Tailing pond multi-dimensional data fusion disaster hidden danger identification and early warning method

Abstract

The invention discloses a tailing pond multi-dimensional data fusion-based disaster hidden danger identification and early warning method, and relates to the related field of disaster hidden danger identification and early warning, and the method comprises the steps: carrying out the data fusion of a multi-dimensional data set, generating a multi-dimensional data fusion result, carrying out the quick deduction of a plurality of environment parameters and the multi-dimensional data fusion result, and carrying out the early warning of the disaster hidden danger. Constructing a tailings pond catastrophe influence assessment mathematical model to perform risk assessment on the tailings pond, generating a plurality of risk levels, analyzing tailings pond dam break trigger criteria, generating a plurality of trigger indexes of the tailings pond to perform sensitivity analysis, determining a disaster trigger sensitivity coefficient and the plurality of risk levels to perform disaster hidden danger identification, and determining the disaster trigger sensitivity coefficient. And generating a disaster early warning signal and combining with the multi-dimensional data set to carry out disaster warning, and formulating emergency response measures to carry out emergency response on the disaster hidden danger of the tailings pond. The technical problems of real-time analysis and comprehensive evaluation of tailings pond data are solved, and the technical effects of improving the recognition accuracy of hidden danger and effectively performing early warning response are achieved.

Description

Technical Field

[0001] The present application relates to the field of disaster hazard identification and early warning, and in particular to a disaster hazard identification and early warning method based on multi-dimensional data fusion of tailings ponds. Background Art

[0002] Tailings ponds are common waste storage facilities in mining operations. Their primary function is to store tailings generated during mining operations. Accidents such as dam failure, landslides, and leaks within these ponds can severely impact the ecological environment and surrounding communities. In recent years, due to their large size and complex structure, potential disasters have been difficult to detect in advance, and the consequences of a disaster can be disastrous. Therefore, effectively monitoring the stability of tailings ponds, identifying potential disasters promptly, and providing effective early warnings remain pressing technical challenges in tailings pond management.

[0003] Traditional tailings dam monitoring methods rely primarily on manual inspections or a single source of monitoring data. These methods suffer from issues such as poor real-time performance, inaccurate data, and a lack of comprehensive assessment capabilities, making them ineffective in addressing complex disaster risks. Furthermore, due to the complex environmental factors affecting tailings dams, such as meteorological and hydrological variations, and soil properties, a single data source cannot fully reflect the operational status and disaster risks of tailings dams. Therefore, traditional tailings dam disaster monitoring methods cannot meet the needs of efficient early warning and emergency response. Summary of the Invention

[0004] This application solves the technical problem of real-time analysis and comprehensive evaluation of various monitoring data in tailings ponds by providing a disaster hazard identification and early warning method based on the fusion of multi-dimensional data of tailings ponds, and achieves the technical effect of combining disaster warning signals and emergency response measures to identify potential disaster risks of tailings ponds in advance, generate disaster warning signals in a timely manner, and formulate effective emergency response strategies, thereby significantly improving the accuracy of identifying disaster hazards in tailings ponds.

[0005] The present application provides a method for identifying and warning of disaster hazards of tailings ponds by multi-dimensional data fusion, comprising: performing multi-dimensional sensing acquisition on the tailings pond by a sensor equipment group to obtain a multi-dimensional initial data set, performing data synchronization on the multi-dimensional initial data set, and determining a multi-dimensional data set; retrieving multiple environmental parameters of the tailings pond, performing data fusion on the multi-dimensional data set to generate a multi-dimensional data fusion result, using dynamic numerical simulation technology to quickly deduce the multiple environmental parameters and the multi-dimensional data fusion result, and constructing a mathematical model for assessing the impact of disasters on tailings ponds; performing a risk assessment on the tailings pond by using the mathematical model for assessing the impact of disasters on tailings ponds to generate multiple risk levels, and analyzing the triggering criteria for tailings dam break to generate multiple triggering indicators for the tailings pond; performing sensitivity analysis according to the multiple triggering indicators to determine a disaster triggering sensitivity coefficient, identifying disaster hazards based on the disaster triggering sensitivity coefficient and the multiple risk levels, and generating a disaster warning signal; issuing a disaster warning based on the disaster warning signal in combination with the multi-dimensional data set, formulating emergency response measures, and executing the emergency response measures to respond to the disaster hazards of the tailings pond.

[0006] In a possible implementation, data synchronization is performed on the multidimensional initial data set to determine the multidimensional data set, and the following processing is performed: wavelet decomposition is performed on the multidimensional data signal of the multidimensional initial data set to obtain data signal wavelet coefficients; threshold quantization is performed based on the data signal wavelet coefficients to determine the data signal wavelet selection threshold; the data signal wavelet coefficients are truncated according to the data signal wavelet selection threshold, and the noise signal smaller than the data signal wavelet selection threshold is set to zero to obtain a valid signal larger than the data signal wavelet selection threshold; the valid signal is filtered and reconstructed to obtain the multidimensional data set.

[0007] In a possible implementation, the multidimensional data set is subjected to data fusion to generate a multidimensional data fusion result, and the following processing is performed: the distribution probability of the collaborative data array of the effective signal in the multidimensional data set is calculated to obtain a distribution probability array; a lattice similarity probability distribution function is constructed, and the lattice distribution of the distribution probability array is subjected to dimensionality reduction processing to generate a lattice dimensionality reduction result; fusion is performed based on the lattice dimensionality reduction result to obtain the multidimensional data fusion result.

[0008] In a possible implementation, the multiple environmental parameters and the multidimensional data fusion results are quickly deduced using dynamic numerical simulation technology to construct a mathematical model for tailings pond disaster impact assessment, and the following processing is performed: a tailings physical and mechanical property database is established based on the three-dimensional structural evolution law of the tailings pond; a cluster analysis is performed on the tailings pond according to the tailings physical and mechanical property database to identify multiple mechanical distribution parameters, and the multiple mechanical distribution parameters include similar distribution parameters and different distribution parameters; based on the similar distribution parameters and the different distribution parameters combined with pore water pressure monitoring data, calculations are performed to determine the generalized hierarchical structure data of the tailings pond; according to the generalized hierarchical structure data of the tailings pond, the multidimensional data fusion results of the tailings pond are dynamically simulated and deduced using dynamic numerical simulation technology to obtain multiple disaster deduction conditions; cross-validation is performed based on the multiple disaster deduction conditions, and the mathematical model for tailings pond disaster impact assessment is constructed according to the verification results.

[0009] In a possible implementation, the tailings pond is subjected to risk assessment through the tailings pond catastrophic impact assessment mathematical model to generate multiple risk levels, and the tailings pond dam break triggering criteria are analyzed to generate multiple triggering indicators of the tailings pond, and the following processing is performed: the tailings pond catastrophic impact assessment mathematical model is activated to perform numerical simulation of the catastrophic impact on the tailings pond to generate multiple catastrophic impact scores; a comprehensive assessment of risk indicators is performed according to the multiple catastrophic impact scores combined with the generalized hierarchical structure data of the tailings pond to generate a multi-layer risk assessment result; a risk analysis of the tailings pond is performed according to the multi-layer risk assessment result to divide the tailings pond into multiple risk levels; a stability calculation of the tailings pond is performed based on the multiple risk levels to obtain a stability coefficient of the tailings pond; a dam break trigger test is performed based on the stability coefficient, and the multiple triggering indicators are set according to the test results.

[0010] In a possible implementation, a sensitivity analysis is performed according to the multiple triggering indicators to determine the disaster triggering sensitivity coefficient, and the following processing is performed: the tailings pond is co-evolved according to the multiple triggering indicators to generate a multi-indicator co-evolution result; a sensitivity analysis is performed based on the multi-indicator co-evolution result to determine the disaster triggering sensitivity coefficient.

[0011] In a possible implementation, disaster hazards are identified based on the disaster trigger sensitivity coefficient and the multiple risk levels, a disaster warning signal is generated, and the following processing is performed: a weighted calculation is performed based on the disaster trigger sensitivity coefficient and the multiple risk levels to generate multiple weight coefficients; the multiple trigger indicators are matched and calculated according to the multiple weight coefficients to obtain a comprehensive risk score; the disaster trigger sensitivity coefficient is correlated with the multiple risk levels for disaster analysis to obtain a preset risk threshold, and it is determined whether the comprehensive risk score is greater than or equal to the preset risk threshold; when the comprehensive risk score is greater than or equal to the preset risk threshold, a warning level is set according to the comprehensive risk score, and the warning level is added to the disaster warning signal.

[0012] In a possible implementation, disaster warnings are issued based on the disaster warning signal in combination with the multidimensional dataset, emergency response measures are formulated, and the following processing is performed: the warning level is mapped to the multidimensional dataset for disaster analysis, and a disaster rescue time limit is set; rescue feedback is performed on the multidimensional data of the tailings pond according to the disaster rescue time limit to generate emergency feedback information; the multidimensional dataset is monitored and adjusted in real time based on the emergency feedback information, and the emergency response measures are formulated.

