A method and device for detecting and preventing external fire in a coal mine underground

Abstract

This disclosure proposes a method and device for detecting and preventing externally-caused fires in coal mines. The method includes acquiring temperature data and multiple sensor data from the underground coal mine area, including carbon monoxide concentration, smoke data, and open flame data; determining whether temperature warning conditions are met based on temperature; processing the temperature and multi-sensor data using data fusion technology to obtain effective feature information; performing a decision judgment based on an adaptive D-S evidence theory-based logical reasoning algorithm and outputting a judgment result; if the temperature warning conditions are met, controlling the fire extinguishing device to extinguish the fire; if the temperature warning conditions are not met, controlling the fire extinguishing device to extinguish the fire when the judgment result indicates the presence of a fire. According to the method of this disclosure, fires can be detected promptly and accurately.

Description

Technical Field

[0001] This disclosure relates to the field of coal mine underground fire detection and prevention technology, and in particular to a method and device for detecting and preventing externally-caused fires in coal mines. Background Technology

[0002] Fire prevention and suppression are crucial aspects of comprehensive coal mine management, impacting both mine property safety and the lives of all employees. Currently, fire prevention and suppression measures in my country's coal mines lag behind, with infrastructure development not keeping pace with intelligent coal mining practices, and supporting equipment insufficient. The fire extinguishing facilities used in coal mines are outdated, primarily relying on traditional methods such as sandboxes, sandbags, and handheld fire extinguishers. These still depend on manual operation, and their operational status is difficult to monitor in real time. In the event of a fire, the condition of the fire extinguishing facilities, the proficiency of on-site personnel in operating the equipment, and the ability to extinguish the fire quickly all depend on the adequacy of daily management and training within the coal mine, posing significant safety hazards.

[0003] In recent years, with the development of digitalization and intelligentization in coal mines, the equipment configuration and management level of mine production and safety processes have reached a high standard, and many important locations have gradually achieved unmanned operation. However, due to the relatively backward technology of coal mine fire extinguishing equipment, on-duty personnel are still required to monitor the situation in real time, making the automatic fire extinguishing system a blind spot in the construction of intelligent coal mines and affecting the overall progress of smart mine development.

[0004] Currently, common area fire prevention and extinguishing solutions mostly involve attaching temperature and smoke sensors at single points along the conveyor belt. These sensors trigger alarms to alert belt operators, who must remain near the belt to activate the belt sprinkler system upon receiving the alarm. This approach has a significant delay in responding to fires and requires personnel to be constantly vigilant. Existing underground fire prevention and extinguishing technologies suffer from this significant delay in responding to fires, and if the conveyor belt fire alarm system is not functioning properly, or if operators fail to monitor the situation effectively, the fire may spread undetected. Summary of the Invention

[0005] This disclosure aims to at least partially address one of the technical problems in the related art.

[0006] Therefore, the first objective of this disclosure is to propose a method for detecting and preventing external fires in coal mines, with the main purpose of enabling timely and accurate detection of fires.

[0007] The second objective of this disclosure is to propose a device for detecting and preventing external fires in coal mines.

[0008] The third objective of this disclosure is to propose a device for detecting and preventing external fires in coal mines.

[0009] To achieve the above objectives, the first aspect of this disclosure provides a method for detecting and preventing externally caused fires in coal mines, comprising:

[0010] The system acquires temperature data and various sensor data from underground coal mine areas, including carbon monoxide concentration, smoke data, and open flame data.

[0011] Based on the temperature, determine whether the temperature warning conditions are met;

[0012] The temperature and multi-sensor data are processed using data fusion technology to obtain effective feature information; a logical reasoning algorithm based on adaptive DS evidence theory is used to make a decision based on the effective feature information and output a judgment result.

[0013] If the temperature warning condition is met, the fire extinguishing device is controlled to extinguish the fire; if the temperature warning condition is not met, the fire extinguishing device is controlled to extinguish the fire when the judgment result indicates that a fire exists.

[0014] In one embodiment of this disclosure, the temperature warning condition is met when the temperature exceeds a temperature threshold or the rate of temperature increase exceeds a set slope.

[0015] In one embodiment of this disclosure, the DS evidence theory is improved by using sensor similarity and confidence weights to obtain an adaptive DS evidence theory logical reasoning algorithm.

[0016] In one embodiment of this disclosure, the step of improving the DS evidence theory using sensor similarity and credibility weights to obtain an adaptive DS evidence theory logical reasoning algorithm includes: improving the recognition framework of the DS evidence theory using sensor similarity and credibility weights, automatically adjusting the absolute credibility of the evidence according to the judgment condition weights, and re-correcting the basic credibility allocation function using the absolute credibility, thereby obtaining the adaptive DS evidence theory logical reasoning algorithm.

[0017] In one embodiment of this disclosure, before determining whether the temperature warning condition is met based on the temperature, the method further includes: performing anti-electromagnetic interference processing on the temperature and data from multiple sensors.

[0018] To achieve the above objectives, a second aspect of this disclosure provides a coal mine underground external fire detection and prevention device, including a data acquisition module, a mine fire monitoring and control module, and a fire extinguishing module;

[0019] The acquisition module includes a temperature-sensing optical fiber and multiple sensors. The temperature-sensing optical fiber is used to acquire the temperature in the underground area of ​​the coal mine, and the multiple sensors are used to acquire various sensor data, including carbon monoxide concentration, smoke data, and open flame data.

[0020] The mine fire monitoring and control module is used to determine whether the temperature warning condition is met based on the temperature; to process the temperature and the multi-sensor data using data fusion technology to obtain effective feature information; to make a decision judgment on the effective feature information based on the adaptive DS evidence theory and output a judgment result; if the temperature warning condition is met, a first fire extinguishing command is generated; if the temperature warning condition is not met, a second fire extinguishing command is generated when the judgment result indicates that a fire exists.

[0021] The fire extinguishing module is used to extinguish a fire upon receiving the first fire extinguishing command or the second fire extinguishing command.

[0022] In one embodiment of this disclosure, the temperature warning condition is met when the temperature exceeds a temperature threshold or the rate of temperature increase exceeds a set slope.

[0023] In one embodiment of this disclosure, in the mine fire monitoring and control module, the DS evidence theory is improved by using sensor similarity and confidence weights to obtain an adaptive DS evidence theory logical reasoning algorithm.

[0024] In one embodiment of this disclosure, the fire extinguishing module includes an automatic fire extinguishing system for the conveyor head and an automatic fire extinguishing system along the conveyor belt tunnel. The automatic fire extinguishing system for the conveyor head uses dry powder fire extinguishing, and the automatic fire extinguishing system along the conveyor belt tunnel uses sprinkler fire extinguishing.

