Intelligent monitoring method for release and migration of harmful gas in deep roadway

Abstract

The invention discloses an intelligent monitoring method for release and migration of harmful gas in a deep roadway, and relates to the technical field of monitoring of the harmful gas in the deep roadway, and the method comprises the following steps: constructing an experiment system, building a deep roadway model through a modularized steel frame structure, and setting a plurality of gas sources to simulate gas release and migration processes in the roadway in different environments. By integrating the multi-sensor network and the intelligent control platform, the system can accurately monitor and predict the release and migration process of the harmful gas in the deep ground roadway. The environment data collected in real time is combined with the gas diffusion model, the gas concentration change is effectively predicted and controlled, the potential risk area is recognized in time, and the monitoring precision is improved. Meanwhile, the intelligent platform automatically adjusts a ventilation and gas recovery system, resource utilization is optimized, manual intervention and energy waste are reduced, experiment safety, sustainability and operation efficiency are improved, and improvement of the environmental protection level is promoted.

Description

Technical Field

[0001] The present invention relates to the technical field of harmful gas monitoring in deep roadway, and particularly to an intelligent monitoring method for the release and migration of harmful gases in deep roadway. Background Art

[0002] With the rapid development of deep roadway mining and underground engineering construction, the issues surrounding the release, migration, and diffusion of harmful gases in the deep environment have become an important research direction in the fields of safety management and environmental protection. In underground roadways, due to the influence of complex strata, there are often accumulations and releases of harmful gases such as carbon monoxide and hydrogen sulfide, which pose a great threat to the safety of miners and the surrounding environment. Therefore, in recent years, many research institutions and enterprises at home and abroad have invested a lot of energy in developing corresponding monitoring and prevention technologies to be able to take effective measures in a timely manner when the concentration of harmful gases is too high and avoid disasters such as gas leakage or explosion. Existing technologies generally detect gas concentration through gas sensors, gas analyzers, and environmental monitoring systems, but usually fail to effectively solve the real-time simulation and precise control of the gas release, migration, and diffusion processes.

[0003] The existing technologies have the following deficiencies:

[0004] Most of the existing harmful gas monitoring devices rely on static sensors and fixed detection systems, and this method cannot real-time simulate the complex gas release and migration behaviors in deep roadway. Many monitoring systems are limited to the monitoring and alarm of gas concentration, lacking real-time dynamic simulation and feedback of complex processes such as gas flow, diffusion, and accumulation in the underground environment. In addition, the current gas disposal systems generally have the problem of slow reaction. Most devices can only be started after the gas concentration reaches a certain threshold, lacking a refined and intelligent control system, and cannot dynamically adjust the ventilation plan or start corresponding gas treatment measures according to real-time data such as gas concentration, temperature, and air pressure, resulting in a relatively high risk of gas diffusion in some special environments (such as high temperature and high pressure conditions). Therefore, there is an urgent need for an intelligent monitoring method that can accurately monitor and simulate the release and migration processes of harmful gases in deep roadway to more effectively prevent gas leakage and related safety accidents.

[0005] The above information disclosed in the background art section is only used to enhance the understanding of the background of the present disclosure, and thus it may include information that does not constitute the prior art known to those of ordinary skill in the art. Summary of the Invention

[0006] The object of the present invention is to provide an intelligent monitoring method for the release and migration of harmful gases in deep roadway. By integrating a multi-sensor network and an intelligent control platform, this system can accurately monitor and predict the release, migration and diffusion process of harmful gases in deep roadway. The real-time collected environmental data is combined with the gas diffusion model to ensure that each stage of the gas concentration change can be effectively predicted and controlled, so as to identify potential risk areas and process them in time, improving the monitoring accuracy. At the same time, the intelligent platform optimizes resource utilization, reduces manual intervention, avoids energy waste, improves experimental safety and sustainability, and promotes the improvement of operation efficiency and environmental protection level by automatically adjusting the ventilation and gas recovery systems, so as to solve the problems in the above-mentioned background technology.

[0007] To achieve the above object, the present invention provides the following technical solutions: An intelligent monitoring method for the release and migration of harmful gases in deep roadway, comprising the following steps:

[0008] Construct an experimental system, build a deep roadway model through a modular steel frame structure, and set up a variety of gas sources to simulate the gas release and migration process under different environments in the roadway;

[0009] Arrange gas sensors and flow velocity sensors in the roadway model to collect the environmental parameters in the roadway in real time and monitor and collect the data during the gas migration process in real time;

[0010] Through the intelligent control platform, according to the data collected in real time, dynamically simulate the gas release and migration process. The intelligent control platform has a dynamic adjustment function and automatically adjusts the ventilation plan and gas recovery measures according to the real-time data;

[0011] Based on the data collected by the sensors, use the dynamic data analysis algorithm to predict and simulate the diffusion path and concentration change of the gas in real time. Establish a gas diffusion model through the algorithm and compare the model with the actual environmental data to accurately predict the further diffusion of harmful gases;

[0012] According to the gas diffusion model and the prediction results, use the adaptive control strategy based on the optimization algorithm to automatically adjust the working state of the ventilation equipment and gas recovery equipment in the roadway to achieve the optimal control of the harmful gas concentration.

[0013] Preferably, the specific steps of constructing an experimental system, building a deep roadway model through a modular steel frame structure, and setting up a variety of gas sources to simulate the gas release and migration process under different environments in the roadway are as follows:

[0014] Design and plan the structure and function of the experimental system;

[0015] Select steel frame materials according to the experimental requirements and ensure that the modular design of the structure is convenient for assembly, disassembly and maintenance;

[0016] Install multiple harmful gas sources, and precisely control the type, flow rate, and concentration of gas release through a gas pump and a pneumatic regulation system;

[0017] Establish a gas flow control and monitoring system, and use a fan, regulating devices, and sensors to monitor gas parameters in real time to ensure precise control and safety during the experiment.

[0018] Preferably, arrange gas sensors and flow velocity sensors in the roadway model, and the specific steps for collecting environmental parameters in the roadway in real time and monitoring and collecting data during the gas migration process are as follows:

[0019] Determine and design the type, location, and layout of gas sensors and temperature and humidity sensors to ensure comprehensive monitoring of environmental parameters in the roadway;

[0020] Install gas sensors and temperature and humidity sensors in the roadway model, and ensure their stability and accuracy, while ensuring good contact with the gas source and the environment;

[0021] Connect the installed sensors to the intelligent control system to achieve real-time data collection, transmission, and processing;

[0022] Monitor the data in real time through the intelligent control system, and dynamically adjust various parameters in the roadway according to the sensor feedback.

