CN112906595A - Landslide prediction method and system based on elastic waves - Google Patents
Landslide prediction method and system based on elastic waves Download PDFInfo
- Publication number
- CN112906595A CN112906595A CN202110235669.9A CN202110235669A CN112906595A CN 112906595 A CN112906595 A CN 112906595A CN 202110235669 A CN202110235669 A CN 202110235669A CN 112906595 A CN112906595 A CN 112906595A
- Authority
- CN
- China
- Prior art keywords
- landslide
- elastic wave
- elastic
- prediction
- signal characteristics
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 36
- 238000000605 extraction Methods 0.000 claims abstract description 13
- 239000000284 extract Substances 0.000 claims description 6
- 238000007781 pre-processing Methods 0.000 claims description 6
- 230000000644 propagated effect Effects 0.000 claims description 4
- 230000004913 activation Effects 0.000 claims description 3
- 238000003491 array Methods 0.000 claims description 3
- 238000001914 filtration Methods 0.000 claims description 3
- 238000010606 normalization Methods 0.000 claims description 3
- 238000011176 pooling Methods 0.000 claims description 3
- 230000008569 process Effects 0.000 abstract description 5
- 239000002689 soil Substances 0.000 description 11
- 238000012544 monitoring process Methods 0.000 description 5
- 238000004458 analytical method Methods 0.000 description 3
- 230000000694 effects Effects 0.000 description 3
- 230000006399 behavior Effects 0.000 description 2
- 230000008859 change Effects 0.000 description 1
- 239000004927 clay Substances 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 238000006073 displacement reaction Methods 0.000 description 1
- 239000011159 matrix material Substances 0.000 description 1
- 230000007246 mechanism Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 239000002245 particle Substances 0.000 description 1
- 239000012466 permeate Substances 0.000 description 1
- 230000000750 progressive effect Effects 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 230000004044 response Effects 0.000 description 1
- 238000004162 soil erosion Methods 0.000 description 1
- 239000000758 substrate Substances 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2218/00—Aspects of pattern recognition specially adapted for signal processing
- G06F2218/08—Feature extraction
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/10—Services
- G06Q50/26—Government or public services
- G06Q50/265—Personal security, identity or safety
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Theoretical Computer Science (AREA)
- Tourism & Hospitality (AREA)
- Strategic Management (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Human Resources & Organizations (AREA)
- Economics (AREA)
- Marketing (AREA)
- Development Economics (AREA)
- General Business, Economics & Management (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Health & Medical Sciences (AREA)
- Educational Administration (AREA)
- General Health & Medical Sciences (AREA)
- Signal Processing (AREA)
- Artificial Intelligence (AREA)
- Primary Health Care (AREA)
- General Engineering & Computer Science (AREA)
- Computer Security & Cryptography (AREA)
- Game Theory and Decision Science (AREA)
- Entrepreneurship & Innovation (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Pit Excavations, Shoring, Fill Or Stabilisation Of Slopes (AREA)
- Testing Or Calibration Of Command Recording Devices (AREA)
Abstract
The invention discloses a landslide prediction method based on elastic waves, which is applied to the technical field of landslide prediction and comprises the following specific steps: constructing a multi-target landslide probability prediction model; acquiring elastic wave signals transmitted in the side slope; picking up the signal characteristics of the elastic wave signals by using a characteristic extraction network; and the signal characteristics are brought into an equation of the multi-target landslide probability prediction model to judge whether landslide occurs or not. The invention discloses a landslide prediction system and a method based on elastic waves, which are used for constructing a multi-target landslide prediction model, determining a prediction result by utilizing the wave speeds of the elastic waves at different moments, greatly improving the prediction precision, dividing the elastic wave propagation process into different time periods by utilizing a division principle, respectively calculating the wave speeds, judging whether the landslide occurs, substituting historical data into the multi-target landslide probability prediction model, determining the wave speed threshold of the elastic waves with the landslide, and determining whether the landslide occurs according to the duration time of the different wave speeds and the current wave speed.
Description
Technical Field
The invention relates to the technical field of landslide prediction, in particular to a landslide prediction method and system based on elastic waves.
