A roof separation layer online monitoring method

Abstract

This invention discloses an online monitoring method for roof delamination, relating to the field of roof delamination monitoring technology. The method includes the following steps: deploying multiple sensors at different layers of the mine roof, selecting different types of sensor deployment schemes based on geological conditions to comprehensively collect rock strata change data, ensuring wide coverage and comprehensive data acquisition. Through multi-level sensor deployment, dynamic sampling frequency adjustment, and multi-dimensional data fusion analysis, the system improves the accuracy of roof delamination monitoring. Combined with environmental feature models, it achieves adaptive early warning for different geological environments, reducing the risk of false alarms and missed alarms. The system can dynamically adjust the sampling frequency to capture key change processes and continuously optimize early warning parameters to avoid "monitoring blind spots" or outdated strategies, improving the real-time performance, flexibility, and stability of mine monitoring, and significantly enhancing the efficiency and intelligence level of mine safety management.

Description

Technical Field

[0001] This invention relates to the field of roof delamination monitoring technology, and specifically to an online roof delamination monitoring method. Background Technology

[0002] Online monitoring of roof delamination refers to the technical means of real-time monitoring of delamination phenomena occurring in the roof strata of mines or underground roadways during mining or support processes. Delamination refers to the weakening or fracturing of the cohesion between rock strata due to stress changes, geological structures, or mining activities, resulting in voids or separation. The online monitoring system continuously collects data on the displacement, pressure, and delamination status of the roof strata through sensors, displacement gauges, and other equipment, and transmits the data to a monitoring platform in real time to analyze roof stability and provide timely warnings of potential roof collapse risks. This technology is widely used in underground mining sites such as coal mines and metal mines, aiming to improve mine safety and operational efficiency.

[0003] The existing technology has the following shortcomings:

[0004] In existing online monitoring systems for roof delamination, inaccurate data interpretation is an easily overlooked but potentially serious problem. In complex geological environments, roof strata subject to stress variations may exhibit irregular phenomena such as fracture propagation and interlayer slippage. These changes are nonlinear and random. If the monitoring system analyzes the data according to a fixed pattern, it may fail to identify early signals of abnormal changes. For example, in soft rock or multi-fault strata, minute fracture propagation may be misinterpreted as normal change, when in fact it is a precursor to roof instability. If the system ignores these signals, critical warning opportunities may be missed, leading to sudden roof collapse and potentially causing a major safety accident in the mine. Therefore, improving the accuracy of data interpretation, especially through targeted analysis of the changing patterns under different geological conditions, is of paramount importance.

[0005] The information disclosed in the background section is only intended to enhance the understanding of the background of this disclosure, and therefore may include information that does not constitute prior art known to those skilled in the art. Summary of the Invention

[0006] The purpose of this invention is to provide an online monitoring method for roof delamination. Through multi-level sensor deployment, dynamic sampling frequency adjustment, and multi-dimensional data fusion analysis, the system improves the accuracy of roof delamination monitoring. Combined with environmental feature models, it achieves adaptive early warning for different geological environments, reducing the risk of false alarms and missed alarms. The system can dynamically adjust the sampling frequency to capture key changes and continuously optimize early warning parameters to avoid "monitoring blind spots" or outdated strategies. This improves the real-time performance, flexibility, and stability of mine monitoring, significantly enhancing the efficiency and intelligence level of mine safety management, thereby solving the problems mentioned in the background technology.

[0007] To achieve the above objectives, the present invention provides the following technical solution: a method for online monitoring of roof delamination, comprising the following steps:

[0008] Multiple sensors are deployed at different layers of the mine roof, and different types of sensor deployment schemes are selected according to geological conditions to comprehensively collect data on rock strata changes, ensuring wide coverage and comprehensive data collection.

[0009] The sensor's dynamic sampling frequency is set, and the sampling interval is automatically adjusted according to the severity of the changes in the roof strata. When a sudden displacement is detected, the sampling frequency is automatically increased to ensure that key changes are captured in real time.

[0010] The collected raw monitoring data are preprocessed and combined with the geological characteristic parameters of the mine to incorporate the differences in the geological environment into the monitoring and analysis, thereby generating an environmental characteristic model.

[0011] Multidimensional data fusion of displacement, pressure and geological parameters is performed to match different types of data in time and space dimensions, generate an overall trend map of rock strata change, and identify potential delamination locations and change patterns.

[0012] A nonlinear trend recognition algorithm is used to analyze the results of multidimensional data fusion. By detecting the rate of change, acceleration and fluctuation amplitude of the data, early abnormal change signals of rock strata are identified, and normal changes and potential roof instability risks are distinguished.

[0013] Based on collected historical and real-time data, an adaptive learning algorithm is used to continuously optimize the early warning model, enabling it to automatically adjust parameters according to new data patterns, thereby improving its adaptability to different geological environments and enhancing the accuracy and real-time performance of the early warning.

[0014] Preferably, multiple sensors are deployed at different layers of the mine roof, and different types of sensor deployment schemes are selected according to geological conditions to comprehensively collect data on rock strata changes, ensuring wide coverage and comprehensive data collection. The specific steps are as follows:

[0015] By comprehensively analyzing the geological structure of the mine and identifying key monitoring areas, the accuracy and relevance of sensor deployment are ensured.

[0016] Select appropriate sensor types and layout schemes based on different geological environments to cover key areas of displacement and stress changes;

[0017] Three-dimensional sensors are installed at different levels of the mine roof to form a multi-layered monitoring network, ensuring comprehensive and reliable data collection.

[0018] By optimizing sensor layout and introducing redundant data acquisition mechanisms, the stability of the monitoring system and the continuity of data acquisition can be improved.

[0019] Preferably, the specific steps for setting the dynamic sampling frequency of the sensor, automatically adjusting the sampling interval according to the severity of changes in the roof strata, and automatically increasing the sampling frequency when a sudden displacement change is detected to ensure that key changes are captured in real time are as follows:

[0020] The initial sampling frequency is set according to geological conditions and historical data to ensure that basic data collection covers early trends in roof changes;

[0021] By using a real-time fluctuation monitoring mechanism to identify abnormal change signals in the data, the accuracy of identifying key changes can be improved.

[0022] When an abnormal signal is detected, the sampling frequency is automatically increased to ensure that key changes are fully captured.

[0023] By dynamically adjusting the sampling strategy through a multi-layered feedback mechanism, the sampling frequency can be flexibly and adaptively adapted to different changing scenarios.

[0024] Preferably, the collected raw monitoring data is preprocessed, and combined with the geological characteristic parameters of the mine, the differences in the geological environment are incorporated into the monitoring and analysis. The specific steps for generating an environmental characteristic model are as follows:

[0025] Collect geological characteristic parameters of the mine and establish a geological information database to provide comprehensive environmental basic information for subsequent data analysis;

[0026] By correlating and matching monitoring data with geological characteristic parameters, the ability to interpret data fluctuations and the accuracy of analysis can be improved.

[0027] By cleaning, denoising, and identifying outliers, the authenticity and reliability of monitoring data are ensured, and interference factors are reduced.

