Tailing pond safety risk early symptom identification system and method based on data mining

Abstract

The invention discloses a tailing pond safety risk early symptom identification system based on data mining, and the system comprises an obtaining module which is used for obtaining tailing pond multi-source monitoring data in real time; the feature extraction module is used for performing feature extraction on the tailings pond multi-source monitoring data to obtain target features; the recognition module is used for recognizing the target features and a preset tailing pond safety risk early symptom database and determining a recognition result; the evaluation module is used for determining a target key index of a disaster type when determining that the identification result shows that the risk exists; determining a tailing pond safety risk assessment value based on the target key index of the disaster type and tailing pond multi-source monitoring data; the early warning module is used for comparing the safety risk assessment value of the tailings pond with a preset safety risk assessment threshold value, and when it is determined that the safety risk assessment value of the tailings pond is larger than or equal to the preset safety risk assessment threshold value, an early warning prompt is given out; risks are found earlier by comparing target features with a database.

Description

Technical Field

[0001] The present invention relates to the field of tailings pond safety risk identification, and in particular to a system and method for identifying early signs of tailings pond safety risks based on data mining. Background Art

[0002] Tailings ponds are important facilities for storing "residual" waste residues after concentrate screening. Long-term storage can easily become a dangerous source of man-made debris flows with high potential energy. Once a dam breach occurs, it will cause huge property losses and casualties. In order to protect the lives and property safety of downstream residents, the country continues to establish and improve the legal and regulatory standards system to strengthen the safe operation monitoring of tailings ponds. However, in recent years, various tailings pond accidents have still occurred in my country, causing huge losses to the downstream environment and the safety of people's lives and property.

[0003] At present, the following problems exist in the safety risk assessment of tailings dams: (1) The data source used for the safety risk assessment of tailings dams is relatively single, and it is impossible to judge the overall safety trend of the tailings dams, resulting in a relatively low assessment accuracy; (2) The current safety risk assessment of tailings dams is directly calculated and evaluated based on monitoring data, resulting in a relatively large calculation pressure and low assessment efficiency; (3) At present, when evaluating the safety risk of tailings dams, it is impossible to identify the early signs of safety risks of tailings dams. The risk level of the tailings dam can only be assessed based on indicators when the risk is about to occur, resulting in insufficient time for emergency risk avoidance when an accident occurs in the tailings dam, missing the best time for risk avoidance, and causing casualties and property losses.

[0004] Therefore, there is an urgent need for a system and method for identifying early signs of safety risks in tailings dams based on data mining to solve the above problems. Summary of the invention

[0005] The present invention aims to solve at least one of the technical problems in the above-mentioned technology to a certain extent. To this end, the first aspect of the present invention aims to propose a system for identifying early signs of safety risks in tailings dams based on data mining, which obtains multi-source monitoring data and extracts features, uses target features to compare with the database to achieve accurate identification of early signs, discovers potential risks earlier, and conducts assessments after identifying the existence of risks, making the assessment more targeted and improving the efficiency and reliability of the assessment.

[0006] The second aspect of the present invention aims to propose a method for identifying early signs of safety risks in tailings dams based on data mining.

[0007] To achieve the above-mentioned purpose, the first embodiment of the present invention proposes a system for identifying early signs of safety risks of tailings dams based on data mining, comprising:

[0008] Acquisition module, used to obtain multi-source monitoring data of tailings pond in real time;

[0009] A feature extraction module is used to extract features from the multi-source monitoring data of the tailings pond to obtain target features;

[0010] An identification module is used to identify the target features with a preset tailings pond safety risk early warning sign database to determine the identification results;

[0011] An evaluation module, for determining target key indicators of the disaster type when it is determined that the identification result shows that there is a risk; and determining a safety risk assessment value of the tailings pond based on the target key indicators of the disaster type and multi-source monitoring data of the tailings pond;

[0012] The early warning module is used to compare the safety risk assessment value of the tailings pond with a preset safety risk assessment threshold, and issue an early warning prompt when it is determined that the safety risk assessment value of the tailings pond is greater than or equal to the preset safety risk assessment threshold.

[0013] Preferably, the acquisition module includes:

[0014] A first acquisition submodule is used to acquire a satellite remote sensing image of the tailings pond area to obtain first data;

[0015] The second acquisition submodule is used to acquire the meteorological data of the tailings pond area to obtain the second data;

[0016] The third acquisition submodule is used to acquire geological disaster data of the tailings pond area to obtain third data;

[0017] A fourth acquisition submodule, used for acquiring tailings pond sensor data based on the sensor device to obtain fourth data;

[0018] A fifth acquisition submodule, used for acquiring the video monitoring data of the tailings pond based on the monitoring device to obtain fifth data;

[0019] The first determination submodule is used to use the first data, the second data, the third data, the fourth data and the fifth data as multi-source monitoring data of the tailings pond.

[0020] Preferably, it also includes a preprocessing module, which is used to preprocess the tailings pond multi-source monitoring data to obtain preprocessed tailings pond multi-source monitoring data;

[0021] The preprocessing module comprises:

[0022] The data cleaning submodule is used to clean the multi-source monitoring data of the tailings pond to obtain the cleaned multi-source monitoring data of the tailings pond;

[0023] The second determination submodule is used to use the cleaned tailings pond multi-source monitoring data as pre-processed tailings pond multi-source monitoring data.

