm is used to construct a decision tree model with the selected features as independent variables and the preset evaluation criteria (such as "excellent", "good", "qualified" or "unqualified") as dependent variables. The decision tree algorithm uses information gain as the criterion for node splitting. The calculation formula for information gain is as follows:

[0091]

[0092] Among them, G(D,A) represents the information gain of data set D on feature A, H(D) represents the entropy of data set D, Values(A) represents all possible values ​​of feature A, and D v represents the subset of feature A in dataset D whose value is v, |D| and |D v | respectively represent the dataset D and subset D v The number of samples. The calculation formula of entropy H(D) is:

[0093]

[0094] Among them, Y is the value set of the target variable, p k is the proportion of samples in dataset D that belong to category k.

[0095] S4. Training decision tree model:

[0096] The decision tree model is trained using the preprocessed data set. During the training process, the optimal features are recursively selected for node splitting until the stopping condition is met (such as the number of samples in the node is less than the predetermined threshold, the information gain is less than the predetermined threshold, or the maximum tree depth is reached), and a trained decision tree model is obtained.

[0097] S5. Input the data to be evaluated and obtain the quantitative score

[0098] The simulated wearing data to be evaluated is input into the trained decision tree model. According to the branch paths and leaf node values ​​of the decision tree, the quantitative scores of the wearer's operating skills and the performance of the self-rescuer can be obtained. The quantitative scores can be in numerical form (such as a score range of 0-100 points) or in grade form (such as "excellent", "good", etc.).

[0099] S6. Integrate the evaluation report and display:

[0100] The quantitative scores are integrated into an evaluation report, which can include the scores of various skills, overall evaluation, and improvement suggestions. The evaluation report is displayed to the wearer through the human-computer interaction interface so that the wearer can understand his or her own operating skills and the performance of the self-rescuer, and make improvements and upgrades based on the evaluation report.

[0101] Embodiment 2:

[0102] In order to select features that have an important impact on the evaluation target, the present invention uses the Pearson correlation coefficient for feature selection. The following is a specific implementation of the feature selection method:

[0103] S201: Obtain a preprocessed training data set containing multiple features.

[0104] S202: For each pair of features in the preprocessed data set, calculate the Pearson correlation coefficient. The Pearson correlation coefficient is a statistical indicator that measures the degree of linear correlation between two variables, and its value range is [-1,1]. When the correlation coefficient is 1, it means that the two variables are completely positively correlated; when the correlation coefficient is -1, it means that the two variables are completely negatively correlated; when the correlation coefficient is 0, it means that there is no linear correlation between the two variables.

[0105] Taking wearing correctness and wearing time as an example, assuming that the data set contains n samples, the wearing correctness of each sample is represented by x, and the wearing time is represented by y. Then the Pearson correlation coefficient between wearing correctness and wearing time can be calculated by the following formula:

[0106]

[0107] Among them, r represents the Pearson correlation coefficient between feature x and feature y, X i and Y i Respectively represent the values ​​of feature x and feature y on the i-th sample, and They represent the mean of feature x and feature y respectively, and n represents the number of samples.

[0108] S203: According to the calculated Pearson correlation coefficient, the candidate feature with a larger absolute value of the correlation coefficient with the target feature (such as wearing correctness) can be selected as a feature that has an important impact on the evaluation target. In specific implementation, a correlation coefficient threshold, such as 0.5, can be set to select candidate features with an absolute value of the correlation coefficient greater than 0.5. Alternatively, the absolute values ​​of the correlation coefficients can be sorted to select several candidate features with a high ranking. Assume that after calculation, the correlation coefficient between the wearing time and the wearing correctness is 0.7, the correlation coefficient between the breathing rate and the wearing correctness is 0.6, and the correlation coefficient between the respiratory resistance and the wearing correctness is only 0.3. In this case, the wearing time and the breathing rate can be selected as features that have an important impact on the wearing correctness, while the feature of respiratory resistance is ignored. With the selected features as independent variables and the preset evaluation criteria as dependent variables, a decision tree model is constructed using the decision tree algorithm. When constructing the model, the CART decision tree algorithm is used to train and construct the model according to the selected features and data sets.

[0109] In order to realize the scoring model training in the intelligent simulation wearing evaluation system for mining self-rescuers, the following steps are taken to obtain and process the training data set:

[0110] S101. Actual wearing data collection:

[0111] Organize a certain number of miners to wear self-rescuers in the actual mine working environment. During the wearing process, use the data acquisition module to record the following data in real time:

[0112] Wearing time: includes the time from the beginning of wearing to the completion of wearing (T1) and the time from the beginning of using the self-rescuer to detachment (T2).

[0113] Correctness of wearing: Use video analysis and sensor data to determine whether the position of the self-rescuer is correct, whether the wearing steps are standard, and whether the self-rescuer is tightened, and convert this information into quantitative indicators.

[0114] Respiratory frequency: Record the average respiratory frequency (F_avg) and maximum respiratory frequency (F_max) during the simulated wearing process.

[0115] Respiratory resistance: At different stages of the use of the self-rescuer, measure and record the respiratory resistance value (R) and its changing trend.

[0116] Self-rescuer pressure: record the changes in the internal pressure (P) of the self-rescuer.

[0117] Ambient temperature: record the ambient temperature (Temp) and its fluctuation range during the simulated wearing process.

[0118] S102, simulated wearing data collection:

[0119] In the simulated mine environment, the simulation wearing module is used to simulate the whole process of miners wearing the self-rescuer. Similarly, the data acquisition module is used to record the same data as above in real time.

[0120] S103. Data annotation:

[0121] The actual wearing data and simulated wearing data collected are labeled. According to the preset evaluation criteria, each set of data is labeled with a corresponding evaluation label, including "excellent", "good", "qualified" or "unqualified". The evaluation criteria comprehensively consider the wearing time, wearing correctness, rationality of breathing rate, acceptable range of breathing resistance, stability of self-rescuer pressure and the impact of ambient temperature on the wearing process.

[0122] S104. Dataset synthesis and division:

[0123] The actual wearing data is combined with the simulated wearing data to form a comprehensive training data set. In order to train the decision tree model and verify its performance, the data set is divided according to a certain ratio (such as 70% training set and 30% validation set). The training set is used to train the decision tree model, and the validation set is used to evaluate the performance of the model and adjust the model parameters.

[0124] Embodiment 3:

[0125] This embodiment is used to describe in detail the specific implementation of the control module, feedback training module and human-computer interaction interface:

[0126] The control module is responsible for the overall control and data management of the simulated wearing process. It is further subdivided into the following submodules:

[0127] Simulation environment parameter setting submodule: This submodule allows the system administrator or operator to set the environmental parameters of the simulated wearing process according to actual needs. These parameters include but are not limited to temperature, humidity, air pressure, and harmful gas concentration. For example, you can simulate the high temperature and high humidity environment in a mine, or set a specific harmful gas concentration (such as carbon monoxide, carbon dioxide, etc.) to evaluate the wearer's ability to cope with extreme conditions.

[0128] Process control submodule: The process control submodule is responsible for controlling the start, pause and end of the simulated wearing process. It monitors various data in the simulated wearing process in real time, such as wearing time, wearing correctness, breathing rate, etc., through interaction with the simulated wearing module and the data acquisition module.

[0129] Emergency Simulation Submodule: In order to evaluate the wearer's ability to deal with emergencies, the Emergency Simulation Submodule is designed to trigger emergencies randomly or according to a preset program during the simulated wearing process. For example, it can simulate emergencies such as sudden power outages, fires, or gas leaks in mines to observe the wearer's reaction speed and self-rescue ability. These emergency situations are designed to improve the wearer's emergency response and self-rescue skills.

[0130] The feedback training module aims to provide the wearer with targeted training suggestions based on the deficiencies and improvement suggestions in the evaluation report, and conduct repeated exercises through simulated training scenarios. This module further includes:

[0131] Training suggestion generation submodule: This submodule automatically generates targeted training suggestions based on the analysis results in the evaluation report. For example, if the evaluation report points out that the wearer has problems with wearing the headset correctly, the training suggestion generation submodule will make specific improvement suggestions, such as adjusting the wearing position, standardizing the wearing steps, etc.

[0132] Simulation training scenario submodule: Based on the output of the training suggestion generation submodule, the simulation training scenario submodule is responsible for generating corresponding simulation training scenarios. These scenarios can be customized according to the actual needs of the wearer, including different environmental parameters, emergency simulations, etc. The wearer can practice repeatedly in these simulation scenarios to improve his wearing skills and self-rescue ability.

[0133] Training effect evaluation submodule: The wearer's performance in the simulated training scenario will be monitored and recorded in real time. The training effect evaluation submodule evaluates the wearer's training effect based on these data and generates a training effect report. The report will include the wearer's performance in various aspects, progress, and areas that still need improvement.

[0134] The human-computer interaction interface is an important platform for the system to interact with the wearer. It provides an intuitive and easy-to-use interface that enables the wearer to easily perform simulated wearing, view evaluation reports, receive training suggestions, and perform simulated training. The human-computer interaction interface further includes:

[0135] Data display area: The data display area displays various data in the simulated wearing process in real time, such as wearing time, wearing correctness, breathing frequency, breathing resistance, etc. These data are presented in the form of charts or numbers, so that the wearer can intuitively understand his or her wearing situation.

[0136] Evaluation report area: The evaluation report area is used to display the evaluation report and its detailed contents. The report will include the wearer's overall performance during the simulated wearing process, analysis of advantages and disadvantages, and suggestions for improvement. The wearer can understand his or her own shortcomings by reading the evaluation report and make improvements accordingly.

[0137] Training suggestion area: The training suggestion area displays targeted training suggestions and simulated training scenarios. The wearer can perform targeted exercises based on the training suggestions and practice repeatedly in the simulated training scenarios. This will help the wearer improve his or her wearing skills and self-rescue ability.

[0138] Operation instruction area: The operation instruction area is used to receive the wearer's operation instructions. The wearer can start, pause, end the simulated wearing, and adjust the simulated environment parameters through this area. This allows the wearer to flexibly control the simulated wearing process according to their needs.

[0139] The present invention also includes a method for intelligent simulation wearing assessment of a mining self-rescuer, the method comprising the following steps:

[0140] Step 1: Send instructions to the control module through the human-computer interaction interface to start the intelligent simulation wearing assessment system for mining self-rescuers, and set the simulation environment parameters according to actual needs, including ambient temperature and breathing resistance simulation level; the control module controls the simulation wearing module to enter the preset simulation wearing state according to the received instructions and parameter settings;

[0141] Step 2: The wearer wears, uses, simulates breathing resistance and disengages the self-rescuer according to the instructions of the simulation wearing module; the data acquisition module collects various data in the simulation wearing process in real time, including wearing time, wearing correctness, breathing frequency, breathing resistance, self-rescuer pressure and ambient temperature, and transmits the collected data to the data storage module for storage;

[0142] Step 3: The intelligent evaluation module reads the collected data from the data storage module, pre-processes and analyzes the data; according to the preset evaluation criteria, the decision tree algorithm is used to quantitatively score the wearer's operating skills; an evaluation report including the wearer's operating skill score, various data indicators and evaluation conclusions is generated, and the evaluation report is stored in the data storage module;

[0143] Step 4: The human-computer interaction interface reads the evaluation report from the data storage module and displays it to the wearer; the feedback training module generates targeted training suggestions based on the evaluation report and provides simulated training scenarios for the wearer to practice repeatedly; the wearer views the evaluation report and training suggestions through the human-computer interaction interface and performs feedback training as needed;

[0144] Step 5: The control module controls the simulated wearing module to end the simulated wearing process according to preset conditions or the wearer's operating instructions; the data storage module stores all the data, evaluation criteria, evaluation reports and training records of this simulated wearing.

[0145] The implementation of this method refers to the above embodiment and will not be described in detail in the specification.

[0146] It should be noted that, in this article, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device.

[0147] Although embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that various changes, modifications, substitutions and variations may be made to the embodiments without departing from the principles and spirit of the present invention, and that the scope of the present invention is defined by the appended claims and their equivalents.

Claims

1. Intelligent simulation wearing assessment system for mining self-rescuer, characterized by: The system comprises: The simulation wearing module is used to simulate the whole process of miners wearing the self-rescuer in the actual working environment, including the wearing, use, breathing resistance simulation and removal of the self-rescuer; The data acquisition module is connected to the simulated wearing module and is used to collect various data in the simulated wearing process in real time, including wearing time, wearing correctness, breathing rate, breathing resistance, self-rescuer pressure and ambient temperature; The intelligent evaluation module is connected to the data acquisition module, and is used to receive and process the collected data, quantitatively score the wearer's operating skills according to the preset evaluation criteria, and output an evaluation report; A control module, connected to the simulated wearing module and the intelligent evaluation module, for controlling the start, pause, and end of the simulated wearing process and adjusting the simulated environment parameters; The feedback training module is connected to the intelligent evaluation module to generate targeted training suggestions based on the evaluation report and provide simulated training scenarios for the wearer to practice repeatedly; A human-computer interaction interface, connected to the control module and the intelligent evaluation module, is used to display real-time data, evaluation reports and training suggestions during the simulated wearing process, and receive the wearer's operating instructions; The data storage module is connected to the data acquisition module, the intelligent evaluation module and the feedback training module, and is used to store all data, evaluation criteria, evaluation reports and training records during the simulated wearing process.

2. The intelligent simulation wearing assessment system for mining self-rescuers according to claim 1 is characterized in that: The wearing time includes the time from the start of wearing to the completion of wearing and the time from the start of using the self-rescuer to the time of detachment; The correctness of wearing includes whether the position of the self-rescuer is correct, whether the wearing steps are standard, and whether the self-rescuer is fastened; The respiratory rate includes the average respiratory rate and the maximum respiratory rate during the simulated wearing process; The breathing resistance includes the breathing resistance value and its changing trend of the self-rescuer at different use stages; The self-rescuer pressure includes the change of the internal pressure of the self-rescuer; The ambient temperature includes the ambient temperature and its fluctuation range during the simulated wearing process.

3. The intelligent simulation wearing assessment system for mining self-rescuers according to claim 1 is characterized in that: The intelligent evaluation module adopts a decision tree algorithm to construct a scoring model, and the scoring model is used to quantitatively score the wearer's operating skills.

4. The intelligent simulation wearing assessment system for mining self-rescuers according to claim 3 is characterized in that: The steps for constructing the scoring model are: S1: Obtain the training data set of the scoring model and perform data preprocessing; S2: Select features that have an important impact on the evaluation target from the preprocessed training data set as input features of the decision tree algorithm; the input features include wearing time, wearing correctness, breathing rate, breathing resistance, self-rescuer pressure and ambient temperature; S3: Using the selected features as independent variables and the preset evaluation criteria as dependent variables, a decision tree model is constructed using a decision tree algorithm; the decision tree algorithm uses the following formula for node splitting: Among them, G(D,A) represents the information gain of data set D on feature A, H(D) represents the entropy of data set D, Values(A) represents all possible values ​​of feature A, and D v represents the subset of feature A in dataset D whose value is v, |D| and |D v | respectively represent the dataset D and subset D v The number of samples; S4: Use the preprocessed data set to train the decision tree model, recursively select the optimal features for node splitting, and obtain a trained decision tree model until the stopping condition is met; S5: inputting the simulated wearing data to be evaluated into the trained decision tree model, and obtaining a quantitative score of the wearer's operating skills according to the branch paths and leaf node values ​​of the decision tree; S6: Integrate the quantitative scores into an evaluation report and display it to the wearer through a human-computer interaction interface.

5. The intelligent simulation wearing assessment system for mining self-rescuers according to claim 4 is characterized in that: The Pearson correlation coefficient is used to select features that have an important impact on the evaluation target from the preprocessed data set. The specific implementation steps include: S201: For each pair of features in the preprocessed data set, calculate the Pearson correlation coefficient. The formula is as follows: Among them, r represents the Pearson correlation coefficient between feature x and feature y, X i and Y i Respectively represent the values ​​of feature x and feature y on the i-th sample, and They represent the mean of feature x and feature y respectively, and n represents the number of samples; S202: According to the calculated Pearson correlation coefficient, select several candidate features with higher absolute values ​​of the correlation coefficient as features that have a significant impact on the evaluation target; S203: Using the selected features as independent variables and the preset evaluation criteria as dependent variables, a decision tree model is constructed using a decision tree algorithm, and subsequent training and quantitative scoring are performed.

