Data fusion method and system applied to accurate prevention and control of dam break risk of tailings pond

Abstract

The invention discloses a data fusion method and system applied to accurate prevention and control of a dam break risk of a tailing pond. The method comprises the following steps: acquiring online monitoring data, equipment operation data, equipment inspection data, business data and natural condition data of the tailing pond, and preprocessing and storing the data; performing association analysis on the stored data, and determining relation attributes among the data according to an analysis result; key monitoring data types related to the dam break risk of the tailings pond are determined based on the relation attributes among the various data, and a data fusion task is generated according to the key monitoring data types; and performing data integration and fusion on related data corresponding to the key monitoring data type based on the data fusion task to construct a tailing pond dam break risk accurate prevention and control data model. According to the method, a set of complete data system is formed, intelligent research and judgment of the operation risk of the tailings pond are realized, the dam break risk of the tailings pond can be quickly predicted according to the subsequently collected real-time data, and the evaluation precision and the response speed are improved.

Description

Technical Field

[0001] The present invention relates to the field of data processing technology, and in particular to a data fusion method and system for precise prevention and control of tailings dam breach risks. Background Art

[0002] Accurate prevention and control of tailings dam breach risk is an important topic involving geological engineering, environmental science and safety management. In the past few decades, many dam breach accidents have caused serious losses to human production and life. Therefore, how to improve the safety of tailings dams has become an urgent task in the field of mine management and environmental protection. With the continuous expansion of mine production scale and the complexity of tailings dam management process, the monitoring and management of tailings dam breach disaster risks are also facing increasing challenges. Traditional tailings dam breach disaster risk assessment methods are often limited by low assessment accuracy, slow response speed, poor stability and other problems, making it difficult to meet the high efficiency, accuracy and safety requirements of modern mine safety production. Summary of the invention

[0003] In response to the above-mentioned problems, the present invention provides a data fusion method and system for precise prevention and control of tailings dam break risks to solve the problem that the traditional tailings dam break disaster risk assessment method mentioned in the background technology is often limited by the problems of low assessment accuracy, slow response speed, poor stability, etc., making it difficult to meet the high efficiency, accuracy and safety requirements of modern mine safety production.

[0004] A data fusion method for accurate prevention and control of tailings dam breach risk, comprising the following steps:

[0005] Obtain online monitoring data, equipment operation data, equipment inspection data, business data and natural condition data of the tailings pond, and perform pre-processing and storage;

[0006] Perform association analysis on the stored data and determine the relationship attributes between the data according to the analysis results;

[0007] Determine the key monitoring data types related to tailings dam breach risk based on the relationship attributes between various data, and generate data fusion tasks based on the key monitoring data types;

[0008] Based on the data fusion task, the relevant data corresponding to the key monitoring data types are integrated and fused to build a precise prevention and control data model for tailings dam break risks.

[0009] Preferably, the obtaining of online monitoring data, equipment operation data, equipment inspection data, business data and natural condition data of the tailings pond and preprocessing and storing the data includes:

[0010] Obtain the data source information of the tailings pond's online monitoring data, equipment operation data, equipment inspection data, business data, and natural condition data;

[0011] Determine the data source access interface for each type of data according to the data source information, determine the access rules for the data source access interface, and generate a configuration file based on the access rules;

[0012] Determine the data attributes of each type of data, determine the data extraction rules for each type of data based on the data attributes, and collect the online monitoring data, equipment operation data, equipment inspection data, business data and natural condition data of the tailings pond from the data source access interface through the configuration file based on the data extraction rules;

[0013] Perform data cleaning, deduplication, and missing value supplementation preprocessing on each type of data, determine the storage method for each type of data, and store the preprocessed multiple data in the preset database according to the storage method.

[0014] Preferably, the stored multiple data are subjected to association analysis, and the relationship attributes between the various data are determined according to the analysis results, including:

[0015] Determine the role and operation subjects of each type of data, and determine the association rules between various data based on the role and operation subjects;

[0016] Determine the logical transformation relationship of the association rules, and determine the entity relationship between various data based on the logical transformation relationship;

[0017] Determine the relationship execution bodies of various data under the association rules according to the entity relationships between various data, wherein the relationship execution bodies include: a starting body, an intermediate body and a terminal body;

[0018] The abnormal progressive mapping description parameters between each type of data and other types of data are determined according to the relationship execution body, and the relationship attributes between various data are determined according to the abnormal progressive mapping description parameters.

