Method and system for constructing surface groundwater combined tailing pond model

Abstract

The invention relates to the technical field of tailing pond model construction, in particular to an earth surface groundwater combined tailing pond model construction method and system. According to the method, the SWAT-MODFLOW coupling model is established, the model combines the advantages of the SWAT model in surface hydrological process simulation and the accuracy of the MODFLOW model in underground water flowing process simulation, the characteristics of the hydrodynamic field and the seepage field of the tailings pond can be more comprehensively described, and the seepage flow of the dam body can be accurately predicted. And meanwhile, a dam body slope stability CPSO-BP prediction model is established by utilizing a coordinated particle swarm optimization algorithm and a BP network, and the model can describe a complex nonlinear relationship between the slope stability and influence factors thereof, so that the prediction precision is improved. The influence of the surface water and the underground water on the tailings pond is comprehensively considered, and compared with a traditional model only considering the surface water, the running state and the instability mechanism of the tailings pond can be simulated more truly.

Description

Technical Field

[0001] The present invention relates to the technical field of tailings pond model construction, and particularly relates to a method and system for constructing a surface and groundwater combined tailings pond model. Background Art

[0002] A tailings pond refers to a site formed by building a dam to intercept the valley mouth or enclosing land, used for storing tailings discharged after ore separation in metal or non-metal mines or other industrial waste residues. A tailings pond is an artificial debris flow hazard source with high potential energy, posing a danger of dam break. Once an accident occurs, it is likely to cause major accidents. There are many tailings ponds distributed across the country. For the safety management of tailings ponds (slag), in order to prevent and reduce production safety accidents in tailings ponds and ensure the safety of people's lives and property. There are many monitoring systems for tailings pond safety management at home and abroad. Such as online-SME, Mine-TRs, M surface and groundwater combined tailings pond model construction method S and other tailings pond monitoring systems, which include water level monitoring, dam body seepage monitoring, dam body displacement monitoring, leakage volume monitoring, etc., and physically monitor a single tailings pond through sensors, ultrasonic level gauges, anchor cable dynamometers, etc.

[0003] Production practice shows that: due to the loose characteristics of the medium constituting the tailings pond dam body, it is prone to cause tailings pond dam break accidents under external disturbances, such as rainfall, earthquake, liquefaction, etc., especially extremely prone to tailings pond dam break under continuous rainfall conditions. However, the existing displacement monitoring and deformation monitoring are point monitoring, with certain limitations, unable to reflect the sliding situation between the loose media of the tailings dam body, and unable to effectively reveal the internal state changes of the tailings dam body, especially the accumulation body.

[0004] In previous studies on the stability of tailings ponds, the influence of surface water, such as mountain floods, was mostly considered; due to the loose, highly heterogeneous medium of the tailings pond and the spatial variability of hydraulic parameters, the groundwater distribution is discontinuous and the hydrodynamic field is complex, which easily causes congestion in groundwater discharge and leads to an increase in the groundwater level in front of the dam; therefore, carrying out research on the instability mechanism of tailings ponds under the combined action of surface water and groundwater has important theoretical significance.

[0005] Previous tailings pond monitoring mainly focused on surface displacement monitoring, water level monitoring, and surface element monitoring. Due to the long formation time of tailings ponds and data loss, the internal structure is unclear; in addition, accurately depicting the internal structure of tailings ponds has become an indispensable part of tailings pond instability and monitoring. Traditional structure depiction mainly relies on drilling, but drilling cannot reflect the heterogeneity of the tailings pond structure. Based on this, it is necessary to study a method for constructing a surface and groundwater combined tailings pond model. Summary of the Invention

[0006] In view of this, the purpose of the present invention is to provide a method for constructing a surface and groundwater combined tailings pond model, which effectively solves the problem that existing tailings pond models generally only consider the description of the surface of the model of surface water, with less research on groundwater and the interior of the tailings pond, and cannot truly simulate the tailings pond.