Background
At present, landslide is one of the main geological disasters, and a great amount of casualties and property loss are caused in the world every year. The most advanced landslide monitoring and forecasting system is applied to monitoring the side slope on the regional scale, and the method has important significance for predicting the occurrence of the rainfall type landslide. Therefore, it is urgently needed to monitor the slope with potential landslide hazard, provide early warning for the potentially disaster-stricken people, and provide reference for analysis and disaster relief.
To date, a variety of slope monitoring techniques have been widely used as early warning systems. Further, the elastic wave characteristics contain a large amount of information about the stress state of the soil. The nondestructive analysis of soil mechanics by using elastic wave waves is increasingly applied to geological engineering. Since the elastic wave velocity in soil can reflect its internal mechanical state, the elastic wave velocity has been used to characterize the soil mechanical state, such as clay rheological behavior, stacking layer geometry, shear modulus, poisson's ratio, loosening ring depth, soil erosion, soil moisture content, soil deformation, and slope displacement. Researches find that the elastic wave characteristics can directly reflect the influence of the change of the boundary conditions on soil body response, slope behaviors and damage mechanisms.
However, in the prior art, due to the observed dimensions affecting the analysis, output and judgment, it is difficult to select the proper resolution of the digital elevation model, i.e., the selection of the pixel size, the grid resolution and the grid size. The occurrence of landslide cannot be accurately predicted by the remote sensing monitoring technology; acoustic emission signals generated by soil particles are weak, attenuation is fast, and application of a slope monitoring technology is limited. In the prior art, the landslide cannot be sensitively, continuously and remotely monitored in real time, and the landslide alarm broadcasting accuracy is poor; and the slope soil is generally in an unsaturated state, and the matrix suction contributes to the shear strength of most of soil. In the rainfall process, rainwater permeates into the slope surface, the substrate suction is reduced, and then the shear strength of the soil body is reduced. When the shear strength is reduced to a point where balance cannot be maintained, the slope slips. For the above, the prior art cannot make an accurate prediction.
Therefore, how to provide a method for predicting landslide disasters by using elastic waves is an urgent problem to be solved by those skilled in the art.
Disclosure of Invention
In view of this, the invention provides a landslide prediction method and a landslide prediction system based on elastic waves, which determine whether landslide occurs according to the wave speeds of the elastic waves at different moments, so that the prediction precision is greatly improved.
In order to achieve the above purpose, the invention provides the following technical scheme:
a landslide prediction method based on elastic waves comprises the following specific steps:
constructing a multi-target landslide probability prediction model;
acquiring elastic wave signals transmitted in the side slope;
picking up the signal characteristics of the elastic wave signals by using a characteristic extraction network;
and the signal characteristics are brought into an equation of the multi-target landslide probability prediction model to judge whether landslide occurs or not.
Through the technical scheme, the invention has the technical effects that: and a multi-target landslide prediction model is constructed, the prediction result is determined by using the wave velocity of the elastic wave at different moments, and the prediction precision is greatly improved.
Preferably, in the elastic wave-based landslide prediction method, the multi-target landslide probability prediction model is expressed as
Wherein, t0Is an initial time t1The next time, H, to the initial time0For the elastic wave at t0Propagation distance of time, H1For the elastic wave at t1The propagation distance at a time, V, is the wave velocity of the elastic wave, alphanIs the current elastic wave velocity coefficient.
Through the technical scheme, the invention has the technical effects that: the method divides the elastic wave propagation process into different time periods by utilizing the division principle, and respectively calculates the wave velocity.
Preferably, in the method for predicting elastic wave-based landslide, the feature extraction network includes four convolutional layers, and each convolutional layer includes a batch normalization unit, a maximum pooling unit, and an activation function.
Preferably, in the method for predicting a landslide based on an elastic wave, the signal features are two-dimensional arrays at different time instants.
Preferably, in the method for predicting a landslide based on an elastic wave, a current elastic wave velocity coefficient α isnIs determined according to the duration of the current wave velocity, and alpha0+α1+...+αn＝1。
Through the technical scheme, the invention has the technical effects that: the duration of the current wave velocity is used as a weighting factor of the current wave velocity, and when a certain velocity is accumulated to a certain degree, landslide can also be caused.
Preferably, in the method for predicting landslide based on elastic waves, whether landslide occurs is judged, historical data is substituted into the multi-target landslide probability prediction model, and an elastic wave speed threshold value of landslide occurs is determined.
An elastic wave-based landslide prediction system comprising: the system comprises an elastic wave emitter, a data acquisition module, a landslide probability prediction module, a data comparison module and a data output module; the elastic wave transmits the elastic wave to the area to be predicted; the data acquisition module picks up elastic wave signals propagated in the side slope and extracts signal characteristics; the landslide probability prediction module is used for inputting the signal characteristics, comparing the signal characteristics with an elastic wave speed threshold value by using the data comparison module, judging whether landslide occurs or not and outputting the landslide through the data output module.
Preferably, in the elastic wave-based landslide prediction system described above, the data acquisition module includes: the device comprises a feature extraction network, a preprocessing unit, a receiving unit and a sending unit; the receiving unit receives the elastic wave signal; denoising and filtering are carried out through the preprocessing unit; and the characteristic extraction network extracts the signal characteristics of the elastic wave signal and sends the signal characteristics to the landslide probability prediction module through the sending unit.
According to the technical scheme, compared with the prior art, the invention discloses and provides a landslide prediction system and method based on elastic waves, a multi-target landslide prediction model is built, the wave velocities of the elastic waves at different moments are utilized to determine the prediction result, the prediction precision is greatly improved, the elastic wave propagation process is divided into different time periods by utilizing the dividing principle, the wave velocities are respectively calculated, whether the landslide occurs or not is judged, historical data are substituted into the multi-target landslide probability prediction model, the elastic wave velocity threshold value of the landslide occurs is determined, and whether the landslide occurs or not is determined according to the duration time of the different wave velocities and the current wave velocity.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, it is obvious that the drawings in the following description are only embodiments of the present invention, and for those skilled in the art, other drawings can be obtained according to the provided drawings without creative efforts.
FIG. 1 is a flow chart of the process of the present invention;
FIG. 2 is a block diagram of the present invention.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
The embodiment of the invention discloses a landslide prediction method based on elastic waves, which comprises the following specific steps of:
s101, constructing a multi-target landslide probability prediction model;
s102, acquiring an elastic wave signal propagated in the slope;
s103, utilizing the characteristic extraction network to pick up the signal characteristics of the elastic wave signals;
and S104, substituting the signal characteristics into an equation of the multi-target landslide probability prediction model, and judging whether the landslide occurs.
To further optimize the above technical processThe probability prediction model of target landslide is expressed as
Wherein, t0Is an initial time t1The next time, H, to the initial time0For the elastic wave at t0Propagation distance of time, H1For the elastic wave at t1The propagation distance at a time, V, is the wave velocity of the elastic wave, alphanIs the current elastic wave velocity coefficient.
In order to further optimize the above technical method, the feature extraction network comprises four convolutional layers, and each convolutional layer comprises a batch normalization unit, a maximum pooling unit and an activation function.
In order to further optimize the above technical method, the signal features are two-dimensional arrays at different times.
In order to further optimize the above technical method, the current elastic wave velocity coefficient alphanIs determined according to the duration of the current wave velocity, and alpha0+α1+...+αn＝1。
In order to further optimize the technical method, whether the landslide occurs or not is judged, historical data are substituted into the multi-target landslide probability prediction model, and the elastic wave speed threshold value of the landslide is determined.
An elastic wave based landslide prediction system, as shown in fig. 2, comprising: the system comprises an elastic wave emitter, a data acquisition module, a landslide probability prediction module, a data comparison module and a data output module; the elastic wave transmits the elastic wave to the area to be predicted; the data acquisition module picks up elastic wave signals propagated in the slope and extracts signal characteristics; the landslide probability prediction module is internally input with signal characteristics, and compares the signal characteristics with an elastic wave speed threshold value by using a data comparison module to judge whether landslide occurs or not and outputs the landslide through a data output module.
In order to further optimize the above technical method, the data acquisition module comprises: the device comprises a feature extraction network, a preprocessing unit, a receiving unit and a sending unit; the receiving unit receives an elastic wave signal; denoising and filtering are carried out through a preprocessing unit; the characteristic extraction network extracts the signal characteristics of the elastic wave signals and sends the signal characteristics to the landslide probability prediction module through the sending unit.
The embodiments in the present description are described in a progressive manner, each embodiment focuses on differences from other embodiments, and the same and similar parts among the embodiments are referred to each other. The device disclosed by the embodiment corresponds to the method disclosed by the embodiment, so that the description is simple, and the relevant points can be referred to the method part for description.
The previous description of the disclosed embodiments is provided to enable any person skilled in the art to make or use the present invention. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the generic principles defined herein may be applied to other embodiments without departing from the spirit or scope of the invention. Thus, the present invention is not intended to be limited to the embodiments shown herein but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.
Claims (8)
1. A landslide prediction method based on elastic waves is characterized by comprising the following specific steps:
constructing a multi-target landslide probability prediction model;
acquiring elastic wave signals transmitted in the side slope;
picking up the signal characteristics of the elastic wave signals by using a characteristic extraction network;
and the signal characteristics are brought into an equation of the multi-target landslide probability prediction model to judge whether landslide occurs or not.
2. The elastic wave-based landslide prediction method according to claim 1, wherein the multi-objective landslide probability prediction model is expressed as
Wherein, t0Is an initial time t1The next time instant which is the initial time instant,H0for the elastic wave at t0Propagation distance of time, H1For the elastic wave at t1The propagation distance at a time, V, is the wave velocity of the elastic wave, alphanIs the current elastic wave velocity coefficient.
3. The method of claim 1, wherein the feature extraction network comprises four convolutional layers, and each convolutional layer comprises a batch normalization unit, a max-pooling unit, and an activation function.
4. The method according to claim 1, wherein the signal features are two-dimensional arrays at different times.
5. The method of claim 2, wherein the current elastic wave velocity coefficient α is anIs determined according to the duration of the current wave velocity, and alpha0+α1+...+αn＝1。
6. The method as claimed in claim 2, wherein the occurrence of landslide is determined, and historical data is substituted into the multi-target landslide probability prediction model to determine the elastic wave speed threshold value of landslide.
7. An elastic wave-based landslide prediction system comprising: the system comprises an elastic wave emitter, a data acquisition module, a landslide probability prediction module, a data comparison module and a data output module; the elastic wave transmits the elastic wave to the area to be predicted; the data acquisition module picks up elastic wave signals propagated in the slope and extracts signal characteristics; the landslide probability prediction module is used for inputting the signal characteristics, comparing the signal characteristics with an elastic wave speed threshold value by using the data comparison module, judging whether landslide occurs or not and outputting the landslide through the data output module.
8. The elastic wave-based landslide prediction system of claim 7, wherein said data acquisition module comprises: the device comprises a feature extraction network, a preprocessing unit, a receiving unit and a sending unit; the receiving unit receives the elastic wave signal; denoising and filtering are carried out through the preprocessing unit; and the characteristic extraction network extracts the signal characteristics of the elastic wave signal and sends the signal characteristics to the landslide probability prediction module through the sending unit.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110235669.9A CN112906595A (en) | 2021-03-03 | 2021-03-03 | Landslide prediction method and system based on elastic waves |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110235669.9A CN112906595A (en) | 2021-03-03 | 2021-03-03 | Landslide prediction method and system based on elastic waves |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN112906595A true CN112906595A (en) | 2021-06-04 |
Family
ID=76108214
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110235669.9A Pending CN112906595A (en) | 2021-03-03 | 2021-03-03 | Landslide prediction method and system based on elastic waves |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112906595A (en) |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110208022A (en) * | 2019-06-12 | 2019-09-06 | 济南雷森科技有限公司 | Power equipment multiple features audio-frequency fingerprint fault diagnosis method and system based on machine learning |
| CN110243413A (en) * | 2019-06-27 | 2019-09-17 | 浙江大学 | A kind of monitoring device and monitoring method of hypergravity centrifugal model physical state |
| CN110259442A (en) * | 2019-06-28 | 2019-09-20 | 重庆大学 | A kind of coal measure strata hydraulic fracturing disrupted beds position recognition methods |
| CN110363963A (en) * | 2019-07-05 | 2019-10-22 | 中国矿业大学(北京) | A kind of rain-induced landslide early warning system based on Elastic Wave Velocity |
| CN110363151A (en) * | 2019-07-16 | 2019-10-22 | 中国人民解放军海军航空大学 | Based on the controllable radar target detection method of binary channels convolutional neural networks false-alarm |
| CN110426458A (en) * | 2019-07-05 | 2019-11-08 | 中国矿业大学(北京) | A kind of new method and monitoring system using Elastic Wave Velocity prediction landslide |
-
2021
- 2021-03-03 CN CN202110235669.9A patent/CN112906595A/en active Pending
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110208022A (en) * | 2019-06-12 | 2019-09-06 | 济南雷森科技有限公司 | Power equipment multiple features audio-frequency fingerprint fault diagnosis method and system based on machine learning |
| CN110243413A (en) * | 2019-06-27 | 2019-09-17 | 浙江大学 | A kind of monitoring device and monitoring method of hypergravity centrifugal model physical state |
| CN110259442A (en) * | 2019-06-28 | 2019-09-20 | 重庆大学 | A kind of coal measure strata hydraulic fracturing disrupted beds position recognition methods |
| CN110363963A (en) * | 2019-07-05 | 2019-10-22 | 中国矿业大学(北京) | A kind of rain-induced landslide early warning system based on Elastic Wave Velocity |
| CN110426458A (en) * | 2019-07-05 | 2019-11-08 | 中国矿业大学(北京) | A kind of new method and monitoring system using Elastic Wave Velocity prediction landslide |
| CN110363151A (en) * | 2019-07-16 | 2019-10-22 | 中国人民解放军海军航空大学 | Based on the controllable radar target detection method of binary channels convolutional neural networks false-alarm |
Non-Patent Citations (2)
| Title |
|---|
| YULONG CHEN等: "Development of elastic wave velocity threshold for rainfall-induced landslide prediction and early warning", 《LANDSLIDES》, pages 955 - 968 * |
| 陈宇龙等: "基于弹性波波速的降雨型滑坡预警系统", 《岩土力学》, vol. 40, no. 09, pages 3373 - 3386 * |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111623722B (en) | Multi-sensor-based slope deformation three-dimensional monitoring system and method | |
| US11859365B2 (en) | System for bridge scour multi-source monitoring, monitoring method thereof, and scour depth evaluating method thereof | |
| KR101788104B1 (en) | System and method for real-time early warning for extreme rainfall-induced landslides | |
| MX2012008316A (en) | Method and system for automated location dependent natural disaster forecast. | |
| Baart et al. | Using 18th century storm-surge data from the Dutch Coast to improve the confidence in flood-risk estimates | |
| Benjamin et al. | Emergent characteristics of rockfall inventories captured at a regional scale | |
| CN114611778B (en) | Reservoir water level early warning method and system based on warehousing flow | |
| CN114333249A (en) | Landslide early warning method and device | |
| CN114298549A (en) | Water conservancy safety monitoring system and method based on big data | |
| CN115116202A (en) | Landslide disaster early warning method, device, equipment and readable storage medium | |
| Karunarathna et al. | Linkages between sediment composition, wave climate and beach profile variability at multiple timescales | |
| CN103197046A (en) | Method for measuring volume water content of debris flow critical soil body and debris flow pre-warning method | |
| Esposito et al. | Evaluation of geomorphic changes and retreat rates of a coastal pyroclastic cliff in the Campi Flegrei volcanic district, southern Italy | |
| CN113566894A (en) | Geological disaster monitoring method, system, terminal and medium based on Internet of things | |
| CN110398775B (en) | Tunnel water burst disaster micro-seismic event signal fluctuation first arrival pickup method and system | |
| CN116796571A (en) | Rock structural stress prediction system based on acoustic emission characteristics | |
| Ceresetti et al. | Multiscale evaluation of extreme rainfall event predictions using severity diagrams | |
| CN115100819A (en) | Landslide hazard early warning method and device based on big data analysis and electronic equipment | |
| Chen et al. | Analysis of storm surge characteristics based on stochastic process | |
| CN116990847B (en) | Beidou GNSS receiver resolving method and system based on edge calculation | |
| CN112906595A (en) | Landslide prediction method and system based on elastic waves | |
| CN110796310A (en) | Method and system for predicting susceptibility to regional geological disasters | |
| CN109905190B (en) | Modeling method for low-frequency ground wave propagation time delay variation characteristic | |
| CN115457739A (en) | Geological disaster early warning method and device, electronic equipment and storage medium | |
| Callaghan et al. | Comparing extreme water levels using different techniques and impact of climate indices |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |