A coal mine slope geological disaster risk monitoring system

Abstract

This invention relates to the field of coal mine monitoring technology, specifically a coal mine slope geological hazard risk monitoring system. The system includes a data synchronization and preprocessing module, a feature fusion and evaluation module, a rate of change curve construction module, a risk dynamic judgment module, an early warning parameter synthesis module, and an early warning message generation module. It acquires raw time-series data of the coal mine slope and integrates multi-source sequence data to obtain standardized spatiotemporal data. Coupled feature analysis is performed on the standardized spatiotemporal data to obtain a comprehensive stability index. Differential fitting is performed on the time-series sequence of the comprehensive stability index to obtain a rate of change curve. Inflection point characteristics and acceleration trends are analyzed to determine the risk level. The time required for the comprehensive stability index to reach the next risk level is predicted to obtain core early warning parameters. The core early warning parameters are combined with the location information of abnormal signal sources to generate structured early warning messages. This invention can improve the efficiency of coal mine slope geological hazard risk monitoring.

Description

Technical Field

[0001] This invention relates to the field of coal mine monitoring technology, and in particular to a coal mine slope geological disaster risk monitoring system. Background Technology

[0002] Existing coal mine slope geological hazard monitoring technologies have significant limitations in data processing. They lack an effective mechanism for integrating multi-source raw time-series data such as slope surface displacement, internal rock stress, rock vibration, and hydrological conditions. They fail to eliminate data format differences through unified timestamp alignment and normalization, resulting in insufficient spatiotemporal consistency of multi-source data. This makes it impossible to form a standardized data foundation that can support comprehensive analysis, thus lacking comprehensive and accurate data basis for subsequent slope stability assessments.

[0003] Existing technologies have shortcomings in risk assessment and early warning. Stability assessments often rely on single characteristic parameters and fail to analyze the correlation strength of different instability stages with overall stability based on historical instability data to determine reasonable feature contribution weights, resulting in significant deviations in the calculation of the comprehensive stability index. Furthermore, risk level determination often uses static threshold comparisons, making it difficult to dynamically analyze the inflection point characteristics and acceleration trends of the comprehensive stability index change rate curve. This makes it impossible to accurately predict when the stability index will reach the next risk level, resulting in insufficient dynamism and timeliness in early warning. Therefore, improving the accuracy and effectiveness of geological hazard risk monitoring and early warning for coal mine slopes has become an urgent problem to be solved. Summary of the Invention

[0004] To achieve the above objectives, the present invention provides a coal mine slope geological hazard risk monitoring system, characterized in that the system includes a data synchronization and preprocessing module, a feature fusion and evaluation module, a rate of change curve construction module, a risk dynamic judgment module, an early warning parameter synthesis module, and an early warning message generation module, wherein: The data synchronization preprocessing module is used to acquire the original time-series data of the coal mine slope and integrate the multi-source sequence data in the original time-series data to obtain the standardized spatiotemporal data of the coal mine slope. The feature fusion evaluation module is used to perform coupled feature analysis on the standardized spatiotemporal data based on the historical instability data of the coal mine slope, and obtain the comprehensive stability index of the standardized spatiotemporal data. The rate of change curve construction module is used to perform difference fitting on the time series of the stability composite index to obtain the rate of change curve of the stability composite index. The risk dynamic judgment module is used to analyze the inflection point characteristics and acceleration trend of the rate of change curve based on a preset risk association rule base in order to determine the risk level of the coal mine slope. The early warning parameter synthesis module is used to extrapolate and predict the time required for the comprehensive stability index to reach the next level of risk based on the rate of change curve, and to perform parameter fusion on the time required and the risk level to obtain the early warning core parameters of the coal mine slope. The early warning message generation module is used to combine the early warning core parameters with the abnormal signal source location information of the standardized spatiotemporal data to generate a structured early warning message for the coal mine slope.

[0005] In a preferred embodiment, when the data synchronization preprocessing module acquires the original time-series data of the coal mine slope and integrates the multi-source sequence data in the original time-series data to obtain the standardized spatiotemporal data of the coal mine slope, it is specifically used for: The original time-series data of the coal mine slope are obtained by collecting information on slope surface displacement, internal rock stress, rock vibration, and hydrological status. By aligning the synthetic displacement sequence, rock pressure sequence, microseismic characteristic sequence, and pore water pressure sequence in the original time series data according to a unified timestamp, the aligned sequence data of the coal mine slope is obtained. The aligned sequence data is normalized to obtain the standardized spatiotemporal data of the coal mine slope.

[0006] In a preferred embodiment, when the feature fusion evaluation module performs coupled feature analysis on the standardized spatiotemporal data based on the historical instability data of the coal mine slope to obtain the comprehensive stability index of the standardized spatiotemporal data, it is specifically used for: Obtain historical instability data of the coal mine slope; The correlation strength between different stages of the slope instability process in the historical instability data and the overall stability loss of the slope is analyzed to obtain the stability contribution weights corresponding to the multi-source feature parameters of the standardized spatiotemporal data. Based on the stability contribution weights, the multi-source feature parameters are weighted and fused to obtain the comprehensive stability index of the standardized spatiotemporal data.

[0007] In a preferred embodiment, when the feature fusion evaluation module performs analysis on the correlation strength between different stages of the slope instability process in the historical instability data and the overall slope stability loss, and obtains the stability contribution weights corresponding to the multi-source feature parameters of the standardized spatiotemporal data, it is specifically used for: Using the key turning points of the slope state in the historical instability data as dividing points, the slope instability process in the historical instability data is divided into a stable stage, a deformation acceleration stage, and a sliding stage. From the historical instability data, extract the feature parameters corresponding to the multi-source feature parameters of the standardized spatiotemporal data during the stable phase, the deformation acceleration phase, and the slippage phase. Calculate the correlation strength between the aforementioned characteristic parameters and the overall stability loss of the slope; The proportion of the correlation strength is used as the stability contribution weight of the multi-source feature parameter.

[0008] In a preferred embodiment, when the rate of change curve construction module performs difference fitting on the time series of the stability composite index to obtain the rate of change curve of the stability composite index, it is specifically used for: The stability composite index is differentially analyzed at fixed time intervals to obtain a sequence of the rate of change of the stability composite index. The discrete data points of the rate of change sequence are constructed by taking the timestamp of the rate of change sequence as the independent variable and the rate of change value corresponding to the timestamp as the dependent variable. Spline interpolation is performed on the discrete data points to obtain the rate of change curve of the stability composite index.

[0009] In a preferred embodiment, when the rate of change curve construction module performs spline interpolation on the discrete data points to obtain the rate of change curve of the stability composite index, it is specifically used for: Based on the values ​​and time intervals of the discrete data points, and using the coordinates of the discrete data points as endpoints, a transition curve segment for the discrete data points is constructed. At the connection point of the transition curve segment, a smooth line constraint is applied to the transition curve segment to obtain a smooth curve segment of the transition curve segment. By connecting the smooth curve segments in chronological order, the rate of change curve of the stability composite index is obtained.

[0010] In a preferred embodiment, when the risk dynamic assessment module executes a pre-set risk association rule base to analyze the inflection point characteristics and acceleration trend of the rate of change curve to determine the risk level of the coal mine slope, it is specifically used for: The number of effective inflection points, the temporal distribution density, and the curvature amplitude at the inflection points of the rate of change curve are used as the inflection point characteristics of the rate of change curve. Differential analysis of the rate of change curve yields the trend of the rate of change acceleration. The statistical mean of the inflection point feature and the quantified value of the acceleration trend are compared with a threshold, and the state identifier of the coal mine slope is marked according to the comparison result. The status identifier is mapped to a preset risk association rule base to confirm the risk level of the coal mine slope.

[0011] In a preferred embodiment, when the early warning parameter synthesis module performs the extrapolation prediction based on the rate of change curve to determine the time required for the comprehensive stability index to reach the next risk level, and then performs parametric fusion of the time required and the risk level to obtain the core early warning parameters for the coal mine slope, it is specifically used for: The instantaneous rate of change of the stability composite index is determined based on the slope of the tangent line of the rate of change curve. By traversing the threshold sequence of the risk association rule base along the increasing direction of the risk level, the next level risk level threshold of the stability comprehensive index is obtained; Based on the instantaneous rate of change, the stability comprehensive index is linearly extrapolated to obtain the time required for the stability comprehensive index to reach the threshold of the next risk level. The required time is scaled to obtain a time scale value for the required time. Convert the risk level into a corresponding risk level value; The level value and the time scale value are combined and encapsulated to obtain the early warning core parameters of the coal mine slope.

[0012] In a preferred embodiment, when the early warning parameter synthesis module performs a linear extrapolation of the stability composite index based on the instantaneous rate of change to obtain the required time for the stability composite index to reach the next level risk level threshold, it is specifically used for: Using the instantaneous rate of change as a rate benchmark, and combining the quantitative difference between the comprehensive stability index and the next-level risk level threshold, a linear extrapolation relationship is established for the comprehensive stability index to reach the next-level risk level threshold. The linear extrapolation relationship is used to analyze the time required for the stability composite index to reach the next risk level threshold.

[0013] In a preferred embodiment, when the early warning message generation module combines the early warning core parameters with the abnormal signal source location information of the standardized spatiotemporal data to generate a structured early warning message for the coal mine slope, it is specifically used for: Spatial analysis is performed on the location information of the abnormal signal source in the standardized spatiotemporal data to obtain the three-dimensional spatial coordinates of the location information of the abnormal signal source. By binding the three-dimensional spatial coordinates with the early warning core parameters, the early warning elements of the coal mine slope are obtained; According to the preset early warning message template, the early warning elements are filled into the message fields corresponding to the early warning message template to generate the structured early warning message for the coal mine slope.

[0014] Compared with the prior art, the present invention has the following beneficial effects: 1. This invention integrates multi-source original time-series data of coal mine slopes through a data synchronization preprocessing module. After unified timestamp alignment and normalization, standardized spatiotemporal data is generated, effectively ensuring the spatiotemporal consistency of the data and providing a reliable data foundation for subsequent analysis. Then, the feature fusion evaluation module combines historical instability data to analyze the correlation strength of different instability stages with stability to determine the feature contribution weight. The comprehensive stability index obtained by weighted fusion is more accurate, significantly improving the accuracy of slope stability assessment.

[0015] 2. This invention obtains a smooth and accurate rate of change curve by differential fitting and spline interpolation of the time series of the stability comprehensive index through a rate of change curve construction module; a risk dynamic judgment module analyzes the inflection point characteristics and acceleration trend of the curve to accurately determine the risk level; an early warning parameter synthesis module extrapolates and predicts the time to reach the next level of risk and integrates parameters; and an early warning message generation module combines abnormal location information to generate structured messages, which greatly improves the accuracy, timeliness and pertinence of risk early warning, and provides strong technical support for the safety control of coal mine slopes. Attached Figure Description

[0016] Figure 1 This is a system architecture diagram of a coal mine slope geological disaster risk monitoring system provided in an embodiment of the present invention.

[0017] The realization of the objective, functional features and advantages of the present invention will be further explained in conjunction with the embodiments and with reference to the accompanying drawings. Detailed Implementation

[0018] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments belong to some, but not all, embodiments of the present invention. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0019] The terminology used in the embodiments of this invention is for the purpose of describing particular embodiments only and is not intended to limit the invention. The singular forms “said” and “the” as used in the embodiments of this invention and the appended claims are also intended to include the plural forms, and “multiple” generally includes at least two unless the context clearly indicates otherwise.

[0020] Depending on the context, the word "if" or "if" as used here can be interpreted as "when," "when," "in response to determination," or "in response to detection." Similarly, depending on the context, the phrase "if determination" or "if detection (of the stated condition or event)" can be interpreted as "when determination," "in response to determination," "when detection (of the stated condition or event)," or "in response to detection (of the stated condition or event)."

[0021] Furthermore, the timing of the steps in the following method embodiments is merely an example and not a strict limitation.

[0022] In practice, the server-side equipment deployed in a coal mine slope geological hazard risk monitoring system may consist of one or more devices. This coal mine slope geological hazard risk monitoring system can be implemented as: a business instance, a virtual machine, and hardware devices. For example, this coal mine slope geological hazard risk monitoring system can be implemented as a business instance deployed on one or more devices in a cloud node. Simply put, this coal mine slope geological hazard risk monitoring system can be understood as software deployed on a cloud node, used to provide a coal mine slope geological hazard risk monitoring system to various user terminals. Alternatively, this coal mine slope geological hazard risk monitoring system can also be implemented as a virtual machine deployed on one or more devices in a cloud node. This virtual machine contains application software for managing various user terminals. Alternatively, this coal mine slope geological hazard risk monitoring system can also be implemented as a server composed of numerous identical or different types of hardware devices, with one or more hardware devices configured to provide a coal mine slope geological hazard risk monitoring system to various user terminals.

[0023] In terms of implementation, the coal mine slope geological hazard risk monitoring system and the user terminal are mutually compatible. That is, if the coal mine slope geological hazard risk monitoring system is implemented as an application installed on a cloud service platform, then the user terminal is a client that establishes a communication connection with the application; or if the coal mine slope geological hazard risk monitoring system is implemented as a website, then the user terminal is implemented as a webpage; or if the coal mine slope geological hazard risk monitoring system is implemented as a cloud service platform, then the user terminal is implemented as a mini-program in an instant messaging application.

[0024] like Figure 1 The figure shown is a system architecture diagram of a coal mine slope geological disaster risk monitoring system provided in an embodiment of the present invention.

