CN117037424A - Single landslide early warning system and method - Google Patents
Single landslide early warning system and method Download PDFInfo
- Publication number
- CN117037424A CN117037424A CN202310837144.1A CN202310837144A CN117037424A CN 117037424 A CN117037424 A CN 117037424A CN 202310837144 A CN202310837144 A CN 202310837144A CN 117037424 A CN117037424 A CN 117037424A
- Authority
- CN
- China
- Prior art keywords
- landslide
- data
- displacement
- rainfall
- correlation
- 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 27
- 238000006073 displacement reaction Methods 0.000 claims abstract description 123
- 238000004422 calculation algorithm Methods 0.000 claims abstract description 78
- 238000004140 cleaning Methods 0.000 claims abstract description 29
- 238000007405 data analysis Methods 0.000 claims abstract description 26
- 238000012544 monitoring process Methods 0.000 claims abstract description 21
- 238000013524 data verification Methods 0.000 claims abstract description 20
- 238000004458 analytical method Methods 0.000 claims abstract description 18
- 239000000178 monomer Substances 0.000 claims abstract description 16
- 238000012545 processing Methods 0.000 claims abstract description 13
- 230000008859 change Effects 0.000 claims description 31
- 230000007613 environmental effect Effects 0.000 claims description 15
- 230000004927 fusion Effects 0.000 claims description 14
- 230000001133 acceleration Effects 0.000 claims description 12
- 238000010219 correlation analysis Methods 0.000 claims description 12
- 230000001360 synchronised effect Effects 0.000 claims description 12
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 claims description 12
- 238000013480 data collection Methods 0.000 claims description 10
- 238000004364 calculation method Methods 0.000 claims description 7
- 238000013145 classification model Methods 0.000 claims description 6
- 238000007418 data mining Methods 0.000 claims description 6
- 238000013507 mapping Methods 0.000 claims description 6
- 238000005070 sampling Methods 0.000 claims description 6
- 238000012163 sequencing technique Methods 0.000 claims description 6
- 238000012795 verification Methods 0.000 claims description 5
- 230000006641 stabilisation Effects 0.000 claims description 4
- 238000011105 stabilization Methods 0.000 claims description 4
- 238000013528 artificial neural network Methods 0.000 claims description 3
- 238000011156 evaluation Methods 0.000 claims description 3
- 239000003673 groundwater Substances 0.000 claims description 3
- 230000036541 health Effects 0.000 claims description 3
- 238000007689 inspection Methods 0.000 claims description 3
- 230000035772 mutation Effects 0.000 claims description 3
- 238000007637 random forest analysis Methods 0.000 claims description 3
- 239000002689 soil Substances 0.000 claims description 3
- 230000003068 static effect Effects 0.000 claims description 3
- 230000000694 effects Effects 0.000 abstract description 4
- 230000009286 beneficial effect Effects 0.000 abstract 1
- 230000007547 defect Effects 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 230000006698 induction Effects 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000003491 array Methods 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 238000013500 data storage Methods 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 230000015654 memory Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G08—SIGNALLING
- G08B—SIGNALLING OR CALLING SYSTEMS; ORDER TELEGRAPHS; ALARM SYSTEMS
- G08B21/00—Alarms responsive to a single specified undesired or abnormal condition and not otherwise provided for
- G08B21/02—Alarms for ensuring the safety of persons
- G08B21/10—Alarms for ensuring the safety of persons responsive to calamitous events, e.g. tornados or earthquakes
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/10—Pre-processing; Data cleansing
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/25—Fusion techniques
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
-
- G—PHYSICS
- G08—SIGNALLING
- G08B—SIGNALLING OR CALLING SYSTEMS; ORDER TELEGRAPHS; ALARM SYSTEMS
- G08B31/00—Predictive alarm systems characterised by extrapolation or other computation using updated historic data
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- General Physics & Mathematics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Evolutionary Computation (AREA)
- Artificial Intelligence (AREA)
- General Engineering & Computer Science (AREA)
- Evolutionary Biology (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Business, Economics & Management (AREA)
- Computing Systems (AREA)
- Emergency Management (AREA)
- Pit Excavations, Shoring, Fill Or Stabilisation Of Slopes (AREA)
- Geology (AREA)
- General Life Sciences & Earth Sciences (AREA)
- Health & Medical Sciences (AREA)
- Biomedical Technology (AREA)
- Biophysics (AREA)
- Computational Linguistics (AREA)
- General Health & Medical Sciences (AREA)
- Molecular Biology (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Testing Or Calibration Of Command Recording Devices (AREA)
- Environmental & Geological Engineering (AREA)
Abstract
The invention is applicable to the technical field of geological monitoring, and provides a single landslide early warning system and a single landslide early warning method, wherein the system comprises a data acquisition cleaning module, an algorithm model library, a data analysis module, a data verification module and an early warning module; the data acquisition cleaning module is used for processing monitoring data of a plurality of landslide; the algorithm model library is used for storing algorithm models for equipment correlation, earth surface displacement correlation and rainfall correlation; the data analysis module is used for carrying out related landslide warning analysis on equipment, ground displacement and rainfall related to the single landslide cause based on the monitoring data and the algorithm model library so as to generate early warning information, and the method has the beneficial effects that: the method can define specific alarm thresholds for different monomer landslide, and pre-judge landslide alarms by pre-judging values such as classification and rainfall so as to achieve the effect of early warning.
Description
Technical Field
The invention belongs to the technical field of geological monitoring, and particularly relates to a single landslide early warning system and method.
Background
The current main monomer landslide warning is mainly real-time warning, and the common method is to infer a general warning threshold value of a region according to the situation of the past year through expert experience, wherein the region is usually the size of a province or a ground city; the second method is to divide coarse granularity by rainfall, such as adopting rainfall landslide alarming threshold value divided according to national dimension internationally; or some domestic scholars calculate the threshold value of the single monomer landslide by a method for improving the tangential angle in recent years in Guizhou.
The applicant found by studying the above prior art: the former two methods have the defect of overlarge alarm area, and all three methods have the defect of incapable early warning.
Disclosure of Invention
The embodiment of the invention aims to provide a single landslide early warning system and a single landslide early warning method, which aim to solve the problems in the background technology.
The embodiment of the invention is realized in such a way that the single landslide early warning system comprises a data acquisition cleaning module, an algorithm model library, a data analysis module, a data verification module and an early warning module;
the data acquisition cleaning module is used for processing monitoring data of a plurality of landslide;
the algorithm model library is used for storing algorithm models for equipment correlation, earth surface displacement correlation and rainfall correlation;
the data analysis module is used for carrying out related landslide warning analysis on equipment, ground displacement and rainfall related to the single landslide cause based on the monitoring data and the algorithm model library so as to generate early warning information;
the data verification module is used for verifying the algorithm model in the algorithm model library and dynamically adjusting the algorithm verification period in a classified mode;
the early warning module is used for opening the early warning information to the outside and receiving the treatment feedback information.
As a further aspect of the present invention, the data collection and cleaning module is specifically configured to: the equipment log collection, the sensor data collection and the meteorological data are synchronized, and the equipment log collection, the sensor data collection and the meteorological data are also used for cleaning the collected and synchronized data, wherein,
the equipment log acquisition specifically comprises the following steps: acquiring an operation log of environmental data acquisition equipment deployed around a single landslide, wherein the operation log is used for judging the operation health state of the environmental data acquisition equipment;
the sensor data acquisition specifically comprises: acquiring relevant environmental data acquired by environmental data acquisition equipment deployed around a single landslide, wherein the relevant environmental data comprises the temperature, vertical earth surface displacement, horizontal earth surface displacement, displacement acceleration and underground water level of the environment;
the cleaning of the collected and synchronized data includes: and carrying out availability processing on the collected and synchronized data, wherein the availability processing comprises the following steps: removing dirty data, filling in empty data and changing unreasonable data.
As still further aspects of the present invention, the algorithm model library includes: the algorithm model library supports continuous data input of single landslide displacement correlation and rainfall correlation so as to output different parameter alarm thresholds of single landslide, wherein,
displacement correlation algorithm model: for a non-rainfall type single landslide, input data are historical monitoring displacement related data of the single landslide, a change rule between two groups of data including horizontal displacement, vertical displacement, displacement acceleration, inclination angle and first corresponding displacement is calculated through a first correlation algorithm, the first correlation algorithm comprises a classification, clustering, regression and association rule correlation algorithm in data mining, and the first corresponding displacement comprises: horizontal, vertical and resultant displacement;
rainfall-related algorithm model: the model aims at a rainfall type single landslide, input data are historical monitoring related data of the single landslide, a change rule between two groups of data including rainfall, water level change, soil humidity, water level change rate and second corresponding displacement is calculated through a second correlation algorithm, the second correlation algorithm comprises a classification, clustering, regression and association rule correlation algorithm in data mining, and the second corresponding displacement comprises: horizontal, vertical and combined displacement.
As a still further aspect of the present invention, the data analysis module is configured to: equipment reliability analysis, rainfall correlation analysis, surface displacement correlation analysis and hybrid analysis.
As a further aspect of the present invention, the data verification module is configured to: and (3) judging the landslide type, judging the landslide stage, judging the main influence factor of the landslide, judging the data acquisition period and verifying the landslide displacement.
As a further aspect of the present invention, in the data analysis module, the device reliability analysis includes: performing confidence evaluation analysis on the fault rate of the equipment and the collected fault data rate through a monitoring equipment log, and performing multiple data cleaning and inspection on the data collected by the equipment with the confidence lower than a preset value; the rainfall correlation analysis includes: the method comprises the steps of completing prediction of whether a single landslide is of a rainfall type and a non-rainfall type, and judging the correlation among rainfall, adjacent water areas, groundwater and landslide displacement by adopting a clustering algorithm in the operation so as to judge whether the single landslide is of a rainfall type; sorting importance of wading parameters affecting the single landslide displacement by adopting a classification model, and then predicting the change of the single landslide displacement along with the change of the important wading parameters by a regression model; the surface displacement correlation analysis includes: in the operation, a classification model is adopted to carry out importance sequencing on displacement parameters influencing the displacement of the single landslide, wherein the sequencing comprises displacement acceleration, displacement increment inclination angle and displacement rate; and then, predicting the change of the single landslide displacement along with the change of the important displacement parameters through a regression model, wherein the important displacement parameters at least comprise one, and the important displacement parameters are combined according to the importance of the displacement parameters.
As a further scheme of the invention, in the data verification module, the landslide type discrimination comprises the step of judging that the landslide deformation is changed into equipment false alarm, rainfall type or non-rainfall type by calling the calculation result in the data analysis module; the landslide stage discrimination comprises the step of judging the landslide type through a time sequence model in an algorithm model, wherein the landslide type comprises mutation, gradual change and stabilization; the data acquisition cycle discrimination includes discriminating the data validity of the landslide by corresponding landslide data quality, thereby determining the time granularity of acquired data for landslide calculation.
As a further aspect of the present invention, in the early warning module, the threshold interface includes: the threshold data interface exposed outwards can be used for other system calls; the threshold log comprises a scheduling log generated when the external system calls the threshold data of the system.
In another aspect, a method for monomer landslide warning, the method comprising:
s01, judging that the data effective interval of the collected landslide data is that the effective data ratio of the landslide during the data collection period is more than 95% through the data cleaning operation of the data collection cleaning module and the data collection period judging operation of the data verification module, and further evaluating the time period of the landslide when the landslide threshold value is calculated;
s02, in a data analysis module, calculating an improved tangent angle of the landslide;
s03, in the data analysis module, the earth surface displacement value of the landslide displacement when the tangential angle threshold value is improved in different alarm stages can be calculated by improving the corresponding relation between the tangential angle and the landslide displacement, namely the static threshold value of the landslide in the current acquisition period;
s04, in the data verification module, judging whether the landslide is a wading landslide;
s05, if the landslide is a wading type landslide, firstly, calculating the mapping relation between rainfall and landslide displacement by adopting a mode of combining Bayesian network with elastic network regression and heuristic algorithm, and secondly, deducing a landslide future deformation value through a future weather forecast rainfall value, so as to forecast an alarm forecast threshold value of a current acquisition period;
s06, if the landslide is a non-wading type landslide, firstly, selecting the importance degree of an influence factor of landslide induced deformation by adopting a random forest and a Bayesian network; secondly, combining landslide displacement data, adopting a neural network algorithm to obtain fusion parameters of deformation influence factors in a plurality of sampling periods, and simultaneously obtaining the mapping relation between the fusion parameters and landslide displacement; and thirdly, selecting an influence factor parameter with the influence factor importance degree of more than 20% by combining the landslide deformation acceleration change rate, predicting a fusion parameter value of the influence factor of the next acquisition period by using the influence factor data of the previous two acquisition periods through a Bayesian network, and further adopting the fusion parameter value to carry out an alarm threshold of the next acquisition period.
Further, in the early warning module, regarding the aspect of the dynamic change of the warning threshold value, the threshold value interval of the wading type landslide is updated once again every sampling period, and the non-wading type landslide is updated and judged according to whether the improved tangential angle reaches 45 degrees or not.
The embodiment of the invention provides a single landslide early warning system and an early warning method. The data acquisition cleaning module is used for processing monitoring data of a plurality of landslide; the algorithm model library comprises algorithm models aiming at equipment correlation, earth surface displacement correlation and rainfall correlation; the data analysis module comprises analysis of relevant degrees of equipment, ground displacement and rainfall related to single landslide induction; the early warning module is used for opening the early warning information outwards and receiving treatment feedback information; the data verification module is used for verifying the algorithm model, dynamically adjusting the algorithm verification period according to the algorithm model classification, defining a specific alarm threshold value for different monomer landslide, and pre-judging landslide alarms through pre-judging values such as classification, rainfall and the like, so that the effect of early warning in advance is achieved.
Drawings
Fig. 1 is a schematic diagram of a main structure of a single landslide warning system.
FIG. 2 is a flow chart of the operation of a single body landslide warning system.
Detailed Description
The present invention will be described in further detail with reference to the drawings and examples, in order to make the objects, technical solutions and advantages of the present invention more apparent. It should be understood that the specific embodiments described herein are for purposes of illustration only and are not intended to limit the scope of the invention.
Specific implementations of the invention are described in detail below in connection with specific embodiments.
The single landslide early warning system and the single landslide early warning method provided by the invention can define specific warning thresholds for different single landslide, and pre-judge landslide warning through pre-judging values such as classification, rainfall and the like, so that the effect of early warning is achieved, and the technical problem in the background technology is solved.
As shown in fig. 1 and fig. 2, a schematic main structure diagram of a monomer landslide early warning system according to an embodiment of the present invention is provided, where the system includes a data acquisition cleaning module, an algorithm model library, a data analysis module, a data verification module and an early warning module;
the data acquisition cleaning module is used for processing monitoring data of a plurality of landslide;
the algorithm model library is used for storing algorithm models for equipment correlation, earth surface displacement correlation and rainfall correlation;
the data analysis module is used for carrying out related landslide warning analysis on equipment, ground displacement and rainfall related to the single landslide cause based on the monitoring data and the algorithm model library so as to generate early warning information;
the data verification module is used for verifying the algorithm model in the algorithm model library and dynamically adjusting the algorithm verification period in a classified mode;
the early warning module is used for opening the early warning information to the outside and receiving the treatment feedback information
As a preferred embodiment of the present invention, the data acquisition cleaning module is specifically configured to: the equipment log collection, the sensor data collection and the meteorological data are synchronized, and the equipment log collection, the sensor data collection and the meteorological data are also used for cleaning the collected and synchronized data, wherein,
the equipment log acquisition specifically comprises the following steps: acquiring an operation log of environmental data acquisition equipment deployed around a single landslide, wherein the operation log is used for judging the operation health state of the environmental data acquisition equipment;
the sensor data acquisition specifically comprises: acquiring relevant environmental data acquired by environmental data acquisition equipment deployed around a single landslide, wherein the relevant environmental data comprises the temperature, vertical earth surface displacement, horizontal earth surface displacement, displacement acceleration and underground water level of the environment;
the cleaning of the collected and synchronized data includes: and carrying out availability processing on the collected and synchronized data, wherein the availability processing comprises the following steps: removing dirty data, filling in vacancy data and changing unreasonable data in the data:
the algorithm model library comprises: the algorithm model library supports continuous data input of single landslide displacement correlation and rainfall correlation so as to output different parameter alarm thresholds of single landslide, wherein,
displacement correlation algorithm model: for a non-rainfall type single landslide, input data are historical monitoring displacement related data of the single landslide, a change rule between two groups of data including horizontal displacement, vertical displacement, displacement acceleration, inclination angle and first corresponding displacement is calculated through a first correlation algorithm, the first correlation algorithm comprises a classification, clustering, regression and association rule correlation algorithm in data mining, and the first corresponding displacement comprises: horizontal, vertical and resultant displacement;
rainfall-related algorithm model: the model aims at a rainfall type single landslide, input data are historical monitoring related data of the single landslide, a change rule between two groups of data including rainfall, water level change, soil humidity, water level change rate and second corresponding displacement is calculated through a second correlation algorithm, the second correlation algorithm comprises a classification, clustering, regression and association rule correlation algorithm in data mining, and the second corresponding displacement comprises: horizontal, vertical and combined displacement. May also include; a timing model.
As another preferred embodiment of the present invention, the data analysis module is configured to: equipment reliability analysis, rainfall correlation analysis, surface displacement correlation analysis and hybrid analysis.
As another preferred embodiment of the present invention, the data verification module is configured to: and (3) judging the landslide type, judging the landslide stage, judging the main influence factor of the landslide, judging the data acquisition period and verifying the landslide displacement.
The embodiment of the invention is applied.
As another preferred embodiment of the present invention, in the data analysis module, the device reliability analysis includes: performing confidence evaluation analysis on the fault rate of the equipment and the collected fault data rate through a monitoring equipment log, and performing multiple data cleaning and inspection on the data collected by the equipment with the confidence lower than a preset value; the rainfall correlation analysis includes: the method comprises the steps of completing prediction of whether a single landslide is of a rainfall type and a non-rainfall type, and judging the correlation among rainfall, adjacent water areas, groundwater and landslide displacement by adopting a clustering algorithm in the operation so as to judge whether the single landslide is of a rainfall type; sorting importance of wading parameters affecting the single landslide displacement by adopting a classification model, and then predicting the change of the single landslide displacement along with the change of the important wading parameters by a regression model; the surface displacement correlation analysis includes: in the operation, a classification model is adopted to carry out importance sequencing on displacement parameters influencing the displacement of the single landslide, wherein the sequencing comprises displacement acceleration, displacement increment inclination angle and displacement rate; then, the variation of the single landslide displacement along with the variation of the important displacement parameters is predicted by a regression model, wherein the important displacement parameters at least comprise one, and the combination is based on the importance of the displacement parameters
When the embodiment of the invention is applied, in the data verification module, the landslide type judgment comprises the step of judging that the landslide deformation is changed into equipment false alarm, rainfall type or non-rainfall type by calling the calculation result in the data analysis module; the landslide stage discrimination comprises the step of judging the landslide type through a time sequence model in an algorithm model, wherein the landslide type comprises mutation, gradual change and stabilization; the data acquisition cycle discrimination includes discriminating the data validity of the landslide by corresponding landslide data quality, thereby determining the time granularity of acquired data for landslide calculation.
As another preferred embodiment of the present invention, in the early warning module, the threshold interface includes: the threshold data interface exposed outwards can be used for other system calls; the threshold log comprises a scheduling log generated when the external system calls the threshold data of the system.
In another aspect, a method for monomer landslide warning, the method comprising:
s01, judging an effective section of the acquired landslide data (the effective section of the data is that the effective data of the landslide accounts for more than 95% in the data acquisition period) through data cleaning operation of a data acquisition cleaning module and data acquisition period judging operation of a data verification module, and further evaluating the time period of the landslide when a landslide threshold value is calculated (the time period refers to the date, the week, the month and the quarter; the displacement acquisition data judged by the landslide threshold value is that of the last section of landslide stabilization period before deformation occurs);
s02, in a data analysis module, calculating an improved tangent angle of the landslide (the data selection principle is the same as that of the step 1, and the improved tangent angle calculation method is calculated by adopting a method common in the industry);
s03, in the data analysis module, the earth surface displacement value of the landslide displacement in different alarm stages (reminding stage, warning stage and alarm stage) when the tangential angle threshold value is improved can be calculated by improving the corresponding relation between the tangential angle and the landslide displacement, namely the static threshold value of the landslide in the current acquisition period;
s04, in the data verification module, judging whether the landslide is a wading landslide;
s05, if the landslide is a wading type landslide, firstly, calculating the mapping relation between rainfall and landslide displacement by adopting a mode of combining Bayesian network with elastic network regression and heuristic algorithm, and secondly, deducing a landslide future deformation value through a future weather forecast rainfall value, so as to forecast an alarm forecast threshold value of a current acquisition period;
s06, if the landslide is a non-wading type landslide, firstly, selecting the importance degree of an influence factor of landslide induced deformation by adopting a random forest and a Bayesian network; secondly, combining landslide displacement data, obtaining fusion parameters of deformation influence factors in a plurality of sampling periods by adopting a neural network algorithm (the fusion parameters are unchanged before the improved tangential angle changes by 45 degrees), and obtaining the mapping relation between the fusion parameters and the landslide displacement; and thirdly, selecting an influence factor parameter with the influence factor importance degree of more than 20% by combining the landslide deformation acceleration change rate, predicting a fusion parameter value of the influence factor of the next acquisition period by using the influence factor data of the previous two acquisition periods through a Bayesian network, and further adopting the fusion parameter value to carry out an alarm threshold of the next acquisition period.
