Digital twin prevention method and system for geological disasters

Abstract

The present invention relates to a digital twin prevention method and system for geological disasters, the method comprising: constructing an information perception network; establishing a basic database; constructing a cumulative displacement prediction model; predicting the changing trend and maximum cumulative displacement of geological disaster points; decomposing the cumulative displacement; obtaining the cumulative displacement prediction result; constructing a multi-factor early warning model; calculating and pushing the early warning level in real time; determining the safety status of the geological disaster point, simulating the stable state and deformation evolution trend of the geological disaster point under different working conditions; and pushing the geological disaster safety prevention and control plan. The system comprises monitoring perception, prediction, early warning, rehearsal and plan modules. Based on digital twin technology, the present invention realizes online monitoring of geological disasters, early prediction of geological disaster deformation development and changes, timely early warning and pushing early warning information, real-time rehearsal simulation of geological disaster deformation and destruction trends, and automatic pushing of geological disaster plan response measures, which can effectively improve the intelligent level of geological disaster prevention and meet the needs of intelligent prevention and management of geological disasters.

Description

Technical Field

[0001] The present invention relates to the field of geological disaster information, and specifically to a geological disaster digital twin prevention method and system. Background Art

[0002] Unexpected geological disasters such as collapses, landslides, and debris flows occur frequently, often causing significant loss of life and property. While engineering solutions are only a minority, scientific prevention is crucial. Currently, China primarily uses technologies such as manual inspections, deformation monitoring, prediction and early warning, and numerical simulation to identify and prevent geological disaster risks. Manual inspections and deformation monitoring are not always timely, preventing the timely detection and early warning of geological disaster risks. Prediction and early warning can predict the occurrence of geological disaster risks, but accuracy is generally low, and the prediction and early warning models cannot automatically update. Numerical simulations also lack real-time performance. In short, existing technologies make it difficult to identify and detect geological disaster risks in advance, and it is impossible to achieve real-time prediction and early warning, simulation, and emergency response based on changes in external geological disaster conditions.

[0003] To address the aforementioned shortcomings of existing technologies, the present invention proposes a digital twin method and system for geological disaster prevention. This system enables online monitoring of geological disasters, advance prediction of deformation and development, timely warning and push notifications, real-time simulation of geological disaster deformation and damage trends, and automatic push notifications of emergency response measures, effectively improving the intelligent level of geological disaster prevention. Summary of the Invention

[0004] The purpose of the present invention is to provide a digital twin prevention method and system for geological disasters.

[0005] In order to achieve the above object, the present invention adopts the following technical solutions:

[0006] A digital twin prevention method for geological disasters includes the following steps:

[0007] S1. Build an information perception network for automatic geological hazard monitoring, manual observation, and collective prevention based on the needs and characteristics of geological hazard projects;

[0008] S2. Collect monitoring and observation data of geological disaster sites and establish a basic geological disaster database;

[0009] S3. Construct a geological disaster cumulative displacement prediction model based on variational mode decomposition and machine learning algorithms;

[0010] S4. Predict the change trend and maximum cumulative displacement of geological hazard sites within the next 7 days based on the cumulative displacement prediction model;

[0011] S4.1. Decompose the accumulated displacement of the landslide into trend, periodic, and random displacement components;

[0012] S4.2. Expand the predictions for the components and obtain the cumulative displacement prediction result after superposition. The cumulative displacement is decomposed according to the following formula:

[0013] S t =T t +P t +R t

[0014] Where: S t is the cumulative displacement, T t is the displacement component of the trend term, P t is the periodic displacement component, R t is the random displacement component;

[0015] S5. Based on the preprocessing of monitoring data, a strategy-based multi-factor early warning model is constructed based on early warning criteria such as reservoir water level, deformation rate of geological hazard body, and critical rainfall;

[0016] S6. Combined with the geological disaster prevention system, calculate and push the warning level of geological disaster points in real time; the critical rainfall threshold is calculated according to the following formula:

[0017] E=c+α×I β

[0018] Where: E is the cumulative rainfall, mm; I is the rainfall intensity of the landslide-inducing rainfall event, with the peak rainfall intensity taken for short duration and the average rainfall intensity taken for long duration, mm / h; α and β are statistical parameters, c is a constant, c ≥ 0.

[0019] S7. Determine the safety status of geological hazard sites based on the warning level. For high-risk sites, construct a finite element simulation model of the geological hazard site based on fluid-structure coupling theory. Use the geological hazard prevention system to simulate the stability and deformation evolution trends of the geological hazard site under different working conditions.

[0020] S8. Based on the early warning and stability status of geological disaster sites and combined with the geological disaster safety knowledge base, the system automatically pushes geological disaster safety prevention and control plans.

[0021] Furthermore, the monitoring data include rainfall, air temperature, groundwater level, reservoir or river water level, surface displacement, deep displacement, surface cracks and ground stress; the observation data include deformation signs of surface buildings, development trends of surface cracks and changes in the inclination of surface trees.

[0022] Furthermore, in step S4, based on the cumulative displacement prediction model and the historical displacement monitoring data, the change trend and maximum cumulative displacement of the geological disaster point in the next 7 days are predicted.

[0023] Furthermore, the multi-factor early warning model can formulate different early warning strategies and early warning thresholds according to regional characteristics.

[0024] A geological disaster digital twin prevention system, comprising:

[0025] The monitoring and perception module is used to access real-time data such as deformation, groundwater level, and rainfall at geological disaster sites through automatic monitoring, manual monitoring, and group monitoring and prevention. After filtering and noise reduction, the monitoring data is automatically stored in the geological disaster database.

[0026] The safety prediction module is used to build a displacement prediction model based on variational mode decomposition and machine learning algorithms. Based on the displacement prediction model and monitoring data, it predicts the change trend and maximum displacement of the geological disaster site within the next 7 days or 2 weeks.

[0027] The safety warning module sets warning thresholds based on factors such as deformation, reservoir water level, and rainfall at the disaster site, constructs a disaster warning model, and automatically calculates the warning level through warning strategy calculation. The warning level is divided into four levels: red, orange, yellow, and blue. Based on monitoring data such as deformation, reservoir water level, and rainfall, the disaster warning model calculates and pushes the warning level of the disaster site in real time.

[0028] The safety rehearsal module is used to construct a finite element calculation model of the geological disaster body. The calculation model is divided into two parts: the sliding body and the sliding bed, and the corresponding material properties are assigned to each part. The calculation model is meshed using three-dimensional tetrahedral pore pressure elements. After setting constraints and loads on the model, fluid-solid coupling analysis and calculation are performed. Through parameter calibration, a finite element simulation rehearsal model of the geological disaster point is constructed. For high warning levels, the stability coefficient and displacement, stress, and strain contour cloud maps of the geological disaster point under different working conditions are simulated online based on the simulation rehearsal model.

[0029] The safety plan module is used to build a geological disaster safety knowledge base based on geological disaster emergency plans, treatment cases, threshold experience and other knowledge; based on the warning and stability status of geological disaster points, combined with the geological disaster safety knowledge base, it pushes geological disaster safety prevention and control plans in real time.

[0030] The present invention has the following beneficial effects:

[0031] Digital twins fully utilize data from physical models, sensor updates, operational history, and other data to integrate multidisciplinary, multi-physical, multi-scale, and multi-probability simulation processes, completing mapping in virtual space to reflect the entire lifecycle of the corresponding entity. Based on digital twin technology, this invention constructs a prevention method and system platform that integrates geological disaster information perception, geological disaster forecasting, geological disaster warning, geological disaster rehearsal, and geological disaster emergency plans. This platform enables online monitoring of geological disasters, advance prediction of geological disaster deformation development and changes, timely warning and push notification of warning information, real-time rehearsal simulation of geological disaster deformation and damage trends, and automatic push notification of geological disaster emergency plan response measures. This effectively improves the intelligent level of geological disaster prevention and meets the needs of intelligent geological disaster prevention and management.

[0032] Field tests have shown that the adoption of this invention can achieve "four predictions": prediction - early prediction and forecast of geological disasters; early warning - timely early warning of geological disasters and pushing warning level information to relevant personnel for decision-making; rehearsal - simulation of geological disasters according to different working conditions; and emergency plan - automatic push of relevant emergency plan response measures according to the current or future status of geological disasters.

[0033] During the water storage process of a certain large reservoir 170, the present invention played a positive role in ensuring the safety of the reservoir area from geological disasters and produced significant economic and social benefits. BRIEF DESCRIPTION OF THE DRAWINGS

[0034] Figure 1 is a flow chart of the present invention;

[0035] Figure 2 This is a schematic diagram of the structure of the strategy-based multi-factor early warning model for geological disasters of the present invention;

[0036] Figure 3 Schematic diagram of a landslide simulation preview model based on finite element method of the present invention;

[0037] Figure 4 Schematic diagram of the system structure of the present invention. DETAILED DESCRIPTION

[0038] The present invention will be further described in detail below with reference to the accompanying drawings and specific examples, but these examples should not be construed as limiting the present invention.

[0039] A digital twin prevention method for geological disasters includes the following steps:

[0040] S1. Build an information perception network for automatic geological hazard monitoring, manual observation, and collective prevention based on the needs and characteristics of geological hazard projects;

[0041] S2. Collect monitoring and observation data of geological disaster sites and establish a basic geological disaster database;

[0042] S3. Construct a geological disaster cumulative displacement prediction model based on variational mode decomposition and machine learning algorithms;

[0043] S4. Predict the change trend and maximum cumulative displacement of geological hazard sites within the next 7 days based on the cumulative displacement prediction model;

[0044] S4.1. Decompose the accumulated displacement of the landslide into trend, periodic, and random displacement components;

[0045] S4.2. Expand the predictions for the components and obtain the cumulative displacement prediction result after superposition. The cumulative displacement is decomposed according to the following formula:

[0046] S t =T t +P t +R t

[0047] Where: S t is the cumulative displacement, T t is the displacement component of the trend term, P t is the periodic displacement component, R t is the random displacement component;

[0048] S5. Based on the preprocessing of monitoring data, a strategy-based multi-factor early warning model is constructed based on early warning criteria such as reservoir water level, deformation rate of geological hazard body, and critical rainfall;

[0049] S6. Combined with the geological disaster prevention system, calculate and push the warning level of geological disaster points in real time; the critical rainfall threshold is calculated according to the following formula:

[0050] E=c+α×I β

[0051] Where: E is the cumulative rainfall, mm; I is the rainfall intensity of the landslide-inducing rainfall event, with the peak rainfall intensity taken for short duration and the average rainfall intensity taken for long duration, mm / h; α and β are statistical parameters, c is a constant, c ≥ 0.

[0052] S7. Determine the safety status of geological hazard sites based on the warning level. For high-risk sites, construct a finite element simulation model of the geological hazard site based on fluid-structure coupling theory. Use the geological hazard prevention system to simulate the stability and deformation evolution trends of the geological hazard site under different working conditions.

[0053] S8. Based on the early warning and stability status of geological disaster sites and combined with the geological disaster safety knowledge base, the system automatically pushes geological disaster safety prevention and control plans.

[0054] A preferred embodiment is: in the above scheme, the monitoring data include rainfall, air temperature, groundwater level, reservoir or river water level, surface displacement, deep displacement, surface cracks and ground stress; the observation data include deformation signs of surface buildings, development trends of surface cracks and changes in the inclination of surface trees.

[0055] A preferred embodiment is: in step S4 of the above solution, based on the cumulative displacement prediction model and historical displacement monitoring data, the change trend and maximum cumulative displacement of the geological disaster point in the next 7 days are predicted.

[0056] A preferred embodiment is: in the above solution, the multi-factor early warning model can formulate different early warning strategies and early warning thresholds according to regional characteristics.

[0057] A geological disaster digital twin prevention system, comprising:

[0058] The monitoring and perception module is used to access real-time data such as deformation, groundwater level, and rainfall at geological disaster sites through automatic monitoring, manual monitoring, and group monitoring and prevention. After filtering and noise reduction, the monitoring data is automatically stored in the geological disaster database.

[0059] The safety prediction module is used to build a displacement prediction model based on variational mode decomposition and machine learning algorithms. Based on the displacement prediction model and monitoring data, it predicts the change trend and maximum displacement of the geological disaster site within the next 7 days or 2 weeks.

[0060] The safety warning module sets warning thresholds based on factors such as deformation, reservoir water level, and rainfall at the disaster site, constructs a disaster warning model, and automatically calculates the warning level through warning strategy calculation. The warning level is divided into four levels: red, orange, yellow, and blue. Based on monitoring data such as deformation, reservoir water level, and rainfall, the disaster warning model calculates and pushes the warning level of the disaster site in real time.

[0061] The safety rehearsal module is used to construct a finite element calculation model of the geological disaster body. The calculation model is divided into two parts: the sliding body and the sliding bed, and the corresponding material properties are assigned to each part. The calculation model is meshed using three-dimensional tetrahedral pore pressure elements. After setting constraints and loads on the model, fluid-solid coupling analysis and calculation are performed. Through parameter calibration, a finite element simulation rehearsal model of the geological disaster point is constructed. For high warning levels, the stability coefficient and displacement, stress, and strain contour cloud maps of the geological disaster point under different working conditions are simulated online based on the simulation rehearsal model.

[0062] The safety plan module is used to build a geological disaster safety knowledge base based on geological disaster emergency plans, treatment cases, threshold experience and other knowledge; based on the warning and stability status of geological disaster points, combined with the geological disaster safety knowledge base, it pushes geological disaster safety prevention and control plans in real time.

[0063] The contents not described in detail in this specification belong to the prior art known to those skilled in the art.

Claims

1. A digital twin prevention method for geological disasters, comprising the following steps: S1. Build an information perception network for automatic geological hazard monitoring, manual observation, and collective prevention based on the needs and characteristics of geological hazard projects; S2. Collect monitoring and observation data of geological disaster sites and establish a basic geological disaster database; S3. Construct a geological disaster cumulative displacement prediction model based on variational mode decomposition and machine learning algorithms; S4. Predict the change trend and maximum cumulative displacement of geological hazard sites within the next 7 days based on the cumulative displacement prediction model; S4.

1. Decompose the accumulated displacement of the landslide into trend, periodic, and random displacement components; S4.

2. Expand the predictions for the components and obtain the cumulative displacement prediction result after superposition. The cumulative displacement is decomposed according to the following formula: ， Where: S t is the cumulative displacement, T t is the displacement component of the trend term, P t is the periodic displacement component, R t is the random displacement component; S5. Based on the preprocessing of monitoring data, a strategy-based multi-factor early warning model is constructed based on the reservoir water level, deformation rate of the geological hazard body, and critical rainfall warning criteria; S6. Combined with the geological disaster prevention system, calculate and push the early warning level of geological disaster points in real time; The critical rainfall threshold is calculated according to the following formula: ， Where: E is the cumulative rainfall, mm; I is the rainfall intensity of the landslide-inducing rainfall event, with the peak rainfall intensity taken for short duration and the average rainfall intensity taken for long duration, mm / h; α and β are statistical parameters, c is a constant, c ≥ 0; S7. Determine the safety status of geological hazard sites based on the warning level. For high-risk sites, construct a finite element simulation model of the geological hazard site based on fluid-structure coupling theory. Use the geological hazard prevention system to simulate the stability and deformation evolution trends of the geological hazard site under different working conditions. S8. Based on the early warning and stability status of geological disaster sites and combined with the geological disaster safety knowledge base, the system automatically pushes geological disaster safety prevention and control plans.

2. The digital twin prevention method for geological disasters according to claim 1, characterized in that: The monitoring data include rainfall, air temperature, groundwater level, reservoir or river water level, surface displacement, deep displacement, surface cracks and ground stress; the observation data include deformation signs of surface buildings, development trends of surface cracks and changes in the inclination of surface trees.

3. The digital twin prevention method for geological disasters according to claim 1 or 2, characterized in that: In step S4, based on the cumulative displacement prediction model and historical displacement monitoring data, the change trend and maximum cumulative displacement of the geological disaster point in the next 7 days are predicted.

4. The digital twin prevention method for geological disasters according to claim 1 or 2, characterized in that: The multi-factor early warning model can formulate different early warning strategies and early warning thresholds according to regional characteristics.

5. The digital twin prevention method for geological disasters according to claim 3, characterized in that: The multi-factor early warning model can formulate different early warning strategies and early warning thresholds according to regional characteristics.

6. A geological disaster digital twin prevention system, characterized by: include: The monitoring and perception module is used to access deformation, groundwater level, and rainfall data of automatic monitoring, manual monitoring, and group monitoring and prevention of geological disasters in real time; after filtering and noise reduction, the monitoring data is automatically stored in the geological disaster database; The safety prediction module is used to build a displacement prediction model based on variational mode decomposition and machine learning algorithms. Based on the displacement prediction model and monitoring data, it predicts the change trend and maximum displacement of the geological disaster site within the next 7 days or 2 weeks. The safety warning module is used to set warning thresholds based on the deformation, reservoir water level, and rainfall factors of the geological disaster point, build a geological disaster warning model, and automatically calculate the warning level through the warning strategy solution; The warning levels are divided into four levels: red, orange, yellow and blue; Based on deformation, reservoir water level, and rainfall monitoring data, the geological disaster early warning model calculates and pushes the early warning level of geological disaster points in real time; The safety rehearsal module is used to construct a finite element calculation model of the geological disaster body. The calculation model is divided into two parts: the sliding body and the sliding bed, and the corresponding material properties are assigned to each part. The calculation model is meshed using three-dimensional tetrahedral pore pressure elements. After setting constraints and loads on the model, fluid-solid coupling analysis and calculation are performed. Through parameter calibration, a finite element simulation rehearsal model of the geological disaster point is constructed. For high warning levels, the stability coefficient and displacement, stress, and strain contour cloud maps under different working conditions of the disaster site are simulated online based on the simulation preview model; The safety plan module is used to build a geological disaster safety knowledge base based on geological disaster emergency plans, treatment cases, and threshold experience knowledge; Based on the early warning and stability status of geological disaster sites and combined with the geological disaster safety knowledge base, geological disaster safety prevention and control plans are pushed in real time.

Images