Slope stability early warning method based on multi-source monitoring data change

By deploying multi-source monitoring equipment and data fusion technology, combining real-time and historical data analysis, hierarchical warning signals are generated, and the inaccuracy of slope stability monitoring caused by a single data source is solved, and the warning accuracy of slope landslide disasters is improved. and timely.

CN119091594APending Publication Date: 2024-12-06CHONGQING UNIV
View PDF 0 Cites 7 Cited by

Patent Information

Application Number
CN202411045267.2
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-08-01
Publication Date
2024-12-06

AI Technical Summary

Technical Problem

The existing slope stability monitoring and early warning systems rely on a single type of monitoring data, resulting in early warning errors and untimely nature, lack of comprehensive analysis and fusion processing of multi-source data, making it difficult to accurately predict slope stability changes.

Method used

Deploy multi-source monitoring equipment, such as geological sensors, weather stations and remote sensing equipment, perform data preprocessing and fusion, combine real-time data analysis and historical data model prediction, generate hierarchical early warning signals and issue responses, and improve the accuracy of slope stability early warning and timely.

Benefits of technology

Through multi-source data fusion and advanced analysis algorithms, early signals of slope stability changes are identified, accurate hierarchical early warning signals are generated, and disasters such as slope landslides are reduced, which improves the accuracy and timeliness of early warnings.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN119091594A_ABST
    Figure CN119091594A_ABST
Patent Text Reader

Abstract

The invention discloses a slope stability early warning method based on multi-source monitoring data change, and relates to the technical field of geological disaster monitoring and early warning, and the method comprises the following steps: S1, deploying a plurality of monitoring devices such as a geological sensor, a meteorological station and a remote sensing device, and collecting the multi-source monitoring data of a slope region such as geological, meteorological and remote sensing images in real time; s2, cleaning, format conversion and abnormal value processing are carried out on the collected original monitoring data, and the data quality is ensured to adapt to follow-up analysis; s3, comprehensively processing data of different monitoring sources by using a data fusion technology, reducing errors of a single data source, and improving data reliability; according to the invention, by deploying the multi-source monitoring equipment, carrying out data preprocessing and fusion, combining real-time data analysis and historical data model prediction, generating a graded early warning signal and issuing a response, the accuracy and timeliness of slope stability early warning are improved, and occurrence of disasters such as slope landslide and the like is effectively reduced.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention relates to the technical field of geological disaster monitoring and early warning, and in particular to a slope stability early warning method based on changes in multi-source monitoring data. Background Art

[0002] Slope landslide is one of the common geological disasters in nature, which poses a great threat to human life and property safety. Especially in mining areas, mountainous areas, along highways, etc., slope landslides occur frequently and are more harmful. Therefore, timely and effective monitoring and early warning of slope stability are crucial to reduce the occurrence of landslide disasters.

[0003] At present, the slope stability monitoring and early warning system mainly relies on a single type of monitoring data, such as geological sensor data, meteorological data or remote sensing images. However, the information from a single data source is often insufficient to fully reflect the actual situation of the slope, which can easily lead to early warning errors and affect the accuracy and timeliness of the early warning. For example, monitoring based solely on geological sensor data may not be able to timely reflect the impact of meteorological factors such as rainfall on slope stability; while monitoring using meteorological data or remote sensing images alone may ignore the impact of geological changes on slope stability. In terms of slope monitoring technology, there have been many studies and applications. For example, geological sensors can monitor slope displacement, deformation, soil moisture and other parameters in real time; meteorological stations can provide meteorological data such as rainfall, temperature and humidity; remote sensing technology can obtain high-resolution slope images through satellites or drones to detect small changes in the surface. These technologies have improved the accuracy and timeliness of slope monitoring to a certain extent, but due to the lack of comprehensive analysis of multi-source data, there is still a lot of room for improvement.

[0004] In addition, the existing slope early warning system also has certain limitations in data processing and analysis. Traditional data processing methods mostly use simple statistical analysis or experience-based discrimination methods, lack of fusion processing and comprehensive analysis of multi-source data, and it is difficult to accurately predict the stability changes of slopes. With the development of artificial intelligence and big data technology, the application of machine learning algorithms in slope monitoring and early warning has gradually increased, but the application of these technologies is still in its infancy and has failed to fully utilize the advantages of multi-source data. Summary of the invention

[0005] The present invention provides a slope stability early warning method based on changes in multi-source monitoring data. The present invention deploys multi-source monitoring equipment, performs data preprocessing and fusion, combines real-time data analysis with historical data model prediction, generates graded early warning signals and issues responses, thereby improving the accuracy and timeliness of slope stability early warnings and effectively reducing the occurrence of disasters such as slope landslides.

[0006] In order to achieve the above object, the present invention provides the following technical solution: a slope stability early warning method based on changes in multi-source monitoring data, comprising the following steps:

[0007] S1. Deploy geological sensors, meteorological stations, remote sensing equipment and other monitoring equipment to collect multi-source monitoring data of the slope area such as geology, meteorology and remote sensing images in real time;

[0008] S2. Clean, convert, and process outliers of the collected raw monitoring data to ensure data quality for subsequent analysis;

[0009] S3. Use data fusion technology to comprehensively process data from different monitoring sources, reduce the error of a single data source, and improve data reliability;

[0010] S4. Use advanced data analysis algorithms to conduct real-time analysis of pre-processed multi-source monitoring data to identify early signals of slope stability changes;

[0011] S5. Compare and analyze real-time data with historical monitoring data, and combine mathematical models and machine learning algorithms to predict the possibility of slope stability changes;

[0012] S6. Generate graded warning signals based on real-time analysis results and model predictions, and determine the warning level for timely response;

[0013] S7. Issue early warning information to relevant departments and personnel via SMS, email and early warning system platform, and provide detailed warning content and response measures.

[0014] Preferably, in step S1, equipment deployment: deploying geological sensors D in the slope area geo 、Weather Station D meteo , Remote sensing equipment D remote , data collection: G(t)={G1(t),G2(t),…,G n (t)}, where G(t) is the geological data set at time t, G1(t) to G n (t) represents the data collected by different geological sensors; M(t) = {M1(t), M2(t), …, M n (t)}, where M(t) is the meteorological data set at time t, M1(t) to M n (t) is the data collected by different weather stations, R(t) = {R1(t), R2(t), …, R n (t)}, where R(t) is the remote sensing data set at time t, R1(t) to R n (t) Data collected by different remote sensing equipment.

[0015] Preferably, in step S2, data cleaning: D(t)=G(t)∪M(t)∪R(t)-N(t), wherein D(t) is the valid data set after preprocessing at time t, and the noise data N(t) is removed, and data in different formats are converted into a unified format F(D(t)): F(D(t))=Convert(D(t)), wherein F(D(t)) is the data set after format conversion, ensuring that all data are represented in a unified format; outlier processing: detect and process the outlier A(t) to obtain the cleaned data C(t): C(t)=D(t)-A(t), wherein C(t) is the cleaned data set at time t, and the outlier A(t) is removed.

[0016] Preferably, in step S3, the data from different monitoring sources are fused to reduce the error of a single data source: fusion (t) = Fusion(C(t)), where F fusion (t) is the fused data set at time t, Fusion(C(t)) is the data fusion operation, and the purpose of data fusion is to integrate different types of data into a unified model.

[0017] Preferably, in step S4, a trend analysis algorithm is used to analyze the data change trend and identify early signals: T(t) = Trend(F fusion (t)), where T(t) is the trend analysis result at time t, Trend(F fusion (t)) is a trend analysis algorithm; this algorithm identifies early signals that may lead to slope instability by analyzing the trend of data changes over time, and then uses an anomaly detection algorithm to detect abnormal changes in the data and identify abnormal events: A detect (t)=Anomaly(F fusion (t)), where A detect (t) is the anomaly detection result at time t, Anomaly(F fusion (t)) is an anomaly detection algorithm that identifies potential slope stability issues by detecting outliers and abnormal patterns in the data.