[0007] To achieve the above object, the technical solution adopted by the present invention is: a method for constructing a surface and groundwater combined tailings pond model, including obtaining historical data and real-time data of the tailings pond based on time series; fusing the historical data and real-time data to obtain sample data, and extracting surface correlation data and tailings correlation data of the sample data; respectively processing the ground correlation data and tailings correlation data to obtain ground model construction data and tailings construction data; Based on the ground model construction data, a surface water dynamic model is constructed according to the SWAT-MODFLOW coupling model; on the framework of the SWAT model and the MODFLOW model, a SWAT-MODFLOW coupling model is established to characterize the hydrodynamic field and seepage field characteristics of the tailings pond, predict the seepage flow of the dam body, and generate the combined driving force of surface water and groundwater, so as to simulate the phreatic line of the dam body under different scenarios and generate phreatic line characteristics; Based on the tailings surface construction data, combined with the coordinated particle swarm optimization algorithm and the BP network, a CPSO-BP prediction model for the slope stability of the dam body is established; the nonlinear relationship between slope stability and its influencing factors is described by the BP network, and the global optimization ability of the coordinated particle swarm optimization algorithm is used to determine the connection weights and thresholds of the BP network, and the accuracy of the BP network is optimized, so as to predict the slope stability of the dam body; Input the phreatic line characteristics into the CPSO-BP prediction model to generate the instability value of the tailings pond; Finally, output the instability value of the tailings pond.

[0008] Furthermore, the surface correlation data includes surface runoff, precipitation, evaporation, wind speed, temperature, seepage, and lateral runoff.

[0009] Furthermore, based on the three-dimensional digital model of the tailings pond ground, meteorological data and underlying surface conditions are input into the SWAT model to simulate the hydrological process under different heavy rainfall conditions; based on the three-dimensional hydrogeological conceptual model of the tailings pond, boundary conditions and hydrogeological parameters are input into the MODFLOW model to simulate the hydrodynamic process and seepage flow of the tailings pond.

[0010] Furthermore, the hydrological process under different heavy rainfall conditions is associated with the hydrodynamic process and seepage flow of the tailings pond through the precipitation infiltration conditions and surface boundary conditions of the tailings pond, jointly depicting the groundwater flow field under different scenarios.

[0011] Further, taking the internal friction angle, slope angle, rock unit weight, slope height, cohesion, and pore pressure as the main influencing factors, they are used as the input of the BP network, and the slope stability coefficient is used as the output of the network.

[0012] Further, the tailings-related data includes tailings surface-related data and tailings internal-related data; the tailings surface-related data is obtained through drone detection and remote sensing detection. The acquisition method of the tailings internal-related data is as follows: combining the existing observation boreholes, multiple electrodes are arranged in the boreholes and on the ground surface to form an electrode array, and the three-dimensional inversion calculation algorithm of the high-density electrical method is used to depict the internal structure of the tailings pond.

[0013] Further, the sample data is subjected to error expansion to obtain the first sample data and the second sample data. Based on the first sample data and the second sample data, tailings pond models are constructed respectively to obtain the first model and the second model, and the stability of the tailings pond is analyzed in a dual-model parallel manner.

[0014] Further, the formation of the first sample data and the second sample data is obtained by reverse compensation based on the error range during the measurement of the corresponding data.

[0015] Further, the test data set is input into the first model and the second model respectively, and the first instability value and the second instability value are obtained respectively. The first instability value, the second instability value and the corresponding target of the test data set are subjected to linear regression analysis to obtain the joint objective function.

[0016] A surface and groundwater combined tailings pond model construction system for implementing the above-mentioned surface and groundwater combined tailings pond model construction method, including a ground-related data acquisition module, a tailings-related data acquisition module, a SWAT-MODFLOW coupling module, a CPSO-BP prediction module, and a visualization output module; The ground-related data acquisition module is used to collect ground-related data, and the tailings-related data acquisition module is used to collect tailings-related data; the SWAT-MODFLOW coupling module is used to receive the ground-related data, and after processing the ground-related data, it depicts the hydrodynamic field and seepage field characteristics of the tailings pond according to the SWAT-MODFLOW coupling model; the CPSO-BP prediction module is used to receive the tailings-related data, and after processing the tailings-related data, it establishes a CPSO-BP prediction model for the slope stability of the dam body based on the coordinated particle swarm algorithm and the BP network; the visualization output module is used to receive the output instability value of the tailings pond and visually display the instability value of the tailings pond.

[0017] The beneficial effects of the above technical solutions are: The present invention provides a method for constructing a surface and groundwater combined tailings pond model, which improves the accuracy of judging the current situation of the tailings pond by integrating historical data and real-time data. By using technical means such as unmanned aerial vehicle detection, remote sensing detection, and high-density electrical method, the associated data on the surface and inside of the tailings are obtained, and the three-dimensional high-precision characterization of the internal structure of the tailings pond is realized.