[0028] Generate environmental characteristic models and dynamically adjust sampling and early warning strategies based on geological differences to improve the accuracy and adaptability of the monitoring system.

[0029] Preferably, the specific steps for identifying the temporal patterns of rock strata changes and potential risk signals by dynamically matching displacement, pressure, and geological parameters over time to generate a sequence of change trends are as follows:

[0030] Synchronize timestamps to establish a unified time series, ensuring that different types of data can be compared and analyzed on the same timeline;

[0031] By analyzing the changing trends of time series data, the fluctuation patterns of rock strata displacement and pressure are identified, and the risk of delamination is preliminarily assessed.

[0032] Establish a time correlation model to analyze the mutual influence and temporal relationship between displacement, pressure and geological parameters;

[0033] The trend sequence is dynamically updated, and the monitoring strategy is adjusted in real time to ensure a rapid response to changes in the rock strata.

[0034] Preferably, the specific steps for integrating multi-level data in the spatial dimension, using 3D modeling to generate an overall trend map of rock strata changes, and intuitively identifying key change areas and potential delamination locations are as follows:

[0035] Spatial matching of sensor data from different layers generates a multi-layered change map of the mine roof, improving the comprehensiveness of data analysis;

[0036] A 3D model is generated using spatial matching data to visually present changes in rock strata and identify key areas of change.

[0037] By integrating temporal and spatial data, an overall trend map is generated, which shows the changing patterns of rock strata and potential delamination locations;

[0038] High-risk areas are marked based on trend charts, and warning parameters are dynamically adjusted to improve the accuracy and flexibility of the system's warnings.

[0039] Preferably, a nonlinear trend recognition algorithm is used to analyze the multidimensional data fusion results. By detecting the rate of change, acceleration, and fluctuation amplitude of the data, early abnormal change signals of the rock strata are identified, and the specific steps to distinguish between normal changes and potential roof instability risks are as follows:

[0040] When analyzing the results of multidimensional data fusion, a multidimensional rate of change matrix is ​​first constructed. The time derivatives of the collected displacement, pressure, and geological parameter data are then calculated to obtain the rate of change for each type of data. The formula for calculating the rate of change is as follows:

[0041] In the formula, M rate (i, t) are the elements of the rate of change matrix of the i-th sensor at time t, D i (t) represents the raw monitoring data of the i-th sensor at time t, where Δt is the time interval, and D i (t-Δt) is the raw monitoring data of the i-th sensor at time t-Δt, which is the raw monitoring data of the previous time.

[0042] Based on the rate of change matrix, the acceleration matrix is ​​further calculated to measure the drasticness and abrupt changes in the data. The expression for calculating the acceleration matrix is ​​as follows:

[0043] In the formula, M accel(i, t) are the elements of the acceleration matrix of the i-th sensor at time t, M rate (i, t-Δt) is the rate of change matrix element of the i-th sensor at time t-Δt, which is the rate of change matrix element of the previous time.

[0044] Preferably, based on the rate of change and acceleration matrix, fluctuation amplitude analysis parameters are calculated to identify abnormal fluctuations in the data. The fluctuation amplitude calculation formula is as follows:

[0045] In the formula, A wave (i) represents the fluctuation amplitude analysis parameter of the i-th sensor. It is the average rate of change of the i-th sensor, and T is the total number of time points;

[0046] Combined with the rate of change M rate (i, t), acceleration M accel (i, t) and fluctuation amplitude parameter A wave (i) Calculate the nonlinear risk assessment index, which is used to ultimately distinguish between normal changes and potential roof instability risks. The calculation formula is as follows:

[0047] R risk (i)=α·M rate (i,t)+β·M accel (i,t)+γ·A wave (i), where R risk (i) is the nonlinear risk assessment index of the i-th sensor, where α, β, and γ are all weighting parameters, and α is used to adjust the rate of change M. rate The impact of (i, t) on the overall risk assessment, β is used to adjust the acceleration M accel The influence of the (i, t) parameter, γ is used to adjust the fluctuation amplitude parameter A. wave The effect of (i).

[0048] Preferably, based on collected historical and real-time data, the early warning model is continuously optimized using an adaptive learning algorithm, enabling it to automatically adjust parameters according to new data patterns, thereby improving its adaptability to different geological environments and enhancing the accuracy and real-time performance of the early warning. The specific steps are as follows:

[0049] First, a basic early warning model is constructed based on the collected historical and real-time data. Key parameters are defined, including displacement change rate, pressure change rate, and environmental characteristic parameter weights. To comprehensively consider the impact of multi-dimensional data, a data weight matrix is ​​used to represent the contribution of each parameter to the early warning model, as shown in the following formula:

[0050] In the formula, M0 is the basic early warning weight matrix, which represents the weight distribution of each parameter of the initial model, and w1, w2, ..., w9 are the weights of different data types at different time points;

[0051] During real-time monitoring, based on the current displacement change rate and pressure change rate, the abnormal deviation rate between the actual data and the model prediction value is calculated. The formula for calculating the abnormal deviation rate is as follows:

[0052] In the formula, D t It is the abnormal deviation rate, V t It is the real-time displacement change rate. It is the rate of change of displacement predicted by the model, P t It is the real-time pressure change rate. It is the rate of change of pressure predicted by the model.

[0053] Preferably, based on the calculated abnormal deviation rate D t The weight values ​​of the basic weight matrix M0 are dynamically adjusted to generate a new weight matrix. The generation formula is as follows: M t =M0+ω·D t ·I, where M t It is the weight matrix after real-time optimization, ω is the learning rate, and I is the identity matrix;

[0054] Based on the optimized weight matrix M t The warning threshold is recalculated to dynamically adjust the warning strategy for different areas. The formula for calculating the warning threshold is as follows:

[0055] In the formula, T t It is the real-time warning threshold, M t [p] is the p-th weight value in the optimized weight matrix, F p It is an influencing factor of geological characteristic parameters.

[0056] The technical effects and advantages provided by the present invention in the above technical solution are as follows:

[0057] This invention, through multi-layered sensor deployment, dynamic sampling frequency adjustment, and multi-dimensional data fusion analysis, effectively improves the accuracy of roof delamination monitoring data interpretation and significantly reduces the risk of missed and false alarms. By combining the mine's geological characteristic parameters to generate an environmental characteristic model, the monitoring process can adaptively adjust to different geological environments, thereby more accurately identifying abnormal signals such as rock strata displacement, stress changes, and fracture propagation. Especially in soft rock layers or areas with dense faults, the system can detect subtle but continuous trends in advance, issuing timely warnings and avoiding delayed warnings or misjudgments caused by fixed thresholds and single data source analysis in traditional monitoring systems. Furthermore, the system can automatically adjust the sampling frequency when abnormal signals are detected, ensuring the capture of detailed data on key changes, thus significantly improving the real-time performance and reliability of monitoring.