[0019] Preferably, determining the key monitoring data types related to the tailings dam breach risk based on the relationship attributes between various data, and generating data fusion tasks according to the key monitoring data types include:

[0020] Determine the factors affecting the risk of tailings dam breach, and determine various data related to the risk of tailings dam breach based on the influencing factors;

[0021] Analyze the correlation between various data related to tailings dam breach risk through data mining or machine learning models, and determine the key monitoring data types based on the correlation between various data and the relationship attributes between various data;

[0022] Determine the data coverage dimensions based on the key monitoring data types, and determine the data volume and data format of the key monitoring data types based on the data coverage dimensions;

[0023] Determine the data fusion processing flow based on data volume and data format, and generate data fusion tasks according to the data fusion processing flow.

[0024] Preferably, the data fusion task is based on which the relevant data corresponding to the key monitoring data type is integrated and fused to construct a tailings dam breach risk accurate prevention and control data model, including:

[0025] Determine the current data format and the exportable data format of the relevant data corresponding to the key monitoring data types, and process the relevant data into a unified format according to the current data format and the exportable data format;

[0026] The processed relevant data are integrated and fused through data integration tools, and the artificial and natural factors affecting the risk of tailings dam breach are determined based on the fused data;

[0027] A precise prevention and control data model for tailings dam breach risk is constructed based on the influencing factors of artificial conditions, natural conditions and historical tailings dam breach accident parameters.

[0028] A data fusion system for precise prevention and control of tailings dam breach risk, the system comprising:

[0029] The acquisition module is used to acquire the online monitoring data, equipment operation data, equipment inspection data, business data and natural condition data of the tailings pond and perform preprocessing and storage;

[0030] An analysis module is used to perform association analysis on the stored data and determine the relationship attributes between the data according to the analysis results;

[0031] A generation module is used to determine the key monitoring data types related to the tailings dam breach risk based on the relationship attributes between various data, and generate data fusion tasks according to the key monitoring data types;

[0032] The data fusion module is used to integrate and fuse the relevant data corresponding to the key monitoring data types based on the data fusion task to build a precise prevention and control data model for the tailings dam breach risk.

[0033] Preferably, the acquisition module includes:

[0034] The acquisition submodule is used to obtain the data source information of the tailings pond's online monitoring data, equipment operation data, equipment inspection data, business data, and natural condition data;

[0035] The first generating submodule is used to determine the data source access interface of each type of data according to the data source information, determine the access rule of the data source access interface, and generate a configuration file based on the access rule;

[0036] The collection submodule is used to determine the data attributes of each type of data, determine the data extraction rules for each type of data according to the data attributes, and collect the online monitoring data, equipment operation data, equipment inspection data, business data and natural condition data of the tailings pond from the data source access interface through the configuration file according to the data extraction rules;

[0037] The data preprocessing and storage submodule is used to perform data cleaning, deduplication, and missing value supplementation preprocessing on each type of data, determine the storage method for each type of data, and store the preprocessed multiple data into the preset database according to the storage method.

[0038] Preferably, the analysis module comprises:

[0039] The first determination submodule is used to determine the role subject and operation subject of each type of data, and determine the association rules between various data according to the role subject and operation subject;

[0040] The second determination submodule is used to determine the logical conversion relationship of the association rule, and determine the entity relationship between various data according to the logical conversion relationship;

[0041] The third determination submodule is used to determine the relationship execution bodies of various data under the association rule according to the entity relationships between various data, and the relationship execution bodies include: a starting body, an intermediate body and a terminal body;

[0042] The fourth determination submodule is used to determine the abnormal progressive mapping description parameters between each type of data and other types of data according to the relationship execution body, and determine the relationship attributes between various types of data according to the abnormal progressive mapping description parameters.

[0043] Preferably, the generating module comprises:

[0044] The fifth determination submodule is used to determine the influencing factors of the tailings dam breach risk, and to determine various data related to the tailings dam breach risk according to the influencing factors;

[0045] The sixth determination submodule is used to analyze the correlation between various types of data related to the risk of tailings dam breach through data mining or machine learning models, and determine the key monitoring data type based on the correlation between various types of data and the relationship attributes between various data;

[0046] A seventh determination submodule is used to determine the data coverage dimension based on the key monitoring data type, and determine the data volume and data format of the key monitoring data type according to the data coverage dimension;

[0047] The second generation submodule is used to determine the data fusion processing flow based on the data volume and data format, and generate a data fusion task according to the data fusion processing flow.

[0048] Preferably, the data fusion module includes:

[0049] A processing submodule is used to determine the current data format and the exportable data format of the relevant data corresponding to the key monitoring data type, and process the relevant data in a unified format according to the current data format and the exportable data format;

[0050] The data fusion submodule is used to integrate and fuse the processed relevant data through data integration tools, and determine the artificial and natural factors affecting the risk of tailings dam breach based on the fused data;

[0051] Construct a sub-module to build a precise prevention and control data model for tailings dam breach risk based on artificial and natural factors and historical tailings dam breach accident parameters.

[0052] 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.

[0053] The technical solution of the present invention is further described in detail below through the accompanying drawings and embodiments. BRIEF DESCRIPTION OF THE DRAWINGS

[0054] The accompanying drawings are used to provide further understanding of the present invention and constitute a part of the specification. They are used to explain the present invention together with the embodiments of the present invention and do not constitute a limitation of the present invention.

[0055] Figure 1 A workflow diagram of a data fusion method for precise prevention and control of tailings dam breach risks provided by the present invention;

[0056] Figure 2 Another workflow diagram of a data fusion method for precise prevention and control of tailings dam breach risk provided by the present invention;

[0057] Figure 3 A schematic diagram of the structure of a data fusion system for precise prevention and control of tailings dam breach risks provided by the present invention;

[0058] Figure 4 This is a structural schematic diagram of an acquisition module in a data fusion system for precise prevention and control of tailings dam breach risks provided by the present invention. DETAILED DESCRIPTION

[0059] Exemplary embodiments will be described in detail herein, examples of which are shown in the accompanying drawings. When the following description refers to the drawings, the same numbers in different drawings represent the same or similar elements unless otherwise indicated. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with the present disclosure. Instead, they are merely examples of devices and methods consistent with some aspects of the present disclosure as detailed in the appended claims.

[0060] Accurate prevention and control of tailings dam breach risk is an important topic involving geological engineering, environmental science and safety management. In the past few decades, many dam breach accidents have caused serious losses to human production and life. Therefore, how to improve the safety of tailings dams has become an urgent task in the field of mine management and environmental protection. With the continuous expansion of mine production scale and the complexity of tailings dam management process, the monitoring and management of tailings dam breach disaster risks are also facing increasing challenges. Traditional tailings dam breach disaster risk assessment methods are often limited by low assessment accuracy, slow response speed, poor stability and other problems, making it difficult to meet the efficient, accurate and safe requirements of modern mine safety production. In order to solve the above problems, this embodiment discloses a data fusion method for accurate prevention and control of tailings dam breach risks. The data fusion method for accurate prevention and control of tailings dam breach risks aims to integrate data from different sources and in different formats into a unified information system to better analyze and predict the risk of tailings dam breach.

[0061] A data fusion method for accurate prevention and control of tailings dam breach risk, such as Figure 1 As shown, the following steps are included:

[0062] Step S101, obtaining online monitoring data, equipment operation data, equipment inspection data, business data and natural condition data of the tailings pond, and pre-processing and storing them;

[0063] Step S102: performing association analysis on the stored data, and determining the relationship attributes between the data according to the analysis results;

[0064] Step S103: determining the key monitoring data types related to the tailings dam breach risk based on the relationship attributes between various data, and generating data fusion tasks according to the key monitoring data types;

[0065] Step S104: Based on the data fusion task, the relevant data corresponding to the key monitoring data type are integrated and fused to construct a precise prevention and control data model for the tailings dam breach risk.

