A safety early warning method and system based on a coal mine sensing device

Abstract

This invention relates to the field of coal mine monitoring and early warning technology, and particularly to a safety early warning method and system based on coal mine sensing equipment. The method includes: collecting equipment characteristics and sensing characteristics of several coal mine sensing devices within a target area at preset time intervals; identifying key coal mine sensing devices based on the equipment characteristics collected at the current time point; determining whether the key coal mine sensing devices are in normal working condition; if the key coal mine sensing devices are in normal working condition, determining the equipment sensing deviation based on the current sensing characteristics and historical sensing characteristics; determining whether the current sensing characteristics meet the early warning standard based on the sensing deviation; if they meet the standard, determining the early warning characteristics based on the current sensing characteristics; and determining a safety early warning strategy for the target area based on the early warning characteristics. This invention can avoid situations where coal mine sensing equipment malfunctions, resulting in false alarms or failures, and can provide timely early warnings of potential risks.

Description

Technical Field

[0001] This invention relates to the field of coal mine monitoring and early warning technology, and in particular to a safety early warning method and system based on coal mine sensing equipment. Background Technology

[0002] Coal mining operations are complex, involving multiple stages such as underground excavation, ventilation, and transportation, and are fraught with various safety hazards, including gas explosions, water inrushes, and roof collapses. The state attaches great importance to coal mine safety and has issued a series of strict policies and regulations, such as the "Coal Mine Safety Regulations," requiring coal mining enterprises to strengthen safety management and improve their safety precautions. Currently, various coal mine sensing devices are widely used to monitor the working environment in real time. While real-time monitoring is possible, these devices have limitations. They are significantly affected by environmental factors and may malfunction or produce false alarms in humid or impurity-laden environments. Furthermore, most current early warning methods rely on threshold settings. Fixed thresholds are set based on safety standards for different gases and environmental parameters. When the data detected by the sensing device exceeds the threshold, an early warning signal is issued. However, this method is relatively simple and cannot consider the trends and correlations of parameter changes. For example, if the gas concentration rises slowly but does not reach the threshold, it may not be able to provide timely warnings of potential risks.

[0003] Chinese patent application publication number CN115822713A discloses a 5G-based coal mine safety early warning system, including a platform and monitoring equipment. The platform includes: a main analysis module, which compares received underground data with standard values ​​specified in relevant regulations to determine the deviation range; if the deviation range exceeds the normal error range, the main analysis module issues an early warning signal; and an alert module, which, upon receiving the early warning signal, sends an alarm to coal mine managers and underground workers. The monitoring equipment detects various underground data and transmits it to the platform via the 5G network, enabling real-time monitoring and comparison of the underground environment, providing early warnings of underground anomalies, and improving production safety.

[0004] Existing technologies have the following problems: While monitoring equipment can monitor environmental data in real time, it may produce false alarms or malfunction if it fails to work properly. Furthermore, the method of simply comparing the deviation range with the standard values ​​specified in relevant regulations and issuing a warning signal when the deviation exceeds the normal error range is too simplistic and fails to consider the trends and correlations of parameter changes, potentially leading to untimely warnings of potential risks. Summary of the Invention

[0005] Therefore, the present invention provides a safety early warning method and system based on coal mine sensing equipment to overcome the problems of existing technologies where monitoring equipment cannot work properly, resulting in false alarms or failures, and where early warning methods are relatively simple and cannot provide timely warnings of potential risks.

[0006] To achieve the above objectives, in one aspect, the present invention provides a safety early warning method based on coal mine sensing equipment, comprising:

[0007] Step S1: Collect the equipment characteristics and sensing characteristics of several coal mine sensing devices in the target area at preset time intervals.

[0008] The equipment features include equipment type, equipment operating voltage, and equipment temperature; the sensing features include gas concentration, carbon monoxide concentration, dust concentration, ambient temperature, and gas flow rate.

[0009] Step S2: Determine the key coal mine sensing devices based on the current equipment characteristics of each coal mine sensing device;

[0010] Step S3: Determine whether the key coal mine sensing device is in normal working condition based on the changes in the device characteristics of the key coal mine sensing device and its corresponding associated coal mine sensing device within a preset time range.

[0011] Step S4: If the key coal mine sensing equipment is in normal working condition, then obtain the current sensing characteristics and historical sensing characteristics of the key coal mine sensing equipment.

[0012] Step S5: Determine the device perception deviation based on the current perception characteristics and historical perception characteristics; determine whether the current perception characteristics meet the warning criteria based on the device perception deviation; if they do, determine the warning characteristics based on the current perception characteristics.

[0013] Step S6: Determine a security warning strategy within the target area based on the warning features.

[0014] Further, step S2 includes:

[0015] Step S21: Cluster the current equipment features of each of the coal mine sensing devices to obtain several cluster sets;

[0016] Step S22: Determine the key cluster set based on the number of device features in each cluster set;

[0017] Step S23: Determine key coal mine sensing devices based on the device characteristics in the key cluster set.

[0018] Further, step S3 includes:

[0019] Step S31: Determine the trend of key feature changes based on the changes in equipment features of the key coal mine sensing equipment within a preset time range;

[0020] Step S32: Determine the trend of change of control features based on the changes in equipment features of the associated coal mine sensing equipment corresponding to the key coal mine sensing equipment within a preset time range;

[0021] The equipment characteristics of the associated coal mine sensing equipment and the key coal mine sensing equipment are in the same cluster set;

[0022] Step S33: Determine whether the key coal mine sensing equipment is in normal working condition based on the changing trends of the key features and the changing trends of the control features.

[0023] Further, step S33 includes:

[0024] Step S331: Determine several mutation nodes based on the changing trends of the key features and the changing trends of the control features;

[0025] Step S332: Determine the trend comparison value between the change trend of the key feature and the change trend of the control feature based on each mutation node;

[0026] Step S333: Compare the trend comparison value with the preset trend comparison value, and determine whether the key coal mine sensing equipment is in normal working condition based on the comparison result;

[0027] If the trend comparison value is greater than or equal to the preset trend comparison value, then the key coal mine sensing device is not in normal working condition.

[0028] If the trend comparison value is less than the preset trend comparison value, then the key coal mine sensing equipment is in normal working condition.

[0029] Further, step S5 includes:

[0030] Step S51: Determine the device perception deviation based on the current perception features and historical perception features;

[0031] Step S52: Compare the device perception deviation with the preset perception deviation, and determine whether the current perception feature meets the warning standard based on the comparison result.

[0032] Further, step S5 includes:

[0033] Step S53: Determine abnormal perception features based on the current perception features and the standard perception features;

[0034] Step S54: Determine several associated sensing features based on the anomaly sensing features;

[0035] Step S55: Determine the warning features based on the correlation between the anomaly perception features and each of the associated perception features;

[0036] Wherein, if the correlation between the abnormality perception feature and each of the associated perception features is a first correlation relationship, then the warning feature is determined to be a first warning feature; if the correlation between the abnormality perception feature and each of the associated perception features is a second correlation relationship, then the warning feature is determined to be a second warning feature.

[0037] Further, step S6 includes:

[0038] If the warning feature is the first warning feature, then the safety warning strategy within the target area is determined to be an emergency safety warning strategy, and the safety warning range is determined based on the number of the associated sensing features, including on-site warning and remote warning;

[0039] If the warning feature is the second warning feature, then the security warning strategy within the target area is determined as a potential security warning strategy, and the degree of security warning is determined based on the abnormal perception feature.

[0040] Further, step S4 includes:

[0041] If the key coal mine sensing equipment is not in normal working condition, an early warning message will be issued.

[0042] Further, step S6 includes:

[0043] The safety warning range is determined based on the comparison between the number of the associated sensing features and the preset number.

[0044] The level of security warning is determined based on the comparison results between the abnormality perception features and their corresponding perception feature standards.

[0045] On the other hand, the present invention also provides a safety early warning system, comprising:

[0046] The information acquisition module is used to collect the equipment characteristics and sensing characteristics of several coal mine sensing devices in the target area at preset time intervals.

[0047] The equipment features include equipment type, equipment operating voltage, and equipment temperature; the sensing features include gas concentration, carbon monoxide concentration, dust concentration, ambient temperature, and gas flow rate.

[0048] The working status determination module is connected to the information acquisition module and is used to determine the key coal mine sensing equipment based on the current equipment characteristics of each coal mine sensing equipment, and to determine whether the key coal mine sensing equipment is in normal working status based on the changes in equipment characteristics of the key coal mine sensing equipment and its corresponding associated coal mine sensing equipment within a preset time range.

[0049] The early warning feature determination module is connected to the information acquisition module and the working status determination module respectively. It is used to acquire the current sensing features and historical sensing features of the key coal mine sensing equipment when the key coal mine sensing equipment is in normal working state, determine the equipment sensing deviation based on the current sensing features and historical sensing features, and determine whether the current sensing features meet the early warning standard based on the equipment sensing deviation. If they meet the standard, the early warning feature is determined based on the current sensing features.

[0050] A safety early warning strategy determination module, which is connected to the early warning feature determination module, is used to determine a safety early warning strategy within the target area based on the early warning features.

[0051] Compared with existing technologies, the advantages of this invention are as follows: This invention identifies key coal mine sensing devices based on the current equipment characteristics of the coal mine sensing equipment, avoiding excessive focus on non-critical equipment and improving the efficiency and accuracy of equipment monitoring. It determines whether the key coal mine sensing devices are in normal working condition based on changes in the equipment characteristics of the key coal mine sensing devices and their corresponding associated coal mine sensing devices, enabling timely confirmation of their normal operation and preventing false alarms or malfunctions. When the key coal mine sensing devices are in normal working condition, it determines whether the current sensing characteristics meet the early warning standards based on the equipment sensing deviation, enabling timely warning of potential risks and avoiding false alarms. When the current sensing characteristics meet the early warning standards, it determines the early warning characteristics based on the current sensing characteristics and then determines the safety early warning strategy for the target area based on the early warning characteristics. Subsequent processing is only triggered when the current sensing characteristics have undergone deviation analysis and are determined to meet the early warning standards, avoiding over-processing of large amounts of data that do not reach the risk level and improving the efficiency and effectiveness of data processing. Determining early warning characteristics based on current perception features allows for clear identification of key factors triggering early warnings. Analyzing these early warning characteristics helps determine appropriate safety early warning strategies, improving the accuracy of safety early warnings and avoiding resource waste.

[0052] Furthermore, this invention identifies key cluster sets through cluster analysis, thereby determining key coal mine sensing equipment, which can improve the targeting and efficiency of monitoring, and can promptly detect sensing equipment exhibiting abnormal conditions.

