Dynamic monitoring of coal mine goaf spontaneous combustion three zones and regulation system by injecting liquid carbon dioxide

Abstract

The application discloses a kind of coal mine goaf spontaneous combustion three-zone dynamic monitoring and liquid carbon dioxide injection regulation system, it is related to mine field combustion prevention technical field;Sensor deployment dynamic adjustment acquisition layout and frequency;Data processing and analysis module, with depth preprocessing and improved neural network division spontaneous combustion three-zone, judge risk;Liquid carbon dioxide injection control module, by regulating valve and fuzzy-neural network algorithm as needed control injection;Remote monitoring and early warning module, based on cloud and big data realizes monitoring, multistage early warning and virtual simulation, each module is coordinated and can be fused with existing system.The application realizes coal mine goaf spontaneous combustion three-zone accurate monitoring and liquid carbon dioxide high-efficiency injection by accurate multi-source monitoring, intelligent analysis decision and dynamic accurate regulation;Can early warning hidden danger, improve prevention and control precision, reduce resource waste, also can be fused with existing system, guarantee coal mine safety production, reduce accident risk.

Description

Technical Field

[0001] This invention relates to the field of fire prevention technology in mines, and in particular to a dynamic monitoring and liquid carbon dioxide injection control system for spontaneous combustion zones in coal mine goafs. Background Technology

[0002] Spontaneous combustion of coal in goaf areas during coal mining is a major hidden danger threatening safe production. With the increasing depth and intensity of coal mining, the goaf area expands and geological conditions become increasingly complex, highlighting the limitations of traditional monitoring and control methods. Current monitoring of spontaneous combustion in coal mine goaf areas largely relies on single-type sensors, such as temperature sensors or carbon monoxide sensors. This monitoring method not only lacks comprehensive information collection but also suffers from low sensor accuracy and slow response speed, making it difficult to accurately capture subtle changes in the early stages of spontaneous combustion, thus failing to detect potential hazards in a timely manner. Furthermore, the sensor installation layout lacks scientific planning and fails to fully consider factors such as the geological structure and ventilation conditions of the goaf area, resulting in data that cannot accurately reflect the actual situation of the three zones of spontaneous combustion, posing significant challenges to subsequent prevention and control efforts.

[0003] In terms of spontaneous combustion prevention, liquid carbon dioxide injection, as a commonly used fire extinguishing technology, has several problems in its control process. Current injection systems mostly employ fixed injection strategies, failing to flexibly adjust according to the dynamic changes in the three spontaneous combustion zones of the goaf and the actual risk level. For example, in areas with low coal spontaneous combustion risk, injecting at the conventional flow rate results in wasted liquid carbon dioxide; while in high-risk areas, the injection volume and duration may be insufficient, making it difficult to effectively suppress coal oxidation and spontaneous combustion. Furthermore, the injection flow control lacks precision; existing regulating valves have slow response speeds and low adjustment accuracy, failing to quickly adapt to the complex and changing conditions of the goaf, leading to a significant reduction in injection effectiveness.

[0004] The entire monitoring and control system lacks effective collaboration and intelligent decision-making capabilities among its various components. Data processing and analysis methods are outdated, relying heavily on simple threshold judgments and statistical analysis, making it difficult to delve into the underlying spontaneous combustion patterns and risk trends. The remote monitoring system has limited functionality, only providing basic data display and alarms, failing to offer managers a scientific basis for decision-making. Furthermore, the system operates independently from the mine's existing safety monitoring and automation control systems, resulting in data silos and severely hindering the overall effectiveness of spontaneous combustion prevention in coal mine goaf areas. A more advanced and intelligent monitoring and control system is urgently needed to ensure safe coal mine production. Summary of the Invention

[0005] The present invention proposes a dynamic monitoring and liquid carbon dioxide injection control system for spontaneous combustion zones in coal mine goaf areas to solve the problems mentioned in the prior art.

[0006] To achieve the above objectives, the present invention adopts the following technical solution: a dynamic monitoring and liquid carbon dioxide injection control system for spontaneous combustion zones in coal mine goafs, comprising:

[0007] Sensor data acquisition module: Temperature sensors, oxygen sensors, and carbon monoxide sensors are installed in the roadways, roof, and floor of the coal mine goaf. A semiconductor carbon monoxide sensor integrating noise reduction algorithms is also included. Remove interference signals, where N filtered The filtered signal, N raw The original signal is N, α is the noise reduction coefficient, and N is the noise reduction coefficient. noise (i) represents the i-th noise sample, which collects carbon monoxide concentration data in real time. The methane sensor uses multi-band spectral detection technology. The sensor is distributed in the goaf area with dynamic grid spacing. The spacing is adjusted in real time according to the mining progress and geological changes in the goaf area. The data acquisition frequency is dynamically set according to the data change rate through an adaptive adjustment algorithm. The collected data is transmitted to the data processing and analysis module through wireless self-organizing network communication.

[0008] The data processing and analysis module receives data from the sensor data acquisition module and first preprocesses the data, including adaptive filtering, data fusion, and feature extraction. For temperature data, an adaptive filtering algorithm based on wavelet transform is used to automatically adjust the filtering parameters to remove noise based on the data's fluctuation characteristics. For gas concentration data, a data fusion algorithm based on Bayesian theory is used, combining prior knowledge and real-time measurement data to improve data accuracy. Then, a deep neural network-based three-zone classification model for spontaneous combustion is applied, incorporating an attention mechanism and formula... Different features are assigned different weights to highlight the influence of features on the classification of the three spontaneous combustion zones, where A i W is the attention weight for the i-th feature. a Let h be the attention weight matrix. i This is the i-th feature vector; simultaneously, based on the data change trend, it is determined using the formula... The weighted rate of change of each gas concentration is calculated to determine the spontaneous combustion risk level, where ΔC weighted β is the weighted rate of change of gas concentration. i C represents the weight of the i-th gas. t+1(i) and C t(i) denoted as the concentration of the i-th gas at adjacent time points, and Δt as the time interval.

[0009] Furthermore, it also includes:

[0010] The liquid carbon dioxide injection control module determines the location, flow rate, and timing of liquid carbon dioxide injection based on the three-zone classification and spontaneous combustion risk level obtained from the data processing and analysis module. A flow regulating valve controls the flow rate of liquid carbon dioxide, equipped with self-learning and adaptive adjustment functions. A fuzzy neural network control algorithm is used to regulate the flow rate, dynamically adjusting the valve opening based on oxygen concentration, temperature, and carbon monoxide concentration. The relationship between the injection flow rate and these factors is mapped using the formula Q = f(O2, T, CO), where Q is the injection flow rate, O2 is the oxygen concentration, and T is the temperature. CO represents the carbon monoxide concentration, and the function f is obtained through neural network training. In the oxidation zone, the injection flow rate is dynamically adjusted according to the oxygen concentration and temperature to reduce the oxygen concentration and inhibit coal oxidation and spontaneous combustion. The injection time is determined based on the duration of spontaneous combustion risk and the injection effect evaluation model. The injection effect evaluation model is evaluated using the formula E = ω1·ΔO2 + ω2·ΔT + ω3·ΔCO, where E is the injection effect evaluation value, ω1, ω2, and ω3 are weighting coefficients, and ΔO2, ΔT, and ΔCO are the changes in oxygen concentration, temperature, and carbon monoxide concentration before and after injection, respectively.

[0011] Remote monitoring and early warning module: Establish a remote monitoring center based on cloud computing and big data analysis, and connect it to the data processing and analysis module through a 5G network to display the temperature, gas concentration, spontaneous combustion zone division, and liquid carbon dioxide injection status information of the goaf in real time; set early warning thresholds for different levels, and when the data exceeds the early warning thresholds of different levels, the system will automatically issue different types of audible and visual alarm signals and notify relevant personnel through SMS, email, and APP push.

[0012] Sensor Fault Diagnosis and Compensation Submodule: This module monitors the sensor's operating status in real time, and determines whether a sensor fault has occurred through feature analysis and anomaly detection algorithms. If a sensor fault occurs, it performs data compensation based on historical data and data from adjacent normal sensors, using a data compensation algorithm based on spatiotemporal correlation. The algorithm is expressed using formulas... The continuity of data is achieved by combining the spatiotemporal correlation coefficient to determine the weights, where C compensated For the compensated data, γ j Let C be the weight of the j-th adjacent sensor. neighbor(j) This represents the data from the j-th adjacent sensor.

[0013] Liquid carbon dioxide storage and supply optimization module: This module monitors the liquid level, pressure, and temperature parameters of the liquid carbon dioxide storage tank in real time, and calculates the state of the liquid carbon dioxide inside the tank using a thermodynamic model. The thermodynamic model considers the material properties of the storage tank, changes in ambient temperature, and the phase change process of carbon dioxide, using formulas... Predict pressure changes within the storage tank, where P is pressure, n is amount of substance, R is gas constant, T is temperature, V is volume, and δ is the influence coefficient of ambient temperature. env The ambient temperature is used as the reference. Based on the demand forecast of the liquid carbon dioxide control module, an optimization strategy based on a genetic algorithm is adopted to optimize the storage and supply strategy of liquid carbon dioxide, taking into account factors such as supply cost, transportation distance, and storage capacity, and to arrange the replenishment and distribution of liquid carbon dioxide. Simultaneously, safety valves and pressure regulating devices are installed to ensure the safety of the storage tank. The safety valve automatically adjusts its opening pressure according to pressure changes within the storage tank, using formula P. open =P base +β·ΔP is dynamically adjusted, where P open To activate pressure, P base The base opening pressure is given by β, which is the pressure adjustment coefficient, and ΔP is the pressure change.

[0014] Furthermore, the sensors in the sensor data acquisition module adopt a modular design, which facilitates installation, maintenance and replacement. The installation position of the sensors is optimized and determined through three-dimensional geological modeling and numerical simulation technology. Based on the geological conditions, ventilation conditions and spontaneous combustion characteristics of coal in the goaf, the monitoring effect of the sensors under different installation positions is simulated, the optimal installation scheme is selected, and data reflecting the spontaneous combustion state of the goaf is accurately collected.

[0015] Furthermore, the deep neural network three-zone classification model in the data processing and analysis module adopts transfer learning and incremental learning techniques; at the same time, the model adopts model fusion technology to fuse neural network models with different structures, and obtains the final classification result through weighted averaging, thereby improving the accuracy of the three-zone classification.

[0016] Furthermore, the flow regulating valve in the liquid carbon dioxide injection control module adopts piezoelectric drive technology, and the control algorithm of the regulating valve adopts a model predictive control method. By establishing a dynamic model of the injection process, the injection effect in the future time is predicted, and the opening of the regulating valve is adjusted in real time according to the prediction result. At the same time, the module is also equipped with a flow feedback regulation function. The flow sensor installed on the injection pipeline monitors the injection flow rate in real time and compares it with the set flow rate, and the error is corrected by the PID control algorithm.

[0017] Furthermore, the remote monitoring and early warning module is equipped with decision support functions. It integrates and correlates geological information, mining technology, and safety regulations of coal mine goaf areas through knowledge graph technology. When abnormal monitoring data occurs, the system performs reasoning and analysis based on the knowledge graph to provide decision suggestions to relevant personnel. At the same time, the module is also equipped with a visual interactive function, allowing users to interact with the virtual simulation model through touch screens and mice to adjust operating parameters in real time.

[0018] Furthermore, the feature analysis and anomaly detection algorithms in the sensor fault diagnosis and compensation module adopt a distributed computing architecture, allocating data processing tasks to computing nodes for parallel processing; at the same time, the module is also equipped with a fault prediction function, which analyzes the historical fault data and current working status data of the sensor, and uses a time series analysis algorithm to predict the time and type of sensor failure, so as to maintain and replace it in advance.

[0019] Furthermore, the optimization strategy based on genetic algorithm in the liquid carbon dioxide storage and supply optimization module adopts an adaptive genetic operator, which dynamically adjusts the crossover probability and mutation probability according to the fitness value during the optimization process, thereby improving the search efficiency and convergence speed of the algorithm. At the same time, the module also considers the quality change factors of liquid carbon dioxide, and adjusts the supply strategy according to the detection results by periodically detecting the purity and impurity content of liquid carbon dioxide.

[0020] Furthermore, the system also includes an interface module for integration with existing coal mine safety monitoring and automation control systems. The interface module adopts standardized data communication protocols and interface specifications to achieve data transmission and real-time sharing. Through data fusion, this system utilizes the resources and data of the existing coal mine systems, while simultaneously feeding back the monitoring data and control information of this system to the existing systems, thereby realizing integrated management of coal mine safety monitoring and control.

[0021] Compared with existing technologies, the beneficial effects of this invention are:

[0022] In the monitoring phase, by deploying a variety of high-precision, customized sensors and adopting a dynamic grid layout and adaptive acquisition frequency adjustment, key data such as temperature and gas concentration in the goaf can be obtained comprehensively, accurately, and in real time. Compared with traditional monitoring methods, the accuracy and timeliness of the data are greatly improved, and potential spontaneous combustion hazards can be detected in advance.

[0023] The data processing and analysis module utilizes advanced algorithms and models to accurately classify the three zones of spontaneous combustion. Furthermore, by weighted calculations of gas concentration change rates, it can more scientifically determine the risk level of spontaneous combustion, providing a reliable basis for prevention and control efforts. The liquid carbon dioxide injection control module's intelligent flow regulating valve and advanced control algorithms can dynamically and precisely adjust the injection location, flow rate, and time based on the risk level and real-time monitoring data. This effectively suppresses coal spontaneous combustion while avoiding the waste of liquid carbon dioxide.

[0024] The remote monitoring and early warning module, based on cloud computing, big data, and virtual simulation technologies, enables efficient data display, multi-level early warning, and intelligent decision support. Managers can intuitively understand the condition of the goaf and obtain decision-making suggestions through a visual interactive interface, improving management efficiency and the scientific basis of decision-making. Furthermore, the collaborative cooperation between the system's sub-modules and its deep integration with existing coal mine systems breaks down information silos, achieving integrated management of safety monitoring and control. This comprehensively improves the overall effectiveness of spontaneous combustion prevention in coal mine goafs, effectively ensuring safe coal mine production and reducing economic losses and safety accidents. Attached Figure Description

[0025] Figure 1 This is a schematic block diagram of the dynamic monitoring and liquid carbon dioxide injection control system for spontaneous combustion zones in coal mine goaf proposed in this invention.

[0026] Figure 2 This is a schematic diagram comparing the accuracy of sensor data acquisition in different systems for dynamic monitoring of spontaneous combustion zones in coal mine goaf and injection of liquid carbon dioxide, as proposed in this invention. Detailed Implementation

[0027] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0028] In the description of this invention, it should be understood that the terms "center," "longitudinal," "lateral," "length," "width," "thickness," "upper," "lower," "front," "rear," "left," "right," "vertical," "horizontal," "top," "bottom," "inner," "outer," "clockwise," and "counterclockwise," etc., indicate the orientation or positional relationship based on the orientation or positional relationship shown in the accompanying drawings. They are only for the convenience of describing this invention and simplifying the description, and do not indicate or imply that the device or element referred to must have a specific orientation, or be constructed and operated in a specific orientation. Therefore, they should not be construed as limitations on this invention.

[0029] Furthermore, the terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of indicated technical features. Thus, features defined with "first" and "second" may explicitly or implicitly include one or more of the stated features. In the description of this invention, "a plurality of" means two or more, unless otherwise explicitly specified. Furthermore, the terms "installed," "connected," and "linked" should be interpreted broadly; for example, they may refer to a fixed connection, a detachable connection, or an integral connection; they may refer to a mechanical connection or an electrical connection; they may refer to a direct connection or an indirect connection through an intermediate medium; and they may refer to the internal connection of two components. Those skilled in the art can understand the specific meaning of the above terms in this invention based on the specific circumstances. The invention will now be described in further detail with reference to the accompanying drawings.

[0030] Reference Figure 1 and Figure 2 : A specific implementation method for a dynamic monitoring and liquid carbon dioxide injection control system for spontaneous combustion zones in coal mine goafs.

[0031] In coal mining operations, the various modules of this application system work closely together, from data acquisition to control and execution, to comprehensively ensure the safety of coal mine goaf areas. Specific implementation details are as follows:

[0032] Multi-sensor data acquisition module: For sensor selection, the temperature sensor is a high-temperature resistant, electromagnetic interference-resistant distributed fiber Bragg grating temperature sensor, with a temperature measurement accuracy of ±0.05℃ in the range of -40℃ to 60℃, and ±0.1℃ in the range of 60℃ to 120℃; the oxygen sensor is an electrochemical sensor based on micro-nano structures, possessing fast response characteristics, with a response time of less than 5 seconds, a measurement range of 0-25% VOL, and an accuracy of ±0.08% VOL; the carbon monoxide sensor is a semiconductor sensor integrating an intelligent noise reduction algorithm, using a noise reduction formula... (where α is preset to 0.3 based on the on-site environment, and n is taken from the 10 most recent noise samples), which improves the measurement accuracy to ±0.8ppm; the methane sensor adopts multi-band spectral detection technology, with a measurement range of 0-100% LEL and an accuracy of ±0.8% LEL.

