CN112903008A - Mountain landslide early warning method based on multi-sensing data fusion technology - Google Patents
Mountain landslide early warning method based on multi-sensing data fusion technology Download PDFInfo
- Publication number
- CN112903008A CN112903008A CN202110052736.3A CN202110052736A CN112903008A CN 112903008 A CN112903008 A CN 112903008A CN 202110052736 A CN202110052736 A CN 202110052736A CN 112903008 A CN112903008 A CN 112903008A
- Authority
- CN
- China
- Prior art keywords
- landslide
- displacement
- probability
- converting
- fuzzy set
- 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
Images
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01D—MEASURING NOT SPECIALLY ADAPTED FOR A SPECIFIC VARIABLE; ARRANGEMENTS FOR MEASURING TWO OR MORE VARIABLES NOT COVERED IN A SINGLE OTHER SUBCLASS; TARIFF METERING APPARATUS; MEASURING OR TESTING NOT OTHERWISE PROVIDED FOR
- G01D21/00—Measuring or testing not otherwise provided for
- G01D21/02—Measuring two or more variables by means not covered by a single other subclass
Landscapes
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Testing Or Calibration Of Command Recording Devices (AREA)
- Pit Excavations, Shoring, Fill Or Stabilisation Of Slopes (AREA)
Abstract
The invention provides a landslide early warning method based on a multi-sensing data fusion technology, which comprises the following steps of: step S1: respectively measuring the effective rainfall, the earth surface displacement and the deep displacement of the monitoring point position, and respectively converting the effective rainfall, the earth surface displacement and the deep displacement into corresponding landslide occurrence probabilities; step S2: converting the three landslide probabilities into an intuitionistic fuzzy set respectively; step S3: calculating a weight coefficient based on entropy and fuzzy divergence measure to obtain a weighted basic probability assignment function; step S4: and carrying out iterative processing by using an improved DS evidence theory fusion rule to obtain a fusion result as the probability of the final landslide. The method can reduce false alarm and missing alarm, and improve the effectiveness and reliability of early warning.
Description
Technical Field
The invention belongs to the technical fields of electronic information science and technology, communication technology and disaster prevention and reduction, and particularly relates to a landslide early warning method based on a multi-sensing data fusion technology.
Background
The landslide is used as a common disaster type in geological disasters, scientific and reasonable monitoring is carried out on the landslide, and the threats to the lives and properties of people can be effectively reduced. According to incomplete statistics, economic loss caused by geological disasters reaches billions of yuan every year, and the number of casualties reaches thousands of people, so that the research on the early warning system is of great significance. The landslide occurrence is a process from gradual change to sudden change, and if the landslide characteristic information of a monitoring point can be accurately and timely acquired and the landslide occurrence time and the landslide development trend are effectively judged, the aims of disaster prevention and reduction can be achieved.
The landslide monitoring method comprises a station setting observation method, a seam measuring method, a GPS measuring method, a close-range shooting remote sensing method, a ground inclination method, an image processing method and the like. The station setting observation method is mainly characterized in that some mark points are arranged on the surface of a slope body, and changes of the mark points are observed by using fixed points. The ground slope measuring method is to embed slope measuring pipe in the drilled hole, slide the slope measuring probe in the pipe, and calculate the deviation of the slope measuring probe from the vertical direction through the different gravity effects of the pendulum bob in the probe, and calculate the deformation of the slope. The seam measuring method is mainly characterized in that a seam measuring instrument or device is arranged at a crack of a mountain body, further monitoring is carried out on an area where landslide is generated, the seam measuring method is suitable for the monitored area where local landslide is generated, and common instruments comprise a seam measuring meter, a telescopic meter, a multifunctional frequency tester and the like. The GPS measurement method can record the three-dimensional coordinate change of the observation point on the surface of the landslide body by using the GPS, and analyze and judge the motion rule of the landslide body according to the long-term change of the coordinate points. The remote sensing method is that a certain signal (generally electromagnetic wave and sound wave) is transmitted to the surface of the slope body by using a transmitting device outside the slope body, the signal change is obtained by reflection, and the precursor information of the slope body is reflected by extracting the signal characteristics. The image processing method for monitoring landslide is characterized in that a marker is calibrated in a tested landslide area, and the motion trail of the marker is identified by using an image processing technology, so that the motion trail of a landslide body is obtained.
The traditional landslide monitoring method is that a geological survey worker holds professional detection equipment by hand to measure on site, and makes judgment by combining own experience, and the requirements on the aspects of measurement efficiency, accuracy and intellectualization are difficult to meet. The three-dimensional coordinate change of the landslide surface is observed by using systems such as a Global Positioning System (GPS), a Remote Sensing (RS) system, a Beidou navigation system and the like, and the motion rule of the landslide body is analyzed through the coordinate change of the test points, so that the precursor information of the landslide body is remotely obtained, but the aspects are only monitoring the surface deformation of the landslide body and cannot accurately monitor the internal information of the landslide body, and thus, accurate prediction is realized. The method of the drilling inclinometer is to drill a hole at a specific position and install a displacement sensor, and can monitor the displacement of any depth in a landslide. The landslide is monitored by an image processing method, a marker is calibrated in a tested landslide area, the motion trail of the marker is identified by using an image processing technology, so that the motion trail of a landslide body is obtained, the change of the surface of the landslide is observed by the method, the landslide can be detected only when the landslide occurs, and good early warning cannot be realized. Meanwhile, a large amount of time is consumed in the transmission amount and the processing amount of data, and the effect is not good in high efficiency and high utilization rate.
Because the landslide forming mechanism is complex, and the traditional landslide early warning system usually only adopts a single sensor for early warning, and does not comprehensively consider the geographic environment, the weather condition and the monitored physical quantity characteristic data, the phenomena of false alarm, missing report and the like are easily generated at the moment, or the problems of untimely and inaccurate early warning and the like are easily generated. Part of the prediction system adopts the traditional fuzzy set theory, does not consider uncertain factors, and is not accurate enough in describing information; or the mean value method is adopted to process the fuzzy matrix, so that the difference of the influence of important parameters such as rainfall, displacement and the like on the landslide cannot be correctly reflected, and therefore effective and comprehensive judgment cannot be made, and the effectiveness and reliability of the early warning system are influenced.
Disclosure of Invention
Aiming at the defects and the blank existing in the prior art, the invention provides a landslide early warning method based on a multi-sensor data fusion technology, and based on the RTK technology, the intuitionistic fuzzy set theory and the multi-sensor fusion technology of a Beidou foundation enhancement system, a novel landslide monitoring system is invented, and the system can make comprehensive and effective evaluation or decision on each element generating landslide, improve the accuracy and the reliability of the landslide early warning, reduce false alarm and missed alarm, and thus can reduce the personal and property loss to the minimum. The multi-sensor fusion technology is characterized in that internal and external characteristic parameters of landslide monitoring points are collected through different sensors, and information provided by the parameters is effectively fused, so that landslide is comprehensively described, the defect that a single sensor has a blind area is overcome, the uncertainty of information is reduced, and the decision accuracy is improved. The intuition fuzzy set considers the membership function, the non-membership function and the hesitation function, and compared with the traditional fuzzy set theory, the intuition fuzzy set theory can express more fuzzy information, has more comprehensive description on events, and is suitable for solving the conditions of inconsistent and uncertain information.
The traditional method only adopts a single sensor for early warning, does not comprehensively consider the geographic environment, the weather condition and the monitored physical quantity characteristic data, and easily generates the phenomena of false alarm, missing report and the like. In order to solve the problem, the system adopts rainfall, RTK surface displacement, a depth displacement sensor and the like for detection, utilizes the RTK to measure the displacement, can reach millimeter-scale precision, utilizes the depth displacement sensor to provide internal deformation information of a monitoring point, and considers other factors causing landslide. On the basis, a method for converting the information obtained by each sensor into a probability and intuitionistic fuzzy set is provided, and an improved evidence theory is utilized to carry out fusion processing, so that a better result is obtained.
The method includes the steps that internal and external landslide characteristic data of monitoring points are accurately obtained through multiple sensors, in order to reflect difference of importance degree of each attribute in an information fusion process, a fusion coefficient in the information fusion is related to influence degree of the parameter on landslide, and a solving method of the fusion coefficient is provided. The principle is shown in fig. 1. 1) The effective rainfall capacity of the position of the monitoring point, the position coordinate of the earth surface and the deep displacement are respectively measured by a rainfall measuring instrument, a GNSS positioning system and a depth displacement transmitter, and the horizontal and vertical displacement of the earth surface and the effective rainfall capacity of the monitoring point are resolved by an RTK technology. The horizontal precision of the displacement measured by RTK can reach 1mm, and the height precision can reach 2.5 mm; the characteristic information of the interior of the landslide point can be obtained by utilizing a deep displacement sensor; most landslides occur in association with strong rainfall. 2) Using models to monitorThe effective rainfall at the survey point, the ratio of the horizontal and vertical displacement, the depth displacement are converted into the probability of occurrence of a landslide p (x). 3) Considering that the landslide is a gradual change and a process from quantitative change to qualitative change, a transition section exists between the gradual change and the qualitative change, so that the probability P (X) of the occurrence of the landslide is converted into a basic probability assignment function { U (x) } of an intuitional fuzzy setR(x),VR(x),πR(x) Where U represents a certain probability of occurrence of a landslide, V represents a certain probability of non-occurrence of a landslide, and pi represents ambiguity representing the probability of possible or impossible occurrence of a landslide. 4) And calculating a divergence measure matrix DMM, and calculating a weighting coefficient of each parameter influencing the landslide according to the DMM and the weighting entropy. 5) Obtaining a weighted basic probability assignment function according to the weighting coefficient; 6) and carrying out iterative processing by utilizing an improved DS evidence theory fusion rule to obtain a fusion result, and making a judgment according to the fusion result. 7) Comparing the fusion result with a set threshold value, and if the fusion result is smaller than the threshold value, continuing monitoring; when the threshold value is larger than the threshold value, the situation that a potential danger occurs in the landslide is shown, early warning is given, images of the site are shot to a mobile terminal (an operator), the result is notified to a disaster prevention and reduction department to make a decision basis, and the monitoring site generates an audible and visual alarm to remind vehicles and personnel of accessories. Meanwhile, an operator can remotely check the information and the pictures of the monitoring points in real time, so that false alarm and missing alarm can be reduced, and the effectiveness and the reliability of early warning are improved.
The invention specifically adopts the following technical scheme:
a landslide early warning method based on a multi-sensor data fusion technology is characterized by comprising the following steps:
step S1: respectively measuring the effective rainfall, the earth surface displacement and the deep displacement of the monitoring point position, and respectively converting the effective rainfall, the earth surface displacement and the deep displacement into corresponding landslide occurrence probabilities;
step S2: converting the three landslide probabilities into an intuitionistic fuzzy set respectively;
step S3: calculating a weight coefficient based on entropy and fuzzy divergence measure to obtain a weighted basic probability assignment function;
step S4: and carrying out iterative processing by using an improved DS evidence theory fusion rule to obtain a fusion result as the probability of the final landslide.
Preferably, in step S1, the effective rainfall, the surface displacement and the deep displacement of the monitoring point position are measured by the rainfall measuring instrument, the GNSS positioning system and the depth displacement transmitter, respectively.
Preferably, step S1 specifically includes the following steps:
step S31: converting the effective rainfall into the probability of landslide:
the effective rainfall is calculated by the following formula:
Al＝0.5406×e-3.392×l+7.94×10-2e-0.1286×l (2)
where l is 0 or x0Represents the rainfall 24 hours of the day, x when l is 11Represents the rainfall 24 hours before the day, and x is 2 hours2Represents x when the rainfall is 24 hours in two days and l is 33Representing 24 hours rainfall in the first three days, AlRepresents a weight coefficient per day;
converting the effective rainfall into a probability of producing landslide using the following equation:
PR(R)＝(1.134×10-4×R3-0.02814×R2+2.348×R+12.96)/100(3)；
step S32: converting the earth surface displacement into the probability of landslide:
calculating the horizontal displacement and the vertical displacement of the measuring point by utilizing a GNSS positioning system and an RTK technology, and converting the ratio of the horizontal displacement and the vertical displacement into the probability of landslide:
PG(k)＝0.8539e0.04242k-2.248e-13.73k (4)
wherein k represents a ratio of the horizontal displacement amount to the vertical displacement amount;
step S33: converting the deep displacement amount into a probability of occurrence of a landslide:
where d represents the depth displacement amount.
Preferably, in step S2, the conventional fuzzy set theory adopts membership and non-membership to describe the fuzzy concept that the event is not black or white, and it is difficult to describe the ambiguity of the event. Considering that the landslide event is a gradual change process from quantitative change to qualitative change, the invention describes the landslide event by adopting three aspects of membership U, non-membership V and hesitation Pi. Membership and non-membership clearly characterize the degree of landslide generation (not generation), hesitation describes the degree of landslide ambiguity generation, and hesitation is greater when the probability of landslide generation is around 50%. With respect to this characteristic, the probability of occurrence of a landslide, which is obtained by converting the effective rainfall amount, the surface displacement amount, and the depth displacement amount, is converted into an intuitive fuzzy set m ═ { u (x), v (x), pi (x) }:
U(x)＝P(x)-0.5π(x) (7)
V(x)＝1-π(x)-U(x) (8)；
the function is characterized in that the hesitation degree is larger when the landslide probability is closer to 50%, and the hesitation degree is smaller when the landslide probability has stronger definition.
Converting the probability of landslide generated by effective rainfall by using formulas (6) to (8) to obtain an intuitionistic fuzzy set
Wherein subscript R represents effective rainfall;
converting the probability of landslide generated by depth displacement by using formulas (6) to (8) to obtain an intuitionistic fuzzy set
Wherein subscript D represents a depth displacement amount;
converting the probability of generating landslide by using the surface displacement ratio by using the formulas (6) to (8) to obtain an intuitionistic fuzzy set
Where subscript G represents the ratio of the amount of horizontal displacement to the amount of vertical displacement of the surface.
Preferably, step S3 specifically includes the following steps:
step S31: determining a weighting coefficient based on the hesitation intuition fuzzy entropy:
wherein n respectively represents R, D, G three fuzzy set functions;
step S32: constructing a similarity matrix C between sensors in any landslide prediction system: the intuitive fuzzy set of three sensors is known as:
the similarity matrix between them is:
wherein, i and j can respectively take three fuzzy set functions of R, D and G; when i ═ j, i.e., the intuitive fuzzy sets, are the same, the similarity between them is 1; the similarity matrix C between the 3 sensors R, D, G in the invention is obtained by the method
Calculating the support Sup for the generation of landslide of the pairs R, D, G, the subscripts representing the different sensors:
normalizing the support of each sensor:
step S33: calculating the weighting coefficient of each sensor intuition fuzzy set to obtain a weighting basic probability assignment function B:
preferably, step S4 specifically includes the following steps:
let the intuitive fuzzy set function be
Performing fusion treatment by using an improved DS evidence theory method, wherein the fusion result is F, and the fusion process is as follows:
the intuitive fuzzy set of the fusion result F is
Performing 2 times of iteration processing on the weighted fuzzy set probability distribution function by using the fusion algorithm to obtain the final fusion result
Preferably, when the membership function in the fusion result is greater than the threshold value of 0.5, a pre-alarm is given, the related departments for disaster prevention and reduction are informed, and an alarm is given on site.
The invention and the preferable scheme thereof have the following beneficial effects:
1) the RTK technology is used for measuring displacement, the horizontal precision can reach 1mm, and the height precision can reach 2.5mm, so that the accuracy of mountain landslide early warning can be greatly improved.
2) And converting the effective rainfall, the surface displacement, the depth displacement and the crack size into the probability of generating the landslide by utilizing each model, providing a probability conversion method, and converting the probability into a basic probability assignment function of an intuitive fuzzy set.
3) And obtaining the intuitive fuzzy set weighting coefficient of each sensor by using a self-adaptive mode to obtain a weighted basic probability assignment function. And (3) considering the gradual change of landslide, giving out how to convert the probability into an intuitive fuzzy set, and giving out the weighting coefficient of each sensor according to the fuzzy entropy and the divergence measure to obtain a weighted fuzzy intuitive probability distribution function.
4) And fusion processing is carried out by utilizing an improved DS evidence theory, and decision judgment is given, so that the reliability and the effectiveness are improved.
In the prior art, if only a single sensor is adopted for early warning, geographical environment, weather conditions and monitored physical quantity characteristic data are not comprehensively considered, and phenomena such as false alarm, missing report and the like are easily generated at the moment. In order to solve the problem, the invention adopts rainfall, RTK surface displacement, a depth displacement sensor and the like for detection, utilizes the RTK to measure the displacement, can reach millimeter-scale precision, utilizes the depth displacement sensor to provide internal deformation information of a monitoring point, and considers other factors causing mountain landslide. On the basis, a method for converting information obtained by each sensor into a probabilistic and intuitive fuzzy set is provided, and an improved evidence theory is utilized to perform fusion processing to obtain a better result, so that the reliability, effectiveness and accuracy of landslide early warning can be effectively improved.
Drawings
The invention is described in further detail below with reference to the following figures and detailed description:
FIG. 1 is a schematic flow chart of an embodiment of the present invention.
Detailed Description
In order to make the features and advantages of the present invention comprehensible, embodiments accompanied with figures are described in detail as follows:
as shown in fig. 1, based on the overall scheme of the landslide early warning method based on the multi-sensor data fusion technology provided by the present invention, a specific embodiment is provided below to further show and explain the scheme:
step 1: monitoring landslide monitoring points by using a rainfall capacity measuring instrument, a GNSS navigation system and a deep displacement sensor, wherein the effective rainfall capacity at a certain moment is 20mm, and the probability of inferring landslide from the parameters is 49.6% according to a formula (3); the ratio of the horizontal displacement to the vertical displacement is 0.1, and the probability of inferring landslide from the parameter is 28.8% according to the formula (4); the deep displacement was 200mm, and the probability of estimating a landslide from this parameter was 22.3% as seen from the formula (5).
Step 2: and (4) converting the probability data acquired by the rainfall capacity measuring instrument, the GNSS navigation system and the deep displacement sensor into an intuitive fuzzy probability distribution function according to the formulas (6) to (8).
Intuitive fuzzy set of rainfall measuring instrument R
Intuitive fuzzy set of depth displacement sense D
Intuitive fuzzy set of GNSS positioning system G
And step 3: and (3) substituting the three intuitive fuzzy perception probability distribution functions obtained in the step (2) into formulas (12) to (13) to obtain a weighting coefficient based on the information entropy.
I(mR)＝0.4,I(mD)＝0.28,I(mG)＝0.32
And 4, step 4: and (3) substituting the three intuitive fuzzy perception probability distribution functions obtained in the step (2) into a formula to obtain a weighting coefficient based on fuzzy divergence measure.
S(mR)＝0.2,S(mD)＝0.29,S(mG)＝0.51
And 5: and (4) processing the weighting coefficients in the step (3) and the step (4) to obtain a final weighting coefficient and obtain a weighted probability distribution function.
Weighting coefficient: omega (m)R)＝0.23,ω(mD)＝0.26,ω(mG)＝0.51
Weighted probability distribution function: m ═ {0.23,0.6,0.17}
Step 6: performing fusion treatment by using an improved DS evidence theory method to obtain a fusion result F
F＝{0.06,0.94,0}
And 7: it can be seen from the fusion result that the probability of occurrence of landslide is 6% and the probability of non-occurrence of landslide is 94%, so the system does not give an alarm. The method can give more accurate results than a single sensor.
The present invention is not limited to the above-mentioned preferred embodiments, and any other various types of landslide warning methods based on multi-sensor data fusion technology can be obtained according to the teaching of the present invention, and all equivalent changes and modifications made according to the claims of the present invention shall fall within the scope of the present invention.
Claims (7)
1. A landslide early warning method based on a multi-sensor data fusion technology is characterized by comprising the following steps:
step S1: respectively measuring the effective rainfall, the earth surface displacement and the deep displacement of the monitoring point position, and respectively converting the effective rainfall, the earth surface displacement and the deep displacement into corresponding landslide occurrence probabilities;
step S2: converting the three landslide probabilities into an intuitionistic fuzzy set respectively;
step S3: calculating a weight coefficient based on entropy and fuzzy divergence measure to obtain a weighted basic probability assignment function;
step S4: and carrying out iterative processing by using an improved DS evidence theory fusion rule to obtain a fusion result as the probability of the final landslide.
2. The landslide early warning method based on multi-sensing data fusion technology according to claim 1, wherein: in step S1, the effective rainfall, the ground surface displacement, and the deep displacement of the monitoring point position are measured by the rainfall measuring instrument, the GNSS positioning system, and the depth displacement transmitter, respectively.
3. The landslide early warning method based on multi-sensing data fusion technology according to claim 2, wherein: step S1 specifically includes the following steps:
step S31: converting the effective rainfall into the probability of landslide:
the effective rainfall is calculated by the following formula:
Al＝0.5406×e-3.392×l+7.94×10-2e-0.1286×l (2)
where l is 0 or x0Represents the rainfall 24 hours of the day, x when l is 11Represents the rainfall 24 hours before the day, and x is 2 hours2Represents the rainfall of 24 hours in the first two days, x when l is 33Representing 24 hours rainfall in the first three days, AlRepresents a weight coefficient per day;
converting the effective rainfall into a probability of producing landslide using the following equation:
PR(R)＝(1.134×10-4×R3-0.02814×R2+2.348×R+12.96)/100 (3)；
step S32: converting the earth surface displacement into the probability of landslide:
calculating the horizontal displacement and the vertical displacement of the measuring point by utilizing a GNSS positioning system and an RTK technology, and converting the ratio of the horizontal displacement and the vertical displacement into the probability of landslide:
PG(k)＝0.8539e0.04242k-2.248e-13.73k (4)
wherein k represents a ratio of the horizontal displacement amount to the vertical displacement amount;
step S33: converting the deep displacement amount into a probability of occurrence of a landslide:
where d represents the depth displacement amount.
4. The landslide early warning method based on multi-sensing data fusion technology according to claim 3, wherein:
in step S2, the landslide event is described by using three aspects of the membership degree U, the non-membership degree V, and the hesitation degree pi, and the probability of landslide occurrence converted from the effective rainfall, the surface displacement amount, and the depth displacement amount is converted into an intuitive fuzzy set m ═ U (x), V (x), pi (x) }:
U(x)＝P(x)-0.5π(x) (7)
V(x)＝1-π(x)-U(x) (8)；
converting the probability of landslide generated by effective rainfall by using formulas (6) to (8) to obtain an intuitionistic fuzzy set
Wherein subscript R represents effective rainfall;
converting the probability of landslide generated by depth displacement by using formulas (6) to (8) to obtain an intuitionistic fuzzy set
Wherein subscript D represents a depth displacement amount;
converting the probability of generating landslide by using the surface displacement ratio by using the formulas (6) to (8) to obtain an intuitionistic fuzzy set
Where subscript G represents the ratio of the amount of horizontal displacement to the amount of vertical displacement of the surface.
5. The landslide early warning method based on multi-sensing data fusion technology of claim 4, wherein step S3 specifically comprises the following steps:
step S31: determining a weighting coefficient based on the hesitation intuition fuzzy entropy:
wherein n respectively represents R, D, G three fuzzy set functions;
step S32: constructing a similarity matrix C between sensors in any landslide prediction system: the intuitive fuzzy set of three sensors is known as:
the similarity matrix between them is:
wherein, i and j can respectively take three fuzzy set functions of R, D and G; when i ═ j, i.e., the intuitive fuzzy sets, are the same, the similarity between them is 1; the similarity matrix C between the 3 sensors R, D, G in the invention is obtained by the method
Calculating the support Sup for the generation of landslide of the pairs R, D, G, the subscripts representing the different sensors:
normalizing the support of each sensor:
step S33: calculating the weighting coefficient of each sensor intuition fuzzy set to obtain a weighting basic probability assignment function B:
6. the landslide early warning method based on multi-sensing data fusion technology of claim 5, wherein step S4 specifically comprises the following steps:
let the intuitive fuzzy set function be
Performing fusion treatment by using an improved DS evidence theory method, wherein the fusion result is F, and the fusion process is as follows:
the intuitive fuzzy set of the fusion result F is
Performing 2 times of iteration processing on the weighted fuzzy set probability distribution function by using the fusion algorithm to obtain the final fusion result
7. The landslide early warning method based on multi-sensing data fusion technology of claim 6, wherein: and generating a pre-alarm when the membership function in the fusion result is greater than 0.5 of the threshold value.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110052736.3A CN112903008B (en) | 2021-01-15 | 2021-01-15 | Mountain landslide early warning method based on multi-sensing data fusion technology |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110052736.3A CN112903008B (en) | 2021-01-15 | 2021-01-15 | Mountain landslide early warning method based on multi-sensing data fusion technology |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN112903008A true CN112903008A (en) | 2021-06-04 |
| CN112903008B CN112903008B (en) | 2023-01-10 |
Family
ID=76114744
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110052736.3A Active CN112903008B (en) | 2021-01-15 | 2021-01-15 | Mountain landslide early warning method based on multi-sensing data fusion technology |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112903008B (en) |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113432645A (en) * | 2021-06-25 | 2021-09-24 | 中国矿业大学 | Dam and slope stability monitoring and early warning method based on NMR and Beidou remote sensing combined measurement |
| CN113723446A (en) * | 2021-07-15 | 2021-11-30 | 杭州鲁尔物联科技有限公司 | Ground disaster monitoring and early warning method and device, computer equipment and storage medium |
| CN113916186A (en) * | 2021-12-15 | 2022-01-11 | 广州吉欧电子科技有限公司 | Deformation monitoring system and method based on GNSS and MEMS |
| CN116861286A (en) * | 2023-06-21 | 2023-10-10 | 四川省人工智能研究院(宜宾) | Multi-mode landslide displacement intelligent prediction method based on fuzzy calculation |
| CN116952943A (en) * | 2023-09-19 | 2023-10-27 | 吉林省林业科学研究院(吉林省林业生物防治中心站) | Forest land slope soil erosion measurement system based on oblique photography |
Citations (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20070088982A1 (en) * | 2005-10-18 | 2007-04-19 | Valerie Guralnik | System and method for combining diagnostic evidences for turbine engine fault detection |
| CN101216998A (en) * | 2008-01-11 | 2008-07-09 | 浙江工业大学 | An information amalgamation method of evidence theory urban traffic flow based on fuzzy rough sets |
| US20090222399A1 (en) * | 2008-02-28 | 2009-09-03 | Sap Ag | Trustworthiness assessment of sensor data processing |
| US20150148997A1 (en) * | 2013-11-28 | 2015-05-28 | Airbus Operations (S.A.S.) | Method for fusing data from sensors using a consistency criterion |
| CN105741474A (en) * | 2016-04-11 | 2016-07-06 | 泉州师范学院 | Fire early-warning method based on multiple sensors |
| CN106779418A (en) * | 2016-12-20 | 2017-05-31 | 河海大学常州校区 | Water contamination accident Intelligent Decision-making Method based on neutral net and evidence theory |
| CN106778883A (en) * | 2016-12-23 | 2017-05-31 | 贵州电网有限责任公司电力科学研究院 | A kind of evidence theory intelligent patrol detection information fusion method based on fuzzy set |
| CN110211336A (en) * | 2019-05-16 | 2019-09-06 | 西南交通大学 | The method of sensor-based landslide data intelligence processing |
| CN110264671A (en) * | 2019-05-18 | 2019-09-20 | 西南交通大学 | A kind of prediction technique based on multi-sensor information fusion in landslide |
| US20190292898A1 (en) * | 2018-03-26 | 2019-09-26 | Baker Hughes, A Ge Company, Llc | Model-based parameter estimation for directional drilling in wellbore operations |
| CN110567324A (en) * | 2019-09-04 | 2019-12-13 | 深圳市唯特视科技有限公司 | multi-target group threat degree prediction device and method based on DS evidence theory |
| US20200387785A1 (en) * | 2019-06-05 | 2020-12-10 | Wuhan University | Power equipment fault detecting and positioning method of artificial intelligence inference fusion |
-
2021
- 2021-01-15 CN CN202110052736.3A patent/CN112903008B/en active Active
Patent Citations (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20070088982A1 (en) * | 2005-10-18 | 2007-04-19 | Valerie Guralnik | System and method for combining diagnostic evidences for turbine engine fault detection |
| CN101216998A (en) * | 2008-01-11 | 2008-07-09 | 浙江工业大学 | An information amalgamation method of evidence theory urban traffic flow based on fuzzy rough sets |
| US20090222399A1 (en) * | 2008-02-28 | 2009-09-03 | Sap Ag | Trustworthiness assessment of sensor data processing |
| US20150148997A1 (en) * | 2013-11-28 | 2015-05-28 | Airbus Operations (S.A.S.) | Method for fusing data from sensors using a consistency criterion |
| CN105741474A (en) * | 2016-04-11 | 2016-07-06 | 泉州师范学院 | Fire early-warning method based on multiple sensors |
| CN106779418A (en) * | 2016-12-20 | 2017-05-31 | 河海大学常州校区 | Water contamination accident Intelligent Decision-making Method based on neutral net and evidence theory |
| CN106778883A (en) * | 2016-12-23 | 2017-05-31 | 贵州电网有限责任公司电力科学研究院 | A kind of evidence theory intelligent patrol detection information fusion method based on fuzzy set |
| US20190292898A1 (en) * | 2018-03-26 | 2019-09-26 | Baker Hughes, A Ge Company, Llc | Model-based parameter estimation for directional drilling in wellbore operations |
| CN110211336A (en) * | 2019-05-16 | 2019-09-06 | 西南交通大学 | The method of sensor-based landslide data intelligence processing |
| CN110264671A (en) * | 2019-05-18 | 2019-09-20 | 西南交通大学 | A kind of prediction technique based on multi-sensor information fusion in landslide |
| US20200387785A1 (en) * | 2019-06-05 | 2020-12-10 | Wuhan University | Power equipment fault detecting and positioning method of artificial intelligence inference fusion |
| CN110567324A (en) * | 2019-09-04 | 2019-12-13 | 深圳市唯特视科技有限公司 | multi-target group threat degree prediction device and method based on DS evidence theory |
Non-Patent Citations (16)
| Title |
|---|
| MAOLI RAN 等: "Research on Probability Statistics Method for Multi-sensor Data Fusion", 《2018 INTERNATIONAL CONFERENCE ON CYBER-ENABLED DISTRIBUTED COMPUTING AND KNOWLEDGE DISCOVERY (CYBERC)》 * |
| YANG YU 等: "Research on the fault diagnosis methods for UUV utilize multi-sensor information fusion technology", 《OCEANS 2016 - SHANGHAI》 * |
| 刘德阳等: "基于多传感器滑坡监测预警***设计及应用", 《微处理机》 * |
| 刘明贵等: "信息融合技术在边坡监测与预报***中的应用", 《岩土工程学报》 * |
| 刘晓悦 等: "基于D-S证据理论的多传感器火灾报警方法", 《华北理工大学学报》 * |
| 刘海波等: "基于D-S证据理论的瓦斯突出危险等级评判策略", 《济南大学学报(自然科学版)》 * |
| 刘海波等: "模糊数据融合在煤矿采掘工作面瓦斯突出预测中的应用", 《自动化仪表》 * |
| 孙晓云等: "基于修正D-S证据理论的锚杆承载力预测方法研究", 《岩土力学》 * |
| 李光等: "多传感器数据融合技术在火灾报警中的应用", 《河北工业大学学报》 * |
| 李明波等: "基于多模块的松散土质滑坡灾害综合预警模型研究", 《西北师范大学学报(自然科学版)》 * |
| 段锁林 等: "基于模糊证据理论算法在火灾检测中的应用", 《计算机工程与应用》 * |
| 温宗周等: "优化GD-模糊规则的滑坡预报模型研究", 《计算机工程与应用》 * |
| 王海洋: "基于D-S证据理论融合算法的电缆沟火灾报警***研究", 《电气应用》 * |
| 蔚晓丹: "基于改进D-S信息融合方法的发动机故障诊断", 《公路交通科技》 * |
| 蔡植善 等: "多传感器数据融合的火灾探测报警***设计", 《泉州师范学院学报》 * |
| 霍冬冬等: "多源数据融合在岩质滑坡监测预警中的应用", 《四川理工学院学报(自然科学版)》 * |
Cited By (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113432645A (en) * | 2021-06-25 | 2021-09-24 | 中国矿业大学 | Dam and slope stability monitoring and early warning method based on NMR and Beidou remote sensing combined measurement |
| CN113723446A (en) * | 2021-07-15 | 2021-11-30 | 杭州鲁尔物联科技有限公司 | Ground disaster monitoring and early warning method and device, computer equipment and storage medium |
| CN113723446B (en) * | 2021-07-15 | 2024-05-24 | 杭州鲁尔物联科技有限公司 | Ground disaster monitoring and early warning method and device, computer equipment and storage medium |
| CN113916186A (en) * | 2021-12-15 | 2022-01-11 | 广州吉欧电子科技有限公司 | Deformation monitoring system and method based on GNSS and MEMS |
| CN113916186B (en) * | 2021-12-15 | 2022-03-22 | 广州吉欧电子科技有限公司 | Deformation monitoring system and method based on GNSS and MEMS |
| CN116861286A (en) * | 2023-06-21 | 2023-10-10 | 四川省人工智能研究院(宜宾) | Multi-mode landslide displacement intelligent prediction method based on fuzzy calculation |
| CN116861286B (en) * | 2023-06-21 | 2024-01-30 | 四川省人工智能研究院(宜宾) | Multi-mode landslide displacement intelligent prediction method based on fuzzy calculation |
| CN116952943A (en) * | 2023-09-19 | 2023-10-27 | 吉林省林业科学研究院(吉林省林业生物防治中心站) | Forest land slope soil erosion measurement system based on oblique photography |
| CN116952943B (en) * | 2023-09-19 | 2023-12-08 | 吉林省林业科学研究院(吉林省林业生物防治中心站) | Forest land slope soil erosion measurement system based on oblique photography |
Also Published As
| Publication number | Publication date |
|---|---|
| CN112903008B (en) | 2023-01-10 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112903008B (en) | Mountain landslide early warning method based on multi-sensing data fusion technology | |
| CN102435165B (en) | CNSS (COMPASS navigation satellite system)-based long-term ground facility deformation monitoring method | |
| RU2587520C1 (en) | Method and system for evaluating risk of high-energy shocks caused by underground development | |
| CN105116440B (en) | A kind of slope rock mass monitoring system and monitoring method | |
| CN108922123B (en) | mine slope slip stability monitoring and early warning method | |
| CN202501869U (en) | Tailing pond on-line safety monitoring system based on internet of things | |
| CN110234811B (en) | Road collapse risk degree evaluation device, evaluation method, and computer program for evaluation | |
| CN106777585B (en) | A kind of ESDA analytic approach of region superficial landslide Temporal-Spatial Variation Law | |
| CN109886456B (en) | Debris flow prediction method based on PCA and mixed kernel function LSSVR | |
| CN104483700B (en) | Formation fracture is monitored and early warning system and method | |
| CN117493815B (en) | BIM-based deep foundation pit monitoring method and system | |
| CN111259335A (en) | Tunnel underpass road construction risk analysis system and method | |
| CN111473770A (en) | Slope condition evaluation method based on comprehensive attribute measurement | |
| CN116011816A (en) | Building structure-oriented multi-disaster monitoring and early warning method and device | |
| CN115688046A (en) | Rock burst prediction method and device and computer equipment | |
| Kim et al. | Integrated tunnel monitoring system using wireless automated data collection technology | |
| CN117648873B (en) | Ground subsidence prediction method, training method, device and equipment | |
| CN109165795A (en) | A kind of set Runoff Forecast System and method for based on swarm intelligence algorithm | |
| Maurer | Moving towards an improved liquefaction hazard framework: lessons resulting from the 2010-2011 Canterbury, New Zealand, earthquake sequence | |
| CN112255691B (en) | Deep fracture geological method for detecting excitation composite frequency | |
| WO2023042303A1 (en) | State determination device, state determination method, and recording medium having state determination program stored thereon | |
| Shaheen et al. | Comparison between Microwave Radar Gauge and Pressure Gauge in Monitoring Sea Level Surface at Alexandria Naval Port | |
| Li et al. | Shock and Vibration of Rainfall on Rotational Landslide and Analysis of Its Deformation Characteristics | |
| Fatkhurrohman et al. | Performance analysis of Sebesi Island automatic water level station as tsunami confirmation system | |
| Weiguo et al. | Research Article Shock and Vibration of Rainfall on Rotational Landslide and Analysis of Its Deformation 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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |