Early warning system and early warning method for geological disasters
By collecting and processing geological parameters and environmental data in real time, establishing early warning models, identifying early warning signals for slip-type dangerous rock collapse, solving the problems of false alarms and lagging traditional monitoring indicators in the existing technology, and achieving large-scale Accurate early warning of dangerous rock collapse.
Patent Information
- Application Number
- CN202410901167.9
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-07-05
- Publication Date
- 2024-11-29
- Estimated Expiration
- Not applicable · inactive patent
Smart Images

Figure CN119049224A_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the technical field of geological disaster monitoring, and in particular to an early warning system and an early warning method for geological disasters. Background Art
[0002] Geological disaster monitoring technology is a series of methods and equipment used to monitor the changes in the earth's surface or near-surface geological structure in real time or regularly, aiming to prevent and reduce the losses caused by geological disasters. These technologies provide early warnings through long-term observation of signs of geological activities, and provide data support for disaster management, risk assessment and emergency response. Rock collapse is a common geological disaster in my country. The causes of large-scale dangerous rock collapse are complex, the distribution range is wide, the concealment and suddenness are strong, and the hazards are great. Its early warning has always been difficult to achieve.
[0003] Currently, in the field of early warning of large-scale dangerous rock collapse disasters, the early warning mode mostly adopts a threshold warning model. Due to the lack of scientific judgment on the physical and mechanical characteristics and dynamic stability of the rock mass, false alarms and missed alarms often occur, and traditional monitoring indicators cannot meet the early warning needs of large-scale dangerous rock collapse disasters. Rock block collapse is mostly caused by the continuous decrease in the degree of adhesion of the rock bridge structure surface and the ultimate result of dynamic damage. In this process of change, traditional stress-strain static indicators and environmental quantity indicator monitoring have certain limitations in terms of early warning timeliness and accuracy.
[0004] Therefore, it is necessary to provide a new early warning system and early warning method for geological disasters to solve the above technical problems. Summary of the invention
[0005] In order to solve the above technical problems, the present invention provides an early warning system and early warning method for geological disasters.
[0006] The early warning system for geological disasters provided in the first aspect of the present application adopts the following technical solutions:
[0007] An early warning system for geological disasters comprises:
[0008] The data acquisition module is used to collect the original geological parameters and environmental data in the detection area in real time and transmit them to the data preprocessing module;
[0009] A data preprocessing module, used for preprocessing the data transmitted by the data acquisition module and transmitting the data to the data storage and management module;
[0010] A data storage and management module, used for receiving and storing data transmitted by the data acquisition module;
[0011] The data analysis and processing module is used to call the geological parameters and environmental data in the data storage and management module, establish an early warning model, calculate and judge whether the critical state of separation damage is approaching or reached, obtain the empirical threshold, set the natural vibration frequency separation stage early warning threshold, and carry out early warning based on the identification of separation damage precursors;
[0012] The warning information release module is used to calculate and trigger the warning signal in real time according to the analysis results of the data analysis and processing module and the preset threshold;
[0013] The monitoring module is used to provide managers with a visual interface to display the data of the data storage and management module, as well as the analysis results of the early warning information release module and the signals that trigger the early warning in real time.
[0014] Furthermore, the data collected by the data collection module include a rock mass parameter measuring instrument for collecting physical property data and a vibration sensor, a displacement sensor and a meteorological monitoring device for collecting geological environment parameters.
[0015] Furthermore, the data storage and management module can integrate the data and establish a historical disaster data set.
[0016] Furthermore, the rock mass parameter measuring instrument is used to obtain the quality of the rock block, and the vibration sensor, displacement sensor and meteorological monitoring equipment are used to collect the slope of the rock mass, vibration frequency data and displacement data of the monitoring point.
[0017] Furthermore, the historical disaster dataset analyzes the time series data of historical disasters to identify the seasonal and periodic patterns of disaster occurrence and their evolution trends over time;
[0018] Furthermore, historical disaster datasets are used to identify typical characteristics and patterns of different disaster types through cluster analysis or time series analysis methods.
[0019] The second aspect of the present application provides an early warning method for geological disasters using the following technical solution:
[0020] S01, data collection and preprocessing: Install the vibration sensor, displacement sensor and meteorological monitoring equipment of the data collection module in the detection area to monitor the vibration frequency, displacement and slope data of the rock mass in real time, use the rock parameter measuring instrument of the data collection module to collect rock block samples in the detection area for detection, and obtain the quality of the rock block. The data preprocessing module preprocesses the collected data and stores it in the data storage and management module;
[0021] S02, parameter calculation and stability assessment: the data analysis and processing module uses the data from the data storage and management module to determine the collapse and instability criteria of sliding-type dangerous rock masses;
[0022] S03. Warning threshold setting and monitoring: When the rock mass enters the separation stage from the stable stage, the friction force begins to be greater than 0, and the natural vibration frequency satisfies the following formula, the separation failure precursor warning is triggered:
[0023]
[0024] According to the above formula, the warning threshold of the natural vibration frequency separation stage is established, and the vibration frequency of the rock mass is continuously monitored and compared with the warning threshold. Once the monitored frequency is close to or lower than the warning threshold, the warning signal is immediately triggered;
[0025] S04, warning release and response: When the warning information release module identifies that the warning conditions have been met, it will promptly release warning information to relevant departments and local residents;
[0026] S05. Post-analysis and research: The early warning information release module records the actual collapse events after each warning in detail, and analyzes the lead time of the warning, the actual collapse situation and the degree of consistency with the early warning model. Based on the measured data and disaster case analysis, the early warning model is continuously optimized and displayed in the monitoring module.
[0027] Furthermore, in step S04, the warning information is issued and responded to in the form of text messages, emails, and broadcasts.
[0028] Furthermore, step S04 of warning issuance and response also includes an emergency plan, which includes measures for evacuation of personnel, traffic control, and standby of rescue teams.
[0029] Compared with the related art, the early warning system and early warning method for geological disasters provided by the present invention have the following beneficial effects:
[0030] 1. The geological disaster early warning system and early warning method adopts a high-performance data acquisition module to capture diversified data including rock micro-motion, stress changes, and environmental parameters in real time to ensure the comprehensiveness and real-time nature of the data. By introducing a dynamic data analysis model, the system can carefully capture the subtle changes in the degree of adhesion of the rock bridge structure surface, fundamentally solving the lag problem of traditional static indicator monitoring and providing strong real-time data support for the dynamic stability assessment of sliding-type dangerous rock masses.
[0031] 2. The early warning system deeply integrates the principles of geological mechanics and modern data analysis technology. Through in-depth analysis of the physical and mechanical properties of rock masses, it achieves a more scientific judgment on the dynamic stability of rock masses. It not only reduces the false alarms and missed alarms of traditional threshold early warning models, but also greatly improves the pertinence and reliability of early warnings, ensuring the accuracy of early warning signals.
[0032] 3. The system comprehensively considers multi-source data and constructs a multi-dimensional risk assessment model, which not only considers the changes in physical parameters, but also integrates the impact of environmental factors on rock stability, providing a comprehensive and integrated early warning perspective. This comprehensive assessment mechanism effectively improves the comprehensiveness and accuracy of the early warning, ensuring that accurate early warnings can be issued in the early stages of sliding-type dangerous rock collapse and destruction, thereby buying valuable time for emergency response. BRIEF DESCRIPTION OF THE DRAWINGS
[0033] Figure 1 A system block diagram of the early warning system for geological disasters provided by the present invention;
[0034] Figure 2 A flowchart of the data analysis and processing module provided by the present invention;
[0035] Figure 3 A flowchart of the early warning method for geological disasters provided by the present invention. DETAILED DESCRIPTION
[0036] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.
[0037] Please refer to Figure 1 , Figure 2 as well as Figure 3 , Figure 1 A system block diagram of the early warning system for geological disasters provided by the present invention; Figure 2 A flowchart of the data analysis and processing module provided by the present invention; Figure 3 A flowchart of the early warning method for geological disasters provided by the present invention.
[0038] Embodiment 1:
[0039] like Figure 1 to Figure 2 As shown, an early warning system for geological disasters adopts the following technical solutions:
[0040] The system includes a data acquisition module, a data preprocessing module, a data storage and management module, a data analysis and processing module, a warning information release module and a monitoring module;
[0041] The data acquisition module is used to collect the original geological parameters and environmental data in the detection area in real time and transmit them to the data storage and management module. The data collected by the data acquisition module includes a rock parameter measuring instrument for collecting physical property data and a vibration sensor, displacement sensor and meteorological monitoring equipment for collecting geological environmental parameters. The rock parameter measuring instrument is used to obtain the rock mass M, and the vibration sensor, displacement sensor and meteorological monitoring equipment are used to collect the slope θ of the rock mass, the vibration frequency data f and displacement data x of the monitoring point.
[0042] The data preprocessing module is used to clean the raw data in the data storage and management module, convert the format to standardization, and align the time and space, and transmit the processed data to the data storage and management module;
[0043] Specifically, intelligent data cleaning includes outlier detection and processing, which automatically identifies and processes outliers by using statistical methods and machine learning algorithms, and outlier identification based on model predictions; it also includes missing value filling, which intelligently selects filling strategies based on data characteristics and ensures data integrity by filling missing data using interpolation methods;
[0044] Advanced format conversion and standardization, including adaptive format conversion, which supports seamless integration of multi-source data by automatically identifying and converting data formats generated by different sensors and devices; and dynamic standardization, which improves the accuracy and efficiency of data analysis by dynamically selecting z-score standardization or min-max standardization methods based on data distribution;
[0045] Spatiotemporal data alignment and fusion, including spatiotemporal data indexing, which can quickly locate and integrate multi-source data within the same spatiotemporal range by building an efficient spatiotemporal indexing mechanism; and spatiotemporal interpolation and alignment: using Kriging interpolation or spatiotemporal cube interpolation to handle problems such as uneven data sampling rates or incomplete spatiotemporal coverage, ensuring data continuity and consistency in time and space;
[0046] Feature engineering and selection, including automatic feature extraction, which automatically extracts meaningful features by applying feature engineering techniques, and extracts frequency domain features of vibration frequency through time series analysis; it also includes feature selection algorithms, which reduce data dimensions and improve model training efficiency and prediction accuracy by integrating recursive feature elimination and model-based feature importance assessment;
[0047] Data quality monitoring and feedback, including real-time data quality assessment, by introducing a data quality monitoring module to evaluate data integrity, accuracy, consistency and other indicators in real time; also includes feedback loop optimization, by establishing a feedback mechanism for data processing effects, reversely optimizing the data preprocessing process according to the model prediction effect, and forming a closed-loop optimization system;
[0048] Through these expansion and optimization measures, the data preprocessing module can not only effectively improve the data quality, but also enhance the efficiency of the data analysis and processing module, providing more accurate and timely decision-making support information for geological disaster warning.
[0049] The data storage and management module is used to receive the original geological parameters and environmental data transmitted by the data acquisition module and the geological parameters and environmental data preprocessed by the data preprocessing module;
[0050] Specifically, the distributed storage architecture includes expanding storage capacity and access speed. By adopting a distributed file system or cloud storage service, a large amount of raw data and processed data are stored in a dispersed manner, which increases storage capacity while significantly improving data access speed through parallel reading and writing.
[0051] Data compression and archiving, including optimizing storage space by implementing intelligent compression strategies for historical data that is not frequently accessed to reduce storage usage, and establishing a data archiving mechanism to migrate data that has not been accessed for a long time to a low-cost storage layer to maintain efficient access to active data;
[0052] Real-time data stream processing, including the introduction of stream processing engines: integrating Apache Kafka, Flink or Spark Streaming stream processing frameworks to achieve real-time data ingestion, processing and storage, provide support for immediate warnings, and reduce data processing delays;
[0053] Data indexing and query optimization, including efficient data retrieval, by indexing frequently queried fields, using inverted indexes and hash indexes to optimize data query performance and ensure rapid response to analytical queries and early warning triggers;
[0054] Data security and privacy protection, including strengthening data protection measures, ensuring that sensitive data is not illegally accessed or leaked by implementing data encryption storage, access control, and data desensitization, and complying with relevant data protection laws and regulations;
[0055] Data version control and backup and recovery, including data integrity assurance, by implementing a data version control mechanism to record every data change for easy traceability and rollback, regularly backing up data, and setting up a disaster recovery plan to ensure rapid service recovery in the event of data loss or system failure;
[0056] Metadata management, including enhancing data management capabilities by establishing a metadata management system to record the source, format, and processing history of data, making it easier to track, understand, and use data, and improving the efficiency of data management and analysis;
[0057] Resource monitoring and automated operation and maintenance, including system health monitoring, real-time monitoring of storage resource usage, system performance and potential failures through integrated monitoring tools, automated alarms and resource allocation to ensure stable system operation;
[0058] Through the above-mentioned expansion and optimization measures, the data storage and management module can not only effectively cope with the storage and management challenges of large-scale data, but also ensure the efficiency, security and reliability of data processing, providing a solid data foundation for the accurate warning and rapid response of the geological disaster early warning system.
[0059] The data analysis and processing module is used to call the pre-processed geological parameters and environmental data, establish an early warning model, calculate and judge whether the critical state of separation damage is approaching or reached, obtain the empirical threshold, set the natural vibration frequency separation stage early warning threshold, and carry out early warning based on separation damage precursor identification;
[0060] Specifically, the following steps are included:
[0061] 1. Construction of advanced early warning model;
[0062] Deepen the integration and analysis of historical disaster data. In addition to identifying seasonal and cyclical patterns, use ARIMA and state-space models to explore the nonlinear relationship between disaster occurrence and rainfall, temperature, and soil moisture, capture long-term trends and cyclical fluctuations, and potential external triggering factors; based on cluster analysis, use autoencoders and variational autoencoders to reduce the dimension and extract patterns of disaster characteristics, and identify more complex spatiotemporal feature patterns, which may include specific patterns of rock deformation, subtle signs of terrain changes, etc.;
[0063] The prediction system integrates machine learning and physical models. On the basis of using random forest as the main prediction model, it integrates gradient boosting tree and neural network to form an integrated learning system to improve the generalization ability and robustness of the model. At the same time, it deeply integrates the principles of geomechanics. For example, by introducing the shear stress and cohesion of the rock mechanics model as the input features of the machine learning model, the model prediction is more in line with the actual physical process of geological disasters; establish an online learning and dynamic adjustment mechanism for the model, so that the system can continuously optimize the model parameters according to the newly collected monitoring data, adapt to environmental changes and the evolution of disaster characteristics, and improve the real-time and accuracy of early warning;
[0064] Enhanced visualization and interactivity: Develop advanced data visualization tools to allow users to explore historical disaster data sets through interactive interfaces, including time series analysis results, disaster patterns from cluster analysis, and the spatiotemporal distribution of model prediction results, enhancing users’ understanding of disaster trends and their ability to interpret warning information; Integrate the prediction results of machine learning models with geographic information systems (GIS) to generate dynamic risk maps and disaster evolution prediction maps, providing decision makers with intuitive risk assessment and emergency response recommendations, and supporting rapid and accurate decision making;
[0065] Through these deepening and improvement measures, the data storage and management module can not only better integrate and analyze historical disaster data, but also build a more accurate and dynamically adaptable geological disaster prediction system through in-depth integration with machine learning models, providing strong scientific and technological support for early warning and effective prevention and control of geological disasters;
[0066] 2. Dynamic optimization of features: dynamically adjust and optimize the feature set based on real-time monitoring data and model feedback, remove irrelevant or low-impact features, introduce newly discovered high-value features, and ensure the efficiency and predictive ability of the model; use time series derivative features and frequency domain feature extraction to enhance the model's sensitivity to weak changes in the rock mass and improve the ability to identify precursors of separation failure
[0067] 3. Real-time data analysis and prediction: Use Apache Kafka and Flink to process and analyze continuously flowing monitoring data, realize instant calculation and release of warning signals, and reduce processing delays; build a virtual environment to simulate different disaster scenarios, verify the accuracy and effectiveness of the warning model, optimize model parameters, and improve the adaptability to different types of disasters;
[0068] 4. Multi-source data fusion and cross-validation, integrating satellite remote sensing, drone monitoring, and ground sensor data for comprehensive analysis to improve the comprehensiveness and accuracy of the model's judgment on geological body stability; using k-fold cross-validation to evaluate the performance of the model on different subsets to ensure the stability and generalization ability of the model;
[0069] 5. Warning result explanation and feedback mechanism, providing a visual interface for warning results, clearly displaying key information such as warning level, affected area, and expected disaster extent, so that decision makers can quickly understand and take action; establishing a post-warning effect evaluation and feedback mechanism, collecting the matching degree between actual disaster occurrence and warning results, and continuously optimizing model algorithms and warning strategies;
[0070] Through the implementation of the above strategies, the data analysis and processing module can not only more keenly identify the precursors of separation and destruction of sliding-type dangerous rock masses, but also provide timely and accurate early warnings in complex and changeable geological environments, effectively assisting in disaster prevention and reducing the losses caused by disasters.
[0071] The warning information release module is used to calculate and trigger the warning signal in real time based on the analysis results of the data analysis and processing module and the preset threshold.
[0072] The monitoring module is used to provide managers with a visual interface to display monitoring data and warning status in real time.
[0073] Embodiment 2:
[0074] Following the same structure as detailed in the first embodiment, the difference from the first embodiment is that the data storage and management module can integrate the data to establish a historical disaster data set. The historical disaster data set identifies the seasonality and periodicity of disaster occurrence and its evolution trend over time by analyzing the time series data of historical disasters. The historical disaster data set identifies the typical characteristics and patterns of different disaster types by cluster analysis or time series analysis methods.
[0075] Integrate the data from the data storage and management module to establish a historical disaster data set, analyze the time series data of historical disasters, identify the seasonal and periodic laws of disasters, and their evolution trends over time; use cluster analysis or time series analysis methods to identify the typical characteristics and patterns of different disaster types, such as the terrain change pattern before a landslide and the early signs of a debris flow;
[0076] Specifically, the following steps are included:
[0077] 1. Data integration and construction of historical disaster datasets;
[0078] After receiving and storing the original monitoring data and pre-processed data, further integrate multi-source data, including but not limited to geological parameters, environmental data, meteorological information and historical disaster records, and ensure the comparability and compatibility of data from different sources and scales through data standardization, laying the foundation for subsequent analysis;
[0079] Using ARIMA and seasonal decomposition time series forecasting models to analyze the time series data of historical disasters, identify the seasonal patterns, periodic characteristics, and long-term trends of disasters, which helps predict the possibility of disasters occurring in a specific season or cycle and make preventive preparations in advance;
[0080] K-means, hierarchical clustering, and DBSCAN are used to group historical disaster data. Based on the geographical environment, scale, and influencing factors of the disaster, typical patterns of different disaster types are identified, such as the terrain deformation pattern before a landslide, the precipitation accumulation and terrain slope characteristics before a debris flow, etc. Combined with time series analysis, the clustering results are further refined to identify the early signs of specific disasters and improve the pertinence and predictability of early warnings.
[0081] 2. Optimization of risk assessment and early warning models;
[0082] Based on historical disaster data sets, correlation analysis, principal component analysis, random forest, and logistic regression are used to analyze the correlation between various factors and disaster occurrence, identify key risk factors, and optimize the input parameters of the early warning model;
[0083] Combine time series analysis and clustering results to dynamically adjust warning thresholds to ensure that the warning model can accurately reflect the risk level of disasters under current environmental and seasonal conditions. Formulate warning rules based on different disaster modes to achieve intelligent triggering of warning signals;
[0084] Establish a historical disaster case database, conduct retrospective analysis of early warning effects, and evaluate the accuracy and timeliness of early warning models. Based on the analysis results, continuously adjust and improve the early warning model to form a data-driven continuous optimization cycle;
[0085] 3. Technology and application expansion;
[0086] Integrate historical disaster data with the Geographic Information System (GIS) to conduct spatial distribution analysis and disaster impact range simulation, generate disaster risk maps, and provide intuitive support for disaster management decisions;
[0087] Combining macro and micro data to conduct multi-scale analysis can not only identify disaster trends in large areas, but also focus on small changes in specific locations, thus improving the level of refinement of early warning;
[0088] Through the above measures, the data storage and management module not only becomes the center of data integration and historical learning, but also provides a deeper analysis capability for the entire early warning system, effectively improving the scientificity and effectiveness of geological disaster early warning.
[0089] Embodiment three:
[0090] like Figure 3 As shown, following the same structure as detailed in Example 1, the difference from Example 1 is that an early warning method for geological disasters adopts the above-mentioned early warning system for geological disasters, and the early warning method for geological disasters includes the following steps:
[0091] S01. Data collection and preprocessing: Install vibration sensors, displacement sensors and meteorological monitoring equipment of the data collection module in the detection area to monitor the vibration frequency f, displacement x and slope θ of the rock mass in real time. Use the rock mass parameter measuring instrument used by the data collection module to collect rock samples in the detection area for detection to obtain the rock mass M.
[0092] The data preprocessing module cleans the collected data, converts the format to standardization, and aligns the data in time and space;
[0093] S02. Parameter calculation and stability assessment: Based on the principle of structural dynamics, the vibration differential equation of rock mass is:
[0094] Mx+Kx=0
[0095] Where M is the mass of the rock block and K is the stiffness coefficient.
[0096] According to the above formula, the stiffness coefficient K of the rock bridge is:
[0097] K=2πMf 2
[0098] Where: f is the natural vibration frequency.
[0099] The sliding force of the rock mass remains unchanged. According to the principle of mechanical equilibrium, we can get:
[0100] F R =F S =Mgsinθ
[0101] Among them: FR is the anti-slip force, Fs is the sliding force, and θ is the slope.
[0102] Based on the fact that the anti-slip force is composed of friction and adhesion, the friction can be obtained by the following formula:
[0103]
[0104] in: is the equivalent friction force, x is the displacement of the particle relative to the neutral point;
[0105] S03. Setting and monitoring of early warning thresholds: When the rock mass enters the separation stage from the stable stage, the friction force begins to be greater than 0. According to the above formula, we can get:
[0106] Mg sinθ-2πMf 2 x≥0
[0107] When the natural vibration frequency satisfies the following formula, the separation damage precursor warning is triggered:
[0108]
[0109] According to the above formula, the warning threshold of the natural vibration frequency separation stage is established, and the vibration frequency of the rock mass is continuously monitored and compared with the warning threshold. Once the monitored frequency is close to or lower than the warning threshold, the warning signal is immediately triggered;
[0110] S04. Warning release and response: When the system recognizes that the warning conditions have been met, the warning information will be released to relevant departments and local residents in a timely manner through the warning information release module. The warning information release module releases warning information in ways including but not limited to SMS, email and broadcast. The warning release and response also includes emergency plans, including but not limited to personnel evacuation, traffic control, and rescue team standby measures;
[0111] S05. Post-analysis and research: For each actual collapse event after the warning, the lead time of the warning, the degree of consistency between the actual collapse situation and the warning model are recorded and analyzed in detail. The warning model is continuously optimized based on measured data and disaster case analysis.
[0112] In the description of the present invention, it should be understood that the terms "upper", "lower", "left", "right", etc. indicate directions or positional relationships based on the directions or positional relationships shown in the accompanying drawings, and are only for the convenience of describing the present invention and simplifying the description, rather than indicating or implying that the device or element referred to must have a specific direction, and a specific direction structure and operation, and therefore, cannot be understood as a limitation on the present invention. In addition, "first" and "second" are only for descriptive purposes, and cannot be understood as indicating or implying relative importance or implicitly indicating the number of technical features indicated. Therefore, the features defined as "first" and "second" may explicitly or implicitly include one or more of the features. In the description of the present invention, unless otherwise specified, "multiple" means two or more.
[0113] In the description of the present invention, it should be noted that, unless otherwise clearly specified and limited, the terms "installed", "connected", "connected", etc. should be understood in a broad sense, for example, it can be a fixed connection, a detachable connection, or an integral connection; it can be a mechanical connection or an electrical connection; it can be a direct connection, or it can be an indirect connection through an intermediate medium, or it can be the internal communication of two components. For ordinary technicians in this field, the specific meanings of the above terms in the present invention can be understood according to specific circumstances.
[0114] The preferred embodiments of the present invention disclosed above are only used to help explain the present invention. The preferred embodiments do not describe all the details in detail, nor do they limit the invention to specific implementation methods. Obviously, many modifications and changes can be made according to the content of this specification. This specification selects and specifically describes these embodiments in order to better explain the principles and practical applications of the present invention, so that those skilled in the art can understand and use the present invention well. The present invention is limited only by the claims and their full scope and equivalents.
Claims
1. An early warning system for geological disasters, characterized in that: include: The data acquisition module is used to collect the original geological parameters and environmental data in the detection area in real time and transmit them to the data preprocessing module; A data preprocessing module, used for preprocessing the data transmitted by the data acquisition module and transmitting the data to the data storage and management module; A data storage and management module, used for receiving and storing data transmitted by the data acquisition module; The data analysis and processing module is used to call the geological parameters and environmental data in the data storage and management module, establish an early warning model, calculate and judge whether the critical state of separation damage is approaching or reached, obtain the empirical threshold, set the natural vibration frequency separation stage early warning threshold, and carry out early warning based on the identification of separation damage precursors; The warning information release module is used to calculate and trigger the warning signal in real time according to the analysis results of the data analysis and processing module and the preset threshold; The monitoring module is used to provide managers with a visual interface to display the data of the data storage and management module, as well as the analysis results of the early warning information release module and the signals that trigger the early warning in real time.
2. The early warning system for geological disasters according to claim 1, characterized in that: The data collected by the data acquisition module include rock parameter measuring instruments that collect physical property data, as well as vibration sensors, displacement sensors and meteorological monitoring equipment that collect geological environment parameters.
3. The early warning system for geological disasters according to claim 1, characterized in that: The data storage and management module can integrate the data and establish a historical disaster data set.
4. The early warning system for geological disasters according to claim 2, characterized in that: The rock mass parameter measuring instrument is used to obtain the quality of the rock block, and the vibration sensor, displacement sensor and meteorological monitoring equipment are used to collect the slope of the rock mass, the vibration frequency data and displacement data of the monitoring point.
5. The early warning system for geological disasters according to claim 3, characterized in that: The historical disaster dataset analyzes the time series data of historical disasters to identify the seasonal and cyclical patterns of disasters and their evolution trends over time.
6. The early warning system for geological disasters according to claim 5, characterized in that: Historical disaster datasets are used to identify typical characteristics and patterns of different disaster types through cluster analysis or time series analysis methods.
7. An early warning method for implementing the early warning system for geological disasters according to any one of claims 1 to 6, characterized in that: The method comprises the following steps: S01, data collection and preprocessing: Install the vibration sensor, displacement sensor and meteorological monitoring equipment of the data collection module in the detection area to monitor the vibration frequency, displacement and slope data of the rock mass in real time, use the rock mass parameter measuring instrument of the data collection module to collect rock block samples in the detection area for detection, and obtain the quality of the rock block. The data preprocessing module preprocesses the collected data and stores it in the data storage and management module; S02, parameter calculation and stability assessment: the data analysis and processing module uses the data from the data storage and management module to determine the collapse and instability criteria of sliding-type dangerous rock masses; S03. Warning threshold setting and monitoring: When the rock mass enters the separation stage from the stable stage, the friction force begins to be greater than 0, and the natural vibration frequency satisfies the following formula, the separation failure precursor warning is triggered: According to the above formula, the warning threshold of the natural vibration frequency separation stage is established, and the vibration frequency of the rock mass is continuously monitored and compared with the warning threshold. Once the monitored frequency is close to or lower than the warning threshold, the warning signal is immediately triggered; S04, warning release and response: When the warning information release module identifies that the warning conditions have been met, it will promptly release warning information to relevant departments and local residents; S05. Post-analysis and research: The early warning information release module records the actual collapse events after each warning in detail, and analyzes the lead time of the warning, the actual collapse situation and the degree of consistency with the early warning model. Based on the measured data and disaster case analysis, the early warning model is continuously optimized and displayed in the monitoring module.
8. The early warning system for geological disasters according to claim 7, characterized in that: Step S04: Warning release and response: The ways of releasing warning information include SMS, email and broadcast.
9. The early warning system for geological disasters according to claim 8, characterized in that: Step S04 warning release and response also includes emergency plans, which include personnel evacuation, traffic control, and rescue team standby measures.
Citation Information
Cited By
Risk pre-control decision support system for coal mine fire and gas disasters
CN119417242A
Traffic engineering geological disaster monitoring and early warning system
CN119559756A
Construction method and system for deep multi-source heterogeneous big database
CN120123440A
Geological investigation monitoring and early warning system and method
CN120179997A
A geological survey monitoring and early warning system and method
CN120179997B