[0025] The coal mine slope geological hazard risk monitoring system 100 described in this invention can be installed on a cloud server. In terms of implementation, it can be used as one or more service devices, or as an application installed on the cloud (e.g., a mobile service operator's server, server cluster, etc.), or it can be developed as a website. Depending on the functions implemented, the coal mine slope geological hazard risk monitoring system 100 may include a data synchronization and preprocessing module 101, a feature fusion and evaluation module 102, a rate of change curve construction module 103, a risk dynamic judgment module 104, an early warning parameter synthesis module 105, and an early warning message generation module 106. The modules described in this invention can also be called units, referring to a series of computer program segments that can be executed by an electronic device's processor and perform a fixed function, stored in the electronic device's memory.

[0026] In this embodiment of the invention, in a coal mine slope geological hazard risk monitoring system, each of the above-mentioned modules can be implemented independently and can call other modules. Here, "calling" can be understood as one module connecting to multiple modules of another type and providing corresponding services to those connected modules. The coal mine slope geological hazard risk monitoring system provided by this embodiment of the invention allows for adjustment of the system's applicability by adding modules and directly calling them without modifying the program code, achieving cluster-based horizontal expansion and enabling quick and flexible expansion of the coal mine slope geological hazard risk monitoring system. In practical applications, the above modules can be set in the same device or different devices, or in virtual devices, such as service instances in a cloud server.

[0027] The following describes, with reference to specific embodiments, each component and its specific workflow of a coal mine slope geological hazard risk monitoring system: The data synchronization preprocessing module 101 is used to acquire the original time-series data of the coal mine slope and integrate the multi-source sequence data in the original time-series data to obtain the standardized spatiotemporal data of the coal mine slope. In this embodiment of the invention, when the data synchronization preprocessing module acquires the original time-series data of the coal mine slope and integrates the multi-source sequence data in the original time-series data to obtain the standardized spatiotemporal data of the coal mine slope, it is specifically used for: The original time-series data of the coal mine slope are obtained by collecting information on slope surface displacement, internal rock stress, rock vibration, and hydrological status. By aligning the synthetic displacement sequence, rock pressure sequence, microseismic characteristic sequence, and pore water pressure sequence in the original time series data according to a unified timestamp, the aligned sequence data of the coal mine slope is obtained. The aligned sequence data is normalized to obtain the standardized spatiotemporal data of the coal mine slope.

[0028] By deploying displacement monitoring equipment in key monitoring areas of coal mine slopes, the positional changes of each monitoring point on the slope surface at different time points are continuously recorded to obtain slope surface displacement information; stress sensors are pre-installed inside the rock mass of the slope to collect pressure data on the rock mass at different times in real time, obtaining internal stress information of the rock mass; vibration sensors are installed at key parts of the slope that are prone to vibration to capture data such as vibration frequency and amplitude of the rock mass at different times, forming rock mass vibration information; hydrological monitoring devices are set up around the slope and inside the rock mass to collect data such as pore water pressure and groundwater level at different time points, obtaining hydrological status information; the collected slope surface displacement information, internal rock mass stress information, rock mass vibration information, and hydrological status information are integrated to form the original time-series data of the coal mine slope.

[0029] First, a unified time recording standard is determined as the reference timestamp for aligning the data sequences. Then, synthetic displacement sequences, rock pressure sequences, microseismic characteristic sequences, and pore water pressure sequences are extracted from the original time-series data, and the original timestamp corresponding to each data point in each sequence is identified. Using the unified reference timestamp as a reference, the original timestamps of the data in each sequence are checked one by one, and data with the same original timestamp as the reference timestamp are matched accordingly. If a sequence has missing data at a given reference timestamp, the preceding and following valid data points in that sequence are found, and the missing data at that reference timestamp is supplemented using appropriate completion methods. This ensures that each reference timestamp contains complete data for synthetic displacement sequences, rock pressure sequences, microseismic characteristic sequences, and pore water pressure sequences, ultimately yielding the aligned sequence data for the coal mine slope.

[0030] First, the synthetic displacement sequence, rock pressure sequence, microseismic characteristic sequence, and pore water pressure sequence in the aligned sequence data are processed separately, and the maximum and minimum values ​​of all data in each sequence are calculated one by one. For each data in the synthetic displacement sequence, the minimum value of the synthetic displacement sequence is subtracted from the data, and then divided by the difference between the maximum and minimum values ​​of the synthetic displacement sequence to obtain the normalized result of the data. Following the same calculation method, each data in the rock pressure sequence, microseismic characteristic sequence, and pore water pressure sequence is calculated separately, and all data in the sequence are converted to the range of 0 to 1. After completing the normalization calculation of all sequence data, the standardized spatiotemporal data of the coal mine slope are obtained by integration.

[0031] The beneficial effects include the ability to comprehensively collect multi-dimensional raw data of coal mine slopes and form raw time-series data. By using unified timestamp alignment processing, the time differences between different series of data are eliminated, ensuring the consistency of data in the time dimension. Subsequent normalization processing eliminates the magnitude differences between different types of data, enabling the data to have a unified measurement standard. The resulting standardized spatiotemporal data can provide accurate, unified, and reliable data support for subsequent feature fusion assessment and other modules, effectively ensuring the accuracy of subsequent slope stability analysis and risk assessment.

[0032] The feature fusion evaluation module 102 is used to perform coupled feature analysis on the standardized spatiotemporal data based on the historical instability data of the coal mine slope, and obtain the comprehensive stability index of the standardized spatiotemporal data. In this embodiment of the invention, when the feature fusion evaluation module performs coupled feature analysis on the standardized spatiotemporal data based on the historical instability data of the coal mine slope to obtain the comprehensive stability index of the standardized spatiotemporal data, it is specifically used for: Obtain historical instability data of the coal mine slope; The correlation strength between different stages of the slope instability process in the historical instability data and the overall stability loss of the slope is analyzed to obtain the stability contribution weights corresponding to the multi-source feature parameters of the standardized spatiotemporal data. Based on the stability contribution weights, the multi-source feature parameters are weighted and fused to obtain the comprehensive stability index of the standardized spatiotemporal data.

[0033] When the feature fusion evaluation module analyzes the correlation strength between different stages of the slope instability process in the historical instability data and the overall slope stability loss, and obtains the stability contribution weights corresponding to the multi-source feature parameters of the standardized spatiotemporal data, it is specifically used for: Using the key turning points of the slope state in the historical instability data as dividing points, the slope instability process in the historical instability data is divided into a stable stage, a deformation acceleration stage, and a sliding stage. From the historical instability data, extract the feature parameters corresponding to the multi-source feature parameters of the standardized spatiotemporal data during the stable phase, the deformation acceleration phase, and the slippage phase. Calculate the correlation strength between the aforementioned characteristic parameters and the overall stability loss of the slope; The proportion of the correlation strength is used as the stability contribution weight of the multi-source feature parameter.

[0034] The complete monitoring records of past instability events of the coal mine slope were retrieved from the database of historical monitoring data stored in the coal mine. These records contain information on the changes of data such as slope surface displacement, internal rock stress, rock vibration, and hydrological conditions over time. They also contain relevant information such as the specific time, instability range, and degree of instability of each instability event. By sorting through these retrieved records, the historical instability data of the coal mine slope were obtained.

[0035] By examining the changes in slope displacement rate and rock mass stress change rate in historical instability data, the points when the displacement rate begins to rise significantly from a slow, stable state, and the points when the stress change rate suddenly accelerates from a flat state, are identified as key inflection points in the slope's condition. Using these two key inflection points as dividing points, the time periods between adjacent key inflection points are defined as follows: the period when both displacement rate and stress change rate remain slow and have small fluctuations is defined as the stable stage of the slope instability process; the period when the displacement rate and stress change rate begin to rise rapidly and fluctuate more is defined as the deformation acceleration stage of the slope instability process; and the period when the displacement rate and stress change rate reach their peak and are closest to the time of the instability event is defined as the pre-slip stage of the slope instability process. Thus, the slope instability process in historical instability data is divided into a stable stage, a deformation acceleration stage, and a pre-slip stage.

[0036] First, it is clarified that the multi-source characteristic parameters of the standardized spatiotemporal data specifically include the characteristic parameters corresponding to the synthetic displacement sequence, rock mass pressure sequence, microseismic characteristic sequence, and pore water pressure sequence. Then, in the stable stage, deformation acceleration stage, and slippage stage of the historical instability data, data consistent with these multi-source characteristic parameter types are selected respectively. For example, historical slope displacement data corresponding to the synthetic displacement sequence, historical rock mass internal pressure data corresponding to the rock mass pressure sequence, historical rock mass vibration frequency and amplitude data corresponding to the microseismic characteristic sequence, and historical rock mass pore water pressure data corresponding to the pore water pressure sequence. These selected data are extracted from the historical instability data of the three stages respectively to obtain the characteristic parameters corresponding to the multi-source characteristic parameters of the standardized spatiotemporal data in the stable stage, deformation acceleration stage, and slippage stage.

[0037] The formula for calculating the correlation strength between characteristic parameters and the overall stability loss of the slope is as follows: ; In the formula, Indicates the strength of the association. Indicates the first Historical feature parameter values ​​collected at each time point This represents the arithmetic mean of the historical feature parameter sequence. Indicates the first The quantitative values ​​of the overall slope stability at each time point. The arithmetic mean of the quantitative sequence of the overall stability state of the slope. This represents the total number of valid data points included during the instability phase. This represents the square root operation. This indicates a summation operation.

[0038] When calculating the correlation strength between characteristic parameters and the overall stability loss of the slope, the required data is first determined as follows: the historical characteristic parameter values ​​collected at each time point are the specific values ​​of the characteristic parameters extracted in the three stages at each time point; the arithmetic mean of the historical characteristic parameter sequence is the result obtained by adding up the historical characteristic parameter values ​​at all time points in the three stages and then dividing the sum by the total number of values; the quantitative value of the overall stability state of the slope corresponding to each time point is the quantitative result determined according to a unified standard based on the slope displacement, stress, hydrological and other states at the corresponding time point in the historical instability data; the arithmetic mean of the quantitative sequence of the overall stability state of the slope is the result obtained by adding up the stability state quantitative values ​​at all time points in the three stages and then dividing the sum by the total number of quantitative values; and the total number of valid data points in the instability stage is the total number of time points in the three stages that simultaneously have historical characteristic parameter values ​​and corresponding stability state quantitative values. The calculations are then performed as follows: First, subtract the arithmetic mean of the historical characteristic parameter sequence from the historical characteristic parameter value at each time point to obtain the deviation of the historical characteristic parameter value at that time point. Simultaneously, subtract the arithmetic mean of the stability state quantification sequence from the stability state quantification value at each time point to obtain the deviation of the stability state quantification value at that time point. Next, multiply the two deviations at the same time point to obtain the deviation product. Add the deviation products of all time points to obtain the total deviation product. Then, calculate the square of the deviation of each historical characteristic parameter value and add them together to obtain the sum of squares of the historical characteristic parameter deviations. Calculate the square of the deviation of each stability state quantification value and add them together to obtain the sum of squares of the stability state quantification deviations. Then, multiply the two sums of squares and take the square root of the product to obtain the square root of the deviation sum of squares. Finally, divide the total deviation product by this square root to obtain the correlation strength between the characteristic parameters and the overall stability loss of the slope.

[0039] First, calculate the absolute value of the correlation strength of each of the multi-source feature parameters. Add these absolute values ​​to obtain the sum of the absolute values ​​of the correlation strength. Then, divide the absolute value of the correlation strength of each multi-source feature parameter by the sum of the absolute values ​​of the correlation strength to obtain the proportion of the correlation strength of each multi-source feature parameter. Determine this proportion as the stability contribution weight corresponding to the multi-source feature parameter, and thus obtain the stability contribution weight corresponding to the multi-source feature parameters of the standardized spatiotemporal data.

[0040] First, extract the multi-source feature parameters from the standardized spatiotemporal data, including the feature parameters and their specific values ​​corresponding to the synthetic displacement sequence, rock mass pressure sequence, microseismic feature sequence, and pore water pressure sequence. Then, multiply the specific value of each multi-source feature parameter by its corresponding stability contribution weight to obtain the weighted value of each multi-source feature parameter. Finally, sum the weighted values ​​of all multi-source feature parameters to obtain the comprehensive stability index of the standardized spatiotemporal data.

[0041] The beneficial effects are as follows: by retrieving and organizing historical records from the database to obtain complete historical instability data of coal mine slopes, key turning points are determined based on displacement and stress change rates to accurately divide the instability stages, characteristic parameters corresponding to the stages are extracted according to the types of multi-source characteristic parameters, and the correlation strength between the characteristic parameters and the overall stability loss of the slope is calculated through detailed steps. The accurate stability contribution weight is determined based on the correlation strength ratio, and finally, the multi-source characteristic parameters are weighted and fused according to the weight to obtain the comprehensive stability index. Each step of the entire process has a clear and detailed implementation method to ensure that the obtained comprehensive stability index is accurate and reliable, which can provide accurate data support for subsequent geological hazard risk assessment of coal mine slopes and effectively improve the scientificity and accuracy of risk monitoring.

[0042] The rate of change curve construction module 103 is used to perform difference fitting on the time series of the stability comprehensive index to obtain the rate of change curve of the stability comprehensive index. In this embodiment of the invention, when the rate of change curve construction module performs difference fitting on the time series of the stability composite index to obtain the rate of change curve of the stability composite index, it is specifically used for: The stability composite index is differentially analyzed at fixed time intervals to obtain a sequence of the rate of change of the stability composite index. The discrete data points of the rate of change sequence are constructed by taking the timestamp of the rate of change sequence as the independent variable and the rate of change value corresponding to the timestamp as the dependent variable. Spline interpolation is performed on the discrete data points to obtain the rate of change curve of the stability composite index.

[0043] When the rate of change curve construction module performs spline interpolation on the discrete data points to obtain the rate of change curve of the stability composite index, it is specifically used for: Based on the values ​​and time intervals of the discrete data points, and using the coordinates of the discrete data points as endpoints, a transition curve segment for the discrete data points is constructed. At the connection point of the transition curve segment, a smooth line constraint is applied to the transition curve segment to obtain a smooth curve segment of the transition curve segment. By connecting the smooth curve segments in chronological order, the rate of change curve of the stability composite index is obtained.

[0044] First, determine a fixed time interval, such as 24 hours, and record the stability index at the same time each day. From the time series of the stability index, extract the stability index values ​​corresponding to two adjacent fixed time nodes. Subtract the stability index value of the previous time node from the stability index value of the later time node to obtain the change in the stability index between these two time nodes. The ratio of this change to the fixed time interval is the rate of change of the stability index within that time interval. Arrange the rates of change corresponding to each fixed time interval in order from morning to night to obtain the rate of change sequence of the stability index.

[0045] Extract the time node corresponding to each rate of change from the rate of change sequence. This time node is the timestamp of the rate of change sequence. Take each timestamp as the independent variable and the corresponding rate of change value as the dependent variable. Match each timestamp with its corresponding rate of change value to form a set of coordinate data containing timestamps and rate of change values. Each set of coordinate data is a discrete data point of the rate of change sequence. Organize and summarize all the discrete data points to form a set of discrete data points of the rate of change sequence.

[0046] First, extract the coordinate values ​​of all discrete data points, including the timestamp and the corresponding rate of change, while confirming the previously set fixed time interval. Select two adjacent discrete data points, using the coordinate value of the first discrete data point as the starting endpoint and the coordinate value of the second discrete data point as the ending endpoint. Based on the difference in coordinate values ​​between these two endpoints and the length of the fixed time interval, draw a curve connecting the two endpoints. This curve is the transition curve segment between the two discrete data points. Following the timestamp order of the discrete data points, perform the above operation sequentially for every two adjacent discrete data points to construct corresponding transition curve segments between all adjacent discrete data points.

[0047] Identify all connection points between transition curve segments. These connection points are the endpoints of the preceding and following transition curve segments, and their coordinates remain consistent across both segments. At each connection point, analyze the tangent directions of the preceding and following transition curve segments. Adjust the curvature of the two transition curve segments near the connection point so that the tangent direction of the preceding and following transition curve segments at the connection point is completely consistent with that of the following transition curve segment, ensuring a smooth transition without sharp angles. After these adjustments, each transition curve segment becomes a smooth, continuous curve segment.

[0048] According to the time sequence of the discrete data point timestamps from morning to night, all smooth curve segments are connected sequentially to ensure that the ending point of the previous smooth curve segment coincides with the starting point of the next smooth curve segment, and the curve trend remains consistent; connect all smooth curve segments into a complete continuous curve, which is the rate of change curve of the stability composite index.

[0049] The beneficial effects are as follows: By performing differential calculations on the stability comprehensive index at fixed time intervals, the rate of change within different time periods can be accurately obtained and a rate of change sequence can be formed, ensuring the temporal consistency and accuracy of the rate of change data; by constructing discrete data points with timestamps and corresponding rate of change values, a clear correspondence between time and rate of change is established, providing a reliable basis for subsequent interpolation operations; by constructing transition curve segments and applying smoothing line constraints at connection points, the problem of broken lines when connecting curves is effectively eliminated, making the trend of smooth curve segments coherent; the rate of change curve obtained by connecting smooth curve segments in chronological order can completely and accurately present the changing trend of the stability comprehensive index, providing a clear and reliable curve basis for the subsequent risk dynamic judgment module to analyze the inflection point characteristics and the trend of change acceleration, thereby improving the accuracy and reliability of trend analysis of geological disaster risk monitoring on coal mine slopes.

[0050] The risk dynamic judgment module 104 is used to analyze the inflection point characteristics and acceleration trend of the rate of change curve based on a preset risk association rule base in order to determine the risk level of the coal mine slope. In this embodiment of the invention, when the risk dynamic determination module executes a preset risk association rule base to analyze the inflection point characteristics and acceleration trend of the rate of change curve to determine the risk level of the coal mine slope, it is specifically used for: The number of effective inflection points, the temporal distribution density, and the curvature amplitude at the inflection points of the rate of change curve are used as the inflection point characteristics of the rate of change curve. Differential analysis of the rate of change curve yields the trend of the rate of change acceleration. The statistical mean of the inflection point feature and the quantified value of the acceleration trend are compared with a threshold, and the state identifier of the coal mine slope is marked according to the comparison result. The status identifier is mapped to a preset risk association rule base to confirm the risk level of the coal mine slope.

[0051] Observe the trend of the rate of change curve, identify all points where the slope changes from positive to negative or vice versa, and designate these points as candidate inflection points. Set a very small threshold for slope change, for example, the absolute value of the slope change is less than 0.001. Calculate the slope change value at each candidate inflection point, and exclude candidate points whose absolute slope change value is less than the threshold. The remaining candidate points are the valid inflection points. Count the total number of valid inflection points to obtain the number of valid inflection points of the rate of change curve. Record the timestamps corresponding to all valid inflection points, find the timestamps of the earliest and latest valid inflection points, and use the latest timestamp... The time span of the effective inflection point is obtained by subtracting the earliest timestamp from the previous timestamp. The temporal distribution density of the rate of change curve is obtained by dividing the number of effective inflection points by the time span. For each effective inflection point, a curve segment with a fixed time interval before and after the inflection point is selected. The average slope of the previous curve segment and the average slope of the next curve segment are calculated. The average slope of the next curve segment is subtracted from the average slope of the previous curve segment, and the absolute value of the difference is used to obtain the curvature amplitude at the effective inflection point. The curvature amplitude calculation of all effective inflection points is completed. The number of effective inflection points, the temporal distribution density, and the curvature amplitude at the inflection point are used together as the inflection point characteristics of the rate of change curve.

[0052] Using the fixed time intervals previously set when processing the stability composite index, extract the rate of change value corresponding to each fixed time interval endpoint from the rate of change curve. Calculate the rate of change values ​​for two adjacent endpoints, subtracting the rate of change value of the previous endpoint from the rate of change value of the latter endpoint to obtain the change in rate of change within that fixed time interval. Divide the change in rate of change by the duration of the fixed time interval to obtain the acceleration value of the rate of change curve within that time interval. Arrange all the calculated acceleration values ​​sequentially according to the time interval order, observe the overall direction of change of the acceleration values, and calculate the arithmetic mean of all acceleration values. This average value is the quantified value of the trend of changing acceleration. If the average value is positive, it indicates that the changing acceleration is increasing; if the average value is negative, it indicates that the changing acceleration is decreasing; if the average value is close to zero, it indicates that the changing acceleration is stable. Thus, the trend of changing acceleration of the rate of change curve is obtained.

[0053] The system retrieves threshold values ​​for the statistical mean of inflection point features from a pre-defined risk association rule base. These threshold values ​​include the threshold for the number of effective inflection points, the threshold for time-series distribution density, and the threshold for the average curvature amplitude at inflection points. Simultaneously, it retrieves the threshold value for the quantitative value of the acceleration trend. The system calculates the statistical mean of the inflection point features. The statistical mean of the number of effective inflection points is the total number of effective inflection points obtained previously. The statistical mean of the time-series distribution density is the time-series distribution density value obtained previously. The statistical mean of the curvature amplitude at inflection points is the arithmetic mean of the curvature amplitudes at all effective inflection points. The system compares the statistical mean of the number of effective inflection points with the threshold for the number of effective inflection points. If the value is greater than the threshold, the system is considered compliant; otherwise, it is considered non-compliant. Similarly, the system compares the statistical mean of the time-series distribution density with the threshold for the time-series distribution density. If the value is greater than the threshold, the system is considered compliant; otherwise, it is considered non-compliant. The statistical mean of curvature amplitude at the inflection point is compared with a threshold value for the mean curvature amplitude. If the mean value is greater than the threshold, it is considered compliant; otherwise, it is considered non-compliant. The quantified value of the acceleration trend is compared with a threshold value for the acceleration trend. If the quantified value is greater than a positive threshold, it is considered accelerating; if it is less than a negative threshold, it is considered accelerating decreasing; if it is between the positive and negative thresholds, it is considered stable. Based on the above comparison results, a status identifier is marked. If two or more of the statistical means of the three inflection point features are compliant and the acceleration trend is accelerating, it is marked as a high-risk candidate. If one of the statistical means of the three inflection point features is compliant and the acceleration trend is stable, it is marked as a medium-risk candidate. If none of the statistical means of the three inflection point features are compliant and the acceleration trend is accelerating decreasing, it is marked as a low-risk candidate. This yields the status identifier for the coal mine slope.

[0054] Open the preset risk association rule base, which stores the correspondence between status identifiers and risk levels. Specifically, a high-risk status identifier corresponds to a level 1 risk, a medium-risk status identifier corresponds to a level 2 risk, and a low-risk status identifier corresponds to a level 3 risk. Match the previously marked status identifiers of the coal mine slope with the status identifiers in the rule base one by one to find the corresponding entry that is completely consistent with the current status identifier. Based on the matched entry, extract the risk level corresponding to the entry. This risk level is the risk level of the coal mine slope.

[0055] The beneficial effects are as follows: by accurately identifying effective inflection points and calculating the number of effective inflection points, the temporal distribution density, and the curvature amplitude at the inflection points, the authenticity and effectiveness of inflection point characteristics are ensured, providing a reliable characteristic basis for risk assessment; by calculating acceleration values ​​at fixed time intervals and determining the trend of changing acceleration, the dynamic change law of the rate of change curve is accurately captured, improving the accuracy of trend analysis; by meticulously comparing with preset thresholds to mark status indicators, and then mapping the status indicators to a preset risk association rule base to confirm the risk level, the risk level assessment process is standardized and controllable, effectively avoiding assessment bias, and comprehensively improving the dynamism, accuracy, and reliability of coal mine slope geological disaster risk assessment, providing accurate risk level references for subsequent early warning work.

[0056] The early warning parameter synthesis module 105 is used to extrapolate and predict the time required for the comprehensive stability index to reach the next level of risk based on the rate of change curve, and to perform parameter fusion on the time required and the risk level to obtain the early warning core parameters of the coal mine slope. In this embodiment of the invention, when the early warning parameter synthesis module extrapolates and predicts the time required for the comprehensive stability index to reach the next risk level based on the rate of change curve, and performs parameter fusion on the required time and the risk level to obtain the early warning core parameters of the coal mine slope, it is specifically used for: The instantaneous rate of change of the stability composite index is determined based on the slope of the tangent line of the rate of change curve. By traversing the threshold sequence of the risk association rule base along the increasing direction of the risk level, the next level risk level threshold of the stability comprehensive index is obtained; Based on the instantaneous rate of change, the stability comprehensive index is linearly extrapolated to obtain the time required for the stability comprehensive index to reach the threshold of the next risk level. The required time is scaled to obtain a time scale value for the required time. Convert the risk level into a corresponding risk level value; The level value and the time scale value are combined and encapsulated to obtain the early warning core parameters of the coal mine slope.

[0057] When the early warning parameter synthesis module performs a linear extrapolation of the stability comprehensive index based on the instantaneous rate of change to obtain the required time for the stability comprehensive index to reach the next level of risk threshold, it is specifically used for: Using the instantaneous rate of change as a rate benchmark, and combining the quantitative difference between the comprehensive stability index and the next-level risk level threshold, a linear extrapolation relationship is established for the comprehensive stability index to reach the next-level risk level threshold. The linear extrapolation relationship is used to analyze the time required for the stability composite index to reach the next risk level threshold.

[0058] Locate the curve point corresponding to the latest timestamp on the rate of change curve, and use this point as the target point for calculating the tangent slope. Select two extremely short time segments of equal duration before and after the target point, and extract the coordinate values ​​of the rate of change curve corresponding to the endpoints of these two time segments. Calculate the difference in rate of change and the time difference between these two coordinate values. Divide the difference in rate of change by the time difference to obtain the tangent slope of the rate of change curve at the target point. Directly determine this tangent slope as the instantaneous rate of change of the stability composite index.

[0059] Open the preset risk association rule library and retrieve the risk level threshold sequence of the stability comprehensive index. This sequence is arranged in ascending order of risk level from low to high. First, determine the current risk level of the coal mine slope. Then, find the threshold position corresponding to the current risk level from the threshold sequence and select the next threshold at that position. This threshold is the next level risk level threshold of the stability comprehensive index.

[0060] First, obtain the specific value of the current stability comprehensive index. Subtract the current stability comprehensive index value from the next-level risk level threshold to obtain the quantitative difference between the two. Use the previously determined instantaneous change rate of the stability comprehensive index as the rate benchmark. Assuming that the instantaneous change rate remains stable during the prediction period, establish a linear extrapolation relationship. Based on this relationship, divide the calculated quantitative difference by the instantaneous change rate to obtain the time required for the stability comprehensive index to reach the next-level risk level threshold, which is the required time.

[0061] The preset time scaling range is 0 to 10, and the maximum possible time required for the comprehensive stability index of the coal mine slope to reach the next risk level is determined. The calculated required time is divided by the preset maximum possible required time to obtain a ratio. If the ratio is greater than 10, the time scale value is set to 10; if the ratio is less than 0, the time scale value is set to 0; if the ratio is between 0 and 10, the ratio is directly used as the time scale value, thus completing the scaling process of the required time and obtaining the time scale value of the required time.

[0062] Retrieve the corresponding rules for risk levels and level values ​​from the risk association rule base; based on the currently determined coal mine slope risk level, find the completely matching entry in the corresponding rules, extract the specific value corresponding to the entry, and determine the value as the level value corresponding to the risk level.

[0063] First, determine that the combination format of the core early warning parameters is a string of "level value - time scale value"; convert the previously obtained level value to a string type, and also convert the time scale value to a string type; use a hyphen as a connector to concatenate the level value string and the time scale value string into a complete string; encapsulate the concatenated string into an independent data unit, which is the core early warning parameter for coal mine slopes.

[0064] The beneficial effects are as follows: Instantaneous change rate is determined by accurately calculating the slope of the tangent line of the change rate curve, ensuring the accuracy of the stability comprehensive index change rate; the next level threshold is obtained by traversing the threshold sequence in the direction of increasing risk level, ensuring the logic and relevance of threshold selection; the required time is calculated based on linear extrapolation, and a unified time dimension measurement standard is established through scaling processing; the level value conversion unifies the expression of risk level; finally, the core parameters of the early warning obtained through combination and encapsulation can clearly integrate risk level and early warning time information, providing accurate and standardized core data for the subsequent generation of structured early warning messages, effectively improving the practicality and transmission efficiency of early warning information.

[0065] The early warning message generation module 106 is used to combine the early warning core parameters with the abnormal signal source location information of the standardized spatiotemporal data to generate the structured early warning message for the coal mine slope.

[0066] In this embodiment of the invention, when the early warning message generation module combines the early warning core parameters with the abnormal signal source location information of the standardized spatiotemporal data to generate the structured early warning message for the coal mine slope, it is specifically used for: Spatial analysis is performed on the location information of the abnormal signal source in the standardized spatiotemporal data to obtain the three-dimensional spatial coordinates of the location information of the abnormal signal source. By binding the three-dimensional spatial coordinates with the early warning core parameters, the early warning elements of the coal mine slope are obtained; According to the preset early warning message template, the early warning elements are filled into the message fields corresponding to the early warning message template to generate the structured early warning message for the coal mine slope.

[0067] The location information of the abnormal signal source is extracted from standardized spatiotemporal data. This information includes the horizontal distance, horizontal direction angle, and vertical height data of the abnormal signal source relative to the preset benchmark point of the coal mine. A three-dimensional coordinate system is established with the center point of the main shaft as the origin. The x-axis is set along the direction of the coal mine slope, the y-axis is set perpendicular to the direction of the slope, and the z-axis is set vertically upward. The coordinate values ​​of the abnormal signal source on the x-axis and y-axis are calculated based on the horizontal distance and horizontal direction angle. The extracted vertical height data is directly used as the z-axis coordinate value, thereby obtaining the three-dimensional spatial coordinates of the abnormal signal source location information.

[0068] The obtained three-dimensional spatial coordinates of the abnormal signal source are associated and matched with the early warning core parameters to ensure that each set of three-dimensional spatial coordinates corresponds to a unique early warning core parameter. This association is organized into a structured data group containing two key information items: "three-dimensional coordinates of the abnormal signal source and early warning core parameters". This structured data group is the early warning element of the coal mine slope.

[0069] The pre-set early warning message template is retrieved. This template contains fixed message fields such as "early warning number, monitoring time, three-dimensional coordinates of the abnormal signal source, core parameters of the early warning, risk level description, and early warning handling suggestions". The early warning number is generated according to the rule of "coal mine unique identifier number - monitoring data processing date - early warning sequence number of the day". The monitoring time is filled with the timestamp of the current standardized spatiotemporal data being processed. The three-dimensional coordinates of the abnormal signal source in the early warning element are filled into the "three-dimensional coordinates of the abnormal signal source" field. The core parameters of the early warning element are filled into the "core parameters of the early warning" field. Then, the pre-set risk level description and early warning handling suggestions are matched with the level values ​​in the core parameters of the early warning and filled into the corresponding fields in sequence. After all fields are filled, a structured early warning message for coal mine slope with a standardized format and complete information is formed.

[0070] The beneficial effects are as follows: by performing three-dimensional spatial analysis on the location information of abnormal signal sources, the spatial coordinates of abnormal locations can be accurately determined, avoiding difficulties in locating risk areas caused by ambiguous location information; binding three-dimensional coordinates with core early warning parameters to form early warning elements can effectively integrate location information with key early warning data, preventing information fragmentation; and generating structured early warning messages according to preset templates can ensure that the format of early warning information is uniform and that key content is not omitted, making it easy for staff to quickly obtain core information such as abnormal location, early warning level, and handling suggestions, and significantly improving the transmission efficiency and practical handling guidance of early warning information for geological disasters on coal mine slopes.

[0071] It will be apparent to those skilled in the art that the present invention is not limited to the details of the exemplary embodiments described above, and that the present invention can be implemented in other specific forms without departing from the spirit or essential characteristics of the present invention.

[0072] This application embodiment can acquire and process relevant data based on artificial intelligence technology. Artificial intelligence is the theory, method, technology, and application system that uses digital computers or machines controlled by digital computers to simulate, extend, and expand human intelligence, perceive the environment, acquire knowledge, and use that knowledge to obtain optimal results.

[0073] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and are not intended to limit it. Although the present invention has been described in detail with reference to preferred embodiments, those skilled in the art should understand that modifications or equivalent substitutions can be made to the technical solutions of the present invention without departing from the spirit and scope of the technical solutions of the present invention.

Claims

1. A coal mine slope geological hazard risk monitoring system, characterized in that, The system includes a data synchronization and preprocessing module, a feature fusion and evaluation module, a rate of change curve construction module, a risk dynamic judgment module, an early warning parameter synthesis module, and an early warning message generation module, wherein: The data synchronization preprocessing module is used to acquire the original time-series data of the coal mine slope and integrate the multi-source sequence data in the original time-series data to obtain the standardized spatiotemporal data of the coal mine slope. The feature fusion evaluation module is used to perform coupled feature analysis on the standardized spatiotemporal data based on the historical instability data of the coal mine slope, and obtain the comprehensive stability index of the standardized spatiotemporal data. The rate of change curve construction module is used to perform difference fitting on the time series of the stability composite index to obtain the rate of change curve of the stability composite index. The risk dynamic judgment module is used to analyze the inflection point characteristics and acceleration trend of the rate of change curve based on a preset risk association rule base in order to determine the risk level of the coal mine slope. The early warning parameter synthesis module is used to extrapolate and predict the time required for the comprehensive stability index to reach the next level of risk based on the rate of change curve, and to perform parameter fusion on the time required and the risk level to obtain the early warning core parameters of the coal mine slope. The early warning message generation module is used to combine the early warning core parameters with the abnormal signal source location information of the standardized spatiotemporal data to generate a structured early warning message for the coal mine slope.

2. The coal mine slope geological hazard risk monitoring system as described in claim 1, characterized in that, When the data synchronization preprocessing module acquires the raw time-series data of the coal mine slope and integrates the multi-source sequence data in the raw time-series data to obtain the standardized spatiotemporal data of the coal mine slope, it is specifically used for: The original time-series data of the coal mine slope are obtained by collecting information on slope surface displacement, internal rock stress, rock vibration, and hydrological status. By aligning the synthetic displacement sequence, rock pressure sequence, microseismic characteristic sequence, and pore water pressure sequence in the original time series data according to a unified timestamp, the aligned sequence data of the coal mine slope is obtained. The aligned sequence data is normalized to obtain the standardized spatiotemporal data of the coal mine slope.

3. The coal mine slope geological hazard risk monitoring system as described in claim 1, characterized in that, When the feature fusion evaluation module performs coupled feature analysis on the standardized spatiotemporal data based on the historical instability data of the coal mine slope to obtain the comprehensive stability index of the standardized spatiotemporal data, it is specifically used for: Obtain historical instability data of the coal mine slope; The correlation strength between different stages of the slope instability process in the historical instability data and the overall stability loss of the slope is analyzed to obtain the stability contribution weights corresponding to the multi-source feature parameters of the standardized spatiotemporal data. Based on the stability contribution weights, the multi-source feature parameters are weighted and fused to obtain the comprehensive stability index of the standardized spatiotemporal data.

4. The coal mine slope geological hazard risk monitoring system as described in claim 3, characterized in that, When the feature fusion evaluation module analyzes the correlation strength between different stages of the slope instability process in the historical instability data and the overall slope stability loss, and obtains the stability contribution weights corresponding to the multi-source feature parameters of the standardized spatiotemporal data, it is specifically used for: Using the key turning points of the slope state in the historical instability data as dividing points, the slope instability process in the historical instability data is divided into a stable stage, a deformation acceleration stage, and a sliding stage. From the historical instability data, extract the feature parameters corresponding to the multi-source feature parameters of the standardized spatiotemporal data during the stable phase, the deformation acceleration phase, and the slippage phase. Calculate the correlation strength between the aforementioned characteristic parameters and the overall stability loss of the slope; The proportion of the correlation strength is used as the stability contribution weight of the multi-source feature parameter.

5. The coal mine slope geological hazard risk monitoring system as described in claim 1, characterized in that, When the rate of change curve construction module performs difference fitting on the time series of the stability composite index to obtain the rate of change curve of the stability composite index, it is specifically used for: The stability composite index is differentially analyzed at fixed time intervals to obtain a sequence of the rate of change of the stability composite index. The discrete data points of the rate of change sequence are constructed by taking the timestamp of the rate of change sequence as the independent variable and the rate of change value corresponding to the timestamp as the dependent variable. Spline interpolation is performed on the discrete data points to obtain the rate of change curve of the stability composite index.

6. The coal mine slope geological hazard risk monitoring system as described in claim 5, characterized in that, When the rate of change curve construction module performs spline interpolation on the discrete data points to obtain the rate of change curve of the stability composite index, it is specifically used for: Based on the values ​​and time intervals of the discrete data points, and using the coordinates of the discrete data points as endpoints, a transition curve segment for the discrete data points is constructed. At the connection point of the transition curve segment, a smooth line constraint is applied to the transition curve segment to obtain a smooth curve segment of the transition curve segment. By connecting the smooth curve segments in chronological order, the rate of change curve of the stability composite index is obtained.

7. The coal mine slope geological hazard risk monitoring system as described in claim 1, characterized in that, The risk dynamic assessment module, when executing a pre-set risk association rule base to analyze the inflection point characteristics and acceleration trend of the rate of change curve to determine the risk level of the coal mine slope, is specifically used for: The number of effective inflection points, the temporal distribution density, and the curvature amplitude at the inflection points of the rate of change curve are used as the inflection point characteristics of the rate of change curve. Differential analysis of the rate of change curve yields the trend of the rate of change acceleration. The statistical mean of the inflection point feature and the quantified value of the acceleration trend are compared with a threshold, and the state identifier of the coal mine slope is marked according to the comparison result. The status identifier is mapped to a preset risk association rule base to confirm the risk level of the coal mine slope.

8. The coal mine slope geological hazard risk monitoring system as described in claim 1, characterized in that, When the early warning parameter synthesis module performs the extrapolation prediction based on the rate of change curve to determine the time required for the comprehensive stability index to reach the next risk level, and then performs parameter fusion on the required time and the risk level to obtain the core early warning parameters for the coal mine slope, it is specifically used for: The instantaneous rate of change of the stability composite index is determined based on the slope of the tangent line of the rate of change curve. By traversing the threshold sequence of the risk association rule base along the increasing direction of the risk level, the next level risk level threshold of the stability comprehensive index is obtained; Based on the instantaneous rate of change, the stability comprehensive index is linearly extrapolated to obtain the time required for the stability comprehensive index to reach the threshold of the next risk level. The required time is scaled to obtain a time scale value for the required time. Convert the risk level into a corresponding risk level value; The level value and the time scale value are combined and encapsulated to obtain the early warning core parameters of the coal mine slope.

9. A coal mine slope geological hazard risk monitoring system as described in claim 8, characterized in that, When the early warning parameter synthesis module performs a linear extrapolation of the stability comprehensive index based on the instantaneous rate of change to obtain the required time for the stability comprehensive index to reach the next level of risk threshold, it is specifically used for: Using the instantaneous rate of change as a rate benchmark, and combining the quantitative difference between the comprehensive stability index and the next-level risk level threshold, a linear extrapolation relationship is established for the comprehensive stability index to reach the next-level risk level threshold. The linear extrapolation relationship is used to analyze the time required for the stability composite index to reach the next risk level threshold.

10. A coal mine slope geological hazard risk monitoring system as described in claim 1, characterized in that, When the early warning message generation module combines the early warning core parameters with the abnormal signal source location information of the standardized spatiotemporal data to generate the structured early warning message for the coal mine slope, it is specifically used for: Spatial analysis is performed on the location information of the abnormal signal source in the standardized spatiotemporal data to obtain the three-dimensional spatial coordinates of the location information of the abnormal signal source. By binding the three-dimensional spatial coordinates with the early warning core parameters, the early warning elements of the coal mine slope are obtained; According to the preset early warning message template, the early warning elements are filled into the message fields corresponding to the early warning message template to generate the structured early warning message for the coal mine slope.

Images