6. The intelligent simulation wearing assessment system for mining self-rescuers according to claim 5 is characterized in that: The method to obtain the training data set for the scoring model is: S101: Organize miners to wear the self-rescuer in an actual working environment, and use the data acquisition module to collect various data in the wearing process in real time, including wearing time, wearing correctness, breathing frequency, breathing resistance, self-rescuer pressure and ambient temperature, as actual wearing data; S102: In a simulation environment, a simulation wearing module is used to simulate the whole process of a miner wearing a self-rescuer, and a data collection module is also used to collect various data in the simulation wearing process in real time as simulation wearing data; S103: annotating the actual wearing data and the simulated wearing data, and marking each set of data with a corresponding evaluation label according to a preset evaluation standard, wherein the evaluation label includes "excellent", "good", "qualified" or "unqualified", which serves as supervised learning information of the decision tree model; S104: synthesize the actual wearing data and the simulated wearing data into a training data set, and divide it into a training set and a validation set according to a certain ratio; the training set is used to train the decision tree model, and the validation set is used to verify the performance of the model and adjust the model parameters.

7. The intelligent simulation wearing assessment system for mining self-rescuers according to claim 1 is characterized in that: The control module further comprises: The simulation environment parameter setting submodule is used to set the environmental parameters during the simulation wearing process, including temperature, humidity, air pressure and harmful gas concentration; The process control submodule is used to control the start, pause and end of the simulated wearing process and monitor various data in the simulated wearing process in real time; The emergency simulation submodule is used to trigger emergency situations randomly or according to a preset program during the simulated wearing process to evaluate the wearer's ability to deal with emergencies.

8. The intelligent simulation wearing assessment system for mining self-rescuers according to claim 1 is characterized in that: The feedback training module further comprises: The training suggestion generation submodule is used to generate targeted training suggestions based on the deficiencies and improvement suggestions in the evaluation report; The simulation training scenario submodule is used to generate simulation training scenarios based on training suggestions for the wearer to practice repeatedly; The training effect evaluation submodule is used to evaluate the wearer's performance in the simulated training scenario and generate a training effect report.

9. The intelligent simulation wearing assessment system for mining self-rescuers according to claim 1 is characterized in that: The human-computer interaction interface further comprises: Data display area, used to display various data in the simulated wearing process in real time; Evaluation report area, used to display the evaluation report and its detailed contents; Training suggestion area, used to display targeted training suggestions and simulated training scenarios; The operation instruction area is used to receive the wearer's operation instructions, including starting, pausing, and ending simulated wearing and adjusting simulated environment parameters.

10. A method for intelligent simulation wearing assessment of a mining self-rescuer, characterized in that: The method comprises the following steps: Step 1: Send instructions to the control module through the human-computer interaction interface to start the intelligent simulation wearing assessment system for mining self-rescuers, and set the simulation environment parameters according to actual needs, including ambient temperature and breathing resistance simulation level; the control module controls the simulation wearing module to enter the preset simulation wearing state according to the received instructions and parameter settings; Step 2: The wearer wears, uses, simulates breathing resistance and disengages the self-rescuer according to the instructions of the simulation wearing module; the data acquisition module collects various data in the simulation wearing process in real time, including wearing time, wearing correctness, breathing frequency, breathing resistance, self-rescuer pressure and ambient temperature, and transmits the collected data to the data storage module for storage; Step 3: The intelligent evaluation module reads the collected data from the data storage module, pre-processes and analyzes the data; according to the preset evaluation criteria, the decision tree algorithm is used to quantitatively score the wearer's operating skills; an evaluation report including the wearer's operating skill score, various data indicators and evaluation conclusions is generated, and the evaluation report is stored in the data storage module; Step 4: The human-computer interaction interface reads the evaluation report from the data storage module and displays it to the wearer; The feedback training module generates targeted training suggestions based on the evaluation report and provides simulated training scenarios for the wearer to practice repeatedly; the wearer views the evaluation report and training suggestions through the human-computer interaction interface and performs feedback training as needed; Step 5: The control module controls the simulated wearing module to end the simulated wearing process according to preset conditions or the wearer's operating instructions; the data storage module stores all the data, evaluation criteria, evaluation reports and training records of this simulated wearing.

Images