Coal mine fire area monitoring and early warning system and method

Abstract

The invention discloses a coal mine fire area monitoring and early warning system and method, and relates to the technical field of coal mine fire smog. Related data of a smog environment is acquired through a data acquisition module, smog comprehensive state calculation is performed on the related data of the smog environment through a data processing module, and a comprehensive smog state index is obtained; the data analysis module carries out multi-source data association on the smoke environment related data, carries out temperature and smoke cooperative change processing based on the temperature gradient and the gas concentration to obtain a temperature and smoke covariant index, carries out covariant combination on the temperature and smoke covariant index and a comprehensive smoke state index to obtain a comprehensive covariant index, and carries out smoke state analysis on the comprehensive covariant index; the comprehensive covariant index is input into a pre-trained smoke grade evaluation model through a smoke grade analysis and evaluation module, a smoke grade evaluation result is output and obtained, so that smoke grade signals are determined, and finally a control center takes response measures according to smoke grades of different smoke grade signals. Accurate monitoring and early warning of fire smoke conditions are realized.

Description

Technical Field

[0001] The present invention relates to the technical field of coal mine fire smoke, in particular to a coal mine fire zone monitoring and early warning system and method. Background Art

[0002] With the continuous increase in coal mining volume, the scope of closed areas in coal mines has continued to expand. Due to factors such as coal pillar crushing and poor airtightness, there is a possibility of air leakage in the closed areas of mines inducing spontaneous combustion of coal, which increases the risk of fire in the closed areas and brings certain risks to coal mine safety production.

[0003] Currently, fire monitoring in closed areas of coal mines mainly relies on single sensors (such as CO and temperature), which leads to certain problems in detection accuracy. It is unable to accurately monitor the specific conditions of fire smoke in the closed areas of mines, resulting in a high false alarm rate of the entire monitoring system. Summary of the Invention

[0004] In order to solve the deficiencies mentioned in the above background technology, the purpose of the present invention is to provide a coal mine fire zone monitoring and early warning system and method.

[0005] In a first aspect, the purpose of the present invention can be achieved by the following technical solution: a coal mine fire area monitoring and early warning system, comprising:

[0006] Data acquisition module: used to collect smoke environment related data and send the smoke environment related data to the data processing module, wherein the smoke environment related data includes smoke density data, temperature gradient data, gas concentration data and pressure gradient data;

[0007] Data processing module: used to pre-process the smoke environment related data, mark the processed smoke environment related data, calculate the comprehensive smoke state using the marked smoke environment related data, obtain the comprehensive smoke state index, and send the comprehensive smoke state index and smoke environment related data to the data analysis module;

[0008] Data analysis module: This module associates multi-source data related to the smoke environment, processes the temperature smoke covariation based on the temperature gradient and gas concentration, and obtains the temperature smoke covariation index. This index is then covariantly combined with the comprehensive smoke state index to obtain the comprehensive covariation index, which is then sent to the smoke level analysis and evaluation module.

[0009] Smoke level analysis and evaluation module: Inputs the comprehensive covariance index into the pre-trained smoke level evaluation model, outputs the smoke level evaluation result, sets the level evaluation predetermined value, determines different smoke levels based on the comparison between the smoke level evaluation result and the level evaluation predetermined value, and sends different smoke level signals to the control center;

[0010] Control center; used to respond to smoke levels according to different smoke level signals.

[0011] In conjunction with the first aspect, in certain implementations of the first aspect, the system further includes: the data processing module performing data preprocessing on the smoke environment related data includes:

[0012] Data verification, data alignment, data cleaning, feature extraction, and data compression.

[0013] In conjunction with the first aspect, in certain implementations of the first aspect, the system further includes: the processing process of the data processing module includes:

[0014] The data identification process is as follows: mark the smoke density data as Yi, the temperature gradient data as Ti, the gas concentration data as Qi, and the pressure gradient data as Di, where i is the number of acquisition times of the data acquisition module, and i=1, 2, 3, ..., n, and n is the total number of acquisition times of the data acquisition module;

[0015] The calculation formula for the comprehensive smoke state is as follows:

[0016] Using the formula The comprehensive smoke state index Wi is calculated;

[0017] Where Y0 is the preset standard smoke density coefficient, T0 is the preset standard temperature gradient coefficient, Q0 is the preset standard gas concentration coefficient, D0 is the preset standard pressure gradient coefficient, k1 is the smoke density influence coefficient, k2 is the temperature gradient influence coefficient, k3 is the gas concentration influence coefficient, k4 is the pressure gradient influence coefficient, and p is the dynamic weight coefficient.