[0018] Preferably, in step S5, a regression analysis model is used to perform regression analysis and prediction based on historical data and real-time data to evaluate future slope stability: R predict (t)=Regression(H(t),F fusion (t)), where R predict (t) is the regression prediction result at time t, Regression(H(t),F fusion(t)) is a regression analysis model; the regression model uses historical data H(t) and real-time fusion data Regression(H(t),F fusion (t)) to predict and evaluate the stability of the future slope; then use the machine learning model and machine learning algorithm to make predictions: ML predict (t)=MLModel(H(t),F fusion (t)), where ML predict (t) is the machine learning prediction result at time t, MLMode l(H(t),F fusion (t)) is a machine learning model. The machine learning model uses historical data and real-time data to make predictions through training algorithms to provide more accurate slope stability assessment.

[0019] Preferably, in step S6, logistic regression warning: using a logistic regression algorithm to generate a warning signal, and judging whether there is a risk on the slope based on the analysis result: logistic (t)=LogisticRegression(T(t),A detect (t),R predict (t),ML predict (t)), where W logistic (t) is the early warning signal based on logistic regression at time t, LogisticRegression(T(t),A detect (t),R predict (t),ML predict (t)) is a logistic regression algorithm, which generates warning signals by analyzing trends, anomaly detection, regression prediction and machine learning results to determine whether there is a risk on the slope; then, a Bayesian network is used for warning: a Bayesian network is used to generate warning signals and a slope risk is assessed through probability inference: W bayes (t) = BayesianNetwork(T(t),A detect (t),R predict (t),ML predict (t)); where W bayes (t) is the early warning signal based on the Bayesian network at time t, BayesianNetwork(T(t),A detect (t),R predict (t),ML predict (t)) is a Bayesian network algorithm; the Bayesian network constructs a probability model, comprehensively analyzes various types of data, evaluates slope risks and generates early warning signals.

[0020] Preferably, in step S7, warning information is released through multiple channels, such as text messages, emails, etc., to ensure that relevant departments and personnel receive warnings in a timely manner:publ ish (t) = Public (W logistic (t),W bayes (t)), where, I publ ish (t) is the warning information released at time t, and Publish is the information release operation; this step releases the warning information to relevant departments and personnel through multiple channels (such as SMS, email, warning system platform, etc.) to ensure that the warning information can be conveyed in time: R action (t)=Response(W logistic (t),W bayes (t)), where R action (t) is the response measure at time t, and response is the response measure generation rule. The specific response measures are as follows: If W logistic (t) or W bayes (t) indicates low risk, then regular monitoring and assessment of slope conditions is recommended;

[0021] If W logistic (t) or W bayes (t) indicates a medium risk and preventive measures are recommended, such as adding monitoring equipment or reducing activities in the slope area.

[0022] If W logistic (t) or W bayes (t) indicates high risk, which means it is recommended to evacuate relevant personnel immediately and take emergency measures, such as reinforcing slopes or setting up cordons, to prevent disasters.

[0023] In the above technical scheme, the technical effects and advantages provided by the present invention are as follows: the present invention deploys multi-source monitoring equipment, performs data preprocessing and fusion, combines real-time data analysis with historical data model prediction, generates graded warning signals and issues responses, thereby improving the accuracy and timeliness of slope stability warnings and effectively reducing the occurrence of disasters such as slope landslides. BRIEF DESCRIPTION OF THE DRAWINGS

[0024] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments recorded in the present invention. For ordinary technicians in this field, other drawings can also be obtained based on these drawings.

[0025] Figure 1 The module diagram of the slope stability early warning method based on multi-source monitoring data changes of the present invention is shown. DETAILED DESCRIPTION

[0026] Example embodiments will now be described more fully with reference to the accompanying drawings. However, example embodiments can be implemented in a variety of forms and should not be construed as limited to the examples set forth herein; rather, these example embodiments are provided so that the description of the present disclosure will be more comprehensive and complete, and the concept of the example embodiments will be fully conveyed to those skilled in the art.