[0058] This invention introduces an adaptive early warning mechanism based on environmental feature models, enabling the monitoring system to dynamically optimize early warning parameters and sampling strategies according to real-time changes in the mine, achieving more flexible monitoring and early warning management. For high-risk areas such as soft rock layers, the system automatically lowers the early warning threshold and increases the sampling frequency, while in more stable areas, unnecessary high-frequency monitoring can be reduced, improving system resource utilization efficiency. Simultaneously, the adaptive early warning mechanism possesses continuous optimization capabilities; the system can continuously adjust the environmental feature model based on real-time feedback, ensuring long-term efficient operation and avoiding problems such as "monitoring blind spots" or outdated strategies. This flexibility and continuous optimization capability not only reduce false alarm and false negative rates but also reduce the burden on mine management personnel, improving the safety, intelligence, and stability of online monitoring of mine roof delamination. Attached Figure Description

[0059] To more clearly illustrate the technical solutions in the embodiments of this application or the prior art, the drawings used in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments recorded in this invention. For those skilled in the art, other drawings can be obtained based on these drawings.

[0060] Figure 1 This is a flowchart of an online monitoring method for roof delamination according to the present invention. Detailed Implementation

[0061] Exemplary embodiments will now be described more fully with reference to the accompanying drawings. However, these exemplary embodiments can be implemented in many forms and should not be construed as limited to the examples set forth herein; rather, they are provided so that the description of this disclosure will be more complete and fully convey the concept of the exemplary embodiments to those skilled in the art.

[0062] This invention provides, for example Figure 1 The method for online monitoring of roof delamination shown includes the following steps:

[0063] Multiple sensors, including displacement sensors and pressure sensors, are deployed at different layers of the mine roof. Different types of sensor deployment schemes are selected according to geological conditions to comprehensively collect data on stress, displacement and fracture changes in the rock strata, ensuring wide coverage and comprehensive data collection.

[0064] Multiple sensors, including displacement and pressure sensors, are deployed at different layers of the mine roof. Different sensor deployment schemes are selected based on geological conditions to comprehensively collect data on stress, displacement, and fracture changes in the rock strata, ensuring broad coverage and comprehensive data acquisition. The specific steps are as follows:

[0065] By comprehensively analyzing the geological structure of the mine and identifying key monitoring areas, the accuracy and relevance of sensor deployment are ensured.

[0066] Before deploying sensors, a comprehensive geological survey and analysis of the mine roof is essential to determine the type, thickness, fault distribution, joint development, and potential weak points of the rock strata. Geological mapping and borehole exploration are used to identify areas prone to delamination, slippage, and fracture propagation. This step aims to accurately locate key monitoring areas, avoiding aimless sensor deployment and improving the targeting and effectiveness of monitoring. Particularly in areas with multiple faults or soft rock layers, these areas should be prioritized for monitoring, as they are more susceptible to roof instability.

[0067] Select appropriate sensor types and layout schemes based on different geological environments to cover key areas of displacement and stress changes;

[0068] Based on the identified geological structural features, select appropriate sensor types. For areas prone to large-scale displacement, such as soft rock layers and coal seam roofs, high-precision displacement sensors should be prioritized. For hard rock layers or areas with a high risk of interlayer slippage, pressure sensors should be deployed to monitor stress changes. Additionally, special types of sensors, such as laser displacement gauges and fiber optic sensors, can be deployed to obtain more comprehensive monitoring data. The sensor deployment plan should consider the shape, depth, and spatial distribution of the mine roadways to ensure a sufficiently wide sensor network coverage and avoid monitoring blind spots.

[0069] Three-dimensional sensors are installed at different levels of the mine roof to form a multi-layered monitoring network, ensuring comprehensive and reliable data collection.

[0070] A three-dimensional monitoring network is formed by installing sensors in different layers of the mine roof. For example, sensors can be placed at the arch, sidewalls, main faults, and key rock strata contact surfaces of the roadway to cover different mechanical layers of the roof. During installation, the fixing method should be selected according to the geological stability of different layers. For example, expansion bolts are used to fix the sensors in relatively stable rock strata, while support devices are used to protect the sensors in easily slippery rock strata. Furthermore, the stability of the sensors and the data acquisition status should be checked regularly to ensure the reliability of long-term monitoring.

[0071] By optimizing sensor layout and introducing redundant data acquisition mechanisms, the stability of the monitoring system and the continuity of data acquisition can be improved.

[0072] After the sensors are deployed, their layout needs to be further optimized based on the feedback from the initial data collection. For areas with significant data fluctuations or ineffective coverage, additional sensors should be added to increase monitoring density. Furthermore, a redundant data acquisition mechanism should be established by deploying backup sensors at key monitoring points to ensure the system can still acquire data even if some sensors fail. The introduction of redundancy effectively improves the stability of the monitoring system and prevents data interruption or omission due to equipment failure.

[0073] The sensor's dynamic sampling frequency is set, and the sampling interval is automatically adjusted according to the severity of the changes in the roof strata. When a sudden displacement is detected, the sampling frequency is automatically increased to ensure that key changes are captured in real time.

[0074] The specific steps for setting the dynamic sampling frequency of the sensor, automatically adjusting the sampling interval according to the severity of changes in the roof strata, and automatically increasing the sampling frequency when a sudden displacement change is detected to ensure that key changes are captured in real time are as follows:

[0075] The initial sampling frequency is set according to geological conditions and historical data to ensure that basic data collection covers early trends in roof changes;

[0076] After the sensors are deployed, the first step is to define sampling rules and set initial sampling frequencies for different conditions based on the mine's geological environment and historical data on roof changes. For example, in relatively stable hard rock strata, the initial sampling frequency can be set to once per hour; while in high-risk areas such as soft rock strata or fault junctions, the initial sampling frequency should be set to once every 10 minutes. When setting the initial frequency, the rock strata type, the stability of the monitoring area, and the accuracy of the monitoring data should be comprehensively considered to ensure that the basic data acquisition of the sensor network can fully cover the early trends of roof changes.

[0077] By using a real-time fluctuation monitoring mechanism to identify abnormal change signals in the data, the accuracy of identifying key changes can be improved.

[0078] The system continuously collects monitoring data and analyzes the displacement and stress changes of the roof strata in real time to identify abnormal signals of data fluctuations. For example, when the system detects a sudden change in the displacement data of a certain sensor within a short period of time, it triggers the fluctuation monitoring mechanism, marks the data as an "abnormal change," and records the amplitude and trend of the fluctuation. This mechanism can effectively avoid false alarms caused by small-scale data fluctuations, while ensuring that critical change signals are not ignored. The identification of abnormal change signals should be combined with the previously deployed sensor network and historical data models to ensure the accuracy of the identification process.

[0079] When an abnormal signal is detected, the sampling frequency is automatically increased to ensure that key changes are fully captured.

[0080] Once the system detects an abnormal change signal, the sensor's sampling frequency should be adjusted immediately, especially for sensors in areas with significant changes. The sampling frequency should be increased to the second or minute level to ensure that critical changes are captured in real time. For example, under normal circumstances, the sampling frequency for a certain area is once every 10 minutes, but when the system detects a sudden displacement change, the sampling frequency can be adjusted to once per minute or higher. Furthermore, upper and lower limits can be set for the sensor's sampling time interval to ensure that the adjusted frequency does not excessively affect the system's stability.

[0081] The sampling strategy is dynamically adjusted through a multi-layered feedback mechanism to ensure flexible and adaptive sampling frequency under different changing scenarios.

[0082] After adjusting the sampling frequency, the system also needs to perform real-time feedback analysis on the collected high-frequency data, and dynamically adjust subsequent sampling strategies based on the changing trend of the roof. For example, when the high-frequency data indicates that the roof changes are stabilizing, the system can gradually restore to a lower sampling frequency to reduce equipment load; conversely, when the changing trend continues to intensify, high-frequency sampling is maintained until the changes stabilize. Simultaneously, this multi-layered feedback mechanism should continuously learn from historical sampling data to optimize future dynamic sampling rules, ensuring that the system can adaptively adjust according to different changing scenarios.

[0083] The collected raw monitoring data is preprocessed and combined with the geological characteristics of the mine, including rock structure type, fault distribution and roof hardness, to incorporate the differences in the geological environment into the monitoring and analysis, and generate an environmental characteristic model.

[0084] The collected raw monitoring data is preprocessed and combined with mine geological characteristic parameters, including rock strata structure type, fault distribution, and roof hardness, to incorporate the differences in the geological environment into the monitoring analysis. The specific steps for generating an environmental characteristic model are as follows:

[0085] Collect geological characteristic parameters of the mine and establish a geological information database to provide comprehensive environmental basic information for subsequent data analysis;

[0086] Before preprocessing the raw monitoring data, key geological parameters of the mine must be collected, including the hierarchical structure of the rock strata, the distribution of faults and joints, rock hardness, and the mining depth. This geological information is typically obtained through drilling sampling, geological mapping, and historical mine reports, and is then categorized and entered into a geological information database. Based on different geological regions, the mine is divided into multiple monitoring sub-regions, and each region is labeled with geological characteristics. This process ensures that geological differences are taken into account during subsequent data analysis, avoiding data interpretation bias due to neglecting environmental variations.

[0087] By correlating and matching monitoring data with geological characteristic parameters, the ability to interpret data fluctuations and the accuracy of analysis can be improved.

[0088] The dynamically acquired sensor data is correlated and matched with the corresponding geological characteristic parameters of the area. For example, displacement data collected by displacement sensors is analyzed in conjunction with parameters such as rock structure and fault distribution to determine whether data fluctuations are related to geological characteristics. In areas with low roof hardness, large displacement changes may indicate fracture propagation or interlayer slip; while in hard rock areas, it is more likely to be short-term elastic deformation caused by stress concentration. This correlation and matching process allows data analysis to be comprehensively judged in conjunction with the geological background, thereby improving the ability to interpret anomalous changes.

[0089] By cleaning, denoising, and identifying outliers, the authenticity and reliability of monitoring data are ensured, and interference factors are reduced.

[0090] The raw monitoring data collected by the sensors undergoes preprocessing, including data cleaning, noise reduction, and outlier identification. Due to the complex environment of mines, the monitoring data may contain interference signals, such as noise generated by equipment vibration, airflow, or human operation. Therefore, data filtering algorithms are needed to filter out noise and label and remove outliers. For example, if a sensor exhibits extreme value changes within a short period and these changes cannot be verified by other sensors, it can be considered an outlier and excluded from the analysis. This preprocessing process ensures the authenticity and reliability of the data, preventing erroneous data from interfering with subsequent analysis.

[0091] Generate environmental characteristic models and dynamically adjust sampling and early warning strategies based on geological differences to improve the accuracy and adaptability of the monitoring system;

[0092] After data preprocessing, an environmental characteristic model is generated by combining geological feature parameters and cleaned data. This model includes the rock strata variation patterns, historical data trends, and potential risk points for each monitoring area, and is dynamically updated. The environmental characteristic model can be used to guide the dynamic sampling strategy and early warning threshold settings of the monitoring system. For example, in soft rock areas, the environmental model can automatically lower the early warning threshold and increase the sampling frequency; while in more stable areas, the model can appropriately reduce the sampling density to save system resources. This dynamic adjustment based on the environmental characteristic model makes the monitoring system more adaptable and accurate.

[0093] Multidimensional data fusion of displacement, pressure and geological parameters is performed to match different types of data in time and space dimensions, generate an overall trend map of rock strata change, and identify potential delamination locations and change patterns.

[0094] The specific steps for identifying temporal patterns and potential risk signals of rock strata changes by dynamically matching displacement, pressure, and geological parameters over time to generate a sequence of change trends are as follows:

[0095] Synchronize timestamps to establish a unified time series, ensuring that different types of data can be compared and analyzed on the same timeline;

[0096] First, the collected displacement, pressure, and geological parameter data are time-stamped and synchronized to ensure that different types of data can be compared and analyzed at the same point in time. Since the sampling frequency and data generation time of the sensors may differ, time alignment is required. The real-time monitoring data of displacement and pressure are time-stamped with the preprocessed geological parameter data to form a unified time series. This step ensures that all types of data can demonstrate the dynamic process of rock strata changes on the same timeline, thereby avoiding data analysis errors caused by time deviations.

[0097] By analyzing the changing trends of time series data, the fluctuation patterns of rock strata displacement and pressure are identified, and the risk of delamination is preliminarily assessed.

[0098] Synchronized time-series data are subjected to trend analysis to identify patterns in displacement and pressure data. For example, data characteristics such as stress increases and decreases, displacement amplitude and frequency over a certain period are observed, and the underlying causes of these changes are analyzed in conjunction with geological parameters. If a sudden shift in displacement accompanied by a sharp increase in pressure is observed within a certain time period, it may indicate the propagation of fractures or interlayer slippage in the roof strata. By analyzing this trend data, time curves of strata changes can be generated, providing a basis for subsequent early warning and analysis.

[0099] Establish a time correlation model to analyze the mutual influence and temporal relationship between displacement, pressure and geological parameters;

[0100] Based on the temporal variation patterns of displacement, pressure, and geological parameter data, correlation models are established between different data types to analyze their mutual influence over time. For example, this study investigates whether pressure changes precede displacement changes, or whether a more pronounced time lag exists in soft rock formations. The established temporal correlation models can help monitoring systems more accurately predict rock strata change trends, thereby improving the timeliness and accuracy of early warnings.

[0101] Dynamically update trend sequences and adjust monitoring strategies in real time to ensure rapid response to changes in rock strata;

[0102] As new monitoring data is continuously collected, the system should dynamically update the time series trends and adjust the monitoring strategy in real time according to data changes. For example, when a sustained increase in pressure data and a sudden change in displacement data are detected, the system can automatically increase the sampling frequency and mark the area as a high-risk area for focused monitoring. This dynamic update mechanism ensures that the monitoring system can respond to changes in rock strata in real time, avoiding missing key changes.

[0103] The specific steps for integrating multi-level data in a spatial dimension, generating an overall trend map of rock strata changes using 3D modeling, and intuitively identifying key change areas and potential delamination locations are as follows:

[0104] Spatial matching of sensor data from different layers generates a multi-layered change map of the mine roof, improving the comprehensiveness of data analysis;

[0105] Based on the sensor placement, displacement and pressure data from different strata are spatially matched to create a multi-layered change map of the mine roof. For example, sensor data installed at the tunnel arch, sidewalls, and fault junctions can be used to generate changes in these areas at the same time point using a spatial matching algorithm. This spatial matching helps the system identify the overall trend of rock strata changes, avoiding the limitations of single-point data analysis, and thus more accurately determining potential delamination locations.

[0106] A 3D model is generated using spatial matching data to visually present changes in rock strata and identify key areas of change.

[0107] The matched spatial data is imported into a 3D modeling system to generate a 3D trend map of the mine roof's changes. In the 3D model, displacement and pressure changes are visualized through color and shape variations, making it easy to identify areas experiencing drastic changes. For example, if the displacement curve of a certain area shows a downward concave trend accompanied by stress concentration, it may be a potential delamination area. 3D modeling not only visually displays changes in rock strata but also helps analyze the depth and extent of these changes.

[0108] By integrating temporal and spatial data, an overall trend map is generated, which shows the changing patterns of rock strata and potential delamination locations;

[0109] Based on 3D modeling, an overall trend map of the mine roof's changes is generated, integrating temporal and spatial data onto a single image. This trend map clearly displays the patterns of rock strata change, including fracture propagation direction, interlayer slip location, and stress concentration areas. Analysis of the trend map can identify early signs of rock strata delamination, enabling timely warnings and preventing roof collapse accidents.

[0110] High-risk areas are marked based on the trend chart, and the warning parameters are dynamically adjusted to improve the accuracy and flexibility of the system's warnings.

[0111] Based on the analysis of the overall trend map, high-risk areas are marked, and the warning parameters for these areas are dynamically adjusted. For example, for areas where cracks are spreading rapidly, the warning threshold can be lowered and the data sampling frequency increased; while for areas where changes are relatively stable, the warning threshold can be appropriately increased and the sampling frequency decreased. This dynamic adjustment mechanism ensures that the system's warning strategy is more accurate and flexible, reducing the risk of false alarms and missed alarms.

[0112] A nonlinear trend recognition algorithm is used to analyze the results of multidimensional data fusion. By detecting the rate of change, acceleration and fluctuation amplitude of the data, early abnormal change signals of rock strata are identified, and normal changes and potential roof instability risks are distinguished.

[0113] A nonlinear trend recognition algorithm is used to analyze the results of multidimensional data fusion. By detecting the rate of change, acceleration, and fluctuation amplitude of the data, early abnormal change signals of the rock strata are identified, and the specific steps to distinguish between normal changes and potential roof instability risks are as follows:

[0114] When analyzing the results of multidimensional data fusion, a multidimensional rate of change matrix is ​​first constructed. The time derivatives of the collected displacement, pressure, and geological parameter data are then calculated to obtain the rate of change for each type of data. The formula for calculating the rate of change is as follows:

[0115] In the formula, M rate (i, t) are the elements of the rate of change matrix of the i-th sensor at time t, D i (t) represents the raw monitoring data of the i-th sensor at time t, where Δt is the time interval, and D i (t-Δt) is the raw monitoring data of the i-th sensor at time t-Δt, which is the raw monitoring data of the previous time.

[0116] rate of change matrix M rateIt can intuitively reflect the rate of change of the roof strata at different time points, providing basic data for subsequent calculations of acceleration and fluctuation amplitude.

[0117] Based on the rate of change matrix, the acceleration matrix is ​​further calculated to measure the drasticness and abrupt changes in the data. The expression for calculating the acceleration matrix is ​​as follows:

[0118] In the formula, M accel (i, t) are the elements of the acceleration matrix of the i-th sensor at time t, M rate (i, t-Δt) is the element of the rate of change matrix of the i-th sensor at time t-Δt, that is, the element of the rate of change matrix at the previous time.

[0119] Acceleration matrix M accel It can be used to identify the degree of drastic change in rock strata. When the acceleration value continues to rise and exceeds a certain threshold, it may indicate that the rock strata are undergoing fracture propagation or interlayer slip.

[0120] Based on the rate of change and acceleration matrix, fluctuation amplitude analysis parameters are calculated to identify abnormal fluctuations in the data. The formula for calculating fluctuation amplitude is as follows:

[0121] In the formula, A wave (i) represents the fluctuation amplitude analysis parameter of the i-th sensor. It is the average rate of change of the i-th sensor, and T is the total number of time points;

[0122] Fluctuation Amplitude Analysis Parameter A wave It can identify abnormal fluctuations from different sensors. When the fluctuation amplitude exceeds a set threshold, it indicates abnormal changes in the rock strata in the area where the sensor is located, requiring close attention.

[0123] Combined with the rate of change M rate (i, t), acceleration M accel (i, t) and fluctuation amplitude parameter A wave (i) Calculate the nonlinear risk assessment index, which is used to ultimately distinguish between normal changes and potential roof instability risks. The calculation formula is as follows:

[0124] R risk (i)=α·M rate (i,t)+β·M accel (i,t)+γ·A wave (i), where R risk (i) is the nonlinear risk assessment index of the i-th sensor, where α, β, and γ are all weighting parameters, and α is used to adjust the rate of change M. rateThe impact of (i, t) on the overall risk assessment, β is used to adjust the acceleration M accel The influence of the (i, t) parameter, γ is used to adjust the fluctuation amplitude parameter A. wave The effect of (i).

[0125] Nonlinear risk assessment index R risk The level of the index directly reflects the instability of the roof strata. When the index value exceeds a certain warning threshold, the system will automatically issue a warning signal, indicating that there may be a risk of roof instability in the area.

[0126] Based on collected historical and real-time data, the early warning model is continuously optimized using adaptive learning algorithms, enabling it to automatically adjust parameters according to new data patterns, improve its adaptability to different geological environments, and thus enhance the accuracy and real-time performance of the early warning.

[0127] Based on collected historical and real-time data, an adaptive learning algorithm is used to continuously optimize the early warning model, enabling it to automatically adjust parameters according to new data patterns and improve its adaptability to different geological environments. The specific steps to enhance the accuracy and real-time performance of the early warning system are as follows:

[0128] First, a basic early warning model is constructed based on the collected historical and real-time data. Key parameters are defined, including displacement change rate, pressure change rate, and environmental characteristic parameter weights. To comprehensively consider the impact of multi-dimensional data, a data weight matrix is ​​used to represent the contribution of each parameter to the early warning model, as shown in the following formula:

[0129] In the formula, M0 is the basic early warning weight matrix, which represents the weight distribution of each parameter in the initial model. w1, w2, ..., w9 are the weights of different data types (displacement, pressure, geological features) at different time points. These weight values ​​are obtained through regression analysis of historical data and will be dynamically updated in subsequent steps.

[0130] This step establishes the basic weight structure of the early warning model. The values ​​of the weight matrix M0 represent the degree of influence of different data on the early warning, providing a basis for subsequent dynamic adjustments.