[0018] In conjunction with the first aspect, in certain implementations of the first aspect, the system further includes: a calculation formula for the dynamic weight coefficient is as follows:

[0019]

[0020] Where α is the time decay factor, R 火 is the distance from the fire source to be detected, R-max is the maximum monitoring radius; △t is the time difference between the current moment and the moment when the data acquisition module collects data.

[0021] In conjunction with the first aspect, in certain implementations of the first aspect, the system further includes: a process in which the data analysis module performs coordinated change processing of temperature and smoke based on the temperature gradient and the gas concentration:

[0022] Using the formula The temperature-smoke covariance index is calculated, where β1 is the temperature covariance proportional coefficient, β2 is the smoke covariance proportional coefficient, and β1+β2=1.

[0023] In conjunction with the first aspect, in certain implementations of the first aspect, the system further includes: the data analysis module covariantly combines the calculated temperature smoke covariance index Xbi and the comprehensive smoke state index Wi to obtain a comprehensive covariance index, and the calculation process is as follows:

[0024]

[0025] Where Hi is the comprehensive covariance index.

[0026] In conjunction with the first aspect, in certain implementations of the first aspect, the system further includes: a level analysis and evaluation process of the smoke level analysis and evaluation module includes:

[0027] Input Hi into the pre-trained smoke level assessment model and output the smoke level assessment result Gi;

[0028] Set the predetermined value G0 for level assessment, compare the smoke level assessment result Gi with the predetermined value G0, and determine the smoke level based on the comparison result:

[0029] When 0<Gi≤G0, the smoke level analysis and evaluation module sends a first-level smoke signal to the control center;

[0030] When G0<Gi≤2G0, the smoke level analysis and evaluation module sends a secondary smoke signal to the control center;

[0031] When 2G0<Gi≤3G0, the smoke level analysis and evaluation module sends a level 3 smoke signal to the control center;

[0032] When Gi>3G0, the smoke level analysis and evaluation module sends a level 4 smoke signal to the control center.

[0033] In a second aspect, in order to achieve the above-mentioned purpose, the present invention discloses a coal mine fire zone monitoring and early warning method, the method comprising the following steps:

[0034] Acquiring smoke environment related data, performing data preprocessing on the smoke environment related data to obtain processed smoke environment related data, wherein the smoke environment related data includes smoke density data, temperature gradient data, gas concentration data, and air pressure gradient data;

[0035] The processed smoke environment-related data is labeled and used to calculate the comprehensive smoke state to obtain the comprehensive smoke state index. The smoke environment-related data is multi-sourced and the temperature smoke covariance index is obtained by processing the temperature gradient and gas concentration based on the coordinated change of temperature smoke.

[0036] The temperature smoke covariance index and the comprehensive smoke state index are covariantly combined to obtain a comprehensive covariance index, which is input into a pre-trained smoke level assessment model to output a smoke level assessment result. A predetermined level assessment value is set, and the smoke level is determined based on the comparison result between the smoke level assessment result and the predetermined level assessment value. Treatment measures are then formulated based on the smoke level.

[0037] Beneficial effects of the present invention:

[0038] The present invention collects smoke environment related data through a data acquisition module, calculates the comprehensive smoke state of the smoke environment related data through a data processing module to obtain a comprehensive smoke state index, and the data analysis module associates the smoke environment related data with multiple sources, performs coordinated change processing of temperature smoke based on temperature gradient and gas concentration to obtain a temperature smoke covariance index, and covariantly combines the temperature smoke covariance index and the comprehensive smoke state index to obtain a comprehensive covariance index, and then uses a smoke level analysis and evaluation module: the comprehensive covariance index is input into a pre-trained smoke level evaluation model, and the smoke level evaluation result is output to determine the smoke level signal, and finally the control center responds according to the smoke level of different smoke level signals, thereby realizing accurate monitoring and early warning of the specific situation of fire smoke. BRIEF DESCRIPTION OF THE DRAWINGS

[0039] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, those skilled in the art can derive other drawings based on these drawings without inventive effort.