[0023] Preferably, through the intelligent control platform, according to the data collected in real time, the specific steps for dynamically simulating the gas release and migration process, and automatically adjusting the ventilation plan and gas recovery measures according to the real-time data are as follows:

[0024] Collect and transmit the environmental parameters in the roadway to the intelligent control platform in real time for data processing and monitoring;

[0025] Based on the environmental data collected in real time, establish a physical model of gas diffusion and migration through the intelligent control platform to simulate the behavior of gas under different environmental conditions;

[0026] According to the simulation results, the intelligent control platform automatically adjusts the ventilation plan and gas recovery measures to optimize the air flow distribution and the emission and recovery of harmful gases;

[0027] The intelligent control platform conducts feedback evaluation according to the adjusted effect, and further improves the control strategy through an optimization mechanism to ensure precise control of the gas concentration.

[0028] Preferably, based on the data collected by the sensors, use a dynamic data analysis algorithm to predict and simulate the gas diffusion path and concentration change in real time, establish a gas diffusion model through the algorithm, and compare the model with the actual environmental data to accurately predict the further diffusion of harmful gases. The specific steps are as follows:

[0029] For the data collected by the sensor, a gas diffusion model is first established, and the spatial distribution of gas concentration is calculated through formulas. The Fick diffusion law is used to describe the diffusion behavior of gas in the roadway. To simplify the analysis, the diffusion coefficient is used to characterize the diffusion speed of gas, and the calculation expression is as follows:

[0030]

[0031] , where C(x, t) is the gas concentration at position x and time t, C 0 is the initial gas concentration, x is the spatial position of gas diffusion, D is the diffusion coefficient of gas, and t is the time;

[0032] According to the environmental parameters collected in real time, the diffusion coefficient of gas is dynamically adjusted to more accurately simulate the diffusion behavior of gas in the actual environment. The calculation expression is as follows:

[0033] D(t) = D 0 (1 + αT(t) - βP(t))

[0034] , where D(t) is the dynamic diffusion coefficient at time t, D 0 is the diffusion coefficient under reference conditions, α is the influence factor of temperature on the diffusion coefficient, T(t) is the temperature at time t, β is the influence factor of air pressure on the diffusion coefficient, and P(t) is the air pressure at time t;

[0035] Based on the gas concentration C(x, t) and the dynamic diffusion coefficient D(t) at time t, the diffusion path of gas is predicted and compared with the actual sensor data, so as to optimize the gas diffusion model. The calculation expression is as follows:

[0036]

[0037] real (x i , t i ) is the gas concentration measured at the x position of the i-th sensor and time t, n is the total number of sensors, C model (x i , t i , D(t)) is the gas concentration predicted by the model. The formula is as follows:

[0038]

[0039] , where x i is the measurement position x of the i-th sensor, x 0 is the position of the gas source, t i is the time point, indicating the time from the start of gas release from the gas source to reach xi The time of the position.

[0040] Preferably, according to the gas diffusion model and the prediction results, an adaptive control strategy based on an optimization algorithm is used to automatically adjust the working states of the ventilation equipment and the gas recovery equipment in the roadway, and the specific steps for realizing the optimal control of the harmful gas concentration are as follows:

[0041] First, through the gas concentration data and environmental parameters collected in real time, the gas diffusion model is used to predict the gas concentration change rate, and the gas concentration change rate is described by the following partial differential equation:

[0042]

[0043] , where, is the change rate of gas concentration with time, C(x, t) is the gas concentration, representing the gas concentration at position x and time t, D is the diffusion coefficient, representing the diffusion rate of gas in the roadway, is the spatial Laplacian operator of the concentration, v is the gas velocity vector, is the convection term, S(x, t) is the gas source term;

[0044] According to the predicted gas concentration change rate Combined with the performance parameters of the ventilation equipment and the gas recovery equipment, an objective optimization function is constructed to minimize the harmful gas concentration and the operating cost in the roadway, and the objective function is expressed as follows:

[0045]

[0046] , where, V is the volume of the roadway, C safe is the set safety gas concentration threshold, λ is the weight factor, E j (v j , P j ) is the energy consumption function of the j-th equipment, which depends on the wind speed v j and the air pressure P j , m is the total number of equipment;

[0047] Using the optimized wind speed v j and pressure P j , the working states of the ventilation and gas recovery equipment are adjusted in real time, and the model is continuously optimized in combination with the feedback data. The control equation of the ventilation system is expressed as follows:

[0048]

[0049] , where, v j (t + 1) is the wind speed of the j-th equipment at time t + 1, v j(t) Wind speed of the j-th device at time t, where ω is the step coefficient, is the gradient of the objective function with respect to the wind speed, representing the impact of wind speed adjustment on the optimization objective.

[0050] In the above technical solution, the technical effects and advantages provided by the present invention are as follows:

[0051] By integrating a multi-sensor network and an intelligent control platform, the system of the present invention can achieve precise monitoring and prediction of the release, migration, and diffusion processes of harmful gases in deep roadway. The real-time collected environmental data is combined with the gas diffusion model, enabling the system to predict the behavior of gases under different environmental conditions at each stage of gas concentration change and adjust control measures in real time. This precise prediction ability can not only effectively identify potential gas accumulation areas and risk points, but also provide comprehensive gas distribution information for experimental personnel, ensuring that potential safety hazards can be detected and addressed in a timely manner, thus greatly improving the accuracy of gas monitoring and management.

[0052] Through intelligent and automated control, the present invention improves the utilization efficiency of resources and the safety of experiments. The intelligent control platform can automatically adjust the ventilation system and gas recovery device based on real-time data, reducing manual intervention and operation errors, optimizing gas flow and concentration management, and avoiding energy waste. For example, the system can dynamically adjust the working states of the fan and the recovery device according to gas concentration changes, ensuring the effective utilization of energy while keeping the gas concentration within a safe range. By continuously optimizing the control strategy, the system also has a self-learning function, making the operation more efficient and environmentally friendly, thus enhancing the intelligent level and sustainability of the entire experimental process. Brief Description of the Drawings

[0053] To more clearly illustrate the technical solutions in the embodiments of the present application or the prior art, the following will briefly introduce the drawings required for use in the embodiments. Obviously, the drawings described below are only some embodiments recorded in the present invention, and those of ordinary skill in the art can also obtain other drawings based on these drawings.

[0054] Figure 1 It is a method flow chart of the intelligent monitoring method for harmful gas release and migration in deep roadway of the present invention. Detailed Embodiments

[0055] Now, the exemplary embodiments will be described more comprehensively with reference to the drawings. However, the exemplary embodiments can be implemented in various forms and should not be construed as limited to the examples set forth herein; rather, these exemplary embodiments are provided so that the present disclosure will be more complete and comprehensive, and will fully convey the concept of the exemplary embodiments to those skilled in the art.

