Tailing pond emergency supervision internet of things large model system and method

Abstract

The application provides a tailing pond emergency supervision Internet of Things large model system and method; the system comprises an emergency supervision management platform, the emergency supervision management platform is configured to determine a plurality of local strain data of the tailing pond based on optical fiber signals acquired through distributed optical fibers and spatial resolution of the distributed optical fibers; determine rainfall response of the tailing pond based on water level information acquired through sensors arranged in the tailing pond; determine tailing stability data at the current time and the future time based on the plurality of local strain data; determine a target time point and corresponding drainage parameters of the target time point based on the rainfall response and the tailing stability data; control a plurality of drainage wells to open drainage valves for drainage at the target time point based on the drainage parameters. Through the system, the drainage parameters of the drainage wells in the tailing pond can be reasonably determined and controlled, the risk of dam break and landslide of the tailing pond is reduced, and the safety of downstream city residents is ensured.

Description

Technical Field

[0001] This specification relates to the field of emergency monitoring of tailings dams, and in particular to a large-scale IoT model system and method for emergency monitoring of tailings dams. Background Technology

[0002] Tailings dams are man-made structures used to store tailings or other industrial waste discharged after ore beneficiation in metal or non-metal mines. Due to factors such as heavy rainfall, tailings dams may accumulate large amounts of water with high potential energy, posing risks such as flooding, dam failure, dam cracking, landslides, and seepage damage. Excessive drainage may also damage drainage wells or exacerbate tailings collapse, potentially impacting the safety of downstream urban residents.

[0003] Therefore, it is hoped that a large-scale IoT model system and method for emergency monitoring of tailings ponds can be provided to monitor tailings ponds, thereby minimizing the occurrence of accidents and ensuring the safety of residents in downstream cities. Summary of the Invention

[0004] The invention includes a large-scale IoT model system for emergency monitoring of tailings dams. The system comprises an emergency monitoring and management platform configured to: determine multiple local strain data of the tailings dam based on fiber optic signals acquired through distributed optical fibers located at multiple geographical locations within the tailings dam and the spatial resolution of the distributed optical fibers; determine the rainfall response of the tailings dam based on water level information acquired through sensors installed in the tailings dam; determine tailings stability data for the current and future times based on the multiple local strain data; determine a target time point and corresponding discharge parameters based on the rainfall response and the tailings stability data; and control multiple drainage wells to open their valves at the target time point to discharge water based on the discharge parameters.

[0005] The invention includes an emergency monitoring method for tailings dams, executed by the emergency monitoring management platform of a tailings dam emergency monitoring IoT big data model system. The method includes: determining multiple local strain data of the tailings dam based on fiber optic signals acquired through distributed optical fibers located at multiple geographical locations within the tailings dam and the spatial resolution of the distributed optical fibers; determining the rainfall response of the tailings dam based on water level information acquired through sensors installed in the tailings dam; determining tailings stability data for the current and future times based on the multiple local strain data; determining a target time point and corresponding discharge parameters based on the rainfall response and the tailings stability data; and controlling multiple drainage wells to open drainage valves at the target time point to discharge water based on the discharge parameters.

[0006] Beneficial effects: The IoT big data model system for emergency monitoring of tailings dams can monitor tailings dams, reasonably determine and control the discharge parameters of different drainage wells in tailings dams, minimize the risk of tailings dam failure and landslides, and ensure the safety of downstream urban residents. Attached Figure Description

[0007] This specification will be further described by way of exemplary embodiments, which will be described in detail with reference to the accompanying drawings. These embodiments are not limiting; in these embodiments, the same reference numerals denote the same structures, wherein:

[0008] Figure 1 This is a schematic diagram of the platform structure of a large-scale IoT model system for emergency monitoring of tailings ponds, as shown in some embodiments of this specification.

[0009] Figure 2 This is an exemplary flowchart of an emergency monitoring method for tailings ponds according to some embodiments of this specification;

[0010] Figure 3 This is an exemplary flowchart illustrating the determination of tailings stability data according to some embodiments of this specification;

[0011] Figure 4 This is an exemplary schematic diagram of a tailings analysis model shown in some embodiments of this specification. Detailed Implementation

[0012] To more clearly illustrate the technical solutions of the embodiments in this specification, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the drawings described below are merely some examples or embodiments of this specification. For those skilled in the art, these drawings can be applied to other similar scenarios without creative effort. Unless obvious from the context or otherwise specified, the same reference numerals in the drawings represent the same structures or operations.

[0013] Flowcharts are used in this specification to illustrate the operations performed by the system according to embodiments of this specification. It should be understood that the preceding or following operations are not necessarily performed in exact order. Instead, the steps can be processed in reverse order or simultaneously. Furthermore, other operations can be added to these processes, or one or more steps can be removed from them.

[0014] Figure 1 This is a schematic diagram of the platform structure of a large-scale IoT model system for emergency monitoring of tailings ponds, as shown in some embodiments of this specification.

[0015] In some embodiments, such as Figure 1As shown, the tailings dam emergency supervision IoT large model system (referred to as system 100) includes an emergency supervision user platform 110, an emergency supervision service platform 120, an emergency supervision management platform 130, an emergency supervision sensor network platform 140, and an emergency supervision object platform 150.

[0016] In some embodiments, one or more platforms in system 100 may exchange information and / or data via a network.

[0017] The Emergency Monitoring User Platform 110 refers to a platform where monitoring users supervise the operation of System 100. Monitoring users include personnel from safety management departments, etc. The Emergency Monitoring User Platform includes at least one user interaction device, such as a mobile phone or computer.

[0018] Emergency monitoring service platform 120 refers to a platform used for receiving and transmitting data and / or information. Emergency monitoring service platform 120 is configured as a server or processor. Emergency monitoring service platform 120 can perform bidirectional data interaction with emergency monitoring user platform 110 and emergency monitoring management platform 130.

[0019] The emergency monitoring and management platform 130 is a comprehensive management platform that manages and coordinates the connections and collaboration between multiple platforms. The emergency monitoring and management platform is configured as a server or processor. The emergency monitoring and management platform 130 communicates with the emergency monitoring object platform 150 through the emergency monitoring sensor network platform 140.

[0020] The emergency monitoring sensor network platform 140 is used for comprehensive management of sensor information and serves as a communication transmission platform for bidirectional data interaction between the emergency monitoring management platform 130 and the emergency monitoring target platform 150. The emergency monitoring sensor network platform 140 can be configured as a communication network or gateway device. The emergency monitoring sensor network platform 140 is responsible for uploading real-time sensor data collected by the emergency monitoring target platform to the emergency monitoring management platform 130, and for issuing control commands generated by the emergency monitoring management platform 130 to the corresponding emergency monitoring target platform 150 for execution.

[0021] The Emergency Monitoring Object Platform 150 is a platform for generating monitoring information and executing control information. The Emergency Monitoring Object Platform 150 includes various monitoring, sensing, and interactive devices, such as drainage facilities, sensors (e.g., water level sensors, seepage pressure sensors), and alarm devices.

[0022] Drainage facilities are devices used for drainage. In some embodiments, drainage facilities include multiple drainage wells and valves for the drainage wells. The number and location of the drainage wells are predetermined according to actual needs.

[0023] A water level sensor is a device installed in a tailings dam to monitor the water level. Water level sensors include float-type water level sensors, ultrasonic water level sensors, and laser water level sensors, among others.

[0024] A pressure sensor is a device used to measure the wetting line and moisture content.

[0025] In some embodiments, the placement location, depth / height, number of sensors, and density of sensors in the tailings dam are set in advance according to actual needs.

[0026] Alarm devices are used to provide early warnings in abnormal situations. The number and location of alarm devices are pre-set according to actual needs.

[0027] For more information on the above, please refer to [link / reference]. Figures 2-4 .

[0028] Through System 100, communication connections can be established between various platforms, forming a closed loop of information operation among the various functional platforms. Under the unified management of the emergency supervision and management platform, the platforms can coordinate and operate in a regular manner, realizing the informatization and intelligentization of tailings dam emergency supervision.

[0029] Figure 2 This is an exemplary flowchart of an emergency monitoring method for tailings ponds, as shown in some embodiments of this specification. Process 200 is executed by the emergency monitoring management platform.

[0030] Step 210: Based on the fiber optic signals acquired through distributed optical fibers located at multiple geographical locations within the tailings dam and the spatial resolution of the distributed optical fibers, determine multiple local strain data of the tailings dam.

[0031] Tailings refer to the waste material remaining after ore has been crushed and beneficiated to extract useful components. Tailings dams are constructed by blocking valley mouths or enclosing land to store tailings or other industrial waste discharged after ore beneficiation in metal or non-metal mines.

[0032] Multiple geographical locations of a tailings dam refer to the multiple locations where optical fibers are distributed within the tailings dam.

[0033] The distribution of optical fibers in the tailings pond (in multiple geographical locations) is pre-set by staff based on prior experience.

[0034] Fiber optic signals refer to laser signals emitted from fiber optic transmitters located inside the tailings dam and transmitted to receivers. When the tailings shift, causing vibration or displacement of the fiber optic cables, the laser signal received by the fiber optic receiver will change.

[0035] In some embodiments, the emergency monitoring and management platform directly acquires fiber optic signals through distributed fiber optic acquisition.

[0036] Spatial resolution refers to data reflecting the accuracy and acquisition density of distributed optical fiber monitoring. In some embodiments, spatial resolution can be determined by the deployment density of the distributed optical fiber. A higher deployment density results in greater spatial resolution, meaning higher detection accuracy and a higher acquisition density in the spatial dimension. Spatial resolution can also be determined by the laser parameters emitted from the transmitting end of the distributed optical fiber. Greater laser emission intensity leads to higher detection accuracy. Smaller laser emission intervals result in a higher acquisition density in the temporal dimension. Laser parameters are preset by technicians based on prior experience.

[0037] Local strain data refers to data reflecting the changes in tailings deposited at different geographical locations within a tailings dam. Local strain data is represented by numerical values; the larger the value, the greater the change in the tailings deposited at the corresponding geographical location. For example, a local strain value of 0 indicates that there is no strain or cracks in the tailings deposited at that location; a change in local strain data from 0 to a positive value indicates the development of cracks in the tailings deposited at that location; and a gradual increase in local strain data indicates that the width of cracks in the tailings deposited at that location is widening.

[0038] In some embodiments, local strain data can be determined based on changes in fiber optic signals acquired through distributed optical fibers. For example, the greater the change in the fiber optic signal acquired through distributed optical fibers at a specific geographical location within the tailings dam, the larger the value of the local strain data corresponding to that location. The higher the spatial resolution of the distributed optical fibers at a specific geographical location within the tailings dam, the more accurate the confirmation result of the local strain data corresponding to that geographical location.

[0039] Step 220: Determine the rainfall response of the tailings dam based on the water level information obtained by sensors installed in the tailings dam.

[0040] Water level information refers to information characterizing the depth of water accumulated above tailings within a tailings dam. For example, water level information can be the average depth at multiple water level sensor locations. Or, it can be a dataset including the water depth at multiple water level sensor locations within the tailings dam.

[0041] Rainfall response refers to the maximum amount of rainfall a tailings dam can withstand per unit time without causing dangers such as collapse or landslides. The higher the rainfall response, the safer the tailings dam.

[0042] In some embodiments, the rainfall response can be determined in multiple ways. For example, the emergency monitoring and management platform can use the average of the historical rainfall responses corresponding to one or more historical water level information corresponding to the current water level information as the rainfall response corresponding to the current water level information. The historical water level information corresponding to the current water level information refers to the historical water level information within a statistical period whose difference from the current water level information is less than a difference threshold. The historical rainfall response corresponding to the historical water level information is determined based on historical circumstances. For example, if a tailings dam experiences a collapse, landslide, or other danger under a certain historical water level, then the rainfall at that historical moment is set as the historical rainfall response corresponding to that historical water level information.

[0043] Step 230: Based on multiple local strain data, determine the tailings stability data at the current moment and future moments.

[0044] Tailings stability data refers to data reflecting the stability of tailings. Tailings stability data is expressed numerically. The larger the value, the more stable the tailings. For example, a value of 0 represents the largest value, indicating the most stable tailings; a value less than 0 represents a smaller value, indicating a less stable tailings.

[0045] In some embodiments, the tailings stability data at the current moment can be determined based on local strain data from multiple geographical locations at the current moment. For example, the tailings stability data at the current moment can be the negative of the ratio of the average of the local strain data from multiple geographical locations at the current moment to the cumulative detection time.

[0046] In some embodiments, the cumulative detection time can refer to the cumulative time from the moment the distributed optical fiber started monitoring to the current moment.

[0047] In some embodiments, tailings stability data at future times can be determined based on local strain data from multiple consecutive historical times within a preset historical period at each geographical location of the tailings dam. The duration of the preset historical period is predetermined based on prior experience.

[0048] Future tailings stability data can be represented by the strain rate of change. The strain rate of change refers to the magnitude of change in local strain data per unit time. Statistical analysis of local strain data within a preset historical period is performed, and the magnitude of change in local strain data per unit time within that historical period is used as the strain rate of change.

[0049] In some embodiments, the emergency monitoring and management platform may select the largest strain change rate among the local strain data from different geographical locations and use its corresponding negative value as the tailings stability data for future moments.

[0050] In some embodiments, the emergency monitoring and management platform uses the negative value corresponding to the average strain change rate of local strain data in different geographical locations as the tailings stability data at future times.

[0051] In some embodiments, crack distribution data can also be determined, and then the slip probability can be determined. Based on the slip probability, tailings stability data can be determined. For more details, see [link to relevant documentation]. Figure 3 .

[0052] Step 240: Based on rainfall response data and tailings stability data, determine the target time point and the corresponding discharge parameters.

[0053] The target time point refers to the planned time for tailings drainage or flood discharge.

[0054] In some embodiments, the emergency monitoring and management platform can determine the target time point in multiple ways. For example, in response to a rainfall response amount being lower than or equal to a preset rainfall threshold and / or tailings stability data at a future time being lower than or equal to a preset stability threshold, the emergency monitoring and management platform can set the target time point as the current time point. As another example, in response to a rainfall response amount being higher than a user-preset rainfall threshold, and tailings stability data at a future time being higher than a user-preset stability threshold, the emergency monitoring and management platform can generate the time required for the rainfall response amount to reach the user-preset rainfall threshold and the time required for the tailings stability data to reach the user-preset stability threshold based on the difference between the rainfall response amount and the preset rainfall threshold, the difference between the tailings stability data and the preset stability threshold, the rate of change of the rainfall response amount, and the rate of change of the strain. The average of the time required for the rainfall response amount to reach the user-preset rainfall threshold and the time required for the tailings stability data to reach the user-preset stability threshold is used as the time interval between the target time point and the current time point. The target time point is calculated based on the time interval between the target time point and the current time point.

[0055] The rate of change of rainfall response refers to the magnitude of change of rainfall response per unit time.

[0056] In some embodiments, the rainfall response amount within a preset historical period is statistically analyzed, and the change range of the rainfall response amount per unit time within the historical period is taken as the rate of change of the rainfall response amount.

[0057] Discharge parameters refer to the operating parameters of the drainage facilities in a tailings dam. Discharge parameters may include discharge volume and discharge rate, among others. For more information on drainage facilities, please refer to [link to relevant documentation]. Figure 1 .

[0058] In some embodiments, the drainage volume may include the number of drainage wells that are open, for example, which drainage wells in the tailings are open and which are not.

[0059] In some embodiments, the drainage rate may include the valve opening degree of different drainage wells. The larger the valve opening degree of the drainage well, the faster the drainage rate. The upper limit of the valve opening degree is preset based on prior experience to prevent damage to the drainage wells and to avoid tailings collapse or landslides caused by excessively rapid drainage.

[0060] In some embodiments, the emergency monitoring and management platform determines the discharge parameters corresponding to the target time point through various methods. For example, the emergency monitoring and management platform can determine the discharge parameters by querying a discharge parameter table based on rainfall response data and tailings stability data.

[0061] The discharge parameter table includes discharge parameters corresponding to different rainfall response amounts and tailings stability data.

[0062] In some embodiments, the discharge parameter table can be constructed based on historical data. For example, the emergency monitoring and management platform can statistically analyze different historical rainfall response values ​​and historical tailings stability data, and determine the changes in rainfall response values ​​when certain discharge parameters are applied. When the change in rainfall response value exceeds a first preset threshold when certain discharge parameters are applied, the discharge parameter with the smallest value among these discharge parameters is used as the discharge parameter in the discharge parameter table corresponding to that rainfall response value and tailings stability data. The first preset threshold is preset based on prior experience.

[0063] In some embodiments, the emergency monitoring and management platform can construct a rainfall vector based on rainfall response data and tailings stability data; search a vector database based on the rainfall vector to determine at least one rainfall-related vector corresponding to the rainfall vector; and determine a target related vector and a candidate discharge parameter corresponding to the target related vector based on at least one rainfall-related vector, and determine the candidate discharge parameter as the discharge parameter.

[0064] In some embodiments, the emergency monitoring and management platform can construct a vector database based on historical data. For example, the platform can store different historical rainfall response values ​​and historical tailings stability data, corresponding to certain discharge parameters applied to those values. Candidate rainfall vectors are constructed based on these historical data. When certain discharge parameters are applied to different historical rainfall response values ​​and tailings stability data, discharge parameters whose changes in rainfall response value exceed a second preset threshold are selected as candidate discharge parameters corresponding to the candidate rainfall vector formed by those rainfall response values ​​and tailings stability data. The second preset threshold is preset based on prior experience.

[0065] A rainfall correlation vector refers to a vector that satisfies a preset vector condition with respect to a rainfall vector. In some embodiments, the preset vector condition is to identify candidate rainfall vectors whose vector distance from the rainfall vector is less than a distance threshold as rainfall correlation vectors. The distance threshold is preset by staff based on prior experience.

[0066] In some embodiments, the emergency monitoring and management platform may use clustering algorithms or other methods to retrieve at least one rainfall-related vector corresponding to a rainfall vector from a vector database.

[0067] The target correlation vector refers to the optimal rainfall correlation vector among at least one rainfall correlation vector corresponding to the rainfall vector in the vector database.

[0068] In some embodiments, the emergency monitoring and management platform may take the rainfall correlation vector with the smallest vector distance as the target correlation vector, determine the corresponding alternative discharge parameter as the alternative discharge parameter of the target correlation vector, and determine the alternative discharge parameter as the discharge parameter corresponding to the target time point.

[0069] By constructing a rainfall vector that includes rainfall response data and tailings stability data, the limitations of traditional single-threshold alarms are avoided, and the true safety status of the tailings dam is comprehensively reflected. At the same time, by using a vector database to retrieve rainfall-related vectors, the recommended discharge parameters are ensured to be based on historical successful cases rather than theoretical models, which significantly reduces the risk of misjudgment.

[0070] In some embodiments, based on the discharge parameters determined above, the emergency monitoring and management platform can adjust the valve opening of the drainage well according to the water level information of the drainage well's geographical location. For example, if the water level sensor at a certain geographical location detects a water level of 0, it means there is no water accumulation above the drainage well at that location, so there is no need to open the valve, and the valve opening is adjusted to 0. Alternatively, if the water level sensor at a certain geographical location detects a water level that is not 0, the emergency monitoring and management platform determines the valve opening of the drainage well based on the calculated drainage rate of the drainage well.

[0071] The drainage rate of a drainage well is directly proportional to the cross-sectional area of ​​the drainage outlet and the water depth in the well from the center of the drainage outlet. In some embodiments, the emergency monitoring and management platform can calculate the drainage rate of the drainage well according to formula (1), and further determine the valve opening of the drainage well based on the positive correlation between the drainage rate of the drainage well and the valve opening.

[0072] (1)

[0073] in, The drainage rate of the drainage well; The flow coefficient, ranging from 0.6 to 1.0, is related to the shape and roughness of the drain outlet and is preset in advance. The cross-sectional area of ​​the drainage outlet of the drainage well is expressed in m². 2 ; It is the acceleration due to gravity; The depth of the water in the well is measured from the center of the drain outlet, in meters.

[0074] In some embodiments, the emergency monitoring and management platform can also estimate the drainage time required based on the drainage volume and drainage rate of the drainage well, and close the drainage well valve after the drainage is completed.

[0075] Step 250: Based on the discharge parameters, control multiple drainage wells to open their drainage valves at the target time point to discharge water.

[0076] In some embodiments, the emergency monitoring and management platform can control multiple designated drainage wells to open their drainage valves at the corresponding valve opening degree at a target time point based on discharge parameters, so as to control the drainage of tailings dams at different geographical locations.

[0077] The IoT big data model system for emergency monitoring of tailings dams can be used to monitor tailings dams, reasonably determine and control the discharge parameters of different drainage wells within the tailings dam, minimize the risk of tailings dam failure and landslides, and ensure the safety of downstream urban residents.

[0078] By integrating multi-source data, using distributed fiber optic sensing, and employing dynamic predictive control, a closed-loop system of "perception-decision-execution" for tailings dam safety management has been constructed. This system enables the rational determination and control of the drainage volume and rate of different drainage wells within the tailings dam, minimizing the risk of tailings dam failures and landslides, and ensuring the safety of downstream urban residents.

[0079] In some embodiments, the emergency monitoring and management platform also estimates multiple estimated response volumes of the tailings dam in multiple future time periods based on multiple estimated water level information, drainage facility data, and tailings static information; and determines multiple estimated discharge parameters for multiple future time periods based on multiple estimated response volumes, tailings stability data, and estimated rainfall data.

[0080] Predicted water level information refers to water level information for multiple future time periods. For example, water level information for future time periods under current discharge parameters.

[0081] In some embodiments, the estimated water level information can be calculated based on the current water level information, discharge parameters, and estimated rainfall data.

[0082] Drainage facility data refers to relevant information about drainage facilities. Examples include the number of drainage wells and their operational status.

[0083] The emergency monitoring and management platform can directly obtain the number of drainage wells in the tailings dam and the working status of the drainage wells through the emergency monitoring object platform.

[0084] Static tailings information refers to data in tailings-related information that changes relatively little, such as tailings slope ratio, initial tailings dam height, tailings accumulation dam height, and tailings type and distribution.

[0085] In some embodiments, the static information of tailings is obtained directly from the emergency monitoring and management platform, which obtains pre-stored data such as the initial height of the tailings dam, the type and distribution of tailings, or by measuring the tailings dam height and the tailings slope ratio at the tailings dam site using measurement technology.

[0086] The estimated response volume refers to the rainfall response volume of the tailings dam over multiple future time periods.

[0087] In some embodiments, the emergency monitoring and management platform can determine the corresponding reference response quantity as the estimated response quantity by querying a rainfall response quantity table based on estimated water level information, drainage facility data, and tailings static information. One estimated water level corresponds to one estimated response quantity.

[0088] In some embodiments, the rainfall response scale includes different actual water level information, drainage facility data, and tailings static information, as well as corresponding reference response values. The rainfall response scale can be constructed based on multiple historical data. For example, the emergency monitoring and management platform can statistically analyze the historical rainfall corresponding to the time when the alarm device first issued an alarm under different actual water level information, drainage facility data, and tailings static information, and set this historical rainfall as the reference response value corresponding to the actual water level information, drainage facility data, and tailings static information. When accelerated crack propagation in the tailings is detected (e.g., when the increase in local strain data exceeds an amplitude threshold), the alarm device issues an alarm.

[0089] Predicted rainfall data refers to rainfall-related data for a predicted future period, such as the predicted rainfall amount and the predicted rainfall time.

[0090] In some embodiments, the emergency monitoring and management platform can obtain estimated rainfall data based on data published by the meteorological station.

[0091] Estimated discharge parameters refer to discharge parameters estimated for a future time period. In some embodiments, estimated discharge parameters can be determined in various ways. For example, the emergency monitoring and management platform determines the estimated discharge parameters based on steps 1 and 2 below.

[0092] Step 1: In response to the estimated response volume not meeting preset conditions, the emergency monitoring and management platform can determine the initial estimated discharge parameters through preset rules. For example, the initial estimated discharge parameters are inversely proportional to the tailings stability data and directly proportional to the discharge parameters at the current moment.

[0093] In some embodiments, the preset conditions may include the estimated response quantity continuously decreasing, or the rate of change of the estimated response quantity exceeding a preset magnitude threshold based on prior experience.

[0094] A continuous decrease in the estimated response volume refers to a trend in the estimated response volume that shows a continuous decrease over multiple future time periods.

[0095] The rate of decrease in the estimated response quantity refers to the magnitude of the decrease in the estimated response quantity per unit time within a future time period. The rate of decrease in the estimated response quantity is directly calculated from the magnitude of the decrease in the estimated response quantity within the future time period and the future time period itself.

[0096] In some embodiments, the emergency monitoring and management platform uses formula (2) to calculate the initial estimated discharge parameters.

[0097] (2)

[0098] in, This refers to the initial estimated discharge parameters; This refers to the excretion parameters at the current moment; This refers to stable tailings data, which is negative.

[0099] Step 2: The emergency monitoring and management platform determines the estimated discharge parameters based on the estimated rainfall amount and the initial estimated discharge parameters in the estimated rainfall data. For example, if the estimated rainfall amount is less than the rainfall response amount, the initial estimated discharge parameters are used as the estimated discharge parameters. Alternatively, if the estimated rainfall amount is not less than the rainfall response amount, the estimated discharge parameters are proportional to the initial estimated discharge parameters and proportional to the ratio of the difference between the estimated rainfall amount and the rainfall response amount to the rainfall response amount. For example, the estimated discharge parameters are calculated using formula (3).

[0100] (3)

[0101] in, This refers to the estimated discharge parameters; This refers to the initial estimated discharge parameters; This refers to the estimated rainfall. This refers to the rainfall response.

[0102] In some embodiments, if the estimated response amount meets preset conditions, it can be determined that no drainage is required. Alternatively, based on rainfall response amount and tailings stability data, the target time point and the corresponding discharge parameters can be determined; see [reference needed]. Figure 2 .

[0103] In some embodiments, the emergency monitoring and management platform can also determine the target time point for the estimated discharge parameters and adjust the valve opening of the drainage well based on the estimated rainfall time in the estimated rainfall data. For details on adjusting the valve opening of the drainage well, please refer to step 240 above.

[0104] In some embodiments, the emergency monitoring and management platform can determine the target time point for the estimated discharge parameters based on the estimated rainfall. For example, the time interval between the target time point and the estimated rainfall time is determined by the time interval between the estimated rainfall time and the current time, and the ratio of the estimated rainfall amount to the rainfall response amount. For example, the emergency monitoring and management platform can use formula (4) to determine the time interval between the target time point and the estimated rainfall time, and then calculate the target time point for the estimated discharge parameters based on the time interval between the target time point and the estimated rainfall time.

[0105] (4)

[0106] in, This refers to the time interval between the target time point and the estimated rainfall time. This refers to the estimated time of rainfall; Refers to the current time. The ratio of estimated rainfall to rainfall response. The maximum value is 1.

[0107] In some embodiments, the emergency monitoring and management platform can adjust the valve opening of multiple drainage wells at a target time point based on estimated discharge parameters.

[0108] By combining predicted rainfall data, tailings static information, and drainage facility data for collaborative calculation, the predicted rainfall response can be estimated in the future. This ensures that the predicted rainfall response is consistent with the actual engineering situation, effectively assesses the risk tolerance of the tailings dam in the future, and allows for flood discharge in advance before potential collapses or landslides, thereby reducing the risk level.

[0109] In some embodiments, the emergency monitoring and management platform can also adjust the valve opening of multiple drainage wells based on changes in multiple estimated response quantities.

[0110] The changes in multiple predicted response quantities are quantitative indicators describing the dynamic characteristics of the predicted response quantities. For example, the magnitude of change in the predicted response quantities. The magnitude of change in the predicted response quantities can be obtained by calculating the magnitude of change in the predicted response quantities per unit time.

[0111] In some embodiments, the emergency monitoring and management platform can use the absolute value of the estimated change in response volume as the required increase in the valve opening of all drainage wells.

[0112] In some embodiments, considering factors such as water evaporation, the rainfall response should gradually increase to ensure the safety of the tailings dam. In response to a gradual decrease in the estimated rainfall, the emergency monitoring and management platform can control a preset number of drainage wells with relatively large distances between their outlets and the water surface, opening the corresponding valves to the maximum value observed under similar historical water level conditions. The preset number can be set based on prior experience.

[0113] Analyzing the variation in rainfall response is one of the important means to assess the risk tolerance of tailings dams. By dynamically analyzing and predicting the changes in response, the valve opening of drainage wells can be reasonably adjusted according to the changes in rainfall response, which can achieve precise control of drainage facilities, reduce the risk of tailings dam disasters, and effectively avoid the problem of untimely temporary control.

[0114] Figure 3 This is an exemplary flowchart illustrating the determination of tailings stability data according to some embodiments of this specification. Process 300 is executed by the emergency monitoring and management platform.

[0115] Step 310: Determine the crack distribution data based on multiple local strain data.

[0116] Fracture distribution data refers to statistical information about the geographical locations of different fractures within a tailings deposit. For example, fracture distribution data may include fracture numbers and corresponding geographic coordinates at different geographical locations.

[0117] For an explanation of local strain data, please refer to [link / reference]. Figure 2 .

[0118] In some embodiments, a change in local strain data from 0 to a positive number indicates the presence of a crack at that geographic location. The emergency monitoring and management platform can determine crack distribution data by statistically analyzing the geographic locations where cracks exist. See [link to documentation] for an explanation of local strain data. Figure 2 .

[0119] Step 320: Based on the static information of the tailings and the crack distribution data, determine the sliding probabilities of multiple geographical areas in the tailings dam.

[0120] For an explanation of static information regarding tailings, please refer to [link / reference needed]. Figure 2 .

[0121] A geographical region refers to the area where a tailings dam is located, divided into several grids at equal intervals in the horizontal direction. Each grid is a geographical region. Another example is division based on pressure sensors, where each pressure sensor is the center of a geographical region, and the midpoint of the line connecting two pressure sensors is the boundary point between two geographical regions.

[0122] The slip probability refers to the probability that a tailings mine will experience safety hazards such as collapse, landslide, or crack propagation. The slip probability can be a range of values. A geographical region can correspond to a specific slip probability.

[0123] In some embodiments, the emergency monitoring and management platform can determine multiple slip probabilities for multiple geographical areas based on tailings static information and crack distribution data using various methods. For example, the platform can retrieve and determine the slip probability for each geographical area from a slip vector database. Exemplarily, the platform can construct a slip vector database, storing reference feature vectors and corresponding reference slip probabilities, selecting at least one slip correlation vector whose distance to the feature vector is less than a distance threshold, and then determining the range of values ​​formed by at least one reference slip probability corresponding to at least one slip correlation vector as the slip probability for that geographical area. The feature vector is a vector constructed based on tailings static information and crack distribution data.

[0124] In some embodiments, the emergency monitoring and management platform can determine a reference slip probability based on historical data. For example, the platform can determine the slip probability as the percentage of slip areas relative to the total number of geographical areas based on historical data showing crack distribution data with differences less than a preset difference threshold and tailings static information. The preset difference threshold is set based on prior experience. The construction of the slip vector database is similar to that of the vector database; for more details, see [link to relevant documentation]. Figure 2 .

[0125] In some embodiments, the emergency monitoring and management platform determines the predicted value of the phreatic line of the tailings dam based on water level information and multiple moisture contents at multiple geographical locations; and determines multiple slip probabilities based on crack distribution data and the predicted value of the phreatic line.

[0126] Moisture content refers to the percentage of moisture contained in soil or tailings materials at different geographical locations within a tailings dam.

[0127] In some embodiments, multiple moisture contents at multiple geographical locations can be determined by collecting data from multiple pressure sensors at multiple geographical locations.

[0128] The wetting line is the boundary between the wetted and dry surfaces formed when water seeps into tailings.

[0129] The predicted wetting line value refers to data characterizing the distribution information of multiple wetting points along the predicted wetting line. The geographical location of the wetting points (such as three-dimensional coordinates) can be a range value. The predicted wetting line value can be represented by a curve (predicted wetting line).

[0130] In some embodiments, the emergency monitoring and management platform determines the initial saturation point based on water level information. The initial saturation point refers to the location where the tailings come into contact with the water surface.

[0131] In some embodiments, the emergency monitoring and management platform can set multiple geographical locations within a preset moisture content range from multiple moisture contents as multiple infiltration points within the range of the infiltration line. The preset moisture content range can be preset based on prior experience. The emergency monitoring and management platform can perform fitting processing on the multiple infiltration points to obtain a predicted infiltration line.

[0132] In some embodiments, the predicted wetting line value can be represented by the wetting height of multiple wetting points. Connecting multiple wetting points forms the predicted wetting line. Wetting points include multiple estimated wetting points and multiple known wetting points.

[0133] In some embodiments, the predicted saturation line values ​​include multiple estimated saturation heights for multiple estimated saturation points and multiple known saturation heights for multiple known saturation points; the multiple estimated saturation heights are determined based on the multiple known saturation points and the multiple known saturation heights.

[0134] The known wetting point refers to the wetting point determined by monitoring with a osmotic pressure sensor. The estimated wetting point refers to the wetting point determined by analyzing the known wetting point.

[0135] In some embodiments, the emergency monitoring and management platform can determine the known wetting height by measuring the height of a known wetting point using a pressure sensor. See [link to pressure sensor description] for details. Figure 1 .

[0136] The estimated wetting height refers to the estimated height corresponding to the wetting point.

[0137] In some embodiments, the emergency monitoring and management platform can determine the estimated infiltration height based on multiple known infiltration points and multiple known infiltration heights. For example, the platform can use a nonlinear fitting algorithm to fit the known infiltration heights to obtain the estimated infiltration height of the infiltration points. Alternatively, the platform can construct a graph structure and determine the estimated infiltration height of the infiltration points based on the graph structure and an infiltration model.

[0138] The graph structure consists of points and edges. Points include known wetting points and estimated wetting points. The properties of known wetting points include known wetting height. Edges are lines connecting two wetting points. The properties of edges include the distance between the two wetting points and the vertical difference in elevation.

[0139] In some embodiments, the distance and vertical difference between two infiltration points can be measured using a pressure sensor.

[0140] A wetting model is a model used to determine the estimated wetting height through a graph structure. Wetting models are machine learning models. For example, a wetting model can include any one or a combination of graph neural network models, large models, or other custom model structures.

[0141] In some embodiments, the infiltration model can be obtained by training a large number of first samples with a first label. In some embodiments, the first sample may include a sample graph structure, and the first label may be the estimated infiltration height of the predicted infiltration point corresponding to the first sample. The first sample may be obtained based on historical data, and the first label corresponding to the first sample may be obtained by manual annotation.

[0142] In some embodiments, the emergency monitoring and management platform can be trained using various methods based on a first sample and a first label. For example, it can be trained using gradient descent. As an example only, multiple first samples with the first label can be input into the initial infiltration model. A loss function is constructed using the first label and the results of the initial infiltration model. The parameters of the initial infiltration model are iteratively updated based on the loss function. The model training is complete when the loss function of the initial infiltration model satisfies the iteration conditions, resulting in a trained infiltration model. The iteration conditions can include loss function convergence, the number of iterations reaching a threshold, etc.

[0143] By using known phreatic points and phreatic heights, a realistic predicted phreatic line can be determined, accurately simulating the actual shape of the phreatic line under different operating conditions in tailings dams. This provides reliable data support for subsequent work and helps improve the accuracy of tailings dam safety assessments.

[0144] In some embodiments, the emergency monitoring and management platform can acquire crack distribution data and predicted seepage line values ​​for multiple different geographical regions. Taking a geographical region as an example, the platform determines the shortest distance between cracks above the seepage line and the predicted seepage line in that region based on the crack distribution data and predicted seepage line values. The shortest distance for cracks crossing the seepage line is 0. The platform can calculate the average of the shortest distances between multiple cracks and the predicted seepage line in that geographical region, and determine the slip probability of that region by the ratio of the average to a benchmark value. The benchmark value can be determined based on the height range of seepage points when the moisture content of the tailings is within a preset range. For example, the benchmark value can be the median of the height range of seepage points.

[0145] In some embodiments, the shortest distance across the crack through the wetting line is 0. A slip probability of 1 is given below the wetting line, indicating that the tailings below the wetting line have been thoroughly soaked by water.

[0146] Crack distribution data is an effective indicator of whether there is a risk in a tailings dam. Based on crack distribution data, the risk of collapse inside the tailings dam can be reasonably assessed. The predicted value of the seepage line is determined based on water level information and water content in multiple geographical locations. Combined with crack distribution data, a comprehensive analysis is conducted, which overcomes the limitations of traditional single-factor assessment and significantly improves the accuracy of the determined sliding probability.

[0147] Step 330: Determine tailings stability data based on multiple sliding probabilities.

[0148] In some embodiments, the emergency monitoring and management platform can determine tailings stability data based on multiple sliding probabilities using various methods. For example, the platform can determine the negative of the highest sliding probability as tailings stability data. Another example is the negative of the average of the maximum values ​​among multiple sliding probabilities within a range.

[0149] For more information on determining tailings stability data, please refer to [link / reference]. Figure 4 .

[0150] By comprehensively considering the static information of tailings and the distribution data of cracks, System 100 effectively improves the accuracy of determining the sliding probability, thereby obtaining more accurate tailings stability data, which helps to discover potential risks in advance and provides strong support for the safety management of tailings dams.

[0151] Figure 4 This is an exemplary schematic diagram of a tailings analysis model shown in some embodiments of this specification.

[0152] In some embodiments, the emergency monitoring and management platform can determine tailings stability data 440 based on tailings static information 410 and multiple sliding probabilities 420 through a tailings analysis model 430.

[0153] For information on sliding probability, please refer to [link / reference]. Figure 3 For data on tailings stability, please refer to [link / reference needed]. Figure 2 .

[0154] Tailings analysis models are models used to analyze and determine tailings stability data. Tailings analysis models can be machine learning models. For example, tailings analysis models can include any one or a combination of recurrent neural networks, large models, or other custom model structures.

[0155] The input to a tailings analysis model can include static tailings information and multiple sliding probabilities. The output of a tailings analysis model can include tailings stability data.

[0156] In some embodiments, the tailings analysis model can be obtained through training on a large number of second samples with second labels. Each training sample of the second samples may include multiple sliding probabilities of the sample, static information of the tailings, etc. The second label corresponding to the second sample is the stable data of the tailings.

[0157] In some embodiments, the second sample can be generated based on historical monitoring data. The second tag can be determined based on the frequency of alarms issued by the historical alarms corresponding to the second sample. For example, the higher the frequency, the smaller the corresponding tailings stability data.

[0158] The training process for the tailings analysis model is similar to that for the infiltration model; please refer to [link / reference]. Figure 3 A description of the training process of the immersion model.

[0159] Determining tailings stability data through tailings analysis models allows for consideration of the impact of multiple factors (such as tailings static information and multiple sliding probabilities) on tailings stability data. This facilitates the use of machine learning models to accurately determine tailings stability data, thereby improving the reliability of risk supervision.

[0160] This specification provides a computer-readable storage medium that stores computer instructions. When a computer reads the computer instructions from the storage medium, the computer executes the aforementioned tailings dam emergency monitoring method.

[0161] The basic concepts have been described above. Obviously, for those skilled in the art, the detailed disclosure above is merely illustrative and does not constitute a limitation of this specification. Although not explicitly stated herein, those skilled in the art may make various modifications, improvements, and corrections to this specification. Such modifications, improvements, and corrections are suggested in this specification and therefore remain within the spirit and scope of the exemplary embodiments described herein.

[0162] Finally, it should be understood that the embodiments described in this specification are merely illustrative of the principles of the embodiments described herein. Other variations may also fall within the scope of this specification. Therefore, alternative configurations of the embodiments described herein are intended to be illustrative rather than limiting, and should be considered consistent with the teachings of this specification. Accordingly, the embodiments described herein are not limited to those explicitly introduced and described herein.

Claims

1. An IoT system for emergency monitoring of tailings dams, characterized in that, The system includes an emergency monitoring and management platform, which is configured as follows: Based on the fiber optic signals acquired through distributed optical fibers located at multiple geographical locations within the tailings dam and the spatial resolution of the distributed optical fibers, multiple local strain data of the tailings dam are determined. Based on the water level information obtained by sensors installed in the tailings dam, the rainfall response of the tailings dam is determined. The rainfall response is the maximum amount of rainfall that the tailings dam can accept per unit time without causing the risk of collapse or landslide. Based on the aforementioned multiple local strain data, tailings stability data for the current and future times are determined; Based on the rainfall response and the tailings stability data, the target time point and the corresponding discharge parameters are determined. Based on the discharge parameters, multiple drainage wells are controlled to open their drainage valves at the target time point to discharge water. In order to determine the discharge parameters, the emergency monitoring and management platform is configured as follows: Based on the rainfall response and the tailings stability data, a rainfall vector is constructed; Based on the rainfall vector, a vector database is searched to determine at least one rainfall-related vector corresponding to the rainfall vector; Based on the at least one rainfall correlation vector, a target correlation vector and a candidate discharge parameter corresponding to the target correlation vector are determined, and the candidate discharge parameter is determined as the discharge parameter; Specifically, a vector database is constructed based on historical data: different historical rainfall response values ​​and historical tailings stability data are stored in the historical data, corresponding to the discharge parameters applied to the different historical rainfall response values ​​and historical tailings stability data; candidate rainfall vectors are constructed based on the different historical rainfall response values ​​and historical tailings stability data in the historical data; when the discharge parameters applied to the different historical rainfall response values ​​and historical tailings stability data are selected, the discharge parameters whose changes in rainfall response value are greater than a second preset threshold are used as the candidate discharge parameters corresponding to the candidate rainfall vectors, where the second preset threshold is preset based on prior experience.

2. The system according to claim 1, characterized in that, The emergency monitoring and management platform is also configured as follows: Based on the aforementioned multiple local strain data, the crack distribution data is determined; Based on the static information of the tailings and the crack distribution data, the sliding probabilities of multiple geographical areas in the tailings dam are determined. The tailings stability data are determined based on the multiple sliding probabilities.

3. The system according to claim 2, characterized in that, The emergency monitoring and management platform is also configured as follows: Based on the water level information and the multiple moisture contents of the multiple geographical locations, the predicted value of the phreatic line of the tailings dam is determined; Based on the crack distribution data and the predicted infiltration line value, the plurality of sliding probabilities are determined.

4. The system according to claim 1, characterized in that, The emergency monitoring and management platform is also configured as follows: Based on multiple estimated water level information, drainage facility data, and tailings static information, the estimated response quantities of the tailings dam are estimated in multiple future time periods. Based on the multiple estimated response quantities, the tailings stability data, and the estimated rainfall data, multiple estimated discharge parameters for the multiple future time periods are determined.

5. A tailings dam emergency monitoring method, characterized in that, The method is executed by the emergency monitoring and management platform of the tailings dam emergency monitoring IoT system, and the method includes: Based on the fiber optic signals acquired through distributed optical fibers located at multiple geographical locations within the tailings dam and the spatial resolution of the distributed optical fibers, multiple local strain data of the tailings dam are determined. Based on the water level information obtained by sensors installed in the tailings dam, the rainfall response of the tailings dam is determined. The rainfall response is the maximum amount of rainfall that the tailings dam can accept per unit time without causing the risk of collapse or landslide. Based on the aforementioned multiple local strain data, tailings stability data for the current and future times are determined; Based on the rainfall response and the tailings stability data, the target time point and the corresponding discharge parameters are determined. Based on the discharge parameters, multiple drainage wells are controlled to open their drainage valves at the target time point to discharge water. To determine the excretion parameters, the method further includes: Based on the rainfall response and the tailings stability data, a rainfall vector is constructed; Based on the rainfall vector, a vector database is searched to determine at least one rainfall-related vector corresponding to the rainfall vector; Based on the at least one rainfall correlation vector, a target correlation vector and a candidate discharge parameter corresponding to the target correlation vector are determined, and the candidate discharge parameter is determined as the discharge parameter; Specifically, a vector database is constructed based on historical data: different historical rainfall response values ​​and historical tailings stability data are stored in the historical data, corresponding to the discharge parameters applied to the different historical rainfall response values ​​and historical tailings stability data; candidate rainfall vectors are constructed based on the different historical rainfall response values ​​and historical tailings stability data in the historical data; when the discharge parameters applied to the different historical rainfall response values ​​and historical tailings stability data are selected, the discharge parameters whose changes in rainfall response value are greater than a second preset threshold are used as the candidate discharge parameters corresponding to the candidate rainfall vectors, where the second preset threshold is preset based on prior experience.

6. The method according to claim 5, characterized in that, The determination of tailings stability data at the current and future times based on the multiple local strain data includes: Based on the aforementioned multiple local strain data, the crack distribution data is determined; Based on the static information of the tailings and the crack distribution data, the sliding probabilities of multiple geographical areas in the tailings dam are determined. The tailings stability data are determined based on the multiple sliding probabilities.

7. The method according to claim 6, characterized in that, The determination of multiple slip probabilities for multiple geographical areas within the tailings dam based on static tailings information and crack distribution data includes: Based on the water level information and the multiple moisture contents of the multiple geographical locations, the predicted value of the phreatic line of the tailings dam is determined; Based on the crack distribution data and the predicted infiltration line value, the plurality of sliding probabilities are determined.

8. The method according to claim 5, characterized in that, The method further includes: Based on multiple estimated water level information, drainage facility data, and tailings static information, the estimated response quantities of the tailings dam are estimated in multiple future time periods. Based on the multiple estimated response quantities, the tailings stability data, and the estimated rainfall data, multiple estimated discharge parameters for the multiple future time periods are determined.

Images