[0013] One or more technical solutions provided in this application have at least the following technical effects or advantages:

[0014] The disaster hazard identification and early warning method for tailings ponds based on multi-dimensional data fusion provided in this application solves the technical problems of real-time analysis and comprehensive evaluation of various monitoring data in tailings ponds, and achieves the technical effect of combining disaster warning signals and emergency response measures to identify potential disaster risks in tailings ponds in advance, generate disaster warning signals in a timely manner, and formulate effective emergency response strategies, thereby significantly improving the accuracy of identifying disaster hazards in tailings ponds. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] To more clearly illustrate the technical solutions of the embodiments of the present invention, the accompanying drawings of the embodiments of the present invention are briefly introduced below. Flowcharts are used in this application to illustrate the operations performed by the methods according to the embodiments of the present application. It should be understood that the preceding or following operations are not necessarily performed in precise order. Instead, the various steps may be processed in reverse order or simultaneously as needed. Furthermore, other operations may be added to these processes, or one or more operations may be removed from these processes.

[0016] Figure 1 A flow chart of a method for identifying and warning of disaster hazards in tailings ponds using multi-dimensional data fusion provided in an embodiment of the present application;

[0017] Figure 2A schematic flow chart of the mathematical model for tailings pond disaster impact assessment is provided for the construction of a method for identifying and warning of disaster hazards in tailings ponds by fusion of multi-dimensional data provided in an embodiment of the present application. DETAILED DESCRIPTION

[0018] The above description is only an overview of the technical solution of the present application. In order to more clearly understand the technical means of the present application, it can be implemented in accordance with the contents of the specification. In order to make the above and other purposes, features and advantages of the present application more obvious and easy to understand, the specific implementation methods of the present application are listed below.

[0019] In order to make the purpose, technical solutions and advantages of this application clearer, the application will be further described in detail below with reference to the accompanying drawings. The described embodiments should not be regarded as limiting this application. All other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of this application.

[0020] In the following description, reference is made to “some embodiments”, which describes a subset of all possible embodiments, but it will be understood that “some embodiments” may be the same subset or different subsets of all possible embodiments and may be combined with each other without conflict, and the terms “first\second” involved are merely used to distinguish similar objects and do not represent a specific ordering of the objects. The terms “including” and “having” and any variations are intended to cover non-exclusive inclusions. For example, a process, method, product, or server that includes a series of steps or units is not necessarily limited to those steps or units that are clearly listed, but may include other steps or modules that are not clearly listed or that are inherent to these processes, methods, products, or devices. Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by those skilled in the art to which this application belongs. The terms used herein are for the purpose of describing the embodiments of this application only.

[0021] The present application embodiment provides a method for identifying and warning of disaster hazards in tailings ponds by integrating multi-dimensional data. Figure 1 As shown, the method includes:

[0022] In step A100, multi-dimensional sensing acquisition is performed on the tailings pond through a sensing equipment group to obtain a multi-dimensional initial data set, data synchronization is performed on the multi-dimensional initial data set, and a multi-dimensional data set is determined; in a possible implementation method, step A100 further includes step A110, wavelet decomposition is performed on the multi-dimensional data signal of the multi-dimensional initial data set to obtain data signal wavelet coefficients; step A120 is executed to perform threshold quantization based on the data signal wavelet coefficients to determine the data signal wavelet selection threshold; step A130 is executed to truncate the data signal wavelet coefficients according to the data signal wavelet selection threshold, and noise signals smaller than the data signal wavelet selection threshold are set to zero to obtain valid signals larger than the data signal wavelet selection threshold; step A140 is executed to filter and reconstruct the valid signal to obtain the multi-dimensional data set.

[0023] By using wavelet transform, the original signal is decomposed into multiple wavelet coefficients. Multiple wavelet coefficients are used to characterize the characteristics of the signal at different scales (or frequencies). The multidimensional data signal of the multidimensional initial data set is decomposed into different frequency components to obtain the data signal wavelet coefficients. The data signal wavelet coefficients contain information about the original signal at different frequencies. Furthermore, based on the statistical characteristics of the data signal wavelet coefficients (such as standard deviation, mean, etc.), an appropriate threshold is selected to determine the data signal wavelet selection threshold. The data signal wavelet selection threshold is used to distinguish between valid signals and noise signals, better intercepting subsequent signals. At the same time, in order to remove noise signals and retain valid signals, each wavelet coefficient is compared with the threshold. If the wavelet coefficient is less than the threshold, it is considered to be a noise signal and is set to zero; if the wavelet coefficient is greater than or equal to the threshold, it is considered to be a valid signal and its value is retained. Finally, a set of wavelet coefficients containing only valid signals is obtained, the noise signal is effectively removed, and a valid signal is obtained. Finally, in order to reconstruct the effective part of the original signal from the truncated wavelet coefficients, the truncated wavelet coefficients can be converted back to the spatial domain or time domain of the original signal through an inverse wavelet transform, thereby obtaining a multidimensional data set, which is the multidimensional initial data set after denoising.

