A method and system for monitoring underground emergency rescue

Abstract

The present invention provides a method and system for monitoring downhole emergency rescue, and relates to the field of downhole monitoring technology. The method comprises: obtaining high-definition video frames and infrared video frames of each downhole area at multiple moments in the current monitoring cycle; determining the abnormal working state score according to the high-definition video frames of each downhole area at multiple moments in the current monitoring cycle; determining the temperature abnormality score according to the infrared video frames of each downhole area at multiple moments in the current monitoring cycle and the infrared video frames of each downhole area at the end of the previous monitoring cycle; obtaining multiple harmful gas concentration data of each downhole area at multiple moments in the current monitoring cycle; determining the gas abnormality score according to the harmful gas concentration data; determining the emergency rescue level according to the abnormal working state score, the temperature abnormality score and the gas abnormality score. According to the present invention, the situation where emergency rescue needs to be implemented in the downhole can be fully and accurately monitored, and the accuracy of emergency rescue can be improved.

Description

Technical Field

[0001] The present invention relates to the technical field of underground monitoring, and in particular to an underground emergency rescue monitoring method and system. Background Art

[0002] In the related technology, CN117846707A provides a mining geotechnical engineering emergency linkage monitoring method based on precise positioning, which relates to the field of mining data processing technology. The method includes: obtaining underground mine environmental monitoring data and environmental reference data, and determining the monitoring data conversion value and abnormal ratio based on the acquired data; if the abnormal ratio shows that the underground mine environment is in a dangerous state, then the underground environment warning type and warning level determined based on the monitoring data conversion value and the abnormal ratio are matched with emergency rescue measures, and the associated emergency linkage terminal is started according to the emergency rescue measures to realize emergency linkage rescue. This technical solution can improve the accuracy of the data detected by the sensor, ensure the recognition accuracy, and reduce the false alarm rate. At the same time, it can automatically generate emergency rescue plans according to the warning type and warning level, and call relevant emergency rescue resources to realize emergency linkage rescue, thereby improving the response speed of emergency linkage rescue.

[0003] CN114370304A discloses a mine tunnel environmental information measurement system and method, wherein the system includes an ultrasonic anemometer, a multi-parameter monitor, a data acquisition module, a central control platform, a data communication module, a flexible mechanical arm, a power conversion module, a display and alarm module and a computer; the multi-parameter monitor also includes an infrared detector, a CH4 gas sensor, a CO gas sensor, an O2 gas sensor, a CO2 gas sensor and a temperature and humidity sensor; the system can not only monitor the environmental information of the mine tunnel in real time and adjust the environment. It can also achieve large-section wind measurement requirements through a flexible mechanical arm. In addition, this solution also provides a mine tunnel environmental information measurement method based on the above system, which can remotely measure the underground environmental conditions and wind flow conditions when the mine is in normal production. It can improve the mine's disaster response and relief capabilities and ensure the safety of emergency rescue personnel.

[0004] Therefore, although emergency rescue can be achieved in the related technology, it does not conduct comprehensive monitoring of the underground based on the three abnormal conditions of abnormal working state, abnormal temperature and abnormal gas, making it difficult to comprehensively and accurately monitor the situations in which emergency rescue needs to be implemented underground.

[0005] The information disclosed in the background technology section of this application is only intended to deepen the understanding of the general background technology of this application, and should not be regarded as an admission or any form of suggestion that the information constitutes the prior art already known to those skilled in the art. Summary of the invention

[0006] The present invention provides an underground emergency rescue monitoring method and system, which can solve the technical problem that it is difficult to comprehensively and accurately monitor the situation where emergency rescue needs to be implemented underground.

[0007] According to a first aspect of the present invention, there is provided an underground emergency rescue monitoring method, comprising: dividing the underground into a plurality of underground areas, installing a high-definition camera and an infrared camera in each underground area, obtaining high-definition video frames and infrared video frames of each underground area at a plurality of moments in the current monitoring cycle, wherein the high-definition video frames are obtained by real-time videos shot by the high-definition camera, and the infrared video frames are obtained by real-time videos shot by the infrared camera; determining a working state abnormality score according to the high-definition video frames of each underground area at a plurality of moments in the current monitoring cycle; determining a temperature abnormality score according to the infrared video frames of each underground area at a plurality of moments in the current monitoring cycle and the infrared video frames of each underground area at the end of the previous monitoring cycle; installing a plurality of harmful gas concentration sensors in each underground area, obtaining a plurality of harmful gas concentration data of each underground area at a plurality of moments in the current monitoring cycle; determining a gas abnormality score according to the harmful gas concentration data; determining an emergency rescue level according to the working state abnormality score, the temperature abnormality score and the gas abnormality score.

[0008] According to the present invention, based on the high-definition video frames of each underground area at multiple moments in the current monitoring cycle, the abnormal working status score is determined, including: through the posture feature encoding level of the trained image recognition model, feature extraction processing is performed on each staff member in the high-definition video frames at multiple moments in the current monitoring cycle to obtain the posture feature vector of each staff member; based on the posture feature vectors of each staff member in the high-definition video frames at multiple moments in the current monitoring cycle and the posture feature vectors of preset abnormal postures, the abnormal working status score is determined.

[0009] According to the present invention, the abnormal working status score is determined based on the posture feature vectors of each worker in the high-definition video frames at multiple moments of the current monitoring period and the posture feature vectors of the preset abnormal postures, including: according to the formula Determine the work status abnormality score ,in, is the posture feature vector of the jth worker at the kth moment in the current monitoring period, is the posture feature vector of the preset abnormal posture, for The transposed vector of is the number of staff members, To monitor the number of cycle times, is the number of preset abnormal postures, j≤ , k≤ , e≤ , and j, k, e, , and All are positive integers, and max is the maximum value function.