[0025] To achieve the above objectives, a third aspect of this disclosure provides a coal mine underground external fire detection and prevention device, comprising: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, the instructions being executed by the at least one processor to enable the at least one processor to execute the coal mine underground external fire detection and prevention method of the first aspect of this disclosure.

[0026] In one or more embodiments of this disclosure, temperature and multiple sensor data from an underground coal mine area are acquired. These sensor data include carbon monoxide concentration, smoke data, and open flame data. A temperature warning condition is determined based on the temperature. Data fusion technology is used to process the temperature and multi-sensor data to obtain effective feature information. A logical reasoning algorithm based on adaptive DS evidence theory is used to make a decision based on the effective feature information and output a judgment result. If the temperature warning condition is met, a fire extinguishing device is controlled to extinguish the fire. If the temperature warning condition is not met, the fire extinguishing device is controlled to extinguish the fire if the judgment result indicates the presence of a fire. In this scenario, by combining temperature and multiple sensor data from the underground coal mine area, both the temperature warning condition and the judgment result are determined. The fire extinguishing device is then controlled to extinguish the fire based on the combined temperature warning condition and judgment result. This improves both the timeliness of fire extinguishing and the accuracy of fire detection, thus enabling timely and accurate detection of fires.

[0027] Additional aspects and advantages of this disclosure will be set forth in part in the description which follows, and in part will be obvious from the description, or may be learned by practice of this disclosure. Attached Figure Description

[0028] To more clearly illustrate the technical solutions in the specific embodiments of this disclosure or the prior art, the accompanying drawings used in the description of the specific embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of this disclosure. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort. The above and / or additional aspects and advantages of this disclosure will become apparent and readily understood from the following description of the embodiments in conjunction with the accompanying drawings, wherein:

[0029] Figure 1 This is a schematic flowchart illustrating a method for detecting and preventing externally-caused fires in coal mines, provided in an embodiment of this disclosure.

[0030] Figure 2 This is a schematic flowchart illustrating the data processing procedure of the smoke sensor provided in the embodiments of this disclosure;

[0031] Figure 3 This is a schematic diagram of the decision-making process provided in the embodiments of this disclosure;

[0032] Figure 4 This is a block diagram of a coal mine underground external fire detection and prevention device provided in an embodiment of the present disclosure;

[0033] Figure 5 A schematic diagram of a scenario for the coal mine underground external fire detection and prevention device provided in an embodiment of this disclosure;

[0034] Figure 6 This is a block diagram of a coal mine external fire detection and prevention device used to implement the coal mine external fire detection and prevention method of the embodiments of this disclosure. Detailed Implementation

[0035] Exemplary embodiments will now be described in detail, examples of which are illustrated in the accompanying drawings. When the following description relates to the drawings, unless otherwise indicated, the same numerals in different drawings denote the same or similar elements. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with those of this disclosure. Rather, they are merely examples of apparatuses and methods consistent with some aspects of the embodiments of this disclosure as detailed in the appended claims.

[0036] In the description of this specification, the references to terms such as "one embodiment," "some embodiments," "example," "specific example," or "some examples," etc., indicate that a specific feature, structure, material, or characteristic described in connection with that embodiment or example is included in at least one embodiment or example of this disclosure. In this specification, the illustrative expressions of the above 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 one or more embodiments or examples. Moreover, without contradiction, those skilled in the art can combine and integrate the different embodiments or examples described in this specification, as well as the features of different embodiments or examples.

[0037] Furthermore, the terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include at least one of that feature. In the description of this disclosure, "a plurality of" means at least two, such as two, three, etc., unless otherwise expressly and specifically defined. It should also be understood that the term "and / or" as used in this disclosure refers to and includes any or all possible combinations of one or more associated listed items.

[0038] Embodiments of this disclosure are described in detail below, examples of which are illustrated in the accompanying drawings, wherein the same or similar reference numerals denote the same or similar elements or elements having the same or similar functions throughout. The embodiments described below with reference to the accompanying drawings are exemplary and intended to explain this disclosure, and should not be construed as limiting this disclosure.

[0039] This disclosure provides a method and device for detecting and preventing external fires in coal mines, the main purpose of which is to detect fires in a timely and accurate manner.

[0040] In the first embodiment, Figure 1This is a schematic flowchart illustrating a method for detecting and preventing externally-caused fires in coal mines, as provided in an embodiment of this disclosure. Figure 1 As shown, the method for detecting and preventing external fires in underground coal mines includes the following steps:

[0041] Step S11: Obtain temperature and various sensor data from the underground coal mine area, including carbon monoxide concentration, smoke data, and open flame data.

[0042] In this embodiment, the temperature of the underground coal mine area in step S11 can be acquired using temperature-measuring optical fibers deployed in the underground coal mine area. Multiple sensor data include carbon monoxide concentration, smoke data, and open flame data. Specifically, carbon monoxide concentration can be acquired using a carbon monoxide sensor. Open flame data can be acquired using a flame sensor. Smoke data can be acquired using a smoke sensor.

[0043] In this embodiment, the smoke sensor is equipped with a zeroed dual-wavelength photosensitive element and a carbon monoxide sensor. After processing and analyzing the data collected by the dual-wavelength photosensitive element and the carbon monoxide sensor, the smoke sensor determines whether there is fire smoke.

[0044] Specifically, Figure 2 This is a schematic flowchart illustrating the data processing procedure of the smoke sensor provided in the embodiments of this disclosure. Figure 3 This is a schematic diagram of the decision-making process provided in an embodiment of the present disclosure.

[0045] like Figure 2 As shown, the smoke sensor collects environmental data through a zeroed dual-wavelength photoelectric sensor and a carbon monoxide sensor. The dual-wavelength photoelectric sensor obtains the response values ​​of the blue and red channels, while the carbon monoxide sensor obtains the carbon monoxide (CO gas) concentration value. The smoke sensor integrates and processes the response values ​​of the blue and red channels and the CO gas concentration value, then sends the integrated data to a decision tree for judgment. It then generates a command indicating the presence or absence of fire smoke. If a command indicating no fire smoke is generated, no action is taken. If a command indicating the presence of fire smoke is generated, an alarm is triggered, and it is determined whether the smoke has dissipated. If the smoke has dissipated, the alarm is canceled; otherwise, the alarm continues.

[0046] like Figure 3As shown, the specific judgment process of the decision tree is as follows: Based on the integrated data, determine whether smoke exists; otherwise, it means there is no fire smoke. If so, determine whether it is weak smoke. If it is weak smoke, determine whether it is a weak smoke mixing area. If it is not a weak smoke mixing area, then there is fire smoke. If it is a weak smoke mixing area, determine whether the CO condition is met. If the CO condition is met, then there is fire smoke. If the CO condition is not met, then there is no fire smoke. If it is not weak smoke, determine whether it is a general smoke mixing area. If it is not a general smoke mixing area, then there is fire smoke. If it is a general smoke mixing area, determine whether the CO condition is met. If the CO condition is met, then there is fire smoke. If the CO condition is not met, then there is no fire smoke.

[0047] In this embodiment, the smoke sensor employs multi-feature fusion sensing technology. Based on in-depth analysis of the aerosol composition of mine smoke, it utilizes elements within the smoke sensor, such as dual-wavelength photoelectric sensitive elements and carbon monoxide sensors, to collect multi-feature information using photoelectric detection and gas-sensing detection technologies. Through integrated processing, it fully extracts the characteristic information of mine smoke, achieving quantitative output of the smoke composition in early-stage mine fires. Qualitative analysis is then performed using decision tree judgment. Based on this embodiment, the smoke sensor can improve the accuracy of smoke detection.

[0048] In this embodiment, considering the weak analog output signals of sensitive components and optoelectronic components, which are susceptible to external electromagnetic interference, after acquiring temperature and multiple sensor data in step S11, before sending the temperature and multiple sensor data to subsequent steps for processing and judgment, the method further includes: performing anti-electromagnetic interference processing on the temperature and multiple sensor data. In this case, by adding weak signal anti-electromagnetic interference processing and optimizing the weak signal detection circuit design, accurate acquisition of various basic information (such as temperature and multiple sensor data) can be achieved, thereby improving the accuracy of the sensing layer in complex electromagnetic environments and meeting the system's anti-interference requirements.

[0049] In step S11, when acquiring temperature and multiple sensor data for the underground coal mine area, it is also necessary to acquire the location information corresponding to the temperature and multiple sensor data, so as to make subsequent judgments and processes on the temperature and multiple sensor data for each area. The location information includes information on the belt conveyor head area or substation area, as well as information on the area along the belt conveyor.

[0050] Step S12: Determine whether the temperature warning conditions are met based on the temperature.

[0051] In this embodiment, temperature warning conditions are determined based on the temperature under different location information.

[0052] In this embodiment, the temperature warning condition is met when the temperature exceeds a temperature threshold or the rate of temperature increase exceeds a set slope in step S12. The set slope is calculated from the set temperature change per unit time.

[0053] Step S13: Use data fusion technology to process temperature and multi-sensor data to obtain effective feature information; use a logical reasoning algorithm based on adaptive DS evidence theory to make a decision based on the effective feature information and output the judgment result.

[0054] In this embodiment, in step S13, data fusion technology based on multi-feature information is used to optimize and combine the complementary and redundant information of temperature and multi-sensor data in space and time under the same location information to extract effective feature information, which is then used as a logical criterion in subsequent steps S13.

[0055] In this embodiment, considering that reasonable optimization criteria and algorithm combinations are prerequisites for data fusion, before utilizing data fusion technology, the accuracy and rationality of the optimization algorithm are first tested. Then, based on multi-feature information data fusion technology, temperature and multi-sensor data are optimized and combined through optimization criteria or algorithm combinations that meet the requirements of accuracy and rationality to complete the fusion analysis and processing of useful information from various information sources, such as collection, transmission, integration, filtering, correlation and synthesis, so as to achieve the extraction of effective feature information.

[0056] In this embodiment, in step S13, the logical reasoning algorithm based on adaptive DS evidence theory makes a decision judgment on the valid feature information and outputs a judgment result. The judgment result is one of two outcomes: a fire exists or a fire does not exist.

[0057] In essence, traditional DS evidence theory posits that multiple sensors typically exhibit data consistency and can mutually verify each other. If a sensor's data significantly differs from that of other sensors, it indicates that the other sensors do not support this anomalous sensor, resulting in low credibility for that sensor. Based on this approach, DS evidence theory defines each sensor as a target sensor. For each target sensor, all sensors are considered as supporting evidence, and the credibility of the target sensor is calculated using this evidence. A weighted average of all target sensor data based on their credibility is then used to obtain the final fusion value.

[0058] In this embodiment, considering that traditional Dempster-Shafer (DS) evidence theory typically assumes that the trust level of evidence identified by each sensor is the same when fusing and recognizing evidence, which is not in line with practical applications, step S13 improves the DS (Dempster-Shafer) evidence theory by using sensor similarity and trust weights to obtain an adaptive DS evidence theory logical reasoning algorithm. This enables reliable decision-making, accurate fire assessment, and improves the accuracy and robustness of automatic fire suppression systems.

[0059] In step S13, the DS evidence theory is improved using sensor similarity and credibility weights to obtain an adaptive DS evidence theory logical reasoning algorithm. This includes: improving the recognition framework of the DS evidence theory by combining the current detection conditions with sensor similarity and credibility weights; automatically adjusting the absolute credibility of the evidence according to the judgment condition weights; and re-correcting the basic credibility allocation function using the absolute credibility, thereby obtaining the adaptive DS evidence theory logical reasoning algorithm.

[0060] Specifically, the logical reasoning algorithm based on adaptive DS evidence theory in step S13 first improves the recognition framework of traditional DS evidence theory by combining the current detection conditions with sensor similarity, introducing spatiotemporal preprocessing to perform spatiotemporal preprocessing on the data detected by the sensors; then, through ST-DS (spatio-temporal DS) data fusion technology, it calculates the trust allocation of evidence based on the spatial distribution of data and the location of feature regions, judges the credibility of disputed data, automatically adjusts the absolute credibility of evidence according to the judgment condition weights, and re-corrects the basic credibility allocation function using the absolute credibility to obtain fused data from homogeneous sensors, thereby obtaining the final fused value. This final fused value is the judgment result. Specifically, the ST-DS data fusion technology utilizes the data consistency among sensors, using all sensors as evidence supporting the target sensor, calculating the credibility of the target sensor through this evidence, and finally performing weighted fusion of all target sensors based on credibility. For multiple sensors, any one is selected as the target sensor, and all sensors are used as evidence supporting the target. Let the target sensors be J(n), n = 1 to S', where S' represents the number of sensors. For each target sensor, the evidence sensors providing supporting evidence to the target sensor J(n) are J(i), i = 1 to S'. The degree of support from evidence sensor J(i) to target sensor J(n) is called the basic trust allocation mi(n) of the evidence. The credibility m(n) of the target sensor is obtained based on all the evidence. If the data of a certain sensor is significantly different from that of other sensors in terms of numerical value and spatiotemporal information, it means that other sensors do not support the data of the target sensor, and the credibility of the target sensor is low. Conversely, if the information of other sensors fully supports the target sensor, the credibility of the target sensor data is high. In this case, the credibility (i.e., absolute credibility) of each target sensor is automatically adjusted. In this case, the logical reasoning algorithm based on adaptive DS evidence theory utilizes a spatiotemporal preprocessing mechanism to remove anomalies and noise according to the spatial and historical change patterns of the data, and to find the data feature regions, thus solving the problems of noise and abnormal data, as well as the easy loss of data features in traditional DS evidence theory. At the same time, by combining the DS evidence theory, the trust allocation of evidence is calculated based on the spatial distribution of data and the location of characteristic regions. This reduces many problems existing in traditional data fusion methods. For example, when the data of some location sensors are significantly higher than the average value of other sensors at a certain moment, the decision system may classify them as erroneous data and remove them, without participating in the final fusion process. This type of data fusion method is prone to losing characteristic information in the monitoring environment, which has an adverse effect on the application of the fused data (such as fire early warning).

[0061] Step S14: If the temperature warning condition is met, control the fire extinguishing device to extinguish the fire; if the temperature warning condition is not met, control the fire extinguishing device to extinguish the fire when the judgment result indicates that a fire exists.

[0062] In step S14, the fire extinguishing device includes an automatic fire extinguishing system for the conveyor head and an automatic fire extinguishing system along the conveyor belt tunnel. The automatic fire extinguishing system for the conveyor head adopts a dry powder fire extinguishing method, and the automatic fire extinguishing system along the conveyor belt tunnel adopts a spray fire extinguishing method.

[0063] In step S14, regarding the information on the conveyor head area or substation area, and the information on the area along the conveyor belt, if the temperature warning conditions are met, the automatic fire extinguishing system at the conveyor head is controlled to perform dry powder fire extinguishing, and the automatic fire extinguishing system along the conveyor belt tunnel is controlled to perform spray fire extinguishing. At this time, fire extinguishing control can be initiated without waiting for the judgment result, enabling timely detection and extinguishing of fires in their nascent stage, preventing greater losses. If the temperature warning conditions are not met, and the judgment result indicates the existence of a fire, the automatic fire extinguishing system at the conveyor head is controlled to perform dry powder fire extinguishing, and the automatic fire extinguishing system along the conveyor belt tunnel is controlled to perform spray fire extinguishing. If the temperature warning conditions are not met and the judgment result indicates no fire, no action is taken.

[0064] In step S14, if the temperature warning condition is met at only one location among the information of the conveyor head area, the substation area, and the area along the conveyor belt, or if the temperature warning condition is not met but the judgment result is that a fire exists, then the fire extinguishing device in the area corresponding to the location information is controlled to extinguish the fire.

[0065] In step S14, if the temperature warning conditions are met, or if the temperature warning conditions are not met but the judgment result indicates that a fire exists, a light or voice alarm will also be triggered.

[0066] In the coal mine underground external fire detection and prevention method of this disclosure embodiment, temperature and multiple sensor data of the underground coal mine area are acquired. These sensor data include carbon monoxide concentration, smoke data, and open flame data. The method determines whether temperature warning conditions are met based on temperature. Data fusion technology is used to process the temperature and multi-sensor data to obtain effective feature information. A logical reasoning algorithm based on adaptive DS evidence theory is used to make a decision based on the effective feature information and output a judgment result. If the temperature warning conditions are met, the fire extinguishing device is controlled to extinguish the fire. If the temperature warning conditions are not met, the fire extinguishing device is controlled to extinguish the fire when the judgment result indicates the presence of a fire. In this case, by comprehensively considering the temperature and multiple sensor data of the underground coal mine area, determining whether the temperature warning conditions are met, and using data fusion technology and the logical reasoning algorithm based on adaptive DS evidence theory to obtain a judgment result, the fire extinguishing device is controlled to extinguish the fire based on the combined temperature warning conditions and the judgment result. This improves both the timeliness of fire extinguishing and the accuracy of fire situation assessment, thus enabling timely and accurate detection of fires.

[0067] The following are embodiments of the apparatus disclosed herein, which can be used to execute embodiments of the method disclosed herein. For details not disclosed in the apparatus embodiments of this disclosure, please refer to the embodiments of the method disclosed herein.

[0068] Please see Figure 4 , Figure 4 This is a block diagram of a coal mine underground external fire detection and prevention device provided in an embodiment of the present disclosure. Figure 5 This is a schematic diagram of a scenario for the coal mine underground external fire detection and prevention device provided in an embodiment of this disclosure. The coal mine underground external fire detection and prevention device 10 includes a data acquisition module 11, a mine fire monitoring and control module 12, and a fire extinguishing module 13.

[0069] In this embodiment, the data acquisition module 11 is located in the underground area of ​​the coal mine. The underground area of ​​the coal mine includes areas such as the belt conveyor head area, the belt conveyor line area, and the substation area.

[0070] In this embodiment, the acquisition module 11 includes a temperature-measuring optical fiber and multiple sensors. Specifically, the acquisition module 11 includes an optical fiber temperature measurement host, which includes a temperature-measuring optical fiber. The temperature-measuring optical fiber is deployed along the conveyor belt rollers, idlers, motors, and the ambient temperature of the roadway. Multiple sensors are used to collect various sensor data. These sensors include a carbon monoxide sensor, a flame sensor, and a smoke sensor. The sensor data includes carbon monoxide concentration, smoke data, and open flame data. Multiple smoke, carbon monoxide, and flame sensors can be used. These sensors are deployed in areas such as the conveyor head area, the area along the conveyor belt, and the substation area. This allows for the acquisition of the required temperature and various sensor data for the underground coal mine area.

[0071] In this embodiment, the coal mine underground external fire detection and prevention device also includes mine fire monitoring and control substations set up in different areas, communication optical fibers, an Ethernet optical fiber ring network set up underground, a ground switch set up above ground, and a host computer. Multiple sensors deployed in different areas are connected to the mine fire monitoring and control substations in those areas, and data from these sensors is uploaded to the host computer via the mine fire monitoring and control substations, communication optical fibers, the Ethernet optical fiber ring network, and the ground switch. The fiber optic temperature measurement host uploads data to the host computer via the communication optical fiber, the Ethernet optical fiber ring network, and the ground switch.

[0072] In some embodiments, such as Figure 5 As shown, smoke, carbon monoxide, and flame sensors, along with temperature-measuring optical fibers, are deployed in areas such as the conveyor head / substation. For example, a single mine fire monitoring and control substation is established for this area. The smoke, carbon monoxide, and flame sensors are connected to this substation. The substation transmits data from the smoke, carbon monoxide, and flame sensors, along with the area's location information, to a host computer via communication optical fibers, an Ethernet fiber optic ring network, and a ground switch. Similarly, the fiber optic temperature measurement host transmits location information and temperature data collected via the temperature-measuring optical fiber to the host computer via communication optical fibers, an Ethernet fiber optic ring network, and a ground switch.

[0073] like Figure 5 As shown, smoke, carbon monoxide, and flame sensors, along with temperature-measuring optical fibers, are deployed along the conveyor belt. For example, there are two mine fire monitoring and control substations in areas such as the conveyor head / substation: Substation K1 and Substation K2. Each substation is connected to smoke, carbon monoxide, and flame sensors. Substation K1 is connected to Substation K2 via an inter-substation bus. Substation K2 uploads data from all smoke, carbon monoxide, and flame sensors along the conveyor belt to the host computer via communication optical fibers, an Ethernet fiber optic ring network, and a ground switch. The fiber optic temperature measurement host uploads location information and temperature data collected via the temperature-measuring optical fiber to the host computer via communication optical fibers, an Ethernet fiber optic ring network, and a ground switch.

[0074] In some embodiments, considering the weak analog output signals of sensitive components and optoelectronic components, which are susceptible to external electromagnetic interference, the coal mine external fire detection and prevention device 10 also includes an anti-electromagnetic interference module. This module processes the temperature and various sensor data collected by the acquisition module 11 to resist electromagnetic interference, and then sends the processed data to the mine fire monitoring and control module 12 and the fire extinguishing module 13 for further processing. In this case, by adding weak signal anti-electromagnetic interference processing and optimizing the weak signal detection circuit design, accurate acquisition of various basic information (such as temperature and various sensor data) is achieved, thereby improving the accuracy of the sensing layer's detection in complex electromagnetic environments and meeting the system's anti-interference requirements.

[0075] In some embodiments, the electromagnetic interference suppression module may include decoupling capacitors and high-frequency bypass capacitors disposed between the power supply and ground of each integrated chip in the underground coal mine fire detection and prevention device 10. The decoupling capacitors and high-frequency bypass capacitors stabilize the power supply voltage of the integrated chips and filter out high-frequency noise. Furthermore, the leads connecting the capacitors should be as short as possible to avoid parasitic inductance causing resonance, and the power supply can use single-point grounding to reduce common impedance coupling in the circuit.

[0076] In some embodiments, the mine fire monitoring and control module 12 can be arranged on a PCB board. When arranging the traces on the PCB board, sensitive signal lines used to transmit analog output signals of sensitive components and optoelectronic components are protected by adding ground wires around the sensitive signal lines. In addition, when arranging weak signal traces, try to avoid proximity to high current signal lines and avoid running parallel to high-speed lines. When wiring, try to minimize the area of ​​loops to reduce induced noise.

[0077] In some embodiments, shielded cables are used when connecting signal lines outside the PCB board. Clock traces for weak signal (i.e., sensitive signal) detection circuits should be as short as possible and isolated with ground lines. Right-angle bends should be avoided as much as possible when routing on the PCB board; 45° bends should be used instead.

[0078] In this embodiment, the mine fire monitoring and control module 12 is used to determine whether the temperature warning conditions are met based on the temperature; to process the temperature and multi-sensor data using data fusion technology to obtain effective feature information; to make a decision judgment on the effective feature information based on the adaptive DS evidence theory and output the judgment result; if the temperature warning conditions are met, a first fire extinguishing command is generated; if the temperature warning conditions are not met, a second fire extinguishing command is generated when the judgment result indicates that a fire exists.

[0079] Specifically, in the mine fire monitoring and control module 12, the temperature warning condition is met when the temperature exceeds the temperature threshold or the temperature increase rate exceeds the set slope. In this case, the mine fire monitoring and control module 12 analyzes and judges the fire situation in the entire roadway based on the temperature and temperature changes detected by the temperature-measuring fiber optic cable.

[0080] In the mine fire monitoring and control module 12, the DS evidence theory is improved using sensor similarity and credibility weights to obtain an adaptive DS evidence theory logical reasoning algorithm. This improvement includes: refining the DS evidence theory's identification framework using sensor similarity and credibility weights; automatically adjusting the absolute credibility of the evidence based on the judgment condition weights; and re-correcting the basic credibility allocation function using the absolute credibility, thereby obtaining the adaptive DS evidence theory logical reasoning algorithm. Specific details can be found in the relevant descriptions in the method embodiments. In this case, the mine fire monitoring and control module 12, through the linkage between the fiber optic temperature measurement host and the mine fire monitoring and control substation, alerts to fires in designated areas, and the substation controls the fire extinguishing modules in each area to extinguish the fires.

[0081] In this embodiment, the mine fire monitoring and control module 12 generates an alarm command when generating a first fire extinguishing command or a second fire extinguishing command. The mine fire monitoring and control substation controls the corresponding alarm module to trigger an alarm based on the alarm command.

[0082] like Figure 5 As shown, the mine fire monitoring and control module 12 is located in the host computer above ground. The mine fire monitoring and control module 12 can be software-based. The mine fire monitoring and control module 12 generates a first fire extinguishing command or a second fire extinguishing command, and then, based on location information, sends the first fire extinguishing command or the second fire extinguishing command to different mine fire monitoring and control substations via ground switches and Ethernet fiber optic ring networks. The mine fire monitoring and control substations then control the fire extinguishing modules in their respective areas.

[0083] In this embodiment, the host computer can also be equipped with functions such as linkage control and parameter display.

[0084] In this embodiment, the fire extinguishing module 13 is used to extinguish a fire when it receives a first fire extinguishing command or a second fire extinguishing command.

[0085] Specifically, the fire extinguishing module 13 includes an automatic fire extinguishing system at the conveyor head and an automatic fire extinguishing system along the conveyor belt tunnel. The automatic fire extinguishing system at the conveyor head is installed in the area of ​​the conveyor head or the substation area, while the automatic fire extinguishing system along the conveyor belt tunnel is installed in the area along the conveyor belt.

[0086] The automatic fire extinguishing system at the conveyor head employs dry powder extinguishing. When the mine fire monitoring and control substation located in the conveyor head area or substation area receives a first or second fire extinguishing command, it controls the automatic fire extinguishing system at the conveyor head to extinguish the fire with dry powder. In some embodiments, the dry powder extinguishing method is, for example, ultrafine dry powder extinguishing.

[0087] The automatic fire suppression system along the belt conveyor roadway uses a sprinkler system. This system includes a water-sprinkler solenoid valve. When the mine fire monitoring and control substation located along the belt conveyor receives the first or second fire suppression command, it controls the water-sprinkler solenoid valve of the automatic fire suppression system along the belt conveyor roadway to open and initiate water spraying for fire suppression.

[0088] In some embodiments, there may be multiple sprinkler solenoid valves, such as... Figure 5 As shown, the sprinkler solenoid valves include, for example, sprinkler solenoid valve A1, sprinkler solenoid valve A2, sprinkler solenoid valve A3, and sprinkler solenoid valve A4. Adjacent sprinkler solenoid valves are spaced 50 meters or 100 meters apart.

[0089] In some embodiments, the coal mine underground external fire detection and prevention device further includes a power supply box. The power supply box is used to provide power to other equipment in the coal mine underground external fire detection and prevention device.

[0090] In some embodiments, the coal mine underground external fire detection and prevention device has a standard communication interface, which enables seamless connection with the smart mine platform, thereby truly achieving unmanned operation.

[0091] In some embodiments, the coal mine underground external fire detection and prevention device also includes a main unit of an automatic fire extinguishing device for mining areas installed underground. The main unit of the automatic fire extinguishing device for mining areas is connected to the mine fire monitoring and control substation and the fiber optic temperature measurement main unit in each area. The main unit of the automatic fire extinguishing device for mining areas is equipped with a mine fire monitoring and control module 12. When the host computer or the coal mine ring network fails, the coal mine underground external fire detection and prevention device can still operate independently.

[0092] In some embodiments, the coal mine underground external fire detection and prevention device further includes an alarm module, which is connected to the mine fire monitoring and control substation. The alarm module provides alarm reminders under the control of the mine fire monitoring and control substation.

[0093] In some embodiments, the coal mine underground external fire detection and prevention device also includes an intrinsically safe control display installed underground. The intrinsically safe control display is located near the mine fire monitoring and control substation, and can be used to temporarily switch to manual control, allowing for manual intervention underground. Thus, the intrinsically safe control display enables switching between automatic fire prevention and extinguishing modes and manual control fire suppression modes.

[0094] In some embodiments, the coal mine underground external fire detection and prevention device also includes equipment for the chief engineer's office, mine leaders, and dispatch room. The equipment for the chief engineer's office, mine leaders, and dispatch room is connected to the host computer and the ground switch. The equipment for the chief engineer's office, mine leaders, and dispatch room is used to remotely monitor the detection and prevention of external fires in the coal mine.

[0095] It should be noted that the foregoing explanation of the embodiment of the method for detecting and preventing external fires in coal mines also applies to the coal mine external fire detection and prevention device of this embodiment, and will not be repeated here.

[0096] In the coal mine external fire detection and prevention device of this embodiment, the device includes a data acquisition module, a mine fire monitoring and control module, and a fire extinguishing module. The data acquisition module includes a temperature-measuring optical fiber and multiple sensors. The temperature-measuring optical fiber is used to acquire the temperature of the underground coal mine area, and the multiple sensors are used to acquire various sensor data, including carbon monoxide concentration, smoke data, and open flame data. The mine fire monitoring and control module is used to determine whether the temperature warning condition is met based on the temperature. It uses data fusion technology to process the temperature and multi-sensor data to obtain effective feature information. It uses a logical reasoning algorithm based on adaptive DS evidence theory to make a decision judgment on the effective feature information and outputs a judgment result. If the temperature warning condition is met, a first fire extinguishing command is generated. If the temperature warning condition is not met, a second fire extinguishing command is generated when the judgment result indicates that a fire exists. The fire extinguishing module is used to extinguish the fire upon receiving the first or second fire extinguishing command. In this scenario, by combining temperature data from various sensors in the underground coal mine area, it is possible to determine whether the temperature warning conditions are met. Furthermore, by utilizing data fusion technology and the logical reasoning algorithm based on adaptive DS evidence theory, a decision is made. The fire extinguishing device is then controlled to extinguish the fire based on the combined temperature warning conditions and the decision, thereby improving both the timeliness of fire extinguishing and the accuracy of fire assessment. As a result, fires can be detected promptly and accurately. To address the current issues of inability to detect underground coal mine fires in real time and the lack of automatic control for fire extinguishing devices, this project utilizes key technologies such as multi-feature fusion sensing technology for smoke, data fusion, and logical reasoning algorithms based on adaptive DS evidence theory to complete the hardware and software design of an underground coal mine external fire detection and prevention device. This includes the development of a fire prevention and extinguishing software platform, resulting in a highly sensitive, reliable, and robust device that enables real-time monitoring of external fires in underground belt conveyor roadways, conveyor heads, and electromechanical chambers. The device allows for intelligent monitoring, analysis, prediction, early warning, and coordinated control of fire parameters, gradually achieving unmanned operation, reducing manpower while increasing production, preventing fires before they occur, and promoting overall technological progress in the industry, thereby generating significant social benefits.

[0097] The coal mine underground external fire detection and prevention device in this embodiment has an early warning function. It can trigger an alarm based on the detection results of temperature, smoke, and flame, and provide early warnings based on the judged temperature and temperature growth rate, so as to extinguish the fire in its early stage. Through a standard communication interface, it can be seamlessly connected with the smart mine platform, thereby truly realizing unattended operation. The temperature of the entire conveyor belt is continuously monitored. According to the different functions of the area, sensors such as smoke, flame, and carbon monoxide are configured to achieve comprehensive monitoring. The use of multiple sensors to confirm the fire situation reduces the probability of false alarms. It has a main unit for an automatic fire extinguishing device for mining areas. When the host computer or the coal mine ring network is faulty, the coal mine underground external fire detection and prevention device can still operate independently. At the locations of important electromechanical equipment at the head and tail of the machine, flame sensors are added according to the different fire sources and conditions, thereby improving the accuracy of fire judgment. More effective powder spraying fire extinguishing method is adopted to extinguish the fire quickly and reduce the losses caused by the fire.

[0098] According to embodiments of this disclosure, this disclosure also provides a coal mine underground external fire detection and prevention device, a readable storage medium, and a computer program product.

[0099] Figure 6 This is a block diagram of an underground external fire detection and prevention device for implementing the method for detecting and preventing external fires in coal mines according to embodiments of the present disclosure. The underground external fire detection and prevention device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workbenches, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The underground external fire detection and prevention device can also represent various forms of mobile devices, such as personal digital processors, cellular phones, smartphones, wearable electronic devices, and other similar computing devices. The components, connections and relationships between components, and functions shown in this disclosure are merely examples and are not intended to limit the implementation of the present disclosure as described and / or claimed herein.

[0100] like Figure 6 As shown, the coal mine underground external fire detection and prevention equipment 20 includes a computing unit 21, which can perform various appropriate actions and processes according to a computer program stored in a read-only memory (ROM) 22 or a computer program loaded from a storage unit 28 into a random access memory (RAM) 23. The RAM 23 can also store various programs and data required for the operation of the coal mine underground external fire detection and prevention equipment 20. The computing unit 21, ROM 22, and RAM 23 are interconnected via a bus 24. An input / output (I / O) interface 25 is also connected to the bus 24.

[0101] Multiple components of the coal mine underground external fire detection and prevention equipment 20 are connected to the I / O interface 25, including: an input unit 26, such as a keyboard and mouse; an output unit 27, such as various types of monitors and speakers; a storage unit 28, such as a disk or optical disk, which is communicatively connected to the computing unit 21; and a communication unit 29, such as a network card, modem, or wireless transceiver. The communication unit 29 allows the coal mine underground external fire detection and prevention equipment 20 to exchange information / data with other coal mine underground external fire detection and prevention equipment through computer networks such as the Internet and / or various telecommunications networks.

[0102] The computing unit 21 can be various general-purpose and / or special-purpose processing components with processing and computing capabilities. Some examples of the computing unit 21 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various special-purpose artificial intelligence (AI) computing chips, various computing units running machine learning model algorithms, a digital signal processor (DSP), and any suitable processor, controller, microcontroller, etc. The computing unit 21 performs the various methods and processes described above, such as performing a method for detecting and preventing externally caused fires in coal mines. For example, in some embodiments, the method for detecting and preventing externally caused fires in coal mines can be implemented as a computer software program, which is tangibly contained in a machine-readable medium, such as storage unit 28. In some embodiments, part or all of the computer program can be loaded and / or installed on the coal mine externally caused fire detection and prevention device 20 via ROM 22 and / or communication unit 29. When the computer program is loaded into RAM 23 and executed by the computing unit 21, one or more steps of the method for detecting and preventing externally caused fires in coal mines described above can be performed. Alternatively, in other embodiments, the computing unit 21 may be configured by any other suitable means (e.g., by means of firmware) to perform a method for detecting and preventing external fires in coal mines.

[0103] Various embodiments of the systems and techniques described above in this disclosure can be implemented in digital electronic circuit systems, integrated circuit systems, field-programmable gate arrays (FPGAs), application-specific integrated circuits (ASICs), application-specific standard products (ASSPs), systems-on-a-chip (SoCs), payload-programmable logic electronic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various embodiments may include: implementations in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which may be a dedicated or general-purpose programmable processor, capable of receiving data and instructions from a storage system, at least one input device, and at least one output device, and transmitting data and instructions to the storage system, the at least one input device, and the at least one output device.

[0104] The program code used to implement the methods of this disclosure may be written in any combination of one or more programming languages. This program code may be provided to a processor or controller of a general-purpose computer, special-purpose computer, or other programmable data processing apparatus, such that when executed by the processor or controller, the program code causes the functions / operations specified in the flowcharts and / or block diagrams to be implemented. The program code may be executed entirely on a machine, partially on a machine, as a standalone software package partially on a machine and partially on a remote machine, or entirely on a remote machine or server.

[0105] In this disclosure, a machine-readable medium can be a tangible medium that may contain or store a program for use by or in conjunction with an instruction execution system, apparatus, or device. A machine-readable medium can be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium can be, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or electronic devices, or any suitable combination of the foregoing. More specific examples of machine-readable storage media include electrical connections based on one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage electronics, magnetic storage electronics, or any suitable combination of the foregoing.

[0106] To provide interaction with a user, the systems and techniques described herein can be implemented on a computer having: a display device for displaying information to the user (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor); and a keyboard and pointing device (e.g., a mouse or trackball) through which the user provides input to the computer. Other types of devices can also be used to provide interaction with the user; for example, feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including sound input, voice input, or tactile input).

[0107] The systems and technologies described herein can be implemented in computing systems that include backend components (e.g., as data servers), or middleware components (e.g., application servers), or frontend components (e.g., user computers with graphical user interfaces or web browsers through which users can interact with implementations of the systems and technologies described herein), or any combination of such backend, middleware, or frontend components. The components of the system can be interconnected via digital data communication of any form or medium (e.g., communication networks). Examples of communication networks include local area networks (LANs), wide area networks (WANs), the Internet, and blockchain networks.

[0108] Computer systems can include clients and servers. Clients and servers are generally geographically separated and typically interact via communication networks. The client-server relationship is created by computer programs running on the respective computers and having a client-server relationship with each other. A server can be a cloud server, also known as a cloud computing server or cloud host, a hosting product within the cloud computing service system that addresses the management difficulties and weak business scalability inherent in traditional physical hosts and VPS (Virtual Private Server) services. Servers can also be servers for distributed systems or servers integrated with blockchain technology.

[0109] It should be understood that the various forms of processes shown above can be used to rearrange, add, or delete steps. For example, the steps described in this disclosure can be executed in parallel, sequentially, or in different orders, as long as the desired result of the technical solution disclosed in this disclosure can be achieved, and this disclosure does not impose any limitations herein.

[0110] The specific embodiments described above do not constitute a limitation on the scope of protection of this disclosure. Those skilled in the art should understand that various modifications, combinations, sub-combinations, and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of this disclosure should be included within the scope of protection of this disclosure.

Claims

1. A method for detecting and preventing externally caused fires in underground coal mines, characterized in that, include: The system acquires temperature data and various sensor data from underground coal mine areas, including carbon monoxide concentration, smoke data, and open flame data. Based on the temperature, determine whether the temperature warning conditions are met; Data fusion technology is used to process the temperature and the data from the various sensors to obtain effective feature information; A logical reasoning algorithm based on adaptive DS evidence theory makes a decision based on the effective feature information and outputs a judgment result. When the temperature warning condition is met, the fire extinguishing device is controlled to extinguish the fire; when the temperature warning condition is not met, the fire extinguishing device is controlled to extinguish the fire when the judgment result indicates that a fire exists. Among them, the logical reasoning algorithm for improving the DS evidence theory by utilizing sensor similarity and confidence weights to obtain an adaptive DS evidence theory includes: The recognition framework of DS evidence theory is improved by using sensor similarity and credibility weights. The absolute credibility of the evidence is automatically adjusted according to the judgment condition weights, and the basic credibility allocation function is re-corrected using the absolute credibility, thereby obtaining an adaptive logical reasoning algorithm for DS evidence theory. The logical reasoning algorithm for improving the DS evidence theory by utilizing sensor similarity and confidence weights to obtain an adaptive DS evidence theory specifically includes: Combining current detection conditions, the recognition framework of the traditional DS evidence theory is improved by using sensor similarity, and spatiotemporal preprocessing is introduced to perform spatiotemporal preprocessing on the data detected by the sensor. Using ST-DS data fusion technology, the trust allocation of evidence is calculated based on the spatial distribution of data and the location of characteristic regions. The credibility of disputed data is judged, the absolute credibility of the evidence is automatically adjusted according to the weight of the judgment conditions, and the basic credibility allocation function is revised again using the absolute credibility. The fused evidence is used to obtain fused data from homogeneous sensors, and the final fused value is obtained. The final fused value is used as the judgment result. The logical reasoning algorithm for improving DS evidence theory using sensor similarity and confidence weights to obtain adaptive DS evidence theory also includes: When using ST-DS data fusion technology, the consistency of data among various sensors is utilized to use all sensors as evidence supporting the target sensor. The credibility of the target sensor is calculated based on the evidence, and all target sensors are weighted and fused according to the credibility. For multiple sensors, select any one as the target sensor and use all sensors as evidence to support the target. Let the target sensor be J(n), n=1~S', where S' represents the number of sensors; For each target sensor, the evidence sensor that provides evidence support to the target sensor J(n) is J(i), i=1~S'. The degree of support of the evidence sensor J(i) to the target sensor J(n) is called the basic trust allocation mi(n) of the evidence. The credibility m(n) of the target sensor is obtained based on all the evidence. When the data from a certain sensor differs significantly from that of other sensors in terms of magnitude and spatiotemporal information, it is determined that the other sensors do not support the data from that target sensor, and the reliability of that target sensor is low. When the information from other sensors fully supports that of the target sensor, the reliability of the data from that target sensor is high, thus achieving automatic adjustment of the reliability of each target sensor.

2. The method for detecting and preventing external fires in coal mines according to claim 1, characterized in that, The temperature warning condition is met when the temperature exceeds the temperature threshold or the rate of temperature increase exceeds the set slope.

3. The method for detecting and preventing external fires in coal mines according to claim 1, characterized in that, Before determining whether the temperature warning conditions are met based on the aforementioned temperature, the process also includes: The temperature and data from various sensors are processed to resist electromagnetic interference.

4. A device for detecting and preventing externally caused fires in coal mines, characterized in that, It includes a data acquisition module, a mine fire monitoring and control module, and a fire extinguishing module; The acquisition module includes a temperature-sensing optical fiber and multiple sensors. The temperature-sensing optical fiber is used to acquire the temperature in the underground area of ​​the coal mine, and the multiple sensors are used to acquire various sensor data, including carbon monoxide concentration, smoke data, and open flame data. The mine fire monitoring and control module is used to determine whether the temperature warning conditions are met based on the temperature; and to process the temperature and the data from the various sensors using data fusion technology to obtain effective feature information. The logical reasoning algorithm based on adaptive DS evidence theory makes a decision judgment on the effective feature information and outputs a judgment result; when the temperature warning condition is met, a first fire extinguishing command is generated; when the temperature warning condition is not met, a second fire extinguishing command is generated when the judgment result indicates that a fire exists. The fire extinguishing module is used to extinguish a fire when it receives the first fire extinguishing command or the second fire extinguishing command. In the mine fire monitoring and control module, the DS evidence theory is improved by using sensor similarity and confidence weights to obtain an adaptive DS evidence theory logical reasoning algorithm. An adaptive logical reasoning algorithm for DS evidence theory is obtained by improving the DS evidence theory using sensor similarity and confidence weights, including: The recognition framework of DS evidence theory is improved by using sensor similarity and credibility weights. The absolute credibility of the evidence is automatically adjusted according to the judgment condition weights, and the basic credibility allocation function is re-corrected using the absolute credibility, thereby obtaining an adaptive logical reasoning algorithm for DS evidence theory. The logical reasoning algorithm for improving the DS evidence theory by utilizing sensor similarity and confidence weights to obtain an adaptive DS evidence theory specifically includes: Combining current detection conditions, the recognition framework of the traditional DS evidence theory is improved by using sensor similarity, and spatiotemporal preprocessing is introduced to perform spatiotemporal preprocessing on the data detected by the sensor. Using ST-DS data fusion technology, the trust allocation of evidence is calculated based on the spatial distribution of data and the location of characteristic regions. The credibility of disputed data is judged, the absolute credibility of the evidence is automatically adjusted according to the weight of the judgment conditions, and the basic credibility allocation function is revised again using the absolute credibility. The fused evidence is used to obtain fused data from homogeneous sensors, and the final fused value is obtained. The final fused value is used as the judgment result. The logical reasoning algorithm for improving DS evidence theory using sensor similarity and confidence weights to obtain adaptive DS evidence theory also includes: When using ST-DS data fusion technology, the consistency of data among various sensors is utilized to use all sensors as evidence supporting the target sensor. The credibility of the target sensor is calculated based on the evidence, and all target sensors are weighted and fused according to the credibility. For multiple sensors, select any one as the target sensor and use all sensors as evidence to support the target. Let the target sensor be J(n), n=1~S', where S' represents the number of sensors; For each target sensor, the evidence sensor that provides evidence support to the target sensor J(n) is J(i), i=1~S'. The degree of support of the evidence sensor J(i) to the target sensor J(n) is called the basic trust allocation mi(n) of the evidence. The credibility m(n) of the target sensor is obtained based on all the evidence. When the data from a certain sensor differs significantly from that of other sensors in terms of magnitude and spatiotemporal information, it is determined that the other sensors do not support the data from that target sensor, and the reliability of that target sensor is low. When the information from other sensors fully supports that of the target sensor, the reliability of the data from that target sensor is high, thus achieving automatic adjustment of the reliability of each target sensor.

5. The coal mine underground external fire detection and prevention device according to claim 4, characterized in that, The temperature warning condition is met when the temperature exceeds the temperature threshold or the rate of temperature increase exceeds the set slope.

6. The coal mine underground external fire detection and prevention device according to claim 4, characterized in that, The fire extinguishing module includes an automatic fire extinguishing system for the conveyor head and an automatic fire extinguishing system along the conveyor roadway. The automatic fire extinguishing system for the conveyor head uses dry powder fire extinguishing, while the automatic fire extinguishing system along the conveyor roadway uses sprinkler fire extinguishing.

7. A device for detecting and preventing external fires in coal mines, characterized in that, include: At least one processor; as well as A memory communicatively connected to the at least one processor; wherein, The memory stores instructions that can be executed by the at least one processor, which, when executed by the at least one processor, enables the at least one processor to perform the method for detecting and preventing external fires in coal mines according to any one of claims 1-3.

Images