[0040] Figure 1 Schematic diagram of the system structure of the present invention;

[0041] Figure 2 It is a schematic flow chart of the method of the present invention. DETAILED DESCRIPTION

[0042] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making any creative efforts shall fall within the scope of protection of the present invention.

[0043] Example 1:

[0044] The following is an introduction to the relevant terms involved in the embodiments of this application:

[0045] Data Verification: Data verification is a verification operation performed to ensure data integrity. A checksum is typically calculated using a specified algorithm on the original data. The recipient then calculates the checksum again using the same algorithm. If the two calculated checksums are identical, the data is considered intact.

[0046] Data cleaning: Data cleaning is the final step in discovering and correcting identifiable errors in data files, including checking data consistency, handling invalid and missing values, etc.

[0047] Multimodality: Multimodality refers to the use of information from multiple different forms or sensory channels for expression, communication, and understanding, typically including visual, auditory, textual, tactile, and other sensory input and output methods. In computer science, artificial intelligence, and machine learning, multimodal technology refers to the integration of data from different modalities (such as images, text, audio, and video) to enhance a model's understanding and reasoning capabilities. This integration improves the completeness and accuracy of information, as each modality provides unique insights for specific tasks. For example, in autonomous driving, cameras provide visual information, while lidar provides spatial perception data. Combining this multimodal information enables the system to better identify obstacles and make accurate decisions. In natural language processing and computer vision, multimodal models can simultaneously handle image and text tasks, such as image-text description generation and visual question answering, helping models achieve cross-domain understanding and generation. This multimodal technology has been widely used in scenarios such as human-computer interaction, autonomous driving, and medical diagnosis, demonstrating its strong application potential.

[0048] like Figure 1 As shown in the figure, the coal mine fire area monitoring and early warning system includes:

[0049] Data acquisition module, data processing module, data analysis module, smoke level analysis and evaluation module and control center;

[0050] The data acquisition module is used to collect smoke environment related data and send the collected smoke environment related data to the data processing module for data processing, wherein the smoke environment related data includes smoke density data, temperature gradient data, gas concentration data and pressure gradient data;

[0051] Specifically, the data acquisition process of the data acquisition module includes the following steps:

[0052] The smoke density data is collected in real time by a laser sensor at the top of the tunnel. The technology uses dual-wavelength laser detection (850nm+1550nm) to differentially eliminate coal dust interference, and an anti-interference design is achieved by automatically cleaning the lens (pulse airflow dust removal every 2 hours). The temperature gradient data refers to the rate of change of temperature, and is obtained by monitoring the axial temperature gradient of the tunnel through a distributed optical fiber temperature measurement system. Specifically, it is performed through a DTS system based on Raman scattering, and the armored optical cable is resistant to mechanical damage to achieve an anti-interference design. The gas concentration data is measured at the ventilation node by a multi-parameter sensor and a multi-channel air chamber design is adopted. In this embodiment, the CO concentration is specifically detected (electrochemical sensor) to represent the fire characteristic index, and a water vapor filter membrane is applied to prevent the influence of condensation. The air pressure gradient data refers to the pressure change trend in the confined space. The air pressure gradient on both sides of the confined wall is detected by a micro-differential pressure transmitter to finally obtain the air pressure gradient data.

[0053] After receiving the smoke environment related data sent by the data acquisition module, the data processing module performs data processing. Specifically, the processing process of the data processing module includes the following steps:

[0054] The smoke environment related data is preprocessed to obtain processed smoke environment related data, wherein the data preprocessing process of the smoke environment related data includes:

[0055] Data verification, data alignment, data cleaning, feature extraction, and data compression;

[0056] Specifically, the data verification is carried out through: frame integrity check: calculating CRC16 and comparing it with the checksum in the packet; AES-128 decryption: using the preset key to decrypt the payload; device legitimacy verification: filtering illegal devices through the node ID whitelist to obtain verified data;

[0057] The data alignment is performed by subjecting the verified data to a spatiotemporal alignment (spatial mapping layer) for data alignment conversion, including processing using a coordinate system conversion algorithm and a spatiotemporal synchronization mechanism to obtain an aligned spatiotemporal dataset;

[0058] The data cleaning is performed by filtering and interpolating the aligned spatiotemporal dataset to remove some invalid data to obtain cleaned data;

[0059] The feature extraction includes: extracting the extinction coefficient change rate of smoke density data, extracting the axial maximum temperature gradient of temperature gradient data, extracting the cumulative exceeding time of gas concentration data, and extracting the air pressure of air pressure gradient data; compressing the features, including standardization and PCA dimensionality reduction;

[0060] The data is compressed using an improved SPIHT compression algorithm; ultimately, the processed smoke environment related data is obtained;

[0061] The processed smoke environment related data are labeled, and the labeled smoke environment related data are used to calculate the comprehensive smoke state to obtain the comprehensive smoke state index;

[0062] The data identification process is as follows: mark the smoke density data as Yi, mark the temperature gradient data as Ti, mark the gas concentration data as Qi, and mark the pressure gradient data as Di, where i is the number of times the data acquisition module collects data, and i=1, 2, 3, ..., n, and n is the total number of times the data acquisition module collects data;

[0063] The calculation formula for the comprehensive smoke state calculation performed by the data processing module is as follows:

[0064] Using the formula The comprehensive smoke state index Wi is calculated;

[0065] Wherein, Y0 is the preset standard smoke density coefficient, T0 is the preset standard temperature gradient coefficient, Q0 is the preset standard gas concentration coefficient, D0 is the preset standard pressure gradient coefficient, k1 is the smoke density influence coefficient, k2 is the temperature gradient influence coefficient, k3 is the gas concentration influence coefficient, k4 is the pressure gradient influence coefficient, and p is the dynamic weight coefficient;

[0066] Furthermore, in a specific implementation process, the preset standard smoke density coefficient, the preset standard temperature gradient coefficient, the preset standard gas concentration coefficient, and the preset standard pressure gradient coefficient are obtained by daily collecting smoke density data, temperature gradient data, gas concentration data, and pressure gradient data, and then performing multiple simulation calculations and taking the average value of the data;

[0067] In this embodiment, the smoke density influence coefficient, temperature gradient influence coefficient, gas concentration influence coefficient, and pressure gradient influence coefficient are calculated by comprehensively evaluating the influence of external factors when the application obtains smoke density data, temperature gradient data, gas concentration data, and pressure gradient data on a daily basis, including human factors, machine detection accuracy issues, and environmental factors. Human factors are those caused by human operation or improper scanning.

[0068] Specifically, in this embodiment, the dynamic weight coefficient is obtained by performing spatiotemporal fusion based on the time and space parts and establishing a spatiotemporal weight matrix. Specifically, the calculation formula of the dynamic weight coefficient is as follows:

[0069]

[0070] Where α is the time decay factor, R火 is the distance from the fire source to the detection, R-max is the maximum monitoring radius; Δt is the time difference between the current moment and the moment when the data acquisition module collects data; wherein, the maximum monitoring radius is associated with the length of the roadway;

[0071] The calculated comprehensive smoke state index Wi and the collected smoke environment related data are sent to the data analysis module for data analysis;

[0072] After receiving the comprehensive smoke state index Wi and smoke environment related data sent by the data processing module, the data analysis module performs data analysis. Specifically, the analysis process of the data analysis module includes the following steps:

[0073] Multi-source data correlation is performed on smoke environment related data, and the temperature smoke covariation index is obtained by processing the temperature smoke covariation based on the temperature gradient and the gas concentration. Specifically, the process of processing the temperature smoke covariation based on the temperature gradient and the gas concentration by the data analysis module includes the following steps:

[0074] Using the formula The temperature-smoke covariance index is calculated, where β1 is the temperature covariance proportional coefficient, β2 is the smoke covariance proportional coefficient, and β1+β2=1;

[0075] The calculated temperature smoke covariance index Xbi and the comprehensive smoke state index Wi are covariantly combined to obtain the comprehensive covariance index. The calculation process is as follows:

[0076]

[0077] Where Hi is the comprehensive covariance index;

[0078] The data analysis module sends the comprehensive covariance index to the smoke level analysis and evaluation module;

[0079] After receiving the comprehensive covariance index sent by the data analysis module, the smoke level analysis and evaluation module performs smoke level analysis and evaluation. Specifically, the specific process of the smoke level analysis and evaluation module includes the following steps:

[0080] The comprehensive covariance index is input into the pre-trained smoke level assessment model to determine the smoke level, and different smoke level signals are sent to the control center. The specific process is as follows:

[0081] Input Hi into the pre-trained smoke level assessment model and output the smoke level assessment result Gi;

[0082] Set the predetermined value G0 for level assessment, compare the smoke level assessment result Gi with the predetermined value G0, and determine the smoke level based on the comparison result:

[0083] When 0<Gi≤G0, the smoke level is determined to be level one, and the smoke level analysis and evaluation module sends a level one smoke signal to the control center. At this time, the smoke feature is single-point CO↑, and the temperature gradient is normal;

[0084] When G0<Gi≤2G0, the smoke level is determined to be level 2 smoke, and the smoke level analysis and evaluation module sends a level 2 smoke signal to the control center. At this time, the smoke characteristics are multi-point smoke + CO↑, where Di>10Pa;

[0085] When 2G0<Gi≤3G0, the smoke level is determined to be level 3 smoke, and the smoke level analysis and evaluation module sends a level 3 smoke signal to the control center. At this time, the smoke feature is that the thermal imager identifies a smoke cluster;

[0086] When Gi>3G0, the smoke level is determined to be level 4 smoke, and the smoke level analysis and evaluation module sends a level 4 smoke signal to the control center. At this time, the smoke feature is confirmed as a flame heat source;

[0087] The smoke level assessment model is pre-built and trained using a spatiotemporal perception multimodal fusion network. The process of pre-building and training based on a moment-to-moment perception multimodal fusion network is as follows:

[0088] Acquire multi-source sensor data, infrared imaging video data, and roadway map structure data, extract spatiotemporal features based on the multi-source sensor data, extract visual features based on the infrared imaging video data, and extract environmental topology based on the roadway map structure data, and fuse the extracted spatiotemporal features, visual features, and environmental topology to obtain fused feature data; wherein the multi-source sensor data includes smoke density, temperature gradient, gas concentration, and pressure gradient;

[0089] The fused feature data is input into a pre-established spatiotemporal perception multimodal fusion network for training. The training process includes single-modal pre-training, cross-modal alignment, end-to-end fine-tuning, and online adaptation. The final training output is a smoke level assessment model.

[0090] After receiving different levels of smoke signals from the smoke level analysis and evaluation module, the control center takes response measures according to different smoke levels, specifically including:

[0091] When the control center receives a level 1 smoke signal, it needs to increase the sampling frequency for processing;

[0092] When the control center receives a secondary smoke signal, it starts local ventilation for treatment;

[0093] When the control center receives a level 3 smoke signal, personnel must be evacuated and nitrogen gas injected for treatment;

[0094] When the control center receives a level 4 smoke signal, it seals off the area and activates the fire extinguishing system;

[0095] Specifically, in order to verify the effect of the present invention, the present invention is further described below through examples:

[0096] Specifically, the training process within the pre-established spatiotemporal perception multimodal fusion network is as follows:

[0097] The unimodal pre-training process is as follows: the spatiotemporal pathway is pre-trained on the UCI Fire dataset; the visual pathway is fine-tuned on the FireNet dataset; the environmental pathway is trained on the SynthTunnel graph dataset; cross-modal alignment is achieved by comparing the cross-modal alignment loss; the end-to-end fine-tuning uses the LAMB (Layer-wise Adaptive Moments) optimizer, the model learning rate is cosine annealing (5e-4→1e-6), and the batch size is 32 (NVIDIA A100);

[0098] The comparison between the specific model evaluation smoke level and the existing technology is shown in Table 1:

[0099] Table 1 Comparison of the evaluation accuracy of the smoke level evaluation model with existing technologies

[0100]

[0101] Embodiment 2: In a second aspect, the present invention discloses a coal mine fire zone monitoring and early warning method, the method comprising the following steps:

[0102] Acquiring smoke environment related data, performing data preprocessing on the smoke environment related data to obtain processed smoke environment related data, wherein the smoke environment related data includes smoke density data, temperature gradient data, gas concentration data, and air pressure gradient data;

[0103] The processed smoke environment-related data is labeled and used to calculate the comprehensive smoke state to obtain the comprehensive smoke state index. The smoke environment-related data is multi-sourced and the temperature smoke covariance index is obtained by processing the temperature gradient and gas concentration based on the coordinated change of temperature smoke.

[0104] The temperature smoke covariance index and the comprehensive smoke state index are covariantly combined to obtain a comprehensive covariance index, which is input into a pre-trained smoke level assessment model to output a smoke level assessment result. A predetermined level assessment value is set, and the smoke level is determined based on the comparison result between the smoke level assessment result and the predetermined level assessment value. Treatment measures are then formulated based on the smoke level.

[0105] Based on the same inventive concept, the present invention also provides a computer device, which includes: one or more processors and a memory for storing one or more computer programs; the program includes program instructions, and the processor is used to execute the program instructions stored in the memory. The processor may be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. It is the computing core and control core of the terminal, which is used to implement one or more instructions, specifically for loading and executing one or more instructions in a computer storage medium to implement the above method.

[0106] It should be further explained that, based on the same inventive concept, the present invention also provides a computer storage medium having a computer program stored thereon, which executes the above method when executed by a processor. The storage medium can be any combination of one or more computer-readable media. The computer-readable medium can be a computer-readable signal medium or a computer-readable storage medium. The computer-readable storage medium can be, for example, but not limited to, an electrical, magnetic, optical, electrical, magnetic, infrared, or semiconductor system, device or component, or any combination thereof. More specific examples (a non-exhaustive list) of computer-readable storage media include: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination thereof. In the present invention, a computer-readable storage medium can be any tangible medium containing or storing a program that can be used by or in conjunction with an instruction execution system, device or component.

[0107] The above formulas are all calculated by removing dimensions and taking their numerical values. The formula is a formula that is closest to the actual situation obtained by collecting a large amount of data and performing software simulation. The preset parameters and preset thresholds in the formula are set by technicians in this field according to actual conditions or obtained by simulating a large amount of data.

[0108] Throughout this specification, references to terms such as "one embodiment," "example," or "specific example" indicate that a specific feature, structure, material, or characteristic described in conjunction with that embodiment or example is included in at least one embodiment or example of the present disclosure. In this specification, schematic representations of these terms do not necessarily refer to the same embodiment or example. Furthermore, the specific features, structures, materials, or characteristics described may be combined in any suitable manner in any one or more embodiments or examples.

[0109] The above shows and describes the basic principles, main features and advantages of the present disclosure. Those skilled in the art should understand that the present disclosure is not limited to the above embodiments. The above embodiments and descriptions are merely illustrative of the principles of the present disclosure. Various changes and improvements may be made to the present disclosure without departing from the spirit and scope of the present disclosure, and such changes and improvements shall fall within the scope of the present disclosure.

Claims

1. Coal mine fire area monitoring and early warning system, characterized by: include: Data acquisition module: used to collect smoke environment related data and send the smoke environment related data to the data processing module, wherein the smoke environment related data includes smoke density data, temperature gradient data, gas concentration data and pressure gradient data; Data processing module: used to pre-process the smoke environment related data, mark the processed smoke environment related data, calculate the comprehensive smoke state using the marked smoke environment related data, obtain the comprehensive smoke state index, and send the comprehensive smoke state index and smoke environment related data to the data analysis module; Data analysis module: This module associates multi-source data related to the smoke environment, processes the temperature smoke covariation based on the temperature gradient and gas concentration, and obtains the temperature smoke covariation index. This index is then covariantly combined with the comprehensive smoke state index to obtain the comprehensive covariation index, which is then sent to the smoke level analysis and evaluation module. Smoke level analysis and evaluation module: Inputs the comprehensive covariance index into the pre-trained smoke level evaluation model, outputs the smoke level evaluation result, sets the level evaluation predetermined value, determines different smoke levels based on the comparison between the smoke level evaluation result and the level evaluation predetermined value, and sends different smoke level signals to the control center; Control center; used to respond to smoke levels according to different smoke level signals.

2. The coal mine fire area monitoring and early warning system according to claim 1 is characterized in that: The data processing module performs data preprocessing on the smoke environment related data, including: Data verification, data alignment, data cleaning, feature extraction, and data compression.

3. The coal mine fire area monitoring and early warning system according to claim 2, characterized in that: The processing process of the data processing module includes: The data identification process is as follows: mark the smoke density data as Yi, the temperature gradient data as Ti, the gas concentration data as Qi, and the pressure gradient data as Di, where i is the number of acquisition times of the data acquisition module, and i=1, 2, 3, ..., n, and n is the total number of acquisition times of the data acquisition module; The calculation formula for the comprehensive smoke state is as follows: Using the formula The comprehensive smoke state index Wi is calculated; Where Y0 is the preset standard smoke density coefficient, T0 is the preset standard temperature gradient coefficient, Q0 is the preset standard gas concentration coefficient, D0 is the preset standard pressure gradient coefficient, k1 is the smoke density influence coefficient, k2 is the temperature gradient influence coefficient, k3 is the gas concentration influence coefficient, k4 is the pressure gradient influence coefficient, and p is the dynamic weight coefficient.

4. The coal mine fire area monitoring and early warning system according to claim 3 is characterized in that: The calculation formula of the dynamic weight coefficient is as follows: Where α is the time decay factor, R 火 is the distance from the fire source to be detected, R-max is the maximum monitoring radius; △t is the time difference between the current moment and the moment when the data acquisition module collects data.

5. The coal mine fire area monitoring and early warning system according to claim 1 is characterized in that: The data analysis module processes the coordinated changes of temperature and smoke based on temperature gradient and gas concentration: Using the formula The temperature-smoke covariance index is calculated, where β1 is the temperature covariance proportional coefficient, β2 is the smoke covariance proportional coefficient, and β1+β2=1.

6. The coal mine fire area monitoring and early warning system according to claim 5, characterized in that: The data analysis module performs covariant combination on the calculated temperature smoke covariance index Xbi and the comprehensive smoke state index Wi to obtain the comprehensive covariance index. The calculation process is as follows: Where Hi is the comprehensive covariance index.

7. The coal mine fire zone monitoring and early warning system according to claim 1, characterized in that: The level analysis and evaluation process of the smoke level analysis and evaluation module includes: Input Hi into the pre-trained smoke level assessment model and output the smoke level assessment result Gi; Set the predetermined value G0 for level assessment, compare the smoke level assessment result Gi with the predetermined value G0, and determine the smoke level based on the comparison result: When 0<Gi≤G0, the smoke level analysis and evaluation module sends a first-level smoke signal to the control center; When G0<Gi≤2G0, the smoke level analysis and evaluation module sends a secondary smoke signal to the control center; When 2G0<Gi≤3G0, the smoke level analysis and evaluation module sends a level 3 smoke signal to the control center; When Gi>3G0, the smoke level analysis and evaluation module sends a level 4 smoke signal to the control center.

8. A coal mine fire zone monitoring and early warning method, characterized in that: The method comprises the following steps: Acquiring smoke environment related data, performing data preprocessing on the smoke environment related data to obtain processed smoke environment related data, wherein the smoke environment related data includes smoke density data, temperature gradient data, gas concentration data, and air pressure gradient data; The processed smoke environment-related data is labeled and used to calculate the comprehensive smoke state to obtain the comprehensive smoke state index. The smoke environment-related data is multi-sourced and the temperature smoke covariance index is obtained by processing the temperature gradient and gas concentration based on the coordinated change of temperature smoke. The temperature smoke covariance index and the comprehensive smoke state index are covariantly combined to obtain a comprehensive covariance index, which is input into a pre-trained smoke level assessment model to output a smoke level assessment result. A predetermined level assessment value is set, and the smoke level is determined based on the comparison result between the smoke level assessment result and the predetermined level assessment value. Treatment measures are then formulated based on the smoke level.

Images