[0027] The present invention provides Figure 1 A slope stability early warning method based on changes in multi-source monitoring data is shown, comprising the following steps: S1, deploying a variety of monitoring equipment such as geological sensors, meteorological stations, and remote sensing equipment to collect multi-source monitoring data of the slope area such as geology, meteorology, and remote sensing images in real time;

[0028] S2. Clean, convert, and process outliers of the collected raw monitoring data to ensure data quality for subsequent analysis;

[0029] S3. Use data fusion technology to comprehensively process data from different monitoring sources, reduce the error of a single data source, and improve data reliability;

[0030] S4. Use advanced data analysis algorithms to conduct real-time analysis of pre-processed multi-source monitoring data to identify early signals of slope stability changes;

[0031] S5. Compare and analyze real-time data with historical monitoring data, and combine mathematical models and machine learning algorithms to predict the possibility of slope stability changes;

[0032] S6. Generate graded warning signals based on real-time analysis results and model predictions, and determine the warning level for timely response;

[0033] S7. Issue early warning information to relevant departments and personnel through SMS, email and early warning system platform, and provide detailed early warning content and response measures; First, deploy a variety of monitoring equipment in the slope area, including geological sensors, meteorological stations and remote sensing equipment. Geological sensors are mainly used to monitor geological changes in slopes, such as soil moisture, surface displacement, seismic activity, etc. These data are crucial to understanding the stability of slopes. Meteorological stations are used to monitor meteorological data, including rainfall, temperature, wind speed and humidity, which also have an important impact on the stability of slopes. Remote sensing equipment obtains remote sensing images of slopes through remote sensing technology, which can detect small changes in the surface, such as the generation and expansion of cracks. Real-time collection of geological data, meteorological data and remote sensing images can provide a comprehensive data basis for subsequent data analysis. The geological data set contains data from multiple geological sensors, the meteorological data set contains data from multiple meteorological stations, and the remote sensing data set contains data from multiple remote sensing devices. These data sets can reflect the real-time status of the slope and provide accurate data support for subsequent early warning analysis.

[0034] In step S2, data cleaning: D(t) = G(t)∪M(t)∪R(t)-N(t), where D(t) is the valid data set after preprocessing at time t, and the noise data N(t) is removed. The data in different formats are converted into a unified format F(D(t)): F(D(t)) = Convert(D(t)), where F(D(t)) is the data set after format conversion, ensuring that all data are represented in a unified format; outlier processing: detect and process the outlier A(t) to obtain the cleaned data C(t): C(t) = D(t)-A(t), where C(t) is the cleaned data set at time t, and the outlier A(t) is removed; the collected data usually contains some noise and outliers, which will affect the subsequent analysis results, so data preprocessing is required. Data cleaning is the first step of data preprocessing, which retains valid data by removing noise data. This step can use filtering algorithms to identify and delete noise data to ensure the accuracy of the data. Format conversion is the second step of data preprocessing, which converts data in different formats into a unified format for subsequent processing and analysis. For example, different sensors may generate data in different formats, and format conversion can unify these data into a standard format. Outlier processing is the third step of data preprocessing, which further cleans the data by detecting and processing outliers. Outlier processing can use statistical methods or machine learning algorithms to identify outliers in the data and process or delete them to ensure the reliability and integrity of the data. The preprocessed data set contains valid data after cleaning, removes noise and outliers, and provides a high-quality data foundation for subsequent data fusion and analysis.

[0035] In step S3, the data from different monitoring sources are fused to reduce the error of a single data source: fusion (t) = Fusion(C(t)), where F fusion(t) is the fused data set at time t, Fusion (C (t)) is the data fusion operation, the purpose of data fusion is to integrate different types of data into a unified model; data fusion is the process of comprehensive processing of data from different monitoring sources, the purpose is to reduce the error caused by a single data source, and improve the reliability and integrity of the data. In the process of data fusion, it is necessary to integrate data from geological sensors, meteorological stations and remote sensing equipment. Data fusion can use a variety of technologies, such as Kalman filtering, Bayesian networks, etc., through which different types of data can be integrated into a unified model. Kalman filtering is an algorithm for processing uncertain data in dynamic systems. It can reduce the error of a single data source by weighted averaging the data of multiple sensors. Bayesian network is a probabilistic model that can improve the reliability of data by building relationships between different data sources and comprehensively analyzing various types of data. The result of data fusion is a unified data set that contains comprehensive data from all monitoring sources, providing a reliable data basis for subsequent real-time data analysis.

[0036] In step S4, the trend analysis algorithm is used to analyze the data change trend and identify early signals: T(t) = Trend(F fusion (t)), where T(t) is the trend analysis result at time t, Trend(F fusion (t)) is a trend analysis algorithm; this algorithm identifies early signals that may lead to slope instability by analyzing the trend of data changes over time, and then uses an anomaly detection algorithm to detect abnormal changes in the data and identify abnormal events: A detect (t)=Anomaly(F fusion (t)), where

[0037] A detect (t) is the anomaly detection result at time t, Anomaly(F fusion(t)) is an anomaly detection algorithm, which identifies potential slope stability problems by detecting outliers and abnormal patterns in the data; real-time data analysis is the process of real-time analysis of preprocessed and fused data, with the goal of identifying early signals and abnormal events of slope stability changes. Trend analysis algorithms are used to analyze the changing trends of data. By modeling and analyzing the changes in data over time, early signals of slope stability changes can be identified. For example, by analyzing the changing trends of geological sensor data, information such as slope displacement changes and soil moisture changes can be identified. Anomaly detection algorithms are used to detect abnormal changes in data. By performing statistical analysis and pattern recognition on the data, abnormal points and abnormal patterns in the data can be identified. For example, by analyzing meteorological data, abnormal rainfall and temperature changes can be identified, which may affect the stability of the slope. The results of real-time data analysis are identified trends and abnormal information, which provide important references for subsequent historical data analysis and model prediction.

[0038] In step S5, the regression analysis model is used to perform regression analysis and prediction based on historical data and real-time data to evaluate the future slope stability: R predict (t)=Regression

[0039] (H(t),F fusion (t)), where R predict (t) is the regression prediction result at time t, Regression(H(t),F fusion (t)) is a regression analysis model; the regression model uses historical data H(t) and real-time fusion data Regression(H(t),F fusion (t)) to predict and evaluate the stability of the future slope; then use the machine learning model and machine learning algorithm to make predictions: ML predict (t)=MLModel(H(t),F fusion (t)), where ML predict (t) is the machine learning prediction result at time t, MLModel(H(t),F fusion(t)) is a machine learning model. The machine learning model uses historical data and real-time data for prediction through training algorithms to provide a more accurate assessment of slope stability. Historical data and model prediction is the process of analyzing and predicting using historical data and real-time data, with the purpose of evaluating the stability of future slopes. The regression analysis model can predict future changes in slope stability by performing regression analysis on historical data and real-time data. The regression analysis model can use methods such as linear regression and multivariate regression to predict future trends by establishing the relationship between historical data and real-time data. The machine learning model can make more accurate predictions through training algorithms such as decision trees and support vector machines. The decision tree algorithm classifies data into different leaf nodes by building a tree structure for prediction. The support vector machine algorithm classifies data into different categories by building a hyperplane for prediction. The machine learning model can provide a more accurate assessment of slope stability by training and learning a large amount of historical data and real-time data. The result of the model prediction is an assessment of future changes in slope stability, which provides an important basis for the generation of early warning signals.

[0040] In step S6, logistic regression warning: use the logistic regression algorithm to generate a warning signal, and determine whether there is a risk on the slope based on the analysis results: logistic (t)=LogisticRegression(T(t),A detect (t),R predict (t),ML predict (t)), where W logistic (t) is the early warning signal based on logistic regression at time t, LogisticRegression

[0041] (T(t),A detect (t),R predict (t),ML predict (t)) is a logistic regression algorithm, which generates warning signals by analyzing trends, anomaly detection, regression prediction and machine learning results to determine whether there is a risk on the slope; then, a Bayesian network is used for warning: a Bayesian network is used to generate warning signals and a slope risk is assessed through probability inference: W bayes (t) = BayesianNetwork(T(t),A detect (t),R predict (t),ML predict (t)); where W bayes (t) is the early warning signal based on the Bayesian network at time t, BayesianNetwork

[0042] (T(t),A detect (t),R predict(t),ML predict (t)) is a Bayesian network algorithm; Bayesian network constructs a probability model, comprehensively analyzes various types of data, evaluates slope risks and generates warning signals; warning signal generation is the process of generating warning signals using the results of real-time data analysis and model prediction. Logistic regression warning generates warning signals through the logistic regression algorithm, and judges whether there is a risk on the slope based on the analysis results. The logistic regression algorithm generates warning signals by analyzing trends, anomaly detection, regression prediction and machine learning results to judge whether there is a risk on the slope. Bayesian network warning generates warning signals through the Bayesian network and evaluates slope risks through probabilistic inference. Bayesian network constructs a probability model, comprehensively analyzes various types of data, evaluates slope risks and generates warning signals. Warning signals are divided into different levels and classified according to the size of the risk. Low risk means that the slope is basically stable, medium risk means that there is a certain risk on the slope and preventive measures need to be taken, and high risk means that there is a greater risk on the slope and emergency measures need to be taken immediately. The result of warning signal generation is a graded warning signal, which provides a basis for the release and response of warning information.

[0043] In step S7, the warning information is released through multiple channels, such as text messages, emails, etc., to ensure that relevant departments and personnel receive the warning in time: publ ish (t) = Public (W logistic (t),W bayes (t)), where, I publ ish (t) is the warning information released at time t, and Publish is the information release operation; this step releases the warning information to relevant departments and personnel through multiple channels (such as SMS, email, warning system platform, etc.) to ensure that the warning information can be conveyed in time: R action (t)=Response(W logistic (t),W bayes (t)), where R action (t) is the response measure at time t, and response is the response measure generation rule. The specific response measures are as follows: If W logistic (t) or W bayes (t) indicates low risk, then regular monitoring and assessment of slope conditions is recommended;

[0044] If W logistic (t) or W bayes (t) indicates a medium risk and preventive measures are recommended, such as adding monitoring equipment or reducing activities in the slope area.

[0045] If W logistic (t) or W bayes(t) indicates high risk, it is recommended to evacuate relevant personnel immediately and take emergency measures, such as reinforcing the slope or setting up a cordon, to prevent disasters; warning information release and response is to release the generated warning signal through multiple channels and take corresponding response measures according to the warning signal. Information release releases warning information to relevant departments and personnel through multiple channels such as text messages and emails to ensure that the warning information can be conveyed in a timely manner. The purpose of warning information release is to enable relevant departments and personnel to understand the risk status of the slope in a timely manner and take corresponding measures. Response measures provide detailed response measures and suggestions based on the warning signal. If the warning signal indicates low risk, it is recommended to monitor and evaluate the slope condition regularly. If the warning signal indicates medium risk, it is recommended to take preventive measures, such as adding monitoring equipment or reducing activities in the slope area. If the warning signal indicates high risk, it is recommended to evacuate relevant personnel immediately and take emergency measures, such as reinforcing the slope or setting up a cordon, to prevent disasters. The purpose of the response measures is to reduce the occurrence of disasters such as slope landslides and ensure the safety of people and property.

[0046] The above embodiments are implemented in whole or in part by software, hardware, firmware or any other combination. When implemented using software, the above embodiments are implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions or computer programs. When the computer instructions or computer programs are loaded or executed on a computer, the process or function described in the embodiment of the present application is generated in whole or in part. The computer is a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions are stored in a computer-readable storage medium, or transmitted from one computer-readable storage medium to another computer-readable storage medium, for example, the computer instructions are transmitted from one website site, computer, server or data center to another website site, computer, server or data center by wired (e.g., infrared, wireless, microwave, etc.) mode. The computer-readable storage medium is any available medium that a computer can access or a data storage device such as a server or data center containing one or more available media sets. The available medium is a magnetic medium (e.g., a floppy disk, a hard disk, a tape), an optical medium (e.g., a DVD), or a semiconductor medium. The semiconductor medium is a solid-state hard disk.

[0047] It should be understood that in the various embodiments of the present application, the size of the serial numbers of the above-mentioned processes does not mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present application.

[0048] Those skilled in the art will clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices and units described above refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0049] The units described as separate components are or are not physically separated, and the components shown as units are or are not physical units, that is, located in one place or distributed on multiple network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0050] In addition, each functional unit in each embodiment of the present application is integrated into one processing unit, each unit exists physically separately, or two or more units are integrated into one unit.

[0051] If the functions are implemented in the form of software functional units and sold or used as independent products, they are stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application is essentially or partly in other words, the part that contributes to the prior art or part of the technical solution is embodied in the form of a software product, and the computer software product is stored in a storage medium, including several instructions for enabling a computer device (such as a personal computer, a server, or a network device) to perform all or part of the steps of the methods described in each embodiment of the present application. The aforementioned storage medium includes: various media for storing program codes, such as USB flash drives, mobile hard disks, read-only memories (ROM), random access memories (RAM), magnetic disks or optical disks.

[0052] The above description is only a specific implementation manner of the present application, but the protection scope of the present application is not limited thereto. Any technician familiar with the technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application.

Claims

1. A slope stability early warning method based on changes in multi-source monitoring data, characterized in that: The following steps are involved: S1. Deploy geological sensors, meteorological stations, remote sensing equipment and other monitoring equipment to collect multi-source monitoring data of the slope area such as geology, meteorology and remote sensing images in real time; S2. Clean, convert, and process outliers of the collected raw monitoring data to ensure data quality for subsequent analysis; S3. Use data fusion technology to comprehensively process data from different monitoring sources, reduce the error of a single data source, and improve data reliability; S4. Use advanced data analysis algorithms to conduct real-time analysis of pre-processed multi-source monitoring data to identify early signals of slope stability changes; S5. Compare and analyze real-time data with historical monitoring data, and combine mathematical models and machine learning algorithms to predict the possibility of slope stability changes; S6. Generate graded warning signals based on real-time analysis results and model predictions, and determine the warning level for timely response; S7. Issue early warning information to relevant departments and personnel via SMS, email and early warning system platform, and provide detailed warning content and response measures.

2. The slope stability early warning method based on multi-source monitoring data changes according to claim 1 is characterized in that: In step S1, equipment deployment: deploy geological sensors D in the slope area geo 、Weather Station D meteo , Remote sensing equipment D remote , data collection: G(t)={G1(t),G2(t),…,G n (t)}, where G(t) is the geological data set at time t, G1(t) to G n (t) represents the data collected by different geological sensors; M(t) = {M1(t), M2(t), …, M n (t)}, where M(t) is the meteorological data set at time t, M1(t) to M n (t) is the data collected by different weather stations, R(t) = {R1(t), R2(t), …, R n (t)}, where R(t) is the remote sensing data set at time t, R1(t) to R n (t) Data collected by different remote sensing equipment.

3. The slope stability early warning method based on multi-source monitoring data changes according to claim 1 is characterized in that: In step S2, data cleaning: D(t)=G(t)∪M(t)∪R(t)-N(t), where D(t) is the valid data set after preprocessing at time t, and the noise data N(t) is removed. Data in different formats are converted into a unified format F(D(t)): F(D(t))=Convert(D(t)), where F(D(t)) is the data set after format conversion, ensuring that all data are represented in a unified format; outlier processing: detect and process the outlier A(t) to obtain the cleaned data C(t): C(t)=D(t)-A(t), where C(t) is the cleaned data set at time t, and the outlier A(t) is removed.

4. The slope stability early warning method based on multi-source monitoring data changes according to claim 1 is characterized in that: In step S3, the data from different monitoring sources are fused to reduce the error of a single data source: fusion (t) = Fusion(C(t)), where F fusion (t) is the fused data set at time t, Fusion(C(t)) is the data fusion operation, and the purpose of data fusion is to integrate different types of data into a unified model.

5. The slope stability early warning method based on multi-source monitoring data changes according to claim 1 is characterized in that: In step S4, the trend analysis algorithm is used to analyze the data change trend and identify early signals: T(t) = Trend(F fusion (t)), where T(t) is the trend analysis result at time t, Trend(F fusion (t)) is a trend analysis algorithm; this algorithm identifies early signals that may lead to slope instability by analyzing the trend of data changes over time, and then uses an anomaly detection algorithm to detect abnormal changes in the data and identify abnormal events: A detect (t)=Anomaly(F fusion (t)), where A detect (t) is the anomaly detection result at time t, Anomaly(F fusion (t)) is an anomaly detection algorithm that identifies potential slope stability issues by detecting outliers and abnormal patterns in the data.

6. The slope stability early warning method based on multi-source monitoring data changes according to claim 1 is characterized in that: In step S5, the regression analysis model is used to perform regression analysis and prediction based on historical data and real-time data to evaluate the future slope stability: R predict (t)=Regression(H(t),F fusion (t)), where R predict (t) is the regression prediction result at time t, Regression(H(t),F fusion (t)) is a regression analysis model; the regression model uses historical data H(t) and real-time fusion data Regression(H(t),F fusion (t)) to predict and evaluate the stability of the future slope; then use the machine learning model and machine learning algorithm to make predictions: ML predict (t)=MLModel(H(t),F fusion (t)), where ML predict (t) is the machine learning prediction result at time t, MLModel(H(t),F fusion (t)) is a machine learning model. The machine learning model uses historical data and real-time data to make predictions through training algorithms to provide more accurate slope stability assessment.

7. The slope stability early warning method based on multi-source monitoring data changes according to claim 1 is characterized in that: In step S6, logistic regression warning: use the logistic regression algorithm to generate a warning signal, and determine whether there is a risk on the slope based on the analysis results: logistic (t)=LogisticRegression(T(t),A detect (t),R predict (t),ML predict (t)), where W logistic (t) is the early warning signal based on logistic regression at time t, LogisticRegression(T(t),A detect (t),R predict (t),ML predict (t)) is a logistic regression algorithm, which generates warning signals by analyzing trends, anomaly detection, regression prediction and machine learning results to determine whether there is a risk on the slope; then, a Bayesian network is used for warning: a Bayesian network is used to generate warning signals and a slope risk is assessed through probability inference: W bayes (t) = BayesianNetwork(T(t),A detect (t),R predict (t),ML predict (t)); where W bayes (t) is the early warning signal based on the Bayesian network at time t, BayesianNetwork(T(t),A detect (t),R predict (t),ML predict (t)) is a Bayesian network algorithm; the Bayesian network constructs a probability model, comprehensively analyzes various types of data, evaluates slope risks and generates early warning signals.

8. The slope stability early warning method based on multi-source monitoring data changes according to claim 1 is characterized in that: In step S7, the warning information is released through multiple channels, such as text messages, emails, etc., to ensure that relevant departments and personnel receive the warning in time: publish (t) = Publish(W logistic (t),W bayes (t)), where, I publish (t) is the warning information released at time t, and Publish is the information release operation; this step releases the warning information to relevant departments and personnel through multiple channels (such as SMS, email, warning system platform, etc.) to ensure that the warning information can be conveyed in time: R action (t)=Response(W logistic (t),W bayes (t)), where R action (t) is the response measure at time t, and response is the response measure generation rule. The specific response measures are as follows: If W logistic (t) or W bayes (t) indicates low risk, then regular monitoring and assessment of slope conditions is recommended; If W logistic (t) or W bayes (t) indicates a medium risk and preventive measures are recommended, such as adding monitoring equipment or reducing activities in the slope area. If W logistic (t) or W bayes (t) indicates high risk, which means it is recommended to evacuate relevant personnel immediately and take emergency measures, such as reinforcing slopes or setting up cordons, to prevent disasters.

Citation Information

Cited By

  • Geological monitoring and early warning method and system for geological investigation

    CN119395762A

  • A geological monitoring and early warning method and system for geological survey

    CN119395762B

  • Landslide geological disaster monitoring and early warning system based on multi-means fusion

    CN119580474A

  • Field geological exploration monitoring system based on remote sensing data

    CN119649587A

  • Remote automatic monitoring platform for slope deformation based on mountain railway engineering

    CN119809462A