A mine roadway roof subsidence quantity monitoring method and system under a complex environment

Abstract

This invention relates to the field of distance measurement technology, specifically to a method and system for monitoring roof subsidence in mine roadways under complex environments. The method involves acquiring subsidence data of the roadway roof at different monitoring points, determining the degree of interference based on abnormal fluctuations in the subsidence data, and determining the state value of different monitoring points based on the distribution of the correlation between the fluctuations of subsidence data between different monitoring points and their adjacent monitoring points. The state value reflects the likelihood that the abnormal subsidence data at a monitoring point is caused by environmental factors. Based on the degree of interference and the state value, a target monitoring point is selected from all different monitoring points. The subsidence data of the target monitoring point is then corrected based on the subsidence data of its adjacent non-target monitoring points. This invention improves the accuracy of subsidence monitoring by correcting subsidence data abnormalities caused by the equipment itself.

Description

Technical Field

[0001] This invention relates to the field of distance measurement technology, specifically to a method and system for monitoring the subsidence of the roof of a mine roadway under complex environments. Background Technology

[0002] As mineral resource extraction extends into deeper and more complex geological conditions, the deep mining environment differs fundamentally from that of shallow mining. The increasing ground stress with depth creates a significant high-stress concentration effect. This, coupled with the intense disturbance of the original stress field of the rock mass during mining, results in an extremely complex stress state in the rock mass surrounding the tunnel, making it highly susceptible to the transformation from elastic to plastic deformation. Simultaneously, deep strata are often accompanied by complex geological structures such as faults and joints. The surrounding rock itself has poor integrity and a fractured structure. Mining disturbance further exacerbates the expansion of rock fissures, causing the surrounding rock to exhibit significant softening characteristics and a substantial decrease in bearing capacity. The combined effects of high stress concentration, fractured and softened surrounding rock, and groundwater erosion make tunnel roof subsidence a core hidden danger that triggers geological disasters such as collapses and spalling, directly threatening the safety of underground workers and the continuity of mining operations.

[0003] Currently, monitoring of roof subsidence in mine roadways mainly relies on two types of technologies: traditional mechanical monitoring and sensor-based monitoring. Sensor-based monitoring enables automated data acquisition and remote real-time transmission, significantly reducing manual intervention, improving monitoring efficiency and timeliness, and offering higher measurement accuracy. It can capture minute displacement deformations and dynamic changes, and supports simultaneous networking of multiple monitoring points, facilitating the construction of a comprehensive monitoring system. However, due to complex environments such as deep, high-stress conditions, abundant groundwater, and fractured surrounding rock, it is susceptible to electromagnetic interference, moisture corrosion, and vibration impacts. This leads to insufficient stability of the monitoring equipment itself, resulting in anomalies such as signal attenuation, data transmission delays or losses, ultimately causing inaccurate monitoring of roof subsidence in mine roadways. Summary of the Invention

[0004] To address the aforementioned technical problems caused by the instability of monitoring equipment due to complex environmental conditions, leading to signal attenuation, data transmission delays or losses, and consequently inaccurate monitoring of roof subsidence in mine roadways, this invention aims to provide a method and system for monitoring roof subsidence in mine roadways under complex environments. The specific technical solution adopted is as follows:

[0005] In a first aspect, the present invention provides a method for monitoring roof subsidence in mine roadways under complex environments, comprising the following steps:

[0006] Obtain data on the subsidence of the tunnel roof at different monitoring points;

[0007] Based on the abnormal fluctuations in the subsidence data at different monitoring points, the degree of interference with the subsidence data is determined, and the degree of interference is used to reflect the abnormal extent of the interference with the subsidence data.

[0008] Based on the distribution of the fluctuation correlation of subsidence data between different monitoring points and their adjacent monitoring points, the state values ​​of different monitoring points are determined. The state values ​​are used to reflect the possibility that the abnormal subsidence data of the monitoring points is caused by environmental factors.

[0009] Based on the degree of interference and the state value, target monitoring points are selected from all different monitoring points. The target monitoring point refers to the monitoring point where the abnormality of the subsidence data is caused by environmental factors and the subsidence data needs to be corrected.

[0010] The subsidence data of the target monitoring point is corrected based on the subsidence data of the adjacent non-target monitoring points of the target monitoring point.

[0011] In conjunction with the first aspect above, in some possible implementations, determining the degree of interference with the subsidence data based on abnormal fluctuations in subsidence data at different monitoring points includes:

[0012] Based on the differences between adjacent data points in the local data segment where each data point in the sinking data is located, the abnormality of each data point in the sinking data is determined, and the abnormality is used to reflect the degree of abnormality of the corresponding data point.

[0013] The degree of interference in the subsidence data is determined based on the difference in the degree of anomaly between adjacent data points in the subsidence data.

[0014] In conjunction with the first aspect mentioned above, in some possible implementations, the state values ​​of different monitoring points are determined based on the distribution of the fluctuation correlation of subsidence data between different monitoring points and their adjacent monitoring points, including:

[0015] Determine the difference in the degree of interference of subsidence data between different monitoring points and their adjacent monitoring points;

[0016] Based on the difference value and the difference in the trend of the subsidence data between different monitoring points and their adjacent monitoring points, the correlation of the changes in the subsidence data between different monitoring points and their adjacent monitoring points is determined. The correlation of changes is used to reflect the degree of correlation between the changes in the subsidence data between different monitoring points and their adjacent monitoring points.

[0017] On the side where adjacent monitoring points are located, the state values ​​of different monitoring points are determined based on the correlation of subsidence data changes between several monitoring points and their adjacent monitoring points.

[0018] In conjunction with the first aspect above, in some possible implementations, based on the difference value and the difference in the trend of subsidence data between different monitoring points and their neighboring monitoring points, the correlation of subsidence data changes between different monitoring points and their neighboring monitoring points is determined, including:

[0019] Determine the DTW distance of subsidence data between different monitoring points and their adjacent monitoring points;

[0020] The difference value and the DTW distance are fused, and the fusion result is subjected to negative correlation normalization to obtain the correlation of subsidence data changes between different monitoring points and their neighboring monitoring points.

[0021] In conjunction with the first aspect mentioned above, in some possible implementations, on the side where adjacent monitoring points are located, the state values ​​of different monitoring points are determined based on the correlation of subsidence data changes between several monitoring points and their adjacent monitoring points, including:

[0022] In the extension direction on the side where the adjacent monitoring points are located, the change correlation sequence is determined by taking the change correlation of the subsidence data between different monitoring points and their adjacent monitoring points as the starting point of the sequence.

[0023] By integrating all the change correlations in the change correlation sequence, the state values ​​of different monitoring points are determined.

[0024] In conjunction with the first aspect above, in some possible implementations, based on the degree of interference and the state value, the target monitoring point is selected from all different monitoring points, including:

[0025] By combining the degree of interference and the state value, the necessity of correction for the subsidence data at different monitoring points is determined. The necessity of correction is used to reflect the degree to which the subsidence data at the monitoring points needs to be corrected.

[0026] The necessity of correction is compared with a set threshold for the necessity of correction, and the monitoring point corresponding to the point where the necessity of correction is greater than the set threshold for the necessity of correction is taken as the target monitoring point.

[0027] In conjunction with the first aspect above, in some possible implementations, the subsidence data of the target monitoring point is corrected based on the subsidence data of adjacent non-target monitoring points, including:

[0028] Based on the degree of anomaly of each data point in the subsidence data of adjacent non-target monitoring points of the target monitoring point, and the state value of adjacent non-target monitoring points of the target monitoring point, the correction weight of each data point in the subsidence data of adjacent non-target monitoring points of the target monitoring point is determined.

[0029] The data points at the same time in the subsidence data of adjacent non-target monitoring points of the target monitoring point are weighted and accumulated using the correction weight to obtain the subsidence correction value of the target monitoring point at each time.

[0030] Based on the subsidence correction value, the corrected subsidence data of the target monitoring point is obtained.

[0031] In conjunction with the first aspect above, in some possible implementations, the method further includes: conducting collapse risk monitoring based on the corrected subsidence data of the target monitoring point and the subsidence data of non-target monitoring points outside the target monitoring point.

[0032] In conjunction with the first aspect mentioned above, collapse risk monitoring can be implemented in several possible ways, including:

[0033] Based on the corrected subsidence data of the target monitoring points, the state values ​​of the target monitoring points are redefined.

[0034] Collapse risk monitoring is conducted based on the status values ​​of the newly determined target monitoring points and the status values ​​of non-target monitoring points outside the target monitoring points.

[0035] Secondly, the present invention also provides a monitoring device for roof subsidence in mine roadways under complex environments, the device comprising:

[0036] The data acquisition module is used to acquire data on the subsidence of the roadway roof at different monitoring points;

[0037] The anomaly analysis module is used to determine the degree of interference with the subsidence data based on the abnormal fluctuations of the subsidence data at different monitoring points. The degree of interference reflects the degree of abnormality of the subsidence data being disturbed.

[0038] The status analysis module is used to determine the status value of different monitoring points based on the distribution of the fluctuation correlation of the subsidence data between different monitoring points and their adjacent monitoring points. The status value is used to reflect the possibility that the abnormal subsidence data of the monitoring points is caused by environmental factors.

[0039] The monitoring point screening module is used to screen out target monitoring points from all different monitoring points based on the degree of interference and the state value. The target monitoring point refers to the monitoring point that needs to be corrected for the subsidence data.

[0040] The data correction module is used to correct the subsidence data of the target monitoring point based on the subsidence data of adjacent non-target monitoring points.

[0041] Thirdly, the present invention also provides a monitoring system for roof subsidence in mine roadways under complex environments, comprising a memory and a processor. The memory is used to store executable computer program code, and the processor is used to call and run the executable computer program code from the memory, causing the system to perform a method for monitoring roof subsidence in mine roadways under complex environments, as described in the first aspect or any possible implementation thereof.

[0042] Fourthly, the present invention also provides a computer program product comprising: computer program code, which, when run on a computer, causes the computer to execute a method for monitoring the roof subsidence of a mine roadway under complex conditions, as described in the first aspect or any possible implementation thereof.

[0043] Fifthly, the present invention also provides a computer-readable storage medium storing computer program code, which, when executed on a computer, causes the computer to perform a method for monitoring the roof subsidence of a mine roadway under complex conditions, as described in the first aspect or any possible implementation thereof.

[0044] This invention has the following beneficial effects: By acquiring subsidence data of the roadway roof at different monitoring points, a data foundation for subsidence monitoring is obtained; during the monitoring process, normal subsidence data should show a smooth trend, therefore, abnormal fluctuations in subsidence data at different monitoring points are analyzed to determine the degree of interference with the subsidence data, which reflects the degree of abnormality in the subsidence data; if the abnormal subsidence data is caused by environmental factors (such as roof subsidence), it will be reflected in the data of multiple sensors, therefore, in order to determine whether the abnormal subsidence data at the monitoring point is due to environmental factors... The issue stems from the instability of the sensor itself. This invention analyzes the distribution of fluctuations in subsidence data between different monitoring points and their neighboring points, determining the state values ​​of different monitoring points. These state values ​​reflect the likelihood that the subsidence data anomalies are caused by environmental factors. Based on the degree of interference and the state values, target monitoring points are selected from all different monitoring points whose subsidence data anomalies are caused by environmental factors and require subsidence data correction. The subsidence data of the target monitoring point is then corrected based on the subsidence data of its neighboring non-target monitoring points. This invention effectively improves the accuracy of subsidence monitoring by correcting subsidence data anomalies caused by the instability of the equipment itself. Attached Figure Description

[0045] To more clearly illustrate the technical solutions and advantages in the embodiments of the present invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0046] Figure 1 This is a flowchart illustrating the steps of a method for monitoring roof subsidence in mine roadways under complex environments, according to an embodiment of the present invention.

[0047] Figure 2 This is a flowchart illustrating the steps for determining the degree of interference in subsidence data according to an embodiment of the present invention.

[0048] Figure 3 This is a flowchart illustrating the steps for determining the state values ​​of different monitoring points according to an embodiment of the present invention.

[0049] Figure 4 This is a flowchart illustrating the steps for selecting target monitoring points according to an embodiment of the present invention.

[0050] Figure 5 This is a flowchart illustrating the steps of correcting the subsidence data of the target monitoring point according to an embodiment of the present invention.

[0051] Figure 6 This is a schematic diagram of a monitoring device for monitoring the subsidence of the roof of a mine roadway in a complex environment, according to an embodiment of the present invention.

[0052] Figure 7 This is a schematic diagram of a mine roadway roof subsidence monitoring system under complex conditions, according to an embodiment of the present invention. Detailed Implementation

[0053] To clearly illustrate the technical features of this solution, the invention will be described in detail below through specific embodiments and in conjunction with the accompanying drawings.

[0054] Embodiments of the present invention will now be described in more detail with reference to the accompanying drawings. While some embodiments of the invention are shown in the drawings, it should be understood that the invention can be implemented in various forms and should not be construed as limited to the embodiments set forth herein. Rather, these embodiments are provided to provide a more thorough and complete understanding of the invention. It should be understood that the accompanying drawings and embodiments are for illustrative purposes only and are not intended to limit the scope of protection of the invention.

[0055] It should be understood that the various steps described in the method embodiments of the present invention may be performed in different orders and / or in parallel. Furthermore, the method embodiments may include additional steps and / or omit the steps shown. The scope of the present invention is not limited in this respect.

[0056] The term "comprising" and its variations as used herein are open-ended inclusions, meaning "including but not limited to". The term "based on" means "at least partially based on". The term "one embodiment" means "at least one embodiment"; the term "another embodiment" means "at least one additional embodiment"; the term "some embodiments" means "at least some embodiments". Definitions of other terms will be given in the description below.

[0057] It should be noted that the concepts of "first" and "second" mentioned in this invention are only used to distinguish different devices, modules or units, and are not used to limit the order of functions performed by these devices, modules or units or their interdependencies.

[0058] Although operations or steps are described in a specific order in the accompanying drawings in the embodiments of the present invention, this should not be construed as requiring these operations or steps to be performed in the specific order or serial order shown, or requiring all of the shown operations or steps to be performed to obtain the desired result. In the embodiments of the present invention, these operations or steps may be performed serially; they may be performed in parallel; or a portion of these operations or steps may be performed.

[0059] Furthermore, it is understood that the data involved in the technical solutions of this invention (including but not limited to the data itself, the acquisition or use of the data) shall comply with the requirements of relevant laws, regulations and related provisions. Unless otherwise defined, all technical and scientific terms used in this invention have the same meaning as commonly understood by one of ordinary skill in the art to which this invention pertains, and all parameters or indicators in the formulas involved in this invention are normalized values ​​that have eliminated the influence of dimensions.

[0060] First, the application scenario of this invention will be explained. After tunnel excavation, the stress balance of the original rock strata is broken, and the surrounding rock will undergo continuous deformation and displacement over time. Roof subsidence is one of the most significant and dangerous phenomena. By systematically monitoring the subsidence, the stability and activity patterns of the roof can be grasped in real time. The sensor monitoring method monitors the subsidence of the tunnel roof by deploying an automated, real-time monitoring system with electronic sensors. The specific process is as follows: Displacement sensors (such as high-precision laser rangefinders or wire-type displacement sensors) are installed at specific monitoring points on the tunnel roof and floor. When the roof subsides, the distance between the roof measuring point and the floor reference point will shorten. The sensor will capture this minute distance change in real time and convert it into an electrical signal. Then, the electrical signal is analyzed to determine the degree of subsidence. Once the subsidence or subsidence speed exceeds a preset safety threshold, the system will automatically issue an alarm.

[0061] Sensor monitoring can capture subtle dynamic changes in the roof through continuous monitoring, greatly improving the timeliness of early warning and providing high data accuracy, avoiding reading errors that may occur with manual measurement. However, in complex environments such as deep high stress, abundant groundwater, and fractured surrounding rock, the sensors are susceptible to electromagnetic interference, moisture corrosion, and vibration impact, leading to insufficient stability of the sensor equipment itself. This can result in signal attenuation, data transmission delays or losses, and consequently, inaccurate monitoring.

[0062] To address the aforementioned issues, this invention provides a method and system for monitoring roof subsidence in mine roadways under complex environments. By acquiring subsidence data from different monitoring points, analyzing the degree of interference affecting the subsidence data at each point, and combining the correlation of subsidence data fluctuations between different monitoring points and their adjacent points, the system determines the state values ​​of different monitoring points. Based on the degree of interference and the state values, target monitoring points whose subsidence data is abnormal due to the instability of the sensor equipment itself are selected, and the subsidence data of the target monitoring points is corrected, thereby improving the accuracy of monitoring roof subsidence in mine roadways.

[0063] The following will describe in detail, with reference to the accompanying drawings, a method and system for monitoring roof subsidence in mine roadways under complex environments provided by an embodiment of the present invention.

[0064] Figure 1 This diagram illustrates the basic flow of a method for monitoring roof subsidence in mine roadways under complex environments, as provided in an embodiment of the present invention. Figure 1 As shown, the method specifically includes the following steps:

[0065] Step S100: Obtain the subsidence data of the roadway roof at different monitoring points.

[0066] The essence of roof subsidence monitoring is to monitor the displacement change of the roadway roof relative to the floor. Therefore, displacement sensors, such as high-precision laser rangefinders or wire-type displacement sensors, are installed at specific monitoring points on the roadway roof or floor. All sensors synchronously collect the subsidence amount of the corresponding monitoring points according to a set frequency, thereby obtaining the subsidence amount data of the roadway roof at different monitoring points. This subsidence amount data refers to the distance data between different monitoring points of the roof and the reference point of the floor.

[0067] In a specific example, the steps to obtain the subsidence data of the roadway roof at different monitoring points are as follows:

[0068] First, based on factors such as geological conditions, tunnel purpose, and the scope of mining impact, determine the location, density, and sensor type of monitoring points. Drill and fix the sensors at the selected monitoring point locations, ensuring installation quality. For example, for key monitoring areas, monitoring points can be arranged at a high density and evenly between the roof and floor, and high-precision laser rangefinders can be installed at these points. These laser rangefinders calculate distance changes by measuring the round-trip time of the laser beam. For non-key monitoring areas, monitoring points can be arranged at a low density, and lower-cost wire-type displacement sensors can be installed at these points. One end of the wire in the wire-type displacement sensor is fixed to the roof, and the sensor body is fixed to the floor. When the roof sinks, pulling the wire activates the sensor, and the internal potentiometer or encoder outputs a displacement signal.

[0069] Secondly, data acquisition substations and transmission networks are set up, and the sinking data is collected, transmitted, and stored. Sensors at each monitoring point automatically collect data at a preset frequency (e.g., once per minute), which is then transmitted in real-time to the server at the ground monitoring center via the transmission network and stored in the database. The transmission network can employ wired transmission, wireless transmission, intrinsically safe mining Wi-Fi / 4G / 5G, LoRa, ZigBee, or a hybrid network, depending on the specific circumstances. Wired transmission uses communication cables (such as RS485, CAN bus, or Ethernet) to directly connect the sensors to the data acquisition substations. Its advantages are stability, reliability, and low latency; its disadvantages are complex wiring and susceptibility to mining damage. Wireless transmission is more suitable for the complex and lengthy environment of mine roadways. When using intrinsically safe mining Wi-Fi / 4G / 5G, base stations are deployed in the main roadways, and sensor data is transmitted wirelessly. Low-power wide-area network technologies such as LoRa and ZigBee have low power consumption and long transmission distances, making them ideal for scenarios with a large number of sensor nodes. When using hybrid transmission, data acquisition substations are set up in the tunnel. The substations collect data from nearby sensors via wired means and then transmit it to the ground central station via wireless or wired backbone network.

[0070] Step S200: Based on the abnormal fluctuations in the subsidence data at different monitoring points, determine the degree of interference with the subsidence data.

[0071] The degree of interference is used to reflect the degree of abnormality in the subsidence data caused by interference.

[0072] During monitoring, normal settlement data should exhibit a smooth trend. Abnormal fluctuations in settlement data at different monitoring points are detected, and the degree of interference with the settlement data is quantified based on the severity of these fluctuations. For example, the greater the difference in fluctuations between local data points in the settlement data, the higher the degree of abnormal interference in the settlement data is likely to be.

[0073] In one possible implementation, such as Figure 2 As shown, in step S200, based on the abnormal fluctuations in the subsidence data at different monitoring points, the degree of interference with the subsidence data is determined, including:

[0074] Step S201: Based on the differences between adjacent data points in the local data where each data point in the subsidence data is located, determine the anomaly of each data point in the subsidence data.

[0075] Anomalies are used to reflect the degree of anomalies of the corresponding data points.

[0076] For example, the subsidence data of any monitoring point is taken as the target data, and any data point in the target data is taken as the target data point. Five data points are taken from each of the left and right neighboring areas of the target data point to form a local data segment containing the target data point. The trend of the local data segment containing the target data point is calculated to obtain the anomaly of the target data point. The calculation formula is as follows:

[0077] ;

[0078] In the formula: This indicates that when the subsidence data of any monitoring point is used as the target data, the first value in the target data is... Anomalies in individual target data points; Indicates the first in the target data In the local data segment where the target data point is located, the first... The magnitude of each data point Indicates the first In the neighborhood data of the nth target data point The magnitude of each data point Indicates the first in the target data The total number of data points in the local data segment where each target data point is located.

[0079] In the above formula, when The larger the value, the greater the magnitude of data change, and the greater the likelihood of anomalies in the target data point. Data points with greater anomalies indicate a potentially greater impact during data collection. Therefore, it is necessary to analyze the correlation of anomalies in the time series data points to determine the degree of interference affecting the current target data.

[0080] Step S202: Determine the degree of interference in the subsidence data based on the difference in the degree of anomaly between adjacent data points in the subsidence data.

[0081] For example, the subsidence data of any monitoring point is taken as the target data, and any data point in the target data is taken as the target data point. The difference in anomalies between adjacent target data points in the target data is calculated and its absolute value is taken. The larger the value, the more likely there are abnormal data points in the continuous data. Then, the absolute values ​​of the differences corresponding to all target data points are summed and the average value is taken to represent the degree of interference of the current target data, and is denoted as . .

[0082] Therefore, the degree of interference with the subsidence data at different monitoring points can be determined.

[0083] Step S300: Based on the distribution of the fluctuation correlation of subsidence data between different monitoring points and their adjacent monitoring points, determine the state value of different monitoring points.

[0084] Among them, the status value is used to reflect the possibility that the abnormality of the subsidence data of the monitoring point is caused by environmental factors.

[0085] Anomalies in subsidence data can be influenced by both environmental factors and the stability of the sensor equipment itself. By comparing the correlation of fluctuations in subsidence data from different monitoring points within the same monitoring area, it can be determined whether the anomalies are caused by environmental factors (such as roof subsidence) or by the instability of the sensor equipment itself. If the anomalies are due to environmental factors, they will be reflected in the data from multiple sensors. For example, when anomalies occur in the tunnel roof subsidence, practical experience shows that there is a prominent point of subsidence that extends outwards, resulting in changes in the sensor data for that area.

[0086] Therefore, analyzing the correlation of subsidence data fluctuations between a monitoring point and its adjacent monitoring points reveals that a greater correlation indicates a greater degree of influence from the environment (i.e., tunnel roof subsidence) on the abnormal data collected by the sensor at that location. In this case, the state value of the monitoring point will be larger, and the subsidence data anomaly at that monitoring point will require less correction. Conversely, a smaller correlation indicates that the subsidence data anomaly at the current monitoring point is more likely caused by its own equipment malfunction. In this case, the state value of the monitoring point will be smaller, and the subsidence data anomaly at that monitoring point will likely require correction.

[0087] In one possible implementation, such as Figure 3 As shown, in step S300, based on the distribution of the fluctuation correlation of subsidence data between different monitoring points and their adjacent monitoring points, the state values ​​of different monitoring points are determined, including:

[0088] Step S301: Determine the difference in the degree of interference between different monitoring points and their adjacent monitoring points in the subsidence data.

[0089] For example, the subsidence data of any monitoring point can be used as the target data. Obtain the target data The degree of interference, and denoted as Simultaneously, the monitoring data of the neighboring monitoring points of any given monitoring point are used as the target neighborhood data. Obtain target neighborhood data The degree of interference, and recorded as Then, the degree of interference is calculated. and absolute value of the difference The absolute value of the difference The degree of interference of the target data The degree of interference with the target neighborhood data The difference value.

[0090] Step S302: Based on the difference value and the difference in the trend of subsidence data between different monitoring points and their neighboring monitoring points, determine the correlation of subsidence data changes between different monitoring points and their neighboring monitoring points.

[0091] Among them, the correlation of changes is used to reflect the degree of correlation between the changes in subsidence data between different monitoring points and their adjacent monitoring points.

[0092] The smaller the difference in the degree of interference in the subsidence data between a monitoring point and its neighboring monitoring points, and the smaller the difference in the trend of subsidence data change, the higher the correlation between the subsidence data changes of that monitoring point and its neighboring monitoring points. Therefore, the correlation between the subsidence data changes of different monitoring points and their neighboring monitoring points can be determined. A higher correlation indicates a greater degree of environmental influence on the subsidence data anomalies of the corresponding monitoring location sensor.

[0093] For example, the DTW distance of subsidence data between different monitoring points and their adjacent monitoring points is determined. That is, the subsidence data of any monitoring point is used as the target data. The monitoring data of the neighboring monitoring points of any given monitoring point are used as the target neighborhood data. At that time, determine the target data and target neighborhood data The DTW distance between them is calculated. The difference values ​​and DTW distances are fused, and the fusion result is negatively correlated and normalized to obtain the correlation between the changes in subsidence data between different monitoring points and their neighboring monitoring points. That is, by fusing target data... and target neighborhood data Difference between Distance from DTW, obtaining target data and target neighborhood data The correlation between the changes is calculated using the following formula:

[0094]

[0095] In the formula: This indicates that the subsidence data at any monitoring point will be used as the target data. The monitoring data of the neighboring monitoring points of any given monitoring point are used as the target neighborhood data. At that time, target data With target neighborhood data Correlation between changes; Represents target data The degree of interference; Represents target neighborhood data The degree of interference; DTW distance between them This represents an exponential function with base e, used to express differences. The fusion results of the distance to DTW are negatively correlated and normalized. When the difference value The smaller the distance to DTW, the stronger the target data. With target neighborhood data The higher the correlation between the changes in the subsidence data, the greater the corresponding correlation. The larger the value, the better.

[0096] Step S303: On the side where the adjacent monitoring points are located, based on the correlation of the changes in the subsidence data between several monitoring points and their adjacent monitoring points, determine the state value of different monitoring points.

[0097] When a tunnel area faces a risk of collapse, the tunnel roof will extend outward from a central point, forming a continuous deformation zone. Therefore, when the subsidence data at a certain monitoring point shows an abnormal change, the subsidence data at its neighboring monitoring points will also show a corresponding change. Thus, based on the correlation of subsidence data changes between several monitoring points and their neighboring monitoring points along the same side, the state value of different monitoring points is determined to reflect the possibility that the abnormal subsidence data of the corresponding monitoring point is caused by environmental factors. Here, the direction of the line connecting the monitoring point to its neighboring monitoring points refers to the direction of the line extending towards the side of the neighboring monitoring point. When the abnormal subsidence data of a monitoring point is not caused by environmental factors, i.e., tunnel roof subsidence, the correlation of subsidence data between its neighboring monitoring points is smaller, and the corresponding state value of that monitoring point is smaller.

[0098] For example, along the extension direction of adjacent monitoring points on different monitoring points, the correlation of changes in subsidence data between different monitoring points and their adjacent monitoring points is used as the starting point of the sequence. A sequence of changes in subsidence data between several monitoring points and their adjacent monitoring points is then determined. That is, starting from any monitoring point, the sequence expands to the side of one of its adjacent monitoring points, extending to several monitoring points (e.g., 10 monitoring points). The original monitoring point and the expanded monitoring points then constitute a monitoring point sequence. The correlation of changes in adjacent monitoring points within this sequence forms a correlation of changes sequence. For example, for monitoring point A, its adjacent monitoring point is B. Along the extension direction from A to B, there are monitoring points C, D, E, F… Then A, B, C, D, E, F… constitute a monitoring point sequence. All correlations in the correlation of changes sequence are merged to determine the state value of different monitoring points. That is, the cumulative value of all correlations in the correlation of changes corresponding to any monitoring point is determined, and this cumulative value is used as the state value of the corresponding monitoring point.

[0099] Therefore, the status values ​​of different monitoring points can be determined.

[0100] Step S400: Based on the degree of interference and the status value, select the target monitoring point from all different monitoring points.

[0101] Among them, the target monitoring point refers to the monitoring point where the abnormality of the subsidence data is caused by environmental factors and the subsidence data needs to be corrected.

[0102] The greater the interference with the subsidence data of a monitoring point, and the smaller the correlation between the fluctuations of subsidence data from different monitoring points within the same monitoring area (i.e., the smaller the state value of the monitoring point), the higher the degree of anomaly in the subsidence data of the corresponding monitoring point. This anomaly is more likely to be caused by the equipment itself at the monitoring point, making it more likely to be a target monitoring point requiring subsidence data correction. Therefore, target monitoring points can be selected from all different monitoring points.

[0103] In one possible implementation, such as Figure 4 As shown, in step S400, target monitoring points are selected from all different monitoring points based on the degree of interference and the state value, including:

[0104] Step S401: Integrate the degree of interference and the state value to determine the necessity of correction for the subsidence data of different monitoring points.

[0105] Among them, the necessity of correction is used to reflect the degree to which the subsidence data of the monitoring point needs to be corrected.

[0106] For example, by fusing the degree of interference and state values ​​corresponding to different monitoring points, the necessity of correction for the subsidence data of different monitoring points is determined, and the calculation formula is as follows:

[0107]

[0108] In the formula: Indicates the first The necessity of correcting the subsidence data at each monitoring point Indicates the first The status value of each monitoring point is not 0. Indicates the first The degree of interference with the subsidence data of each monitoring point; This represents a normalization function, such as a maximum / minimum value normalization function, used to normalize values ​​to the range [0,1].

[0109] Step S402: Compare the correction necessity with the set correction necessity threshold, and take the monitoring point corresponding to the correction necessity being greater than the set correction necessity threshold as the target monitoring point.

[0110] The necessity of correction reflects the degree to which the subsidence data of the monitoring point needs to be corrected. The greater the necessity of correction, the more necessary the subsidence data of the corresponding monitoring point is to be corrected. Therefore, based on the necessity of correction, monitoring points that need to be corrected for subsidence data can be selected from all different monitoring points, and these monitoring points can be used as target monitoring points.

[0111] For example, a reasonable threshold for the necessity of correction can be set in advance. If a threshold for the necessity of correction is set... The value is 0.32. Among them, the correction necessity threshold... The specific value can be determined by statistically analyzing historical data. Specifically, this involves statistically analyzing the necessity of correction for subsidence data at different monitoring points in historical mine roadway roof subsidence monitoring, determining the minimum necessity of correction when subsidence data is abnormal due to factors of the monitoring equipment itself, and using this minimum necessity of correction as the threshold for the necessity of correction. The necessity of correction at different monitoring points is compared with a set threshold. Monitoring points whose necessity exceeds the threshold are designated as target monitoring points. This allows for the selection of target monitoring points from all available monitoring points that require correction of the subsidence data.

[0112] Step S500: Correct the subsidence data of the target monitoring point based on the subsidence data of the adjacent non-target monitoring points of the target monitoring point.

[0113] When correcting the sedimentation data of a target monitoring point, the correction process can be achieved using the sedimentation data of adjacent non-target monitoring points (such as non-target monitoring points within the eight-neighborhood of the target monitoring point). For example, weights can be assigned to different adjacent non-target monitoring points based on their distance from the target monitoring point. The greater the distance, the smaller the corresponding weight, and the cumulative value of all weights is 1. Then, by using this weight, the sedimentation data of each adjacent non-target monitoring point of the target monitoring point are weighted, multiplied, and summed to obtain the corrected sedimentation data of the target monitoring point.

[0114] In one possible implementation, such as Figure 5 As shown, in step S500, the subsidence data of the target monitoring point is corrected based on the subsidence data of adjacent non-target monitoring points, including:

[0115] Step S501: Based on the degree of anomaly of each data point in the subsidence data of the adjacent non-target monitoring points of the target monitoring point, and the state value of the adjacent non-target monitoring points of the target monitoring point, determine the correction weight of each data point in the subsidence data of the adjacent non-target monitoring points of the target monitoring point.

[0116] The lower the degree of abnormality of the data points in the sinking data of the adjacent non-target monitoring points of the target monitoring point, and the larger the state value of the adjacent non-target monitoring point, the more likely the data points in the sinking data of the adjacent non-target monitoring point are to be normal data, and the greater the corresponding correction weight.

[0117] For example, based on the degree of anomaly of each data point in the subsidence data of adjacent non-target monitoring points of the target monitoring point, and the state value of the adjacent non-target monitoring points of the target monitoring point, the correction weight of each data point in the subsidence data of adjacent non-target monitoring points of the target monitoring point is determined, and the calculation formula is as follows:

[0118]

[0119] In the formula: Indicates target monitoring point The b-th adjacent non-target monitoring point (target monitoring point) The correction weight of the i-th data point in the subsidence data of non-target monitoring points (excluding the target monitoring point) within the eight neighborhoods of the target monitoring point; Indicates target monitoring point The state value of the b-th adjacent non-target monitoring point; Indicates target monitoring point The anomaly of the i-th data point in the subsidence data of the b-th adjacent non-target monitoring point; Indicates target monitoring point The number of adjacent non-target monitoring points; This represents the minimum value greater than 0, used to prevent the denominator from being 0. It can be set empirically. .

[0120] Step S502: Use correction weights to weight and accumulate the data points at the same time in the subsidence data of adjacent non-target monitoring points of the target monitoring point to obtain the subsidence correction value of the target monitoring point at each time.

[0121] Using the correction weights of the data points at the same time from the subsidence data of all adjacent non-target monitoring points at the target monitoring point, the data points of all adjacent non-target monitoring points at the same time are weighted, multiplied, and then summed. This summed value is used as the subsidence correction value of the target monitoring point's subsidence data at that time. The calculation formula is as follows:

[0122]

[0123] In the formula: Indicates target monitoring point The subsidence correction value corresponding to the i-th data point in the subsidence data; Indicates target monitoring point The b-th adjacent non-target monitoring point (target monitoring point) The i-th data point in the subsidence data of the non-target monitoring points in the eight neighboring areas; Indicates target monitoring point The correction weight of the i-th data point in the subsidence data of the b-th adjacent non-target monitoring point; Indicates target monitoring point The number of adjacent non-target monitoring points.

[0124] Step S503: Based on the subsidence correction value, obtain the corrected subsidence data of the target monitoring point.

[0125] The corrected subsidence values ​​corresponding to all data points in the subsidence data of the target monitoring point constitute the corrected subsidence data of the target monitoring point. Therefore, the corrected subsidence data of the target monitoring point is obtained based on the corrected subsidence values ​​of the target monitoring point.

[0126] In one possible implementation, the method further includes monitoring collapse risk based on the corrected subsidence data of the target monitoring point and the subsidence data of non-target monitoring points outside the target monitoring point.

[0127] Based on the corrected subsidence data of the target monitoring point and the subsidence data of non-target monitoring points outside the target monitoring point, when conducting collapse risk monitoring, it is possible to determine whether the subsidence or subsidence rate exceeds the preset safety threshold, and to issue a collapse risk warning based on the judgment result.

[0128] In one possible implementation, collapse risk monitoring includes: redetermining the state value of the target monitoring point based on the corrected subsidence data of the target monitoring point; and conducting collapse risk monitoring based on the redetermined state value of the target monitoring point and the state values ​​of non-target monitoring points outside the target monitoring point.

[0129] For example, based on the corrected subsidence data of the target monitoring point, the state value of the target monitoring point is recalculated in the same way as the state value of the monitoring point described above. The recalculated state value of the target monitoring point and the state values ​​of non-target monitoring points (the other monitoring points besides the target monitoring point) are normalized to the range of [0,1] to obtain the normalized state value.

[0130] Pre-set appropriate state thresholds For example, setting a state threshold The value is 0.7. Here, the state threshold is set. The specific value can be determined by statistically analyzing historical data. Specifically, this involves statistically analyzing the normalized state values ​​of different monitoring points in historical mine roadway roof subsidence monitoring, determining the minimum normalized state value at which a monitoring point has a collapse risk, and using this minimum normalized state value as the state threshold. The normalized state value of each monitoring point is compared with the state threshold. The comparison is performed when the normalized state value is greater than the set state threshold. If a warning is issued when the current monitoring point is at risk of collapse, it indicates that the monitoring point is at risk of collapse.

[0131] Based on the same inventive concept, embodiments of the present invention also provide a monitoring device for roof subsidence in mine roadways under complex environments, such as... Figure 6 As shown, the device includes:

[0132] The data acquisition module is used to acquire data on the subsidence of the roadway roof at different monitoring points;

[0133] The anomaly analysis module is used to determine the degree of interference with the subsidence data based on the abnormal fluctuations in the subsidence data at different monitoring points. The degree of interference reflects the degree of abnormality in the subsidence data due to interference.

[0134] The status analysis module is used to determine the status value of different monitoring points based on the distribution of the fluctuation correlation of the subsidence data between different monitoring points and their adjacent monitoring points. The status value is used to reflect the possibility that the abnormal subsidence data of the monitoring points is caused by environmental factors.

[0135] The monitoring point screening module is used to screen out target monitoring points from all different monitoring points based on the degree of interference and status value. The target monitoring point refers to the monitoring point that needs to be corrected for the subsidence data.

[0136] The data correction module is used to correct the subsidence data of the target monitoring point based on the subsidence data of adjacent non-target monitoring points.

[0137] It should be noted that the device provided in the above embodiments is only an example of the division of the above functional modules. In actual applications, the above functions can be assigned to different functional modules as needed, that is, the internal structure of the computer device can be divided into different functional modules to complete all or part of the functions described above.

[0138] Based on the same inventive concept, embodiments of the present invention also provide a monitoring system for roof subsidence in mine roadways under complex environments, such as... Figure 7 As shown, the system includes: a memory, a processor, and computer program code stored in the memory and running on the processor, wherein when the processor executes the computer program code, the system can perform any of the aforementioned methods for monitoring the roof subsidence of mine roadways under complex environments.

[0139] In this embodiment of the invention, the system can be divided into functional modules according to the above method example. For example, each module can correspond to a separate functional module, or two or more functions can be integrated into one processing module. The integrated module can be implemented in hardware. It should be noted that the module division in this embodiment is illustrative and only represents one logical functional division. In actual implementation, there may be other division methods.

[0140] Based on the same inventive concept, embodiments of the present invention also provide a computer program product, which includes: computer program code, which, when run on a computer, causes the computer to execute any of the aforementioned methods for monitoring the subsidence of the roof of a mine roadway under complex conditions.

[0141] Based on the same inventive concept, embodiments of the present invention also provide a computer-readable storage medium storing computer program code, which, when executed on a computer, causes the computer to perform any of the aforementioned methods for monitoring the subsidence of the roof of a mine roadway under complex conditions.

[0142] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, and not to limit them. Although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features. Such modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the scope of the technical solutions of the embodiments of the present invention, and should all be included within the protection scope of the present invention.

Claims

1. A method for monitoring roof subsidence in mine roadways under complex environments, characterized in that, Includes the following steps: Obtain data on the subsidence of the tunnel roof at different monitoring points; Based on the abnormal fluctuations in the subsidence data at different monitoring points, the degree of interference with the subsidence data is determined. The degree of interference reflects the abnormal extent to which the subsidence data is disturbed. Based on the distribution of the fluctuation correlation of subsidence data between different monitoring points and their adjacent monitoring points, the state values ​​of different monitoring points are determined. The state values ​​are used to reflect the possibility that the abnormal subsidence data of the monitoring points is caused by environmental factors. Based on the degree of interference and the status value, target monitoring points are selected from all different monitoring points. Target monitoring points refer to monitoring points where the abnormality of the subsidence data is caused by environmental factors and requires correction of the subsidence data. Based on the subsidence data of adjacent non-target monitoring points of the target monitoring point, the subsidence data of the target monitoring point is corrected. Based on the abnormal fluctuations in the subsidence data from different monitoring points, the degree of interference with the subsidence data is determined, including: determining the anomalousness of each data point in the subsidence data based on the differences between adjacent data points in the local data segment where each data point is located; the anomalousness is used to reflect the degree of anomalousness of the corresponding data point; and determining the degree of interference with the subsidence data based on the differences in the degree of anomalousness between adjacent data points in the subsidence data. Based on the distribution of the fluctuation correlation of subsidence data between different monitoring points and their adjacent monitoring points, the state values ​​of different monitoring points are determined, including: determining the difference in the degree of interference of subsidence data between different monitoring points and their adjacent monitoring points; based on the difference value and the difference in the trend of subsidence data between different monitoring points and their adjacent monitoring points, determining the change correlation of subsidence data between different monitoring points and their adjacent monitoring points, the change correlation is used to reflect the degree of change correlation of subsidence data between different monitoring points and their adjacent monitoring points; in the extension direction on the side where the adjacent monitoring points of different monitoring points are located, taking the change correlation of subsidence data between different monitoring points and their adjacent monitoring points as the starting point of the sequence, determining a change correlation sequence composed of the change correlation of subsidence data between several monitoring points and their adjacent monitoring points, and merging all change correlations in the change correlation sequence to obtain the state values ​​of different monitoring points. Based on the subsidence data of adjacent non-target monitoring points of the target monitoring point, the subsidence data of the target monitoring point is corrected, including: determining the correction weight of each data point in the subsidence data of adjacent non-target monitoring points of the target monitoring point based on the degree of anomaly of each data point in the subsidence data of adjacent non-target monitoring points of the target monitoring point and the state value of adjacent non-target monitoring points of the target monitoring point; using the correction weight, weighted summation of the data points in the subsidence data of adjacent non-target monitoring points of the target monitoring point at the same time to obtain the subsidence correction value of the target monitoring point at each time; and obtaining the corrected subsidence data of the target monitoring point based on the subsidence correction value.

2. The method for monitoring roof subsidence in mine roadways under complex environments according to claim 1, characterized in that, Based on the difference values ​​and the differences in the changing trends of subsidence data between different monitoring points and their neighboring monitoring points, the correlation of changes in subsidence data between different monitoring points and their neighboring monitoring points is determined, including: Determine the DTW distance of subsidence data between different monitoring points and their adjacent monitoring points; The difference value and DTW distance are fused, and the fusion result is negatively correlated and normalized to obtain the correlation of subsidence data changes between different monitoring points and their neighboring monitoring points.

3. The method for monitoring roof subsidence in mine roadways under complex environments according to claim 1, characterized in that, Based on the degree of interference and state values, target monitoring points were selected from all different monitoring points, including: By integrating the degree of interference and the state value, the necessity of correction for the subsidence data at different monitoring points is determined. The necessity of correction is used to reflect the degree to which the subsidence data at the monitoring points need to be corrected. The necessity of correction is compared with the set threshold for the necessity of correction, and the monitoring point corresponding to the point where the necessity of correction is greater than the set threshold for the necessity of correction is taken as the target monitoring point.

4. The method for monitoring roof subsidence in mine roadways under complex environments according to claim 1, characterized in that, The method also includes: monitoring collapse risk based on the corrected subsidence data of the target monitoring point and the subsidence data of non-target monitoring points outside the target monitoring point.

5. The method for monitoring roof subsidence in mine roadways under complex environments according to claim 4, characterized in that, Conduct collapse risk monitoring, including: Based on the corrected subsidence data of the target monitoring points, the state values ​​of the target monitoring points are redefined. Collapse risk monitoring is conducted based on the status values ​​of the newly determined target monitoring points and the status values ​​of non-target monitoring points outside the target monitoring points.

6. A monitoring system for roof subsidence in mine roadways under complex environments, characterized in that, The method includes a memory, a processor, and executable computer program code stored in the memory and executable on the processor. When the processor executes the computer program code, it performs a method for monitoring the roof subsidence of a mine roadway under complex conditions as described in any one of claims 1 to 5.

Images