[0056] The present invention provides asFigure 1 The intelligent monitoring method for the release and migration of harmful gases in deep roadway shown in the figure includes the following steps:

[0057] Construct an experimental system, build a deep roadway model through a modular steel frame structure, and set up various gas sources to simulate the gas release and migration processes under different environments in the roadway;

[0058] The specific steps for constructing an experimental system, building a deep roadway model through a modular steel frame structure, and setting up various gas sources to simulate the gas release and migration processes under different environments in the roadway are as follows:

[0059] Design and plan the structure and functions of the experimental system;

[0060] In the initial stage of building the experimental system, it is first necessary to conduct a detailed design of the structure of the entire experimental system, including the dimensions of the roadway model, the specific scheme of modular design, the installation positions of gas sources, and the control module during the experiment. The design of the roadway model should take into account various parameters required for the experiment (such as roadway length, height, width) and key factors for gas release and migration (such as gas concentration, temperature, air pressure, etc.). At this stage, engineering calculations and simulation analyses are required to ensure that the experimental system can meet the simulation requirements for gas release, migration, and diffusion processes. In addition, it is also necessary to plan the modular structure of the experimental system so that different parts of the model (such as gas sources, gas pumps, air pressure regulation systems) can be easily installed, disassembled, and maintained, facilitating flexible adjustment according to experimental needs.

[0061] Select steel frame materials according to experimental requirements and ensure that the structural modular design is convenient for assembly, disassembly, and maintenance;

[0062] Once the experimental design scheme is determined, the next step is to select suitable steel frame materials for building the experimental system. As the main body supporting the experimental system, the steel frame structure needs to have the characteristics of high strength, strong compressive capacity, and corrosion resistance. Therefore, the selection of materials is crucial. Common steel frame materials include carbon steel, stainless steel, and galvanized steel. The specific choice of which material should be determined according to the requirements of the experimental environment and cost control. The modular steel frame design requires that the dimensions, shapes, and interfaces of each module be standardized so that they can be flexibly assembled and disassembled during actual construction. The steel frame structure should not only meet the requirements of physical stability and load-bearing capacity but also reserve appropriate space for installing gas sources, sensors, and other monitoring devices to ensure that all parts of the equipment can be successfully integrated during the construction process.

[0063] Install various harmful gas sources and precisely control the type, flow rate, and concentration of gas release through gas pumps and air pressure regulation systems;

[0064] The gas source is the core equipment for simulating the release and migration of harmful gases. Installing and adjusting the position, quantity, and type of gas sources are key steps in the experimental system. In this step, first, the type of gas source needs to be determined according to the experimental design plan. Common gas sources include various harmful gas cylinders, gas pumps, and regulating valves. For each gas source, appropriate transmission pipelines and regulating systems should be selected according to its properties. For example, gas cylinders need to be equipped with pressure regulating valves and gas pipeline connection devices to ensure that the gas can be released at a predetermined pressure and precisely controlled. Each gas source also needs to be connected to a pneumatic regulating system to control the flow rate and concentration of gas release and simulate the gas release process under different environments. It should be noted that all gas sources and gas pipeline connection devices need to undergo strict safety inspections to prevent accidents such as leakage and explosion.

[0065] Establish a gas flow control and monitoring system, use fans, regulating devices, and sensors to monitor gas parameters in real time, and ensure the precise control and safety of the experimental process;

[0066] To ensure the accurate monitoring of the migration and diffusion of gas during the experimental process, a gas flow control and monitoring system needs to be set up. The gas flow control system should include multiple fans, ventilation ducts, gas flow regulating devices, etc. These devices work together to simulate the natural flow and artificial regulation of gas in the roadway. The setting of fans should be selected according to the size of the experimental roadway and the gas diffusion requirements to ensure uniform distribution of airflows in the roadway. The gas flow regulating device can adjust the gas flow rate according to the experimental needs and simulate the gas diffusion characteristics under different wind speeds. The gas monitoring system monitors key parameters such as gas concentration, temperature, and humidity in real time through gas sensors arranged at different positions in the roadway. The data of these sensors will be fed back to the intelligent control platform through the real-time monitoring system, helping the experimental personnel to track the migration of gas in real time and adjust the experimental conditions or initiate emergency measures according to the data.

[0067] Arrange gas sensors and flow velocity sensors in the roadway model to collect the environmental parameters in the roadway in real time and monitor and collect data during the gas migration process;

[0068] The specific steps for arranging gas sensors and flow velocity sensors in the roadway model to collect the environmental parameters in the roadway in real time and monitor and collect data during the gas migration process are as follows:

[0069] Determine and design the type, position, and layout of gas sensors and temperature and humidity sensors to ensure comprehensive monitoring of the environmental parameters in the roadway;

[0070] In the design stage of the experimental system, it is first necessary to clarify the types of sensors to be installed in the roadway model and their layout. The selection of gas sensors should be customized according to the types of harmful gases involved in the experiment, such as carbon monoxide, hydrogen sulfide, methane and other gases. The selected sensors are required to have high sensitivity, fast response speed, high temperature and high pressure resistance, and be able to operate stably in complex environments. At the same time, the temperature and humidity sensors need to be able to work under extreme temperature and humidity conditions, which is very important for simulating the environment of deep roadway. In the layout design, the sensors should be evenly distributed in different areas of the roadway model to comprehensively collect data such as gas concentration, temperature, humidity and air pressure. In particular, gas sensors should be installed at multiple heights and positions in order to obtain multi-dimensional data, so as to more accurately reflect the distribution and migration of gas in the roadway.

[0071] Install gas sensors and temperature and humidity sensors in the roadway model, and ensure their stability and accuracy, while having good contact with the gas source and the environment;

[0072] The installation process should ensure the stability and accuracy of each sensor. For gas sensors, first, it is necessary to fix them on the wall surface or specific area of the roadway model, and firmly install the sensors through appropriate brackets. The installation position of the sensors should avoid being directly affected by the strong air flow of the fan or heating equipment to prevent interference with the data they collect. The temperature and humidity sensors should be arranged at multiple positions, especially in the low-lying areas or ventilation dead ends where gas accumulation may occur, in order to obtain comprehensive environmental data. During installation, it is also necessary to ensure good contact between the sensors and the gas source, temperature and humidity environment, so as to accurately reflect the real environmental conditions. When connecting the sensors, standardized cables and signal interfaces need to be used to ensure the stability of data transmission and anti-interference ability, and avoid signal conflicts or data transmission errors between sensors.

[0073] Connect the installed sensors to the intelligent control system to realize real-time data collection, transmission and processing;

[0074] After installation, the sensors need to be effectively integrated with the intelligent control system. This step mainly includes the configuration of the data acquisition system and the connection of the signal interfaces of the sensors. The sensors transmit the collected data to the intelligent control platform wirelessly or by wire. The intelligent control system needs to be able to receive data from various sensors in real time and perform data processing, storage and display. The data acquisition system should have the ability of high-precision and high-frequency sampling, and be able to accurately capture the changes of environmental parameters such as gas concentration, temperature and humidity, and air pressure. During the integration process, it is also necessary to check the calibration of the sensors to ensure that all sensors are in normal working condition. The intelligent control platform should also have an alarm function. When the gas concentration or other environmental parameters exceed the predetermined safety threshold, it can issue an alarm in time and automatically start emergency measures, such as adjusting the ventilation system or starting the gas recovery device.

