Tailing pond water level dynamic early warning system, method and equipment and storage medium

Abstract

The invention relates to the field of tailing pond supervision, and discloses a tailing pond water level dynamic early warning system, method and equipment and a storage medium. The system comprises a water level monitoring module used for continuously collecting real-time water level data of discrete point locations of a tailing pond area; the edge calculation module is used for preprocessing the real-time water level data and generating a corresponding trigger type inspection instruction; the trigger routing inspection module is used for responding to the trigger routing inspection instruction, executing a routing inspection task on a region corresponding to the trigger routing inspection instruction, and collecting spatial domain water level data of a tailing pond region; and the data processing module is used for fusing the water level field data and the water level prediction data according to the real-time water level data to generate multi-level safety early warning information. According to the application, through cooperative operation of all the modules, a set of three-dimensional monitoring and early warning system is constructed, evolution from traditional single passive monitoring to global active early warning is realized, and the accuracy and reliability of tailing pond safety monitoring are improved.

Description

Technical Field

[0001] This invention relates to the field of tailings dam monitoring, and in particular to a tailings dam water level dynamic early warning system, method, equipment and storage medium. Background Technology

[0002] Tailings dams are critical facilities in mining production, and their safe and stable operation is the lifeline of mining enterprises. The dynamic changes in water level within the dam are one of the core indicators for assessing its stability. Excessively high or rapidly rising water levels significantly increase the risk of dam failure. Therefore, real-time and accurate monitoring and early warning of water levels are core technical areas for preventing major safety accidents. Currently, this field mainly relies on installing water level gauges, video surveillance, and other sensing equipment at fixed points within the dam area to construct a ground-based monitoring network. Its core objective is to achieve continuous perception of the dam's water level status and to issue alarms for exceeding limits.

[0003] However, existing monitoring methods based on fixed sensors have significant technical bottlenecks: First, data reliability is insufficient. Single-point sensors are prone to data stagnation or distortion due to their own failures, probe accumulation, or data transmission interruptions, resulting in false alarms or missed alarms. Second, there is a lack of global and trend perception capabilities. Discrete point data cannot reflect the overall spatial distribution of water levels in the reservoir area, cannot effectively identify anomalies such as local dry beaches and seepage, and cannot build predictive models based on historical data to achieve early warning. Summary of the Invention

[0004] In view of this, the purpose of the present invention is to overcome the shortcomings of the prior art and provide a tailings dam water level dynamic early warning system, method, equipment and storage medium.

[0005] This invention provides the following technical solution: In a first aspect, the present invention provides a tailings dam water level dynamic early warning system, the system comprising an edge computing module, a trigger inspection module, a data processing module, and multiple water level monitoring modules; The water level monitoring module is used to continuously collect real-time water level data at discrete points in the tailings dam area; The edge computing module is used to preprocess the real-time water level data and generate corresponding trigger-based inspection commands. The triggered inspection module is used to respond to the triggered inspection command, perform inspection tasks on the area corresponding to the triggered inspection command, and collect spatial water level data of the tailings dam area. The data processing module is used to fuse the real-time water level data and the spatial domain water level data to generate fused water level field data, and based on the time series of the fused water level field data, to predict the water level height for a preset future time period to generate water level prediction data. Based on the real-time water level data, the fused water level field data and the water level prediction data, and combined with preset multi-level early warning rules, multi-level safety early warning information is generated.

[0006] In an optional implementation, the edge computing module includes a data stagnation diagnostic unit, and the trigger-based inspection command includes a first trigger-based inspection command. The data stagnation diagnosis unit is used to calculate the standard deviation of the real-time water level data of each water level monitoring module within a first preset time period, and to determine whether the standard deviation is less than a preset stability threshold. The data stagnation diagnosis unit is further configured to identify the corresponding water level monitoring module as a data stagnation abnormal water level monitoring module if there is a water level monitoring module whose standard deviation is less than the preset stability threshold, and generate a first trigger-type inspection command for the area where the data stagnation abnormal water level monitoring module is located.

[0007] In an optional implementation, the edge computing module further includes a rate of change diagnostic unit, and the trigger-type inspection command further includes a second trigger-type inspection command. The rate of change diagnostic unit is used to calculate the rate of change of water level of real-time water level data of each water level monitoring module within a second preset time period, and to determine whether the absolute value of the rate of change of water level is greater than a preset rate change threshold, wherein the second preset time period is shorter than the first preset time period. The rate of change diagnostic unit is further configured to determine that if the absolute value of the water level change rate is greater than the preset rate change threshold, the tailings dam area is in a state of rapid water level change, and generate a second type of triggered inspection command for the area where the water level monitoring module with the largest absolute value of the water level change rate is located and its downstream area.

[0008] In an optional implementation, the edge computing module further includes a spatial consistency diagnostic unit, and the triggered inspection command further includes a third triggered inspection command. The spatial consistency diagnostic unit is used to calculate the overall standard deviation of the real-time water level data of each of the water level monitoring modules, and to determine whether the overall standard deviation is greater than a preset spatial dispersion threshold. The spatial consistency diagnostic unit is further configured to determine that the tailings dam area is in an abnormal state of water level spatial distribution consistency if the overall standard deviation is greater than the preset spatial dispersion threshold, and generate a third type of triggered inspection command for the tailings dam area.

[0009] In an optional implementation, the data processing module includes a data fusion unit; The data fusion unit is used to process the spatial domain water level data using a preset point cloud processing algorithm to generate water surface elevation grid data, wherein the water surface elevation grid data is a function of spatial coordinates and time. The data fusion unit is also used to take the real-time water level data of each water level monitoring module within the same preset time period as calibration points, perform spatial interpolation correction and reliability verification on the water surface elevation grid data, and generate the fused water level field data.

[0010] In an optional implementation, the data processing module further includes a trend prediction unit; The trend prediction unit is used to select the historical water level data sequence of a preset key area in the fused water level field data, use a preset time series prediction algorithm and predict the water level height for a preset future time period based on the historical water level data sequence, and generate the water level prediction data. The formula for the preset time series prediction algorithm is as follows:

[0011] In the formula, To preset the prediction step size, For the present Always looking towards the future After step length Water level prediction data for the preset key area at a given time. For preset drift items, For the first Preset autoregressive coefficients, To predetermine the autoregressive order, , For the present Before the moment Water level measurement data at each time step For the present Random error at time, The moving average order is... , For the first The average coefficient of order, This is historical prediction error data.

[0012] In an optional implementation, the data processing module further includes an early warning decision unit, and the security early warning information includes first-level security early warning information, second-level security early warning information and third-level security early warning information; The early warning decision unit is used to issue the first-level safety early warning information when the real-time water level data or the fused water level field data show that the current water level exceeds the preset safe operation water level line but is lower than the preset warning water level line, and the water level prediction data shows that the future water level will not exceed the current water level. The early warning decision unit is also used to issue the secondary safety early warning information when the difference between the current water level and the preset warning water level line is less than a preset proximity threshold, or when the water level prediction data shows that the future water level will exceed the current water level and exceed the preset warning water level line. The early warning decision unit is also used to issue the Level 3 safety early warning information and automatically trigger the linkage mechanism with the external emergency response system when the real-time water level data or the fused water level field data show that the current water level has exceeded the preset warning water level line, or the water level prediction data shows that the absolute value of the predicted rate of change of the future water level within a preset short time period is greater than the preset sharp rise threshold.

[0013] Secondly, the present invention provides a dynamic early warning method for tailings dam water level, applied to a dynamic early warning system for tailings dam water level as described in any of the foregoing embodiments. The system includes an edge computing module, a trigger inspection module, a data processing module, and multiple water level monitoring modules. The method includes: The water level monitoring module continuously collects real-time water level data at discrete points in the tailings dam area. The edge computing module preprocesses the real-time water level data to generate corresponding trigger-based inspection commands. The trigger inspection module responds to the trigger inspection command and performs an inspection task on the area corresponding to the trigger inspection command, collecting spatial water level data of the tailings dam area. The data processing module fuses the real-time water level data and the spatial domain water level data to generate fused water level field data. Based on the time series of the fused water level field data, it predicts the water level height for a preset future time period to generate water level prediction data. Based on the real-time water level data, the fused water level field data, and the water level prediction data, and combined with preset multi-level early warning rules, it generates multi-level safety early warning information.

[0014] Thirdly, this disclosure provides a computer device, which includes a memory and a processor. The memory stores a computer program, and the processor executes the computer program to implement the steps of the tailings dam water level dynamic early warning method described in the second aspect.

[0015] Fourthly, this disclosure provides a computer-readable storage medium storing a computer program that, when executed by a processor, implements the steps of the tailings dam water level dynamic early warning method described in the second aspect.

[0016] The beneficial effects of this application are: The tailings dam water level dynamic early warning system provided in this application constructs a three-dimensional monitoring and early warning system through the coordinated operation of a water level monitoring module, an edge computing module, a trigger inspection module, and a data processing module. The water level monitoring module provides continuous point data, the trigger inspection module provides global spatial data as needed, the edge computing module enables intelligent trigger judgment, and the data processing module completes multi-source data fusion, trend prediction, and hierarchical early warning. This system realizes the evolution from traditional single passive monitoring to global proactive early warning, improving the accuracy and reliability of tailings dam safety monitoring.

[0017] To make the above-mentioned objects, features and advantages of the present invention more apparent and understandable, preferred embodiments are described below in detail with reference to the accompanying drawings. Attached Figure Description

[0018] To more clearly illustrate the technical solutions of the embodiments of the present invention, the accompanying drawings used in the embodiments will be briefly described below. It should be understood that the following drawings only show some embodiments of the present invention and should not be regarded as a limitation on the scope. For those skilled in the art, other related drawings can be obtained based on these drawings without creative effort. In the various drawings, similar components are numbered similarly.

[0019] Figure 1 This paper shows a schematic diagram of the structure of a tailings dam water level dynamic early warning system provided in an embodiment of this application; Figure 2 A flowchart of a tailings dam water level dynamic early warning method provided in an embodiment of this application is shown; Figure 3 A schematic diagram of the structure of a computer device provided in an embodiment of this application is shown.

[0020] Explanation of key component symbols: 100-Tailings dam water level dynamic early warning system; 110-Water level monitoring module; 120-Edge computing module; 130-Trigger inspection module; 140-Data processing module; 121-Data stagnation diagnosis unit; 122-Change rate diagnosis unit; 123-Spatial consistency diagnosis unit; 141-Data fusion unit; 142-Trend prediction unit; 143-Early warning decision unit. Detailed Implementation

[0021] Embodiments of the present invention are described in detail below. Examples of these embodiments are shown in the accompanying drawings, wherein the same or similar reference numerals denote the same or similar elements or elements having the same or similar functions throughout. The embodiments described below with reference to the accompanying drawings are exemplary and are only used to explain the present invention, and should not be construed as limiting the present invention.

[0022] It should be noted that the terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of technical features indicated. Therefore, a feature defined as "first" or "second" may explicitly or implicitly include one or more of that feature. In the description of this invention, "a plurality of" means two or more, unless otherwise explicitly specified.

[0023] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application belongs. The terminology used herein in the template description is for the purpose of describing particular embodiments only and is not intended to limit the invention. The term "and / or" as used herein includes any and all combinations of one or more of the associated listed items.

[0024] Example 1 like Figure 1 The diagram shown is a structural schematic of a tailings dam water level dynamic early warning system 100 in an embodiment of this application. The system includes multiple water level monitoring modules 110, an edge computing module 120, a trigger inspection module 130, and a data processing module 140.

[0025] Preferably, several water level monitoring modules 110 are deployed at preset discrete points in the tailings pond area. These modules are used to continuously collect real-time water level data at the discrete points in the tailings pond area.

[0026] Understandably, the water level monitoring module 110 forms the foundation of the system's sensing network. It consists of several high-precision water level gauges (such as pressure-type and radar-type water level sensors), which are deployed at pre-selected discrete points within the tailings dam area. These discrete points include, for example, near drainage wells, on the top of the tailings beach, and in dry beach areas. The core function of the water level monitoring module 110 is to collect real-time water level data at its location in a high-frequency, continuous manner, and to continuously transmit this discrete real-time water level data to the backend via wireless communication technologies (such as LoRa, 4G / 5G), providing a basic, continuous time-series data source for the entire system.

[0027] Preferably, the edge computing module 120 is communicatively connected to several water level monitoring modules 110, and is used to preprocess the real-time water level data collected by each water level monitoring module 110, generate corresponding trigger-based inspection instructions, and send them to the trigger-based inspection module 130 to trigger the trigger-based inspection module 130 to execute the inspection task.

[0028] Understandably, the edge computing module 120 is responsible for aggregating a large amount of real-time water level data uploaded by various water level monitoring modules 110 in real time, and performing preliminary data cleaning, filtering, and other preprocessing work to ensure data quality. Its core lies in the embedded trigger judgment engine. This engine, based on the real-time water level data uploaded by several water level monitoring modules 110, uses various built-in intelligent algorithm models to analyze the incoming real-time water level data stream in real time, diagnosing abnormal states such as data stagnation, sudden rate changes, and excessive spatial dispersion. It calculates a set of judgment indicators in real time to characterize abnormal states and dynamic changes in water level, and compares the values ​​of these indicators with preset thresholds. When any judgment indicator exceeds its corresponding threshold, a trigger inspection command is generated and sent to the trigger inspection module 130, triggering the intelligent decision-making of the trigger inspection module 130. This pushes some of the system's decision-making capabilities down to the edge, greatly improving response speed and reliability.

[0029] In one optional implementation, the edge computing module 120 includes a data stagnation diagnosis unit 121, and the triggered inspection command includes a first triggered inspection command. The data stagnation diagnosis unit 121 is configured to: for each water level monitoring module 110, calculate the standard deviation of its real-time water level data in the most recent first preset time period; determine whether the standard deviation is less than a preset stability threshold; if the determination is yes, then identify the corresponding water level monitoring module 110 as a data stagnation abnormal water level monitoring module 110, and generate a first type of triggered inspection command for the local area where the data stagnation abnormal water level monitoring module 110 is located.

[0030] Specifically, the data stagnation diagnosis unit 121 continuously collects and caches a series of real-time water level data arranged in chronological order within the most recent first preset time period for each water level monitoring module 110, forming a real-time water level data sequence. Subsequently, the data stagnation diagnosis unit 121 calls a mathematical calculation routine to quantitatively analyze the dispersion of all data points within the real-time water level data sequence relative to its arithmetic mean, i.e., calculates its standard deviation. This statistical indicator can effectively reflect the fluctuation of real-time water level data within the first preset time period. If the calculation result is significantly low, i.e., the standard deviation is less than a preset stability threshold set based on sensor accuracy and environmental noise levels, it indicates that the real-time water level data output by the water level monitoring module 110 lacks any meaningful changes over a long period, presenting a nearly horizontal straight line. This abnormal state usually stems from substantial faults such as the sensor probe being completely buried and blocked by sediment, internal electronic component failure, or data transmission link interruption, causing it to fail to accurately reflect the dynamic changes in the actual water level. Once such data stagnation anomaly is diagnosed, the engine will immediately determine that the water level monitoring module 110 is malfunctioning and identify it as a water level monitoring module with data stagnation anomaly, and automatically generate a first triggered inspection command. This command contains the precise location information of the water level monitoring module with data stagnation anomaly, and directs the triggered inspection module 130 to go to its local area, using airborne sensors to verify and check the accuracy of the water level at that point and in the surrounding area, thereby confirming the fault and obtaining the real water level data for that area.

[0031] Through the above technical solution, the data stagnation diagnosis unit 121 in this embodiment intelligently identifies the faults of the water level monitoring module 110 through statistical methods, freeing the system from relying on a single data source that may be distorted, and performs targeted verification by activating the trigger inspection module 130, ensuring the reliability and authenticity of the basic monitoring data, which constitutes a key link in the system to realize proactive fault diagnosis and maintenance.

[0032] In one optional implementation, the edge computing module 120 further includes a rate of change diagnostic unit 122, and the triggered inspection command further includes a second triggered inspection command. The rate of change diagnostic unit 122 is configured to: for each water level monitoring module 110, calculate its water level change rate in the most recent second preset time period; determine whether the absolute value of the water level change rate is greater than a preset rate change threshold; if the determination is yes, then determine that the tailings dam area is in a state of rapid water level change, and generate a second triggered inspection command for the area where the water level monitoring module 110 with the largest water level change rate is located and its downstream area.

[0033] Specifically, the rate of change diagnostic unit 122 is the core processing unit of the system for responding to rapid changes in the reservoir water level. For each water level monitoring module 110, the rate of change diagnostic unit 122 calculates the rate of water level change within the most recent second preset time period (the second preset time period is shorter than the first preset time period) by calculating the difference between the current water level value and the water level value at a previous moment, and then dividing by the corresponding time interval. This rate of water level change directly reflects the severity of the rise or fall in water level. After calculation, the rate of change diagnostic unit 122 compares the absolute value of the rate of water level change with a preset rate mutation threshold set in advance based on historical hydrological data, reservoir capacity characteristics, and safety regulations. If the absolute value exceeds the preset rate mutation threshold, it indicates that the water level in the tailings dam area has experienced an abnormally drastic change in a short period of time. This change may be due to an emergency situation such as a sharp increase in runoff caused by heavy rainfall, sudden blockage of drainage culverts, or leakage. Once the tailings dam area is determined to be experiencing a rapid change in water level, the engine will immediately activate the response mechanism. Among all the sensors that have triggered alarms, the water level monitoring module 110 with the largest absolute value of the water level change rate will be located. The area where this module is located will be determined as the center or starting area of ​​the abnormal change, and a second triggered inspection command will be automatically generated. This command not only requires the triggered inspection module 130 to conduct a detailed investigation of the core area of ​​the abnormality, but also emphasizes the need to simultaneously scan the downstream area. This aims to quickly assess the scope of the danger, confirm the specific cause of the water level anomaly, and provide crucial global data for determining whether there is a risk of dam overflow or dam failure.

[0034] Through the above technical solution, the rate of change diagnosis unit 122 in this embodiment can quickly respond to potential emergencies by capturing abnormal and drastic fluctuations in water level in real time, and guide the inspection module 130 to conduct key inspections of the core abnormal area and downstream risk area, which greatly enhances the system's ability to perceive and respond to acute risks and is an important guarantee for realizing proactive emergency early warning.

[0035] In one optional implementation, the edge computing module 120 further includes a spatial consistency diagnostic unit 123, and the triggered inspection command further includes a third triggered inspection command. The spatial consistency diagnostic unit 123 is configured to: at any sampling time, calculate the overall standard deviation of the real-time water level data collected by all water level monitoring modules 110; determine whether the overall standard deviation is greater than a preset spatial dispersion threshold; if so, determine that the spatial distribution consistency of the water level in the tailings dam area is abnormal, and generate a third triggered inspection command for the tailings dam area (or a highly discrete area).

[0036] Specifically, at each unified sampling moment, the spatial consistency diagnostic unit 123 synchronously acquires real-time water level data reported by all water level monitoring modules 110, and statistically analyzes these real-time water level data from different discrete points as a whole dataset. Its core operation is to calculate the overall standard deviation of this set of real-time water level data. This overall standard deviation quantifies the degree of dispersion and spatial distribution difference of the real-time water level data at each discrete point within the tailings dam area relative to the global average level at the current moment. After calculation, the spatial consistency diagnostic unit 123 compares the obtained overall standard deviation value with a preset spatial dispersion threshold, pre-set based on the flatness of the dam area's topography and the water level distribution characteristics under normal hydrological conditions. If the overall standard deviation is greater than the preset spatial dispersion threshold, it indicates that the water surface in the tailings dam area is in an extremely unstable and abnormal state, with excessively large differences in the real-time water level data at each discrete point. This spatial inconsistency anomaly usually indicates serious problems such as dry beaches, damming, uneven settlement, or localized leakage in the local area. Once this abnormal state is determined, the engine will immediately generate a third triggered inspection command. This command requires the triggered inspection module 130 to perform a comprehensive scanning inspection of the entire tailings dam area or important local areas with significantly high dispersion identified by the system. The aim is to quickly obtain high-precision water surface elevation data for the entire area, accurately grasp the actual spatial distribution of the water surface, locate abnormal areas, and find out the root cause of inconsistent water level distribution.

[0037] Through the above technical solution, the spatial consistency diagnosis unit 123 in this embodiment effectively identifies potential distributional anomalies by analyzing the statistical characteristics of water level data in the spatial dimension, and drives the inspection module 130 to perform a full-domain scan to find out the cause. This makes up for the deficiency that a single water level monitoring module cannot perceive the global status, and significantly improves the system's comprehensive control over the overall operating status of the reservoir area.

[0038] Preferably, the trigger inspection module 130 includes a UAV flight platform, an airborne high-precision positioning module, an airborne water level sensing sensor, and an airborne communication module. The trigger inspection module 130 is used to respond to trigger inspection commands, perform inspection tasks on the area corresponding to the trigger inspection command, and collect spatial water level data of the tailings dam area.

[0039] Understandably, the trigger inspection module 130 is the system's mobility-enhancing sensing component and also the actuator for global information acquisition. It is not only a flight platform but also an airborne mobile monitoring station integrating a high-precision RTK positioning module (for centimeter-level accurate positioning), airborne water level sensing sensors (such as LiDAR or high-performance optical cameras), and a high-speed data communication module. The core value of the trigger inspection module 130 lies in its responsiveness. Upon receiving a trigger inspection command, it can autonomously fly to the designated airspace, perform inspection tasks, and collect a wide range of high-density spatial water level information from the reservoir area. This compensates for the spatial limitations of fixed-point monitoring, enabling a global scan of the water surface morphology.

[0040] It should also be noted that, in addition to the trigger inspection module 130, the system in this embodiment also includes a periodic inspection module. The periodic inspection module is configured to automatically generate a full-area inspection command and send it to the trigger inspection module 130 according to a preset fixed time period, so as to instruct it to perform a full-range routine scan inspection of the tailings dam area, rather than relying solely on the output results of the trigger judgment engine.

[0041] Compared to traditional methods relying on manual foot surveys, photography, and measurement, this technical solution, through the intervention of drone detection units, can quickly and automatically acquire high-resolution orthophotos and high-precision 3D models of the tailings dam surface. This reduces the workload that previously required several person-days to just a few hours, significantly freeing up manpower and reducing labor intensity and safety risks. The exported 3D model serves as the unique and accurate base map of the tailings dam's current condition, achieving a leap from abstract description to intuitive and measurable 3D visualization management of the dam's status. This not only provides a precise display tool for daily management but also creates standardized electronic archives, providing an immutable data foundation for compliance reviews, engineering calculations, and historical retrospective analysis.

[0042] Preferably, the data processing module 140 is located in the cloud and is responsible for collaborative management and advanced analysis. It is connected to the edge computing module 120 and the trigger inspection module 130. It is used to fuse real-time water level data and spatial domain water level data to generate high-precision fused water level field data. Based on the time series of the fused water level field data, it predicts the water level height for a preset future time period to generate water level prediction data. Based on the real-time water level data, fused water level field data and water level prediction data, combined with preset multi-level early warning rules, it generates multi-level safety early warning information.

[0043] Understandably, the data processing module 140 ultimately provides users with global situational awareness, early warning information dissemination, and decision support through a visual interface. By combining changing data with early warning thresholds, it transforms passive response into proactive early warning. Simultaneously, the intuitive 3D display of changes significantly enhances managers' ability to perceive the risk situation, providing strong data support for taking targeted engineering measures and achieving scientific decision-making.

[0044] In one optional implementation, the data processing module 140 includes a data fusion unit 141. The data fusion unit 141 is the core of processing multi-source heterogeneous data. It receives two types of water level data with different properties: one is real-time water level data (point data) with high temporal resolution but discrete spatial distribution from the water level monitoring module 110; the other is spatial domain water level data (typically represented as point clouds or digital elevation models) with high spatial resolution but discontinuous temporal distribution from the trigger inspection module 130. The data fusion unit 141 uses spatiotemporal interpolation algorithms and data assimilation techniques to use the discrete real-time water level data generated by the water level monitoring module 110 as precise control points to calibrate and correct the spatial domain water level data generated by the inspection module. Ultimately, it generates a continuous and unified fused water level field data that accurately reflects the water level height at any location within the entire tailings dam area at a specific time. The fused water level field data is a continuous spatial function that reflects the water level height at any point within the entire tailings dam area at a specific time. This integrated water level field data possesses both temporal continuity and spatial integrity, providing a reliable data foundation for subsequent accurate predictions.

[0045] Specifically, firstly, the spatial domain water level data is processed using a preset point cloud processing algorithm (including point cloud filtering, classification, and other preprocessing algorithms) to generate water surface elevation grid data. This water surface elevation grid data is a function of spatial coordinates (X, Y) and time (t) as independent variables, accurately recording the water surface elevation value (Z) of each grid point within the inspection coverage area at a specific time. Then, to improve the absolute accuracy and reliability of the water surface elevation data, the data fusion unit 141 simultaneously acquires real-time water level data from discrete points reported by all water level monitoring modules 110 within the same preset time period. These fixed real-time water level data points are considered highly reliable and accurate calibration points because their sensors directly contact the water surface and are continuously measured over a long period. Next, the core algorithm of the data fusion unit 141 uses these discrete calibration points to systematically correct and optimize the water surface elevation grid data using spatial interpolation correction techniques (such as Kriging interpolation, co-Kriging interpolation, or the minimum curvature method), eliminating potential systematic errors in the measurements triggered by the inspection module 130. Finally, the data fusion unit 141 outputs an optimized, unified fused water level field data.

[0046] It should be noted that the fused water level field data is a spatially continuous function that can accurately and reliably reflect the water level height at any point within the entire tailings pond area at a specific query time. Taking Kriging interpolation as an example: Kriging interpolation assumes that the data are spatially correlated, meaning that points closer together have more similar values. This correlation is described by a variogram. The algorithm needs to construct a variogram model to quantify this spatial correlation. The variogram describes how data differences change with distance. During calculation, the distance between all known residual point pairs (the locations of the water level monitoring module 110) and the squared difference of their residual values ​​(the difference between the actual water level elevation measured by the water level monitoring module 110 at the same spatial location and time point and the corresponding elevation value extracted from the water surface elevation grid data initially generated by the trigger inspection module 130) are analyzed, and these point pairs are plotted as a scatter plot. Then, a mathematical function (such as a spherical model, exponential model, or Gaussian model) is used to fit these scatter points, forming a definite variogram curve. The curve shows that within a certain distance range, the difference between points increases with increasing distance, and beyond this range, the difference tends to stabilize. Then, the algorithm enters the prediction phase, which calculates for each point in the grid to be predicted. For any location where the residual needs to be predicted, the algorithm searches for all known residual points within a certain range, centered on that location. The predicted value is not a simple weighted average of the residuals of these known points, but rather a set of optimal weights is determined by solving a system of Kriging equations. This system of Kriging equations is a linear system established by using the two mathematical conditions of spatial unbiasedness and minimizing the variance of the prediction error as constraints, and quantifying spatial correlation using a pre-fitted variogram model. Ultimately, the predicted residual for that point is a linear combination of the residuals of these known points with their corresponding weights as coefficients. The measurement value of the trigger inspection module 130 at that point plus the predicted residual value is the final water level value corresponding to that point in the fused water level field data. In summary, the specific operation of Kriging interpolation involves objectively determining spatial weights through a variogram model, and then using these weights to perform a weighted average of the values ​​at known points (position of water level monitoring module 110), thereby obtaining the optimal spatial prediction result with the smallest error. In this invention, this process transforms discrete residual observations into a continuous residual correction surface, providing a scientific basis for accurately correcting water surface elevation grid data.

[0047] Through the above technical solution, this embodiment combines the accuracy of the water level monitoring module 110 with the globality of the trigger inspection module 130, and uses a spatial interpolation algorithm to generate continuous and accurate fused water level field data across the entire domain. This solves the problem that traditional monitoring methods cannot obtain spatially continuous water level distribution, and provides a reliable data foundation for subsequent trend prediction and accurate early warning.

[0048] In an optional implementation, the data processing module 140 further includes a trend prediction unit 142, used to select historical water level data sequences of preset key areas from the fused water level field data, employ a preset time series prediction algorithm, and predict the water level height for a preset future time period based on the historical water level data sequences, thereby generating water level prediction data. This enables the system to anticipate potential risks, rather than merely responding to anomalies that have already occurred.

[0049] Specifically, firstly, historical water level data sequences of preset key areas from the fused water level field data are selected as input. It should be noted that these preset key areas are known and inherently risky critical points, such as the area surrounding the drainage channel, the front area of ​​the shoal (sub-dam), and the boundary between the dry shoal and the water surface. Then, a preset time series prediction algorithm is applied to predict the water level height for a preset future time period based on the historical water level data sequences, generating water level prediction data. The preset time series prediction algorithm is calculated using the following mathematical formula: the predicted water level value at a future time is equal to a linear combination of the historical water level data sequences plus a random error term. Its general formula is:

[0050] In the formula, The preset prediction step size indicates how long in the future the water level data will be predicted. It is a value set according to business needs, which determines whether the prediction is short-term (e.g., the next 1 hour), medium-term (e.g., the next 6 hours), or long-term (e.g., the next 24 hours). For the present Always looking towards the future After step length Predicted water level data for key areas at specific times; The preset drift term is a constant obtained by fitting historical data. It ensures that even if the historical water level and recent error are both zero, the predicted value will not be zero, but will have a basic trend value that represents the deterministic linear trend in the time series. For the first The pre-defined autoregressive coefficients of the first order need to be estimated through training with historical data; they quantify the past first order. The degree and direction (positive or negative correlation) of the water level data at each time point on the current forecast data. The larger the absolute value, the greater the impact; The preset autoregression order is a model hyperparameter that needs to be determined, representing how many historical time steps of data are used for prediction. ; For the present Before the moment Water level measurement data at each time step; For the present The random error at time t represents the model's performance at time t. Unpredictable random shocks that cannot be explained by historical data (such as brief showers, minor measurement noise, etc.) are random variables with zero mean and constant variance. This is the order of the moving average, which is also a model hyperparameter, indicating how many past time steps' prediction error should be used to correct the current prediction. ; For the first The average coefficient of order; Historical prediction error data represents the model's performance at time [time value missing]. The difference between the prediction made and the actual observed value at that time.

[0051] In an optional implementation, the data processing module 140 further includes an early warning decision unit 143, used to generate and issue multi-level safety early warning information based on real-time water level data, fused water level field data, and water level prediction data, combined with preset multi-level early warning rules. The safety early warning information includes Level 1, Level 2, and Level 3 safety early warning information. The early warning decision unit 143 comprehensively considers the current state reflected by the real-time water level data, the global spatial distribution presented by the fused water level field data, and the future development trend predicted by the water level prediction data, and matches them with a preset multi-level early warning rule base. This rule base defines the triggering conditions for different levels of early warning (such as combining multiple criteria such as absolute water level height, rate of rise, and inundation range). Based on this, the early warning decision unit 143 performs logical reasoning and judgment, automatically generating and issuing safety early warning information of different levels, thus forming a closed loop from accurate perception to intelligent decision-making.

[0052] Specifically, when real-time water level data or integrated water level field data show that the current water level exceeds the preset safe operating water level line but is lower than the preset warning water level line, and water level prediction data shows that the future water level will not exceed the current water level, the early warning decision unit 143 issues a Level 1 safety early warning information; when real-time water level data or integrated water level field data show that the difference between the current water level and the preset warning water level line is less than the preset proximity threshold, or when water level prediction data shows that the future water level will exceed the current water level and exceed the preset warning water level line, the early warning decision unit 143 issues a Level 2 safety early warning information; when real-time water level data or integrated water level field data show that the current water level has exceeded the preset warning water level line, or when water level prediction data shows that the absolute value of the predicted rate of change of the future water level within a preset short time period is greater than the preset rapid rise threshold, the early warning decision unit 143 issues a Level 3 safety early warning information and automatically triggers the linkage mechanism with the external emergency response system.

[0053] Through the above technical solutions, the three modules of data fusion, trend prediction and early warning decision-making are progressively integrated, transforming the original monitoring data into a comprehensive situational awareness with spatiotemporal continuity, which is then elevated to a forward-looking prediction of future risks, and finally forms decision-making instructions with guiding significance.

[0054] The tailings dam water level dynamic early warning system 100 provided in this application embodiment constructs a three-dimensional monitoring and early warning system through the coordinated operation of a water level monitoring module 110, an edge computing module 120, a trigger inspection module 130, and a data processing module 140. The water level monitoring module 110 provides continuous point data, the trigger inspection module 130 provides global spatial data on demand, the edge computing module 120 realizes intelligent trigger judgment, and the data processing module 140 completes multi-source data fusion, trend prediction, and hierarchical early warning. This system realizes the evolution from traditional single passive monitoring to global proactive early warning, improving the accuracy and reliability of tailings dam safety monitoring.

[0055] Example 2 like Figure 2 The diagram shows a flowchart of a tailings dam water level dynamic early warning method according to an embodiment of this application. The tailings dam water level dynamic early warning method provided in this embodiment is applied to a tailings dam water level dynamic early warning system as described in Embodiment 1. The system includes an edge computing module, a trigger inspection module, a data processing module, and multiple water level monitoring modules. The method specifically includes the following steps: Step S110: Continuously collect real-time water level data at discrete points in the tailings dam area through the water level monitoring module; Step S120: The edge computing module preprocesses the real-time water level data to generate corresponding trigger-based inspection commands. Step S130: The inspection module responds to the trigger inspection command and performs an inspection task on the area corresponding to the trigger inspection command, collecting spatial water level data of the tailings dam area. Step S140: The data processing module merges the real-time water level data and the spatial domain water level data to generate merged water level field data. Based on the time series of the merged water level field data, the water level height for a preset future time period is predicted to generate water level prediction data. Based on the real-time water level data, the merged water level field data, and the water level prediction data, and combined with preset multi-level early warning rules, multi-level safety early warning information is generated.

[0056] The tailings dam water level dynamic early warning method provided in this application embodiment can realize all processes of the tailings dam water level dynamic early warning system corresponding to Embodiment 1, and can achieve the same technical effect. To avoid repetition, it will not be described again here.

[0057] Example 3 This application also provides a computer device. Please refer to the following for details. Figure 3 , Figure 3 This is a basic structural block diagram of the computer device in this embodiment.

[0058] The computer device 3 includes a memory 31, a processor 32, and a network interface 33 that are interconnected via a system bus. It should be noted that only a computer device 3 with a memory 31, a processor 32, and a network interface 33 is shown in the figure; however, it should be understood that it is not required to implement all the components shown, and more or fewer components can be implemented alternatively. Those skilled in the art will understand that the computer device described here is a device capable of automatically performing numerical calculations and / or information processing according to pre-set or stored instructions, and its hardware includes, but is not limited to, microprocessors, application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), digital signal processors (DSPs), embedded devices, etc.

[0059] The computer device can be a desktop computer, laptop, handheld computer, or cloud server, etc. The computer device can interact with the user via a keyboard, mouse, remote control, touchpad, or voice control.

[0060] The memory 31 includes at least one type of readable storage medium, including flash memory, hard disk, multimedia card, card-type memory (e.g., SD or D slot compatibility test memory), random access memory (RAM), static random access memory (SRAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), programmable read-only memory (PROM), magnetic memory, disk, optical disk, etc. In some embodiments, the memory 31 may be an internal storage unit of the computer device 3, such as the hard disk or memory of the computer device 3. In other embodiments, the memory 31 may also be an external storage device of the computer device 3, such as a plug-in hard disk, smart media card (SMC), secure digital card (SD), flash card, etc., equipped on the computer device 3. Of course, the memory 31 may also include both the internal storage unit and its external storage device of the computer device 3. In this embodiment, the memory 31 is typically used to store the operating system and various application software installed on the computer device 3, such as computer-readable instructions for slot compatibility testing methods. In addition, the memory 31 can also be used to temporarily store various types of data that have been output or will be output.

[0061] In some embodiments, the processor 32 may be a central processing unit (CPU), controller, microcontroller, microprocessor, or other tailings dam water level dynamic early warning chip. The processor 32 is typically used to control the overall operation of the computer device 3. In this embodiment, the processor 32 is used to execute computer-readable instructions stored in the memory 31 or to process data, such as executing computer-readable instructions for the slot compatibility testing method.

[0062] The network interface 33 may include a wireless network interface or a wired network interface, which is typically used to establish communication connections between the computer device 3 and other electronic devices.

[0063] The computer equipment provided in this embodiment can execute the above-described tailings dam water level dynamic early warning method. Here, the tailings dam water level dynamic early warning method can be any of the tailings dam water level dynamic early warning methods described in the various embodiments above.

[0064] Example 4 This embodiment also provides a computer-readable storage medium storing a computer program thereon. When the computer program is executed by a processor, it implements the steps of the tailings dam water level dynamic early warning method in this embodiment.

[0065] In this embodiment, the computer-readable storage medium includes flash memory, hard disk, multimedia card, card-type memory (e.g., SD or DX memory), random access memory (RAM), static random access memory (SRAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), programmable read-only memory (PROM), magnetic memory, magnetic disk, optical disk, etc. In some embodiments, the computer-readable storage medium can be an internal storage unit of a computer device, such as the hard disk or memory of the computer device. In other embodiments, the computer-readable storage medium can also be an external storage device of the computer device, such as a plug-in hard disk, smart media card (SMC), secure digital (SD) card, flash card, etc., equipped on the computer device. Of course, the computer-readable storage medium can also include both the internal storage unit and the external storage device of the computer device. In this embodiment, the computer-readable storage medium is typically used to store the operating system and various application software installed on the computer device. In addition, the computer-readable storage medium can also be used to temporarily store various types of data that have been output or will be output.

[0066] In the several embodiments provided in this application, it should be understood that the disclosed systems and methods can also be implemented in other ways. The system embodiments described above are merely illustrative; for example, the flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of systems, methods, and computer program products according to various embodiments of the present invention. In this regard, each block in a flowchart or block diagram may represent a module, segment, or portion of code containing one or more executable instructions for implementing a specified logical function. It should also be noted that, as an alternative implementation, the functions marked in the blocks may occur in a different order than those marked in the drawings. For example, two consecutive blocks may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each block in the block diagram and / or flowchart, and combinations of blocks in the block diagram and / or flowchart, can be implemented using a dedicated hardware-based system that performs the specified function or action, or using a combination of dedicated hardware and computer instructions.

[0067] In addition, the functional modules or units in the various embodiments of the present invention can be integrated together to form an independent part, or each module can exist independently, or two or more modules can be integrated to form an independent part.

[0068] If the aforementioned functions are implemented as software functional modules and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this invention, or the part that contributes to the prior art, or a part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a smartphone, personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of this invention. The aforementioned storage medium can be a non-volatile storage medium or a volatile storage medium. For example, the storage medium can be a USB flash drive, a portable hard drive, a read-only memory (ROM), a random access memory (RAM), a magnetic disk, or an optical disk, or any other medium capable of storing program code.

[0069] The above description is merely a specific embodiment of the present invention, but the scope of protection of the present invention is not limited thereto. Any changes or substitutions that can be easily conceived by those skilled in the art within the scope of the technology disclosed in the present invention should be included within the scope of protection of the present invention.

Claims

1. A tailings dam water level dynamic early warning system, characterized in that, The system includes an edge computing module, a trigger inspection module, a data processing module, and multiple water level monitoring modules; The water level monitoring module is used to continuously collect real-time water level data at discrete points in the tailings dam area; The edge computing module is used to preprocess the real-time water level data and generate corresponding trigger-based inspection commands. The triggered inspection module is used to respond to the triggered inspection command, perform inspection tasks on the area corresponding to the triggered inspection command, and collect spatial water level data of the tailings dam area. The data processing module is used to fuse the real-time water level data and the spatial domain water level data to generate fused water level field data, and based on the time series of the fused water level field data, to predict the water level height for a preset future time period to generate water level prediction data. Based on the real-time water level data, the fused water level field data and the water level prediction data, and combined with preset multi-level early warning rules, multi-level safety early warning information is generated.

2. The tailings dam water level dynamic early warning system according to claim 1, characterized in that, The edge computing module includes a data stagnation diagnosis unit, and the trigger-based inspection command includes a first trigger-based inspection command. The data stagnation diagnosis unit is used to calculate the standard deviation of the real-time water level data of each water level monitoring module within a first preset time period, and to determine whether the standard deviation is less than a preset stability threshold. The data stagnation diagnosis unit is further configured to identify the corresponding water level monitoring module as a data stagnation abnormal water level monitoring module if there is a water level monitoring module whose standard deviation is less than the preset stability threshold, and generate a first trigger-type inspection command for the area where the data stagnation abnormal water level monitoring module is located.

3. The tailings dam water level dynamic early warning system according to claim 2, characterized in that, The edge computing module also includes a rate of change diagnostic unit, and the trigger-type inspection command also includes a second trigger-type inspection command; The rate of change diagnostic unit is used to calculate the rate of change of water level of real-time water level data of each water level monitoring module within a second preset time period, and to determine whether the absolute value of the rate of change of water level is greater than a preset rate change threshold, wherein the second preset time period is shorter than the first preset time period. The rate of change diagnostic unit is further configured to determine that if the absolute value of the water level change rate is greater than the preset rate change threshold, the tailings dam area is in a state of rapid water level change, and generate a second type of triggered inspection command for the area where the water level monitoring module with the largest absolute value of the water level change rate is located and its downstream area.

4. The tailings dam water level dynamic early warning system according to claim 3, characterized in that, The edge computing module also includes a spatial consistency diagnostic unit, and the trigger-type inspection command also includes a third trigger-type inspection command. The spatial consistency diagnostic unit is used to calculate the overall standard deviation of the real-time water level data of each of the water level monitoring modules, and to determine whether the overall standard deviation is greater than a preset spatial dispersion threshold. The spatial consistency diagnostic unit is further configured to determine that the tailings dam area is in an abnormal state of water level spatial distribution consistency if the overall standard deviation is greater than the preset spatial dispersion threshold, and generate a third type of triggered inspection command for the tailings dam area.

5. The tailings dam water level dynamic early warning system according to claim 1, characterized in that, The data processing module includes a data fusion unit; The data fusion unit is used to process the spatial domain water level data using a preset point cloud processing algorithm to generate water surface elevation grid data, wherein the water surface elevation grid data is a function of spatial coordinates and time. The data fusion unit is also used to take the real-time water level data of each water level monitoring module within the same preset time period as calibration points, perform spatial interpolation correction and reliability verification on the water surface elevation grid data, and generate the fused water level field data.

6. The tailings dam water level dynamic early warning system according to claim 1, characterized in that, The data processing module also includes a trend prediction unit; The trend prediction unit is used to select the historical water level data sequence of a preset key area in the fused water level field data, use a preset time series prediction algorithm and predict the water level height for a preset future time period based on the historical water level data sequence, and generate the water level prediction data. The formula for the preset time series prediction algorithm is as follows: In the formula, To preset the prediction step size, For the present Always looking towards the future After step length Water level prediction data for the preset key area at the specified time. For preset drift items, For the first Preset autoregressive coefficients, To predetermine the autoregressive order, , For the present Before the moment Water level measurement data at each time step For the present Random error at time, The moving average order is... , For the first The average coefficient of order, This is historical prediction error data.

7. The tailings dam water level dynamic early warning system according to claim 1, characterized in that, The data processing module also includes an early warning decision unit, and the security early warning information includes first-level security early warning information, second-level security early warning information and third-level security early warning information; The early warning decision unit is used to issue the first-level safety early warning information when the real-time water level data or the fused water level field data show that the current water level exceeds the preset safe operation water level line but is lower than the preset warning water level line, and the water level prediction data shows that the future water level will not exceed the current water level. The early warning decision unit is also used to issue the secondary safety early warning information when the difference between the current water level and the preset warning water level line is less than a preset proximity threshold, or when the water level prediction data shows that the future water level will exceed the current water level and exceed the preset warning water level line. The early warning decision unit is also used to issue the Level 3 safety early warning information and automatically trigger the linkage mechanism with the external emergency response system when the real-time water level data or the fused water level field data show that the current water level has exceeded the preset warning water level line, or the water level prediction data shows that the absolute value of the predicted rate of change of the future water level within a preset short time period is greater than the preset sharp rise threshold.

8. A method for dynamic early warning of tailings dam water level, characterized in that, The tailings dam water level dynamic early warning system as described in any one of claims 1-7, the system comprising an edge computing module, a trigger inspection module, a data processing module, and multiple water level monitoring modules, the method comprising: The water level monitoring module continuously collects real-time water level data at discrete points in the tailings dam area. The edge computing module preprocesses the real-time water level data to generate corresponding trigger-based inspection commands. The trigger inspection module responds to the trigger inspection command and performs an inspection task on the area corresponding to the trigger inspection command, collecting spatial water level data of the tailings dam area. The data processing module fuses the real-time water level data and the spatial domain water level data to generate fused water level field data. Based on the time series of the fused water level field data, it predicts the water level height for a preset future time period to generate water level prediction data. Based on the real-time water level data, the fused water level field data, and the water level prediction data, and combined with preset multi-level early warning rules, it generates multi-level safety early warning information.

9. A computer device, characterized in that, It includes a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to implement the steps of the tailings dam water level dynamic early warning method according to claim 8.

10. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a computer program, which, when executed by a processor, implements the steps of the tailings dam water level dynamic early warning method according to claim 8.

Images