CN117116024A - Geological disaster monitoring and early warning system, method, computer medium and computer - Google Patents
Geological disaster monitoring and early warning system, method, computer medium and computer Download PDFInfo
- Publication number
- CN117116024A CN117116024A CN202311353590.1A CN202311353590A CN117116024A CN 117116024 A CN117116024 A CN 117116024A CN 202311353590 A CN202311353590 A CN 202311353590A CN 117116024 A CN117116024 A CN 117116024A
- Authority
- CN
- China
- Prior art keywords
- early warning
- data
- geological
- preset
- disaster
- 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.)
- Granted
Links
- 238000000034 method Methods 0.000 title claims abstract description 69
- 238000012544 monitoring process Methods 0.000 title claims abstract description 68
- 238000012549 training Methods 0.000 claims abstract description 22
- 238000010801 machine learning Methods 0.000 claims abstract description 5
- 230000001681 protective effect Effects 0.000 claims description 34
- 238000012545 processing Methods 0.000 claims description 22
- 230000002159 abnormal effect Effects 0.000 claims description 18
- 230000006870 function Effects 0.000 claims description 13
- 238000004458 analytical method Methods 0.000 claims description 12
- 238000007477 logistic regression Methods 0.000 claims description 12
- 230000008569 process Effects 0.000 claims description 12
- 238000009499 grossing Methods 0.000 claims description 11
- 230000000694 effects Effects 0.000 claims description 6
- 238000012360 testing method Methods 0.000 claims description 6
- 238000010606 normalization Methods 0.000 claims description 5
- 238000010276 construction Methods 0.000 claims description 2
- 239000002184 metal Substances 0.000 claims description 2
- 230000036961 partial effect Effects 0.000 claims description 2
- 239000011435 rock Substances 0.000 abstract description 10
- 239000010410 layer Substances 0.000 description 22
- 238000012806 monitoring device Methods 0.000 description 13
- 238000010586 diagram Methods 0.000 description 8
- 239000000463 material Substances 0.000 description 8
- 230000035945 sensitivity Effects 0.000 description 7
- 239000011241 protective layer Substances 0.000 description 6
- 230000002829 reductive effect Effects 0.000 description 5
- 239000002689 soil Substances 0.000 description 5
- 238000004590 computer program Methods 0.000 description 4
- 230000007797 corrosion Effects 0.000 description 4
- 238000005260 corrosion Methods 0.000 description 4
- 238000001514 detection method Methods 0.000 description 4
- 239000002356 single layer Substances 0.000 description 4
- 230000001960 triggered effect Effects 0.000 description 4
- 230000004888 barrier function Effects 0.000 description 3
- 230000007613 environmental effect Effects 0.000 description 3
- 238000003672 processing method Methods 0.000 description 3
- 239000004575 stone Substances 0.000 description 3
- 241001465754 Metazoa Species 0.000 description 2
- 230000009471 action Effects 0.000 description 2
- 230000003044 adaptive effect Effects 0.000 description 2
- 230000000903 blocking effect Effects 0.000 description 2
- 230000008859 change Effects 0.000 description 2
- 230000007547 defect Effects 0.000 description 2
- 230000009545 invasion Effects 0.000 description 2
- 230000000670 limiting effect Effects 0.000 description 2
- 238000013507 mapping Methods 0.000 description 2
- 230000007246 mechanism Effects 0.000 description 2
- 230000002035 prolonged effect Effects 0.000 description 2
- 238000007619 statistical method Methods 0.000 description 2
- 244000025254 Cannabis sativa Species 0.000 description 1
- 241001391944 Commicarpus scandens Species 0.000 description 1
- 238000006424 Flood reaction Methods 0.000 description 1
- 241000282412 Homo Species 0.000 description 1
- 230000001133 acceleration Effects 0.000 description 1
- 238000006243 chemical reaction Methods 0.000 description 1
- 230000001684 chronic effect Effects 0.000 description 1
- 238000004140 cleaning Methods 0.000 description 1
- 230000010485 coping Effects 0.000 description 1
- 238000007405 data analysis Methods 0.000 description 1
- 238000013480 data collection Methods 0.000 description 1
- 238000013500 data storage Methods 0.000 description 1
- 238000013079 data visualisation Methods 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 230000001066 destructive effect Effects 0.000 description 1
- 238000006073 displacement reaction Methods 0.000 description 1
- 238000011478 gradient descent method Methods 0.000 description 1
- 239000011796 hollow space material Substances 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 239000012811 non-conductive material Substances 0.000 description 1
- 230000003449 preventive effect Effects 0.000 description 1
- 238000012216 screening Methods 0.000 description 1
- 230000002123 temporal effect Effects 0.000 description 1
- 238000012876 topography Methods 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 description 1
Classifications
-
- 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
-
- 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
Landscapes
- Business, Economics & Management (AREA)
- Emergency Management (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Engineering & Computer Science (AREA)
- Computing Systems (AREA)
- Life Sciences & Earth Sciences (AREA)
- Environmental & Geological Engineering (AREA)
- General Life Sciences & Earth Sciences (AREA)
- Geology (AREA)
- Alarm Systems (AREA)
Abstract
The invention discloses a geological disaster monitoring and early warning method, which comprises the following steps: acquiring historical geological data and network body electrifying data, and integrating the historical geological data and the network body electrifying data to construct a data set; training the data set continuously by adopting a machine learning method to obtain a corrected disaster early warning model; deploying a disaster early warning model, and judging whether a preset disaster phenomenon exists in an early warning area according to continuously collected real-time geological data and network body electrifying data; if yes, triggering early warning alarm, acquiring preset early warning information according to real-time geological data and network body electrifying data, further feeding back the early warning alarm information containing the preset early warning information to a preset object, and if not, re-acquiring the real-time geological data and the network body electrifying data; disaster state data of the early warning area are obtained, and meanwhile, the disaster state data are continuously and synchronously fed back to a preset object. The invention can timely catch early signs of geological disasters such as mud-rock flow and landslide.
Description
Technical Field
The invention relates to the technical field of disaster early warning equipment, in particular to a geological disaster monitoring and early warning system, a geological disaster monitoring and early warning method, a computer medium and a computer.
Background
Geological disasters are geological effects or geological phenomena formed under the action of natural or human factors, which cause loss of human lives and properties and damage to the environment. Both debris flow and landslide are natural geological disasters, commonly occurring in mountainous or hilly areas, and pose a serious threat to humans and the environment. Among them, debris flow is a kind of rapid-flow natural disaster in which water, soil, rock and other debris materials are mixed, and such natural disaster is often accompanied by destructive floods, mud and boulders, causing great damage to houses, roads, bridges and farms, and possibly causing casualties. Landslide refers to the process that soil, rock or rock layer on a landslide loses stability and slides downwards under the action of certain external force, and the landslide can be chronic and gradual or can be rapid and suddenly generated, and can cause soil underground slip, house damage, road blockage and the like to seriously threaten life and property of people depending on the property of landslide materials and external conditions.
At present, the existing monitoring and early warning of geological disasters such as mud-rock flow and landslide generally adopts regional rainfall monitoring, geological monitoring, satellite remote sensing monitoring and the like; however, the monitoring and early warning is generally in a range, and cannot effectively monitor the slight condition of the geological disaster at the beginning, such as a few sparse falling stones, so that after the geological disaster is identified by the monitoring and early warning, the geological disaster is formed, and the defects that early warning is not timely and people can not be timely warned and evacuated at the early stage of the geological disaster are caused.
In order to solve the problem, a geological disaster monitoring and early warning system capable of timely capturing early signs of geological disasters and timely finding out occurrence of the geological disasters is needed.
Disclosure of Invention
The invention aims to: in order to overcome the defects, the invention aims to provide a geological disaster monitoring and early warning system, a geological disaster monitoring and early warning method, a geological disaster monitoring and early warning computer and a geological disaster early warning computer are flexible to apply, the falling stone condition along a mountain road area can be monitored in real time, and after falling stone occurs and a protective net structure is impacted, the geological disaster grade is judged according to the set damage scale of the protective net, so that the early warning area with the geological disaster is immediately monitored in a corresponding grade.
In order to solve the technical problems, the invention provides a geological disaster monitoring and early warning system, which comprises:
the protection assembly comprises fixing pieces and a protection net structure, and a plurality of fixing pieces are arranged in an array along the road of the road to be early-warned; the protective net structure is arranged between the fixing pieces and is provided with a hollow layer;
the early warning assembly comprises an electrifying structure, an early warning alarm and an early warning unit, wherein the electrifying structure comprises a wire mesh and an electrifying connecting piece, the wire mesh is paved in the hollow layer, and two ends of the electrifying connecting piece are respectively and electrically connected with the wire mesh and a road power supply system to be early warned; the early warning alarm is arranged in an early warning area of a road to be early warned, and early warning alarm information comprising the early warning area is fed back to a preset object through the early warning alarm; the two ends of the early warning unit are respectively connected with the wire mesh and the early warning alarm, the electrifying state of the wire mesh is judged in real time through the early warning unit, and after the wire mesh has the preset electrifying problem, preset early warning information is fed back to the early warning alarm;
and the remote monitoring equipment is connected with the early warning alarm, and the state of the early warning area is identified and judged through the remote monitoring equipment.
By adopting the technical scheme, the protection net structure can be utilized to provide protection for geological disasters along the mountain road, so that invasion of falling objects to the mountain road is prevented, the overall safety of the road is improved, and accidents are reduced; further, when the protection net structure provides protection, the change of the energizing state of the wire mesh can be detected in real time, and once the energized wire mesh has problems such as breakage (power off) or touch (short circuit), early warning and alarming are immediately carried out, so that early signs of geological disasters are captured in time, and the occurrence of the geological disasters is found in time; further, the remote monitoring equipment is utilized to enable related safety institutions or managers to monitor the condition of the road from a remote position in real time, so that measures can be taken in time to cope with geological disasters, and the safety of the road area and surrounding urban areas is ensured.
As an optimal mode of the invention, a protection early warning interval is formed among a plurality of fixing pieces, and the protection net structure is paved in the protection early warning interval.
As a preferable mode of the invention, the protective net structure comprises a protective layer and a hollow layer, wherein the protective layer is made of insulating and corrosion-resistant materials; the hollow layer is laid in the protection layer and is provided with a hollow section.
As a preferable mode of the invention, the wire mesh is laid in the hollow space, and the mesh size of the wire mesh is set according to disaster early warning requirements.
As a preferable mode of the invention, after the wire mesh is broken, the early warning unit judges the wire mesh breaking parameter, and then feeds back the early warning of the first preset level to the early warning alarm according to the wire mesh breaking parameter.
As a preferable mode of the invention, after the wire mesh is short-circuited, the early warning unit judges the wire mesh short-circuit parameter, and then feeds back the early warning of the second preset level to the early warning alarm according to the wire mesh short-circuit parameter.
As a preferable mode of the invention, the early warning alarm is integrated with the geographic information system, and the early warning area information matched with the early warning alarm is divided according to the first preset level or the second preset level, wherein the early warning area information at least comprises patrol path data matched with the early warning area.
By adopting the technical scheme, the integrated device can provide more comprehensive and real-time geological disaster monitoring and early warning with GIS (Geographic Information System or Geo-Information system, namely a geographic information system), ensure that the phenomenon occurring at the early stage of the geological disaster can be captured more timely and accurately, and further effectively protect lives and properties of people.
As a preferable mode of the invention, the remote monitoring device adopts a remote control aircraft, and the detection area matched with the information of the early warning area is obtained through flight patrol of the remote control aircraft.
As a preferable mode of the invention, the remote monitoring equipment adopts a remote control mobile device, and the detection area matched with the information of the early warning area is moved by adopting the remote control mobile device.
As a preferable mode of the invention, the early warning assembly further comprises a vibration sensor, wherein the vibration sensor is arranged on the protective net structure and is connected with the early warning alarm, the vibration sensor is provided with preset-level vibration, and vibration early warning information matched with the preset-level vibration is fed back to the early warning alarm through the vibration sensor.
By adopting the technical scheme, the vibration related to the geological disaster can be accurately detected, and the alarm is timely triggered, so that the efficiency and the reliability of the geological disaster monitoring and early warning system are improved, and the related safety mechanism or manager can take appropriate measures for dealing when the alarm is triggered.
The invention also provides a geological disaster monitoring and early warning method, which comprises the following steps:
S1: judging whether a preset electrifying problem exists in an electrifying structure of the road to be pre-warned in real time according to pre-warning monitoring data of the road to be pre-warned;
s2: if yes, real-time judging preset early warning information (comprising the number of the preset electrifying problem electrifying structures, the area corresponding to the number, the specific problem type and the disaster grade corresponding to the specific problem type) of the problem electrifying structure and simultaneously feeding back geological disaster early warning to the preset object; if not, returning to the step S1;
s3: and (3) patrol monitoring is carried out on the early warning area matched with the problem electrifying structure by the remote monitoring equipment, and the state of the early warning area acquired by the remote monitoring equipment is synchronously fed back to a preset object.
The invention also provides a computer medium, wherein the computer medium is stored with a computer program, and the computer program is executed by a processor to realize the geological disaster monitoring and early warning method.
The invention also provides a computer, comprising the computer medium.
Compared with the prior art, the technical scheme of the invention has the following advantages:
1. the protection of geological disasters can be provided for the mountain road, and invasion of falling objects to the mountain road is prevented, so that the overall safety of the road is improved, and accidents are reduced; the method has the advantages that the change of the electrifying state of the wire mesh can be detected in real time while the protection is provided, and once the electrified wire mesh has the electrifying problem, early warning and alarming are immediately carried out, so that the processing and coping capacity of geological disasters are improved, and the potential risks and dangerous situations are reduced;
2. Real-time monitoring of remote positions can be provided for related safety institutions or managers, so that the safety institutions or managers can take measures in time to cope with geological disasters, and the safety of road areas and surrounding urban areas is ensured;
3. the integrated device and the GIS can provide more comprehensive and real-time geological disaster monitoring and early warning, and ensure that the phenomenon occurring in the early stage of the geological disaster can be captured more timely and accurately;
4. the vibration related to the geological disaster can be accurately detected, and the alarm is timely triggered, so that the efficiency and the reliability of the geological disaster monitoring and early warning system are improved, and the related safety mechanism or manager can take appropriate measures for dealing when the alarm is triggered.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the following description will briefly explain the drawings used in the embodiments or the description of the prior art, and it is obvious that the drawings in the following description are only embodiments of the present invention, and other drawings can be obtained according to the provided drawings without inventive effort for a person skilled in the art.
Fig. 1 is a schematic diagram of a monitoring and early warning system of a rod-type fixing structure of the present invention.
FIG. 2 is a schematic diagram of a single layer protection net structure of the present invention.
Fig. 3 is a schematic diagram of a first connection of the geological disaster monitoring and early warning system of the present invention.
Fig. 4 is a schematic diagram of a monitoring and early warning system of the frame type fixing structure of the present invention.
FIG. 5 is a schematic view of a multi-layered protective screening structure according to the present invention.
Fig. 6 is a schematic view of a dense wire mesh of the present invention.
Fig. 7 is a schematic view of a sparse wire mesh of the present invention.
Fig. 8 is a schematic diagram of a monitoring and early warning system of a remotely controlled vehicle according to the present invention.
Fig. 9 is a schematic diagram of a monitoring and early warning system of the remote control mobile device of the present invention.
FIG. 10 is a schematic diagram of a monitoring and early warning system integrated with a geographic information system according to the present invention.
Fig. 11 is a schematic view of a vibration sensor mounting guard assembly of the present invention.
Fig. 12 is a schematic view of a protective assembly of the present invention with vibration and humidity sensors installed.
Fig. 13 is a flow chart of a geological disaster monitoring and early warning method of the present invention.
FIG. 14 is a flow chart of a method of constructing a dataset of the present invention.
Fig. 15 is a flowchart of a data set preset processing method of the present invention.
FIG. 16 is a flow chart of the model training method of the present invention.
Fig. 17 is a flowchart of the missing value processing method of the present invention.
Fig. 18 is a flowchart of an outlier processing method of the present invention.
FIG. 19 is a flow chart of a model deployment warning method of the present invention.
Fig. 20 is a second connection schematic diagram of the geological disaster monitoring and early warning system of the present invention.
Description of the specification reference numerals:
3. the system comprises remote monitoring equipment, 5, a geographic information system, 10, fixing parts, 11, a protective net structure, 20, an electrifying structure, 21, an early warning alarm, 22, an early warning unit, 23, a vibration sensor, 24, a humidity sensor, 30, a remote control aircraft, 31, a remote control mobile device, 40, a supervision terminal, 41, a public terminal, 100, a fixing rod, 101, a fixing frame, 102, a protective early warning section, 110, a hollow layer, 111, a protective layer, 200, a wire mesh, 201, an electrifying connecting part, 202, a mesh of the wire mesh, 1000, a data processing module, 1001, a model training module, 1002, a model prediction module, 1003, an early warning alarm module, 1004 and a region monitoring module.
Detailed Description
Embodiments of the present invention are described in detail below, examples of which are illustrated in the accompanying drawings, wherein like or similar reference numerals refer to like or similar elements or elements having like or similar functions throughout. The embodiments described below by referring to the drawings are illustrative and intended to explain the present invention and should not be construed as limiting the invention.
Referring to fig. 1-3, in some embodiments, a geological disaster monitoring and early warning system is at least composed of a protection component, an early warning component and a remote monitoring device 3.
< protective Assembly >
The protection component comprises a fixing piece 10 and a protection net structure 11, wherein the fixing piece 10 is arranged at the road edge position of a road to be early-warned, and the road to be early-warned is usually a road paved along a mountain; the protection net structure 11 is installed between a plurality of fixing pieces 10, and the protection net structure 11 is unfolded through the fixing pieces 10 so as to protect and early warn mountain falling rocks, and further, the protection net structure 11 is further provided with a hollow layer 110.
< Pre-alarm Assembly >
The pre-warning assembly comprises a power-on structure 20, a pre-warning alarm 21 and a pre-warning unit 22, wherein the power-on structure 20 comprises a wire mesh 200 and a power-on connecting piece 201, the wire mesh 200 is paved in a hollow layer 110, no barrier exists between mesh openings 202 of the wire mesh, in addition, the area of each wire mesh 200 is set by operators, all wires connected with each other in a body mode are adopted, when any wire of the wire mesh 200 is broken, the wire mesh 200 is powered off, and when any two wire meshes 200 of the wire mesh 200 touch, the wire mesh 200 is short-circuited; each wire mesh 200 is connected with at least one electrifying connecting piece 201, two ends of the electrifying connecting piece 201 are respectively electrically connected with the wire mesh 200 and a road power supply system to be pre-warned, and the wire mesh 200 is electrified through the electrifying connecting piece 201;
The early warning alarm 21 is arranged in an early warning area of a road to be early warned, and early warning alarm information comprising the early warning area is fed back to a preset object through the early warning alarm 21; each wire mesh 200 is connected with at least one early warning unit 22, two ends of the early warning unit 22 are respectively connected with the wire mesh 200 and the early warning alarm 21, the electrifying state of the wire mesh 200 is judged in real time through the early warning unit 22, and after the wire mesh 200 has a preset electrifying problem, preset early warning information is fed back to the early warning alarm 21; specifically, the preset object is a supervision terminal 40 of a geological disaster monitoring and early warning company and an early warning area public terminal 41 corresponding to the road to be early warned. Further, the preset power-on problem at least comprises power-off and short circuit; the preset early warning information at least comprises the number of the wire meshes 200 with preset electrifying problems, the area corresponding to the number of the wire meshes 200, specific electrifying problem types, early warning grades corresponding to the specific electrifying problem types and the like.
It can be understood that in this embodiment, the early warning unit 22 is connected to the power-on structure 20, and the early warning unit 22 is connected to the early warning alarm 21, which may be wired or wireless; the warning alarm 21 is connected to a preset object, typically by wireless connection.
Specifically, the breakage and short circuit of the wire mesh 200 are provided with different early warning levels, and the early warning level of the breakage is greater than the early warning level of the short circuit; namely: after any wire of the wire mesh 200 breaks, the wire mesh 200 is immediately powered off by the power-on connector 201, at this time, the early warning unit 22 can immediately receive the number of connected power-off power-on structures 20, and then identify the area of the wire mesh 200 matched with the number of power-on structures 20 according to the number of power-on structures 20, and then divide the number of power-on structures 20 and the area of the wire mesh 200 into matched early warning grades (such as first preset grade early warning), and then feed back the corresponding early warning grades to the early warning alarm 21; after any wire in the wire mesh 200 touches, the wire mesh 200 immediately shorts the conductive connection piece 201, at this time, the early warning unit 22 can immediately receive the number of connected shorted conductive structures 20, and further identify the area of the wire mesh 200 matched with the number of conductive structures 20, and then divide the area of the wire mesh 200 into matched early warning levels (such as a second preset level early warning) according to the number of conductive structures 20 and the area of the wire mesh 200, and further feed back the corresponding early warning levels to the early warning alarm 21.
< remote monitoring device 3>
The remote monitoring device 3 is connected with the early warning alarm 21, and the state of the early warning area is identified and judged through the remote monitoring device 3; the remote monitoring device 3 includes, but is not limited to, a remote control aircraft 30 (e.g., an unmanned aerial vehicle with a camera set), a remote control mobile device 31 (e.g., a robot with a camera set), etc.; further, the state of the early warning area comprises image data, address data, preset early warning information and the like of the early warning area; further, the remote monitoring device 3 is also connected with a supervision terminal 40 of a geological disaster monitoring and early warning company. It will be appreciated that in this embodiment, the remote monitoring device 3 is connected to the alarm 21, and the remote monitoring device 3 is also connected to the supervision terminal 40 of the geological disaster monitoring and early warning company, typically by wireless connection.
Therefore, one aspect of the invention provides a working principle of a geological disaster monitoring and early warning system:
judging whether a preset electrifying problem exists in an electrifying structure 20 of the road to be pre-warned in real time according to pre-warning monitoring data of the road to be pre-warned;
if yes, the preset early warning information (including the number of the preset electrifying problem electrifying structures 20, the area corresponding to the number, the specific problem type and the disaster grade corresponding to the specific problem type) of the problem electrifying structures 20 is judged in real time, and the geological disaster early warning is fed back to the preset object; if not, re-acquiring early warning monitoring data;
The remote monitoring device 3 is enabled to patrol and monitor the early warning area matched with the problem electrifying structure 20, and meanwhile the state of the early warning area acquired by the remote monitoring device 3 is synchronously fed back to a preset object.
In some embodiments, referring to fig. 1, the fixing member 10 may adopt a rod-type fixing structure, where the rod-type fixing structure is composed of a plurality of fixing rods 100, the plurality of fixing rods 100 are arranged in a linear array along a road of a road to be pre-warned along a direction, and a protection pre-warning section 102 is formed between any two fixing rods 100, so that the protection net structure 11 is laid in the protection pre-warning section 102; specifically, the height of the fixing rod 100 is set by an operator according to the protection and early warning range of actual requirements, and it can be understood that the higher the fixing rod 100 is, the larger the protection and early warning range is, whereas the shorter the fixing rod 100 is, the smaller the protection and early warning range is.
In the practical implementation process, if the rod type fixing structure is adopted, the rod type fixing structure is firstly arranged at the road edge of the road to be early-warned, then a plurality of fixing rods 100 are arranged along the road edge of the road to be early-warned, so that a plurality of protection early-warning intervals 102 are formed, a plurality of protection net structures 11 are sequentially paved at the protection early-warning intervals 102, two ends of the protection net structures 11 are respectively connected with the adaptive fixing rods 100, and the protection net structures 11 are unfolded to provide protection early-warning for the road area to be early-warned.
In some embodiments, referring to fig. 4, the fixing member 10 may further adopt a frame-type fixing structure, the frame-type fixing structure is designed by using fixing frames 101, and a plurality of fixing frames 101 are arranged in a linear array along the road of the road to be pre-warned, and each fixing frame 101 is provided with at least one protection pre-warning section 102, so that the protection net structure 11 is paved in the protection pre-warning section 102; specifically, the area of the fixed frame 101 is set by an operator according to the protection pre-warning range of the actual requirement, and it can be understood that the larger the area of the fixed frame 101 is, the larger the protection pre-warning range is, whereas the smaller the area of the fixed frame 101 is, the smaller the protection pre-warning range is.
In the practical implementation process, if the frame-type fixing structure is adopted, the protection net structure 11 is paved at the protection early warning section 102 of the frame-type fixing structure, the protection net structure 11 is unfolded, the fixing frames 101 are further installed at the road edge of the road to be early warned, and then the fixing frames 101 are sequentially arranged along the road edge direction of the road to be early warned so as to provide protection early warning for the road area to be early warned.
In some embodiments, referring to fig. 2, the protective net structure 11 is provided with at least one layer, and the protective net structure 11 is provided with a hollow layer 110, the wire mesh 200 is laid in the hollow layer 110, and no barrier for blocking the mesh of the wire mesh 200 exists in the hollow layer 110; specifically, the outside of the single-layer protection net structure 11 is made of insulating and corrosion-resistant materials, so that personnel or animals can be prevented from touching and getting electric shock, and the service life of the protection net structure 11 can be prolonged.
In the practical implementation process, the intensity of the single-layer protective net structure 11 is lower, if the single-layer protective net structure 11 is adopted, the protective effect of falling objects is reduced, meanwhile, the early warning sensitivity is improved, after the falling objects collide with the protective net structure 11, the wire mesh 200 in the protective net structure 11 is easy to break or touch each other, so that the power-on problem of power-off or short circuit is generated, and the timeliness of geological disaster early warning is improved.
In some embodiments, referring to fig. 5, the protective net structure 11 is provided with at least two layers, namely, a protective layer 111 and a hollow layer 110, wherein the protective layer 111 is made of an insulating and corrosion-resistant material, the hollow layer 110 can be made of any non-conductive material, and no barrier for blocking the mesh of the wire mesh 200 exists in the hollow layer 110, so that the wire mesh 200 is laid in the hollow layer 110; specifically, the protective layer 111 of the multi-layer protective net structure 11 is made of insulating and corrosion-resistant materials, so that personnel or animals can be prevented from touching and getting an electric shock, the service life of the protective net structure 11 can be prolonged, and the protective effect of falling objects can be improved through the multi-layer design.
In the practical implementation process, the intensity of the multi-layer protective net structure 11 is higher, if the multi-layer protective net structure 11 is adopted, the protective effect of falling objects is improved, meanwhile, the early warning sensitivity is reduced, and only when the larger falling objects collide with the protective net structure 11, the wire mesh 200 in the protective net structure 11 is broken or mutually contacted, so that the power-on problem of power-off or short circuit is generated, and the early warning of geological disasters is carried out.
In some embodiments, referring to fig. 6-7, the mesh 202 size of the wire mesh is set by the operator according to the actual requirement, the mesh 202 size of the wire mesh is matched with the early warning sensitivity, it is understood that the wire mesh 200 with sparse mesh size has early warning sensitivity, which is smaller than the wire mesh 200 with dense mesh size.
Specifically, the operator selects the wire mesh 200 with the adaptive mesh size according to the actual early warning sensitivity requirement and cost, when the mesh size is sparse, the breakage and the touch of the wire are less, the early warning sensitivity is lower at this moment, and when the mesh size is dense, the breakage and the touch of the wire are more, and the early warning sensitivity is high at this moment.
In an actual implementation, a mesh size map may be formulated for different types of geological disasters. This table will list the recommended mesh sizes associated with different disaster types (e.g., landslide, debris flow, rock collapse); the mapping table making process comprises the following steps:
firstly, the mapping table should list various possible geological disaster types, such as landslide, mud-rock flow, rock collapse and the like, each type of geological disaster has unique characteristics, and different requirements are set for protective measures;
For each type of geological disaster, the table should list the recommended mesh sizes associated therewith, which will be determined based on the study and experience of the particular geological disaster to ensure that the protection net has sufficient effectiveness;
consideration of geological environmental factors is also important in determining recommended mesh sizes, for example, factors such as geological conditions, soil type, grade, etc. may affect the size and speed of the disaster and thus the choice of mesh size.
In this embodiment, the mesh size map table may refer to the following table:
| type of geological disaster | Recommended mesh size (unit: mm) |
| Landslide | 10 |
| Debris flow | 5 |
| Rock collapse | 12 |
| Vibration caused by earthquake | 6 |
This example table shows the relationship between different geological disaster types and recommended mesh sizes, which in practice can be adjusted by the designer according to the actual settings for the operator to select the appropriate mesh size wire mesh 200 in different geological disaster situations to improve the efficiency and reliability of the protection system.
In some embodiments, referring to fig. 8, the remote monitoring device 3 adopts the remote control aircraft 30, and feeds back the image data, the address data and the preset early warning information of the early warning area to the preset object in real time by adopting the remote control aircraft 30 to fly and patrol the detection area matched with the early warning area information, specifically, while the remote control aircraft 30 flies and patrol.
In an actual implementation process, the remote control aircraft 30 may adopt an existing unmanned aerial vehicle device, and patrol monitoring is performed on the early warning area through at least one unmanned aerial vehicle device, and further, different numbers of unmanned aerial vehicle devices may be dispatched to perform patrol monitoring according to disaster grades.
In some embodiments, referring to fig. 9, the remote monitoring device 3 uses a remote control mobile device 31, and uses the remote control mobile device 31 to move a detection area matching with the information of the early warning area, specifically, while the remote control mobile device 31 patrols, the image data, the address data and the preset early warning information of the early warning area are fed back to the preset object in real time.
In an actual implementation process, the remote control aircraft 30 may adopt an existing robot device, and patrol the early warning area through at least one robot device, and further, send different numbers of robot devices to patrol the early warning area according to the disaster level.
In some embodiments, referring to fig. 10, the early warning alarm 21 is integrated with the geographic information system 5, and the early warning area information is matched according to the early warning division of the first preset level or the second preset level, wherein the early warning area information at least includes patrol path data matched with the early warning area.
Specifically, the process of integrating the early warning alarm 21 and the geographic information system 5 to divide and match the early warning region information is as follows:
various geographic information data are collected, including data of topography, geology, hydrology, weather, etc., which may include data collection using various means such as satellite remote sensing, unmanned aerial vehicle, lidar, geological exploration, and sensor networks. These data may be high resolution digital terrain models (DEMs), geologic maps, soil data, rainfall data, etc.;
the geographic information data of different sources are standardized so as to be integrated and analyzed in a GIS, and data cleaning, format conversion and geographic coordinate system unification are required;
creating a Spatial database for storing geographic information data for retrieval, query and analysis, wherein the common Spatial databases include PostgreSQL/PostGIS, mySQL Spatial, oracle Spatial, and the like;
selecting proper GIS platform or software such as ArcGIS, QGIS, GRASS GIS, etc. for data visualization, analysis and space modeling;
analyzing by using a GIS tool so as to divide an early warning area, wherein the early warning area comprises the number of the electrifying structures 20 with preset electrifying problems, the area of the wire mesh 200 corresponding to the number of the electrifying structures 20, specific electrifying problem types, early warning grades corresponding to the specific electrifying problem types and the like;
Integrating satellite remote sensing data with a GIS (geographic information system) so as to facilitate patrol path data matched with an early warning area;
advanced analysis tools in GIS, such as spatial interpolation, multi-criterion decision analysis, spatial statistical analysis and the like, are utilized to more accurately determine the early warning area;
and establishing a decision support system integrated with the GIS, so that the geological disaster emergency unit can better understand and manage the geological disaster risk and take proper preventive and countermeasure measures.
In some embodiments, referring to fig. 12, the early warning assembly further includes a vibration sensor 23, where the vibration sensor 23 is installed on the protection net structure 11 and connected with the early warning alarm 21, the vibration sensor 23 is provided with a preset level of vibration, and the vibration sensor 23 feeds back vibration early warning information matched with the preset level of vibration to the early warning alarm 21.
Specifically, the vibration sensor 23 may be at least one selected from a displacement sensor, a speed sensor, an acceleration sensor, a force sensor, a strain sensor, a torsional vibration sensor, and a torque sensor; the vibration sensors 23 are installed inside or outside the fixed bars 100 or the fixed frames 101, and each fixed bar 100 or the fixed frame 101 is provided with at least one vibration sensor 23, so that the sensor can detect vibration data related to geological disasters sensitively; in arranging the vibration sensor 23, the data acquisition frequency of the vibration sensor 23 is set to ensure enough data points for vibration analysis, typically, high frequency data acquisition (e.g., 100 samples per second) is critical for accurate monitoring of vibration events; meanwhile, the data of the vibration sensor 23 are stored on the cloud server, so that the data are prevented from being lost due to geological disasters, and the data storage safety is improved; further, the vibration sensor 23 is calibrated at set time intervals to ensure its accuracy and stability, and the calibration should include the vibration level occurring in the simulated disaster scenario.
In the actual implementation process, existing vibration analysis algorithms such as frequency domain analysis, time domain analysis, waveform recognition and the like are used for processing the sensor data to recognize potential geological disaster related vibrations, so that when the real-time sensor data is detected, the real-time sensor data is compared with preset-level vibrations, if the vibrations matched with the preset-level vibrations are detected, the real-time sensor data is immediately fed back to the early warning alarm 21 to trigger early warning alarm;
meanwhile, preset vibration levels of different geological disaster types, such as geological disasters with different vibration characteristics, such as earthquake, landslide, debris flow and the like, should be defined, further, a triggering vibration threshold value is set for each geological disaster type, and when the detected vibration exceeds a specific threshold value, the vibration sensor 23 feeds back to the early warning alarm 21 so as to trigger an early warning alarm.
Further, according to different geological disaster types, the early warning alarm 21 should set different alarm types, including at least one of sound alarm, short message, email, and mobile application notification; the warning alarm 21 immediately sends real-time feedback to the public of the relevant entity and the corresponding warning area, including disaster type, location and recommended countermeasures, upon triggering the warning alarm.
Further, in order to ensure that the early warning alarm 21 fails to work when a geological disaster occurs, the early warning alarm 21 should be set to periodically feed back the equipment state to the corresponding remote terminal, and when the early warning alarm 21 exceeds a set time threshold and is not fed back, the area where the early warning alarm 21 is located is judged to have the geological disaster.
Further, if all the warning alarms 21 in a certain area have problems and cannot work, the disaster grade warning in the certain area is raised to the highest level, and the highest grade warning is sent to relevant units and public in the certain area and the surrounding areas.
In some embodiments, referring to fig. 12, a temperature and humidity sensor 24 matched with the vibration sensor 23 may be further installed on the protection net structure 11, when the vibration sensor 23 reaches the early warning threshold, the temperature and humidity sensor 24 is synchronously used to acquire environmental temperature and humidity data, and the temperature and humidity sensor 24 is connected with the early warning alarm 21, and the environmental temperature and humidity sensor 24 feeds back flood or debris flow early warning information to the early warning alarm 21.
Referring to fig. 13, in some embodiments, a geological disaster monitoring and early warning method includes the following working steps:
step S1: and acquiring historical geological data and network body electrifying data, and integrating the historical geological data and the network body electrifying data to construct a data set.
Specifically, in step S1, referring to fig. 14, the method includes the following steps:
step S10: collecting historical geological data, including geological activity vibration intensity, temperature and humidity information; when acquiring historical geological data, the time stamp and the position information of the data need to be ensured;
step S11: collecting network body power-on data of protective net structures arranged along a road to be pre-warned, wherein the network body power-on data comprise power-off or short-circuit state data of metal wire nets contained in each protective net structure; the network body electrifying data comprise electrifying state data, time stamps and position information of each wire mesh corresponding to geological activity vibration intensity, temperature and humidity, and the electrifying state at least comprises short circuit and power failure;
step S12: time alignment is carried out on the historical geological data and the network body energizing data, so that the historical geological data and the network body energizing data have the same time stamp, and the data are aligned in time;
step S13: performing position alignment on the historical geological data and the network body energizing data to enable the historical geological data and the network body energizing data to have the same position information so as to correlate the data;
step S14: combining the aligned historical geological data with the wire mesh energizing data to construct a data set, wherein each sample in the data set comprises geological data and aligned wire mesh energizing data;
Step S15: for a pair ofEach sample in the dataset is disaster marked, indicating whether the sample represents the presence or absence of a geological disaster risk; wherein each sample is marked, indicating whether the sample represents the presence (positive class) or absence (negative class) of a geological disaster risk; the sample label isIndicating that there is a risk of geological disasters (positive class,) Or is not present (negative class,）；
step S16: and carrying out preset processing on the data set, wherein the preset processing comprises missing value, abnormal value and characteristic normalization processing.
Further, referring to fig. 15, the method for performing the preset processing on the data set is as follows:
step S160: performing missing value processing on the data set: deleting the row where the missing value is located or filling the missing value or interpolating; wherein, the missing value refers to blank or unrecorded value in the data;
step S161: outlier processing is performed on the data set: deleting the row where the outlier is located or smoothing the outlier or replacing the outlier with an adapted threshold; wherein the outlier is a significantly different value than most data;
step S162: feature normalization processing is carried out on the data set: scaling the values of the different features to the same scale using a min-max scaling method:
Wherein,is an original feature, andthe range of the values is as follows，Is a normalized feature; better convergence and training of the model are facilitated through normalization processing; in the actual data processing process, the above formula may be applied for each data to ensure that all features in the data set are normalized.
Step S2: the method for training the data set continuously by adopting the machine learning method to obtain a corrected disaster early warning model comprises the following steps: extracting preset features in the constructed data set, generating state data related to geological disasters, and training the state data by adopting a logistic regression method to obtain a corrected disaster early warning model;
specifically, referring to fig. 16, in step S2, the method includes the steps of:
step S20: extracting preset characteristics in the construction data set, wherein the preset characteristics comprise geological activity vibration intensity, temperature and humidity information related to geological disasters and matched net body power-on data, so as to generate state data related to the geological disasters;
step S21: dividing the state data into a training set and a testing set according to a preset proportion; wherein the preset ratio is typically 70% training, 30% testing;
Step S22: training the logistic regression model using the training set:
wherein,is the predicted output of the model and,is a parameter of the model and is a parameter of the model,is a transpose of the parameters and,is a natural logarithm of the number of the pairs,is a feature of the input;
and minimizing the loss function by gradient descent method with the aim of continuously updating model parametersTo reduce the value of the loss function; loss function vs. parameterThe gradient of (c) is calculated as follows:
wherein,is a loss function representing the prediction error of the model;is the number of training samples that are to be taken,is the firstThe characteristics of the individual samples are such that,is the firstLabel of each sample (0 or 1),is the loss function versus parameterIs a partial derivative of (2);
parameters (parameters)The update rule is as follows:
wherein the method comprises the steps ofIs optimized，The learning rate is controlled to be the step length of gradient descent, the learning rate is an important super parameter, and the operator is required to set according to actual conditions;
in this way, the parameters are iteratively updated using a gradient descent algorithmUntil the loss function converges or reaches a set number of exercises.
In logistic regression, a logarithmic Loss function (Log Loss) is generally used as the Loss function, and the expression of the logarithmic Loss function is as follows:
wherein,is the predictive output of the model, i.e. the sample Probability of belonging to the positive class.
Step S23: evaluating the trained logistic regression model by using the test set, and setting the corrected logistic regression model as a disaster early warning model; wherein evaluating the trained logistic regression model using the test set typically evaluates the performance of the model using at least one of the metrics of accuracy, precision, recall, F1 score, etc.
Further, accuracy is the ratio of the number of correctly classified samples to the total number of samples, and the performance of the model is evaluated by using accuracy：。
The accuracy is the proportion of the model predicted to be the positive class in the sample, and the performance of the model is estimated by adopting the accuracy:。
the recall rate is the proportion of the model correctly predicted to be the positive class in the sample actually being the positive class, and the performance of the model is evaluated by adopting the recall rate:。
the F1 score is a harmonic mean of accuracy and recall, used to balance accuracy and recall performance of the model, and the performance of the model is evaluated using the F1 score:
specifically, depending on the requirements of the application and the nature of the model, appropriate performance metrics are chosen to account for the performance of the model, e.g., if more emphasis is placed on reducing False Positives (False Positives), accuracy is concerned; if more emphasis is placed on identifying True cases (True posives), recall rates, etc. are focused on.
Step S3: deploying a disaster early warning model, and continuously collecting real-time geological data and network body electrifying data at the same time, so as to judge whether a preset disaster phenomenon exists in an early warning area according to the real-time geological data and the network body electrifying data;
step S4: if yes, triggering early warning alarm, acquiring preset early warning information according to real-time geological data and network body energizing data, further feeding back the early warning alarm information containing the preset early warning information to a preset object, and if not, returning to the step S3, and re-acquiring the real-time geological data and the network body energizing data;
when continuously collecting real-time geological data and network body energizing data, the method can use a deployed disaster early warning model to predict, and if the disaster early warning model predicts potential geological disaster risks (positive types), the method triggers early warning.
Step S5: disaster state data of the early warning area are obtained, and meanwhile, the disaster state data are continuously and synchronously fed back to a preset object.
Referring to fig. 17, in some real-time examples, particularly in step S160, the method includes the steps of:
step S1600: identifying missing values in the dataset; wherein the missing value is typically represented by a special identifier (such as NaN or null);
Step S1601: judging whether a row which contains at least one missing value and has a low proportion of the missing value exists in the data set or not;
step S1602: if yes, deleting the row containing the missing value in the data set, namely: if a row in the dataset contains one or more missing values and the proportion of missing values is small, then the row containing missing values can be deleted; the method for processing the missing values is suitable for the conditions that the proportion of the missing values is low and the missing values have little influence on the overall analysis of the data set;
if not, step S1603 is executed: and carrying out preset filling on missing values existing in the data set, or carrying out preset interpolation on the missing values existing in the data set.
Specifically, for numerical features, filling missing values may be selected, common filling methods include replacing missing values with mean, median, or other statistics; exemplary, e.g., replacing the missing value with the average value:
assume that there is a numerical featureThe number of times that the missing value NaN is included may be filled with the missing value using the mean μ:
wherein the method comprises the steps ofIs the feature after filling, μ isA mean value throughout the dataset.
Specifically, for spatial or temporal data, an interpolation method can be selected to infer possible values of the missing values according to known data, where the interpolation method includes linear interpolation, polynomial interpolation, kriging interpolation, and the like; illustratively, the missing values are estimated, for example, by linear interpolation:
Assume that there is one-dimensional time series data in whichAndis the data of the known time pointIs the missing point in time, and can be estimated using linear interpolationIs the value of (1):
wherein,andit is a known point in time at which,is the missing time point.
Referring to fig. 18, in some real-time examples, particularly in step S161, the method includes the steps of:
step S1610: identifying outliers in the dataset; wherein outliers are typically significantly different values than most data points, which can be detected by visual or statistical methods;
step S1611: judging whether the abnormal value in the data set is lower in proportion or not, and the influence of the abnormal value on the overall analysis of the data set is larger;
step S1612: if yes, deleting the row containing the abnormal value in the data set, namely: if the influence of the outlier on the overall analysis of the data set is large, selecting to delete the row containing the outlier; the method is suitable for the situation that the proportion of the abnormal value is low and the influence of the abnormal value on the analysis result is large.
If not, then step S1613 is performed: and processing the abnormal value existing in the data set by adopting a preset smoothing method, or replacing the abnormal value with a preset threshold value.
Specifically, the preset smoothing method comprises the steps of using sliding window average and exponential smoothing to reduce the influence of abnormal values, wherein the selection of the preset smoothing method is based on the property of data and the requirement of problems; exemplary, e.g., dealing with outliers with an exponential smoothing method:
Exponential smoothing is a method of smoothing data by weighting average data points, typically used for time series data, as follows:
initializing smoothed valuesFor the first observation of data, i.e.
For subsequent data pointsCalculating a smoothed value：
Wherein,is a smoothing parameter, controls the weight of the new data point, and usually takes a value between 0 and 1;
each data point in the raw data is then replaced with its corresponding smoothed value.
Specifically, the abnormal value is replaced by a preset threshold value, so that the abnormal value is not considered as abnormal any more, and the selection of the preset threshold value is adjusted according to the requirements and the characteristics of the data; illustratively, an outlier greater than a certain threshold is replaced with the threshold:
assuming that we have a numerical feature that contains outliers, we can choose to replace outliers above a certain threshold with the threshold, which can be a fixed constant or can be determined based on the distribution and characteristics of the data.
Referring to fig. 19, in some real-time examples, particularly in step S3, the method includes the steps of:
step S30: deploying the disaster early warning model to a preset object, and continuously collecting real-time geological data and network energizing data;
Step S31: inputting continuously collected real-time geological data and network electrifying data into a disaster early warning model, and judging whether a preset disaster phenomenon exists in an early warning area according to the output result of the disaster early warning model;
step S32: if yes, triggering early warning alarm, acquiring preset early warning information according to real-time geological data and network body electrifying data, further feeding back the early warning alarm information containing the preset early warning information to a preset object, and if not, returning to the step S31, and inputting the acquired real-time geological data and network body electrifying data into a disaster early warning model.
The invention also provides a computer medium, wherein the computer medium is stored with a computer program, and the computer program is executed by a processor to realize the geological disaster monitoring and early warning method.
The invention also provides a computer, comprising the computer medium.
Referring to fig. 20, the invention further provides a geological disaster monitoring and early warning system, which uses the geological disaster early warning method to monitor and early warn geological disasters, and further comprises:
the data processing module 1000 is configured to acquire historical geological data and network body power-on data, and integrate the historical geological data and the network body power-on data to construct a data set;
The model training module 1001 is configured to train the data set continuously by using a machine learning method to obtain a corrected disaster early warning model, and includes: extracting preset features in the constructed data set, generating state data related to geological disasters, and training the state data by adopting a logistic regression method to obtain a corrected disaster early warning model;
the model prediction module 1002 is configured to deploy a disaster early warning model, and continuously collect real-time geological data and network body power-on data, so as to judge a preset disaster phenomenon of an early warning area according to the real-time geological data and the network body power-on data;
the early warning alarm module 1003 is configured to trigger an early warning alarm, and obtain preset early warning information according to real-time geological data and network body power-on data, so as to feed back early warning alarm information containing the preset early warning information to a preset object;
the area monitoring module 1004 is configured to obtain disaster status data of the early warning area, and continuously and synchronously feed back the disaster status data to a preset object.
In the description of the present specification, a description referring to terms "one embodiment," "some embodiments," "examples," "specific examples," or "some examples," etc., means that a particular feature, structure, material, or characteristic described in connection with the embodiment or example is included in at least one embodiment or example of the present invention. In this specification, schematic representations of the above terms are not necessarily directed to the same embodiment or example. Furthermore, the particular features, structures, materials, or characteristics described may be combined in any suitable manner in any one or more embodiments or examples. Furthermore, the different embodiments or examples described in this specification and the features of the different embodiments or examples may be combined and combined by those skilled in the art without contradiction.
While embodiments of the present invention have been shown and described above, it will be understood that the above embodiments are illustrative and not to be construed as limiting the invention, and that variations, modifications, alternatives and variations may be made to the above embodiments by one of ordinary skill in the art within the scope of the invention.
Claims (10)
1. The geological disaster monitoring and early warning method is characterized by comprising the following steps of:
step S1: acquiring historical geological data and network body electrifying data, and integrating the historical geological data and the network body electrifying data to construct a data set;
step S2: the method for training the data set continuously by adopting the machine learning method to obtain a corrected disaster early warning model comprises the following steps: extracting preset features in the constructed data set, generating state data related to geological disasters, and training the state data by adopting a logistic regression method to obtain a corrected disaster early warning model;
step S3: deploying a disaster early warning model, and continuously collecting real-time geological data and network body electrifying data at the same time, so as to judge whether a preset disaster phenomenon exists in an early warning area according to the real-time geological data and the network body electrifying data;
step S4: if yes, triggering early warning alarm, acquiring preset early warning information according to real-time geological data and network body energizing data, further feeding back the early warning alarm information containing the preset early warning information to a preset object, and if not, returning to the step S3, and re-acquiring the real-time geological data and the network body energizing data;
Step S5: disaster state data of the early warning area are obtained, and meanwhile, the disaster state data are continuously and synchronously fed back to a preset object.
2. The geological disaster monitoring and early warning method according to claim 1, wherein in step S1, the method comprises the steps of:
step S10: collecting historical geological data, including geological activity vibration intensity, temperature and humidity information;
step S11: collecting network body power-on data of protective net structures arranged along a road to be pre-warned, wherein the network body power-on data comprise power-off or short-circuit state data of metal wire nets contained in each protective net structure;
step S12: time alignment is carried out on the historical geological data and the network body electrifying data, so that the historical geological data and the network body electrifying data have the same time stamp;
step S13: performing position alignment on the historical geological data and the network body electrifying data to enable the historical geological data and the network body electrifying data to have the same position information;
step S14: combining the aligned historical geological data with the wire mesh energizing data to construct a data set, wherein each sample in the data set comprises geological data and aligned wire mesh energizing data;
step S15: performing disaster marking on each sample in the data set to indicate whether the sample represents the existence or non-existence of geological disaster risks;
Step S16: and carrying out preset processing on the data set, wherein the preset processing comprises missing value, abnormal value and characteristic normalization processing.
3. The geological disaster monitoring and early warning method according to claim 2, wherein in step S16, the method comprises the steps of:
step S160: performing missing value processing on the data set: delete the row where the missing value is located or fill the missing value or interpolate:
step S161: outlier processing is performed on the data set: deleting the row where the outlier is located or smoothing the outlier or replacing the outlier with an adapted threshold;
step S162: feature normalization processing is carried out on the data set: scaling the values of the different features to the same scale using a min-max scaling method:wherein (1)>Is the original feature, and->The range of the values is as follows，/>Is a normalized feature.
4. A geological disaster monitoring and warning method according to claim 3, characterized in that in step S160, the method comprises the steps of:
step S1600: identifying missing values in the dataset;
step S1601: judging whether a row which contains at least one missing value and has a low proportion of the missing value exists in the data set or not;
step S1602: if yes, deleting the row containing the missing value in the data set, and if not, carrying out preset filling on the missing value existing in the data set, or carrying out preset interpolation on the missing value existing in the data set.
5. A geological disaster monitoring and early warning method according to claim 3, characterized in that in step S161, the method comprises the steps of:
step S1610: identifying outliers in the dataset;
step S1611: judging whether the abnormal value in the data set is lower in proportion or not, and the influence of the abnormal value on the overall analysis of the data set is larger;
step S1612: if yes, deleting the row containing the abnormal value in the data set, otherwise, adopting a preset smoothing method to process the abnormal value in the data set, or replacing the abnormal value with a preset threshold value.
6. The geological disaster monitoring and early warning method according to claim 2, wherein in step S2, the method comprises the steps of:
step S20: extracting preset characteristics in the construction data set, wherein the preset characteristics comprise geological activity vibration intensity, temperature and humidity information related to geological disasters and matched net body power-on data, so as to generate state data related to the geological disasters;
step S21: dividing the state data into a training set and a testing set according to a preset proportion;
step S22: training the logistic regression model using the training set:wherein (1)>Is the predictive output of the model,/ >Is a parameter of the model, +.>Is the transpose of the parameters>Is natural logarithm, is->Is a feature of the input;
and optimizing parameters by minimizing loss functions：/> Wherein->Is optimized +.>，/>Is a loss function representing the prediction error of the model; />Is the number of training samples, +.>Is->Characteristics of individual samples, +_>Is->Label of individual samples->Is a loss function vs. parameter->Partial derivative of>Is the learning rate;
step S23: and evaluating the trained logistic regression model by using the test set, and setting the corrected logistic regression model as a disaster early warning model.
7. The geological disaster monitoring and early warning method according to claim 6, wherein in step S3, the method comprises the steps of:
step S30: deploying the disaster early warning model to a preset object, and continuously collecting real-time geological data and network energizing data;
step S31: inputting continuously collected real-time geological data and network electrifying data into a disaster early warning model, and judging whether a preset disaster phenomenon exists in an early warning area according to the output result of the disaster early warning model;
step S32: if yes, triggering early warning alarm, acquiring preset early warning information according to real-time geological data and network body electrifying data, further feeding back the early warning alarm information containing the preset early warning information to a preset object, and if not, returning to the step S31, and inputting the acquired real-time geological data and network body electrifying data into a disaster early warning model.
8. A geological disaster monitoring and early warning system, comprising:
the data processing module is used for acquiring historical geological data and network body electrifying data, integrating the historical geological data and the network body electrifying data and constructing a data set;
the model training module is used for continuously training the data set by adopting a machine learning method to obtain a corrected disaster early warning model, and comprises the following steps: extracting preset features in the constructed data set, generating state data related to geological disasters, and training the state data by adopting a logistic regression method to obtain a corrected disaster early warning model;
the model prediction module is used for deploying a disaster early warning model, continuously collecting real-time geological data and network body electrifying data, and judging a preset disaster phenomenon of an early warning area according to the real-time geological data and the network body electrifying data;
the early warning alarm module is used for triggering early warning alarm, acquiring preset early warning information according to real-time geological data and network body power-on data, and feeding back early warning alarm information containing the preset early warning information to a preset object;
the regional monitoring module is used for acquiring disaster state data of the early warning region and continuously feeding back the disaster state data to a preset object synchronously.
9. The geological disaster monitoring and early warning system of claim 8, further comprising:
the protection assembly comprises fixing pieces and a protection net structure, a plurality of fixing pieces are arranged in an array along the road of the road to be early-warned, and a protection early-warning interval is formed among the plurality of fixing pieces; the protective net structure is arranged in the protective early warning interval and is provided with a hollow layer;
the early warning assembly comprises an electrifying structure, an early warning alarm and an early warning unit, wherein the electrifying structure comprises a wire mesh and an electrifying connecting piece, the wire mesh is paved in the hollow layer, and two ends of the electrifying connecting piece are respectively and electrically connected with the wire mesh and a road power supply system to be early warned; the early warning alarm is arranged in an early warning area of a road to be early warned, and early warning alarm information comprising the early warning area is fed back to a preset object through the early warning alarm; the two ends of the early warning unit are respectively connected with the wire mesh and the early warning alarm, the electrifying state of the wire mesh is judged in real time through the early warning unit, and after the wire mesh has the preset electrifying problem, preset early warning information is fed back to the early warning alarm;
And the remote monitoring equipment is connected with the early warning alarm, and the state of the early warning area is identified and judged through the remote monitoring equipment.
10. The geological disaster monitoring and early warning system according to claim 9, wherein the early warning assembly further comprises a vibration sensor and a temperature and humidity sensor, wherein the vibration sensor and the temperature and humidity sensor are installed in the protective net structure and are respectively connected with the early warning alarm, and the vibration sensor is used for passing through the vibration sensor.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311353590.1A CN117116024B (en) | 2023-10-19 | 2023-10-19 | Geological disaster monitoring and early warning system, method, computer medium and computer |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311353590.1A CN117116024B (en) | 2023-10-19 | 2023-10-19 | Geological disaster monitoring and early warning system, method, computer medium and computer |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN117116024A true CN117116024A (en) | 2023-11-24 |
| CN117116024B CN117116024B (en) | 2023-12-26 |
Family
ID=88796833
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311353590.1A Active CN117116024B (en) | 2023-10-19 | 2023-10-19 | Geological disaster monitoring and early warning system, method, computer medium and computer |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117116024B (en) |
Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2005017230A (en) * | 2003-06-27 | 2005-01-20 | Central Japan Railway Co | Falling-rock detection line attaching tool, and falling rock detector |
| CN102063776A (en) * | 2010-11-18 | 2011-05-18 | 南宁铁路局 | Dangerous rock falling stone alarm system and method for dangerous rock falling stone alarm |
| CN104751374A (en) * | 2015-03-27 | 2015-07-01 | 深圳供电局有限公司 | Method for predicting wireless communication fault of metering automation system |
| CN105788179A (en) * | 2016-03-23 | 2016-07-20 | 重庆交通大学 | System and method of intelligently monitoring dangerous rock collapse and rockfall hazard |
| US20170046628A1 (en) * | 2014-05-14 | 2017-02-16 | Nec Corporation | Information processing device, anomaly detection method and recording medium |
| CN110390800A (en) * | 2019-06-06 | 2019-10-29 | 北京市地质研究所 | Net formula disaster monitoring and early-warning system |
| CN112687081A (en) * | 2021-01-19 | 2021-04-20 | 交通运输部公路科学研究所 | Monitoring and grading early warning method for toppling type collapse disaster |
| CN115662066A (en) * | 2022-07-07 | 2023-01-31 | 柳州职业技术学院 | Natural disaster detection device and prediction method |
| CN115691084A (en) * | 2022-10-31 | 2023-02-03 | 西安长地空天科技有限公司 | Slope safety monitoring method and device based on multi-source heterogeneous sensor data fusion |
-
2023
- 2023-10-19 CN CN202311353590.1A patent/CN117116024B/en active Active
Patent Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2005017230A (en) * | 2003-06-27 | 2005-01-20 | Central Japan Railway Co | Falling-rock detection line attaching tool, and falling rock detector |
| CN102063776A (en) * | 2010-11-18 | 2011-05-18 | 南宁铁路局 | Dangerous rock falling stone alarm system and method for dangerous rock falling stone alarm |
| US20170046628A1 (en) * | 2014-05-14 | 2017-02-16 | Nec Corporation | Information processing device, anomaly detection method and recording medium |
| CN104751374A (en) * | 2015-03-27 | 2015-07-01 | 深圳供电局有限公司 | Method for predicting wireless communication fault of metering automation system |
| CN105788179A (en) * | 2016-03-23 | 2016-07-20 | 重庆交通大学 | System and method of intelligently monitoring dangerous rock collapse and rockfall hazard |
| CN110390800A (en) * | 2019-06-06 | 2019-10-29 | 北京市地质研究所 | Net formula disaster monitoring and early-warning system |
| CN112687081A (en) * | 2021-01-19 | 2021-04-20 | 交通运输部公路科学研究所 | Monitoring and grading early warning method for toppling type collapse disaster |
| CN115662066A (en) * | 2022-07-07 | 2023-01-31 | 柳州职业技术学院 | Natural disaster detection device and prediction method |
| CN115691084A (en) * | 2022-10-31 | 2023-02-03 | 西安长地空天科技有限公司 | Slope safety monitoring method and device based on multi-source heterogeneous sensor data fusion |
Also Published As
| Publication number | Publication date |
|---|---|
| CN117116024B (en) | 2023-12-26 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Pecoraro et al. | Monitoring strategies for local landslide early warning systems | |
| KR101788104B1 (en) | System and method for real-time early warning for extreme rainfall-induced landslides | |
| US20230046111A1 (en) | Multilevel Rapid Warning System for Landslide Detection | |
| CN102741895B (en) | Method and system for automated location dependent natural disaster forecast | |
| US20230259798A1 (en) | Systems and methods for automatic environmental planning and decision support using artificial intelligence and data fusion techniques on distributed sensor network data | |
| CN107610421A (en) | A kind of geo-hazard early-warning analysis system and method | |
| Kirschbaum et al. | A dynamic landslide hazard assessment system for Central America and Hispaniola | |
| CN112561274A (en) | Typhoon-induced geological disaster risk assessment method based on multi-element situation | |
| CN110858334A (en) | Road safety assessment method and device and road safety early warning system | |
| Mück et al. | Assessing building vulnerability to earthquake and tsunami hazard using remotely sensed data | |
| KR101290824B1 (en) | Infrastructure maintenance and management businesssupport system | |
| Cappello et al. | Lava flow hazards—An impending threat at Miyakejima volcano, Japan | |
| Pollino et al. | An open source GIS system for earthquake early warning and post-event emergency management | |
| CN118094375A (en) | Four-in-one mining ground surface subsidence space-time continuous sensing method | |
| CN117116024B (en) | Geological disaster monitoring and early warning system, method, computer medium and computer | |
| Sättele et al. | A classification of warning system for natural hazards | |
| Balamurugan et al. | An IoT based Natural Disaster Monitoring for Railway Accident Warning Alert System | |
| CN116050837A (en) | Comprehensive monitoring early warning and safety assessment scheme for tailing pond multielement disasters | |
| Mandal et al. | A neural network based prediction model for flood in a disaster management system with sensor networks | |
| Zuccolo et al. | Regional Low‐Magnitude GMPE to Estimate Spectral Accelerations for Earthquake Early Warning Applications in Southern Italy | |
| CN114118797A (en) | Real-time monitoring system and method based on tunnel risks and disasters | |
| TWI784583B (en) | Portable Automatic Disaster Early Warning and Notification System | |
| CN106231298B (en) | Giant-screen remotely intelligently monitoring method, apparatus and system | |
| CN112071009A (en) | Optical fiber pipeline early warning system and method thereof | |
| CN116739357B (en) | Multi-mode fusion perception city existing building wide area monitoring and early warning method and device |
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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |