A coal mine fire prevention early warning method based on intelligent monitoring

Abstract

The application discloses a coal mine fire prevention early warning method based on intelligent monitoring, and relates to the technical field of coal mine fire prevention early warning, and comprises the following steps: acquiring coal mine environment information data parameters in real time through a coal mine fire prevention early warning system, wherein the environment information data parameters comprise humidity dynamic parameter information and air pressure parameter information. The application intelligently evaluates the environment through the generated environment safety change index; when judging that the environment is high-risk, the system dynamically adjusts the sampling frequency based on a preset sampling frequency, timely captures subtle changes in the early stage of fire such as methane diffusion or air static pressure fluctuation, ensures rapid early warning, improves the accuracy and timeliness of signal capture, and strives for early intervention time for managers. In a low-risk environment, the system collects data at a fixed sampling frequency, reduces unnecessary calculation tasks and energy consumption, supports long-term monitoring and trend analysis. Through the double regulation mechanism, the system guarantees data integrity, optimizes resource utilization and operation efficiency.

Description

Technical Field

[0001] This invention relates to the field of coal mine fire prevention and early warning technology, and specifically to a coal mine fire prevention and early warning method based on intelligent monitoring. Background Technology

[0002] Intelligent monitoring-based coal mine fire prevention and early warning is a systematic solution that utilizes modern information technology to monitor the coal mine environment in real time to prevent and reduce fire risks. It employs technologies such as sensor networks, the Internet of Things (IoT), big data, and artificial intelligence to monitor parameters such as temperature, gas concentrations (e.g., carbon monoxide, methane), and ventilation status in the mine around the clock. The system automatically analyzes the monitoring data, identifies potential fire risks, such as abnormal temperature increases or excessive levels of harmful gases, and issues early warnings of possible fires through predictive models and algorithms.

[0003] The core value of this system lies in improving the speed and predictability of fire prevention in coal mines, and reducing oversights caused by human inspections. The early warning system can push real-time alarm information to mine managers and relevant departments based on different risk levels, and provide corresponding emergency response suggestions. By identifying risks in advance and taking measures to prevent fire accidents, it not only protects the lives of coal miners but also reduces losses of equipment and mineral resources. Simultaneously, this intelligent monitoring system can analyze historical data, summarize patterns in fire occurrence, and thereby optimize mine fire prevention measures and management plans, promoting the continuous improvement of coal mine safety production.

[0004] The existing technology has the following shortcomings:

[0005] Existing coal mine fire early warning systems typically collect environmental data at fixed frequencies, which is effective under normal circumstances, but has limitations in capturing early signs of fires. Fixed-frequency data collection cannot respond promptly to minute changes within a short period, while temperature and gas concentrations (such as carbon monoxide and methane) can fluctuate drastically in the early stages of a fire. If the system fails to acquire this critical data in a timely manner, mine managers will be unable to quickly perceive the risk, missing the golden time for early fire intervention. Once the fire gets out of control, a small fire source can quickly evolve into an uncontrollable blaze, leading to a deterioration of the mine environment, paralysis of the smoke extraction system, significantly increasing the difficulty of firefighting and the risk of personnel being trapped, making evacuation and rescue operations more complex and challenging.

[0006] The information disclosed in the background section is only intended to enhance the understanding of the background of this disclosure, and therefore may include information that does not constitute prior art known to those skilled in the art. Summary of the Invention

[0007] The purpose of this invention is to provide a coal mine fire prevention and early warning method based on intelligent monitoring to solve the problems mentioned in the background art.

[0008] To achieve the above objectives, the system intelligently assesses the environment using a generated environmental safety change index. When a high-risk environment is identified, the system dynamically adjusts the sampling frequency based on a preset frequency to promptly capture subtle changes in the early stages of a fire, such as methane diffusion or fluctuations in atmospheric static pressure, ensuring rapid early warning and improving the accuracy and timeliness of signal capture, thus providing managers with early intervention time. In low-risk environments, the system collects data at a fixed sampling frequency, reducing unnecessary computational tasks and energy consumption, and supporting long-term monitoring and trend analysis. Through this dual control mechanism, the system ensures data integrity while optimizing resource utilization and operational efficiency. This invention provides the following technical solution: a coal mine fire prevention and early warning method based on intelligent monitoring, comprising the following steps:

[0009] The coal mine fire prevention and early warning system acquires real-time environmental information data parameters of the coal mine, including dynamic humidity parameters and air pressure parameters.

[0010] Anomaly analysis is performed on the collected humidity dynamic parameters and air pressure parameters. The anomaly-analyzed humidity dynamic parameters and air pressure parameters are then input into a pre-learned machine learning model. The machine learning model generates an environmental safety change index, which is then used to intelligently evaluate the coal mine environmental information data parameters acquired in real time by the coal mine fire prevention and early warning system.

[0011] Based on the evaluation results of the machine learning model, the coal mine environmental information data parameters acquired in real time by the coal mine fire prevention and early warning system are divided into low-risk environmental information or high-risk environmental information, and the coal mine environmental information data parameters acquired in real time by the coal mine fire prevention and early warning system are intelligently perceived.

[0012] Once an environment is identified as low-risk, sampling is continuously performed at a preset environmental sampling frequency. Once an environment is identified as high-risk, the sampling frequency is dynamically adjusted based on the preset environmental sampling frequency to promptly capture subtle differences in environmental changes.

[0013] Preferably, the humidity dynamic parameter information includes changes in the methane gas diffusion rate, and the air pressure parameter information includes fluctuations in air static pressure. The changes in the methane gas diffusion rate refer to the dynamic changes in the diffusion rate of methane gas in different areas of the mine over time. The fluctuations in air static pressure refer to the drastic changes in the static pressure of the air in the mine over a short period of time, which reflects the stability of the mine ventilation system and the balance of gas flow.

[0014] Preferably, after performing anomaly analysis on local humidity fluctuations, a local humidity instantaneous fluctuation index is generated; after performing anomaly analysis on air static pressure fluctuations, an air static pressure fluctuation anomaly index is generated; the local humidity instantaneous fluctuation index and air static pressure fluctuation anomaly index generated after anomaly analysis are input into a pre-learned machine learning model to generate an environmental safety change index; and the environmental safety change index is used to intelligently evaluate the coal mine environmental information data parameters obtained in real time by the coal mine fire prevention and early warning system.

[0015] Preferably, the logic for generating a local humidity instantaneous fluctuation index through anomaly analysis of local humidity fluctuations is as follows:

[0016] Within the detection window, local humidity data is collected, and the collected local humidity data is calibrated as H(t). i ), H(t) i ) indicates at time t i The local humidity value obtained from the i-th sampling at time t i ={t1, t2, t3, ..., t n}, where n represents the total number of samples;

[0017] For every two consecutive sampling times, the instantaneous humidity change rate is calculated using the following expression:

[0018]

[0019] In the formula, ΔH(t) i () is the instantaneous rate of change of humidity at time point t. i The instantaneous humidity value at time t, i.e., the instantaneous humidity recorded at the i-th sampling point, H(t) i-1 ) is at the previous time point t i-1 The instantaneous humidity value is used to calculate the change in humidity, and Δt is the time interval between two samplings;

[0020] Based on the instantaneous humidity change rate, the acceleration of humidity fluctuations is further calculated to capture the severity of humidity changes. The calculation expression is as follows:

[0021]

[0022] In the formula, ΔA H (t i ) indicates at time t i The acceleration of humidity fluctuations over time, ΔH(t) i-1 ) is at the previous time point t i-1 The instantaneous rate of change of humidity;

[0023] A dynamic sensitivity function is introduced to capture significant fluctuations in humidity over a short period of time, while amplifying instantaneous and drastic changes. The calculation expression is as follows:

[0024]

[0025] In the formula, S(t) i ) represents time point t i The dynamic sensitivity value at any given time, where λ is the sensitivity adjustment parameter and θ is the threshold for humidity fluctuation;

[0026] Then, the instantaneous anomaly coefficient is calculated, and the calculation expression is as follows:

[0027] E H (t i ) = A H (t i )·S(t i )

[0028] In the formula, E H (t i ) represents time point t i The instantaneous anomaly coefficient at any given moment;

[0029] The absolute values ​​of all instantaneous anomaly coefficients are accumulated to generate a local humidity instantaneous fluctuation index, calculated as follows:

[0030]

[0031] In the formula, I H It is the local humidity instantaneous fluctuation index.

[0032] Preferably, the logic for performing anomaly analysis on air static pressure fluctuations and generating an air static pressure fluctuation anomaly index is as follows:

[0033] Under the detection window, the air static pressure data of the mine is decomposed and the time series data is divided into multiple small windows. The length of each sliding window is W, and the expression is as follows: {P(t)|t∈[t0,t0+W]), where P(t) is the air static pressure value at time point t, t0 is the start time of the sliding window, and t0+W is the end time of the sliding window;

[0034] Within each sliding window, the change in static air pressure between consecutive time points is calculated using a differential operation; that is, the instantaneous fluctuation amplitude of the static air pressure. The calculation expression is as follows:

[0035] ΔP(t)=|P(t+Δt)-P(t)|

[0036] In the formula, ΔP(t) is the change in air static pressure at time t, and Δt is the time interval between two samplings;

[0037] Further nonlinear analysis was performed on the detected change in air static pressure ΔP(t) to calculate the rate of change, and the calculation expression is as follows:

[0038]

[0039] In the formula, R(t) is the nonlinear rate of change of the static air pressure at time t, α and β are both smoothing coefficients, and γ is a nonlinear adjustment coefficient.

[0040] To quantify the overall intensity of hydrostatic fluctuations, the nonlinear rate of change R(t) at each time point is integrated to generate the cumulative fluctuation energy, as shown in the following expression:

[0041]

[0042] In the formula, E W Accumulated fluctuation energy;

[0043] Accumulated fluctuation energy E W The input is fed into a nonlinear mapping function to generate the final air static pressure fluctuation anomaly index, calculated as follows:

[0044]

[0045] In the formula, I P It is an abnormal index of air static pressure fluctuation. τ is the amplification factor used to adjust the exponential range, τ is the energy threshold, and tanh(·) is the hyperbolic tangent function that maps the energy value to the 0-1 range.

[0046] Preferably, the local humidity instantaneous fluctuation index I H and the abnormal index of air static pressure fluctuation I P The data is input into a pre-learned machine learning model, which generates the Environmental Safety Change Index (ESCI) based on the following formula:

[0047]

[0048] In the formula, f1 and f2 are the local humidity instantaneous fluctuation indices I. H and the abnormal index of air static pressure fluctuation I P The preset proportional coefficients, and both f1 and f2 are greater than 0.

[0049] Preferably, the generated environmental safety change index is compared and analyzed with a pre-set environmental safety change index reference threshold. The analysis results are as follows:

[0050] If the environmental safety change index is greater than or equal to the preset environmental safety change index reference threshold, the coal mine environmental information data parameters obtained in real time by the coal mine fire prevention and early warning system will be classified as high-risk environmental information.

[0051] If the environmental safety change index is less than the preset reference threshold for the environmental safety change index, the coal mine environmental information data parameters obtained in real time by the coal mine fire prevention and early warning system will be classified as low-risk environmental information.

[0052] The technical effects and advantages provided by the present invention in the above technical solution are as follows:

[0053] This invention provides an intelligent assessment of the environment through a generated environmental safety change index. When the system determines that an environment is at high risk, it can dynamically adjust the sampling frequency based on a preset frequency to quickly respond to and capture subtle changes in the early stages of a fire. For example, in the early stages of a fire, dramatic fluctuations in methane gas diffusion rate or atmospheric static pressure may be extremely brief, and traditional fixed sampling frequencies cannot respond to these rapid fluctuations in time. Through this dynamic adjustment mechanism, the system can increase the sampling frequency, acquire key data more quickly, and ensure timely warnings when risks escalate. This significantly improves the accuracy and timeliness of capturing early fire signals, thus providing mine managers with ample time for early intervention.

[0054] This invention addresses situations where environmental information is deemed low-risk. The system collects data at a preset fixed sampling frequency without performing additional computational tasks. This design effectively saves system computing resources and energy consumption because, in stable environments with no significant risk, the fixed sampling frequency meets data collection needs without the need for dynamic frequency adjustments to prevent oversampling. This not only facilitates long-term monitoring of stable environments and ensures continuous basic data collection but also supports subsequent trend analysis and baseline establishment. This intelligent control mechanism allows the system to maximize resource utilization while ensuring safety, avoiding unnecessary resource waste. This dual control approach—maintaining a fixed frequency during low-risk periods and flexibly adjusting during high-risk periods—ensures data integrity while improving system efficiency and sustainability. Attached Figure Description

[0055] To more clearly illustrate the technical solutions in the embodiments of this application or the prior art, the drawings used in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments recorded in this invention. For those skilled in the art, other drawings can be obtained based on these drawings.

[0056] Figure 1 This is a flowchart of a coal mine fire prevention and early warning method based on intelligent monitoring according to the present invention. Detailed Implementation

[0057] Exemplary embodiments will now be described more fully with reference to the accompanying drawings. However, these exemplary embodiments can be implemented in many forms and should not be construed as limited to the examples set forth herein; rather, they are provided so that the description of this disclosure will be more complete and fully convey the concept of the exemplary embodiments to those skilled in the art.

[0058] This invention provides, for example Figure 1 The method for early warning of coal mine fires based on intelligent monitoring, as shown, includes the following steps:

[0059] The coal mine fire prevention and early warning system acquires real-time environmental information data parameters of the coal mine, including dynamic humidity parameters and air pressure parameters.

[0060] The humidity dynamic parameter information includes local humidity fluctuations, and the air pressure parameter information includes air static pressure fluctuations. Local humidity fluctuations refer to the rapid increase or decrease of humidity in a specific area of ​​the mine in a short period of time, rather than a steady or slow change. Air static pressure fluctuations refer to the drastic changes in the static pressure of the air in the mine in a short period of time, which reflects the stability of the mine ventilation system and the balance of gas flow.

[0061] Anomaly analysis is performed on the collected humidity dynamic parameters and air pressure parameters. The anomaly-analyzed humidity dynamic parameters and air pressure parameters are then input into a pre-learned machine learning model. The machine learning model generates an environmental safety change index, which is then used to intelligently evaluate the coal mine environmental information data parameters acquired in real time by the coal mine fire prevention and early warning system.

[0062] After performing anomaly analysis on local humidity fluctuations, a local humidity instantaneous fluctuation index is generated. After performing anomaly analysis on air static pressure fluctuations, an air static pressure fluctuation anomaly index is generated. The local humidity instantaneous fluctuation index and air static pressure fluctuation anomaly index generated after anomaly analysis are input into a pre-learned machine learning model. The machine learning model generates an environmental safety change index. The environmental safety change index is used to intelligently evaluate the coal mine environmental information data parameters obtained in real time by the coal mine fire prevention and early warning system.

[0063] Localized humidity fluctuations in coal mine environments can be a crucial early warning sign of a fire. During spontaneous combustion or initial combustion phases in coal mines, rising temperatures cause rapid evaporation of moisture from surrounding materials, releasing water vapor and resulting in abnormal fluctuations in localized humidity over short periods. Poor ventilation or gas accumulation can also lead to humidity changes. Therefore, monitoring instantaneous humidity fluctuations can detect potential risks of fire or ventilation system malfunctions in advance. However, monitoring methods with fixed sampling frequencies may miss these minute changes over short periods. Humidity fluctuations often occur instantaneously; if the system collects data at fixed time intervals (e.g., every 10 minutes), it may fail to capture critical changes occurring within the sampling interval. For example, if humidity rises or falls rapidly within seconds, but the system's sampling period is long, these important warning signals will be ignored, leading to the failure to detect and address the initial risks of a fire in a timely manner. Once the fire escalates, the difficulty of extinguishing it and the risk of personnel evacuation both increase significantly.

[0064] The logic for generating a local humidity instantaneous fluctuation index through anomaly analysis of local humidity fluctuations is as follows:

[0065] Within the detection window, local humidity data is collected, and the collected local humidity data is calibrated as H(t). i ), H(t) i ) indicates at time t i The local humidity value obtained from the i-th sampling at time t i ={t1, t2, t3, ..., t n}, where n represents the total number of samples;

[0066] The collected local humidity data typically includes the following key indicators. This data helps to comprehensively understand the humidity conditions in different areas of the coal mine, so as to monitor early signs of fire or abnormal ventilation in a timely manner:

[0067] 1. Instantaneous humidity value

[0068] This is a humidity value collected at a specific moment, representing the humidity level of the environment at a particular point in time. This is the most basic humidity data, typically collected in real time by sensors.

[0069] 2. Humidity change rate

[0070] Calculating the humidity change at two consecutive sampling times helps determine whether the humidity is steadily rising, falling, or experiencing sudden fluctuations. This is crucial for detecting subtle changes in the early stages of a fire.

[0071] 3. Humidity fluctuation range

[0072] This indicates the range of humidity fluctuations within a specific time period. By comparing the highest and lowest humidity values ​​over a period of time, it's possible to understand whether the humidity has experienced drastic fluctuations, especially changes within a short period.

[0073] 4. Differences in local humidity distribution

[0074] Humidity distribution at different locations, especially the uniformity of humidity at different depths and in different areas within the mine, can help identify poor ventilation or localized anomalies.

[0075] 5. Time series trend of humidity

[0076] The trend of humidity values ​​over a period of time is often used to predict the future direction of humidity changes. A continuous upward or downward trend may indicate environmental changes or be a precursor to a fire.

[0077] 6. Humidity gradient

[0078] This refers to the humidity differences between different areas. Humidity gradients can indicate whether humidity is evenly distributed in a mine, especially in poorly ventilated areas where higher humidity gradients may be observed, indicating potential risks.

[0079] Local humidity data includes multiple indicators such as instantaneous humidity values, humidity change rate, fluctuation amplitude, humidity distribution differences, time trends, and humidity gradients. This data not only provides current environmental humidity information but also helps to provide early warnings of potential hazards such as fires or ventilation failures by analyzing dynamic humidity changes.

[0080] For every two consecutive sampling times, the instantaneous humidity change rate is calculated using the following expression:

[0081]

[0082] In the formula, ΔH(t) i () is the instantaneous rate of change of humidity at time point t. i The instantaneous humidity value at time t, i.e., the instantaneous humidity recorded at the i-th sampling point, H(t) i-1 ) is at the previous time point t i-1 The instantaneous humidity value, i.e., the result of the (i-1)th sampling, H(t) i-1 ) and H(t i ) represents data from two consecutive samples used to calculate the change in humidity, and Δt is the time interval between the two samples, that is, the time elapsed from the (i-1)th sample to the ith sample.

[0083] Based on the instantaneous humidity change rate, the acceleration of humidity fluctuations is further calculated to capture the severity of humidity changes. The calculation expression is as follows:

[0084]

[0085] In the formula, ΔA H (t i ) indicates at time t i The acceleration of humidity fluctuations over time, ΔH(t) i-1 ) is at the previous time point t i-1 The instantaneous rate of change of humidity;

[0086] A dynamic sensitivity function is introduced to capture significant fluctuations in humidity over a short period of time, while amplifying instantaneous and drastic changes. The calculation expression is as follows:

[0087]

[0088] In the formula, S(t) i ) represents time point t i The dynamic sensitivity value at any given time, λ is the sensitivity adjustment parameter used to control the steepness of the curve, and θ is the threshold for humidity fluctuations used to determine whether an abnormal level has been reached;

[0089] Significant fluctuations in humidity acceleration refer to drastic changes in humidity over a short period. These changes not only reflect the rate of change in humidity levels but also reveal abnormal dynamics in the environment. Below are some common types of significant humidity acceleration fluctuations and their potential implications:

[0090] 1. Humidity rises rapidly.

[0091] Phenomenon: Humidity increases rapidly in a short period of time, and the rate of increase accelerates (the rate of change continues to increase).

[0092] Possible reasons:

[0093] Early stage of spontaneous combustion of coal seam: The spontaneous combustion process releases water vapor, causing the humidity to rise rapidly in local areas.

[0094] Equipment or pipeline rupture: Moisture suddenly leaks into a specific area of ​​the mine.

[0095] Obstructed ventilation: This causes humidity to accumulate in certain areas and cannot be expelled.

[0096] risk:

[0097] A rapid increase in humidity within a short period of time may be an early sign of spontaneous combustion; timely detection can help prevent fires in advance.

[0098] Poor ventilation can lead to humidity buildup, increasing the risk of other parameters (such as methane concentration) exceeding the standard.

[0099] 2. Humidity decreases rapidly.

[0100] Phenomenon: The humidity level drops rapidly in a short period of time, and the rate of decline continues to accelerate.

[0101] Possible reasons:

[0102] A sudden strong wind entered: The ventilation system was malfunctioning, causing the humidity to be rapidly expelled.

[0103] A rapid rise in temperature: such as in the early stages of a fire or when equipment overheats, causing moisture in the air to evaporate and the air to become dry.

[0104] Excessive fan operation: Abnormal operation of the exhaust system, excessive dehumidification, resulting in humidity imbalance.

[0105] risk:

[0106] A sharp drop in humidity can dry out the environment, increasing the risk of spontaneous combustion of flammable materials.

[0107] Abnormalities in the ventilation system can cause air pressure imbalances, resulting in uneven gas concentration distribution and exacerbating fire hazards.

[0108] 3. Humidity fluctuates frequently and with increased amplitude (accelerated oscillations).

[0109] Phenomenon: Humidity fluctuates frequently and rapidly within a short period of time, meaning that humidity fluctuations in different directions are increasing.

[0110] Possible reasons:

[0111] Unstable ventilation systems: such as ventilation equipment that frequently starts and stops, leading to unstable humidity.

[0112] Multi-source moisture interference: If there are multiple sources of humidity at the same time (such as pipe leaks and spontaneous combustion), humidity fluctuations will occur.

[0113] Frequent changes in airflow direction: The ventilation path is constantly changing, which makes it impossible for moisture to diffuse stably.

[0114] risk:

[0115] Humidity oscillations may cause abnormal sensor data, increasing the probability of false alarms or missed alarms.

[0116] Drastic fluctuations in humidity can mask other potential early signs of fire, affecting the system's early warning effectiveness.

[0117] 4. Humidity changes accelerate synchronously with other parameters.

[0118] Phenomenon: Humidity fluctuates rapidly and changes synchronously with parameters such as temperature and gas concentration (e.g., methane, carbon monoxide).

[0119] Possible reasons:

[0120] The spontaneous combustion process of coal seams: humidity, temperature and gas concentration may change drastically at the same time in the early stages of a fire.

[0121] Overall failure of the ventilation system: This causes humidity and gas concentration to rise or fall simultaneously.

[0122] risk:

[0123] The simultaneous and accelerated changes in multiple parameters indicate a possible early stage of fire or a serious malfunction in the ventilation system, requiring urgent investigation.

[0124] Significant fluctuations in humidity acceleration include accelerated increases and decreases in humidity, frequent oscillations, and synchronous changes with other parameters. These fluctuations not only reflect drastic changes in humidity itself but may also reveal potential fires, ventilation anomalies, or equipment malfunctions within coal mines. By accurately capturing these significant fluctuations in humidity acceleration, fire early warning systems can identify risks in advance and prevent accidents from occurring.

[0125] Then, the instantaneous anomaly coefficient is calculated, and the calculation expression is as follows:

[0126] E H (t i ) = A H (t i )·S(t i )

[0127] In the formula, E H (t i ) represents time point t i The instantaneous anomaly coefficient at any given moment;

[0128] Instantaneous anomaly coefficient E H (t i The purpose of this coefficient is to quantitatively assess the degree of drastic fluctuation in humidity at a specific moment, and to amplify humidity fluctuation signals that may indicate environmental anomalies by combining the results of the humidity change rate and sensitivity function. It can capture sudden anomalies in humidity changes, such as water vapor released in the early stages of a fire or sudden humidity changes caused by ventilation system failure. This coefficient not only reflects the significance of current humidity fluctuations but also filters out anomalies that are crucial to mine safety through real-time analysis. Its main value lies in avoiding missed detections caused by fixed-frequency sampling, improving the system's response speed to fire precursors and ventilation failures, and providing timely warnings to management personnel. In other words, the instantaneous anomaly coefficient amplifies potential risk signals in the environment that are not easily detected, enabling the system to quickly detect anomalies in minute changes and prevent problems before they occur.

[0129] The absolute values ​​of all instantaneous anomaly coefficients are accumulated to generate a local humidity instantaneous fluctuation index, calculated as follows:

[0130]

[0131] In the formula, I H It is an index of instantaneous fluctuations in local humidity;

[0132] As shown in the expression for the local humidity instantaneous fluctuation index, a larger index value indicates a more drastic fluctuation in humidity within a short period. This suggests the presence of unstable factors in the mine environment, such as poor ventilation or moisture release before spontaneous combustion of coal seams. In such cases, a fixed sampling frequency early warning system is more likely to miss these rapid and transient changes, increasing the probability of the system failing to respond promptly. A larger index value also increases the risk of missed detections, as crucial information within the sampling interval may not be captured. Conversely, a smaller index value indicates a more stable humidity level, making fixed-frequency sampling more reliable and reducing the probability of missed detections.

[0133] In coal mine environments, fluctuations in static pressure can indeed be a crucial early warning sign of a fire. When localized combustion or spontaneous combustion occurs in the coal seam, the rising air temperature causes air expansion, leading to dramatic fluctuations in static pressure within a short period. Furthermore, gas release, ventilation system malfunctions, or airflow turbulence can also alter static pressure, and these phenomena are often closely related to early signs of a fire. However, if fire warning systems use a fixed sampling frequency, they may miss these instantaneous pressure fluctuation signals. This is because fixed-frequency sampling can only acquire data within specific intervals and cannot continuously capture rapid and transient anomalies. In the early stages of a fire, static pressure fluctuations and other environmental parameters such as temperature or hazardous gas concentrations often change drastically within seconds. If the system happens to fail to sample during this period, the risk signals will be ignored. This will prevent mine managers from promptly detecting early signs of a fire, missing the golden time for emergency intervention, and increasing the likelihood of the fire worsening.

[0134] The logic for generating an anomaly index for air static pressure fluctuations through anomaly analysis is as follows:

[0135] Under the detection window, the air static pressure data of the mine is decomposed, and the time series data is divided into multiple small windows. Each sliding window has a length of W and is used to capture short-term fluctuations. The expression is as follows: {P(t)|t∈[t0,t0+W]}, where P(t) is the air static pressure value at time t, t0 is the start time of the sliding window, and t0+W is the end time of the sliding window.

[0136] Within each sliding window, the change in static air pressure between consecutive time points is calculated using a differential operation; that is, the instantaneous fluctuation amplitude of the static air pressure. The calculation expression is as follows:

[0137] ΔP(t) = |P(t+Δt) - P(t)|

[0138] In the formula, ΔP(t) is the change in air static pressure at time t, and Δt is the time interval between two samplings;

[0139] Calculating the change in static air pressure over consecutive time points is crucial for capturing instantaneous fluctuations in air pressure within a mine. This is a vital signal for identifying ventilation system anomalies, early signs of fire, or gas leaks. During a fire or spontaneous combustion, localized air expansion or gas release causes drastic changes in static air pressure within a short period. If the system can detect these pressure changes promptly, it can issue warnings before the fire or explosion risk escalates, preventing the disaster from spreading. Conversely, if pressure fluctuations are not captured, danger signals will be ignored, potentially causing management to miss critical emergency intervention time. Therefore, the change in static pressure over consecutive time points reflects the dynamic state of airflow in the mine, providing crucial information for fire prevention and early warning.

[0140] Further nonlinear analysis was performed on the detected change in air static pressure ΔP(t) to calculate the rate of change, and the calculation expression is as follows:

[0141]

[0142] In the formula, R(t) is the nonlinear rate of change of air static pressure at time t, α and β are both smoothing coefficients. α is mainly used to avoid division by zero error or extreme results when the change in air static pressure |ΔP(t)| is close to 0. β is mainly used to adjust the intensity response of the fluctuation of the change in air static pressure, especially to control the growth rate of the result when the nonlinear change is large. γ is a nonlinear adjustment coefficient used to control the sensitivity to drastic changes.

[0143] To quantify the overall intensity of hydrostatic fluctuations, the nonlinear rate of change R(t) at each time point is integrated to generate the cumulative fluctuation energy, as shown in the following expression:

[0144]

[0145] In the formula, E W Accumulated fluctuation energy;

[0146] Accumulated fluctuation energy E W The input is fed into a nonlinear mapping function to generate the final air static pressure fluctuation anomaly index, calculated as follows:

[0147]

[0148] In the formula, I P It is an abnormal index of air static pressure fluctuation. τ is the amplification factor used to adjust the exponential range, τ is the energy threshold used to control the system's sensitivity to abnormal fluctuations, and tanh(·) is the hyperbolic tangent function that maps the energy value to the 0-1 range.

[0149] The main purpose of mapping accumulated energy values ​​to the 0-1 range is to standardize and unify the processing of fluctuating energy at different scales, making the early warning system more flexible and easier to understand. In coal mine environments, different detection windows may accumulate fluctuating energy of different magnitudes; for example, the energy generated by small fluctuations in static pressure and severe ventilation anomalies can differ greatly. Using the hyperbolic tangent function to map these energy values ​​to the [0,1] range ensures that the outputs of all abnormal indicators are within the same standardized interval, helping managers to more intuitively assess the severity of risks and avoid excessively large or complex values ​​that could affect their judgment.

[0150] Furthermore, compressing the energy value to the 0-1 range enhances the system's ability to distinguish between minor anomalies and severe fluctuations. The hyperbolic tangent function is characterized by slow change at small values ​​and gradual saturation at larger values. This makes the system more tolerant of low-energy fluctuations and less prone to false alarms; while at larger energy values, the exponent rapidly approaches 1, clearly indicating a serious anomaly. In this way, the system can filter out minor fluctuations to avoid false alarms while simultaneously issuing rapid alerts for high-risk events, ensuring the accuracy and timeliness of warnings.

[0151] As shown in the formula for calculating the air static pressure fluctuation anomaly index, a larger index value indicates more drastic fluctuations in air static pressure within the detection window. This suggests potential sudden or instantaneous changes in the mine environment, such as ventilation system malfunctions, gas releases, or localized combustion. In such cases, monitoring with a fixed sampling frequency is prone to missing these crucial short-term changes, leading to delayed system response and fire warnings, and increasing the risk of missed reports. Therefore, a larger index value means a higher probability that fixed-frequency sampling will fail to capture instantaneous changes. Conversely, a smaller index value indicates relatively stable air static pressure fluctuations with fewer short-term changes. While fixed-frequency sampling still has limitations, the probability of missing critical signals is relatively low.

[0152] The local humidity instantaneous fluctuation index I H and the abnormal index of air static pressure fluctuation I P The data is input into a pre-learned machine learning model, which generates the Environmental Safety Change Index (ESCI) based on the following formula:

[0153]

[0154] In the formula, f1 and f2 are the local humidity instantaneous fluctuation indices I. H and the abnormal index of air static pressure fluctuation I P The preset proportional coefficients, and both f1 and f2 are greater than 0.

[0155] According to the calculation expression of the environmental safety change index, the larger the value of the instantaneous local humidity fluctuation index generated after anomaly analysis of local humidity fluctuation, and the larger the value of the abnormal air static pressure fluctuation index generated after anomaly analysis of air static pressure fluctuation, the larger the value of the environmental safety change index, indicating that the probability of sudden abnormality in the mine environment is greater. Conversely, it indicates that the mine environment is within a safe and controllable range.

[0156] Based on the evaluation results of the machine learning model, the coal mine environmental information data parameters acquired in real time by the coal mine fire prevention and early warning system are divided into low-risk environmental information or high-risk environmental information, and the coal mine environmental information data parameters acquired in real time by the coal mine fire prevention and early warning system are intelligently perceived.

[0157] The generated environmental safety change index was compared and analyzed with the pre-set environmental safety change index reference threshold. The analysis results are as follows:

[0158] If the environmental safety change index is greater than or equal to the preset environmental safety change index reference threshold, the coal mine environmental information data parameters obtained in real time by the coal mine fire prevention and early warning system will be classified as high-risk environmental information.

[0159] If the environmental safety change index is less than the preset reference threshold for the environmental safety change index, the coal mine environmental information data parameters obtained in real time by the coal mine fire prevention and early warning system will be classified as low-risk environmental information.

[0160] Once the environmental information is determined to be low-risk, it will continue to collect data at a preset environmental sampling frequency. Once the environmental information is determined to be high-risk, it will dynamically adjust the sampling frequency based on the preset environmental sampling frequency to capture subtle differences in environmental changes in a timely manner.

[0161] For information about low-risk environments, the system will collect data at a pre-set fixed sampling frequency. This means that the system will not increase the sampling frequency or perform additional data analysis operations in this case, thereby saving computing resources and energy consumption. The fixed sampling frequency is suitable for monitoring stable environments, ensuring the continuous collection of basic data, and providing support for long-term trend analysis and the establishment of baselines for normal conditions.

[0162] For environmental information identified as high-risk, the specific steps for dynamically adjusting the sampling frequency based on a preset environmental sampling frequency to promptly capture subtle differences in environmental changes are as follows:

[0163] Based on changes in environmental risk, the sampling frequency is dynamically adjusted using a nonlinear adjustment formula. The calculation expression for the sampling frequency adjustment is as follows:

[0164]

[0165] In the formula, Sampling Fr represents the adjusted sampling frequency, Sampling Fr0 represents the preset sampling frequency, k is an adjustment coefficient used to control the increase of the sampling frequency, and ESCI ref It is the reference threshold for the environmental safety change index, and π is the sensitivity coefficient, which is used to adjust the degree of response to environmental changes;

[0166] The adjusted sampling frequency Smapling Fr is applied to the data collection of the next time period, and environmental changes are continuously monitored to form a feedback loop. If the risk level continues to rise, the sampling frequency will be further increased; if the environment returns to stability, the sampling frequency will gradually decrease back to the preset level Sampling Fr0.

[0167] This invention provides an intelligent assessment of the environment through a generated environmental safety change index. When the system determines that an environment is at high risk, it can dynamically adjust the sampling frequency based on a preset frequency to quickly respond to and capture subtle changes in the early stages of a fire. For example, in the early stages of a fire, dramatic fluctuations in methane gas diffusion rate or atmospheric static pressure may be extremely brief, and traditional fixed sampling frequencies cannot respond to these rapid fluctuations in time. Through this dynamic adjustment mechanism, the system can increase the sampling frequency, acquire key data more quickly, and ensure timely warnings when risks escalate. This significantly improves the accuracy and timeliness of capturing early fire signals, thus providing mine managers with ample time for early intervention.

[0168] This invention addresses situations where environmental information is deemed low-risk. The system collects data at a preset fixed sampling frequency without performing additional computational tasks. This design effectively saves system computing resources and energy consumption because, in stable environments with no significant risk, the fixed sampling frequency meets data collection needs without the need for dynamic frequency adjustments to prevent oversampling. This not only facilitates long-term monitoring of stable environments and ensures continuous basic data collection but also supports subsequent trend analysis and baseline establishment. This intelligent control mechanism allows the system to maximize resource utilization while ensuring safety, avoiding unnecessary resource waste. This dual control approach—maintaining a fixed frequency during low-risk periods and flexibly adjusting during high-risk periods—ensures data integrity while improving system efficiency and sustainability.

[0169] The foregoing has only described certain exemplary embodiments of the present invention by way of illustration. Undoubtedly, those skilled in the art can modify the described embodiments in various ways without departing from the spirit and scope of the present invention. Therefore, the foregoing drawings and descriptions are illustrative in nature and should not be construed as limiting the scope of protection of the claims of the present invention.

Claims

1. A coal mine fire prevention and early warning method based on intelligent monitoring, characterized in that, Includes the following steps: The coal mine fire prevention and early warning system acquires real-time environmental information data parameters of the coal mine, including dynamic humidity parameters and air pressure parameters. Anomaly analysis is performed on the collected humidity dynamic parameters and air pressure parameters. The anomaly-analyzed humidity dynamic parameters and air pressure parameters are then input into a pre-learned machine learning model. The machine learning model generates an environmental safety change index, which is then used to intelligently evaluate the coal mine environmental information data parameters acquired in real time by the coal mine fire prevention and early warning system. Based on the evaluation results of the machine learning model, the coal mine environmental information data parameters acquired in real time by the coal mine fire prevention and early warning system are divided into low-risk environmental information or high-risk environmental information, and the coal mine environmental information data parameters acquired in real time by the coal mine fire prevention and early warning system are intelligently perceived. Once the environmental information is determined to be low-risk, it will continue to collect data at a preset environmental sampling frequency. Once the environmental information is determined to be high-risk, it will dynamically adjust the sampling frequency based on the preset environmental sampling frequency to capture subtle differences in environmental changes in a timely manner. The humidity dynamic parameter information includes changes in the methane gas diffusion rate, and the air pressure parameter information includes fluctuations in air static pressure. Changes in the methane gas diffusion rate refer to the dynamic changes in the diffusion rate of methane gas in different areas of the mine over time. Fluctuations in air static pressure refer to the drastic changes in the static pressure of the air in the mine over a short period of time, which reflects the stability of the mine ventilation system and the balance of gas flow. After performing anomaly analysis on local humidity fluctuations, a local humidity instantaneous fluctuation index is generated. After performing anomaly analysis on air static pressure fluctuations, an air static pressure fluctuation anomaly index is generated. The local humidity instantaneous fluctuation index and air static pressure fluctuation anomaly index generated after anomaly analysis are input into a pre-learned machine learning model. The machine learning model generates an environmental safety change index. The environmental safety change index is used to intelligently evaluate the coal mine environmental information data parameters obtained in real time by the coal mine fire prevention and early warning system. The logic for generating a local humidity instantaneous fluctuation index through anomaly analysis of local humidity fluctuations is as follows: Within the detection window, local humidity data is collected, and the collected local humidity data is calibrated as follows: , Indicates time The first moment The local humidity value obtained from the second sampling. ,in, Indicates the total number of samples; For every two consecutive sampling times, the instantaneous humidity change rate is calculated using the following expression: In the formula, It is the instantaneous humidity change rate at a given time point. The instantaneous humidity value at time t, i.e., the value at the t moment. The instantaneous humidity recorded at the time of the next sampling. At the previous point in time The instantaneous humidity value is used to calculate changes in humidity. It is the time interval between two samples; Based on the instantaneous humidity change rate, the acceleration of humidity fluctuations is further calculated to capture the severity of humidity changes. The calculation expression is as follows: In the formula, Indicates time The rate of change in humidity at any given time. At the previous point in time The instantaneous rate of change of humidity; A dynamic sensitivity function is introduced to capture significant fluctuations in humidity over a short period of time, while amplifying instantaneous and drastic changes. The calculation expression is as follows: In the formula, Indicates a point in time The dynamic sensitivity value at any given time. It is a sensitivity adjustment parameter. It is the threshold for humidity fluctuations; Then, the instantaneous anomaly coefficient is calculated, and the calculation expression is as follows: In the formula, Indicates a point in time The instantaneous anomaly coefficient at any given moment; The absolute values ​​of all instantaneous anomaly coefficients are accumulated to generate a local humidity instantaneous fluctuation index, calculated as follows: In the formula, It is the local humidity instantaneous fluctuation index.

2. The coal mine fire prevention and early warning method based on intelligent monitoring according to claim 1, characterized in that, The logic for generating an anomaly index for air static pressure fluctuations through anomaly analysis is as follows: Within the detection window, the air static pressure data of the mine is decomposed, dividing the time series data into multiple small windows, each with a sliding window length of [length missing]. The expression is as follows: In the formula, It is a point in time. The static air pressure at a given time. It is the start time of the sliding window. It is the end time of the sliding window; Within each sliding window, the change in static air pressure between consecutive time points is calculated using a differential operation; that is, the instantaneous fluctuation amplitude of the static air pressure. The calculation expression is as follows: In the formula, It is a point in time. Change in static air pressure over time It is the time interval between two samples; Further analysis of the detected changes in air static pressure A nonlinear analysis is performed to calculate the rate of change, and the calculation expression is as follows: In the formula, It is a point in time. The nonlinear rate of change of air static pressure at any given time. , All are smoothing coefficients. It is a non-linear adjustment coefficient; To quantify the overall intensity of static pressure fluctuations, the nonlinear rate of change at each time point is... Integrating, we generate the cumulative fluctuation energy, calculated as follows: In the formula, Accumulated fluctuation energy; Accumulated fluctuation energy The input is fed into a nonlinear mapping function to generate the final air static pressure fluctuation anomaly index, calculated as follows: In the formula, It is an abnormal index of air static pressure fluctuation. It is the magnification factor, used to adjust the exponent range. It is the energy threshold. It is a hyperbolic tangent function that maps energy values ​​to the range of 0-1.

3. The coal mine fire prevention and early warning method based on intelligent monitoring according to claim 1, characterized in that: Local humidity instantaneous fluctuation index and air static pressure fluctuation anomaly index The data is input into a pre-learned machine learning model, which then generates an environmental safety change index. The formula used is: In the formula, , Local humidity instantaneous fluctuation index and air static pressure fluctuation anomaly index The preset proportional coefficient, and , All are greater than 0.

4. A coal mine fire prevention and early warning method based on intelligent monitoring according to claim 3, characterized in that: The generated environmental safety change index was compared and analyzed with the pre-set environmental safety change index reference threshold. The analysis results are as follows: If the environmental safety change index is greater than or equal to the preset environmental safety change index reference threshold, the coal mine environmental information data parameters obtained in real time by the coal mine fire prevention and early warning system will be classified as high-risk environmental information. If the environmental safety change index is less than the preset reference threshold for the environmental safety change index, the coal mine environmental information data parameters obtained in real time by the coal mine fire prevention and early warning system will be classified as low-risk environmental information.

Images