[0010] According to the present invention, a temperature anomaly score is determined based on infrared video frames of each downhole area at multiple moments in the current monitoring cycle and infrared video frames of each downhole area at the end of the previous monitoring cycle, including: determining a plurality of temperature anomaly pixels whose corresponding temperatures are higher than a preset temperature threshold among a plurality of pixel points in the infrared video frames of each downhole area at multiple moments in the current monitoring cycle; performing a connected domain analysis on the plurality of temperature anomaly pixels to obtain temperature anomaly areas of each downhole area at multiple moments in the current monitoring cycle; obtaining temperature anomaly area areas of each downhole area at multiple moments in the current monitoring cycle based on the temperature anomaly areas; and determining a temperature anomaly score based on the temperature anomaly area areas and the historical temperature anomaly area areas in the infrared video frames of each downhole area at the end of the previous monitoring cycle.

[0011] According to the present invention, the temperature anomaly score is determined based on the area of ​​the temperature anomaly region and the historical temperature anomaly area in the infrared video frame of each downhole area at the end of the last monitoring cycle, including: according to the formula , Determining the Temperature Anomaly Score ,in, is the temperature anomaly score of the ith underground area at the kth moment in the current monitoring period, is the temperature anomaly area of ​​the ith underground area at the kth moment in the current monitoring period, is the temperature anomaly area threshold, is the area of ​​the historical temperature anomaly of the ith underground area at the end of the last monitoring cycle, is the number of underground areas, is the number of monitoring cycle time, i≤ , k≤ , and i, k, and All are positive integers, and max is the maximum value function.

[0012] According to the present invention, a gas anomaly score is determined based on the harmful gas concentration data, including: fitting the harmful gas concentration data and multiple moments of the current monitoring period to obtain a harmful gas concentration function; determining a harmful gas concentration derivative function based on the harmful gas concentration function; determining a harmful gas concentration change rate based on the harmful gas concentration derivative function; obtaining preset concentration thresholds for multiple harmful gas concentrations; and determining a gas anomaly score based on the harmful gas concentration data, the harmful gas concentration change rate and the preset concentration threshold.

[0013] According to the present invention, the gas anomaly score is determined according to the harmful gas concentration data, the harmful gas concentration change rate and the preset concentration threshold, including: according to the formula , Determining the Gas Anomaly Score ,in, is the gas anomaly score of the vth harmful gas in the ith underground area at the kth moment in the current monitoring period, is the concentration data of the vth harmful gas in the ith underground area at the kth moment in the current monitoring period, is the preset concentration threshold of the vth harmful gas concentration, is the concentration change rate of the vth harmful gas in the ith underground area at the kth moment in the current monitoring period, is the preset concentration change rate threshold of the vth harmful gas concentration, is the number of underground areas, To monitor the number of cycle times, is the amount of harmful gas, i≤ , k≤ , v≤ , and i, k, v, , and All are positive integers.

[0014] According to the present invention, the emergency rescue level is determined according to the working state abnormality score, the temperature abnormality score and the gas abnormality score, including: according to the formula A first condition C1, a second condition C2 and a second condition C3 are obtained, wherein: Score the abnormality of the working status, is the abnormal working status scoring threshold, Score the temperature anomaly, is the temperature anomaly scoring threshold, Score the gas anomaly, is the gas anomaly score threshold; when any one of the first condition C1, the second condition C2 and the second condition C3 is met, the emergency rescue level is determined to be level 1; when any two of the first condition C1, the second condition C2 and the second condition C3 are met, the emergency rescue level is determined to be level 2; when the first condition C1, the second condition C2 and the second condition C3 are all met, the emergency rescue level is determined to be level 3.

[0015] According to a second aspect of the present invention, there is provided an underground emergency rescue monitoring system, comprising: a video frame module, for dividing an underground well into a plurality of underground areas, installing a high-definition camera and an infrared camera in each underground area, respectively, and obtaining high-definition video frames and infrared video frames of each underground area at a plurality of moments in a current monitoring cycle, wherein the high-definition video frames are obtained by real-time videos captured by the high-definition camera, and the infrared video frames are obtained by real-time videos captured by the infrared camera; a working state abnormality scoring module, for determining a working state abnormality score according to high-definition video frames of each underground area at a plurality of moments in a current monitoring cycle; a temperature abnormality scoring module, for determining a temperature abnormality score according to infrared video frames of each underground area at a plurality of moments in a current monitoring cycle and infrared video frames of each underground area at the end of a previous monitoring cycle; a harmful gas concentration data module, for installing a plurality of harmful gas concentration sensors in each underground area, and obtaining a plurality of harmful gas concentration data of each underground area at a plurality of moments in a current monitoring cycle; a gas abnormality scoring module, for determining a gas abnormality score according to the harmful gas concentration data; and an emergency rescue level module, for determining an emergency rescue level according to the working state abnormality score, the temperature abnormality score and the gas abnormality score.