[0024] Execute step A200, retrieve multiple environmental parameters of the tailings pond, perform data fusion on the multi-dimensional dataset to generate a multi-dimensional data fusion result, and use kinetic numerical simulation technology to quickly deduce the multiple environmental parameters and the multi-dimensional data fusion result, and construct a mathematical model for evaluating the disaster impact of the tailings pond; In a possible implementation, step A200 further includes step A210, calculate and obtain the co-data array distribution probability of the effective signals in the multi-dimensional dataset to obtain a distribution probability array; execute step A220, construct a dot matrix similarity probability distribution function, perform dimensionality reduction processing on the dot matrix distribution of the distribution probability array to generate a dot matrix dimensionality reduction result; execute step A230, perform fusion based on the dot matrix dimensionality reduction result to obtain the multi-dimensional data fusion result.

[0025] To evaluate the cooperation or correlation between effective signals in a multi-dimensional dataset, statistical methods or machine learning algorithms such as covariance matrix, correlation analysis, mutual information, etc. can be used to calculate the similarity or correlation between data points, and a distribution probability array is constructed, where each element represents the probability of co-occurrence between data points, to obtain the distribution probability array, and the distribution probability array is used to characterize the cooperative distribution characteristics of effective signals in the multi-dimensional dataset. Further, a dot matrix similarity probability distribution function is constructed, and the dot matrix similarity probability distribution function is as follows:

[0026] L = ∑ i ∑ j KL[P(x i |x j )||Q(z i |z j )];

[0027] Where KL is a measure of the closeness between the dot matrix distribution of the distribution probability array and the dimensionality-reduced dot matrix distribution of the distribution probability array, and dimensionality reduction processing is performed with the constraint that KL approaches 0. L is the divergence representing the similarity between the dot matrix distribution of the distribution probability array and the dimensionality-reduced dot matrix distribution of the distribution probability array. P(x i |x j ) is the similarity probability regarding dot matrix x i and dot matrix x j in the dimensionality-reduced dot matrix distribution based on the distribution probability array. Q(z i |z j ) is the similarity probability regarding dot matrix z i and dot matrix z j in the dot matrix distribution based on the distribution probability array. (i, j) is any coordinate point in the co-data array of the effective signals, the value range of i is 0 < i < n, the value range of j is 0 < j < n, and n is the total number of coordinate points in the co-data array of the effective signals.

[0028] The lattice distribution of the distribution probability array is reduced in dimension using the lattice similarity probability distribution function. The lattice dimensionality reduction result is generated and used to characterize the point set of the original data in a lower-dimensional space, where each point still retains certain key features or similarity information in the original data. In order to conduct further analysis or visualization, the data points after dimensionality reduction need to be fused into a comprehensive representation. The lattice dimensionality reduction results can be fused by performing clustering, classification, regression or other forms of machine learning tasks on the dimensionality reduced point set to obtain the multidimensional data fusion result. The multidimensional data fusion result can be a single value, a vector, a matrix or a more complex structure, depending on the fusion method and purpose, providing a strong data foundation for subsequent disaster risk identification.

[0029] In one possible implementation, Figure 2 As shown, step A200 further includes step A240, establishing a database of physical and mechanical properties of tailings based on the three-dimensional structural evolution law of the tailings pond; executing step A250, performing cluster analysis on the tailings pond according to the physical and mechanical properties database of the tailings, and identifying multiple mechanical distribution parameters, wherein the multiple mechanical distribution parameters include similar distribution parameters and different distribution parameters; executing step A260, performing calculations based on the similar distribution parameters and the different distribution parameters in combination with pore water pressure monitoring data to determine the generalized hierarchical structure data of the tailings pond; executing step A270, performing dynamic simulation and deduction on the multi-dimensional data fusion results of the tailings pond according to the generalized hierarchical structure data of the tailings pond using dynamic numerical simulation technology to obtain multiple disaster deduction conditions; executing step A280, performing cross-validation based on the multiple disaster deduction conditions, and constructing the mathematical model for disaster impact assessment of the tailings pond according to the verification results.

[0030] Collect and organize the physical and mechanical property data of tailings. Through laboratory testing, field monitoring, and literature research, obtain the physical and mechanical parameters of tailings such as density, strength, deformation modulus, and permeability coefficient, and establish a corresponding database. Then, analyze the database of physical and mechanical properties of tailings using clustering algorithms (such as K-means and hierarchical clustering), and divide the tailings pond into regions with similar or different mechanical properties. These regions can correspond to different tailings accumulation layers, different mineral compositions, or different geological conditions. At the same time, regions with similar distribution parameters are merged into one layer, and regions with different distribution parameters are divided into different layers. Combined with pore water pressure monitoring data, considering the water distribution and permeability characteristics within the tailings pond, the hierarchical structure is further refined to determine the generalized hierarchical structure data of the tailings pond.