[0066] In this embodiment, the online monitoring data is represented as the scene online monitoring data of the tailings pond;

[0067] In this embodiment, the relationship attributes are represented as logical relationship attributes between various data, such as progressive attributes, causal attributes, etc.

[0068] The working principle of the above technical solution is: obtain the online monitoring data, equipment operation data, equipment inspection data, business data and natural condition data of the tailings pond and perform preprocessing and storage; perform correlation analysis on the various stored data, and determine the relationship attributes between various data according to the analysis results; determine the key monitoring data types related to the tailings pond dam break risk based on the relationship attributes between various data, and generate data fusion tasks according to the key monitoring data types; based on the data fusion tasks, integrate and fuse the relevant data corresponding to the key monitoring data types to construct a precise prevention and control data model for the tailings pond dam break risk.

[0069] The beneficial effects of the above technical solution are: by integrating data with dam break risks from different sources and in different formats of tailings ponds to reveal the intrinsic connection between the data, studying the early signs of safety risks of tailings ponds, combining the influence of natural conditions on the operation risks of tailings ponds, accident case analysis and force majeure factors, a complete data system is formed, and data mining technology is used to realize intelligent analysis of tailings pond operation risks. The dam break risk of the tailings pond can be quickly predicted based on the real-time data collected subsequently, thereby improving the assessment accuracy and response speed, and solving the problem that the traditional tailings pond dam break disaster risk assessment method mentioned in the prior art is often limited by low assessment accuracy, slow response speed, poor stability and other problems, making it difficult to meet the high efficiency, accuracy and safety requirements of modern mine safety production.

[0070] In this embodiment, before obtaining the online monitoring data, equipment operation data, equipment inspection data, business data and natural condition data of the tailings pond and pre-processing and storing them, it also includes:

[0071] Determine the data flows of online monitoring data, equipment operation data, equipment inspection data, business data, and natural condition data respectively;

[0072] Determine the data subjects of online monitoring data, equipment operation data, equipment inspection data, business data and natural condition data according to the data flow, and obtain the control attributes of the data subjects;

[0073] Determine the network control subdomains of online monitoring data, equipment operation data, equipment inspection data, business data and natural condition data according to the control attributes;

[0074] Obtain the data security transmission strategy of the network control subdomain, and determine the respective uplink permissions for online monitoring data, equipment operation data, equipment inspection data, business data, and natural condition data based on the data security transmission strategy;

[0075] Build data responsibility matrices for online monitoring data, equipment operation data, equipment inspection data, business data, and natural condition data based on the on-chain permissions;

[0076] Build a data upload system based on the data responsibility matrix, and determine the data collection request parameters for online monitoring data, equipment operation data, equipment inspection data, business data, and natural condition data based on the data upload system;

[0077] Generate data collection instructions according to data collection request parameters and obtain online monitoring data, equipment operation data, equipment inspection data, business data and natural condition data of the tailings pond according to the data collection instructions.

[0078] The beneficial effects of the above technical solution are: by constructing a data upload system, the responsive data collection request parameters can be accurately generated according to the retrieval permissions of various data, so that the data end can quickly identify the data collection instructions and safely transmit the data, which not only ensures data security but also can quickly collect different types of data, avoids the occurrence of excessive data leading to the inability to guarantee data quality due to fusion, and improves stability and reliability.

[0079] In one embodiment, Figure 2 As shown, the online monitoring data, equipment operation data, equipment inspection data, business data and natural condition data of the tailings pond are obtained and pre-processed and stored, including:

[0080] Step S201, obtaining the data source information of the online monitoring data, equipment operation data, equipment inspection data, business data and natural condition data of the tailings pond;

[0081] Step S202: determine the data source access interface of each type of data according to the data source information, determine the access rules of the data source access interface, and generate a configuration file based on the access rules;

[0082] Step S203, determining the data attributes of each type of data, determining the data extraction rules for each type of data according to the data attributes, and collecting the online monitoring data, equipment operation data, equipment inspection data, business data and natural condition data of the tailings pond from the data source access interface through the configuration file according to the data extraction rules;

[0083] Step S204: perform data cleaning, deduplication, and missing value supplementation preprocessing on each type of data, determine the storage method of each type of data, and store the preprocessed multiple data into a preset database according to the storage method.

[0084] The beneficial effects of the above technical solution are: by generating access configuration files and data extraction rules for each data source, it is possible to stably and completely collect relevant data from each data source access interface while ensuring stability and reliability during data transmission, thereby ensuring data quality. At the same time, data is collected with reasonable identity information, avoiding cost losses caused by data leakage, and improving practicality and stability.

[0085] In one embodiment, the stored multiple data are subjected to association analysis, and the relationship attributes between the various data are determined according to the analysis results, including:

[0086] Determine the role and operation subjects of each type of data, and determine the association rules between various data based on the role and operation subjects;

[0087] Determine the logical transformation relationship of the association rules, and determine the entity relationship between various data based on the logical transformation relationship;

[0088] Determine the relationship execution bodies of various data under the association rules according to the entity relationships between various data, wherein the relationship execution bodies include: a starting body, an intermediate body and a terminal body;

[0089] The abnormal progressive mapping description parameters between each type of data and other types of data are determined according to the relationship execution body, and the relationship attributes between various data are determined according to the abnormal progressive mapping description parameters.

[0090] In this embodiment, the abnormal progressive mapping description parameters are expressed as behavior description parameters of an abnormal mapping relationship body of a non-progressive relationship between each type of data and other types of data.

[0091] The beneficial effects of the above technical solution are: by determining the relationship executor of various data and then determining the abnormal progressive mapping description parameters between each type of data and other types of data, the relationship attributes between various data are determined according to the abnormal progressive mapping description parameters. The relationship attributes between various data can be determined according to the relevant description parameters of the causal relationship, progressive relationship, conditional relationship, transition relationship, parallel relationship and total-to-specific relationship between each type of data and other data, thereby ensuring the comprehensiveness, objectivity and reliability of the acquisition of relationship attributes.

[0092] In one embodiment, determining the key monitoring data types related to the tailings dam breach risk based on the relationship attributes between various data types, and generating data fusion tasks according to the key monitoring data types, includes:

[0093] Determine the factors affecting the risk of tailings dam breach, and determine various data related to the risk of tailings dam breach based on the influencing factors;

[0094] Analyze the correlation between various data related to tailings dam breach risk through data mining or machine learning models, and determine the key monitoring data types based on the correlation between various data and the relationship attributes between various data;

[0095] Determine the data coverage dimensions based on the key monitoring data types, and determine the data volume and data format of the key monitoring data types based on the data coverage dimensions;

[0096] Determine the data fusion processing flow based on data volume and data format, and generate data fusion tasks according to the data fusion processing flow.

[0097] The beneficial effects of the above technical solution are: by determining the data volume and data format of the key monitored data types and then determining the data fusion processing flow, the limiting factors of various types of data in the fusion process can be fully considered, and corresponding solutions can be made through different functional components to ensure the smooth progress of the fusion process, providing practicality and stability.

[0098] In one embodiment, the data fusion task is based on which the relevant data corresponding to the key monitoring data type is integrated and fused to build a tailings dam breach risk accurate prevention and control data model, including:

[0099] Determine the current data format and the exportable data format of the relevant data corresponding to the key monitoring data types, and process the relevant data into a unified format according to the current data format and the exportable data format;

[0100] The processed relevant data are integrated and fused through data integration tools, and the artificial and natural factors affecting the risk of tailings dam breach are determined based on the fused data;

[0101] A precise prevention and control data model for tailings dam breach risk is constructed based on the influencing factors of artificial conditions, natural conditions and historical tailings dam breach accident parameters.

[0102] The beneficial effects of the above technical solution are: by constructing a precise data model for the prevention and control of tailings dam breach risks, it is possible to determine the abnormal indicators of each data that may lead to tailings dam breach based on the inherent connections between various types of data, and then use the model to conduct safety assessments for subsequent real-time indicators. The risk of tailings dam breach can be assessed in the first place, thereby improving safety and indirectly reducing cost losses.

[0103] In one embodiment, this embodiment also discloses a data fusion system for precise prevention and control of tailings dam breach risks, such as Figure 3 As shown, the system includes:

[0104] The acquisition module 301 is used to acquire the online monitoring data, equipment operation data, equipment inspection data, business data and natural condition data of the tailings pond and perform preprocessing and storage;

[0105] An analysis module 302 is used to perform association analysis on the stored data and determine the relationship attributes between the data according to the analysis results;

[0106] A generation module 303 is used to determine the key monitoring data types related to the tailings dam breach risk based on the relationship attributes between various data, and generate data fusion tasks according to the key monitoring data types;

[0107] The data fusion module 304 is used to integrate and fuse the relevant data corresponding to the key monitoring data type based on the data fusion task to build a precise prevention and control data model for the tailings dam breach risk.

[0108] The working principle and beneficial effects of the above technical solution have been explained in the method embodiment and will not be repeated here.

[0109] In one embodiment, Figure 4 As shown, the acquisition module 301 includes:

[0110] The acquisition submodule 3011 is used to obtain the data source information of the online monitoring data, equipment operation data, equipment inspection data, business data and natural condition data of the tailings pond;

[0111] The first generating submodule 3012 is used to determine the data source access interface of each type of data according to the data source information, determine the access rule of the data source access interface, and generate a configuration file based on the access rule;

[0112] The collection submodule 3013 is used to determine the data attributes of each type of data, determine the data extraction rules for each type of data according to the data attributes, and collect the online monitoring data, equipment operation data, equipment inspection data, business data and natural condition data of the tailings pond from the data source access interface through the configuration file according to the data extraction rules;

[0113] The data preprocessing and storage submodule 3014 is used to perform data cleaning, deduplication, and missing value supplementation preprocessing on each type of data, determine the storage method of each type of data, and store the preprocessed multiple data into a preset database according to the storage method.

[0114] In one embodiment, the analysis module comprises:

[0115] The first determination submodule is used to determine the role subject and operation subject of each type of data, and determine the association rules between various data according to the role subject and operation subject;

[0116] The second determination submodule is used to determine the logical conversion relationship of the association rule, and determine the entity relationship between various data according to the logical conversion relationship;

[0117] The third determination submodule is used to determine the relationship execution bodies of various data under the association rule according to the entity relationships between various data, and the relationship execution bodies include: a starting body, an intermediate body and a terminal body;

[0118] The fourth determination submodule is used to determine the abnormal progressive mapping description parameters between each type of data and other types of data according to the relationship execution body, and determine the relationship attributes between various types of data according to the abnormal progressive mapping description parameters.

[0119] In one embodiment, the generating module comprises:

[0120] The fifth determination submodule is used to determine the influencing factors of the tailings dam breach risk, and to determine various data related to the tailings dam breach risk according to the influencing factors;

[0121] The sixth determination submodule is used to analyze the correlation between various types of data related to the risk of tailings dam breach through data mining or machine learning models, and determine the key monitoring data type based on the correlation between various types of data and the relationship attributes between various data;

[0122] A seventh determination submodule is used to determine the data coverage dimension based on the key monitoring data type, and determine the data volume and data format of the key monitoring data type according to the data coverage dimension;

[0123] The second generation submodule is used to determine the data fusion processing flow based on the data volume and data format, and generate a data fusion task according to the data fusion processing flow.

[0124] In one embodiment, the data fusion module includes:

[0125] A processing submodule is used to determine the current data format and the exportable data format of the relevant data corresponding to the key monitoring data type, and process the relevant data in a unified format according to the current data format and the exportable data format;

[0126] The data fusion submodule is used to integrate and fuse the processed relevant data through data integration tools, and determine the artificial and natural factors affecting the risk of tailings dam breach based on the fused data;

[0127] Construct a sub-module to build a precise prevention and control data model for tailings dam breach risk based on artificial and natural factors and historical tailings dam breach accident parameters.

[0128] Those skilled in the art should understand that the first and second in the present invention merely refer to different application stages.

[0129] Other embodiments of the present disclosure will be readily apparent to those skilled in the art after considering the specification and practicing the disclosure disclosed herein. This application is intended to cover any variations, uses, or adaptations of the present disclosure that follow the general principles of the present disclosure and include common knowledge or customary techniques in the art that are not disclosed in the present disclosure. The specification and examples are to be considered exemplary only, and the true scope and spirit of the present disclosure are indicated by the following claims.

[0130] It should be understood that the present disclosure is not limited to the exact structures that have been described above and shown in the drawings, and that various modifications and changes may be made without departing from the scope thereof. The scope of the present disclosure is limited only by the appended claims.

Claims

1. A data fusion method for precise prevention and control of tailings dam breach risk, characterized in that: The following steps are involved: Obtain online monitoring data, equipment operation data, equipment inspection data, business data and natural condition data of the tailings pond, and perform pre-processing and storage; Perform association analysis on the stored data and determine the relationship attributes between the data according to the analysis results; Determine the key monitoring data types related to tailings dam breach risk based on the relationship attributes between various data, and generate data fusion tasks based on the key monitoring data types; Based on the data fusion task, the relevant data corresponding to the key monitoring data types are integrated and fused to build a precise prevention and control data model for tailings dam break risks.

2. The data fusion method for accurate prevention and control of tailings dam breach risk according to claim 1 is characterized in that: The obtaining of online monitoring data, equipment operation data, equipment inspection data, business data and natural condition data of the tailings pond and pre-processing and storing the data includes: Obtain the data source information of the tailings pond's online monitoring data, equipment operation data, equipment inspection data, business data, and natural condition data; Determine the data source access interface for each type of data according to the data source information, determine the access rules for the data source access interface, and generate a configuration file based on the access rules; Determine the data attributes of each type of data, determine the data extraction rules for each type of data based on the data attributes, and collect the online monitoring data, equipment operation data, equipment inspection data, business data and natural condition data of the tailings pond from the data source access interface through the configuration file based on the data extraction rules; Perform data cleaning, deduplication, and missing value supplementation preprocessing on each type of data, determine the storage method for each type of data, and store the preprocessed multiple data in the preset database according to the storage method.

3. The data fusion method for accurate prevention and control of tailings dam breach risk according to claim 1 is characterized in that: The stored data are analyzed for association, and the relationship attributes between the data are determined based on the analysis results, including: Determine the role and operation subjects of each type of data, and determine the association rules between various data based on the role and operation subjects; Determine the logical transformation relationship of the association rules, and determine the entity relationship between various data based on the logical transformation relationship; Determine the relationship execution bodies of various data under the association rules according to the entity relationships between various data, wherein the relationship execution bodies include: a starting body, an intermediate body and a terminal body; The abnormal progressive mapping description parameters between each type of data and other types of data are determined according to the relationship execution body, and the relationship attributes between various data are determined according to the abnormal progressive mapping description parameters.

4. The data fusion method for accurate prevention and control of tailings dam breach risk according to claim 1 is characterized in that: Determining the key monitoring data types related to the tailings dam breach risk based on the relationship attributes between various data, and generating data fusion tasks according to the key monitoring data types, includes: Determine the factors affecting the risk of tailings dam breach, and determine various data related to the risk of tailings dam breach based on the influencing factors; Analyze the correlation between various data related to tailings dam breach risk through data mining or machine learning models, and determine the key monitoring data types based on the correlation between various data and the relationship attributes between various data; Determine the data coverage dimensions based on the key monitoring data types, and determine the data volume and data format of the key monitoring data types based on the data coverage dimensions; Determine the data fusion processing flow based on data volume and data format, and generate data fusion tasks according to the data fusion processing flow.

5. The data fusion method for accurate prevention and control of tailings dam breach risk according to claim 1 is characterized in that: The data fusion task integrates and fuses the relevant data corresponding to the key monitoring data types to build a precise prevention and control data model for tailings dam breach risk, including: Determine the current data format and the exportable data format of the relevant data corresponding to the key monitoring data types, and process the relevant data into a unified format according to the current data format and the exportable data format; The processed relevant data are integrated and fused through data integration tools, and the artificial and natural factors affecting the risk of tailings dam breach are determined based on the fused data; A precise prevention and control data model for tailings dam breach risk is constructed based on the influencing factors of artificial conditions, natural conditions and historical tailings dam breach accident parameters.

6. A data fusion system for precise prevention and control of tailings dam breach risk, characterized in that: The system includes: The acquisition module is used to acquire the online monitoring data, equipment operation data, equipment inspection data, business data and natural condition data of the tailings pond and perform preprocessing and storage; An analysis module is used to perform association analysis on the stored data and determine the relationship attributes between the data according to the analysis results; A generation module is used to determine the key monitoring data types related to the tailings dam breach risk based on the relationship attributes between various data, and generate data fusion tasks according to the key monitoring data types; The data fusion module is used to integrate and fuse the relevant data corresponding to the key monitoring data types based on the data fusion task to build a precise prevention and control data model for the tailings dam breach risk.

7. The data fusion system for precise prevention and control of tailings dam breach risk according to claim 6 is characterized in that: The acquisition module comprises: The acquisition submodule is used to obtain the data source information of the tailings pond's online monitoring data, equipment operation data, equipment inspection data, business data, and natural condition data; The first generating submodule is used to determine the data source access interface of each type of data according to the data source information, determine the access rule of the data source access interface, and generate a configuration file based on the access rule; The collection submodule is used to determine the data attributes of each type of data, determine the data extraction rules for each type of data according to the data attributes, and collect the online monitoring data, equipment operation data, equipment inspection data, business data and natural condition data of the tailings pond from the data source access interface through the configuration file according to the data extraction rules; The data preprocessing and storage submodule is used to perform data cleaning, deduplication, and missing value supplementation preprocessing on each type of data, determine the storage method for each type of data, and store the preprocessed multiple data into the preset database according to the storage method.

8. The data fusion system for precise prevention and control of tailings dam breach risk according to claim 6 is characterized in that: The analysis module comprises: The first determination submodule is used to determine the role subject and operation subject of each type of data, and determine the association rules between various data according to the role subject and operation subject; The second determination submodule is used to determine the logical conversion relationship of the association rule, and determine the entity relationship between various data according to the logical conversion relationship; The third determination submodule is used to determine the relationship execution bodies of various data under the association rule according to the entity relationships between various data, and the relationship execution bodies include: a starting body, an intermediate body and a terminal body; The fourth determination submodule is used to determine the abnormal progressive mapping description parameters between each type of data and other types of data according to the relationship execution body, and determine the relationship attributes between various types of data according to the abnormal progressive mapping description parameters.

9. The data fusion system for precise prevention and control of tailings dam breach risk according to claim 6 is characterized in that: The generating module comprises: The fifth determination submodule is used to determine the influencing factors of the tailings dam breach risk, and to determine various data related to the tailings dam breach risk according to the influencing factors; The sixth determination submodule is used to analyze the correlation between various types of data related to the risk of tailings dam breach through data mining or machine learning models, and determine the key monitoring data type based on the correlation between various types of data and the relationship attributes between various data; A seventh determination submodule is used to determine the data coverage dimension based on the key monitoring data type, and determine the data volume and data format of the key monitoring data type according to the data coverage dimension; The second generation submodule is used to determine the data fusion processing flow based on the data volume and data format, and generate a data fusion task according to the data fusion processing flow.

10. The data fusion system for precise prevention and control of tailings dam breach risk according to claim 6 is characterized in that: The data fusion module comprises: A processing submodule is used to determine the current data format and the exportable data format of the relevant data corresponding to the key monitoring data type, and process the relevant data in a unified format according to the current data format and the exportable data format; The data fusion submodule is used to integrate and fuse the processed relevant data through data integration tools, and determine the artificial and natural factors affecting the risk of tailings dam breach based on the fused data; Construct a sub-module to build a precise prevention and control data model for tailings dam breach risk based on artificial and natural factors and historical tailings dam breach accident parameters.

Images