[0033] During the installation and deployment phase, based on the 3D geological model of the goaf and the mining progress, sensor nodes were installed every 20 meters in the roadway and every 50 square meters in the roof and floor. Fiber optic temperature sensors were embedded 3-5 cm deep into the coal face using specialized construction teams and fixed with high-temperature adhesive. Other gas sensors were installed in specially designed explosion-proof housings, fixed to the roadway sidewall at a height of 1.5-2 meters. The initial sensor acquisition frequency was set to once per minute. The system monitored the data change rate in real time. When the temperature change rate in a certain area exceeded 1℃ / 10 minutes, an adaptive adjustment algorithm was used to increase the sensor acquisition frequency in that area to once every 2 minutes. Data transmission adopted the ZigBee wireless self-organizing network protocol. Each sensor node was equipped with a low-power processor, which initially encoded the collected data and transmitted it to the goaf edge aggregation node via multi-hop relay, and then sent it to the data processing and analysis module via fiber optic network.

[0034] Data Processing and Analysis Module: After the data transmitted from the aggregation node enters the preprocessing unit, the temperature data is processed using an adaptive filtering algorithm based on wavelet transform. A sym4 wavelet basis is selected for three-level decomposition, and the threshold is automatically adjusted based on the energy distribution of high-frequency coefficients to effectively filter out noise. Gas concentration data fusion is based on Bayesian theory. Historical monitoring data is used to determine the prior probability distribution of each sensor's measurement values, and the posterior probability is calculated by combining this with real-time data to obtain the fusion result.

[0035] An improved deep neural network model for spontaneous combustion of three zones is built on the TensorFlow framework and consists of 5 convolutional layers and 3 fully connected layers. An attention mechanism is introduced, using a formula... Calculate the feature weights, where W a The matrix parameters were optimized using the backpropagation algorithm. The training dataset integrated on-site monitoring data and laboratory simulation data from 10 typical coal mines across the country, totaling 200,000 samples. The model was trained using stochastic gradient descent with a learning rate of 0.001, and completed after 50 iterations.

[0036] When calculating the weighted rate of change of gas concentration, the weights are set as follows: oxygen concentration weight β1 = 0.4, carbon monoxide concentration weight β2 = 0.3, and methane concentration weight β3 = 0.3, according to the formula... The weighted gas concentration change rate for each area is calculated every 10 minutes to assess the risk level of spontaneous combustion.

[0037] Liquid carbon dioxide injection control module: The intelligent flow regulating valve adopts piezoelectric drive technology with a response time of less than 0.5 seconds and is installed at the branch node of the injection pipeline in the goaf. The fuzzy neural network control algorithm is implemented through MATLAB programming. The fuzzy controller inputs are oxygen concentration deviation, temperature deviation, and carbon monoxide concentration deviation, and the output is the regulating valve opening control signal. The neural network part adopts a 3-layer structure: 3 nodes in the input layer, 10 nodes in the hidden layer, and 1 node in the output layer. The weights are determined through offline training.

[0038] During the injection process, the real-time collected data on oxygen concentration (O2), temperature (T), and carbon monoxide concentration (CO) are input into the algorithm to calculate the injection flow rate (Q) based on the formula Q = f(O2, T, CO). When a region is in the oxidation zone and the oxygen concentration exceeds 18%, the injection flow rate in that region is increased preferentially. In the injection effect evaluation model, ω1 = 0.5, ω2 = 0.3, and ω3 = 0.2 are set. Every 30 minutes after injection, the effect is evaluated according to the formula E = ω1·ΔO2 + ω2·ΔT + ω3·ΔCO. If the effect is not met, the injection strategy is adjusted.

[0039] Remote monitoring and early warning module: The remote monitoring center is located in the coal mine's ground dispatch room. The server uses Huawei FusionServer Pro series (128GB memory, 24-core CPU), and is running Windows Server 2019 operating system and self-developed monitoring software. After receiving data via 5G network, it displays the temperature field of the goaf, gas concentration distribution, spontaneous combustion zone division, and injection pipeline status in real time on a 3D visualization interface.

[0040] The warning thresholds are set at three levels: Level 1 warning is triggered when the temperature exceeds 50℃, the oxygen concentration is below 18%, and the carbon monoxide concentration exceeds 100ppm; Level 2 warning is triggered when the temperature exceeds 60℃, the oxygen concentration is below 16%, and the carbon monoxide concentration exceeds 200ppm; Level 3 warning is triggered when the temperature exceeds 70℃, the oxygen concentration is below 14%, and the carbon monoxide concentration exceeds 300ppm. When different levels of warnings are triggered, the system issues yellow, orange, and red audible and visual alarms respectively, and sends information to 10 relevant personnel, including the mine manager and safety director, via SMS platform. The virtual simulation function is developed based on the Unity3D platform, importing geological models and real-time data of the goaf area. Users can simulate and adjust injection parameters, ventilation conditions, and other operating conditions to assist in decision-making.

[0041] Sensor Fault Diagnosis and Compensation Submodule: The sensor fault diagnosis program is written in Python and deployed on edge computing nodes. Multi-scale feature analysis utilizes the PyWavelets library for 5-scale wavelet decomposition to extract energy and entropy features; anomaly detection is based on the support vector machine algorithm from the Scikit-learn library, with a training set containing 100,000 normal data sets and 20,000 fault simulation data sets. After a fault occurs, a data compensation algorithm based on spatiotemporal correlation is initiated, determining the weight γ by calculating the spatiotemporal correlation coefficient of adjacent sensors. j According to the formula Complete data compensation to ensure monitoring continuity.

[0042] Liquid carbon dioxide storage and supply optimization submodule: The liquid carbon dioxide storage tank is equipped with high-precision level, pressure, and temperature sensors, collecting data 5 times per minute. An improved thermodynamic model, implemented using C# programming, is deployed in the storage tank control system to calculate pressure in real time. When the pressure exceeds 1.8 MPa, the intelligent safety valve activates according to formula P... open =P base +β·ΔP(P base =1.8MPa, β=0.2) Automatically adjusts the opening pressure. The optimization strategy based on a genetic algorithm was developed on the Java platform, with a population size of 50, an initial crossover probability of 0.8, and an initial mutation probability of 0.1, adaptively adjusting. Liquid carbon dioxide purity is checked weekly; if purity is below 98%, this tank is used first and replenished promptly.

[0043] Data representation and interpretation

[0044] Comparison Projects Traditional system This application system Average time to detect spontaneous combustion hazards (days) 5 1 Average savings in liquid carbon dioxide (tons / month) 0 30 Spontaneous combustion rate in goaf areas (times / year) 2 0.3 Average decision response time (minutes) 60 10

[0045] Traditional systems, due to limitations in sensor performance and outdated data processing methods, suffer from delayed detection of spontaneous combustion hazards, averaging 5 days and missing the optimal prevention and control window. The system proposed in this application, leveraging high-precision sensors and advanced algorithms, significantly reduces hazard detection time to 1 day, providing ample time for early intervention. Regarding liquid carbon dioxide usage, traditional systems lack intelligent control, resulting in resource waste; the system proposed in this application saves 30 tons per month through precise control. In terms of safety, traditional systems average 2 spontaneous combustion incidents per year; the system proposed in this application, through real-time monitoring and intelligent control, reduces the incident rate to 0.3 times per incident. In terms of decision-making and response, traditional systems rely on manual analysis, averaging 60 minutes; the system proposed in this application, utilizing remote intelligent monitoring and virtual simulation, can complete decision-making and response within 10 minutes, greatly improving the coal mine's ability to cope with spontaneous combustion risks and ensuring safe production.

[0046] The above are merely preferred embodiments of the present invention, but the scope of protection of the present invention is not limited thereto. Any equivalent substitutions or modifications made by those skilled in the art within the scope of the technology disclosed in the present invention, based on the technical solution and inventive concept of the present invention, should be covered within the scope of protection of the present invention.

Claims

1. A dynamic monitoring and liquid carbon dioxide injection control system for spontaneous combustion zones in coal mine goafs, characterized in that, include: Sensor data acquisition module: Temperature sensors, oxygen sensors, and carbon monoxide sensors are installed in the roadways, roof, and floor of the coal mine goaf. The methane sensor adopts multi-band spectral detection technology. The sensors are distributed in the goaf with dynamic grid spacing, which is adjusted in real time according to the mining progress and geological changes in the goaf. The data acquisition frequency is dynamically set according to the data change rate through an adaptive adjustment algorithm. The acquired data is transmitted to the data processing and analysis module through wireless self-organizing network communication. The data processing and analysis module receives data from the sensor data acquisition module and first preprocesses the data, including adaptive filtering, data fusion, and feature extraction. For temperature data, an adaptive filtering algorithm based on wavelet transform is used to automatically adjust the filtering parameters to remove noise based on the data's fluctuation characteristics. For gas concentration data, a data fusion algorithm based on Bayesian theory is used, combining prior knowledge and real-time measurement data to improve data accuracy. Then, a deep neural network-based three-zone classification model for spontaneous combustion is applied, incorporating an attention mechanism and formula... Different features are assigned different weights to highlight their impact on the classification of the three spontaneous combustion zones. Let be the attention weight for the i-th feature. This is the attention weight matrix. This is the i-th feature vector; simultaneously, based on the data change trend, it is determined using the formula... The weighted rate of change of each gas concentration is calculated to determine the spontaneous combustion risk level, whereby... This represents the weighted rate of change in gas concentration. Let i be the weight of the i-th gas. and Let be the concentrations of the i-th gas at adjacent time points. For time intervals; The liquid carbon dioxide injection control module determines the location, flow rate, and timing of liquid carbon dioxide injection based on the spontaneous combustion zone classification and risk level obtained from the data processing and analysis module. A flow regulating valve controls the flow rate of liquid carbon dioxide, equipped with self-learning and adaptive adjustment functions. A fuzzy neural network control algorithm is used to regulate the flow rate, dynamically adjusting the valve opening based on oxygen concentration, temperature, and carbon monoxide concentration. The relationship between the injection flow rate and these factors is expressed using formulas. Perform mapping, where Q is the injection flow rate. Let T be the oxygen concentration, CO be the carbon monoxide concentration, and the function f be obtained through neural network training. In the oxidation zone, the injection flow rate is dynamically adjusted according to the oxygen concentration and temperature to reduce the oxygen concentration and inhibit coal oxidation and spontaneous combustion. The injection time is determined based on the duration of spontaneous combustion risk and the injection effect evaluation model, which is based on the formula... An evaluation was conducted, where E represents the evaluation value for the injection effect. These are the weighting coefficients. These represent the changes in oxygen concentration, temperature, and carbon monoxide concentration before and after injection.

2. The dynamic monitoring and liquid carbon dioxide injection control system for spontaneous combustion zones in coal mine goafs according to claim 1, characterized in that, Also includes: Remote monitoring and early warning module: Establish a remote monitoring center based on cloud computing and big data analysis, and connect it to the data processing and analysis module through a 5G network to display the temperature, gas concentration, spontaneous combustion zone division, and liquid carbon dioxide injection status information of the goaf in real time; set early warning thresholds for different levels, and when the data exceeds the early warning thresholds of different levels, the system will automatically issue different types of audible and visual alarm signals and notify relevant personnel through SMS, email, and APP push. Sensor Fault Diagnosis and Compensation Submodule: This module monitors the sensor's operating status in real time, and determines whether a sensor fault has occurred through feature analysis and anomaly detection algorithms. If a sensor fault occurs, it performs data compensation based on historical data and data from adjacent normal sensors, using a spatiotemporal correlation-based data compensation algorithm. The algorithm is expressed using formulas... The continuity of data is achieved by combining the spatiotemporal correlation coefficient to determine the weights. For the compensated data, Let j be the weight of the j-th adjacent sensor. This represents the data from the j-th adjacent sensor.

3. The dynamic monitoring and liquid carbon dioxide injection control system for spontaneous combustion zones in coal mine goafs according to claim 1, characterized in that, Also includes: Liquid carbon dioxide storage and supply optimization module: This module monitors the liquid level, pressure, and temperature parameters of the liquid carbon dioxide storage tank in real time, and calculates the state of the liquid carbon dioxide inside the tank using a thermodynamic model. The thermodynamic model considers the material properties of the storage tank, changes in ambient temperature, and the phase change process of carbon dioxide, using formulas... Predict pressure changes within a storage tank, where P is pressure, n is the amount of substance, R is the gas constant, T is temperature, and V is volume. The environmental temperature influence coefficient. The ambient temperature is considered. Based on the demand forecast of the liquid carbon dioxide control module, an optimization strategy based on a genetic algorithm is adopted, combining supply cost, transportation distance, and storage capacity factors to optimize the storage and supply strategy of liquid carbon dioxide, arranging its replenishment and distribution. Simultaneously, safety valves and pressure regulating devices are installed to ensure the safety of the storage tank. The safety valve automatically adjusts its opening pressure according to pressure changes within the storage tank, using a formula... Dynamic adjustments are made, among which To activate stress, The base opening pressure is given by β, where β is the pressure adjustment coefficient. This represents the change in pressure.

4. The dynamic monitoring and liquid carbon dioxide injection control system for spontaneous combustion zones in coal mine goafs according to claim 1, characterized in that, The sensors in the sensor data acquisition module adopt a modular design, which facilitates installation, maintenance and replacement. The installation position of the sensors is optimized and determined through three-dimensional geological modeling and numerical simulation technology. Based on the geological conditions, ventilation conditions and spontaneous combustion characteristics of coal in the goaf, the monitoring effect of the sensors under different installation positions is simulated, the optimal installation scheme is selected, and the data reflecting the spontaneous combustion state of the goaf is accurately collected. The sensor data acquisition module integrates a semiconductor carbon monoxide sensor with a noise reduction algorithm. Remove interference signals, among which This is the filtered signal. The original signal is represented by α, which is the noise reduction coefficient. For the i-th noise sample, carbon monoxide concentration data is collected in real time.

5. The dynamic monitoring and liquid carbon dioxide injection control system for spontaneous combustion zones in coal mine goafs according to claim 1, characterized in that, The deep neural network three-zone classification model for spontaneous combustion in the data processing and analysis module adopts transfer learning and incremental learning techniques. At the same time, the model uses model fusion technology to fuse neural network models with different structures and obtain the final classification result through weighted averaging, thereby improving the accuracy of spontaneous combustion three-zone classification.

6. The dynamic monitoring and liquid carbon dioxide injection control system for spontaneous combustion zones in coal mine goafs according to claim 2, characterized in that, The flow regulating valve in the liquid carbon dioxide injection control module adopts piezoelectric drive technology, and the control algorithm of the regulating valve adopts a model predictive control method. By establishing a dynamic model of the injection process, the injection effect in the future time is predicted, and the opening of the regulating valve is adjusted in real time according to the prediction results. At the same time, the module is also equipped with a flow feedback regulation function. The flow sensor installed on the injection pipeline monitors the injection flow rate in real time and compares it with the set flow rate, and the error is corrected by the PID control algorithm.

7. The dynamic monitoring and liquid carbon dioxide injection control system for spontaneous combustion zones in coal mine goafs according to claim 2, characterized in that, The remote monitoring and early warning module is equipped with decision support functions. It integrates and correlates geological information, mining technology, and safety regulations of coal mine goaf areas through knowledge graph technology. When abnormal monitoring data occurs, the system performs reasoning and analysis based on the knowledge graph to provide decision suggestions to relevant personnel. At the same time, the module is also equipped with a visual interactive function, allowing users to interact with the virtual simulation model through touch screens and mice to adjust operating parameters in real time.

8. The dynamic monitoring and liquid carbon dioxide injection control system for spontaneous combustion zones in coal mine goafs according to claim 2, characterized in that, The feature analysis and anomaly detection algorithms in the sensor fault diagnosis and compensation module adopt a distributed computing architecture, which distributes data processing tasks to computing nodes for parallel processing. At the same time, the module is also equipped with a fault prediction function. By analyzing the historical fault data and current working status data of the sensor, a time series analysis algorithm is used to predict the time and type of sensor failure and perform maintenance and replacement in advance.

9. The dynamic monitoring and liquid carbon dioxide injection control system for spontaneous combustion zones in coal mine goafs according to claim 3, characterized in that, The optimization strategy based on genetic algorithm in the liquid carbon dioxide storage and supply optimization module adopts an adaptive genetic operator, which dynamically adjusts the crossover probability and mutation probability according to the fitness value during the optimization process, thereby improving the search efficiency and convergence speed of the algorithm. At the same time, the module also considers the quality change factors of liquid carbon dioxide, and adjusts the supply strategy according to the detection results by periodically detecting the purity and impurity content of liquid carbon dioxide.

10. The dynamic monitoring and liquid carbon dioxide injection control system for spontaneous combustion zones in coal mine goafs according to claim 1, characterized in that, It also includes an interface module for integration with existing safety monitoring and automation control systems in coal mines; the interface module adopts standardized data communication protocols and interface specifications to realize data transmission and real-time sharing; through data fusion, this system utilizes the resources and data of existing coal mine systems, while feeding back the monitoring data and control information of this system to the existing systems, thereby realizing integrated management of coal mine safety monitoring and control.

Images