Tailings pond risk warning and disposal full-process collaborative management platform

Abstract

The present invention discloses a full-process collaborative management platform for tailings pond risk warning and disposal, comprising: an early warning module, used to evaluate the risk of the tailings pond based on the tailings pond monitoring data, and determine whether to issue an early warning prompt; a query module, used to query the collaborative disposal solution database based on the early warning prompt after the early warning module issues the early warning prompt, and determine a target collaborative disposal solution; an acquisition module, used to execute the target collaborative disposal solution and obtain collaborative disposal feedback data from relevant departments; a risk assessment module, used to evaluate the risk of the tailings pond based on the collaborative disposal feedback data from relevant departments, and obtain a first risk assessment value; an early warning release module, used to compare the first risk assessment value with a preset risk assessment threshold, and when it is determined that the first risk assessment value is less than the preset risk assessment threshold, send an early warning release instruction to the early warning module; real-time monitoring and early warning of tailings pond risks, rapid determination of collaborative disposal solutions, and improved risk avoidance efficiency.

Description

Technical Field

[0001] The present invention relates to the technical field of tailings pond risk warning and disposal, and in particular to a tailings pond risk warning and disposal full-process collaborative management platform. Background Art

[0002] Tailings ponds, specifically designed to store industrial waste residues generated during metal and non-metallic mining, are essential facilities for maintaining normal production. However, these facilities also pose a significant safety hazard: the danger of high-energy man-made debris flows. The waste residue accumulated in tailings ponds often contains a large amount of water, forming a mud-like substance. This can lead to dam failures if exposed to extreme weather conditions, poor management, or design flaws.

[0003] In recent years, with the rapid advancement of global industrialization, particularly the increasing mining activity, the number of tailings ponds has increased dramatically both domestically and internationally. These ponds are not only large in scale but also widely distributed, ranging from bustling urban areas to remote mountainous areas. However, this rapid growth has not been accompanied by a simultaneous improvement in safety management, resulting in serious safety hazards in some tailings ponds.

[0004] At present, the existing technology for the management of tailings ponds has the following main problems: (1) early warning of the safety risks of tailings ponds, but no relevant risk avoidance plan is provided after the warning; (2) after the warning occurs, the lifting of the warning can only rely on human experience to judge; (3) after the warning is issued, it is impossible for various emergency departments to coordinate and deal with it, resulting in relatively low risk avoidance efficiency.

[0005] Therefore, there is an urgent need for a tailings pond risk warning and disposal full-process collaborative management platform to solve the above problems. Summary of the Invention

[0006] The present invention aims to solve at least one of the technical problems in the above-mentioned technologies to a certain extent. To this end, the purpose of the present invention is to propose a collaborative management platform for the entire process of tailings pond risk warning and disposal, which realizes real-time monitoring and accurate warning of tailings pond risks, quickly determines appropriate collaborative disposal plans, and coordinates multi-department disposal to improve risk avoidance efficiency. The setting of the warning cancellation module can avoid unnecessary continuous warnings, making management more reasonable and accurate.

[0007] To achieve the above objectives, the present invention proposes a tailings pond risk warning and disposal full-process collaborative management platform, including:

[0008] The early warning module is used to assess the risk of the tailings pond based on the tailings pond monitoring data and determine whether to issue an early warning;

[0009] A query module is used to query the collaborative disposal solution database based on the early warning prompt after the early warning module issues the early warning prompt, and determine the target collaborative disposal solution;

[0010] The acquisition module is used to execute the target collaborative disposal plan and obtain collaborative disposal feedback data from relevant departments;

[0011] A risk assessment module is used to assess the risk of the tailings pond based on the collaborative disposal feedback data of relevant departments to obtain a first risk assessment value;

[0012] The warning cancellation module is used to compare the first risk assessment value with a preset risk assessment threshold, and when it is determined that the first risk assessment value is less than the preset risk assessment threshold, send a warning cancellation instruction to the warning module.

[0013] Preferably, the early warning module includes:

[0014] The first acquisition submodule is used to obtain real-time tailings pond monitoring data;

[0015] A preprocessing submodule, configured to preprocess the real-time tailings pond monitoring data to obtain preprocessed real-time tailings pond monitoring data;

[0016] The feature extraction submodule is used to extract features from the pre-processed real-time tailings pond monitoring data and determine the risk type of the tailings pond;

[0017] A first risk assessment submodule is configured to assess the risk of the tailings pond based on the pre-processed real-time tailings pond monitoring data, the risk type of the tailings pond, and a preset algorithm to obtain a second risk assessment value;

[0018] The early warning issuing submodule is used to compare the second risk assessment value with a preset risk assessment threshold, and issue an early warning prompt when it is determined that the second risk assessment value is greater than or equal to the preset risk assessment threshold; the early warning prompt includes the risk type of the tailings pond.

[0019] Preferably, the preprocessing submodule includes:

[0020] An outlier processing unit, configured to perform outlier processing on the real-time tailings pond monitoring data to obtain an outlier processing result;

[0021] The confirmation unit is used to use the abnormal value processing result as pre-processed real-time tailings pond monitoring data.

[0022] Preferably, the outlier processing unit includes:

[0023] a first detection subunit, configured to classify the real-time tailings pond monitoring data to obtain a plurality of real-time tailings pond monitoring sub-data groups; and perform anomaly detection on the plurality of real-time tailings pond monitoring sub-data groups to obtain a plurality of abnormal data groups;

[0024] a second detection subunit, configured to perform abnormal data point detection on the plurality of abnormal data groups to obtain a plurality of abnormal data points;

[0025] The outlier processing subunit is used to:

[0026] Take any abnormal data point as the second data point;

[0027] Determine the target area with the second data point as the center and the preset distance as the radius;

[0028] Get the data value of each data point in the target area;

[0029] The median of the data values ​​of each data point in the target area is used as the replacement value of the second data point;

[0030] Traverse all abnormal data points and get the replacement value of each abnormal data point;

[0031] The abnormal data values ​​are replaced based on the replacement values ​​of all abnormal data points to complete the abnormal value processing of the real-time tailings pond monitoring sub-data group.

[0032] Preferably, the first detection subunit includes:

[0033] A first computing component is configured to:

[0034] Classifying the real-time tailings pond monitoring data to obtain a plurality of real-time tailings pond monitoring sub-data groups;

[0035] Randomly select a real-time tailings pond monitoring sub-data group as the target data group;

[0036] Sorting the data in the target data group based on the time series to obtain a sorted target data group; and evenly dividing the sorted target data group into a number of target sub-data groups;

[0037] Randomly select a target sub-data group as the first data group;

[0038] Calculating the mean of the data values ​​in the first data group to obtain a first mean;

[0039] Calculating the mean of the data values ​​of the other target sub-data groups in the target data group except the first data group to obtain a second mean;

[0040] Calculating the ratio of the first mean to the second mean to obtain a first ratio;

[0041] The first detection component is used to:

[0042] comparing the first ratio with a preset threshold, and when it is determined that the first ratio is greater than or equal to the preset threshold, treating the first data group as an abnormal data group;

[0043] Traverse all target sub-data groups and obtain several abnormal data groups.

[0044] Preferably, the second detection subunit includes:

[0045] The second computing component is configured to:

[0046] Randomly select an abnormal data group as the second data group;

[0047] Obtaining data values ​​corresponding to each data point in the second data group;

[0048] Take any data point as the first data point;

[0049] Calculating the difference between the first data point and the data values ​​of the other data points in the second data group except the first data point to obtain a plurality of difference values ​​corresponding to the first data point;

[0050] Summing the plurality of differences to obtain a sum value of the first data point;

[0051] Traversing all first data points in the second data group to obtain a sum value corresponding to each first data point;

[0052] Calculate the mean of the sum values ​​corresponding to all first data points to obtain the target mean;

[0053] Calculate the ratio of the sum value corresponding to each first data point to the target mean to obtain the abnormal evaluation value of each first data point;

[0054] Second detection component:

[0055] Comparing the abnormality evaluation value of each first data point with a preset evaluation threshold, and taking the first data point whose abnormality evaluation value is greater than or equal to the preset evaluation threshold as an abnormal data point;

[0056] All first data points in the second data group are traversed to obtain a number of abnormal data points.

[0057] Preferably, the first risk assessment submodule is used to assess the risk of the tailings pond based on the real-time tailings pond monitoring data, the risk type of the tailings pond and a preset algorithm to obtain a second risk assessment value, including:

[0058] The default algorithm is:

[0059]

[0060] Where θ represents the second risk assessment value; σ t represents the preset weight value corresponding to the t-th risk type; e represents a natural constant; A t represents the total number of real-time tailings pond monitoring data obtained for the assessment of the t-th risk type; B t represents the number of abnormal data in the real-time tailings pond monitoring data obtained when evaluating the t-th risk type; C t represents the mean value of the real-time tailings dam monitoring data obtained when evaluating the t-th risk type; X represents the total number of risk types in the tailings dam risk assessment.

[0061] Preferably, the risk assessment module includes:

[0062] The second acquisition submodule is used to query the target feedback data in the collaborative disposal feedback data of the relevant departments based on the risk type; the target feedback data is used as data for the risk assessment of the tailings pond;

[0063] The calculation submodule is used to obtain a first risk assessment value based on the target feedback data and a preset algorithm.

[0064] Preferably, the method for constructing a collaborative disposal solution database includes:

[0065] Obtain historical data of tailings ponds;

[0066] Classifying the tailings pond historical data based on tailings pond disaster types to obtain a plurality of historical disaster type data sets; the historical disaster type data sets include tailings pond historical disaster data and historical collaborative disposal solution process data; the tailings pond historical disaster data and historical collaborative disposal solution process data have a one-to-one correspondence;

[0067] Take any historical disaster type data set as the target data set;

[0068] Performing feature extraction on each tailings pond historical disaster data in the target data set to obtain a first data feature corresponding to each tailings pond historical disaster data in the target data set;

[0069] Take any tailings pond historical disaster data as the target historical disaster data;

[0070] Obtain historical collaborative disposal plan process data corresponding to the target historical disaster data;

[0071] Verifying the historical collaborative disposal solution process data, and obtaining target collaborative disposal solution process data after passing the verification;

[0072] Get the preset blank database;

[0073] The first data feature corresponding to the historical disaster data of each tailings pond and the target collaborative disposal solution process data are associated and stored in the preset blank database to obtain a collaborative disposal solution database.

[0074] Preferably, the historical collaborative disposal solution process data is verified, and after the verification is passed, the target collaborative disposal solution process data is obtained, including:

[0075] Splitting the historical collaborative disposal solution process data to obtain a plurality of historical collaborative disposal solution process sub-data;

[0076] Performing feature extraction on a plurality of historical collaborative disposal solution process sub-data respectively to obtain a second data feature corresponding to each historical collaborative disposal solution process sub-data;

[0077] Matching the second data feature based on the sensitive features in the preset sensitive feature library; using the successfully matched second data feature as the initial pending feature to obtain a plurality of initial pending features; using the successfully matched sensitive feature as the target sensitive feature to obtain a plurality of target sensitive features;

[0078] Obtain verification information corresponding to each target sensitive feature; the verification information includes a demand value corresponding to each initially undetermined feature;

[0079] The sum of several demand values ​​is calculated to obtain the total demand of all the initial pending features in the historical collaborative disposal solution process sub-data;

[0080] Comparing the demand sum with a preset demand threshold;

[0081] If the total demand is greater than or equal to a preset demand threshold, the historical collaborative disposal solution process data is used as the target collaborative disposal solution process data;

[0082] If the total demand is less than a preset demand threshold, the historical collaborative disposal solution process data and the tailings pond historical disaster data corresponding to the historical collaborative disposal solution process data are deleted;

[0083] Traverse all historical collaborative processing solution process data to obtain several target collaborative processing solution process data.

[0084] The present invention provides a collaborative management platform for the entire process of tailings pond risk warning and disposal. By evaluating the tailings pond risk through tailings pond monitoring data, it can timely and accurately issue warnings for tailings pond risks, thereby improving safety assurance capabilities; by querying the collaborative disposal solution database, it ensures the scientific nature and effectiveness of disposal measures; executing the collaborative disposal solution and obtaining feedback data helps to continuously optimize the disposal process and solution; the existence of the risk assessment module can quantitatively evaluate the disposal effect, facilitating an intuitive understanding of risk status changes; the warning cancellation module ensures the rationality of the warning and avoids unnecessary continuous warning interference; it promotes collaboration among relevant departments and improves work efficiency and management level.

[0085] Other features and advantages of the present invention will be described in the following description, and in part will become apparent from the description, or will be understood by practicing the present invention. The purpose and other advantages of the present invention can be realized and obtained by the structures particularly pointed out in the written description and the accompanying drawings.

[0086] The technical solution of the present invention is further described in detail below through the accompanying drawings and embodiments. BRIEF DESCRIPTION OF THE DRAWINGS

[0087] The accompanying drawings are used to provide a further understanding of the present invention and constitute a part of the specification. Together with the embodiments of the present invention, they are used to explain the present invention and do not constitute a limitation of the present invention. In the accompanying drawings:

[0088] Figure 1 This is a block diagram of a tailings pond risk warning and disposal full-process collaborative management platform according to one embodiment of the present invention;

[0089] Figure 2 is a block diagram of an early warning module according to one embodiment of the present invention;

[0090] Figure 3 is a block diagram of a preprocessing submodule according to one embodiment of the present invention. DETAILED DESCRIPTION

[0091] The preferred embodiments of the present invention are described below with reference to the accompanying drawings. It should be understood that the preferred embodiments described herein are only used to illustrate and explain the present invention, and are not used to limit the present invention.

[0092] Example 1

[0093] like Figure 1 As shown, a tailings pond risk warning and disposal full-process collaborative management platform includes:

[0094] The early warning module is used to assess the risk of the tailings pond based on the tailings pond monitoring data and determine whether to issue an early warning;

[0095] A query module is used to query the collaborative disposal solution database based on the early warning prompt after the early warning module issues the early warning prompt, and determine the target collaborative disposal solution;

[0096] The acquisition module is used to execute the target collaborative disposal plan and obtain collaborative disposal feedback data from relevant departments;

[0097] A risk assessment module is used to assess the risk of the tailings pond based on the collaborative disposal feedback data of relevant departments to obtain a first risk assessment value;

[0098] The warning cancellation module is used to compare the first risk assessment value with a preset risk assessment threshold, and when it is determined that the first risk assessment value is less than the preset risk assessment threshold, send a warning cancellation instruction to the warning module.

[0099] In this embodiment, the tailings pond monitoring data includes water level data, dam displacement data, infiltration line data, reservoir pressure data, dry beach length and slope data, rainfall data, seepage data, dam internal stress and strain data, video monitoring data and geological environment data.

[0100] In this embodiment, the early warning prompt includes the risk type of the tailings pond.

[0101] In this embodiment, the collaborative disposal solution database is a summary database of collaborative disposal solutions for different types of risks that are set up in advance, and is used to query collaborative disposal solutions based on the characteristics of different types of risks.

[0102] In this embodiment, the collaborative disposal feedback data of the relevant departments is of the same data type as the tailings pond monitoring data, that is, the tailings pond monitoring data after executing the target collaborative disposal plan is the collaborative disposal feedback data of the relevant departments.

[0103] In this embodiment, the preset risk assessment threshold is a value set based on industry experience.

[0104] The beneficial effects of the above technical solution are: by evaluating the risk of the tailings pond through the tailings pond monitoring data, it is possible to issue early warnings for the tailings pond risks in a timely and accurate manner, thereby improving the safety assurance capability; by querying the collaborative disposal solution database, the scientific nature and effectiveness of the disposal measures are ensured; the implementation of the collaborative disposal solution and the acquisition of feedback data help to continuously optimize the disposal process and solution; the existence of the risk assessment module can quantitatively evaluate the disposal effect, facilitating an intuitive understanding of the changes in risk status; the early warning cancellation module ensures the rationality of the early warning and avoids unnecessary continuous early warning interference; it promotes collaboration among relevant departments and improves work efficiency and management level.

[0105] Example 2

[0106] like Figure 2 As shown, the early warning module includes:

[0107] The first acquisition submodule is used to obtain real-time tailings pond monitoring data;

[0108] A preprocessing submodule, configured to preprocess the real-time tailings pond monitoring data to obtain preprocessed real-time tailings pond monitoring data;

[0109] The feature extraction submodule is used to extract features from the pre-processed real-time tailings pond monitoring data and determine the risk type of the tailings pond;

[0110] A first risk assessment submodule is configured to assess the risk of the tailings pond based on the pre-processed real-time tailings pond monitoring data, the risk type of the tailings pond, and a preset algorithm to obtain a second risk assessment value;

[0111] The early warning issuing submodule is used to compare the second risk assessment value with a preset risk assessment threshold, and issue an early warning prompt when it is determined that the second risk assessment value is greater than or equal to the preset risk assessment threshold; the early warning prompt includes the risk type of the tailings pond.

[0112] In this embodiment, the real-time tailings pond monitoring data is preprocessed, and the preprocessing includes outlier processing.

[0113] In this embodiment, a specific implementation method for extracting features from pre-processed real-time tailings pond monitoring data and determining the risk type of the tailings pond is as follows: the pre-processed monitoring data is classified into different types, such as water level, displacement, pressure, etc.; for each type of data, key characteristic indicators that can reflect the risk are determined. For example, for water level data, the water level change rate, maximum water level, etc. can be selected; for displacement data, the displacement amount, displacement speed, etc. can be selected; statistical methods are used to calculate characteristic indicators, such as mean, variance, extreme value, etc.; the changing trends and patterns of characteristic indicators over time are analyzed to extract time series features, such as periodicity, trend, etc.; pattern recognition techniques, such as cluster analysis and classification algorithms, are used to classify data features to determine the category to which the risk type belongs; the correlation between different characteristic indicators is analyzed to discover potential risk correlation patterns; the extracted features are combined with expert experience and knowledge to clarify the risk type.

[0114] The beneficial effects of the above technical solution are: real-time monitoring data can be obtained in a timely manner through the first acquisition submodule, which can quickly respond to changes in the tailings pond; the preprocessing submodule ensures the accuracy and availability of the data, providing a reliable basis for subsequent analysis; the feature extraction submodule can accurately determine the risk type, making the risk assessment more targeted; the first risk assessment submodule conducts risk assessment based on a comprehensive range of factors, which improves the scientificity and accuracy of the assessment; the early warning issuance submodule issues early warning prompts in a timely manner based on the comparison of the assessment value with the threshold, and includes the risk type, which allows relevant personnel to quickly understand the specific risk situation so that they can take timely response measures to ensure the safe operation of the tailings pond.

[0115] Example 3

[0116] like Figure 3 As shown, the preprocessing submodule includes:

[0117] An outlier processing unit, configured to perform outlier processing on the real-time tailings pond monitoring data to obtain an outlier processing result;

[0118] The confirmation unit is used to use the abnormal value processing result as pre-processed real-time tailings pond monitoring data.

[0119] The beneficial effects of the above technical solution are: removing or correcting abnormal data through the outlier processing unit to ensure that subsequent analysis is based on more reliable data and avoid misleading the overall results by outliers; obtaining more accurate pre-processed data, which is conducive to the accuracy of subsequent feature extraction and risk assessment; making the entire early warning module run based on high-quality data, improving the stability and reliability of the system; reducing erroneous risk assessments and early warnings caused by outliers, making early warnings more reasonable and credible.

[0120] Example 4

[0121] Outlier processing unit, including:

[0122] a first detection subunit, configured to classify the real-time tailings pond monitoring data to obtain a plurality of real-time tailings pond monitoring sub-data groups; and perform anomaly detection on the plurality of real-time tailings pond monitoring sub-data groups to obtain a plurality of abnormal data groups;

[0123] a second detection subunit, configured to perform abnormal data point detection on the plurality of abnormal data groups to obtain a plurality of abnormal data points;

[0124] The outlier processing subunit is used to:

[0125] Take any abnormal data point as the second data point;

[0126] Determine the target area with the second data point as the center and the preset distance as the radius;

[0127] Get the data value of each data point in the target area;

[0128] The median of the data values ​​of each data point in the target area is used as the replacement value of the second data point;

[0129] Traverse all abnormal data points and get the replacement value of each abnormal data point;

[0130] The abnormal data values ​​are replaced based on the replacement values ​​of all abnormal data points to obtain the outlier processing results.

[0131] The working principle of the above technical solution is: First, the first detection subunit classifies the real-time tailings pond monitoring data in order to perform more detailed anomaly detection, thereby finding several abnormal data groups. Then, the second detection subunit further performs accurate detection of abnormal data points on the abnormal data group to determine the specific abnormal data points. Then, for each abnormal data point, the outlier processing subunit determines a target area with it as the center and a preset distance as the radius, obtains the data values ​​of each data point in the area, and uses the median of these data values ​​as the replacement value of the abnormal data point. After traversing all abnormal data points to obtain their respective replacement values, the abnormal data values ​​are finally replaced with these replacement values ​​to obtain the result after outlier processing. This method of determining the replacement value of abnormal data points based on local area data characteristics can reduce the impact of outliers on the overall data to a certain extent, making data processing more reasonable and accurate.

[0132] The beneficial effects of the above technical solution are: by gradually detecting and processing abnormal data points, the impact of outliers on the overall data quality is effectively reduced, making subsequent data-based analysis and decision-making more accurate; it can accurately find abnormal data points and make targeted corrections, rather than roughly processing the entire data set; use the target area centered on the abnormal data point to determine the replacement value, which is more suitable for local data characteristics and avoids excessive or unreasonable correction; while processing outliers, try to maintain the integrity and consistency of the data and reduce damage to the original data structure; make the processed real-time tailings pond monitoring data more reliable, and provide a more solid foundation for subsequent risk assessment and other work.

[0133] Example 5

[0134] The first detection subunit includes:

[0135] A first computing component is configured to:

[0136] Classifying the real-time tailings pond monitoring data to obtain a plurality of real-time tailings pond monitoring sub-data groups;

[0137] Randomly select a real-time tailings pond monitoring sub-data group as the target data group;

[0138] Sorting the data in the target data group based on the time series to obtain a sorted target data group; and evenly dividing the sorted target data group into a number of target sub-data groups;

[0139] Randomly select a target sub-data group as the first data group;

[0140] Calculating the mean of the data values ​​in the first data group to obtain a first mean;

[0141] Calculating the mean of the data values ​​of the other target sub-data groups in the target data group except the first data group to obtain a second mean;

[0142] Calculating the ratio of the first mean to the second mean to obtain a first ratio;

[0143] The first detection component is used to:

[0144] comparing the first ratio with a preset threshold, and when it is determined that the first ratio is greater than or equal to the preset threshold, treating the first data group as an abnormal data group;

[0145] Traverse all target sub-data groups and obtain several abnormal data groups.

[0146] The working principle of the above technical solution is: first, the first calculation component classifies the real-time tailings pond monitoring data to obtain several sub-data groups, and then for any target data group, it is sorted based on the time series and evenly divided into several target sub-data groups. Then, the mean of one of the target sub-data groups (the first data group) is calculated to obtain a first mean, and the mean of the other target sub-data groups is calculated to obtain a second mean, and then the ratio of the two (the first ratio) is calculated. The first detection component compares the first ratio with a preset threshold value. If it is greater than or equal to the preset threshold value, the first data group is determined to be an abnormal data group, and all abnormal data groups are found by traversing all target sub-data groups. The whole process detects and determines abnormal data groups through this method based on data grouping, mean calculation and ratio comparison.

[0147] The beneficial effects of the above technical solution are: through careful grouping, calculation and comparison, it is possible to more accurately identify data groups that may have anomalies, thereby improving the accuracy of anomaly detection; sorting and analysis based on time series are more in line with the actual generation law of data, which helps to discover anomalies that are inconsistent with normal trends; by calculating the ratio of the first data group to the mean of other groups, local comparative analysis can be performed, which can more keenly perceive relative anomalies; combining multiple calculation and judgment methods can reduce the misjudgment of normal data to a certain extent and improve the reliability of anomaly judgment; it has good adaptability to real-time tailings pond monitoring data of different types and characteristics, and can adapt to a variety of complex situations; accurately detected abnormal data groups can provide clear goals and basis for subsequent operations such as outlier processing, thereby improving the work efficiency and quality of the entire system.

[0148] Example 6

[0149] The second detection subunit includes:

[0150] The second computing component is configured to:

[0151] Randomly select an abnormal data group as the second data group;

[0152] Obtaining data values ​​corresponding to each data point in the second data group;

[0153] Take any data point as the first data point;

[0154] Calculating the difference between the first data point and the data values ​​of the other data points in the second data group except the first data point to obtain a plurality of difference values ​​corresponding to the first data point;

[0155] Summing the plurality of differences to obtain a sum value of the first data point;

[0156] Traversing all first data points in the second data group to obtain a sum value corresponding to each first data point;

[0157] Calculate the mean of the sum values ​​corresponding to all first data points to obtain the target mean;

[0158] Calculate the ratio of the sum value corresponding to each first data point to the target mean to obtain the abnormal evaluation value of each first data point;

[0159] Second detection component:

[0160] Comparing the abnormality evaluation value of each first data point with a preset evaluation threshold, and taking the first data point whose abnormality evaluation value is greater than or equal to the preset evaluation threshold as an abnormal data point;

[0161] All first data points in the second data group are traversed to obtain a number of abnormal data points.

[0162] In this embodiment, assume that the abnormal data set is [10, 15, 20, 25, 30]. First, select 10 as the first data point, and calculate the difference between it and 15, 20, 25, and 30 as 5, 10, 15, and 20 respectively. The sum of these differences is 50. Then select 15 as the first data point, and calculate the difference between it and 20, 25, and 30 as 5, 10, and 15 respectively. The sum is 30, and so on. After traversing all the first data points, the sums are obtained, assuming they are 50, 30, 20, 10, and 15 respectively. The mean of these sums is calculated as (50+30+20+10+15) / 5=25. Then calculate the ratio of the sum of each first data point to the target mean. For example, the abnormal evaluation value corresponding to 50 is 50 / 25=2. If the preset evaluation threshold is 1.5, then the first data point corresponding to 50 (i.e., the value 10) is determined to be an abnormal data point. By traversing all the first data points in this way, several abnormal data points are finally determined.