[0075] The intelligent control system monitors data in real time and dynamically adjusts various parameters in the roadway according to the sensor feedback;

[0076] After the connection between the sensors and the control system is completed, the system enters the real-time data monitoring stage. The intelligent control system displays environmental parameters such as gas concentration, temperature, humidity, and air pressure in the roadway in real time through a set data monitoring interface, and predicts and simulates the processes of gas diffusion, accumulation, release, etc. through data analysis algorithms. Through the integrated feedback mechanism, the system can adjust the experimental environment or operating parameters according to real-time data. For example, when the gas concentration exceeds the standard, the system can automatically adjust the speed of the fan, turn on the gas recovery system, etc., so as to achieve precise control of the gas diffusion process. At the same time, the system should have the functions of remote monitoring and data storage, and all the collected data can be uploaded to the cloud platform in real time, which is convenient for subsequent data analysis, experimental review and safety management. Through this efficient real-time monitoring system, experimental personnel can always master the dynamic information of gas migration and take timely safety measures according to the data analysis results.

[0077] Through the intelligent control platform, according to the real-time collected data, dynamically simulate the gas release and migration process, including the diffusion and accumulation processes of gas under different geothermal temperatures, air pressures, wind speeds, etc. The intelligent control platform has a dynamic adjustment function and automatically adjusts the ventilation plan and gas recovery measures according to real-time data;

[0078] Through the intelligent control platform, according to the real-time collected data, dynamically simulate the gas release and migration process. The specific steps of automatically adjusting the ventilation plan and gas recovery measures according to real-time data are as follows:

[0079] Collect and transmit the environmental parameters in the roadway to the intelligent control platform in real time for data processing and monitoring;

[0080] First of all, gas sensors and temperature and humidity sensors installed in the roadway will collect environmental parameters such as harmful gas concentration, temperature, air pressure, humidity, etc. in real time and transmit these data to the intelligent control platform. In order to ensure the real-time and accuracy of the data, the sensors should have high sensitivity and high-frequency data collection capabilities. The intelligent control platform needs to be able to process and store the input data from multiple sensors, including gas concentrations and physical parameters at different positions, different heights and different environmental conditions. This data provides the necessary input for subsequent gas diffusion simulation and dynamic adjustment, enabling the system to reflect the changes in gas flow and the dynamic changes in the environment in the roadway in real time.

[0081] Establish a physical model of gas diffusion and migration through the intelligent control platform based on the real-time collected environmental data to simulate the behavior of gas under different environmental conditions;

[0082] After obtaining real-time environmental data, the intelligent control platform will establish a physical model of gas diffusion and migration based on this data to simulate the behavior of gas under different conditions such as geothermal temperature, air pressure, and wind speed. Specifically, the system will use algorithms such as fluid mechanics models and gas diffusion models to predict and simulate the processes of gas flow, diffusion, and accumulation. The model will consider the effects of different air temperatures, air pressures, wind speeds, and roadway structures on the gas, and calculate the diffusion path and concentration distribution of the gas in the roadway through mathematical formulas and physical laws. Through these simulations, the system can monitor the behavior of the gas under specific conditions in real time during the experiment and provide a scientific basis for subsequent adjustments.

[0083] According to the simulation results, the intelligent control platform automatically adjusts the ventilation plan and gas recovery measures to optimize the air flow distribution and the emission and recovery of harmful gases;

[0084] Based on the simulation results, the intelligent control platform can automatically adjust the ventilation plan and gas recovery measures according to the real-time gas diffusion situation. The adjustment of the ventilation system includes adjusting the rotation speed and air volume of the fan according to parameters such as gas concentration, air pressure, and wind speed to optimize the air flow distribution and effectively discharge or dilute harmful gases. At the same time, the system can control the operation of the gas recovery device to ensure that the recovery module is automatically started when the gas concentration is too high, reducing the impact of harmful gases on the air quality in the roadway. Through these automatic adjustment functions, the intelligent platform can dynamically adapt to environmental changes, achieve real-time control of gas concentration, and ensure the safety of the experimental environment.

[0085] The intelligent control platform conducts feedback evaluation based on the adjusted effects and further improves the control strategy through an optimization mechanism to ensure precise control of gas concentration;

[0086] Finally, the intelligent control platform will evaluate the effects of the ventilation and gas recovery measures after each adjustment and further optimize the control strategy based on the feedback data. If it is found that the gas concentration is still too high or the gas diffusion has not been effectively curbed, the system will adjust the operation plan again to ensure that the problems of gas diffusion and accumulation are solved. This closed-loop feedback mechanism enables the system to gradually optimize the operation and precisely control the gas release and migration process. Through continuous monitoring and optimization, the system can ensure good gas control effects under different experimental conditions, whether it is high temperature, low air pressure, or different wind speed conditions, and ensure the smooth progress of the experiment.

[0087] Based on the data collected by the sensors, use dynamic data analysis algorithms to predict and simulate the gas diffusion path and concentration changes in real time, establish a gas diffusion model through the algorithms, and compare the model with the actual environmental data to accurately predict the further diffusion of harmful gases;

[0088] Based on the data collected by sensors, the dynamic data analysis algorithm is used to predict and simulate the diffusion path and concentration change of gas in real time. The specific steps to establish a gas diffusion model through the algorithm and compare the model with the actual environmental data to accurately predict the further diffusion of harmful gases are as follows:

[0089] For the data collected by sensors, first establish a gas diffusion model, calculate the spatial distribution of gas concentration through formulas, and use Fick's diffusion law to describe the diffusion behavior of gas in the roadway. For simplicity of analysis, the diffusion coefficient is used to characterize the diffusion speed of gas, and the calculation expression is as follows:

[0090]

[0091] , where C(x, t) is the gas concentration at position x and time t, C 0 is the initial gas concentration, x is the spatial position of gas diffusion, usually represented as the length, width or height direction of the roadway, D is the diffusion coefficient of gas (affected by environmental factors such as temperature and air pressure), and t is the time, representing the time elapsed since the gas was released;

[0092] In this formula, the diffusion of gas concentration over time in the roadway can be calculated by the above formula. The determination of the D value needs to be dynamically adjusted according to experimental data and environmental parameters (such as temperature, humidity, etc.). This formula provides the change of gas concentration with time and space for the first-step calculation, and the subsequent steps will use this concentration distribution to predict the gas diffusion path.

[0093] Dynamically adjust the diffusion coefficient of gas according to the real-time collected environmental parameters. At this time, the diffusion coefficient is affected by environmental conditions (such as temperature T(t) and air pressure P(t)). By adjusting the diffusion coefficient, the diffusion behavior of gas in the actual environment can be more accurately simulated, and the calculation expression is as follows:

[0094] D(t) = D 0 (1 + αT(t) - βP(t))

[0095] , where D(t) is the dynamic diffusion coefficient at time t, D 0 is the diffusion coefficient under reference conditions (usually the value at standard temperature and air pressure), α is the influence factor of temperature on the diffusion coefficient, T(t) is the temperature at time t, β is the influence factor of air pressure on the diffusion coefficient, and P(t) is the air pressure at time t;

[0096] Through this step, the changes in temperature T(t) and air pressure P(t) are associated with the diffusion coefficient D(t) of gas, enabling the diffusion coefficient to be dynamically adjusted according to the changes in the actual environment. This dynamic adjustment ensures that the gas diffusion model can reflect environmental changes in real time and improves the prediction accuracy of the model.

[0097] Based on the gas concentration C(x, t) and the dynamic diffusion coefficient D(t) at time t, predict the diffusion path of the gas, and compare it with the actual sensor data, so as to optimize the gas diffusion model. By calculating the error between the predicted concentration and the actual concentration, optimize the parameters in the diffusion model (such as diffusion coefficient, initial concentration, etc.). The calculation expression is as follows:

[0098]

[0099] , where ΔC is the error between the predicted concentration and the actual concentration, C real (x i ,t i ) is the gas concentration measured at the position x of the i-th sensor and at time t, n is the total number of sensors, C model (x i ,t i ,D(t)) is the gas concentration predicted by the model. The formula is as follows:

[0100]

[0101] , where x i is the measurement position x of the i-th sensor, x 0 is the position of the gas source, which is the starting point of gas release, t i is the time point, indicating the time from the start of gas release to reaching the x i position.

[0102] By minimizing the error ΔC, that is, optimizing the difference between the predicted value and the actual value, the diffusion model can be corrected to ensure that the predicted gas diffusion path and concentration change in the model are consistent with the actual environmental data. This step is a dynamic feedback process. Through continuous comparison and optimization, the accuracy of the model is improved, making future gas diffusion predictions more reliable.

[0103] According to the gas diffusion model and the prediction results, use an adaptive control strategy based on an optimization algorithm to automatically adjust the working states of the ventilation equipment and gas recovery equipment in the roadway to achieve optimal control of the harmful gas concentration;

[0104] According to the gas diffusion model and the prediction results, the specific steps to use an adaptive control strategy based on an optimization algorithm to automatically adjust the working states of the ventilation equipment and gas recovery equipment in the roadway to achieve optimal control of the harmful gas concentration are as follows:

[0105] First, based on the gas concentration data and environmental parameters (such as temperature T, air pressure P, wind speed v, etc.) collected in real time, use the gas diffusion model to predict the gas concentration change rate. The gas concentration change rate is described by the following partial differential equation:

[0106]

[0107] , where is the rate of change of gas concentration with time, describing the rate of change of gas concentration with time at position x, C(x, t) is the gas concentration, representing the gas concentration at position x and time t, D is the diffusion coefficient, representing the rate of gas diffusion in the roadway, is the spatial Laplacian of the concentration, representing the second-order derivative of the gas concentration in the spatial dimension and being the core mathematical description of the diffusion process, v is the gas velocity vector, representing the speed and direction of gas flow, is the convection term, representing the rate of change of the gas carried by the air flow in space, S(x, t) is the gas source term, representing the rate of gas release at position x and time t;

[0108] By solving the above partial differential equation, the distribution of gas concentration C(x, t) at each position in the roadway can be obtained as the input for subsequent optimization control.

[0109] According to the predicted rate of change of gas concentration Combined with the performance parameters of the ventilation equipment and gas recovery equipment, a target optimization function is constructed to minimize the harmful gas concentration and operating cost in the roadway. The target function is expressed as follows:

[0110]

[0111] , where V is the volume of the roadway, the integration domain covers the entire roadway model, C safe is the set safety gas concentration threshold, λ is the weight factor, used to balance the weight between gas concentration optimization and equipment energy consumption, E j (v j , P j ) is the energy consumption function of the j-th equipment, depending on the wind speed v j and air pressure P j , and m is the total number of equipment;

[0112] By performing constrained optimization on the target function J (such as Lagrangian optimization method or gradient descent method), the optimal wind speed v j of the ventilation equipment and the working pressure P j of the gas recovery equipment are calculated.

[0113] Using the optimized wind speed v j and pressure P j , the working states of the ventilation and gas recovery equipment are adjusted in real time, and the model is continuously optimized in combination with the feedback data. The control equation of the ventilation system is expressed as follows:

[0114]

[0115] , where v j (t + 1) is the wind speed of the j-th device at time t + 1, and v j (t) is the wind speed of the j-th device at time t. ω is the step size coefficient used to control the update amplitude of the optimization algorithm, and is the gradient of the objective function with respect to the wind speed, representing the impact of wind speed adjustment on the optimization objective.

[0116] Through the adaptive optimization strategy, the system can dynamically respond to environmental changes, ensure that the gas concentration in the roadway is always within the safe range, and achieve the optimal control effect with the minimum energy consumption.

[0117] Embodiment 1: In this embodiment, by arranging multiple sensors (including gas sensors, temperature and humidity sensors, barometric pressure sensors, etc.) in the deep roadway model, real-time collection of environmental parameters such as harmful gas concentration, temperature and humidity, and barometric pressure in the roadway is achieved. These sensors will be connected to the intelligent control platform to ensure the timely transmission and processing of data. To accurately monitor the release, migration, and accumulation process of gas in the roadway, the arrangement of sensors is very crucial and must be scientifically arranged according to the characteristics of gas diffusion, the ventilation conditions of the roadway, and the main gas accumulation areas.

[0118] Specifically, gas sensors should be arranged at the following key positions:

[0119] Around the gas source: The sensor should be adjacent to the gas source to monitor the change of gas concentration in real time and ensure that the initial change of gas release can be detected quickly.

[0120] Gas accumulation areas: Gas usually accumulates in low-lying areas or areas with poor ventilation. Therefore, sensors should be installed at multiple low-lying positions in the roadway, especially in dead ends of the air flow or areas with poor ventilation, in order to monitor these areas where gas is likely to accumulate.

[0121] Before and after the ventilation system: Arranging sensors near the inlet and outlet of the fan can provide real-time feedback on the impact of air flow on gas concentration, thereby providing a basis for evaluating the ventilation effect. The air supply volume adjustment of the fan will be intelligently optimized based on the data at these positions.

[0122] On both sides and in the middle of the roadway: To obtain comprehensive data, sensors should also be installed on both sides and in the middle of the roadway to reflect the lateral distribution of gas concentration and ensure comprehensive monitoring of the gas situation in the entire roadway.

[0123] This arrangement ensures comprehensive monitoring of gas distribution, thereby providing accurate data support for subsequent gas diffusion simulation and dynamic adjustment.

[0124] After data collection, the intelligent control platform establishes a physical model of gas diffusion and migration through real-time processing and analysis of sensor data. Combining data such as wind speed, air pressure, and temperature in the roadway, the system uses fluid mechanics and gas diffusion models to simulate the behavior of gas under different conditions. This model not only considers the location of the gas source but also dynamically adjusts the gas release rate, air flow distribution, and changes in gas concentration in the model according to the real-time data feedback from the sensors.

[0125] Through real-time data and modeling algorithms, the system can accurately predict the gas diffusion and accumulation conditions after a certain point in time. For example, the intelligent platform can calculate how gas will accumulate in certain areas (such as low-lying areas or ventilation dead ends) when the current ventilation is insufficient and predict the optimal fan air supply position and flow rate, so as to adjust the ventilation system and optimize the ventilation effect. In addition, the platform can also calculate the evolution of gas concentration and predict what level the gas concentration will reach within a certain period of time, providing data support for subsequent gas treatment measures.

[0126] Through the established gas diffusion and migration model, the intelligent control platform can automatically adjust the ventilation system and gas recovery device according to the real-time monitored data. The platform can evaluate the air supply effect of the fan in real time and make corresponding adjustments according to the change in gas concentration. For example, when the gas concentration in a certain area (such as a ventilation dead end) is detected to exceed the standard, the system will automatically increase the air volume of the fan near this area or activate other standby fans to promote gas diffusion and emission. The system will also adjust the operating state of the fan according to the actual effect evaluation of the fan to ensure that the gas can be processed in a timely and effective manner.

[0127] The gas recovery system can also be adjusted according to the instructions of the intelligent control platform. When the concentration of harmful gas is too high, the platform will automatically activate the recovery module (such as activated carbon adsorption, chemical scrubbing and other devices) to recover the excessive harmful gas. Through this intelligent adjustment process, the system ensures that the gas concentration in the roadway is always maintained within a safe range.

[0128] In this embodiment, the system not only monitors the gas release and migration process in real time but also has a feedback mechanism for optimizing ventilation and gas recovery measures. Through real-time feedback data, the intelligent control platform can evaluate the current ventilation and gas recovery effects. For example, assuming that the gas concentration in a certain area of the roadway is still too high after a certain period of ventilation, the platform will automatically re-evaluate the gas diffusion model and provide adjustment suggestions, such as increasing the operating power of the fan or adjusting the working mode of the recovery device.

[0129] The core advantage of this intelligent system lies in its iterative optimization function. After each operation adjustment, the system collects data and analyzes it to determine whether the current treatment measures have achieved the expected effect. If the gas concentration has not been effectively controlled, the system will adjust the operation strategy again, increasing the air supply volume of the fan or increasing the working frequency of the recovery device. Through this real-time data feedback and intelligent optimization, the system can continuously improve the control effect in each test stage, ensuring that the gas concentration always remains at a safe level.

[0130] The implementation of this intelligent monitoring system can ensure the safety and accuracy of the entire experimental process. First, through reasonable sensor layout, the system can comprehensively monitor the gas distribution in the roadway and detect any potential gas leakage or abnormal concentration in real time. Second, through real-time data analysis and intelligent algorithms, the system can predict the gas diffusion process and dynamically adjust ventilation and gas recovery measures according to experimental conditions. Finally, through continuous feedback and optimization, the system can ensure that the gas concentration in the experimental environment always remains within a safe range, effectively guaranteeing the smooth progress of the experiment and ensuring the safety of experimental personnel.

[0131] Through the multi-sensor network and dynamic adjustment mechanism of the intelligent control platform, this implementation method can accurately monitor the release and migration process of harmful gases in deep roadway, and continuously adjust the experimental environment according to real-time data, optimizing gas treatment measures. This system can not only provide real-time monitoring data, but also calculate the future changes in gas concentration through intelligent algorithms and automatically adjust ventilation plans and gas recovery measures, thus realizing dynamic optimization during the experiment. The implementation of this system will significantly improve the safety and accuracy of the experimental process, providing a new intelligent solution for the management of harmful gases in deep roadway.

[0132] Embodiment 2: In this embodiment, by integrating a gas release and recovery control system, a fully enclosed experimental platform is built, which can simulate the release process of different gas sources in deep roadway and use chemical and physical methods to recover harmful gases. Combined with the intelligent control platform, the system can monitor the gas concentration in real time and automatically adjust ventilation and gas recovery measures, thus effectively dealing with gas leakage and diffusion problems.

[0133] In this embodiment, the experimental platform adopts a modular design. Through multiple gas sources, a pressure regulation system, a fan and a gas recovery module, it accurately simulates the release and migration of harmful gases in the roadway. In the selection of gas sources, different types of harmful gas sources are set on the experimental platform, such as carbon monoxide, hydrogen sulfide, etc. These gas sources are connected to the pressure regulation device through pipelines, and can simulate the release process of gases under different pressures, ensuring the authenticity and diversity of the experiment.

[0134] Gas sources are set at different positions in the roadway model and can be flexibly adjusted according to experimental requirements. The release amount and flow rate of each gas source can be precisely controlled to simulate the gas release situation under different environments. During the gas release process, the system will monitor the gas concentration in real time and adjust the release mode according to environmental conditions (such as temperature, humidity, etc.) to ensure that the simulated environment is as close as possible to the actual situation.

[0135] The core of the system is the intelligent control platform. The platform monitors environmental parameters such as gas concentration, air temperature, and air pressure in the roadway in real time through sensor data and controls the gas recovery and ventilation systems according to the real-time data. The gas recovery system integrates chemical washing and physical adsorption technologies and can efficiently recover harmful gases in the roadway. When the gas concentration exceeds the set threshold, the intelligent control platform will automatically start the recovery system. The chemical washing device can treat the toxic substances in the harmful gases, while the physical adsorption system uses materials such as activated carbon to adsorb and remove the gases.

[0136] The intelligent platform can not only monitor the gas concentration in real time but also dynamically adjust devices such as gas sources, fans, and recovery systems according to sensor data. For example, when the gas concentration in a certain area is too high, the system will adjust the running speed of the fan to increase the ventilation volume; at the same time, start the gas recovery system to process the excessive gas. Through the refined control of this system, the gas concentration in the experimental environment is always within the safe range.

[0137] This experimental system has strong feedback and optimization capabilities. When the ventilation and recovery measures fail to achieve the expected results, the system will adjust the operation strategy according to the real-time data. For example, if the air volume of the fan is not enough to control the gas concentration, the system will automatically increase the number of fans or raise the wind speed; if the gas recovery efficiency is not high, the system will automatically increase the processing capacity of the recovery device. Through this adaptive mechanism, the system can flexibly adjust the operation under different experimental conditions to ensure that the gas concentration is always controlled at a safe level.

[0138] The system also has efficient data analysis and optimization functions. By collecting and analyzing data such as gas diffusion, accumulation, and wind speed, the system can identify potential risk factors and make predictions. For example, before the experiment starts, the system will predict the possible gas accumulation areas and risk points based on historical data and take preventive measures in advance. Through big data analysis, the intelligent control platform can continuously optimize the gas diffusion simulation and control strategy to ensure the accuracy and safety of the experiment.

[0139] Embodiment 3: In this embodiment, by introducing big data analysis and artificial intelligence technology into the gas safety management system, the diffusion and accumulation process of gas in deep roadway is monitored and predicted in real time. The system can utilize the combination of historical data and real-time data to optimize the gas diffusion model, and based on the optimization algorithm of artificial intelligence, automatically adjust the ventilation and gas recovery measures to ensure that the gas concentration is always maintained within the safe range.

[0140] When implementing this solution, first establish a large data collection and storage platform to collect the data of sensors in the roadway in real time, including information such as harmful gas concentration, temperature, air pressure, humidity, wind speed, etc. These data are not only used for the current gas management experiment, but also for training and optimizing the gas diffusion prediction model. Through the storage function of the big data platform, the system can accumulate tens of thousands of experimental data and analyze the laws of gas behavior through data mining technology.

[0141] The system combines historical data and real-time collected environmental parameters to model the gas diffusion behavior through artificial intelligence technologies (such as machine learning and deep learning algorithms). Through continuous training, the model is continuously optimized, enabling the system to accurately predict the gas diffusion path, accumulation points, etc. according to different environmental conditions (such as high temperature, high humidity, high air pressure, etc.). The prediction ability of the AI model enables the system to anticipate the gas migration process in the roadway in advance and provide more decision-making support.

[0142] Based on the optimized gas diffusion prediction model, the intelligent control platform can make real-time predictions and adjust the ventilation plan and gas recovery measures according to the prediction results. For example, when the AI model predicts that the gas concentration in a certain area will exceed the safety threshold, the system can start the fan or recovery device in advance to reduce the risk of gas leakage. Through this real-time dynamic control, the system can ensure that the gas concentration in the roadway is always within the safe range and avoid potential explosion and poisoning accidents.

[0143] In addition, the system can also continuously adjust its control strategy according to real-time data. After each adjustment, the system will evaluate the effect according to the feedback data and continue to optimize the operation strategy. For example, when a certain control scheme fails to effectively reduce the gas concentration, the system can adjust the algorithm, increase the recovery equipment or adjust the ventilation air volume until the best effect is achieved.

[0144] The system also has safety warning and emergency response functions, and can trigger an alarm when the gas concentration is too high or the equipment malfunctions. The warning information can be not only displayed to the operators through a visual interface, but also notified to relevant personnel in real time by means of voice reminders or text messages. In case of an emergency, the system will automatically execute preset emergency response measures, such as starting an emergency ventilation system or switching to a standby gas recovery device. Through this intelligent emergency response mechanism, the system can quickly respond in case of gas leakage or anomalies, ensuring the safety of the experiment.

[0145] By integrating a multi-sensor network and an intelligent control platform, the system of the present invention can achieve precise monitoring and prediction of the release, migration, and diffusion processes of harmful gases in deep roadway. The real-time collected environmental data is combined with the gas diffusion model, enabling the system to predict the behavior of the gas under different environmental conditions at each stage of the gas concentration change and adjust the control measures in real time. This precise prediction ability can not only effectively identify potential gas accumulation areas and risk points, but also provide comprehensive gas distribution information for experimental personnel, ensuring that potential safety hazards can be discovered and handled in a timely manner, thus greatly improving the accuracy of gas monitoring and management.

[0146] Through intelligent and automatic control, the present invention improves the utilization efficiency of resources and the safety of the experiment. The intelligent control platform can automatically adjust the ventilation system and gas recovery device based on real-time data, reducing manual intervention and operation errors, optimizing gas flow and concentration management, and avoiding energy waste. For example, the system can dynamically adjust the working states of the fan and the recovery device according to the gas concentration change, ensuring the effective utilization of energy while keeping the gas concentration within a safe range. By continuously optimizing the control strategy, the system also has a self-learning function, making the operation more efficient and environmentally friendly, thus enhancing the intelligent level and sustainability of the entire experimental process.

[0147] The above formulas are all dimensionless and take their numerical values for calculation. The formula is obtained by collecting a large amount of data for software simulation to get a formula closest to the actual situation. The preset parameters in the formula are set by those skilled in the art according to the actual situation.

[0148] Only some exemplary embodiments of the present invention have been described by way of illustration above. Undoubtedly, for those of ordinary skill in the art, without departing from the spirit and scope of the present invention, the described embodiments can be modified in various different ways. Therefore, the above drawings and descriptions are illustrative in nature and should not be construed as limiting the protection scope of the claims of the present invention.

[0149] It should be noted that in this text, relational terms such as first and second are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any actual relationship or order between these entities or operations. Moreover, the terms "comprising", "including" or any other variants thereof are intended to cover non-exclusive inclusion, such that a process, method, article or device comprising a series of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such process, method, article or device. Without further limitation, an element defined by the statement "comprising an..." does not exclude the presence of additional identical elements in the process, method, article or device comprising the element.

[0150] It should be understood that in various embodiments of the present application, the magnitudes of the sequence numbers of the above processes do not imply the order of execution, and the order of execution of each process should be determined by its function and internal logic, and should not constitute any limitation to the implementation process of the embodiments of the present application.

[0151] Those of ordinary skill in the art can realize that the units and algorithm steps of the examples described in conjunction with the embodiments disclosed herein can be implemented by electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are executed in a hardware or software manner depends on the specific application and design constraints of the technical solution. Professional technicians can use different methods for each specific application to implement the described functions, but such implementation should not be considered to exceed the scope of the present application.

[0152] Those skilled in the art can clearly understand that for the convenience and brevity of description, the specific working processes of the systems, devices and units described above can refer to the corresponding processes in the foregoing method embodiments, and will not be elaborated herein.

[0153] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place, or may be distributed to multiple network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0154] In addition, in each embodiment of the present application, the functional units can be integrated into one processing unit, or each unit can exist physically alone, or two or more units can be integrated into one unit.

[0155] As described above, this is only the specific implementation manner of the present application. However, the protection scope of the present application is not limited thereto. Any person skilled in the art within the technical scope disclosed by the present application can easily think of changes or substitutions, which should all be covered within the protection scope of the present application. Therefore, the protection scope of the present application shall be subject to the protection scope of the claims described above.

[0156] Only some exemplary embodiments of the present invention have been described by way of illustration above. Without doubt, for those of ordinary skill in the art, the described embodiments can be modified in various different ways without departing from the spirit and scope of the present invention. Therefore, the above drawings and descriptions are illustrative in nature and should not be construed as limiting the protection scope of the claims of the present invention.

Claims

1. An intelligent monitoring method for the release and migration of harmful gases in deep underground tunnels, characterized in that: The following steps are involved: Construct an experimental system, build a deep underground tunnel model through a modular steel frame structure, and set up multiple gas sources to simulate the gas release and migration process under different environments in the tunnel; Gas sensors and flow rate sensors are arranged in the tunnel model to collect environmental parameters in the tunnel in real time, and to monitor and collect data during gas migration in real time; Through the intelligent control platform, the gas release and migration process is dynamically simulated based on the real-time collected data. The intelligent control platform has a dynamic adjustment function, which automatically adjusts the ventilation plan and gas recovery measures according to the real-time data; Based on the data collected by the sensors, the dynamic data analysis algorithm is used to predict and simulate the diffusion path and concentration changes of the gas in real time. The gas diffusion model is established through the algorithm and compared with the actual environmental data to accurately predict the further diffusion of harmful gases. According to the gas diffusion model and prediction results, an adaptive control strategy based on the optimization algorithm is used to automatically adjust the working status of the ventilation equipment and gas recovery equipment in the tunnel to achieve optimal control of the concentration of harmful gases.

2. The intelligent monitoring method for the release and migration of harmful gases in deep underground tunnels according to claim 1 is characterized in that: The specific steps of constructing the experimental system, building a deep underground tunnel model through a modular steel frame structure, and setting up multiple gas sources to simulate the gas release and migration process under different environments in the tunnel are as follows: Design and plan the structure and function of the experimental system; Select steel frame materials according to experimental requirements and ensure that the modular structure is easy to assemble, disassemble and maintain; Install multiple hazardous gas sources and precisely control the type, flow rate and concentration of gas release through gas pumps and gas pressure regulation systems; A gas flow control and monitoring system was established, and fans, regulators and sensors were used to monitor gas parameters in real time to ensure precise control and safety of the experimental process.

3. The intelligent monitoring method for the release and migration of harmful gases in deep underground tunnels according to claim 1 is characterized in that: The specific steps of arranging gas sensors and flow rate sensors in the tunnel model to collect environmental parameters in the tunnel in real time and to monitor and collect data during gas migration in real time are as follows: Determine and design the type, location and layout of gas sensors and temperature and humidity sensors to ensure comprehensive monitoring of environmental parameters in the tunnel; Install gas sensors and temperature and humidity sensors in the tunnel model and ensure their stability and accuracy, as well as good contact with the gas source and environment; Connect the installed sensors to the intelligent control system to achieve real-time data collection, transmission and processing; The data is monitored in real time through an intelligent control system, and various parameters in the tunnel are dynamically adjusted based on sensor feedback.

4. The intelligent monitoring method for the release and migration of harmful gases in deep underground tunnels according to claim 1 is characterized in that: Through the intelligent control platform, the gas release and migration process is dynamically simulated based on the real-time collected data. The specific steps for automatically adjusting the ventilation plan and gas recovery measures based on the real-time data are as follows: Real-time collection and transmission of tunnel environmental parameters to the intelligent control platform for data processing and monitoring; Through the intelligent control platform, a physical model of gas diffusion and migration is established based on real-time collected environmental data to simulate the behavior of gas under different environmental conditions; Based on the simulation results, the intelligent control platform automatically adjusts the ventilation scheme and gas recovery measures to optimize air flow distribution and the emission and recovery of harmful gases; The intelligent control platform conducts feedback evaluation based on the adjusted effects and further improves the control strategy through optimization mechanism to ensure accurate control of gas concentration.

5. The intelligent monitoring method for the release and migration of harmful gases in deep underground tunnels according to claim 1 is characterized in that: Based on the data collected by the sensor, the dynamic data analysis algorithm is used to predict and simulate the diffusion path and concentration changes of the gas in real time. The gas diffusion model is established through the algorithm, and the model is compared with the actual environmental data to accurately predict the further diffusion of harmful gases. The specific steps are as follows: The data collected by the sensor is used to establish a gas diffusion model, and the spatial distribution of gas concentration is calculated through a formula. The Fick diffusion law is used to describe the diffusion behavior of gas in the tunnel. To simplify the analysis, the diffusion coefficient is used to characterize the diffusion rate of the gas. The calculation expression is as follows: ， Where C(x, t) is the gas concentration at position x and time t, C0 is the initial gas concentration, x is the spatial position of gas diffusion, D is the diffusion coefficient of the gas, and t is time; The diffusion coefficient of the gas is dynamically adjusted according to the environmental parameters collected in real time. By adjusting the diffusion coefficient, the diffusion behavior of the gas in the actual environment can be more accurately simulated. The calculation expression is as follows: D(t)=D0(1+αT(t)-βP(t)), Where D(t) is the dynamic diffusion coefficient at time t, D0 is the diffusion coefficient under reference conditions, α is the influence factor of temperature on the diffusion coefficient, T(t) is the temperature at time t, β is the influence factor of air pressure on the diffusion coefficient, and P(t) is the air pressure at time t; Based on the gas concentration C(x, t) and the dynamic diffusion coefficient D(t) at time t, the gas diffusion path is predicted and compared with the actual sensor data to optimize the gas diffusion model. The calculation expression is as follows: ， Where ΔC is the error between the predicted concentration and the actual concentration, C real (x i ,t i ) is the gas concentration measured at the i-th sensor position x and time t, n is the total number of sensors, C model (x i , t i , D(t)) is the gas concentration predicted by the model, and the formula is as follows: ， In the formula, x i is the measurement position x of the ith sensor, x0 is the position of the gas source, t i is the time point, indicating the time from when the gas source starts to release and reaches x i The time of the location.

6. The intelligent monitoring method for the release and migration of harmful gases in deep underground tunnels according to claim 1 is characterized in that: According to the gas diffusion model and prediction results, the adaptive control strategy based on the optimization algorithm is used to automatically adjust the working status of the ventilation equipment and gas recovery equipment in the tunnel to achieve the optimal control of the concentration of harmful gases. The specific steps are as follows: First, the gas concentration change rate is predicted using the gas diffusion model based on the real-time collected gas concentration data and environmental parameters. The gas concentration change rate is described by the following partial differential equation: ， In the formula, is the rate of change of gas concentration over time, C(x, t) is the gas concentration, which indicates the gas concentration at position x and time t, and D is the diffusion coefficient, which indicates the rate at which the gas diffuses in the tunnel. (x, t) is the spatial Laplace operator of the concentration, v is the gas velocity vector, is the convection term, S(x, t) is the gas source term; According to the predicted gas concentration change rate Combining the performance parameters of ventilation equipment and gas recovery equipment, a target optimization function is constructed to minimize the concentration of harmful gases in the tunnel and the operating cost. The target function is expressed as follows: ， Where V is the volume of the tunnel, C safe is the set safety gas concentration threshold, λ is the weight factor, E j (v j , P j ) is the energy consumption function of the jth device, which depends on the wind speed v j and air pressure P j , m is the total number of devices; Using the optimized wind speed v j and pressure P j , adjust the working status of ventilation and gas recovery equipment in real time, and continuously optimize the model based on feedback data. The control equation of the ventilation system is expressed as follows: ， In the formula, v j (t+1) is the wind speed of the jth device at time t+1, v j (t) is the wind speed of the jth device at time t, ω is the step coefficient, It is the gradient of the objective function with respect to wind speed, indicating the impact of wind speed adjustment on the optimization objective.

Images