In the early warning module, regarding the aspect of the dynamic change of the warning threshold value, the threshold value interval of the wading type landslide is updated once again every sampling period, and the non-wading type landslide is updated and judged according to whether the improved tangential angle reaches 45 degrees or not.
The monomer landslide early warning system and method provided by the embodiment of the invention comprise a data acquisition cleaning module, a data storage module, an algorithm model library, a data analysis module, an alarm module and a data transmission module. The data acquisition cleaning module is used for processing monitoring data of a plurality of landslide; the algorithm model library comprises algorithm models aiming at equipment correlation, earth surface displacement correlation and rainfall correlation; the data analysis module comprises analysis of relevant degrees of equipment, ground displacement and rainfall related to single landslide induction; the early warning module is used for opening the early warning information outwards and receiving treatment feedback information; the data verification module is used for verifying the algorithm model, dynamically adjusting the algorithm verification period according to the algorithm model classification, defining a specific alarm threshold value for different monomer landslide, and pre-judging landslide alarms through pre-judging values such as classification, rainfall and the like, so that the effect of early warning in advance is achieved.
In order to be able to load the method and system described above to function properly, the system may include more or less components than those described above, or may combine some components, or different components, in addition to the various modules described above, for example, may include input and output devices, network access devices, buses, processors, memories, and the like.
The processor may be a central processing unit (CentralProcessingUnit, CPU), other general purpose processors, digital signal processors (DigitalSignalProcessor, DSP), application specific integrated circuits (ApplicationSpecificIntegratedCircuit, ASIC), off-the-shelf programmable gate arrays (Field-ProgrammableGateArray, FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, or the like. The general purpose processor may be a microprocessor or the processor may be any conventional processor or the like, which is a control center of the above system, and various interfaces and lines are used to connect the various parts.
The technical features of the above-described embodiments may be arbitrarily combined, and all possible combinations of the technical features in the above-described embodiments are not described for brevity of description, however, as long as there is no contradiction between the combinations of the technical features, they should be considered as the scope of the description.
The foregoing examples illustrate only a few embodiments of the invention and are described in detail herein without thereby limiting the scope of the invention. It should be noted that it will be apparent to those skilled in the art that several variations and modifications can be made without departing from the spirit of the invention, which are all within the scope of the invention. Accordingly, the scope of protection of the present invention is to be determined by the appended claims.
The foregoing description of the preferred embodiments of the invention is not intended to be limiting, but rather is intended to cover all modifications, equivalents, and alternatives falling within the spirit and principles of the invention.
Claims (10)
1. The single landslide early warning system is characterized by comprising a data acquisition cleaning module, an algorithm model library, a data analysis module, a data verification module and an early warning module;
the data acquisition cleaning module is used for processing monitoring data of a plurality of landslide;
the algorithm model library is used for storing algorithm models for equipment correlation, earth surface displacement correlation and rainfall correlation;
the data analysis module is used for carrying out related landslide warning analysis on equipment, ground displacement and rainfall related to the single landslide cause based on the monitoring data and the algorithm model library so as to generate early warning information;
the data verification module is used for verifying the algorithm model in the algorithm model library and dynamically adjusting the algorithm verification period in a classified mode;
the early warning module is used for opening the early warning information to the outside and receiving the treatment feedback information.
2. The single landslide warning system of claim 1, wherein the data acquisition cleaning module is specifically configured to: the equipment log collection, the sensor data collection and the meteorological data are synchronized, and the equipment log collection, the sensor data collection and the meteorological data are also used for cleaning the collected and synchronized data, wherein,
the equipment log acquisition specifically comprises the following steps: acquiring an operation log of environmental data acquisition equipment deployed around a single landslide, wherein the operation log is used for judging the operation health state of the environmental data acquisition equipment;
the sensor data acquisition specifically comprises: acquiring relevant environmental data acquired by environmental data acquisition equipment deployed around a single landslide, wherein the relevant environmental data comprises the temperature, vertical earth surface displacement, horizontal earth surface displacement, displacement acceleration and underground water level of the environment;
the cleaning of the collected and synchronized data includes: and carrying out availability processing on the collected and synchronized data, wherein the availability processing comprises the following steps: removing dirty data, filling in empty data and changing unreasonable data.
3. The monomer landslide warning system of claim 1 wherein the algorithm model library comprises: the algorithm model library supports continuous data input of single landslide displacement correlation and rainfall correlation so as to output different parameter alarm thresholds of single landslide, wherein,
displacement correlation algorithm model: for a non-rainfall type single landslide, input data are historical monitoring displacement related data of the single landslide, a change rule between two groups of data including horizontal displacement, vertical displacement, displacement acceleration, inclination angle and first corresponding displacement is calculated through a first correlation algorithm, the first correlation algorithm comprises a classification, clustering, regression and association rule correlation algorithm in data mining, and the first corresponding displacement comprises: horizontal, vertical and resultant displacement;
rainfall-related algorithm model: the model aims at a rainfall type single landslide, input data are historical monitoring related data of the single landslide, a change rule between two groups of data including rainfall, water level change, soil humidity, water level change rate and second corresponding displacement is calculated through a second correlation algorithm, the second correlation algorithm comprises a classification, clustering, regression and association rule correlation algorithm in data mining, and the second corresponding displacement comprises: horizontal, vertical and combined displacement.
4. The monomer landslide warning system of claim 1 wherein the data analysis module is configured to: equipment reliability analysis, rainfall correlation analysis, surface displacement correlation analysis and hybrid analysis.
5. The monomer landslide warning system of claim 1 wherein the data verification module is configured to: and (3) judging the landslide type, judging the landslide stage, judging the main influence factor of the landslide, judging the data acquisition period and verifying the landslide displacement.
6. A monomer landslide warning system of claim 3 wherein in the data analysis module the device reliability analysis comprises: performing confidence evaluation analysis on the fault rate of the equipment and the collected fault data rate through a monitoring equipment log, and performing multiple data cleaning and inspection on the data collected by the equipment with the confidence lower than a preset value; the rainfall correlation analysis includes: the method comprises the steps of completing prediction of whether a single landslide is of a rainfall type and a non-rainfall type, and judging the correlation among rainfall, adjacent water areas, groundwater and landslide displacement by adopting a clustering algorithm in the operation so as to judge whether the single landslide is of a rainfall type; sorting importance of wading parameters affecting the single landslide displacement by adopting a classification model, and then predicting the change of the single landslide displacement along with the change of the important wading parameters by a regression model; the surface displacement correlation analysis includes: in the operation, a classification model is adopted to carry out importance sequencing on displacement parameters influencing the displacement of the single landslide, wherein the sequencing comprises displacement acceleration, displacement increment inclination angle and displacement rate; and then, predicting the change of the single landslide displacement along with the change of the important displacement parameters through a regression model, wherein the important displacement parameters at least comprise one, and the important displacement parameters are combined according to the importance of the displacement parameters.
7. The single landslide early warning system of any one of claims 1-6 wherein in the data verification module, the landslide type discrimination includes determining that the landslide is to be a false positive, a rainfall type or a non-rainfall type by invoking the calculation result in the data analysis module; the landslide stage discrimination comprises the step of judging the landslide type through a time sequence model in an algorithm model, wherein the landslide type comprises mutation, gradual change and stabilization; the data acquisition cycle discrimination includes discriminating the data validity of the landslide by corresponding landslide data quality, thereby determining the time granularity of acquired data for landslide calculation.
8. The monomer landslide warning system of claim 1 wherein in the warning module the threshold interface comprises: the threshold data interface exposed outwards can be used for other system calls; the threshold log comprises a scheduling log generated when the external system calls the threshold data of the system.
9. A monomer landslide early warning method applied to the monomer landslide early warning system of any one of claims 1-8, characterized in that the method comprises the following steps:
s01, judging the effective interval of the collected landslide data through the data cleaning operation of the data collecting and cleaning module and the data collecting period judging operation of the data verifying module, and further evaluating the time period of the landslide when calculating a landslide threshold value;
s02, in a data analysis module, calculating an improved tangent angle of the landslide;
s03, in the data analysis module, the earth surface displacement value of the landslide displacement when the tangential angle threshold value is improved in different alarm stages can be calculated by improving the corresponding relation between the tangential angle and the landslide displacement, namely the static threshold value of the landslide in the current acquisition period;
s04, in the data verification module, judging whether the landslide is a wading landslide;
s05, if the landslide is a wading type landslide, firstly, calculating the mapping relation between rainfall and landslide displacement by adopting a mode of combining Bayesian network with elastic network regression and heuristic algorithm, and secondly, deducing a landslide future deformation value through a future weather forecast rainfall value, so as to forecast an alarm forecast threshold value of a current acquisition period;
s06, if the landslide is a non-wading type landslide, firstly, selecting the importance degree of an influence factor of landslide induced deformation by adopting a random forest and a Bayesian network; secondly, combining landslide displacement data and adopting a neural network algorithm to obtain fusion parameters of deformation influence factors under a plurality of sampling periods, wherein the fusion parameters are unchanged before the improved tangential angle changes by 45 degrees, and the mapping relation between the fusion parameters and the landslide displacement can be obtained; and thirdly, selecting an influence factor parameter with the influence factor importance degree of more than 20% by combining the landslide deformation acceleration change rate, predicting a fusion parameter value of the influence factor of the next acquisition period by using the influence factor data of the previous two acquisition periods through a Bayesian network, and further adopting the fusion parameter value to carry out an alarm threshold of the next acquisition period.
10. The method for early warning a single landslide according to claim 9, wherein in the early warning module, regarding the aspect of dynamic change of the warning threshold, the threshold interval of the wading type landslide is updated once again every sampling period, and the non-wading type landslide is updated and judged according to whether the improved tangential angle reaches 45 degrees.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310837144.1A CN117037424A (en) | 2023-07-10 | 2023-07-10 | Single landslide early warning system and method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310837144.1A CN117037424A (en) | 2023-07-10 | 2023-07-10 | Single landslide early warning system and method |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN117037424A true CN117037424A (en) | 2023-11-10 |
Family
ID=88627037
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310837144.1A Pending CN117037424A (en) | 2023-07-10 | 2023-07-10 | Single landslide early warning system and method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117037424A (en) |
-
2023
- 2023-07-10 CN CN202310837144.1A patent/CN117037424A/en active Pending
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109359698B (en) | Leakage identification method based on long-time memory neural network model | |
| CN101135614B (en) | Anomaly monitoring device and method | |
| AU2003250981B2 (en) | Method and device for determining an expectancy range for a level echo and a spurious echo | |
| CN113538861B (en) | Geological disaster information management system based on mineral geological exploration | |
| Kwon et al. | Spatio-temporal drought patterns of multiple drought indices based on precipitation and soil moisture: a case study in South Korea | |
| CN110703214B (en) | Weather radar state evaluation and fault monitoring method | |
| CN109298959A (en) | A kind of memory abnormal detection method and equipment | |
| CN113723446B (en) | Ground disaster monitoring and early warning method and device, computer equipment and storage medium | |
| CN116308415A (en) | Sewage discharge data true and false risk assessment method | |
| CN115375137A (en) | Safety risk early warning prediction system of non-coal mine mountain tailing mine base | |
| CN115454778A (en) | Intelligent monitoring system for abnormal time sequence indexes in large-scale cloud network environment | |
| CN114118576A (en) | Regional geological disaster trend prediction method and system | |
| CN116343436A (en) | Landslide detection method, landslide detection device, landslide detection equipment and landslide detection medium | |
| CN115909664A (en) | BIM-based river channel safety early warning method, device and equipment | |
| CN109030499A (en) | A kind of device and method preventing defect counts repeat count suitable for target defect continuous on-line detection | |
| CN115271408A (en) | Management method and system of ship equipment, readable storage medium and computer equipment | |
| CN117037424A (en) | Single landslide early warning system and method | |
| CN113128098B (en) | Concrete dam singular value detection method and equipment based on DE-LOF | |
| CN106526545A (en) | Method for detecting robust CFAR detector | |
| Donnelly | Morphologic change by overwash: establishing and evaluating predictors | |
| CN113486134A (en) | Rainfall abnormality detection method and device, computer device and storage medium | |
| CN113487223A (en) | Risk assessment method and risk assessment system based on information fusion | |
| US20110015967A1 (en) | Methodology to identify emerging issues based on fused severity and sensitivity of temporal trends | |
| ten Veldhuis et al. | Statistical analysis of hydrological response in urbanising catchments based on adaptive sampling using inter-amount times | |
| CN115129706B (en) | Soil moisture observation data quality evaluation method considering periodic characteristics |
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 |