[0163] The working principle of the above technical solution is: first, the second calculation component selects one from the abnormal data group as the second data group, obtains the data value of the data point therein, calculates the difference between it and the data value of other data points in the group for one data point (first data point) and sums it up to obtain the sum value of the data point, and obtains the corresponding sum value by traversing all the first data points. Then, the average of all the sum values ​​is calculated to obtain the target mean, and then the ratio of the sum value of each first data point to the target mean is calculated to obtain the abnormal evaluation value. Then, the second detection component compares the abnormal evaluation value of each first data point with the preset evaluation threshold, determines that the first data point with an abnormal evaluation value greater than or equal to the preset evaluation threshold is an abnormal data point, and finds all abnormal data points by traversing all the first data points. The whole process accurately determines the specific abnormal data point through further analysis and calculation of the data points in the abnormal data group.

[0164] The beneficial effects of the above technical solution are: through detailed analysis and calculation of data points within anomaly data groups, anomalous data points can be more accurately identified, improving the accuracy of anomaly detection; by considering the relationship between each data point and other data points, as well as factors such as the overall mean, the assessment of the degree of anomaly of the data point is more comprehensive and objective; this method can be applied to various types of data groups and scenarios, showing strong versatility and adaptability. By calculating the anomaly evaluation value and comparing it with a preset threshold, a clear quantitative standard is provided for judging anomalies, reducing the influence of subjective factors.

[0165] Example 7

[0166] The first risk assessment submodule is used to assess the risk of the tailings pond based on the real-time tailings pond monitoring data, the risk type of the tailings pond and a preset algorithm to obtain a second risk assessment value, including:

[0167] The default algorithm is:

[0168]

[0169] Where θ represents the second risk assessment value; σ t represents the preset weight value corresponding to the t-th risk type; e represents a natural constant; A t represents the total number of real-time tailings pond monitoring data obtained for the assessment of the t-th risk type; B t represents the number of abnormal data in the real-time tailings pond monitoring data obtained when evaluating the t-th risk type; C t represents the mean value of the real-time tailings dam monitoring data obtained when evaluating the t-th risk type; X represents the total number of risk types in the tailings dam risk assessment.

[0170] The beneficial effects of the above technical solution are: through a specific preset algorithm, different risk types and related monitoring data can be quantified and calculated to obtain a clear second risk assessment value, making the risk assessment more scientific and accurate; it comprehensively considers multiple factors such as the weight of the risk type, the total number of real-time monitoring data, the number of abnormal data, and the data mean, and comprehensively reflects the risk status of the tailings pond; the assessment value can be continuously updated according to real-time monitoring data to adapt to the dynamic changes in the risk status of the tailings pond; it provides reliable data support and basis for relevant decision-making, which helps to take more targeted risk prevention and control measures; the unified algorithm ensures the consistency and comparability of the assessment, which facilitates risk comparison and management between different tailings ponds.

[0171] Example 9

[0172] The method for constructing a collaborative disposal solution database includes:

[0173] Obtain historical data of tailings ponds;

[0174] Classifying the tailings pond historical data based on tailings pond disaster types to obtain a plurality of historical disaster type data sets; the historical disaster type data sets include tailings pond historical disaster data and historical collaborative disposal solution process data; the tailings pond historical disaster data and historical collaborative disposal solution process data have a one-to-one correspondence;

[0175] Take any historical disaster type data set as the target data set;

[0176] Performing feature extraction on each tailings pond historical disaster data in the target data set to obtain a first data feature corresponding to each tailings pond historical disaster data in the target data set;

[0177] Take any tailings pond historical disaster data as the target historical disaster data;

[0178] Obtain historical collaborative disposal plan process data corresponding to the target historical disaster data;

[0179] Verifying the historical collaborative disposal solution process data, and obtaining target collaborative disposal solution process data after passing the verification;

[0180] Get the preset blank database;

[0181] The first data feature corresponding to the historical disaster data of each tailings pond and the target collaborative disposal solution process data are associated and stored in the preset blank database to obtain a collaborative disposal solution database.

[0182] In this embodiment, the historical collaborative disposal plan process data is verified. The verification mainly checks whether there are sensitive operation features in the historical collaborative disposal plan process data, such as whether the specific operations in the collaborative disposal plan violate regulations. If violations occur, the number of specific illegal operations is counted to obtain the demand degree of each illegal operation. If the overall demand degree is greater than or equal to the preset demand degree threshold, it is equivalent to special handling of special matters, a special operation to resolve risks under special circumstances; if the demand degree is less than the preset demand degree threshold, it means that these sensitive operations can be avoided and can be deleted directly.

[0183] The beneficial effects of the above technical solution are: by classifying the historical data of tailings ponds according to disaster types, a special collaborative disposal solution database can be constructed for different types of disasters, thereby improving the pertinence and applicability of the solution; it covers a wealth of historical disaster data and corresponding collaborative disposal solution process data, providing sufficient reference for subsequent responses to various situations; extracting data features and storing them in association with collaborative disposal solutions, making it easy to quickly and accurately match appropriate disposal solutions based on disaster characteristics; and verifying historical collaborative disposal solution process data to ensure that the solutions stored in the database have certain reliability and effectiveness.

[0184] Example 10

[0185] The historical collaborative disposal solution process data is verified, and after verification, the target collaborative disposal solution process data is obtained, including:

[0186] Splitting the historical collaborative disposal solution process data to obtain a plurality of historical collaborative disposal solution process sub-data;

[0187] Performing feature extraction on a plurality of historical collaborative disposal solution process sub-data respectively to obtain a second data feature corresponding to each historical collaborative disposal solution process sub-data;

[0188] Matching the second data feature based on the sensitive features in the preset sensitive feature library; using the successfully matched second data feature as the initial pending feature to obtain a plurality of initial pending features; using the successfully matched sensitive feature as the target sensitive feature to obtain a plurality of target sensitive features;

[0189] Obtain verification information corresponding to each target sensitive feature; the verification information includes a demand value corresponding to each initially undetermined feature;

[0190] The sum of several demand values ​​is calculated to obtain the total demand of all the initial pending features in the historical collaborative disposal solution process sub-data;

[0191] Comparing the demand sum with a preset demand threshold;

[0192] If the total demand is greater than or equal to a preset demand threshold, the historical collaborative disposal solution process data is used as the target collaborative disposal solution process data;

[0193] If the total demand is less than a preset demand threshold, the historical collaborative disposal solution process data and the tailings pond historical disaster data corresponding to the historical collaborative disposal solution process data are deleted;

[0194] Traverse all historical collaborative processing solution process data to obtain several target collaborative processing solution process data.

[0195] The beneficial effects of the above technical solution are: by splitting process data and extracting features for sensitive feature matching, more detailed verification is achieved to ensure the reliability and security of the solution; matching based on a preset sensitive feature library can promptly discover features that may have problems and avoid potential risks; by calculating the total demand and comparing it with the threshold, the importance and applicability of the solution can be accurately judged to ensure that the retained solution has a high value; deleting solutions with insufficient demand and related disaster data helps maintain the high quality and effectiveness of the database.

[0196] Obviously, those skilled in the art may make various changes and modifications to the present invention without departing from the spirit and scope of the present invention. Thus, if such changes and modifications fall within the scope of the claims and their equivalents, the present invention is intended to include such changes and modifications.

Claims

1. A tailings pond risk warning and disposal full-process collaborative management platform, characterized by: include: The early warning module is used to assess the risk of the tailings pond based on the tailings pond monitoring data and determine whether to issue an early warning; A query module is used to query the collaborative disposal solution database based on the early warning prompt after the early warning module issues the early warning prompt, and determine the target collaborative disposal solution; The acquisition module is used to execute the target collaborative disposal plan and obtain collaborative disposal feedback data from relevant departments; A risk assessment module is used to assess the risk of the tailings pond based on the collaborative disposal feedback data of relevant departments to obtain a first risk assessment value; an early warning cancellation module, configured to compare the first risk assessment value with a preset risk assessment threshold, and send an early warning cancellation instruction to the early warning module when it is determined that the first risk assessment value is less than the preset risk assessment threshold; Early warning module, including: The first acquisition submodule is used to obtain real-time tailings pond monitoring data; A preprocessing submodule, configured to preprocess the real-time tailings pond monitoring data to obtain preprocessed real-time tailings pond monitoring data; The feature extraction submodule is used to extract features from the pre-processed real-time tailings pond monitoring data and determine the risk type of the tailings pond; A first risk assessment submodule is configured to assess the risk of the tailings pond based on the pre-processed real-time tailings pond monitoring data, the risk type of the tailings pond, and a preset algorithm to obtain a second risk assessment value; an early warning issuing submodule, configured to compare the second risk assessment value with a preset risk assessment threshold, and issue an early warning prompt when it is determined that the second risk assessment value is greater than or equal to the preset risk assessment threshold; the early warning prompt includes the risk type of the tailings pond; The first risk assessment submodule is used to assess the risk of the tailings pond based on the real-time tailings pond monitoring data, the risk type of the tailings pond and a preset algorithm to obtain a second risk assessment value, including: The default algorithm is: in, represents the second risk assessment value; represents the preset weight value corresponding to the t-th risk type; e represents a natural constant; represents the total number of real-time tailings pond monitoring data obtained for the assessment of the t-th risk type; represents the number of abnormal data in the real-time tailings pond monitoring data obtained when evaluating the t-th risk type; represents the mean value of the real-time tailings pond monitoring data obtained when evaluating the t-th risk type; Represents the total number of risk types in the tailings dam risk assessment.

2. The tailings pond risk warning and disposal full-process collaborative management platform according to claim 1, characterized in that: Preprocessing submodule, including: An outlier processing unit, configured to perform outlier processing on the real-time tailings pond monitoring data to obtain an outlier processing result; The confirmation unit is used to use the abnormal value processing result as pre-processed real-time tailings pond monitoring data.

3. The tailings pond risk warning and disposal full-process collaborative management platform according to claim 2, characterized in that: Outlier processing unit, including: a first detection subunit, configured to classify the real-time tailings pond monitoring data to obtain a plurality of real-time tailings pond monitoring sub-data groups; and perform anomaly detection on the plurality of real-time tailings pond monitoring sub-data groups to obtain a plurality of abnormal data groups; a second detection subunit, configured to perform abnormal data point detection on the plurality of abnormal data groups to obtain a plurality of abnormal data points; The outlier processing subunit is used to: Take any abnormal data point as the second data point; Determine the target area with the second data point as the center and the preset distance as the radius; Get the data value of each data point in the target area; The median of the data values ​​of each data point in the target area is used as the replacement value of the second data point; Traverse all abnormal data points and get the replacement value of each abnormal data point; The abnormal data values ​​are replaced based on the replacement values ​​of all abnormal data points to obtain the outlier processing results.

4. The tailings pond risk warning and disposal full-process collaborative management platform according to claim 3, characterized in that: The first detection subunit includes: A first computing component is configured to: Classifying the real-time tailings pond monitoring data to obtain a plurality of real-time tailings pond monitoring sub-data groups; Randomly select a real-time tailings pond monitoring sub-data group as the target data group; Sorting the data in the target data group based on the time series to obtain a sorted target data group; and evenly dividing the sorted target data group into a number of target sub-data groups; Randomly select a target sub-data group as the first data group; Calculating the mean of the data values ​​in the first data group to obtain a first mean; Calculating the mean of the data values ​​of the other target sub-data groups in the target data group except the first data group to obtain a second mean; Calculating the ratio of the first mean to the second mean to obtain a first ratio; The first detection component is used to: comparing the first ratio with a preset threshold, and when it is determined that the first ratio is greater than or equal to the preset threshold, treating the first data group as an abnormal data group; Traverse all target sub-data groups and obtain several abnormal data groups.

5. The tailings pond risk warning and disposal full-process collaborative management platform according to claim 4, characterized in that: The second detection subunit includes: The second computing component is configured to: Randomly select an abnormal data group as the second data group; Obtaining data values ​​corresponding to each data point in the second data group; Take any data point as the first data point; Calculating the difference between the first data point and the data values ​​of the other data points in the second data group except the first data point to obtain a plurality of difference values ​​corresponding to the first data point; Summing the plurality of differences to obtain a sum value of the first data point; Traversing all first data points in the second data group to obtain a sum value corresponding to each first data point; Calculate the mean of the sum values ​​corresponding to all first data points to obtain the target mean; Calculate the ratio of the sum value corresponding to each first data point to the target mean to obtain the abnormal evaluation value of each first data point; Second detection component: Comparing the abnormality evaluation value of each first data point with a preset evaluation threshold, and taking the first data point whose abnormality evaluation value is greater than or equal to the preset evaluation threshold as an abnormal data point; All first data points in the second data group are traversed to obtain a number of abnormal data points.

6. The tailings pond risk warning and disposal full-process collaborative management platform according to claim 1, characterized in that: Risk assessment module, including: The second acquisition submodule is used to query the target feedback data in the collaborative disposal feedback data of the relevant departments based on the risk type; the target feedback data is used as data for the risk assessment of the tailings pond; The calculation submodule is used to obtain a first risk assessment value based on the target feedback data and a preset algorithm.

7. The tailings dam risk warning and disposal full-process collaborative management platform according to claim 1, characterized in that: The method for constructing a collaborative disposal solution database includes: Obtain historical data of tailings ponds; Classifying the tailings pond historical data based on tailings pond disaster types to obtain a plurality of historical disaster type data sets; the historical disaster type data sets include tailings pond historical disaster data and historical collaborative disposal solution process data; the tailings pond historical disaster data and historical collaborative disposal solution process data have a one-to-one correspondence; Take any historical disaster type data set as the target data set; Performing feature extraction on each tailings pond historical disaster data in the target data set to obtain a first data feature corresponding to each tailings pond historical disaster data in the target data set; Take any tailings pond historical disaster data as the target historical disaster data; Obtain historical collaborative disposal plan process data corresponding to the target historical disaster data; Verifying the historical collaborative disposal solution process data, and obtaining target collaborative disposal solution process data after passing the verification; Get the preset blank database; The first data feature corresponding to the historical disaster data of each tailings pond and the target collaborative disposal solution process data are associated and stored in the preset blank database to obtain a collaborative disposal solution database.

8. The tailings pond risk warning and disposal full-process collaborative management platform according to claim 7, characterized in that: The historical collaborative disposal solution process data is verified, and after verification, the target collaborative disposal solution process data is obtained, including: Splitting the historical collaborative disposal solution process data to obtain a plurality of historical collaborative disposal solution process sub-data; Performing feature extraction on a plurality of historical collaborative disposal solution process sub-data respectively to obtain a second data feature corresponding to each historical collaborative disposal solution process sub-data; Matching the second data feature based on the sensitive features in the preset sensitive feature library; using the successfully matched second data feature as the initial pending feature to obtain a plurality of initial pending features; using the successfully matched sensitive feature as the target sensitive feature to obtain a plurality of target sensitive features; Obtain verification information corresponding to each target sensitive feature; the verification information includes the demand value corresponding to each initially undetermined feature; The sum of several demand values ​​is calculated to obtain the total demand of all the initial pending features in the historical collaborative disposal solution process sub-data; Comparing the demand sum with a preset demand threshold; If the total demand is greater than or equal to a preset demand threshold, the historical collaborative disposal solution process data is used as the target collaborative disposal solution process data; If the total demand is less than a preset demand threshold, the historical collaborative disposal solution process data and the tailings pond historical disaster data corresponding to the historical collaborative disposal solution process data are deleted; Traverse all historical collaborative processing solution process data to obtain several target collaborative processing solution process data.

Images