[0016] Technical effect: According to the present invention, through high-definition cameras and infrared cameras, real-time visual data can be provided, and the working status and underground temperature of the staff can be understood more intuitively, thereby improving the ability to identify abnormal conditions underground. At the same time, through multiple harmful gas concentration sensors, the concentration changes of multiple harmful gases can be monitored in real time, and the leakage or abnormal concentration of harmful gases can be discovered in time, thereby improving the safety of underground operations, so that the situation of emergency rescue in the underground can be fully and accurately monitored, and the accuracy of emergency rescue can be improved. The emergency rescue level is automatically determined through the comprehensive evaluation of the abnormal working status score, the abnormal temperature score and the abnormal gas score, which reduces the subjectivity of human judgment, judges the safety status of the underground more scientifically, can quickly generate emergency rescue plans, and improve response efficiency. When determining the abnormal working status score, the posture feature vectors of each staff member in the high-definition video frames at multiple moments of the current monitoring cycle and the posture feature vectors of the preset abnormal postures can be compared to determine the abnormal working status score, which can timely identify the abnormal situation in the working status of the staff, thereby taking emergency rescue measures and improving the safety of underground operations. When determining the temperature anomaly score, the temperature anomaly score can be determined based on the relative difference between the temperature anomaly area of ​​the ith downhole area at the kth moment of the current monitoring cycle and the temperature anomaly area threshold, as well as the historical temperature anomaly area of ​​the ith downhole area at the end of the previous monitoring cycle. The severity of the temperature anomaly condition can be judged by the degree to which the temperature anomaly area exceeds the threshold and the degree of change relative to the end of the previous monitoring cycle. This objectively and accurately describes the temperature anomaly condition in the downhole area, which helps to improve the scientificity, comprehensiveness and objectivity of temperature anomaly monitoring. When determining the gas anomaly score, the gas anomaly score can be determined based on the relative difference between the harmful gas concentration data and the preset concentration threshold, as well as the relative difference between the harmful gas concentration change rate and the preset concentration change rate threshold. The severity of the gas anomaly condition in the downhole area can be objectively and accurately described by the degree to which the harmful gas concentration exceeds the threshold and the rate of change, which helps to improve the scientificity, comprehensiveness and objectivity of temperature anomaly monitoring. When determining the emergency rescue level, the emergency rescue level can be determined by the working status abnormality score, temperature abnormality score and gas abnormality score. That is, a comprehensive assessment of multiple factors such as working status, temperature and gas concentration can fully identify potential safety risks, thereby understanding the current safety status underground and improving the accuracy of emergency rescue. The division of emergency rescue levels is helpful to formulate corresponding emergency response measures and improve the safety of emergency rescue.

[0017] It should be understood that the above general description and the following detailed description are exemplary and explanatory only and do not limit the present invention. Other features and aspects of the present invention will become more apparent from the following detailed description of exemplary embodiments with reference to the accompanying drawings. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings in the following description are only some embodiments of the present invention. For those of ordinary skill in the art, other embodiments can be obtained based on these drawings without creative work.

[0019] Figure 1 A schematic diagram of a process flow of an underground emergency rescue monitoring method according to an embodiment of the present invention is exemplarily shown;

[0020] Figure 2 A block diagram of an underground emergency rescue monitoring system according to an embodiment of the present invention is exemplarily shown. DETAILED DESCRIPTION

[0021] In order to make the purpose, technical solution and advantages of the embodiments of the present invention clearer, the technical solution in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. 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 creative work are within the scope of protection of the present invention.

[0022] The technical solution of the present invention is described in detail with specific embodiments below. The following specific embodiments can be combined with each other, and the same or similar concepts or processes may not be described in detail in some embodiments.

[0023] Figure 1The flowchart of the underground emergency rescue monitoring method according to an embodiment of the present invention is exemplarily shown, and the method comprises: step S101, dividing the underground into multiple underground areas, installing a high-definition camera and an infrared camera in each underground area, and obtaining high-definition video frames and infrared video frames of each underground area at multiple moments in the current monitoring cycle, wherein the high-definition video frame is obtained by the real-time video captured by the high-definition camera, and the infrared video frame is obtained by the real-time video captured by the infrared camera; step S102, determining the abnormal working state score according to the high-definition video frames of each underground area at multiple moments in the current monitoring cycle; step S103, determining the temperature abnormality score according to the infrared video frames of each underground area at multiple moments in the current monitoring cycle and the infrared video frames of each underground area at the end of the previous monitoring cycle; step S104, installing multiple harmful gas concentration sensors in each underground area, and obtaining multiple harmful gas concentration data of each underground area at multiple moments in the current monitoring cycle; step S105, determining the gas abnormality score according to the harmful gas concentration data; step S106, determining the emergency rescue level according to the abnormal working state score, the temperature abnormality score and the gas abnormality score.

[0024] According to the underground emergency rescue monitoring method of the embodiment of the present invention, through high-definition cameras and infrared cameras, real-time visual data can be provided, and the working status and underground temperature of the staff can be more intuitively understood, thereby improving the ability to identify abnormal conditions underground. At the same time, through multiple harmful gas concentration sensors, the concentration changes of multiple harmful gases can be monitored in real time, and the leakage or abnormal concentration of harmful gases can be discovered in time, thereby improving the safety of underground operations, so that the situations requiring emergency rescue in the underground can be fully and accurately monitored, and the accuracy of emergency rescue can be improved. The emergency rescue level is automatically determined through a comprehensive evaluation of the abnormal working status score, the abnormal temperature score, and the abnormal gas score, which reduces the subjectivity of human judgment, more scientifically judges the safety status of the underground, can quickly generate emergency rescue plans, and improve response efficiency.

[0025] According to one embodiment of the present invention, in step S101, each detection cycle can be set to 10 minutes, 20 minutes, etc., and the interval between adjacent moments can be set to 10 seconds, 20 seconds, etc., and the present invention does not limit this. Dividing the underground space into multiple independent areas allows for more sophisticated monitoring and management. In each divided underground area, a high-definition camera and an infrared camera are installed to capture the real-time situation of all scenes in the underground area. The high-definition camera obtains high-definition video frames at multiple moments in the current monitoring cycle, providing a clear image of the working status of the underground staff in real time. At the same time, the infrared camera obtains infrared video frames at multiple moments in the current monitoring cycle, and the underground temperature changes can be dynamically monitored in real time.

[0026] According to one embodiment of the present invention, in step S102, high-definition video frames of each underground area at multiple moments in the current monitoring period are analyzed, which involves using computer vision technology and image processing algorithms to identify key information such as the number and body posture of underground workers, thereby determining the abnormal work status score.

[0027] According to one embodiment of the present invention, step S102 includes: performing feature extraction processing on the areas where each staff member is located in the high-definition video frames at multiple moments in the current monitoring period through the posture feature encoding level of the trained image recognition model to obtain the posture feature vector of each staff member; determining the work status abnormality score based on the posture feature vector of each staff member in the high-definition video frames at multiple moments in the current monitoring period and the posture feature vector of the preset abnormal posture.

[0028] According to one embodiment of the present invention, the image recognition model can be a convolutional neural network model. The posture feature encoding level of the trained image recognition model is used to extract the posture features of each staff member, so as to analyze the posture, action mode, etc. of the staff member, and generate a posture feature vector by encoding. The posture feature vector usually contains the relative positions of the key points of the staff member, for example, the relative positions of the key points at the positions of the staff member's arms, elbows, waist, knees, ankles, etc. relative to the key points of the head. The specific actions and states of the staff member can be described by the posture feature vector. A set of preset posture feature vectors of abnormal postures is set, that is, the postures of the staff member that need emergency rescue, for example, the posture of falling to the ground and twitching, the posture of running away or avoiding danger, etc., which are used to compare with the actual posture feature vector, so as to identify potential abnormal situations. By comparing the posture feature vectors of each staff member in the high-definition video frames at multiple moments of the current monitoring cycle with the preset abnormal posture feature vectors, the abnormal score of the working state is determined.

[0029] According to one embodiment of the present invention, the abnormal working status score is determined based on the posture feature vectors of each worker in the high-definition video frames at multiple moments in the current monitoring period and the posture feature vectors of the preset abnormal postures, including: determining the abnormal working status score according to formula (1): , (1) Among them, is the posture feature vector of the jth worker at the kth moment in the current monitoring period, The posture feature vector of the preset abnormal posture, for The transposed vector of is the number of staff members, To monitor the number of cycle times, is the number of preset abnormal postures, j≤ , k≤ , e≤ , and j, k, e, , and All are positive integers, and max is the maximum value function.

[0030] According to one embodiment of the present invention, in formula (1), The maximum value of the similarity between the posture feature vector of the jth staff member at the kth moment in the current monitoring period and the posture feature vector of the preset abnormal posture can be used to indicate the degree of abnormality of the working state of the jth staff member at the kth moment in the current monitoring period. The larger the value is, the more abnormal the working state of the jth staff member at the kth moment in the current monitoring period is, and the more likely it is that emergency rescue resources will be needed. The various preset abnormal postures may include the above-mentioned postures such as falling to the ground, convulsing, and falling. The present invention does not limit the specific types of abnormal postures. It is the average value of the abnormality degree of the work status of each staff member at multiple moments in the current monitoring period, that is, the work status abnormality score. The higher the work status abnormality score, the more the staff member needs emergency rescue resources, and the lower the work status abnormality score, the more the staff member does not need emergency rescue resources.

[0031] In this way, the abnormal working status score can be determined by comparing the posture feature vectors of each worker in the high-definition video frames at multiple moments in the current monitoring period with the posture feature vectors of the preset abnormal postures. The abnormal situation in the working status of the workers can be identified in time, so that emergency rescue measures can be taken to improve the safety of underground operations.

[0032] According to one embodiment of the present invention, in step S103, the infrared video frames of each underground area at multiple moments in the current monitoring cycle contain the temperature information of each underground area at different time points. The temperature data extracted from the infrared video frames of the current monitoring cycle is compared with the temperature data at the end of the previous monitoring cycle to identify temperature changes and abnormal conditions.

[0033] According to one embodiment of the present invention, step S103 includes: determining a plurality of temperature abnormality pixel points whose corresponding temperatures are higher than a preset temperature threshold value among a plurality of pixel points in the infrared video frames of each downhole area at multiple moments in the current monitoring cycle; performing a connected domain analysis on the plurality of temperature abnormality pixel points to obtain temperature abnormality regions of each downhole area at multiple moments in the current monitoring cycle; obtaining the temperature abnormality region area of ​​each downhole area at multiple moments in the current monitoring cycle based on the temperature abnormality region; determining the temperature abnormality score based on the temperature abnormality region area and the historical temperature abnormality region area in the infrared video frames of each downhole area at the end of the previous monitoring cycle.

[0034] According to one embodiment of the present invention, a plurality of temperature abnormality pixels having temperatures higher than a preset temperature threshold are determined in the infrared video frames of each downhole area at multiple moments in the current monitoring cycle. The preset temperature threshold can be set to be 20% or 30% higher than the temperature in normal air, etc., and the present invention is not limited to this. The connectivity relationship between the plurality of temperature abnormality pixels can be determined to form a connected domain, and the boundary and range of the connected domain can be used as the boundary and range of the temperature abnormality area, wherein the connected domain refers to a collection of pixels with mutual connection or adjacent relationship. According to the identified temperature abnormality area, the area of ​​each temperature abnormality area is calculated, and the calculation of the area can be achieved by counting the number of temperature abnormality pixels constituting the temperature abnormality area, and the number of pixels can be used as the unit. The area of ​​the temperature abnormality area in the infrared video frame of each downhole area at the end of the last monitoring cycle can be used as a benchmark for comparing the abnormal conditions of the current monitoring cycle.

[0035] According to one embodiment of the present invention, the temperature anomaly score is determined based on the temperature anomaly area and the historical temperature anomaly area in the infrared video frame of each downhole area at the end of the last monitoring cycle, including: determining the temperature anomaly score according to formulas (2) and (3): , (2) (3) Among them, is the temperature anomaly score of the ith underground area at the kth moment in the current monitoring period, is the temperature anomaly area of ​​the ith underground area at the kth moment in the current monitoring period, is the temperature anomaly area threshold, is the area of ​​the historical temperature anomaly of the ith underground area at the end of the last monitoring cycle, is the number of underground areas, is the number of monitoring cycle time, i≤ , k≤ , and i, k, and All are positive integers, and max is the maximum value function.

[0036] According to one embodiment of the present invention, in formula (2), when and That is, when the temperature anomaly area of ​​the ith downhole area at the kth moment of the current monitoring cycle is greater than or equal to the temperature anomaly area threshold, and the temperature anomaly area of ​​the ith downhole area at the kth moment of the current monitoring cycle is greater than or equal to the historical temperature anomaly area of ​​the ith downhole area at the end of the previous monitoring cycle, the temperature anomaly score of the ith downhole area at the kth moment of the current monitoring cycle is and The maximum of the two. It is the relative difference between the temperature anomaly area of ​​the ith downhole area at the kth moment in the current monitoring cycle and the temperature anomaly area threshold, indicating the degree to which the temperature anomaly area of ​​the ith downhole area at the kth moment in the current monitoring cycle exceeds the threshold. The larger the relative difference, the greater the degree to which the temperature anomaly area of ​​the ith downhole area at the kth moment in the current monitoring cycle exceeds the threshold, the more serious the temperature anomaly condition, and the higher the temperature anomaly score of the ith downhole area at the kth moment in the current monitoring cycle. It is the relative deviation between the temperature anomaly area of ​​the ith downhole region at the kth moment of the current monitoring cycle and the historical temperature anomaly area of ​​the ith downhole region at the end of the previous monitoring cycle. The larger the relative deviation, the greater the change in the temperature anomaly area of ​​the ith downhole region at the kth moment of the current monitoring cycle relative to the end of the previous monitoring cycle, the more serious the temperature anomaly condition, and the higher the temperature anomaly score of the ith downhole region at the kth moment of the current monitoring cycle. The smaller the relative deviation, the smaller the change in the temperature anomaly area of ​​the ith downhole region at the kth moment of the current monitoring cycle relative to the end of the previous monitoring cycle, that is, the temperature anomaly condition is relatively stable, and the lower the temperature anomaly score of the ith downhole region at the kth moment of the current monitoring cycle. The maximum value of the above two items is taken as the temperature anomaly score of the ith downhole region at the kth moment of the current monitoring cycle. When or That is, when the temperature anomaly area of ​​the ith downhole area at the kth moment of the current monitoring cycle is less than the temperature anomaly area threshold, or the temperature anomaly area of ​​the ith downhole area at the kth moment of the current monitoring cycle is less than the historical temperature anomaly area of ​​the ith downhole area at the end of the previous monitoring cycle, the temperature anomaly score of the ith downhole area at the kth moment of the current monitoring cycle is 0, indicating that the temperature anomaly area of ​​the ith downhole area at the kth moment of the current monitoring cycle does not exceed the threshold and is within the safe range, or the temperature anomaly area is getting smaller relative to the end of the previous monitoring cycle, and the temperature anomaly situation is improving. In formula (3), It is the average value of the temperature anomaly scores of each underground area at multiple moments in the current monitoring period, that is, the temperature anomaly score. The higher the temperature anomaly score, the more serious the temperature anomaly condition in the underground area, and the easier it is to trigger emergency rescue.

[0037] In this way, the temperature anomaly score can be determined based on the temperature anomaly area of ​​the ith downhole area at the kth moment in the current monitoring cycle and the temperature anomaly area threshold, as well as the relative difference from the historical temperature anomaly area of ​​the ith downhole area at the end of the previous monitoring cycle. The severity of the temperature anomaly condition can be judged by the degree to which the temperature anomaly area exceeds the threshold and the degree of change relative to the end of the previous monitoring cycle, thereby objectively and accurately describing the temperature anomaly condition in the downhole area, which helps to improve the scientificity, comprehensiveness and objectivity of temperature anomaly monitoring.

[0038] According to one embodiment of the present invention, in step S104, various types of harmful gas concentration sensors are installed in each underground area to monitor and record the concentration data of harmful gases in real time. For example, carbon monoxide concentration sensors, methane concentration sensors, etc. The harmful gas concentration data reflects the changes in the concentration of harmful gases in each underground area during the monitoring period.

[0039] According to an embodiment of the present invention, in step S105, a gas anomaly score is determined based on the harmful gas concentration data.

[0040] According to one embodiment of the present invention, step S105 includes: fitting the harmful gas concentration data and multiple moments of the current monitoring period to obtain a harmful gas concentration function; determining a harmful gas concentration derivative function based on the harmful gas concentration function; determining a harmful gas concentration change rate based on the harmful gas concentration derivative function; obtaining preset concentration thresholds for multiple harmful gas concentrations; and determining a gas anomaly score based on the harmful gas concentration data, the harmful gas concentration change rate and the preset concentration threshold.

[0041] According to one embodiment of the present invention, the harmful gas concentration data and multiple moments of the current monitoring period are fitted to obtain a harmful gas concentration function for describing the change of the harmful gas concentration over time in the current monitoring period. The harmful gas concentration function is derived to obtain a harmful gas concentration derivative function. Multiple moments of the current monitoring period are substituted into the harmful gas concentration derivative function to determine the rate of change of the harmful gas concentration. The preset concentration threshold of the harmful gas concentration is set based on safety standards and industry specifications, and is used to identify the safety limit of the gas concentration.

[0042] According to an embodiment of the present invention, the gas anomaly score is determined according to the harmful gas concentration data, the harmful gas concentration change rate and the preset concentration threshold, including: determining the gas anomaly score according to formulas (4) and (5): , (4) (5) Among them, is the gas anomaly score of the vth harmful gas in the ith underground area at the kth moment in the current monitoring period, is the concentration data of the vth harmful gas in the ith underground area at the kth moment in the current monitoring period, is the preset concentration threshold of the vth harmful gas concentration, is the concentration change rate of the vth harmful gas in the ith underground area at the kth moment in the current monitoring period, is the preset concentration change rate threshold of the vth harmful gas concentration, is the number of underground areas, To monitor the number of cycle times, is the amount of harmful gas, i≤ , k≤ , v≤ , and i, k, v, , and All are positive integers.

[0043] According to one embodiment of the present invention, in formula (4), when and That is, when the concentration data of the vth harmful gas in the ith downhole area at the kth moment of the current monitoring period is greater than or equal to the preset concentration threshold of the vth harmful gas concentration, and the change rate of the vth harmful gas concentration in the ith downhole area at the kth moment of the current monitoring period is greater than or equal to the preset concentration change rate threshold of the vth harmful gas concentration, the gas anomaly score of the vth harmful gas in the ith downhole area at the kth moment of the current monitoring period is . It is the relative difference between the concentration data of the vth harmful gas in the ith underground area at the kth moment of the current monitoring cycle and the preset concentration threshold of the vth harmful gas concentration, indicating the degree to which the concentration of the vth harmful gas in the ith underground area at the kth moment of the current monitoring cycle exceeds the threshold. The larger the relative difference, the greater the degree to which the concentration of the vth harmful gas in the ith underground area at the kth moment of the current monitoring cycle exceeds the threshold, the more serious the gas anomaly is, and the higher the gas anomaly score of the vth harmful gas in the ith underground area at the kth moment of the current monitoring cycle. It is the relative deviation between the change rate of the vth harmful gas concentration in the ith downhole area at the kth moment in the current monitoring cycle and the preset concentration change rate threshold of the vth harmful gas concentration. The larger the relative deviation is, the faster the concentration of the vth harmful gas in the ith downhole area at the kth moment in the current monitoring cycle is rising, the more serious the gas anomaly is, and the higher the gas anomaly score of the vth harmful gas in the ith downhole area at the kth moment in the current monitoring cycle is. The smaller the relative deviation is, the slower the concentration of the vth harmful gas in the ith downhole area at the kth moment in the current monitoring cycle is rising, that is, the gas anomaly is relatively stable, and the lower the gas anomaly score of the vth harmful gas in the ith downhole area at the kth moment in the current monitoring cycle is. The product of the above two items is taken as the gas anomaly score of the vth harmful gas in the ith downhole area at the kth moment in the current monitoring cycle. When or That is, when the concentration data of the vth harmful gas in the ith underground area at the kth moment of the current monitoring cycle is less than the preset concentration threshold of the vth harmful gas concentration, or the concentration change rate of the vth harmful gas in the ith underground area at the kth moment of the current monitoring cycle is less than the preset concentration change rate threshold of the vth harmful gas concentration, the gas anomaly score of the vth harmful gas in the ith underground area at the kth moment of the current monitoring cycle is 0, indicating that the concentration of the vth harmful gas in the ith underground area at the kth moment of the current monitoring cycle does not exceed the threshold and is at a safe level, or the concentration of the vth harmful gas in the ith underground area at the kth moment of the current monitoring cycle is decreasing, and the gas anomaly condition is improving. In formula (5), It is the average value of the gas anomaly scores of various harmful gases in each underground area at multiple moments in the current monitoring period, that is, the gas anomaly score. The higher the gas anomaly score, the more serious the gas anomaly condition in the underground area, and the easier it is to trigger emergency rescue.

[0044] In this way, the gas anomaly score can be determined based on the relative difference between the harmful gas concentration data and the preset concentration threshold, as well as the relative difference between the harmful gas concentration change rate and the preset concentration change rate threshold. The severity of the gas anomaly condition in the underground area can be objectively and accurately described by the degree to which the harmful gas concentration exceeds the threshold and the rate of change, which helps to improve the scientificity, comprehensiveness and objectivity of temperature anomaly monitoring.

[0045] According to an embodiment of the present invention, in step S106, corresponding emergency measures and response plans may be formulated according to the emergency rescue level, which may include evacuation of on-site personnel, equipment maintenance, increased ventilation, etc.

[0046] According to an embodiment of the present invention, determining the emergency rescue level according to the working state abnormality score, the temperature abnormality score and the gas abnormality score includes: obtaining a first condition C1, a second condition C2 and a second condition C3 according to formula (6), (6) Among them, Score the abnormality of the working status, is the abnormal working status scoring threshold, Score the temperature anomaly, is the temperature anomaly scoring threshold, Score the gas anomaly, is the gas anomaly score threshold; when any one of the first condition C1, the second condition C2 and the second condition C3 is met, the emergency rescue level is determined to be level 1; when any two of the first condition C1, the second condition C2 and the second condition C3 are met, the emergency rescue level is determined to be level 2; when the first condition C1, the second condition C2 and the second condition C3 are all met, the emergency rescue level is determined to be level 3.

[0047] According to one embodiment of the present invention, in formula (6), the first condition C1 indicates that the work state abnormality score is greater than or equal to the work state abnormality score threshold, the staff is in a dangerous state, and emergency rescue is required. The second condition C2 indicates that the temperature abnormality score is greater than or equal to the temperature abnormality score threshold, the underground temperature is not suitable for operation or a fire occurs, and emergency rescue is required. The second condition C3 indicates that the gas abnormality score is greater than or equal to the gas abnormality score threshold, the concentration of harmful gas exceeds the human tolerance range or is at the explosion boundary, and emergency rescue is required.

[0048] According to one embodiment of the present invention, when any one of the above three conditions is met, it is determined to be a level 1 emergency rescue level, indicating that there is an obvious abnormal situation, which requires immediate attention and preliminary emergency measures, such as issuing an alarm to underground workers to notify them of the abnormal situation and prepare to take preliminary measures. When any two of the above three conditions are met at the same time, it is determined to be a level 2 emergency rescue level, indicating that there are multiple more serious abnormal situations, which require more attention and a more comprehensive emergency response plan, such as immediately organizing the orderly evacuation of underground workers, shutting down all dangerous equipment, and sending professional mine rescue teams into the mine. When all three conditions are met, it is determined to be a level 3 emergency rescue level, which is the highest level of emergency response, indicating that there is an extremely serious emergency situation, and the most comprehensive and rapid emergency measures need to be taken immediately, such as immediately blocking the underground dangerous area to prevent untrained or unprotected personnel from entering, and launching a comprehensive emergency rescue operation.

[0049] In this way, the emergency rescue level can be determined by the working status abnormality score, temperature abnormality score and gas abnormality score. That is, the comprehensive evaluation of multiple factors such as working status, temperature and gas concentration can fully identify potential safety risks, thereby understanding the current safety situation underground and improving the accuracy of emergency rescue. The division of emergency rescue levels is helpful to formulate corresponding emergency response measures and improve the safety of emergency rescue.

[0050] According to the underground emergency rescue monitoring method of the embodiment of the present invention, through the high-definition camera and the infrared camera, real-time visual data can be provided, and the working status and underground temperature of the staff can be understood more intuitively, thereby improving the ability to identify abnormal conditions underground. At the same time, through multiple harmful gas concentration sensors, the concentration changes of multiple harmful gases can be monitored in real time, and the leakage or abnormal concentration of harmful gases can be discovered in time, thereby improving the safety of underground operations, so that the situation of emergency rescue in the underground can be fully and accurately monitored, and the accuracy of emergency rescue can be improved. The emergency rescue level is automatically determined through the comprehensive evaluation of the abnormal working state score, the abnormal temperature score and the abnormal gas score, which reduces the subjectivity of human judgment, judges the safety status of the underground more scientifically, can quickly generate emergency rescue plans, and improve response efficiency. When determining the abnormal working state score, the posture feature vectors of each staff member in the high-definition video frames at multiple moments of the current monitoring cycle and the posture feature vectors of the preset abnormal postures can be compared to determine the abnormal working state score, and the abnormal situation in the working state of the staff member can be identified in time, so that emergency rescue measures can be taken to improve the safety of underground operations. When determining the temperature anomaly score, the temperature anomaly score can be determined based on the relative difference between the temperature anomaly area of ​​the ith downhole area at the kth moment of the current monitoring cycle and the temperature anomaly area threshold, as well as the historical temperature anomaly area of ​​the ith downhole area at the end of the previous monitoring cycle. The severity of the temperature anomaly condition can be judged by the degree to which the temperature anomaly area exceeds the threshold and the degree of change relative to the end of the previous monitoring cycle. This objectively and accurately describes the temperature anomaly condition in the downhole area, which helps to improve the scientificity, comprehensiveness and objectivity of temperature anomaly monitoring. When determining the gas anomaly score, the gas anomaly score can be determined based on the relative difference between the harmful gas concentration data and the preset concentration threshold, as well as the relative difference between the harmful gas concentration change rate and the preset concentration change rate threshold. The severity of the gas anomaly condition in the downhole area can be objectively and accurately described by the degree to which the harmful gas concentration exceeds the threshold and the rate of change, which helps to improve the scientificity, comprehensiveness and objectivity of temperature anomaly monitoring. When determining the emergency rescue level, the emergency rescue level can be determined by the working status abnormality score, temperature abnormality score and gas abnormality score. That is, a comprehensive assessment of multiple factors such as working status, temperature and gas concentration can fully identify potential safety risks, thereby understanding the current safety status underground and improving the accuracy of emergency rescue. The division of emergency rescue levels is helpful to formulate corresponding emergency response measures and improve the safety of emergency rescue.

[0051] Figure 2The block diagram of the underground emergency rescue monitoring system according to an embodiment of the present invention is exemplarily shown, and the system includes: a video frame module, which is used to divide the underground into multiple underground areas, install a high-definition camera and an infrared camera in each underground area, and obtain high-definition video frames and infrared video frames of each underground area at multiple moments in the current monitoring cycle, wherein the high-definition video frame is obtained by the real-time video captured by the high-definition camera, and the infrared video frame is obtained by the real-time video captured by the infrared camera; a working state abnormality scoring module, which is used to determine the working state abnormality score according to the high-definition video frames of each underground area at multiple moments in the current monitoring cycle; a temperature abnormality scoring module, which is used to determine the temperature abnormality score according to the infrared video frames of each underground area at multiple moments in the current monitoring cycle and the infrared video frames of each underground area at the end of the previous monitoring cycle; a harmful gas concentration data module, which is used to install multiple harmful gas concentration sensors in each underground area, and obtain multiple harmful gas concentration data of each underground area at multiple moments in the current monitoring cycle; a gas abnormality scoring module, which is used to determine the gas abnormality score according to the harmful gas concentration data; an emergency rescue level module, which is used to determine the emergency rescue level according to the working state abnormality score, the temperature abnormality score and the gas abnormality score.

[0052] It should be understood by those skilled in the art that the embodiments of the present invention described above and shown in the accompanying drawings are only examples and do not limit the present invention. The purpose of the present invention has been fully and effectively achieved. The functional and structural principles of the present invention have been demonstrated and explained in the embodiments, and the embodiments of the present invention may be deformed or modified in any way without departing from the principles.

Claims

1. A method for monitoring underground emergency rescue, characterized in that: include: The underground is divided into multiple underground areas, and a high-definition camera and an infrared camera are respectively installed in each underground area to obtain high-definition video frames and infrared video frames of each underground area at multiple moments in the current monitoring period, wherein the high-definition video frame is obtained by the real-time video shot by the high-definition camera, and the infrared video frame is obtained by the real-time video shot by the infrared camera; the working state abnormality score is determined according to the high-definition video frames of each underground area at multiple moments in the current monitoring period; the temperature abnormality score is determined according to the infrared video frames of each underground area at multiple moments in the current monitoring period and the infrared video frames of each underground area at the end of the previous monitoring period; multiple harmful gas concentration sensors are installed in each underground area to obtain multiple harmful gas concentration data of each underground area at multiple moments in the current monitoring period; the gas abnormality score is determined according to the harmful gas concentration data; the emergency rescue level is determined according to the working state abnormality score, the temperature abnormality score and the gas abnormality score; Among them, according to the infrared video frames of each downhole area at multiple moments in the current monitoring cycle and the infrared video frames of each downhole area at the end of the previous monitoring cycle, the temperature anomaly score is determined, including: determining a plurality of temperature anomaly pixels whose corresponding temperatures are higher than a preset temperature threshold among a plurality of pixel points in the infrared video frames of each downhole area at multiple moments in the current monitoring cycle; performing a connected domain analysis on the plurality of temperature anomaly pixels to obtain the temperature anomaly areas of each downhole area at multiple moments in the current monitoring cycle; according to the temperature anomaly areas, obtaining the temperature anomaly area areas of each downhole area at multiple moments in the current monitoring cycle; according to the temperature anomaly areas, determining the temperature anomaly score according to the temperature anomaly area area and the historical temperature anomaly area areas in the infrared video frames of each downhole area at the end of the previous monitoring cycle; according to the temperature anomaly area area and the historical temperature anomaly area areas in the infrared video frames of each downhole area at the end of the previous monitoring cycle, determining the temperature anomaly score, including: according to the formula , Determining the Temperature Anomaly Score ,in, is the temperature anomaly score of the ith underground area at the kth moment in the current monitoring period, is the temperature anomaly area of ​​the ith underground area at the kth moment in the current monitoring period, is the temperature anomaly area threshold, is the area of ​​the historical temperature anomaly of the ith underground area at the end of the last monitoring cycle, is the number of underground areas, is the number of monitoring cycle time, i≤ , k≤ , and i, k, and are all positive integers, and max is a maximum value function; according to the abnormal working state score, the abnormal temperature score and the abnormal gas score, the emergency rescue level is determined, including: according to the formula A first condition C1, a second condition C2 and a second condition C3 are obtained, wherein: Score the abnormality of the working status, is the abnormal working status scoring threshold, Score the temperature anomaly, is the temperature anomaly scoring threshold, Score the gas anomaly, is the gas anomaly score threshold; when any one of the first condition C1, the second condition C2 and the second condition C3 is met, the emergency rescue level is determined to be level 1; when any two of the first condition C1, the second condition C2 and the second condition C3 are met, the emergency rescue level is determined to be level 2; when the first condition C1, the second condition C2 and the second condition C3 are all met, the emergency rescue level is determined to be level 3.

2. The underground emergency rescue monitoring method according to claim 1, characterized in that: The abnormal working status score is determined based on the high-definition video frames of each underground area at multiple moments in the current monitoring cycle, including: performing feature extraction processing on each staff member in the high-definition video frames at multiple moments in the current monitoring cycle through the posture feature encoding level of the trained image recognition model to obtain the posture feature vector of each staff member; the abnormal working status score is determined based on the posture feature vectors of each staff member in the high-definition video frames at multiple moments in the current monitoring cycle and the posture feature vectors of preset abnormal postures.

3. The underground emergency rescue monitoring method according to claim 2, characterized in that: According to the posture feature vectors of each worker in the high-definition video frames at multiple moments of the current monitoring period and the posture feature vectors of the preset abnormal postures, the abnormal working status score is determined, including: according to the formula Determine the work status abnormality score ,in, is the posture feature vector of the jth worker at the kth moment in the current monitoring period, is the posture feature vector of the preset abnormal posture, for The transposed vector of is the number of staff members, To monitor the number of cycle times, is the number of preset abnormal postures, j≤ , k≤ , e≤ , and j, k, e, , and All are positive integers, and max is the maximum value function.

4. The underground emergency rescue monitoring method according to claim 1, characterized in that: Determine a gas anomaly score based on the harmful gas concentration data, including: fitting the harmful gas concentration data and multiple moments in the current monitoring period to obtain a harmful gas concentration function; determine a harmful gas concentration derivative function based on the harmful gas concentration function; determine a harmful gas concentration change rate based on the harmful gas concentration derivative function; obtain preset concentration thresholds for multiple harmful gas concentrations; and determine a gas anomaly score based on the harmful gas concentration data, the harmful gas concentration change rate, and the preset concentration threshold.

5. The underground emergency rescue monitoring method according to claim 4, characterized in that: According to the harmful gas concentration data, the harmful gas concentration change rate and the preset concentration threshold, a gas anomaly score is determined, including: according to the formula , Determining the Gas Anomaly Score ,in, is the gas anomaly score of the vth harmful gas in the ith underground area at the kth moment in the current monitoring period, is the concentration data of the vth harmful gas in the ith underground area at the kth moment in the current monitoring period, is the preset concentration threshold of the vth harmful gas concentration, is the concentration change rate of the vth harmful gas in the ith underground area at the kth moment in the current monitoring period, is the preset concentration change rate threshold of the vth harmful gas concentration, is the number of underground areas, To monitor the number of cycle times, is the amount of harmful gas, i≤ , k≤ , v≤ , and i, k, v, , and All are positive integers.

6. An underground emergency rescue monitoring system for executing the underground emergency rescue monitoring method according to any one of claims 1 to 5, characterized in that: include: A video frame module is used to divide the underground into multiple underground areas, install a high-definition camera and an infrared camera in each underground area, and obtain high-definition video frames and infrared video frames of each underground area at multiple moments in the current monitoring cycle, wherein the high-definition video frame is obtained by the real-time video captured by the high-definition camera, and the infrared video frame is obtained by the real-time video captured by the infrared camera; a working state abnormality scoring module is used to determine the working state abnormality score according to the high-definition video frames of each underground area at multiple moments in the current monitoring cycle; a temperature abnormality scoring module is used to determine the temperature abnormality score according to the infrared video frames of each underground area at multiple moments in the current monitoring cycle and the infrared video frames of each underground area at the end of the previous monitoring cycle; a harmful gas concentration data module is used to install multiple harmful gas concentration sensors in each underground area to obtain multiple harmful gas concentration data of each underground area at multiple moments in the current monitoring cycle; a gas abnormality scoring module is used to determine the gas abnormality score according to the harmful gas concentration data; an emergency rescue level module is used to determine the emergency rescue level according to the working state abnormality score, the temperature abnormality score and the gas abnormality score.

Images