[0031] Furthermore, dynamic numerical simulation technology is used to simulate the evolution process of tailings ponds under different conditions and predict potential disaster risks. This means using finite element analysis (FEA), discrete element analysis (DEM) or other numerical simulation methods, combined with the generalized hierarchical structure data of the tailings pond, to conduct dynamic simulation deduction of the tailings pond. During the deduction process, the influence of factors such as the physical and mechanical properties of the tailings, moisture distribution, and external loads is considered. The consistency and rationality of the simulation results under different disaster deduction conditions are then verified by comparing them. At the same time, the deduction results are further verified and adjusted in combination with on-site monitoring data and historical disaster cases, and multiple disaster deduction conditions are set to ensure the accuracy and reliability of the disaster deduction results. Finally, by combining statistics, machine learning or data mining and other technologies, multiple disaster deduction conditions can be cross-validated to generate cross-validation results, and a tailings pond disaster impact assessment model can be constructed according to the cross-validation results. The tailings pond disaster impact assessment model can output the disaster risk level or probability of the tailings pond under different conditions based on multiple factors such as the structural characteristics, physical and mechanical properties, moisture distribution, and external load of the tailings pond, thereby improving the assessment accuracy of the tailings pond disaster impact.

[0032] Execute step A300, conduct risk assessment of the tailings pond through the tailings pond catastrophic impact assessment mathematical model, generate multiple risk levels, and analyze the tailings pond dam break triggering criteria to generate multiple triggering indicators of the tailings pond; in one possible implementation, step A300 further includes step A310, activate the tailings pond catastrophic impact assessment mathematical model to perform catastrophic impact numerical simulation of the tailings pond, and generate multiple catastrophic impact scores; execute step A320, conduct a comprehensive assessment of risk indicators according to the multiple catastrophic impact scores combined with the generalized hierarchical structure data of the tailings pond, and generate a multi-layer risk assessment result; execute step A330, conduct risk analysis of the tailings pond according to the multi-layer risk assessment results, and divide it into multiple risk levels; execute step A340, perform stability calculation of the tailings pond based on the multiple risk levels, and obtain the stability coefficient of the tailings pond; execute step A350, perform a dam break trigger test based on the stability coefficient, and set the multiple triggering indicators according to the test results.

[0033] The method activates the tailings dam catastrophic impact assessment mathematical model, utilizes the activated tailings dam catastrophic impact assessment mathematical model, and performs numerical simulations on the catastrophic impact of the tailings dam under different conditions. By inputting data such as the structural parameters, physical and mechanical properties, moisture distribution, and external loads of the tailings dam, the method runs the tailings dam catastrophic impact assessment mathematical model to generate multiple catastrophic impact scores. The multiple catastrophic impact scores are used to evaluate the potential catastrophic risk of the tailings dam under different conditions. The multiple catastrophic impact scores are further comprehensively evaluated in combination with the generalized hierarchical structure data of the tailings dam to generate a multi-layer risk assessment result. This refers to combining the catastrophic impact scores with the hierarchical structure data of the tailings dam, analyzing the mutual influence and constraint relationships between different layers, and using methods such as weighted average and fuzzy comprehensive evaluation to calculate the risk assessment results for each layer. Finally, the risk assessment results of each layer are integrated to form a multi-layer risk assessment report. Based on the multi-layer risk assessment results, the tailings dam is divided into multiple risk levels for targeted risk management. This refers to setting risk level classification standards, such as low risk, medium risk, high risk, and extremely high risk. Based on the results of multi-layer risk assessment, each layer or the entire tailings pond is classified into corresponding risk levels.

[0034] Furthermore, quantitative calculations of the tailings dam's stability can be performed based on multiple risk levels. This involves using limit equilibrium methods, finite element methods, or other stability calculation methods. Input data, such as the tailings dam's structural parameters and physical and mechanical properties, can be used to calculate the tailings dam's stability coefficient. This stability coefficient reflects the tailings dam's stability under current conditions. Ultimately, a series of dam-break triggering conditions, such as rising water levels, increased rainfall, and earthquakes, are set through dam-break triggering tests. Under each condition, numerical simulation models or physical experiments are run to observe the tailings dam's response. When a tailings dam fails, the corresponding triggering conditions are recorded as dam-break trigger indicators. The dam-break triggering test results are then compiled and analyzed to analyze the relationship between different triggering conditions and dam-break risk. Based on these analysis results, appropriate dam-break triggering indicators are established, such as water level thresholds, rainfall thresholds, and earthquake intensity. These indicators will be used in the tailings dam's routine safety monitoring and early warning system to promptly identify and address potential safety risks.

[0035] Execute step A400, perform sensitivity analysis according to the multiple trigger indicators, determine the disaster trigger sensitivity coefficient, identify disaster hazards based on the disaster trigger sensitivity coefficient and the multiple risk levels, and generate a disaster warning signal; in one possible implementation, step A400 further includes step A410, perform co-evolution of the tailings pond according to the multiple trigger indicators, and generate a multi-indicator co-evolution result; execute step A420, perform sensitivity analysis based on the multi-indicator co-evolution result, and determine the disaster trigger sensitivity coefficient.

[0036] The evolution of the tailings pond is simulated using numerical simulation models or system dynamics models, using multiple triggering indicators (such as water level, rainfall, earthquake intensity, and changes in the physical and mechanical properties of tailings) as input variables. By adjusting the values ​​of the input variables, observing the changes in the tailings pond's response, and simulating the evolution of the tailings pond under the combined action of different triggering indicators, the co-evolution results of multiple indicators are generated. These results can also be visualized, such as time series graphs, scatter plots, and heat maps. Through comparative analysis, key triggering indicators and their interactions are identified, providing a basis for subsequent sensitivity analysis.

[0037] Further sensitivity analysis methods, such as local sensitivity analysis (such as differential method, difference method, etc.) or global sensitivity analysis (such as variance analysis, sensitivity index method, etc.), can be used to further process the results of multi-indicator co-evolution. By calculating the influence of each triggering indicator on the probability of triggering tailings pond disaster or the degree of disaster, the disaster triggering sensitivity coefficient is determined. The disaster triggering sensitivity coefficient may include a water level sensitivity coefficient and a settlement sensitivity coefficient. The water level sensitivity coefficient is used to characterize the risk of dam break when the water level change reaches a certain critical point. The settlement sensitivity coefficient is used to characterize that rapid settlement may indicate problems with the tailings pond structure, increasing the probability of disaster occurrence. The sensitivity of each triggering indicator to the triggering of tailings pond disasters is quantified, providing a scientific basis for the safety management and early warning of tailings ponds.

[0038] In one possible implementation, step A400 further includes step A430, performing a weighted calculation based on the disaster trigger sensitivity coefficient and the multiple risk levels to generate multiple weight coefficients; executing step A440, matching and calculating the multiple trigger indicators according to the multiple weight coefficients to obtain a comprehensive risk score; executing step A450, correlating the disaster trigger sensitivity coefficient with the multiple risk levels to perform disaster analysis, obtain a preset risk threshold, and determine whether the comprehensive risk score is greater than or equal to the preset risk threshold; executing step A460, when the comprehensive risk score is greater than or equal to the preset risk threshold, setting a warning level according to the comprehensive risk score, and adding the warning level to the disaster warning signal.

[0039] The disaster trigger sensitivity coefficient is weighted and calculated with each risk level to identify the difference in sensitivity of the trigger indicators under different risk levels, and a reasonable weight is assigned to each trigger indicator to generate multiple weight coefficients. The calculation process of the weight coefficient can include expert scoring, statistical analysis or machine learning methods to reflect its relative importance in the tailings dam disaster risk. The actual value of each trigger indicator is further multiplied by the corresponding weight coefficient, and then all products are added together to obtain a comprehensive risk score. The comprehensive risk score is used to characterize the contribution of different trigger indicators to the tailings dam disaster risk.

[0040] By associating the disaster trigger sensitivity coefficient and risk level, a preset risk threshold is set. The preset risk threshold can be determined through historical disaster data, expert experience, statistical analysis and other methods. The preset risk threshold is used to judge whether the disaster risk of the tailings pond has reached a level that requires early warning. It can characterize the disaster risk level of the tailings pond under different conditions and be used to trigger corresponding early warning signals.

[0041] The comprehensive risk score is further compared with the preset risk threshold to determine whether the disaster risk of the tailings pond has reached the warning level. If the comprehensive risk score is greater than or equal to the preset risk threshold, the disaster risk of the tailings pond is considered to be high and the warning signal needs to be triggered; if the comprehensive risk score is less than the preset risk threshold, the disaster risk of the tailings pond is considered to be within an acceptable range and there is no need to trigger the warning signal temporarily. When the comprehensive risk score reaches or exceeds the preset risk threshold, the corresponding warning level is set according to the comprehensive risk score, and the warning level is added to the disaster warning signal, which means that the corresponding warning level (such as level 1 warning, level 2 warning, etc.) is determined according to the size of the comprehensive risk score and the preset warning level classification standard. Then, the warning level is combined with the disaster warning signal and the relevant personnel are notified in a timely manner through SMS, email, automatic alarm system, etc., so that the relevant personnel can be notified in time to take countermeasures.

[0042] Finally, step A500 is executed to issue a disaster warning based on the disaster warning signal in combination with the multidimensional data set, formulate emergency response measures, and execute the emergency response measures to respond to the disaster hazards of the tailings pond.