[0131] During real-time monitoring, based on the current displacement change rate and pressure change rate, the abnormal deviation rate between the actual data and the model prediction value is calculated. The formula for calculating the abnormal deviation rate is as follows:

[0132] In the formula, D t It is the outlier rate, used to measure the degree of outlier in the current data, V. t It is the real-time displacement change rate. It is the rate of change of displacement predicted by the model, P t It is the real-time pressure change rate. It is the rate of change of pressure predicted by the model;

[0133] By calculating the abnormal deviation rate D t It identifies the degree of anomalies in real-time data, providing input values ​​for the dynamic optimization of the model.

[0134] Based on the calculated abnormal deviation rate D t The weight values ​​of the basic weight matrix M0 are dynamically adjusted to generate a new weight matrix. The generation formula is as follows: M t =M0+ω·D t ·I, where M t It is the weight matrix after real-time optimization, ω is the learning rate, which controls the magnitude of weight adjustment, and I is the identity matrix, used to maintain the consistency of the direction of weight adjustment;

[0135] Adjusted weight matrix M t This allows for a more accurate reflection of current geological environment changes, enabling early warning models to dynamically adapt to new data patterns. This is achieved by adjusting the weight matrix M. t This enables the early warning model to adapt to changes in the geological environment in real time and improves its ability to identify abnormal situations.

[0136] Based on the optimized weight matrix M t The warning threshold is recalculated to dynamically adjust the warning strategy for different areas. The formula for calculating the warning threshold is as follows:

[0137] In the formula, T t It is the real-time warning threshold, M t [p] is the p-th weight value in the optimized weight matrix, F p It is an influencing factor of geological characteristic parameters.

[0138] New warning threshold T t It can automatically adjust based on the geological characteristics of different regions and real-time monitoring data to ensure the accuracy and real-time performance of the early warning system. This is achieved by calculating the real-time early warning threshold T. t The system dynamically optimizes the early warning strategy, enabling it to flexibly adjust the early warning level and sampling frequency based on real-time data.

[0139] Specific Implementation Method 1: To achieve accurate monitoring of changes in the roof strata of a mine, multi-layered sensor deployment and dynamic sampling frequency adjustment are key steps. The core objective of this implementation method is to ensure that the sensor deployment covers different geological strata within the mine, thereby acquiring comprehensive data on strata displacement, stress changes, and fracture propagation. Simultaneously, by dynamically adjusting the sampling frequency, real-time monitoring and early warning can be achieved.

[0140] First, based on the mine's geological conditions, displacement and pressure sensors need to be deployed at different layers of the roof. During deployment, key areas such as the tunnel's arch, sidewalls, and fault junctions should be considered, as these areas are typically stress concentration points and prone to fracture propagation or interlayer slip. Sensor deployment should not only consider coverage but also redundancy to prevent data loss due to individual sensor malfunctions. Furthermore, selecting different types of sensors based on different geological environments is crucial. For example, laser displacement sensors can be chosen in soft rock layers, while high-sensitivity pressure sensors are more suitable for hard rock layers. This multi-layered deployment strategy ensures that the system can acquire comprehensive data on rock layer changes within the mine, avoiding the limitations of single-point monitoring.

[0141] After the sensors are deployed, a dynamic sampling frequency adjustment mechanism needs to be set up to achieve real-time monitoring of rock strata changes. Normally, the system collects data at a set initial sampling frequency, such as once per hour. However, when the system detects abnormal changes in sensor data in a certain area, such as sudden displacement or a rapid increase in pressure, the dynamic sampling mechanism will automatically trigger, immediately increasing the sampling frequency in that area to the minute or second level to capture critical changes. The advantage of this dynamic adjustment mechanism is that it can effectively cope with the uncertainty of rock strata changes, especially in the early stages of roof instability, accurately recording the changes and avoiding data delays or loss caused by a fixed sampling frequency.

[0142] Dynamic sampling frequency adjustment relies not only on real-time data feedback from sensors but also on a comprehensive assessment combining historical data trends and geological characteristic parameters. For example, in areas where fracture propagation has historically occurred, the system can set a lower warning threshold in advance to identify risk signals at an early stage. Linking the dynamic sampling mechanism with data analysis can significantly improve the system's monitoring accuracy, especially in complex geological environments, avoiding misjudgments or missed detections due to data fluctuations. This linkage mechanism ensures that the system not only passively responds to data changes but also proactively adjusts its sampling strategy based on environmental characteristics.

[0143] The combined application of multi-level sensor deployment and dynamic sampling frequency adjustment effectively solves problems such as data delay, monitoring blind spots, and high false alarm rates in online monitoring of mine roof delamination. In this way, the system can respond promptly to early abnormal changes in the mine roof, providing real-time data support and decision-making basis for mine safety management personnel. Future development can further optimize sensor sensitivity and data transmission rate, and introduce more types of sensors, such as fiber optic sensors and acoustic sensors, to improve the comprehensiveness and accuracy of data acquisition.

[0144] Specific Implementation Method 2: In the process of online monitoring of roof delamination in mines, relying solely on raw data collected by sensors is insufficient to accurately reflect the actual changes in rock strata. Therefore, by combining mine geological characteristic parameters, preprocessing the raw data, and then performing multi-dimensional data fusion analysis, the accuracy of data interpretation and the intelligence level of the monitoring system can be effectively improved.

[0145] First, a comprehensive collection of geological characteristic parameters of the mine is necessary. These parameters include the structural type of the rock strata, the distribution of faults and joints, the hardness of the rock strata, and the mining depth. This information is typically obtained through geological mapping, borehole sampling, and historical mine reports, and then categorized and entered into a geological information database. During the data entry process, the geological characteristics of different areas of the mine need to be labeled, dividing the mine into several monitoring sub-regions. The geological characteristic labels for each sub-region are crucial for subsequent data analysis, effectively preventing data analysis biases caused by neglecting geological differences.

[0146] After collecting the raw monitoring data, preprocessing is required to ensure its authenticity and reliability. Preprocessing includes data cleaning, noise reduction, and outlier identification. The mine environment is complex, and the data may contain a lot of noise interference, such as equipment vibration, airflow, or human operation. Therefore, the system needs to apply filtering algorithms to remove these interference signals and label and remove outliers. For example, if a sensor shows an extreme value change within a short period of time, while other sensors do not detect a similar change, this data can be considered an outlier and removed to avoid misleading subsequent analysis.

[0147] After data preprocessing, displacement, pressure, and geological characteristic parameter data need to be fused in multiple dimensions. In the temporal dimension, different types of data are synchronized with time stamps to ensure comparative analysis on the same timeline, identifying the temporal trend of rock strata changes. In the spatial dimension, sensor data from different layers are matched, and a 3D model is used to generate an overall trend map of rock strata changes. This multidimensional fusion analysis enables the system to comprehensively understand rock strata changes from both temporal and spatial perspectives, identifying potential delamination risks such as fracture propagation and interlayer slip.

[0148] After the fusion analysis is completed, the system can generate a mine environmental characteristic model based on the data analysis results. This model includes the changing trends, risk levels, and geological feature labels for each monitoring area. As new data is continuously collected, the system needs to dynamically update the environmental characteristic model to adapt to changes in different areas. This dynamic updating of the environmental characteristic model makes the monitoring system more intelligent and adaptable, enabling it to adjust monitoring strategies and early warning parameters according to different scenarios, significantly improving monitoring accuracy.

[0149] Specific Implementation Method 3: In the process of monitoring roof delamination in mines, relying solely on fixed early warning parameters is often insufficient to adapt to complex geological environments. Therefore, by generating environmental characteristic models and dynamically adjusting the early warning parameters and sampling frequency for each area, the accuracy and flexibility of early warning can be significantly improved.

[0150] The construction of the environmental characteristic model requires combining historical monitoring data, real-time acquired data, and geological characteristic parameters of the mine. The model divides the mine into different monitoring sub-regions and sets corresponding change patterns and risk level labels for each region. The model includes elements such as rock strata type, stress concentration areas, historical delamination locations, and change trends. The purpose of constructing the environmental characteristic model is to provide the system with a flexible monitoring and early warning strategy, achieving precise adaptation to different geological environments.

[0151] Guided by the environmental characteristic model, the system can adaptively adjust the sampling frequency and early warning threshold according to the geological characteristics and trends of different regions. For example, in soft rock areas, the system can lower the early warning threshold and increase the sampling frequency to capture signals of fracture propagation earlier; while in hard rock areas, the early warning threshold can be appropriately increased to reduce unnecessary high-frequency monitoring. This adaptive adjustment mechanism can significantly improve the system's monitoring efficiency and early warning accuracy, avoiding false alarms or missed alarms caused by fixed parameter settings.

[0152] As new data is continuously collected, the environmental characteristic model requires real-time feedback and optimization. The system can continuously adjust the model's parameter settings based on data analysis results, making it more closely reflect actual rock strata changes. This real-time optimization of the environmental characteristic model ensures that the system's monitoring strategy can be continuously upgraded as the mine environment changes, improving the long-term stability and reliability of the monitoring.

[0153] This invention, through multi-layered sensor deployment, dynamic sampling frequency adjustment, and multi-dimensional data fusion analysis, effectively improves the accuracy of roof delamination monitoring data interpretation and significantly reduces the risk of missed and false alarms. By combining the mine's geological characteristic parameters to generate an environmental characteristic model, the monitoring process can adaptively adjust to different geological environments, thereby more accurately identifying abnormal signals such as rock strata displacement, stress changes, and fracture propagation. Especially in soft rock layers or areas with dense faults, the system can detect subtle but continuous trends in advance, issuing timely warnings and avoiding delayed warnings or misjudgments caused by fixed thresholds and single data source analysis in traditional monitoring systems. Furthermore, the system can automatically adjust the sampling frequency when abnormal signals are detected, ensuring the capture of detailed data on key changes, thus significantly improving the real-time performance and reliability of monitoring.

[0154] This invention introduces an adaptive early warning mechanism based on environmental feature models, enabling the monitoring system to dynamically optimize early warning parameters and sampling strategies according to real-time changes in the mine, achieving more flexible monitoring and early warning management. For high-risk areas such as soft rock layers, the system automatically lowers the early warning threshold and increases the sampling frequency, while in more stable areas, unnecessary high-frequency monitoring can be reduced, improving system resource utilization efficiency. Simultaneously, the adaptive early warning mechanism possesses continuous optimization capabilities; the system can continuously adjust the environmental feature model based on real-time feedback, ensuring long-term efficient operation and avoiding problems such as "monitoring blind spots" or outdated strategies. This flexibility and continuous optimization capability not only reduce false alarm and false negative rates but also reduce the burden on mine management personnel, improving the safety, intelligence, and stability of online monitoring of mine roof delamination.

[0155] The above formulas are all dimensionless calculations. The formulas are derived from software simulations based on a large amount of collected data to obtain the most recent real-world results. The preset parameters in the formulas are set by those skilled in the art according to the actual situation.

[0156] The foregoing has only described certain exemplary embodiments of the present invention by way of illustration. Undoubtedly, those skilled in the art can modify the described embodiments in various ways without departing from the spirit and scope of the present invention. Therefore, the foregoing drawings and descriptions are illustrative in nature and should not be construed as limiting the scope of protection of the claims of the present invention.

[0157] It should be noted that, in this document, the use of relational terms such as "first" and "second" is merely for distinguishing one entity or operation from another, and does not necessarily require or imply any such actual relationship or order between these entities or operations. Furthermore, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitations, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes the element.

[0158] It should be understood that in the various embodiments of this application, the order of the above-mentioned processes does not imply the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of this application.

[0159] Those skilled in the art will recognize that the units and algorithm steps of the various examples described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this application.

[0160] Those skilled in the art will understand that, for the sake of convenience and brevity, the specific working processes of the systems, devices, and units described above can be referred to the corresponding processes in the foregoing method embodiments, and will not be repeated here.

[0161] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0162] In addition, the functional units in the various embodiments of this application can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit.

[0163] The above description is merely a specific embodiment of this application, but the scope of protection of this application is not limited thereto. Any variations or substitutions that can be easily conceived by those skilled in the art within the scope of the technology disclosed in this application should be included within the scope of protection of this application. Therefore, the scope of protection of this application should be determined by the scope of the claims.

[0164] The foregoing has only described certain exemplary embodiments of the present invention by way of illustration. Undoubtedly, those skilled in the art can modify the described embodiments in various ways without departing from the spirit and scope of the present invention. Therefore, the foregoing drawings and descriptions are illustrative in nature and should not be construed as limiting the scope of protection of the claims of the present invention.

Claims

1. A roof separation layer online monitoring method, characterized in that, Includes the following steps: Multiple sensors are deployed at different layers of the mine roof, and different types of sensor deployment schemes are selected according to geological conditions to comprehensively collect data on rock strata changes, ensuring wide coverage and comprehensive data collection. The sensor's dynamic sampling frequency is set, and the sampling interval is automatically adjusted according to the severity of changes in the roof strata. When a sudden displacement is detected, the sampling frequency is automatically increased to ensure that key changes are captured in real time. The collected raw monitoring data are preprocessed and combined with the geological characteristic parameters of the mine to incorporate the differences in the geological environment into the monitoring and analysis, thereby generating an environmental characteristic model. Multidimensional data fusion of displacement, pressure and geological parameters is performed to match different types of data in time and space dimensions, generate an overall trend map of rock strata change, and identify potential delamination locations and change patterns. A nonlinear trend recognition algorithm is used to analyze the results of multidimensional data fusion. By detecting the rate of change, acceleration and fluctuation amplitude of the data, early abnormal change signals of rock strata are identified, and normal changes and potential roof instability risks are distinguished. Based on collected historical and real-time data, the early warning model is continuously optimized using adaptive learning algorithms, enabling it to automatically adjust parameters according to new data patterns, improve its adaptability to different geological environments, and thus enhance the accuracy and real-time performance of the early warning. The specific steps for preprocessing the collected raw monitoring data, incorporating the differences in the geological environment into the monitoring analysis, and generating an environmental characteristic model are as follows: Collect geological characteristic parameters of the mine and establish a geological information database to provide comprehensive environmental basic information for subsequent data analysis; By correlating and matching monitoring data with geological characteristic parameters, the ability to interpret data fluctuations and the accuracy of analysis can be improved. By cleaning, denoising, and identifying outliers, the authenticity and reliability of monitoring data are ensured, and interference factors are reduced. Generate environmental characteristic models and dynamically adjust sampling and early warning strategies based on geological differences to improve the accuracy and adaptability of the monitoring system; The specific steps for identifying temporal patterns and potential risk signals of rock strata changes by dynamically matching displacement, pressure, and geological parameters over time to generate a sequence of change trends are as follows: Synchronize timestamps to establish a unified time series, ensuring that different types of data can be compared and analyzed on the same timeline; By analyzing the changing trends of time series data, the fluctuation patterns of rock strata displacement and pressure are identified, and the risk of delamination is preliminarily assessed. Establish a time correlation model to analyze the mutual influence and temporal relationship between displacement, pressure and geological parameters; Dynamically update trend sequences and adjust monitoring strategies in real time to ensure rapid response to changes in rock strata; The specific steps for integrating multi-level data in a spatial dimension, generating an overall trend map of rock strata changes using 3D modeling, and intuitively identifying key change areas and potential delamination locations are as follows: Spatial matching of sensor data from different layers generates a multi-layered change map of the mine roof, improving the comprehensiveness of data analysis; A 3D model is generated using spatial matching data to visually present changes in rock strata and identify key areas of change. By integrating temporal and spatial data, an overall trend map is generated, which shows the changing patterns of rock strata and potential delamination locations; High-risk areas are marked based on trend charts, and warning parameters are dynamically adjusted to improve the accuracy and flexibility of the system's warnings.

2. The roof separation layer online monitoring method according to claim 1, characterized in that, The specific steps for deploying multiple sensors at different layers of the mine roof, and selecting different types of sensor deployment schemes based on geological conditions, to comprehensively collect data on rock strata changes and ensure wide coverage and comprehensive data collection are as follows: By comprehensively analyzing the geological structure of the mine and identifying key monitoring areas, the accuracy and relevance of sensor deployment are ensured. Select appropriate sensor types and layout schemes based on different geological environments to cover key areas of displacement and stress changes; Three-dimensional sensors are installed at different levels of the mine roof to form a multi-layered monitoring network, ensuring comprehensive and reliable data collection. By optimizing sensor layout and introducing redundant data acquisition mechanisms, the stability of the monitoring system and the continuity of data acquisition can be improved.

3. The method for online monitoring of roof delamination according to claim 1, characterized in that, The specific steps for setting the dynamic sampling frequency of the sensor, automatically adjusting the sampling interval according to the severity of changes in the roof strata, and automatically increasing the sampling frequency when a sudden displacement is detected to ensure that key changes are captured in real time are as follows: The initial sampling frequency is set according to geological conditions and historical data to ensure that basic data collection covers early trends in roof changes; By using a real-time fluctuation monitoring mechanism to identify abnormal change signals in the data, the accuracy of identifying key changes can be improved. When an abnormal signal is detected, the sampling frequency is automatically increased to ensure that key changes are fully captured. By dynamically adjusting the sampling strategy through a multi-layered feedback mechanism, the sampling frequency can be flexibly and adaptively adapted to different changing scenarios.

4. The method for online monitoring of roof delamination according to claim 1, characterized in that, A nonlinear trend recognition algorithm is used to analyze the results of multidimensional data fusion. By detecting the rate of change, acceleration, and fluctuation amplitude of the data, early abnormal change signals of the rock strata are identified, and the specific steps to distinguish between normal changes and potential roof instability risks are as follows: When analyzing the results of multidimensional data fusion, a multidimensional rate of change matrix is ​​first constructed. The time derivatives of the collected displacement, pressure, and geological parameter data are then calculated to obtain the rate of change for each type of data. The formula for calculating the rate of change is as follows: In the formula, It is the first Each sensor in time Elements of the rate of change matrix at time t, It is the first Each sensor in time The original monitoring data at any given time, It is a time interval. It is the first Each sensor in time The raw monitoring data at the current moment, that is, the raw monitoring data at the previous moment; Based on the rate of change matrix, the acceleration matrix is ​​further calculated to measure the drasticness and abrupt changes in the data. The expression for calculating the acceleration matrix is ​​as follows: In the formula, It is the first Each sensor in time The elements of the acceleration matrix changing over time, It is the first Each sensor in time The elements of the rate of change matrix at time 1 are the elements of the rate of change matrix at the previous time 2.

5. The method for online monitoring of roof delamination according to claim 4, characterized in that, Based on the rate of change and acceleration matrix, fluctuation amplitude analysis parameters are calculated to identify abnormal fluctuations in the data. The formula for calculating fluctuation amplitude is as follows: In the formula, It is the first Fluctuation amplitude analysis parameters of each sensor It is the first The average rate of change of each sensor It represents the total number of points in time. Combined with rate of change acceleration and fluctuation amplitude parameters A nonlinear risk assessment index is calculated to ultimately distinguish between normal changes and potential roof instability risks. The calculation formula is as follows: In the formula, It is the first Nonlinear risk assessment index for individual sensors , as well as These are all weight parameters. Used to adjust the rate of change Impact on overall risk assessment Used to adjust acceleration The influence of parameters, Used to adjust fluctuation amplitude parameters The impact.

6. The method for online monitoring of roof delamination according to claim 1, characterized in that, Based on collected historical and real-time data, an adaptive learning algorithm is used to continuously optimize the early warning model, enabling it to automatically adjust parameters according to new data patterns and improve its adaptability to different geological environments. The specific steps to enhance the accuracy and real-time performance of the early warning system are as follows: First, a basic early warning model is constructed based on the collected historical and real-time data. Key parameters are defined, including displacement change rate, pressure change rate, and environmental characteristic parameter weights. To comprehensively consider the impact of multi-dimensional data, a data weight matrix is ​​used to represent the contribution of each parameter to the early warning model, as shown in the following formula: In the formula, This is the basic early warning weight matrix, representing the weight distribution of each parameter in the initial model. Weights for different data types at different points in time; During real-time monitoring, based on the current displacement change rate and pressure change rate, the abnormal deviation rate between the actual data and the model prediction value is calculated. The formula for calculating the abnormal deviation rate is as follows: In the formula, It is the abnormal deviation rate. It is the real-time displacement change rate. It is the rate of change of displacement predicted by the model. It is the real-time pressure change rate. It is the rate of change of pressure predicted by the model.

7. The method for online monitoring of roof delamination according to claim 6, characterized in that, Based on the calculated abnormal deviation rate Dynamically adjust the basic weight matrix The weights are used to generate a new weight matrix, as shown in the following formula: In the formula, It is the weight matrix after real-time optimization. It's the learning rate. It is the identity matrix; Based on the optimized weight matrix The warning threshold is recalculated to dynamically adjust the warning strategy for different areas. The formula for calculating the warning threshold is as follows: In the formula, It is a real-time warning threshold. It is the first in the optimized weight matrix Each weight value It is an influencing factor of geological characteristic parameters.

Images