[0053] Furthermore, this invention determines the trend of key feature changes by analyzing the changes in the equipment characteristics of critical coal mine sensing equipment. This enables real-time monitoring of the equipment characteristics of critical coal mine sensing equipment and allows for determination of the equipment's operational status based on these trend changes. By comparing the trend of key feature changes with the trend of control features, considering the changes in the equipment characteristics of the critical coal mine sensing equipment itself and its associated equipment, a more comprehensive assessment of the critical coal mine sensing equipment's operating status can be achieved. This avoids potential misjudgments that might occur if relying solely on changes in a single equipment feature to determine the equipment's operating status. Changes in certain features of a single piece of equipment may be due to normal influences from other equipment or external factors. By analyzing the trend of changes in the features of associated equipment, it is possible to more accurately distinguish between normal operating changes and malfunctions, thus improving the accuracy of equipment operating status assessment.

[0054] Furthermore, by identifying mutation nodes, this invention can accurately pinpoint the moments when the trends of change in key features and control features change significantly. The trend comparison values ​​determined in this way can improve the accuracy of the comparison, thereby improving the accuracy and efficiency of determining whether key coal mine sensing equipment is in normal working condition.

[0055] Furthermore, this invention determines abnormal sensing features by comparing current sensing features with standard sensing features, which can keenly capture deviations between current sensing features and normal conditions. By determining associated sensing features, it can uncover other potential risk factors closely related to the current anomaly, which helps to comprehensively assess the potential risks of coal mine sensing equipment. Based on the correlation between abnormal sensing features and associated sensing features, it determines early warning features, making the early warning basis more scientific and reasonable, and improving the accuracy of early warning. Attached Figure Description

[0056] Figure 1 This is a flowchart of a safety early warning method based on coal mine sensing equipment according to an embodiment of the present invention;

[0057] Figure 2 This is a logic diagram for determining whether a key coal mine sensing device is in normal working condition, according to an embodiment of the present invention.

[0058] Figure 3 This is a logic diagram for determining whether the current perceived feature meets the warning criteria in an embodiment of the present invention;

[0059] Figure 4 This is a structural block diagram of the safety early warning system according to an embodiment of the present invention. Detailed Implementation

[0060] To make the objectives and advantages of the present invention clearer, the present invention will be further described below with reference to embodiments; it should be understood that the specific embodiments described herein are merely for explaining the present invention and are not intended to limit the present invention.

[0061] Preferred embodiments of the present invention will now be described with reference to the accompanying drawings. Those skilled in the art should understand that these embodiments are merely illustrative of the technical principles of the present invention and are not intended to limit the scope of protection of the present invention.

[0062] It should be noted that in the description of this invention, the terms "upper", "lower", "left", "right", "inner", "outer", etc., which indicate directions or positional relationships, are based on the directions or positional relationships shown in the accompanying drawings. This is only for the convenience of description and is not intended to indicate or imply that the device or element must have a specific orientation, or be constructed and operated in a specific orientation. Therefore, it should not be construed as a limitation of this invention.

[0063] Furthermore, it should be noted that, in the description of this invention, unless otherwise explicitly specified and limited, the terms "installation," "connection," and "linking" should be interpreted broadly. For example, they can refer to a fixed connection, a detachable connection, or an integral connection; they can refer to a mechanical connection or an electrical connection; they can refer to a direct connection or an indirect connection through an intermediate medium; and they can refer to the internal connection of two components. Those skilled in the art can understand the specific meaning of the above terms in this invention according to the specific circumstances.

[0064] Please see Figure 1 The diagram shows a flowchart of a safety early warning method based on coal mine sensing equipment according to an embodiment of the present invention. The present invention provides a safety early warning method based on coal mine sensing equipment, comprising:

[0065] Step S1: Collect the equipment characteristics and sensing characteristics of several coal mine sensing devices in the target area at preset time intervals.

[0066] The equipment features include equipment type, equipment operating voltage, and equipment temperature; the sensing features include gas concentration, carbon monoxide concentration, dust concentration, ambient temperature, and gas flow rate.

[0067] In practice, equipment characteristics also include equipment operating current, equipment material, and measurement range, while sensing characteristics include environmental humidity, mine pressure, oxygen concentration, carbon dioxide concentration, and personnel behavior. By collecting the equipment characteristics and sensing characteristics of coal mine sensing equipment, a comprehensive understanding of the overall environmental conditions and equipment operation status of the coal mine can be achieved.

[0068] It is understandable that the implementers can set a preset time period according to the actual situation. Preferably, the preset time period is set to 10s to 30s.

[0069] Step S2: Determine the key coal mine sensing devices based on the current equipment characteristics of each coal mine sensing device;

[0070] Specifically, step S2 includes:

[0071] Step S21: Cluster the current equipment features of each of the coal mine sensing devices to obtain several cluster sets;

[0072] It is understood that the current equipment characteristics are the equipment characteristics of each coal mine sensing device collected at the current collection time. Those skilled in the art know that any existing method that can cluster the current equipment characteristics falls within the protection scope of this invention, and will not be elaborated here.

[0073] Step S22: Determine the key cluster set based on the number of device features in each cluster set;

[0074] In implementation, clusters with more than a first preset number of equipment features are identified as key clusters. Since the equipment features of each coal mine sensing device are not necessarily consistent, and the number of sensing devices of the same type in coal mines is not unique, clustering can group devices with similar features together. If the number of equipment features is too small, there may be abnormal situations. Therefore, clusters with more than a first preset number of equipment features are identified as key clusters, focusing on the majority of coal mine sensing devices, which can improve the accuracy of subsequent identification of key coal mine sensing devices and early warning features.

[0075] Step S23: Determine key coal mine sensing devices based on the device characteristics in the key cluster set.

[0076] In implementation, the features of each device in the key cluster can be input into the target neural network model to obtain the key coal mine sensing devices output by the target neural network model.

[0077] It is understood that the equipment features of each coal mine sensing device collected from historical data can be clustered to determine several historical key clusters. The equipment features in each historical key cluster are used as training samples, and the historical key coal mine sensing devices corresponding to the equipment features in each historical key cluster are used as sample labels to train the initial neural network model to obtain the target neural network model. Those skilled in the art will understand that any neural network model capable of training key coal mine sensing devices falls within the protection scope of this invention, and will not be elaborated further here.

[0078] This invention identifies key cluster sets through cluster analysis, thereby determining key coal mine sensing equipment. This improves the targeting and efficiency of monitoring and enables timely detection of sensing equipment exhibiting abnormal conditions.

[0079] Step S3: Determine whether the key coal mine sensing device is in normal working condition based on the changes in the device characteristics of the key coal mine sensing device and its corresponding associated coal mine sensing device within a preset time range.

[0080] Please see Figure 2 As shown, this is a logic diagram for determining whether a key coal mine sensing device is in normal working condition according to an embodiment of the present invention; specifically, step S3 includes:

[0081] Step S31: Determine the trend of key feature changes based on the changes in equipment features of the key coal mine sensing equipment within a preset time range;

[0082] In practice, the implementers can set a preset time range according to the actual situation. Preferably, the preset time range is set to 5 to 8 times the preset time period.

[0083] Step S32: Determine the trend of change of control features based on the changes in equipment features of the associated coal mine sensing equipment corresponding to the key coal mine sensing equipment within a preset time range;

[0084] The equipment characteristics of the associated coal mine sensing equipment and the key coal mine sensing equipment are in the same cluster set;

[0085] In implementation, the equipment feature value corresponding to each equipment feature is determined according to the preset feature value reference table. The comprehensive equipment feature value of the key / related coal sensing equipment at each collection time point is determined by summing or averaging the equipment feature values ​​corresponding to each equipment feature. The changing trend of key / control features is determined based on the comprehensive equipment feature values ​​of each collection time point within the preset time range. The corresponding curves are plotted by fitting the data with each collection time point as the horizontal axis and the comprehensive equipment feature value of each collection time point as the vertical axis to obtain the changing trend of key / control features.

[0086] Understandably, implementers can set up preset characteristic value reference tables based on actual conditions or historical data of equipment that has passed qualification inspections. For example, equipment types include environmental monitoring, equipment status monitoring, and personnel behavior detection, with corresponding characteristic values ​​of 1, 2, and 3 respectively; equipment operating voltage is divided into low operating voltage (2V~12V), medium-low operating voltage (12V~24V), and medium-high operating voltage (24V~220V), with corresponding characteristic values ​​of 1~2, 2~3, and 3~4 respectively (the corresponding operating voltage range is determined based on the actual key / reference coal sensing equipment's operating voltage, and the specific equipment characteristic value is determined based on the ratio of the equipment's operating voltage to the operating voltage range, for example, the operating voltage of a gas sensor). If the voltage is 3V, which is a low operating voltage, then the corresponding equipment characteristic value is 1+(3-2) / (12-2)=1.1). The equipment temperature range is -40℃~80℃, and the corresponding equipment characteristic value is 1~2 (the temperature range is determined according to the actual key / comparison coal sensing equipment temperature, and the specific equipment characteristic value is determined according to the ratio of equipment temperature to temperature range. For example, if the gas sensor equipment temperature is 20℃, then its corresponding equipment characteristic value is 1+(20+40) / (80+40)=1.5). Then, if the equipment type of the key sensing equipment at the current acquisition time point is environmental monitoring, the equipment operating voltage is 3V, and the equipment temperature is 20℃, then its corresponding comprehensive equipment characteristic value is 1+1.1+1.5=3.6.

[0087] It is understandable that, based on the equipment characteristics of the key coal mine sensing equipment at the current data collection time and other coal mine sensing equipment in the key cluster, the associated coal mine sensing equipment is determined. The equipment characteristics of the key coal mine sensing equipment are Y1, Y2, ..., Y... j , ..., Y m The key clustering sets the equipment characteristics of coal mine sensing equipment other than key coal mine sensing equipment as E. i,1 E i,2 , ..., E i,j , ..., E i,m Where j = 1, 2, ..., m, i = 1, 2, ..., n, m is the number of equipment features, n is the number of coal mine sensing devices in the key cluster excluding key coal mine sensing devices, and Y j E is the j-th equipment feature among the equipment features of key coal mine sensing equipment. i,j Let J be the j-th equipment feature among the equipment features of the i-th coal mine sensing device in the key cluster set. Then, the matching degree P between the key coal mine sensing device and the equipment feature of the i-th coal mine sensing device in the key cluster set is... i =(∑ m j＝1 Y j ×E i,j ) / (sqrt(∑m j＝1 (Y j ) 2 )×sqrt(∑ m j＝1 (E i,j ) 2 )); sqrt() is the preset square root determination function; if max(P i If ) is greater than P, then max(P) i The associated coal mine sensing equipment is identified as a key coal mine sensing equipment. Here, P is a preset matching degree threshold. The actual implementer can set the preset matching degree threshold according to the actual situation. The larger the preset matching degree threshold value, the higher the matching degree requirement between the key coal mine sensing equipment and the associated coal mine sensing equipment. Preferably, the preset matching degree threshold value range can be set to 0.7 to 0.85.

[0088] Step S33: Determine whether the key coal mine sensing equipment is in normal working condition based on the changing trends of the key features and the changing trends of the control features.

[0089] This invention determines the trend of key feature changes by analyzing the changes in the equipment characteristics of critical coal mine sensing equipment. This enables real-time monitoring of the equipment characteristics of critical coal mine sensing equipment and allows for determination of the equipment's operational status based on these trend changes. By comparing the trend of key feature changes with the trend of control features, considering the changes in the equipment characteristics of the critical coal mine sensing equipment itself and its associated equipment, a more comprehensive assessment of the critical coal mine sensing equipment's operating status can be achieved. This avoids potential misjudgments that might occur if relying solely on changes in a single equipment feature to determine its operating status. Changes in certain features of a single piece of equipment may be due to normal influences from other equipment or external factors. By analyzing the trend of changes in the features of associated equipment, it is possible to more accurately distinguish between normal operating changes and malfunctions, thus improving the accuracy of equipment operating status assessment.

[0090] Specifically, step S33 includes:

[0091] Step S331: Determine several mutation nodes based on the changing trends of the key features and the changing trends of the control features;

[0092] In practice, a mutation node is a point where the integrated equipment characteristic value suddenly changes significantly in the trend of change of key characteristics / the trend of change of control characteristics. It can also be determined based on the slope of the trend of change of key characteristics / the trend of change of control characteristics.

[0093] Step S332: Determine the trend comparison value between the change trend of the key feature and the change trend of the control feature based on each mutation node;

[0094] In implementation, key mutation lists and control mutation lists are determined based on the comprehensive equipment characteristic values ​​corresponding to the changing trends of key characteristics at each mutation node and the changing trends of control characteristics. Based on the key mutation lists GT1, GT2, ..., GT... k , ..., GT g List of control mutations: DT1, DT2, ..., DT k , ..., DT g Where k = 1, 2, ..., g, g is the number of mutation nodes, and GT k DT represents the integrated equipment characteristic value corresponding to the k-th mutation node in the list of critical mutations. k To compare the integrated equipment characteristic value corresponding to the k-th mutation node in the mutation list, the trend comparison value Q = sqrt(∑ g k＝1 (GT k -DT k ) 2 ).

[0095] Step S333: Compare the trend comparison value with the preset trend comparison value, and determine whether the key coal mine sensing equipment is in normal working condition based on the comparison result;

[0096] If the trend comparison value is greater than or equal to the preset trend comparison value, then the key coal mine sensing device is not in normal working condition.

[0097] If the trend comparison value is less than the preset trend comparison value, then the key coal mine sensing equipment is in normal working condition.

[0098] It is understandable that the smaller the trend comparison value, the higher the similarity between the key mutation list and the control mutation list, and the lower the possibility of abnormality in the key coal mine sensing equipment. When the trend comparison value is less than the preset trend comparison value, it means that the key coal mine sensing equipment is in normal working condition. The actual implementers can set the preset trend comparison value according to the actual situation. Preferably, the preset trend comparison value is set to a range of 1 to 3.

[0099] By identifying mutation nodes, this invention can accurately pinpoint the moments when the trends of key feature changes and control feature changes significantly change. The trend comparison values ​​determined in this way can improve the accuracy of the comparison, thereby improving the accuracy and efficiency of determining whether key coal mine sensing equipment is in normal working condition.

[0100] Step S4: If the key coal mine sensing equipment is in normal working condition, then obtain the current sensing characteristics and historical sensing characteristics of the key coal mine sensing equipment.

[0101] Specifically, step S4 includes:

[0102] If the key coal mine sensing equipment is not in normal working condition, an early warning message will be issued.

[0103] Step S5: Determine the device perception deviation based on the current perception characteristics and historical perception characteristics; determine whether the current perception characteristics meet the warning criteria based on the device perception deviation; if they do, determine the warning characteristics based on the current perception characteristics.

[0104] Please see Figure 3 As shown, this is a logic judgment diagram for determining whether the current perceived feature meets the warning criteria in an embodiment of the present invention; specifically, step S5 includes:

[0105] Step S51: Determine the device perception deviation based on the current perception features and historical perception features;

[0106] In practice, the historical and current sensory features are collected at the same time. For example, if the current sensory feature is collected for the third time within a preset time range corresponding to the current time, then the historical sensory features are the sensory features collected for the third time within each preset time range before the current time. By comparing sensory features at the same time, changes in sensory features can be clearly observed, avoiding omissions or misjudgments.

[0107] Understandably, the historical and current perception features are normalized, and the differences between the corresponding perception features are calculated and summed or averaged based on the normalization results to determine the device perception bias.

[0108] Step S52: Compare the device perception deviation with the preset perception deviation, and determine whether the current perception feature meets the warning standard based on the comparison result.

[0109] In implementation, if the equipment sensing deviation is greater than the preset sensing deviation, the current sensing characteristic is determined to meet the warning standard. If it meets the warning standard, it indicates a certain safety risk, requiring a safety warning. If the equipment sensing deviation is less than or equal to the preset sensing deviation, the current sensing characteristic is determined to not meet the warning standard, indicating no safety risk at this time. Implementers can set the preset sensing deviation based on actual conditions or the average sensing deviation of key coal mine sensing equipment that has passed qualification inspections in historical data.

[0110] Specifically, in step S5, determining the warning features based on the current perceived features includes:

[0111] Step S53: Determine abnormal perception features based on the current perception features and the standard perception features;

[0112] During implementation, the current sensing characteristics are compared with the standard sensing characteristics, and the sensing characteristics with the greatest degree of change are identified as abnormal sensing characteristics. Practitioners can determine the standard sensing characteristics based on actual conditions or on the average sensing characteristics of key coal mine sensing equipment that has passed qualification inspections during normal operation, according to historical data.

[0113] Step S54: Determine several associated sensing features based on the anomaly sensing features;

[0114] In implementation, the associated sensing features corresponding to abnormal sensing features are determined based on a pre-set sensing feature association table. Practitioners can determine the associated sensing features for each sensing feature based on actual conditions or several single-factor experiments to set up the pre-set sensing feature association table. For example, changes in ambient temperature affect the physical state and chemical reaction rate of methane. Generally, increased temperature increases the activity of methane molecules, which may accelerate the desorption of methane from coal seams and other media, thus increasing methane concentration. Therefore, methane concentration and ambient temperature are correlated.

[0115] Step S55: Determine the warning features based on the correlation between the anomaly perception features and each of the associated perception features;

[0116] Wherein, if the correlation between the abnormality perception feature and each of the associated perception features is a first correlation relationship, then the warning feature is determined to be a first warning feature; if the correlation between the abnormality perception feature and each of the associated perception features is a second correlation relationship, then the warning feature is determined to be a second warning feature.

[0117] Specifically, step S55 includes:

[0118] If the correlation coefficient between the anomaly perception feature and the associated perception feature is greater than a preset correlation coefficient, then the correlation between the anomaly perception feature and the associated perception feature is determined to be the first correlation relationship;

[0119] If the correlation coefficient between the abnormality perception feature and the associated perception feature is less than or equal to a preset correlation coefficient, then the correlation between the abnormality perception feature and the associated perception feature is determined to be a second correlation relationship.

[0120] In practice, the method for determining the correlation coefficient between anomaly perception features and related perception features is existing technology and will not be elaborated here.

[0121] Understandably, if the correlation coefficient between the abnormal perception feature and the associated perception feature is greater than the preset correlation coefficient, it indicates that there may be abnormalities in a non-unique perception feature. In this case, the probability of a security risk increases, the probability of misjudgment is relatively small, and the degree of danger may be relatively large. Therefore, the warning feature is determined as the first warning feature. If the correlation coefficient between the abnormal perception feature and the associated perception feature is less than or equal to the preset correlation coefficient, it indicates that only the abnormal perception feature may be abnormal. Misjudgment may occur, or the degree of danger may be relatively small. Therefore, the warning feature is determined as the second warning feature.

[0122] In practice, implementers can set a preset correlation coefficient based on the actual situation or the mean of the correlation coefficients between abnormal perception features and associated perception features that have passed the qualification test in historical data. Preferably, the preset correlation coefficient is set to a range of 0.5 to 0.8.

[0123] This invention determines abnormal sensing features by comparing current sensing features with standard sensing features, which can keenly capture deviations between current sensing features and normal conditions. By determining associated sensing features, it can uncover other potential risk factors closely related to the current anomaly, which helps to comprehensively assess the potential risks of coal mine sensing equipment. Based on the correlation between abnormal sensing features and associated sensing features, it determines early warning features, making the basis for early warning more scientific and reasonable, and improving the accuracy of early warning.

[0124] Step S6: Determine a security warning strategy within the target area based on the warning features.

[0125] Specifically, step S6 includes:

[0126] If the warning feature is the first warning feature, then the safety warning strategy within the target area is determined to be an emergency safety warning strategy, and the safety warning range is determined based on the number of the associated sensing features, including on-site warning and remote warning;

[0127] If the warning feature is the second warning feature, then the security warning strategy within the target area is determined as a potential security warning strategy, and the degree of security warning is determined based on the abnormal perception feature.

[0128] Specifically, step S6 includes:

[0129] The safety warning range is determined based on the comparison between the number of the associated sensing features and the preset number.

[0130] The level of security warning is determined based on the comparison results between the abnormality perception features and their corresponding perception feature standards.

[0131] In implementation, if the number of associated sensing features is greater than a preset number, the safety warning range is determined to be an on-site warning, and a warning message is issued. The on-site warning includes an emergency notification to all personnel in the coal mine to evacuate and to shut down the power switches of all equipment. If the number of associated sensing features is less than or equal to the preset number, the safety warning range is determined to be a remote warning, and a warning message is issued. The remote warning includes sending an abnormal alarm to the remote monitoring center, prompting timely maintenance and handling of the abnormal situation.

[0132] During implementation, if the difference between the abnormal sensing feature and its corresponding sensing feature standard is greater than the preset difference, the degree of safety warning is determined to be relatively high, and on-site personnel need to be promptly notified to conduct abnormal analysis and elimination. If the difference between the abnormal sensing feature and its corresponding sensing feature standard is less than or equal to the preset difference, the degree of safety warning is determined to be relatively low, and the corresponding abnormal sensing feature is marked as a key feature and excluded, not recorded in the historical coal mine sensing equipment information, and the coal mine sensing equipment information is re-collected and analyzed.

[0133] It is understood that the perception feature standard is the data corresponding to the abnormal perception features in the standard perception features. The actual implementer can set the preset number according to the actual situation or based on the maximum number of associated perception features corresponding to each perception feature in the preset perception feature association table. Preferably, the preset number is set to 1 / 2 to 2 / 3 of the maximum number of associated perception features corresponding to each perception feature in the preset perception feature association table.

[0134] This invention identifies key coal mine sensing devices by analyzing their current characteristics, avoiding excessive focus on non-critical equipment and improving the efficiency and accuracy of equipment monitoring. It determines whether key coal mine sensing devices are functioning normally based on changes in their characteristics with their corresponding associated devices, ensuring timely detection and preventing false alarms or malfunctions. When key sensing devices are functioning normally, it determines whether current sensing characteristics meet warning standards based on sensing deviations, providing timely warnings of potential risks and avoiding false alarms. When current sensing characteristics meet warning standards, it determines warning features and safety warning strategies for the target area. Subsequent processing is only triggered when current sensing characteristics, after deviation analysis, meet warning standards, avoiding over-processing of large amounts of data that do not meet risk levels and improving data processing efficiency and effectiveness. Determining warning features based on current sensing characteristics clearly identifies key factors triggering warnings. Analyzing warning features to determine safety warning strategies allows for tailored responses to different warning characteristics, improving the accuracy of safety warnings and avoiding resource waste.

[0135] On the other hand, the present invention also provides a safety early warning system, comprising:

[0136] The information acquisition module is used to collect the equipment characteristics and sensing characteristics of several coal mine sensing devices in the target area at preset time intervals.

[0137] The equipment features include several equipment features, the sensing features include several sensing features, the equipment features include equipment type, equipment operating voltage and equipment temperature, and the sensing features include gas concentration, carbon monoxide concentration, dust concentration, ambient temperature and gas flow rate.

[0138] The working status determination module is connected to the information acquisition module and is used to determine the key coal mine sensing equipment based on the current equipment characteristics of each coal mine sensing equipment, and to determine whether the key coal mine sensing equipment is in normal working status based on the changes in equipment characteristics of the key coal mine sensing equipment and its corresponding associated coal mine sensing equipment within a preset time range.

[0139] The early warning feature determination module is connected to the information acquisition module and the working status determination module respectively. It is used to acquire the current sensing features and historical sensing features of the key coal mine sensing equipment when the key coal mine sensing equipment is in normal working state, determine the equipment sensing deviation based on the current sensing features and historical sensing features, and determine whether the current sensing features meet the early warning standard based on the equipment sensing deviation. If they meet the standard, the early warning feature is determined based on the current sensing features.

[0140] A safety early warning strategy determination module, which is connected to the early warning feature determination module, is used to determine a safety early warning strategy within the target area based on the early warning features.

[0141] Specifically, the safety early warning method based on coal mine sensing equipment provided by the present invention can be applied to the above-mentioned safety early warning system to achieve the same technical effect, which will not be elaborated here.

[0142] The technical solution of the present invention has been described above with reference to the preferred embodiments shown in the accompanying drawings. However, it will be readily understood by those skilled in the art that the scope of protection of the present invention is obviously not limited to these specific embodiments. Without departing from the principles of the present invention, those skilled in the art can make equivalent changes or substitutions to the relevant technical features, and the technical solutions after these changes or substitutions will all fall within the scope of protection of the present invention.

Claims

1. A safety early warning method based on coal mine sensing equipment, characterized in that, include: Step S1: Collect the equipment characteristics and sensing characteristics of several coal mine sensing devices in the target area at preset time intervals. The equipment features include equipment type, equipment operating voltage, and equipment temperature; the sensing features include gas concentration, carbon monoxide concentration, dust concentration, ambient temperature, and gas flow rate. Step S2: Determine the key coal mine sensing devices based on the current equipment characteristics of each coal mine sensing device; Step S3: Determine whether the key coal mine sensing device is in normal working condition based on the changes in the device characteristics of the key coal mine sensing device and its corresponding associated coal mine sensing device within a preset time range. Step S4: If the key coal mine sensing equipment is in normal working condition, then obtain the current sensing characteristics and historical sensing characteristics of the key coal mine sensing equipment. Step S5: Determine the device perception deviation based on the current perception characteristics and historical perception characteristics; determine whether the current perception characteristics meet the warning criteria based on the device perception deviation; if they do, determine the warning characteristics based on the current perception characteristics. Step S6: Determine a security warning strategy within the target area based on the warning features; Step S5 includes: Step S53: Determine abnormal perception features based on the current perception features and the standard perception features; Step S54: Determine several associated sensing features based on the anomaly sensing features; Step S55: Determine a warning feature based on the correlation between the anomaly perception feature and each of the associated perception features; wherein, if the correlation between the anomaly perception feature and each of the associated perception features is a first correlation, then the warning feature is determined to be a first warning feature; if the correlation between the anomaly perception feature and each of the associated perception features is a second correlation, then the warning feature is determined to be a second warning feature. Step S55 includes: If the correlation coefficient between the anomaly perception feature and the associated perception feature is greater than a preset correlation coefficient, then the correlation between the anomaly perception feature and the associated perception feature is determined to be the first correlation relationship; If the correlation coefficient between the abnormality perception feature and the associated perception feature is less than or equal to a preset correlation coefficient, then the correlation between the abnormality perception feature and the associated perception feature is determined to be a second correlation relationship.

2. The safety early warning method based on coal mine sensing equipment according to claim 1, characterized in that, Step S2 includes: Step S21: Cluster the current equipment features of each of the coal mine sensing devices to obtain several cluster sets; Step S22: Determine the key cluster set based on the number of device features in each cluster set; Step S23: Determine key coal mine sensing devices based on the device characteristics in the key cluster set.

3. The safety early warning method based on coal mine sensing equipment according to claim 2, characterized in that, Step S3 includes: Step S31: Determine the trend of key feature changes based on the changes in equipment features of the key coal mine sensing equipment within a preset time range; Step S32: Determine the trend of change of control features based on the changes in equipment features of the associated coal mine sensing equipment corresponding to the key coal mine sensing equipment within a preset time range; The equipment characteristics of the associated coal mine sensing equipment and the key coal mine sensing equipment are in the same cluster set; Step S33: Determine whether the key coal mine sensing equipment is in normal working condition based on the changing trends of the key features and the changing trends of the control features.

4. The safety early warning method based on coal mine sensing equipment according to claim 3, characterized in that, Step S33 includes: Step S331: Determine several mutation nodes based on the changing trends of the key features and the changing trends of the control features; Step S332: Determine the trend comparison value between the change trend of the key feature and the change trend of the control feature based on each mutation node; Step S333: Compare the trend comparison value with the preset trend comparison value, and determine whether the key coal mine sensing equipment is in normal working condition based on the comparison result; If the trend comparison value is greater than or equal to the preset trend comparison value, then the key coal mine sensing device is not in normal working condition. If the trend comparison value is less than the preset trend comparison value, then the key coal mine sensing equipment is in normal working condition.

5. The safety early warning method based on coal mine sensing equipment according to claim 4, characterized in that, Step S5 includes: Step S51: Determine the device perception deviation based on the current perception features and historical perception features; Step S52: Compare the device perception deviation with the preset perception deviation, and determine whether the current perception feature meets the warning standard based on the comparison result.

6. The safety early warning method based on coal mine sensing equipment according to claim 5, characterized in that, Step S6 includes: If the warning feature is the first warning feature, then the safety warning strategy within the target area is determined to be an emergency safety warning strategy, and the safety warning range is determined based on the number of the associated sensing features, including on-site warning and remote warning; If the warning feature is the second warning feature, then the security warning strategy within the target area is determined as a potential security warning strategy, and the degree of security warning is determined based on the abnormal perception feature.

7. The safety early warning method based on coal mine sensing equipment according to claim 6, characterized in that, Step S4 includes: If the key coal mine sensing equipment is not in normal working condition, an early warning message will be issued.

8. The safety early warning method based on coal mine sensing equipment according to claim 7, characterized in that, Step S6 includes: The safety warning range is determined based on the comparison between the number of the associated sensing features and the preset number. The level of security warning is determined based on the comparison results between the abnormality perception features and their corresponding perception feature standards.

9. A safety early warning system, which employs the safety early warning method based on coal mine sensing equipment as described in any one of claims 1-8, characterized in that, include: The information acquisition module is used to collect the equipment characteristics and sensing characteristics of several coal mine sensing devices in the target area at preset time intervals. The equipment features include equipment type, equipment operating voltage, and equipment temperature; the sensing features include gas concentration, carbon monoxide concentration, dust concentration, ambient temperature, and gas flow rate. The working status determination module is connected to the information acquisition module and is used to determine the key coal mine sensing equipment based on the current equipment characteristics of each coal mine sensing equipment, and to determine whether the key coal mine sensing equipment is in normal working status based on the changes in equipment characteristics of the key coal mine sensing equipment and its corresponding associated coal mine sensing equipment within a preset time range. The early warning feature determination module is connected to the information acquisition module and the working status determination module respectively. It is used to acquire the current sensing features and historical sensing features of the key coal mine sensing equipment when the key coal mine sensing equipment is in normal working state, determine the equipment sensing deviation based on the current sensing features and historical sensing features, and determine whether the current sensing features meet the early warning standard based on the equipment sensing deviation. If they meet the standard, the early warning feature is determined based on the current sensing features. Wherein, the warning feature is determined based on the correlation between the anomaly perception feature and each of the associated perception features, the anomaly perception feature is determined based on the current perception feature and the standard perception feature, and the associated perception feature is determined based on the anomaly perception feature; If the correlation between the anomaly detection feature and each of the associated detection features is a first correlation, then the warning feature is determined to be a first warning feature; if the correlation between the anomaly detection feature and each of the associated detection features is a second correlation, then the warning feature is determined to be a second warning feature. If the correlation coefficient between the anomaly perception feature and the associated perception feature is greater than a preset correlation coefficient, then the correlation between the anomaly perception feature and the associated perception feature is determined to be the first correlation relationship; If the correlation coefficient between the abnormality sensing feature and the associated sensing feature is less than or equal to a preset correlation coefficient, then the correlation between the abnormality sensing feature and the associated sensing feature is determined to be a second correlation relationship. A safety early warning strategy determination module, which is connected to the early warning feature determination module, is used to determine a safety early warning strategy within the target area based on the early warning features.

Images