[0043] In one possible implementation, step A500 further includes step A510, mapping the warning level to the multidimensional data set for disaster analysis and setting a disaster rescue time limit; executing step A520, performing rescue feedback on the multidimensional data of the tailings pond according to the disaster rescue time limit, and generating emergency feedback information; executing step A530, performing real-time monitoring and adjustment of the multidimensional data set based on the emergency feedback information, and formulating the emergency response measures.

[0044] The use of data analysis tools (such as data mining, machine learning algorithms, etc.) to process multidimensional data sets means combining the warning level with the multidimensional data set (which may include data on the geography, geology, structure, environment, operation, etc. of the tailings pond) to conduct in-depth disaster analysis. Combined with the warning level, key disaster risk factors, possible disaster paths and disaster impact ranges are identified to more comprehensively understand the disaster risks and possible disaster consequences faced by the tailings pond. At the same time, based on factors such as the disaster characteristics of the tailings pond, the availability of rescue resources, and the urgency of the disaster impact, a disaster rescue time limit is set. The disaster rescue time limit should be urgent enough to prompt relevant personnel to act quickly, but not too urgent so as not to affect the rescue effect, so as to ensure that effective rescue measures can be taken quickly before or after the disaster occurs to reduce disaster losses.

[0045] Utilizing real-time monitoring systems and data analysis tools, the multi-dimensional data of the tailings pond is monitored and fed back in real time within the set disaster rescue time limit, and emergency feedback information is generated in a timely manner, including disaster development trends, rescue resource needs, personnel safety status, etc., to obtain the latest disaster information and rescue progress, and provide a basis for formulating and adjusting emergency response measures.

[0046] Finally, combined with emergency feedback, the multidimensional dataset is updated and optimized to ensure data accuracy and timeliness. Simultaneously, emergency response measures, including evacuation plans, relief material allocation, and personnel deployment, are formulated or adjusted based on the latest disaster status and rescue needs. This reflects the latest disaster status and rescue progress, and is then used to formulate and adjust emergency response measures accordingly.

[0047] The embodiments of the present application solve the technical problems of real-time analysis and comprehensive evaluation of various monitoring data in tailings ponds, and achieve the technical effect of combining disaster warning signals and emergency response measures to identify potential disaster risks in tailings ponds in advance, generate disaster warning signals in a timely manner, and formulate effective emergency response strategies, thereby significantly improving the accuracy of identifying disaster hazards in tailings ponds.

[0048] The above specific embodiments do not constitute a limitation to the scope of protection of this application. It should be understood by those skilled in the art that various modifications, combinations and substitutions can be made according to design requirements and other factors. Any modifications, equivalent replacements and improvements made within the spirit and principles of this application should be included in the scope of protection of this application. In some cases, the actions or steps recorded in this application can be performed in an order different from that in the embodiments and can still achieve the desired results. In addition, the processes depicted in the accompanying drawings do not necessarily require the specific order or continuous order shown to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

Claims

1. A method for identifying and warning of disaster hazards in tailings ponds based on multi-dimensional data fusion, characterized in that: The method comprises: Perform multi-dimensional sensing acquisition on the tailings pond by a sensor device group to obtain a multi-dimensional initial data set, synchronize the multi-dimensional initial data set, and determine a multi-dimensional data set; Retrieving multiple environmental parameters of the tailings pond, fusing the multidimensional data sets to generate a multidimensional data fusion result, and using dynamic numerical simulation technology to quickly deduce the multiple environmental parameters and the multidimensional data fusion result to construct a mathematical model for tailings pond disaster impact assessment; Conduct risk assessment on the tailings pond using the tailings pond disaster impact assessment mathematical model to generate multiple risk levels, and analyze the tailings pond dam break triggering criteria to generate multiple tailings pond triggering indicators; Performing sensitivity analysis according to the multiple trigger indicators to determine a disaster trigger sensitivity coefficient, identifying disaster hidden dangers based on the disaster trigger sensitivity coefficient and the multiple risk levels, and generating a disaster warning signal; Disaster warning is performed based on the disaster warning signal in combination with the multidimensional data set, emergency response measures are formulated, and the emergency response measures are executed to respond to the disaster hazards of the tailings pond.

2. The method for identifying and warning of disaster hazards in tailings ponds by multi-dimensional data fusion according to claim 1, characterized in that: Performing data synchronization on the multidimensional initial data set to determine the multidimensional data set, the method comprising: Performing wavelet decomposition on the multidimensional data signal of the multidimensional initial data set to obtain wavelet coefficients of the data signal; Performing threshold quantization based on the wavelet coefficients of the data signal to determine a data signal wavelet selection threshold; The data signal wavelet coefficients are intercepted according to the data signal wavelet selection threshold, noise signals smaller than the data signal wavelet selection threshold are set to zero, and valid signals larger than the data signal wavelet selection threshold are obtained; The effective signal is filtered and reconstructed to obtain the multi-dimensional data set.

3. The method for identifying and warning of disaster hazards in tailings ponds by multi-dimensional data fusion according to claim 2, characterized in that: Performing data fusion on the multidimensional data set to generate a multidimensional data fusion result, the method comprising: Calculating and obtaining the coordinated data array distribution probability of the valid signal in the multi-dimensional data set to obtain a distribution probability array; Constructing a dot matrix similarity probability distribution function, performing dimensionality reduction processing on the dot matrix distribution of the distribution probability array, and generating a dot matrix dimensionality reduction result; Fusion is performed based on the lattice dimensionality reduction result to obtain the multidimensional data fusion result.

4. The method for identifying and warning of disaster hazards in tailings ponds by multi-dimensional data fusion according to claim 1, characterized in that: The multiple environmental parameters and the multi-dimensional data fusion results are rapidly deduced using dynamic numerical simulation technology to construct a mathematical model for tailings pond disaster impact assessment, the method comprising: Establish a database of physical and mechanical properties of tailings based on the three-dimensional structural evolution of tailings ponds; Performing cluster analysis on the tailings pond according to the tailings physical and mechanical property database to identify multiple mechanical distribution parameters, wherein the multiple mechanical distribution parameters include similar distribution parameters and dissimilar distribution parameters; Determine the generalized hierarchical structure data of the tailings pond by performing calculation based on the similar distribution parameters, the dissimilar distribution parameters and the pore water pressure monitoring data; According to the generalized hierarchical structure data of the tailings pond, dynamic simulation deduction is performed on the multi-dimensional data fusion result of the tailings pond using dynamic numerical simulation technology to obtain multiple disaster deduction conditions; Cross-validation is performed based on the multiple disaster deduction conditions, and the tailings pond disaster impact assessment mathematical model is constructed according to the validation results.

5. The method for identifying and warning of disaster hazards in tailings ponds by multi-dimensional data fusion according to claim 4, characterized in that: The tailings dam disaster impact assessment mathematical model is used to conduct a risk assessment on the tailings dam to generate multiple risk levels, and the tailings dam failure triggering criteria are analyzed to generate multiple triggering indicators of the tailings dam. The method includes: activating the tailings pond catastrophic impact assessment mathematical model to perform numerical simulation of the catastrophic impact of the tailings pond and generate multiple catastrophic impact scores; Performing a comprehensive risk index assessment based on the multiple disaster impact scores combined with the generalized hierarchical structure data of the tailings pond to generate a multi-layer risk assessment result; Conduct risk analysis of the tailings pond according to the multi-level risk assessment results and divide the risk into multiple levels; Performing stability calculation of the tailings pond based on the multiple risk levels to obtain a stability coefficient of the tailings pond; A dam break trigger test is performed based on the stability coefficient, and the multiple trigger indicators are set according to the test results.

6. The method for identifying and warning of disaster hazards in tailings ponds by multi-dimensional data fusion according to claim 1, characterized in that: Performing sensitivity analysis according to the multiple trigger indicators to determine the disaster trigger sensitivity coefficient includes: Conduct co-evolution of the tailings pond according to multiple trigger indicators to generate multi-indicator co-evolution results; A sensitivity analysis is conducted based on the co-evolution results of multiple indicators to determine the disaster triggering sensitivity coefficient.

7. The method for identifying and warning of disaster hazards in tailings ponds by multi-dimensional data fusion according to claim 1, characterized in that: Disaster hidden dangers are identified based on the disaster trigger sensitivity coefficient and the multiple risk levels, and a disaster warning signal is generated, the method comprising: Performing weighted calculation based on the disaster trigger sensitivity coefficient and the multiple risk levels to generate multiple weight coefficients; Matching and calculating the multiple trigger indicators according to the multiple weight coefficients to obtain a comprehensive risk score; Performing a disaster analysis on the correlation between the disaster trigger sensitivity coefficient and the multiple risk levels to obtain a preset risk threshold, and determining whether the comprehensive risk score is greater than or equal to the preset risk threshold; When the comprehensive risk score is greater than or equal to the preset risk threshold, a warning level is set according to the comprehensive risk score, and the warning level is added to the disaster warning signal.

8. The tailings pond disaster hazard identification and early warning method based on multi-dimensional data fusion according to claim 7, characterized in that: Performing disaster warnings based on the disaster warning signal in combination with the multidimensional dataset and formulating emergency response measures, the method includes: Mapping the warning level to the multidimensional dataset to perform disaster analysis and set a disaster rescue time limit; Performing rescue feedback on the multi-dimensional data of the tailings pond according to the disaster rescue time limit to generate emergency feedback information; The multidimensional dataset is monitored and adjusted in real time based on the emergency feedback information, and the emergency response measures are formulated.

Images