[0018] Regarding the association between surface water and groundwater, the present invention establishes a SWAT-MODFLOW coupling model. This model combines the advantages of the SWAT model in simulating surface hydrological processes and the accuracy of the MODFLOW model in simulating groundwater flow processes, and can more comprehensively characterize the hydrodynamic field and seepage field characteristics of the tailings pond, and accurately predict the seepage flow of the dam body. At the same time, a CPSO-BP prediction model for the slope stability of the dam body is established by using the coordinated particle swarm optimization algorithm and the BP network. This model can describe the complex non-linear relationship between slope stability and its influencing factors, and improves the prediction accuracy.

[0019] At the same time, the present invention reduces the influence of data errors on the model prediction results through sample data error expansion and dual-model parallel analysis, and further improves the prediction accuracy.

[0020] By constructing a hydrodynamic model and a dam body stability model, the present invention can predict the influence of underground drainage conditions, stage rainstorm events, etc. on the model, comprehensively considers the influence of surface water and groundwater on the tailings pond, and can more realistically simulate the operation state and instability mechanism of the tailings pond compared with the traditional model that only considers surface water. This method and system can be used for predictive analysis of tailings ponds, timely discover potential safety hazards, and provide a scientific basis for the safety management and maintenance of tailings ponds, and has important practical application value. BRIEF DESCRIPTION OF THE DRAWINGS

[0021] Figure 1 is the implementation flowchart of the present invention; Figure 2 is the implementation flowchart of dual-model prediction; Figure 3 is the implementation block diagram of the SWAT-MODFLOW coupling model; DETAILED DESCRIPTION OF THE EMBODIMENTS

[0022] The present invention will be further described in detail below in conjunction with the drawings and specific embodiments: Example 1. This example aims to provide a method for constructing a surface and groundwater combined tailings pond model, which is mainly used for predictive analysis of tailings ponds and forming a tailings pond model. In view of the problem that the existing tailings pond models only consider the surface characterization of the model of surface water and have less research on groundwater and the inside of the tailings pond and cannot realistically simulate the tailings pond, this example provides an analysis model for the instability mechanism of the tailings pond under the combined drive of surface water and groundwater.

[0023] Specifically, a method for constructing a surface and groundwater combined tailings pond model includes obtaining historical data and real-time data of the tailings pond based on time series; the historical data refers to basic geological data, hydrogeological data, three-dimensional terrain data, medium property data, rainfall detection data, and water level detection data; analyzing the type of tailings pond, the type of tailings pond medium, and the formation method of the tailings pond.

[0024] Fuse the historical data and real-time data to obtain sample data, and extract the surface correlation data and tailings correlation data of the sample data; process the ground correlation data and tailings correlation data respectively to obtain ground model construction data and tailings construction data. In this embodiment, through data fusion, the current situation of the tailings pond is judged according to the historical data and further combined with the real-time detection data.

[0025] The tailings correlation data includes tailings surface correlation data and tailings internal correlation data; the tailings surface correlation data is obtained through drone detection and remote sensing detection. The three-dimensional terrain data is obtained by measuring the drone to form a ground digital model, and the remote sensing data of the reservoir area is obtained through a resource and environment remote sensing satellite.

[0026] The acquisition method of the tailings internal correlation data is as follows: combining the existing observation boreholes, arranging multiple electrodes in the boreholes and on the surface to form an electrode array, and using the algorithm of three-dimensional inversion calculation by high-density electrical method to depict the internal structure of the tailings pond. The borehole logging data is obtained through exploration and drilling to obtain the reservoir area structure data. Using high-density electrical method, carry out surface, cross-hole and joint inversion to depict the internal structure and dam body characteristics of the tailings pond three-dimensionally and with high precision; at the same time, select a typical section and use wireless telemetry to monitor the internal structure and dam body characteristics of the tailings pond. And summarize the monitoring data to form the tailings internal correlation data.

[0027] The data for constructing the ground model includes surface runoff, groundwater runoff data, and seepage flow rate. Based on the data for constructing the ground model, a surface hydrodynamic model is constructed according to the SWAT-MODFLOW coupling model. On the frameworks of the SWAT model and the MODFLOW model, the SWAT-MODFLOW coupling model is established to characterize the hydrodynamic field and seepage field characteristics of the tailings pond, predict the seepage flow rate of the dam body, and generate the combined driving force of surface water and groundwater, so as to simulate the phreatic line of the dam body under different scenarios and generate the phreatic line characteristics. The SWAT is used to simulate the main hydrological processes, including surface runoff, precipitation, evaporation, wind speed, temperature, seepage, lateral runoff, etc. However, the simulation of the groundwater part is relatively rough. Considering the limitations of the SWAT model, on the frameworks of the SWAT model and the MODFLOW model, the SWAT-MODFLOW coupling model is established to more comprehensively consider the surface-subsurface processes and more accurately describe the groundwater flow process, characterize the hydrodynamic field and seepage field characteristics of the tailings pond, and accurately predict the seepage flow rate of the dam body.

[0028] Based on the three-dimensional digital ground model of the tailings pond, meteorological data and underlying surface conditions are input into the SWAT model to simulate the hydrological processes under different heavy rainfall conditions. Based on the three-dimensional hydrogeological conceptual model of the tailings pond, boundary conditions and hydrogeological parameters are input into the MODFLOW model to simulate the hydrodynamic process and seepage flow rate of the tailings pond. The hydrological processes under different heavy rainfall conditions are related to the hydrodynamic process and seepage flow rate of the tailings pond through the precipitation infiltration conditions and surface boundary conditions of the tailings pond, jointly characterizing the groundwater flow field under different scenarios.

[0029] Based on the data for constructing the tailings surface, combining the cooperative particle swarm optimization algorithm and the BP network, a CPSO-BP prediction model for the slope stability of the dam body is established. The non-linear relationship between slope stability and its influencing factors is described by the BP network. The global optimization ability of the cooperative particle swarm optimization algorithm is used to determine the connection weights and thresholds of the BP network, optimize the accuracy of the BP network, and thus predict the slope stability of the dam body.

[0030] In order to analyze the stability of the tailings pond dam body, a CPSO-BP prediction model for the slope stability of the dam body is established using the cooperative particle swarm optimization algorithm and the BP network. The BP network can well describe the complex non-linear relationship between slope stability and its influencing factors. Six main influencing factors, namely the internal friction angle, slope angle, rock specific weight, slope height, cohesion, and pore pressure ratio, are used as the inputs of the network, and the slope stability coefficient is used as the output of the network. To avoid the BP network falling into a local optimum, the global optimization ability of the cooperative particle swarm optimization algorithm is used to determine the connection weights and thresholds of the BP network, giving full play to the advantages of the BP network and achieving the purpose of improving the prediction accuracy of the model.

[0031] Input the phreatic line characteristics into the CPSO-BP prediction model to generate the instability value of the tailings pond; finally, output the instability value of the tailings pond.

[0032] This embodiment provides a method for constructing a surface and groundwater combined tailings pond model. By integrating historical data and real-time data, the accuracy of judging the current situation of the tailings pond is improved. Using technical means such as unmanned aerial vehicle detection, remote sensing detection, and high-density electrical method, the associated data on the surface and inside of the tailings are obtained, and a three-dimensional high-precision characterization of the internal structure of the tailings pond is realized.

[0033] Regarding the association between surface water and groundwater, this embodiment establishes a SWAT-MODFLOW coupling model. This model combines the advantages of the SWAT model in simulating surface hydrological processes and the accuracy of the MODFLOW model in simulating groundwater flow processes, and can more comprehensively characterize the hydrodynamic field and seepage field characteristics of the tailings pond, and accurately predict the seepage flow of the dam body. At the same time, a CPSO-BP prediction model for the slope stability of the dam body is established using the cooperative particle swarm algorithm and the BP network. This model can describe the complex non-linear relationship between slope stability and its influencing factors, and improve the prediction accuracy.

[0034] This embodiment comprehensively considers the influence of surface water and groundwater on the tailings pond. Compared with the traditional model that only considers surface water, it can more realistically simulate the operation state and instability mechanism of the tailings pond, which is beneficial to enhancing the safety stability and natural disaster resistance of the tailings pond dam, improving the reliability of the flood prevention and drainage, and seepage drainage facilities of the tailings pond, significantly improving the prediction ability of the tailings pond model, helping to enhance the prevention and resolution of the environmental risks of the tailings pond, building a bottom line for preventing and controlling the environmental risks of the tailings pond, reducing the environmental negative effects of the tailings pond, improving the prediction level of the tailings pond, and ensuring the safe operation of the tailings pond.