[0024] Preferably, the data cleaning submodule includes:

[0025] Abnormal evaluation unit, used to:

[0026] Read multi-source monitoring data of tailings pond and determine the data to be cleaned;

[0027] Input the data to be cleaned into the pre-trained classification model for classification, and obtain a set of data to be cleaned in several categories;

[0028] Take any data set to be cleaned;

[0029] Calculating anomaly evaluation values ​​of the data set to be cleaned;

[0030] Comparing the abnormal evaluation value with a preset abnormal evaluation threshold;

[0031] When it is determined that the abnormality evaluation value is greater than or equal to the preset abnormality evaluation threshold, the set of data to be cleaned is used as the target set of data to be cleaned;

[0032] A screening unit is used to evenly divide the data in the target to-be-cleaned data set into a plurality of target to-be-cleaned sub-data, and determine whether each target to-be-cleaned sub-data is an abnormal sub-data; when it is determined that the target to-be-cleaned sub-data is an abnormal sub-data, calculate the deviation coefficient corresponding to the abnormal sub-data;

[0033] Data cleaning unit, used for:

[0034] Comparing the deviation coefficient corresponding to the abnormal sub-data with a preset deviation coefficient threshold;

[0035] If the deviation coefficient corresponding to the abnormal sub-data is greater than or equal to a preset deviation coefficient threshold, the abnormal sub-data is deleted;

[0036] If the deviation coefficient corresponding to the abnormal sub-data is less than the preset deviation coefficient threshold, obtaining a preset data cleaning rule; and performing data cleaning on the abnormal sub-data based on the preset data cleaning rule;

[0037] Traverse all the data sets to be cleaned to obtain the multi-source monitoring data of the tailings pond after cleaning.

[0038] Preferably, the screening unit comprises:

[0039] A segmentation subunit is used to evenly divide the data in the target to-be-cleaned data set into a plurality of target to-be-cleaned sub-data;

[0040] The first calculation subunit is used to calculate the data value variance in each target sub-data to be cleaned, and obtain the variance value corresponding to each target sub-data to be cleaned;

[0041] A screening subunit, used for comparing the variance value with a preset variance threshold;

[0042] When it is determined that the variance value is greater than or equal to a preset variance threshold, the target to-be-cleaned sub-data corresponding to the variance value is taken as abnormal sub-data;

[0043] Traverse all the target sub-data to be cleaned and obtain several abnormal sub-data;

[0044] The second calculation subunit is used to calculate the deviation coefficient corresponding to each abnormal sub-data.

[0045] Preferably, the identification module comprises:

[0046] A mapping submodule, used to map the target feature to a preset space to obtain a target feature vector corresponding to the target feature;

[0047] A similarity calculation submodule, used for calculating the similarity between the target feature vector corresponding to the target feature and the feature vector in the preset tailings pond safety risk early sign database;

[0048] The recognition result determination submodule is used to use the similarity calculation result as the recognition result.

[0049] Preferably, the assessment module includes:

[0050] A risk determination submodule, used to compare the recognition result with a preset similarity threshold, and when it is determined that the recognition result is greater than or equal to the preset similarity threshold, determine that there is a risk in the tailings pond;

[0051] Filter submodule, used to:

[0052] When determining that there is a risk in the tailings pond, obtaining historical disaster information of the tailings pond; the historical disaster information of the tailings pond includes indicator information corresponding to different disaster types of the tailings pond and the frequency of abnormal occurrence of various indicators;

[0053] Construct a disaster indicator correlation coefficient matrix based on the indicator information corresponding to different disaster types of tailings ponds;

[0054] Based on the frequency of abnormal occurrence of various indicators and the disaster indicator correlation coefficient matrix, the correlation degree of each indicator is determined, and the correlation degrees corresponding to several indicators are obtained;

[0055] Comparing the correlations corresponding to the plurality of indicators with a preset correlation threshold;

[0056] The corresponding indicator when the correlation degree is greater than or equal to the preset correlation degree threshold is used as the target key indicator of the disaster type:

[0057] The sixth acquisition submodule is used to obtain data values ​​corresponding to target key indicators in the tailings pond multi-source monitoring data;

[0058] The calculation submodule is used to determine the safety risk assessment value of the tailings pond based on the data values ​​corresponding to the target key indicators in the multi-source monitoring data of the tailings pond and a preset algorithm.

[0059] Preferably, the calculation submodule is used to determine the safety risk assessment value of the tailings pond based on the data values ​​corresponding to the target key indicators in the multi-source monitoring data of the tailings pond and a preset algorithm, including:

[0060]

[0061] Where P represents the safety risk assessment value of the tailings dam; χ represents the average risk value of the safety risk assessment value of the tailings dam; Λ i，j represents the risk value corresponding to the jth target key indicator in the i-th disaster type; m represents the total number of disaster types; n represents the total number of target key indicators; f(x)dx represents the probability density function of the risk of occurrence of the i-th disaster type.

[0062] Preferably, the early warning module includes:

[0063] A comparison submodule, used to compare the tailings pond safety risk assessment value with a preset safety risk assessment threshold;

[0064] A warning information generation submodule, used to generate warning information when it is determined that the safety risk assessment value of the tailings pond is greater than or equal to a preset safety risk assessment threshold;

[0065] The query submodule is used to query the current duty information table and determine the current shift manager information;

[0066] The warning sending submodule is used to send the warning information to the current shift manager to make a warning prompt.

[0067] To achieve the above-mentioned purpose, the second embodiment of the present invention proposes a method for identifying early signs of safety risks of tailings dams based on data mining, comprising:

[0068] Obtain multi-source monitoring data of tailings ponds in real time;

[0069] Extracting multi-source monitoring data of the tailings pond to obtain target features;

[0070] Identify the target features with the preset tailings dam safety risk early warning sign database to determine the identification results;

[0071] When it is determined that the identification results show that there is a risk, determine the target key indicators of the disaster type; determine the safety risk assessment value of the tailings pond based on the target key indicators of the disaster type and the multi-source monitoring data of the tailings pond;

[0072] The tailings pond safety risk assessment value is compared with a preset safety risk assessment threshold, and when it is determined that the tailings pond safety risk assessment value is greater than or equal to the preset safety risk assessment threshold, an early warning prompt is issued.

[0073] The present invention proposes a system and method for identifying early signs of safety risks in tailings ponds based on data mining. By acquiring multi-source monitoring data and performing feature extraction, the status of the tailings pond can be understood more comprehensively and deeply, and the accuracy of risk identification can be improved. The early signs can be accurately identified by comparing the features with the database, and potential risks can be discovered earlier. After the risk is identified, an assessment is performed to make the assessment more targeted and improve the efficiency and reliability of the assessment. An early warning is issued in time according to the comparison between the assessment value and the threshold value, so as to gain time for taking countermeasures and reduce the risk hazards. This helps to improve the overall safety protection level of the tailings pond and reduce the possibility of accidents.

[0074] Other features and advantages of the present invention will be described in the following description, and partly become apparent from the description, or 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.

[0075] The technical solution of the present invention is further described in detail below through the accompanying drawings and embodiments. BRIEF DESCRIPTION OF THE DRAWINGS

[0076] 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:

[0077] Figure 1 It is a block diagram of a system for identifying early signs of safety risks of tailings dams based on data mining according to an embodiment of the present invention;

[0078] Figure 2 is a block diagram of an acquisition module according to an embodiment of the present invention;

[0079] Figure 3 The present invention is a flowchart of a method for identifying early signs of safety risks in tailings dams based on data mining according to an embodiment of the present invention. DETAILED DESCRIPTION

[0080] The preferred embodiments of the present invention are described below in conjunction with 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.

[0081] Example 1

[0082] like Figure 1As shown, a system for identifying early signs of safety risks of tailings dams based on data mining includes:

[0083] Acquisition module, used to obtain multi-source monitoring data of tailings pond in real time;

[0084] A feature extraction module is used to extract features from the multi-source monitoring data of the tailings pond to obtain target features;

[0085] An identification module is used to identify the target features with a preset tailings pond safety risk early warning sign database to determine the identification results;

[0086] An evaluation module, for determining target key indicators of the disaster type when it is determined that the identification result shows that there is a risk; and determining a safety risk assessment value of the tailings pond based on the target key indicators of the disaster type and multi-source monitoring data of the tailings pond;

[0087] The early warning module is used to compare the safety risk assessment value of the tailings pond with a preset safety risk assessment threshold, and issue an early warning prompt when it is determined that the safety risk assessment value of the tailings pond is greater than or equal to the preset safety risk assessment threshold.

[0088] In this embodiment, the tailings pond multi-source monitoring data includes but is not limited to satellite remote sensing image data, meteorological data, geological disaster data, tailings pond sensor data and video surveillance data.

[0089] In this embodiment, a feature extraction model is used to extract features from the multi-source monitoring data of the tailings pond; the feature extraction model includes a convolutional neural network model, etc.

[0090] In this embodiment, the preset tailings dam safety risk early sign database is a tailings dam safety risk early sign database established based on feature analysis of historical disaster data of tailings dams.

[0091] In this embodiment, the recognition result is the calculated value of the similarity between the feature vector of the target feature and the feature vector in the preset tailings dam safety risk early sign database.

[0092] In this embodiment, the preset security risk assessment threshold is set in advance based on industry experience.

[0093] The beneficial effects of the above technical scheme are: by acquiring multi-source monitoring data and performing feature extraction, a more comprehensive and in-depth understanding of the status of the tailings pond can be obtained, thereby improving the accuracy of risk identification; the use of features and database comparison can be used to achieve accurate identification of early signs and discover potential risks earlier; an assessment is conducted after the risk is identified, making the assessment more targeted and improving the efficiency and reliability of the assessment; an early warning is issued in a timely manner based on the comparison of the assessment value with the threshold, thereby gaining time for taking countermeasures and reducing risk hazards; it helps to improve the overall safety level of the tailings pond and reduce the possibility of accidents.

[0094] Example 2

[0095] like Figure 2 Shown: Get module, including:

[0096] A first acquisition submodule is used to acquire a satellite remote sensing image of the tailings pond area to obtain first data;

[0097] The second acquisition submodule is used to acquire the meteorological data of the tailings pond area to obtain the second data;

[0098] The third acquisition submodule is used to acquire geological disaster data of the tailings pond area to obtain third data;

[0099] A fourth acquisition submodule, used for acquiring tailings pond sensor data based on the sensor device to obtain fourth data;

[0100] A fifth acquisition submodule, used for acquiring the video monitoring data of the tailings pond based on the monitoring device to obtain fifth data;

[0101] The first determination submodule is used to use the first data, the second data, the third data, the fourth data and the fifth data as multi-source monitoring data of the tailings pond.

[0102] In this embodiment, the second data includes actual meteorological data, meteorological forecast data, meteorological statistical data and meteorological warning data.

[0103] In this embodiment, the third data includes access to geological disaster risk type data, geological disaster monitoring and early warning data, and geological disaster early warning feedback monthly report data.

[0104] In this embodiment, the fourth data includes displacement data, infiltration line data, reservoir water level data, and seepage water volume data. Suitable displacement sensors, such as total stations, GPS displacement monitors, etc., are installed at key locations of the tailings reservoir, and measurements and data collection are performed regularly. The displacement change data is obtained in real time by connecting the sensors to the data collection system; infiltration line monitoring sensors, such as pressure measuring tubes, etc., are buried; the sensors monitor water pressure changes in real time, and the position data of the infiltration line is obtained by conversion; water level sensors, such as immersion water level gauges, are installed at appropriate locations in the reservoir; the sensors continuously monitor the water level height and transmit data; the seepage water volume can be indirectly calculated by setting flow sensors in relevant areas or combining other measurement methods, and the collected data is analyzed and processed to obtain accurate seepage water volume information.

[0105] In this embodiment, the fifth data includes monitoring data of the overflow well location, monitoring data of the beach top ore release location, monitoring data of the tail pipe, monitoring data of the downstream slope of the dam body, monitoring data of the inlet and outlet of the flood discharge facilities, monitoring data of the reservoir water level gauge and monitoring data of the dry beach benchmark.

[0106] The beneficial effects of the above technical scheme are: different types of data are obtained through multiple channels, including satellite remote sensing images, meteorological data, geological disaster data, sensor data and video monitoring data, which can comprehensively reflect the various conditions of the tailings pond; it covers multiple dimensions such as space, meteorology, geology, etc., making the monitoring of the tailings pond more three-dimensional and in-depth; real-time data is obtained by using sensor equipment and monitoring equipment to ensure the timeliness and accuracy of the data, which helps to discover problems in a timely manner; multi-source data are integrated together to facilitate comprehensive analysis and evaluation, and to better understand the overall status and potential risks of the tailings pond; the integration of multiple data can improve the early warning capabilities of potential dangers and abnormal situations, and buy time for taking corresponding measures.

[0107] Example 3

[0108] It also includes a preprocessing module, which is used to preprocess the tailings pond multi-source monitoring data to obtain preprocessed tailings pond multi-source monitoring data;

[0109] The preprocessing module comprises:

[0110] The data cleaning submodule is used to clean the multi-source monitoring data of the tailings pond to obtain the cleaned multi-source monitoring data of the tailings pond;

[0111] The second determination submodule is used to use the cleaned tailings pond multi-source monitoring data as pre-processed tailings pond multi-source monitoring data.

[0112] The beneficial effects of the above technical solution are: through the data cleaning sub-module, noise, errors and outliers in the data can be removed, thereby improving the accuracy and reliability of the data; ensuring that the pre-processed multi-source monitoring data of the tailings pond is purer and more effective, providing a more valuable basis for subsequent analysis and decision-making; clean data is conducive to subsequent accurate analysis and modeling, avoiding erroneous conclusions or decisions due to data problems; high-quality data input helps the entire monitoring system to operate stably and reduce failures or anomalies caused by data problems.

[0113] Example 4

[0114] Data cleaning submodule, including:

[0115] Abnormal evaluation unit, used to:

[0116] Read multi-source monitoring data of tailings pond and determine the data to be cleaned;

[0117] Input the data to be cleaned into the pre-trained classification model for classification, and obtain a set of data to be cleaned in several categories;

[0118] Take any data set to be cleaned;

[0119] Calculating anomaly evaluation values ​​of the data set to be cleaned;

[0120] Comparing the abnormal evaluation value with a preset abnormal evaluation threshold;

[0121] When it is determined that the abnormality evaluation value is greater than or equal to the preset abnormality evaluation threshold, the set of data to be cleaned is used as the target set of data to be cleaned;

[0122] A screening unit is used to evenly divide the data in the target to-be-cleaned data set into a plurality of target to-be-cleaned sub-data, and determine whether each target to-be-cleaned sub-data is an abnormal sub-data; when it is determined that the target to-be-cleaned sub-data is an abnormal sub-data, calculate the deviation coefficient corresponding to the abnormal sub-data;

[0123] Data cleaning unit, used for:

[0124] Comparing the deviation coefficient corresponding to the abnormal sub-data with a preset deviation coefficient threshold;

[0125] If the deviation coefficient corresponding to the abnormal sub-data is greater than or equal to a preset deviation coefficient threshold, the abnormal sub-data is deleted;

[0126] If the deviation coefficient corresponding to the abnormal sub-data is less than the preset deviation coefficient threshold, obtaining a preset data cleaning rule; and performing data cleaning on the abnormal sub-data based on the preset data cleaning rule;

[0127] Traverse all the data sets to be cleaned to obtain the multi-source monitoring data of the tailings pond after cleaning.

[0128] In this embodiment, the abnormal evaluation value of the data set to be cleaned is calculated:

[0129]

[0130] Among them, A represents the abnormal evaluation value of the data set to be cleaned; δ represents the error factor; ρ represents the range of the data in the data set to be cleaned; σ represents the variance of the data in the data set to be cleaned; θ represents the standard deviation of the data in the data set to be cleaned; e represents the natural constant; B represents the mean of the data in the data set to be cleaned.

[0131] In this embodiment, the classification model includes but is not limited to a decision tree classification model, a naive Bayes classification model, a support vector machine classification model, a neural network classification model, and the like.

[0132] In this embodiment, the preset deviation coefficient threshold is used to measure the degree of deviation of the data and is determined based on historical data analysis.

[0133] In this embodiment, the preset data cleaning rules include removing duplicate data, processing missing values, correcting data format, removing outliers, consistency checking, cleaning invalid characters, etc.

[0134] The working principle of the above technical solution is: classify the data to be cleaned to obtain several categories of data sets to be cleaned; first evaluate the entire data set to be cleaned to determine whether the data anomaly in the data set to be cleaned exceeds the preset anomaly evaluation threshold, and if it exceeds the preset anomaly evaluation threshold, the data set to be cleaned is used as the target data set to be cleaned; perform a second screening on the target data set to be cleaned, divide the data in the target data set to be cleaned into several target sub-data to be cleaned on average, and determine whether each target sub-data to be cleaned is an abnormal sub-data; perform a third screening on the abnormal sub-data, screen based on the deviation coefficient, and when it is determined that the target sub-data to be cleaned is an abnormal sub-data, calculate the deviation coefficient corresponding to the abnormal sub-data; if the deviation coefficient corresponding to the abnormal sub-data is greater than or equal to the preset deviation coefficient threshold, delete the abnormal sub-data; if the deviation coefficient corresponding to the abnormal sub-data is less than the preset deviation coefficient threshold, obtain the preset data cleaning rule; perform data cleaning on the abnormal sub-data based on the preset data cleaning rule; by screening the data set to be cleaned three times, determining the abnormal sub-data, and performing data cleaning on the abnormal sub-data, the cleaning efficiency and accuracy are improved.

[0135] The beneficial effects of the above technical solution are: the abnormal evaluation unit can accurately identify data sets that may have abnormalities, thereby improving the pertinence and efficiency of data screening; the screening unit further subdivides the data and judges the abnormal sub-data, and calculates the deviation coefficient at the same time, which helps to more accurately evaluate the degree of abnormality of the data; different processing methods are adopted according to different deviation coefficients, that is, data with serious abnormalities are directly deleted, and data with relatively minor abnormalities are cleaned according to rules, thereby ensuring the rationality and scientificity of data processing; finally, the cleaned multi-source monitoring data of the tailings pond can be obtained, which effectively improves the quality and accuracy of the data and provides a more reliable basis for subsequent analysis and decision-making.

[0136] Example 5

[0137] Screening unit, including:

[0138] A segmentation subunit is used to evenly divide the data in the target to-be-cleaned data set into a plurality of target to-be-cleaned sub-data;

[0139] The first calculation subunit is used to calculate the data value variance in each target sub-data to be cleaned, and obtain the variance value corresponding to each target sub-data to be cleaned;

[0140] A screening subunit, used for comparing the variance value with a preset variance threshold;

[0141] When it is determined that the variance value is greater than or equal to a preset variance threshold, the target to-be-cleaned sub-data corresponding to the variance value is taken as abnormal sub-data;

[0142] Traverse all the target sub-data to be cleaned and obtain several abnormal sub-data;

[0143] The second calculation subunit is used to calculate the deviation coefficient corresponding to each abnormal sub-data.

[0144] In this embodiment, the preset variance threshold is used to measure the fluctuation of data and is set in advance based on industry experience.

[0145] In this embodiment, the deviation coefficient includes:

[0146]

[0147] Where Q represents the deviation coefficient corresponding to the abnormal sub-data; x p Represents the data value of the pth data in the abnormal sub-data; represents the mean value of the data in the abnormal sub-data; c represents the standard deviation of the abnormal sub-data; s represents the total number of data in the abnormal sub-data.

[0148] The beneficial effects of the above technical solution are: the data is subdivided by the segmentation subunits, which facilitates a more accurate analysis of the data characteristics of each small part; the first calculation subunit calculates the variance, which can effectively reflect the discreteness of the data, thereby accurately identifying the sub-data with a higher possibility of abnormality; the screening subunit makes judgments based on the variance threshold, which improves the accuracy and reliability of screening abnormal sub-data; traverses all target sub-data to be cleaned to ensure that there are no omissions, and can comprehensively find potential abnormal situations; the second calculation subunit calculates the deviation coefficient, which provides a quantitative basis for further processing of abnormal sub-data, making subsequent processing decisions more scientific and reasonable.

[0149] Example 6

[0150] Identification module, including:

[0151] A mapping submodule, used to map the target feature to a preset space to obtain a target feature vector corresponding to the target feature;

[0152] A similarity calculation submodule, used for calculating the similarity between the target feature vector corresponding to the target feature and the feature vector in the preset tailings pond safety risk early sign database;

[0153] The recognition result determination submodule is used to use the similarity calculation result as the recognition result.

[0154] In this embodiment, the similarity calculation method includes but is not limited to Euclidean distance and cosine similarity algorithm.

[0155] In this embodiment, the target feature is mapped to a preset space to obtain a specific implementation method of a target feature vector corresponding to the target feature: first, the dimension and feature representation of the preset space are determined. This can be a multidimensional vector space. Then, through a certain mapping algorithm or function, the value of the target feature is converted and processed so that it corresponds to the dimension of the preset space. For example, linear transformation, nonlinear transformation and other methods can be used to calculate and combine the various attribute values ​​of the target feature to obtain the coordinate value in the preset space, thereby forming a target feature vector.

[0156] In this embodiment, the target feature vector corresponding to the target feature is calculated for similarity with the feature vector in the preset tailings dam safety risk early sign database: the target feature vector and the feature vector in the database are standardized or normalized to eliminate the influence of factors such as dimension; common methods such as cosine similarity, Euclidean distance, Pearson correlation coefficient, etc. can be used; the target feature vector and each feature vector in the database are calculated one by one, and the corresponding similarity value is obtained according to the selected similarity measurement method; the calculated similarity values ​​are compared and sorted to determine those feature vectors that are most similar to the target feature vector; a suitable similarity threshold is set according to actual needs, and when the similarity reaches or exceeds the threshold, it can be considered that there is a certain degree of similarity; according to the results of the similarity calculation and threshold judgment, relevant information is output, such as similar feature vectors and their corresponding similarity values.

[0157] The beneficial effects of the above technical solution are: the mapping submodule converts the target features into feature vectors, which is convenient for digital processing and comparison, and improves the efficiency of data processing; the similarity calculation submodule can accurately determine the similarity between the target features and the early signs of known safety risks by comparing with the feature vectors in the preset database; the recognition result determination submodule can quickly obtain the recognition results, which is helpful to timely discover the possible safety risks of the tailings pond and achieve early warning; with the help of feature vectors and similarity calculation, the accuracy and reliability of recognition are improved.

[0158] Example 7

[0159] Assessment modules include:

[0160] A risk determination submodule, used to compare the recognition result with a preset similarity threshold, and when it is determined that the recognition result is greater than or equal to the preset similarity threshold, determine that there is a risk in the tailings pond;

[0161] Filter submodule, used to:

[0162] When determining that there is a risk in the tailings pond, obtaining historical disaster information of the tailings pond; the historical disaster information of the tailings pond includes indicator information corresponding to different disaster types of the tailings pond and the frequency of abnormal occurrence of various indicators;

[0163] Construct a disaster indicator correlation coefficient matrix based on the indicator information corresponding to different disaster types of tailings ponds;

[0164] Based on the frequency of abnormal occurrence of various indicators and the disaster indicator correlation coefficient matrix, the correlation degree of each indicator is determined, and the correlation degrees corresponding to several indicators are obtained;

[0165] Comparing the correlations corresponding to the plurality of indicators with a preset correlation threshold;

[0166] The corresponding indicator when the correlation degree is greater than or equal to the preset correlation degree threshold is used as the target key indicator of the disaster type;

[0167] The sixth acquisition submodule is used to obtain data values ​​corresponding to target key indicators in the tailings pond multi-source monitoring data;

[0168] The calculation submodule is used to determine the safety risk assessment value of the tailings pond based on the data values ​​corresponding to the target key indicators in the multi-source monitoring data of the tailings pond and a preset algorithm.

[0169] In this embodiment, when there is a risk in the tailings pond, there may be one or more corresponding disaster types, so the target key indicators of the disaster type should be determined based on historical data.

[0170] In this embodiment, a disaster indicator correlation coefficient matrix is ​​constructed based on the indicator information corresponding to different disaster types of the tailings pond, including:

[0171] The disaster indicator correlation coefficient matrix is:

[0172]

[0173] Among them, G represents the disaster index correlation coefficient matrix; α mn Represents the correlation between the mth disaster type and the nth indicator, and when there is a correlation between the mth disaster type and the nth indicator, α mn =1; when there is no correlation between the mth disaster type and the nth indicator, α mn =0.

[0174] In this embodiment, the correlation degree of each indicator is determined based on the frequency of abnormal occurrence of various indicators and the disaster indicator correlation coefficient matrix, including:

[0175]

[0176] Where W represents the correlation matrix of the indicators; W = [W1, W2…, W n ],W1,W2…,W n are the correlations of each indicator respectively; F represents the frequency matrix of abnormality of various indicators, F = [F1, F2…, F n ],F1,F2…,F n Indicates the frequency of abnormality of each indicator.

[0177] In this embodiment, the preset correlation threshold is set in advance based on industry experience.

[0178] The beneficial effects of the above technical scheme are: the risk determination submodule accurately judges whether there is a risk in the tailings pond based on the identification results and thresholds, thereby improving the objectivity and accuracy of risk judgment; the screening submodule can deeply analyze the key indicators related to disasters by obtaining historical disaster information and constructing a correlation coefficient matrix, making the assessment more targeted; determining the target key indicators helps to focus on the key points and conduct subsequent assessments and monitoring more efficiently; the calculation submodule combines multi-source monitoring data and preset algorithms to determine the safety risk assessment value, making the assessment results more scientific and reliable; overall, it is conducive to comprehensive control of the safety risks of the tailings pond, timely discovery of potential risks and early warning, and ensuring the safe operation of the tailings pond.

[0179] Example 8

[0180] The calculation submodule is used to determine the safety risk assessment value of the tailings pond based on the data values ​​corresponding to the target key indicators in the multi-source monitoring data of the tailings pond and the preset algorithm, including:

[0181]

[0182] Where P represents the safety risk assessment value of the tailings dam; χ represents the average risk value of the safety risk assessment value of the tailings dam; Λ i，j represents the risk value corresponding to the jth target key indicator in the ith disaster type; m represents the total number of disaster types; n represents the total number of target key indicators; f(x)dx represents the probability density function of the risk of occurrence of the ith disaster type; t represents the unit time.

[0183] The beneficial effects of the above technical scheme are: through specific formula calculation, the safety risk assessment value of the tailings pond can be accurately quantified, making the assessment result more objective and comparable; the formula comprehensively considers multiple factors such as the average risk value, the risk values ​​of different disaster types and target key indicators, the number of disaster types, the number of target key indicators and the probability density function of risk occurrence, and comprehensively reflects the risk status of the tailings pond; it provides a scientific decision-making basis for relevant departments and personnel, and helps to formulate more reasonable risk response strategies and measures; the assessment value can be dynamically adjusted according to real-time monitoring data and changes, and changes in the safety status of the tailings pond can be reflected in a timely manner.

[0184] Example 9

[0185] Early warning module, including:

[0186] A comparison submodule, used to compare the tailings pond safety risk assessment value with a preset safety risk assessment threshold;

[0187] A warning information generation submodule, used to generate warning information when it is determined that the safety risk assessment value of the tailings pond is greater than or equal to a preset safety risk assessment threshold;

[0188] The query submodule is used to query the current duty information table and determine the current shift manager information;

[0189] The warning sending submodule is used to send the warning information to the current shift manager to make a warning prompt.

[0190] The beneficial effects of the above technical scheme are: it can timely discover situations where the safety risk of the tailings pond exceeds the threshold, and quickly generate early warning information, thereby improving the timeliness of response; determine the management personnel information by querying the duty information table, and ensure that the early warning information is accurately sent to the relevant responsible persons to avoid information confusion and omissions; clarify the responsibilities of the current shift managers, which helps them to take timely response measures and strengthen the management and supervision of the tailings pond; help to prevent possible risks in advance, ensure the safety of the tailings pond and the surrounding environment, and reduce the probability of potential hazards.

[0191] To achieve the above purpose, if Figure 3 As shown, the second embodiment of the present invention proposes a method for identifying early signs of safety risks of tailings dams based on data mining, including steps S1-S5:

[0192] S1: Real-time acquisition of multi-source monitoring data of tailings ponds;

[0193] S2: extracting the multi-source monitoring data of the tailings pond to obtain target features;

[0194] S3: Identify the target features with the preset tailings dam safety risk early sign database to determine the identification results;

[0195] S4: When it is determined that the identification result shows that there is a risk, determine the target key indicators of the disaster type; based on the target key indicators of the disaster type and the multi-source monitoring data of the tailings pond, determine the safety risk assessment value of the tailings pond;

[0196] S5: Compare the tailings pond safety risk assessment value with a preset safety risk assessment threshold, and issue a warning prompt when it is determined that the tailings pond safety risk assessment value is greater than or equal to the preset safety risk assessment threshold.

[0197] The beneficial effects of the above technical scheme are: by acquiring multi-source monitoring data and performing feature extraction, a more comprehensive and in-depth understanding of the status of the tailings pond can be obtained, thereby improving the accuracy of risk identification; the use of features and database comparison can be used to achieve accurate identification of early signs and discover potential risks earlier; an assessment is conducted after the risk is identified, making the assessment more targeted and improving the efficiency and reliability of the assessment; an early warning is issued in a timely manner based on the comparison of the assessment value with the threshold, thereby gaining time for taking countermeasures and reducing risk hazards; it helps to improve the overall safety level of the tailings pond and reduce the possibility of accidents.

[0198] Obviously, those skilled in the art can make various changes and modifications to the present invention without departing from the spirit and scope of the present invention. Thus, if these modifications and variations of the present invention fall within the scope of the claims of the present invention and their equivalents, the present invention is also intended to include these modifications and variations.

Claims

1. A system for identifying early signs of safety risks in tailings dams based on data mining, characterized in that: include: Acquisition module, used to obtain multi-source monitoring data of tailings pond in real time; A feature extraction module is used to extract features from the multi-source monitoring data of the tailings pond to obtain target features; An identification module is used to identify the target features with a preset tailings pond safety risk early warning sign database to determine the identification results; An evaluation module for determining target key indicators of the disaster type when it is determined that the identification results indicate the existence of a risk; Determine the safety risk assessment value of the tailings pond based on the target key indicators of the disaster type and the multi-source monitoring data of the tailings pond; The early warning module is used to compare the safety risk assessment value of the tailings pond with a preset safety risk assessment threshold, and issue an early warning prompt when it is determined that the safety risk assessment value of the tailings pond is greater than or equal to the preset safety risk assessment threshold.

2. The tailings dam safety risk early sign identification system based on data mining as claimed in claim 1, characterized in that: Get modules, including: A first acquisition submodule is used to acquire a satellite remote sensing image of the tailings pond area to obtain first data; The second acquisition submodule is used to acquire the meteorological data of the tailings pond area to obtain the second data; The third acquisition submodule is used to acquire geological disaster data of the tailings pond area to obtain third data; A fourth acquisition submodule, used for acquiring tailings pond sensor data based on the sensor device to obtain fourth data; A fifth acquisition submodule, used for acquiring the video monitoring data of the tailings pond based on the monitoring device to obtain fifth data; The first determination submodule is used to use the first data, the second data, the third data, the fourth data and the fifth data as multi-source monitoring data of the tailings pond.

3. The tailings dam safety risk early sign identification system based on data mining as claimed in claim 1, characterized in that: It also includes a preprocessing module, which is used to preprocess the tailings pond multi-source monitoring data to obtain preprocessed tailings pond multi-source monitoring data; The preprocessing module comprises: The data cleaning submodule is used to clean the multi-source monitoring data of the tailings pond to obtain the cleaned multi-source monitoring data of the tailings pond; The second determination submodule is used to use the cleaned tailings pond multi-source monitoring data as pre-processed tailings pond multi-source monitoring data.

4. The tailings dam safety risk early sign identification system based on data mining as claimed in claim 3 is characterized in that: Data cleaning submodule, including: Abnormal evaluation unit, used to: Read multi-source monitoring data of tailings pond and determine the data to be cleaned; Input the data to be cleaned into the pre-trained classification model for classification, and obtain a set of data to be cleaned in several categories; Take any data set to be cleaned; Calculating anomaly evaluation values ​​of the data set to be cleaned; Comparing the abnormal evaluation value with a preset abnormal evaluation threshold; When it is determined that the abnormality evaluation value is greater than or equal to the preset abnormality evaluation threshold, the set of data to be cleaned is used as the target set of data to be cleaned; A screening unit is used to evenly divide the data in the target to-be-cleaned data set into a plurality of target to-be-cleaned sub-data, and determine whether each target to-be-cleaned sub-data is an abnormal sub-data; when it is determined that the target to-be-cleaned sub-data is an abnormal sub-data, calculate the deviation coefficient corresponding to the abnormal sub-data; Data cleaning unit, used for: Comparing the deviation coefficient corresponding to the abnormal sub-data with a preset deviation coefficient threshold; If the deviation coefficient corresponding to the abnormal sub-data is greater than or equal to a preset deviation coefficient threshold, the abnormal sub-data is deleted; If the deviation coefficient corresponding to the abnormal sub-data is less than the preset deviation coefficient threshold, obtaining a preset data cleaning rule; and performing data cleaning on the abnormal sub-data based on the preset data cleaning rule; Traverse all the data sets to be cleaned to obtain the multi-source monitoring data of the tailings pond after cleaning.

5. The tailings dam safety risk early sign identification system based on data mining as claimed in claim 4 is characterized in that: Screening unit, including: A segmentation subunit is used to evenly divide the data in the target to-be-cleaned data set into a plurality of target to-be-cleaned sub-data; The first calculation subunit is used to calculate the data value variance in each target sub-data to be cleaned, and obtain the variance value corresponding to each target sub-data to be cleaned; A screening subunit, used for comparing the variance value with a preset variance threshold; When it is determined that the variance value is greater than or equal to a preset variance threshold, the target to-be-cleaned sub-data corresponding to the variance value is taken as abnormal sub-data; Traverse all the target sub-data to be cleaned and obtain several abnormal sub-data; The second calculation subunit is used to calculate the deviation coefficient corresponding to each abnormal sub-data.

6. The tailings dam safety risk early sign identification system based on data mining as claimed in claim 1, characterized in that: Identification module, including: A mapping submodule, used to map the target feature to a preset space to obtain a target feature vector corresponding to the target feature; A similarity calculation submodule, used for calculating the similarity between the target feature vector corresponding to the target feature and the feature vector in the preset tailings pond safety risk early sign database; The recognition result determination submodule is used to use the similarity calculation result as the recognition result.

7. The tailings dam safety risk early sign identification system based on data mining as claimed in claim 6, characterized in that: Assessment modules include: A risk determination submodule, used to compare the recognition result with a preset similarity threshold, and when it is determined that the recognition result is greater than or equal to the preset similarity threshold, determine that there is a risk in the tailings pond; Filter submodule, used to: Obtaining historical disaster information of tailings ponds; the historical disaster information of tailings ponds includes indicator information corresponding to different disaster types of tailings ponds and the frequency of abnormal occurrence of various indicators; Construct a disaster indicator correlation coefficient matrix based on the indicator information corresponding to different disaster types of tailings ponds; Based on the frequency of abnormal occurrence of various indicators and the disaster indicator correlation coefficient matrix, the correlation degree of each indicator is determined, and the correlation degrees corresponding to several indicators are obtained; Comparing the correlations corresponding to the plurality of indicators with a preset correlation threshold; The corresponding indicator when the correlation degree is greater than or equal to the preset correlation degree threshold is used as the target key indicator of the disaster type; The sixth acquisition submodule is used to obtain data values ​​corresponding to target key indicators in the tailings pond multi-source monitoring data; The calculation submodule is used to determine the safety risk assessment value of the tailings pond based on the data values ​​corresponding to the target key indicators in the multi-source monitoring data of the tailings pond and a preset algorithm.

8. The tailings dam safety risk early sign identification system based on data mining as claimed in claim 7, characterized in that: The calculation submodule is used to determine the safety risk assessment value of the tailings pond based on the data values ​​corresponding to the target key indicators in the multi-source monitoring data of the tailings pond and the preset algorithm, including: Where P represents the safety risk assessment value of the tailings dam; χ represents the average risk value of the safety risk assessment value of the tailings dam; Λ i,j represents the risk value corresponding to the jth target key indicator in the i-th disaster type; m represents the total number of disaster types; n represents the total number of target key indicators; f(x)dx represents the probability density function of the risk of occurrence of the i-th disaster type.

9. The tailings dam safety risk early sign identification system based on data mining as claimed in claim 1, characterized in that: Early warning module, including: A comparison submodule, used to compare the tailings pond safety risk assessment value with a preset safety risk assessment threshold; A warning information generation submodule, used to generate warning information when it is determined that the safety risk assessment value of the tailings pond is greater than or equal to a preset safety risk assessment threshold; The query submodule is used to query the current duty information table and determine the current shift manager information; The warning sending submodule is used to send the warning information to the current shift manager to make a warning prompt.

10. A method for identifying early signs of safety risks in tailings dams based on data mining, characterized in that: include: Obtain multi-source monitoring data of tailings ponds in real time; Extracting multi-source monitoring data of the tailings pond to obtain target features; Identify the target features with the preset tailings dam safety risk early warning sign database to determine the identification results; When it is determined that the identification results indicate that there is a risk, determine the target key indicators for the type of disaster; Determine the safety risk assessment value of the tailings pond based on the target key indicators of the disaster type and the multi-source monitoring data of the tailings pond; The tailings pond safety risk assessment value is compared with a preset safety risk assessment threshold, and when it is determined that the tailings pond safety risk assessment value is greater than or equal to the preset safety risk assessment threshold, an early warning prompt is issued.

Images