[0035] Example 2. On the basis of Example 1, this embodiment further expands the sample data and provides double-model detection to improve the prediction accuracy.

[0036] In view of the fact that during the sample collection process, due to the deviation of the collected data, there will be an error between the collected data and the real data. In order to reduce the impact of the error on the model, this embodiment performs error expansion on the sample data to obtain the first sample data and the second sample data. The formation of the first sample data and the second sample data is obtained by performing reverse compensation based on the error range during the measurement of the corresponding data. For example, if the error during data collection is plus or minus 3, the first sample data is obtained by adding 3 to the sample data, and the second sample data is obtained by subtracting 3 from the sample data.

[0037] Based on the first sample data and the second sample data, the tailings pond model is constructed to obtain the first model and the second model, and the stability of the tailings pond is analyzed in parallel using the dual models. The test data set is input into the first model and the second model, and the first instability value and the second instability value are obtained respectively. The first instability value, the second instability value and the corresponding target of the test data set are subjected to linear regression analysis to obtain the joint objective function.

[0038] The specific construction method of the joint objective function is as follows: Y t =β1X t1 +β2X t2 +ε; where Y t is the test data set; X t1 is the first instability value set; X t2 is the second instability value set; β1 and β2 are coefficients; ε is a constant.

[0039] This embodiment reduces the impact of data errors on model prediction results through sample data error expansion and dual-model parallel analysis, further improves prediction accuracy, thereby avoiding interference caused by data errors and improving the accuracy of model prediction.

[0040] Example 3: This example provides a surface and groundwater combined tailings pond model construction system.

[0041] A surface groundwater combined tailings pond model construction system, comprising a ground-related data acquisition module, a tailings-related data acquisition module, a SWAT-MODFLOW coupling module, a CPSO-BP prediction module and a visualization output module; The ground-related data acquisition module is used to collect ground-related data, and the tailings-related data acquisition module is used to collect tailings-related data; the SWAT-MODFLOW coupling module is used to receive ground-related data, and after processing the ground-related data, the hydrodynamic field and seepage field characteristics of the tailings pond are characterized according to the SWAT-MODFLOW coupling model; the CPSO-BP prediction module is used to receive tailings-related data, and after processing the tailings-related data, a CPSO-BP prediction model for dam slope stability is established based on the coordinated particle swarm algorithm and BP network; the visualization output module is used to receive the output of the tailings pond instability value and visualize the tailings pond instability value.

[0042] This embodiment provides a system for implementing a model construction method. The system includes a ground correlation data acquisition module, a tailings correlation data acquisition module, a SWAT-MODFLOW coupling module, a CPSO-BP prediction module, and a visualization output module, realizing a systematic process from data acquisition, processing, model construction to result output. This embodiment can be used for predicting and analyzing tailings ponds, timely discovering potential safety hazards, and providing a scientific basis for the safety management and maintenance of tailings ponds, having important practical application value.

[0043] The above-described embodiments of the present invention do not constitute a limitation to the protection scope of the present invention. The basic concept of the present invention lies in comprehensively considering the impacts of surface water and groundwater on tailings ponds, and can more realistically simulate the operation state and instability mechanism of tailings ponds compared with traditional models that only consider surface water. Any modifications, equivalent replacements, improvements, etc. made within the spirit and principle of the present invention shall be included within the protection scope of the claims of the present invention.

Claims

1. A method for constructing a combined surface and groundwater tailings pond model, characterized in that: Including obtaining historical data and real-time data of the tailings pond based on time series; fusing the historical data and real-time data to obtain sample data, and extracting surface correlation data and tailings correlation data of the sample data; Processing the surface correlation data and tailings correlation data respectively to obtain surface model construction data and tailings model construction data; Based on the surface model construction data, constructing a surface hydrodynamic model according to the SWAT-MODFLOW coupling model; on the framework of the SWAT model and the MODFLOW model, a SWAT-MODFLOW coupling model is established to characterize the hydrodynamic field and seepage field characteristics of the tailings pond, predict the seepage flow of the dam body, generate the combined driving force of surface water and groundwater, so as to simulate the phreatic line of the dam body under different scenarios and generate phreatic line characteristics; Based on the tailings model construction data, combining the cooperative particle swarm optimization algorithm and the BP network, establishing a CPSO-BP prediction model for the stability of the dam slope; describing the non-linear relationship between slope stability and its influencing factors through the BP network, using the global optimization ability of the cooperative particle swarm optimization algorithm to determine the connection weights and thresholds of the BP network, and optimizing the accuracy of the BP network, so as to predict the stability of the dam slope; Inputting the phreatic line characteristics into the CPSO-BP prediction model to generate the instability value of the tailings pond; Finally, outputting the instability value of the tailings pond.

2. The method for constructing a surface and groundwater combined tailings pond model according to claim 1, characterized in that: The surface correlation data includes surface runoff, precipitation, evaporation, wind speed, temperature, seepage and lateral runoff.

3. The method for constructing a surface and groundwater combined tailings pond model according to claim 1, wherein: Based on the three-dimensional digital model of the tailings pond surface, inputting meteorological data and underlying surface conditions into the SWAT model to simulate the hydrological process under different heavy rainfall conditions; Based on the three-dimensional hydrogeological conceptual model of the tailings pond, inputting boundary conditions and hydrogeological parameters into the MODFLOW model to simulate the hydrodynamic process and seepage flow of the tailings pond.

4. The method for constructing a surface and groundwater combined tailings pond model according to claim 3, wherein: The hydrological process under different heavy rainfall conditions is associated with the hydrodynamic process and seepage flow of the tailings pond through the precipitation infiltration conditions and surface boundary conditions of the tailings pond, jointly characterizing the groundwater flow field under different scenarios.

5. The method for constructing a surface and groundwater combined tailings pond model according to claim 1, wherein: Taking the internal friction angle, slope angle, rock unit weight, slope height, cohesion and pore pressure as the main influencing factors as the input of the BP network, and taking the slope stability coefficient as the output of the network.

6. The method for constructing a surface and groundwater combined tailings pond model according to claim 1, wherein: The tailings correlation data includes tailings surface correlation data and tailings internal correlation data; the tailings surface correlation data is obtained through drone detection and remote sensing detection, and the acquisition method of the tailings internal correlation data is: combining the existing observation boreholes, arranging multiple electrodes in the boreholes and on the surface to form an electrode array, and using the algorithm of three-dimensional inversion calculation of the high-density resistivity method to characterize the internal structure of the tailings pond.

7. The method for constructing a surface and groundwater combined tailings pond model according to claim 1, wherein: Performing error expansion on the sample data to obtain the first sample data and the second sample data, respectively constructing a tailings pond model based on the first sample data and the second sample data to obtain the first model and the second model, and analyzing the stability of the tailings pond in a dual-model parallel manner.

8. The method for constructing a surface and groundwater combined tailings pond model according to claim 7, wherein: The formation of the first sample data and the second sample data is obtained by reverse compensation based on the error range during the measurement of the corresponding data.

9. The method for constructing a surface and groundwater combined tailings pond model according to claim 7, wherein: The test data set is input into the first model and the second model respectively, and the first instability value and the second instability value are obtained respectively. Linear regression analysis is performed on the first instability value, the second instability value and the corresponding target of the test data set to obtain a joint objective function.

10. A surface and groundwater combined tailings pond model construction system for implementing the surface and groundwater combined tailings pond model construction method according to claim 1, characterized in that: It includes a ground correlation data acquisition module, a tailings correlation data acquisition module, a SWAT-MODFLOW coupling module, a CPSO-BP prediction module and a visualization output module; The ground correlation data acquisition module is used to acquire ground correlation data, and the tailings correlation data acquisition module is used to acquire tailings correlation data; the SWAT-MODFLOW coupling module is used to receive the ground correlation data, and after processing the ground correlation data, it characterizes the hydrodynamic field and seepage field characteristics of the tailings pond according to the SWAT-MODFLOW coupling model; the CPSO-BP prediction module is used to receive the tailings correlation data, and after processing the tailings correlation data, it establishes a CPSO-BP prediction model for the slope stability of the dam body based on the coordinated particle swarm algorithm and the BP network; the visualization output module is used to receive the output instability value of the tailings pond and visually display the instability value of the tailings pond.

Images