CN113936228A - High slope monitoring and early warning system based on unmanned aerial vehicle data check - Google Patents
High slope monitoring and early warning system based on unmanned aerial vehicle data check Download PDFInfo
- Publication number
- CN113936228A CN113936228A CN202111027783.9A CN202111027783A CN113936228A CN 113936228 A CN113936228 A CN 113936228A CN 202111027783 A CN202111027783 A CN 202111027783A CN 113936228 A CN113936228 A CN 113936228A
- Authority
- CN
- China
- Prior art keywords
- data
- monitoring
- slope
- unmanned aerial
- aerial vehicle
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Images
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01B—MEASURING LENGTH, THICKNESS OR SIMILAR LINEAR DIMENSIONS; MEASURING ANGLES; MEASURING AREAS; MEASURING IRREGULARITIES OF SURFACES OR CONTOURS
- G01B21/00—Measuring arrangements or details thereof, where the measuring technique is not covered by the other groups of this subclass, unspecified or not relevant
- G01B21/02—Measuring arrangements or details thereof, where the measuring technique is not covered by the other groups of this subclass, unspecified or not relevant for measuring length, width, or thickness
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01C—MEASURING DISTANCES, LEVELS OR BEARINGS; SURVEYING; NAVIGATION; GYROSCOPIC INSTRUMENTS; PHOTOGRAMMETRY OR VIDEOGRAMMETRY
- G01C9/00—Measuring inclination, e.g. by clinometers, by levels
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/23—Clustering techniques
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F30/00—Computer-aided design [CAD]
- G06F30/20—Design optimisation, verification or simulation
- G06F30/27—Design optimisation, verification or simulation using machine learning, e.g. artificial intelligence, neural networks, support vector machines [SVM] or training a model
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
- G06N3/084—Backpropagation, e.g. using gradient descent
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
Abstract
The invention provides a high slope monitoring and early warning system based on unmanned aerial vehicle data checking, which comprises an unmanned aerial vehicle for acquiring slope images, a stay wire type displacement sensor array embedded in a slope, a fixed inclinometer and seepage monitoring equipment, wherein the stay wire type displacement sensor array is arranged on the slope; the unmanned aerial vehicle is used for monitoring image data of the side slope from the air; the stay wire type displacement sensor array is used for monitoring displacement data of the side slope surface; the fixed inclinometer and the seepage monitoring equipment are used for monitoring the internal slip data of the side slope; and carrying out real-time slope safety monitoring through data of the unmanned aerial vehicle, the stay wire type displacement sensor, the fixed inclinometer and the seepage monitoring equipment. By adopting the scheme, the cracks can be effectively identified, and sensitive information can be further strengthened; and secondly, the cracks of dangerous parts, the slight movement of dangerous rocks and the slight deformation on the monitoring section can be accurately identified and captured, future data is predicted, and the real-time state of the side slope is simulated and displayed, so that the monitoring result of the side slope is visual and vivid.
Description
Technical Field
The invention relates to the field of monitoring and early warning of a high slope, in particular to a high slope monitoring and early warning system based on unmanned aerial vehicle data checking.
Background
In human activities, such as the construction of railways, highways and other engineering processes, slope slip disasters often occur due to construction disturbance or the influence of natural weather on high slopes. For example, in some railways and highways, the monitoring, early warning and timely treatment are not carried out due to the fact that the railways and the highways are subjected to powerful blasting and forced excavation and the side slopes are not supported, so that the traffic and the personal safety are damaged, huge economic loss and adverse social effects are caused, and the traffic is even interrupted in some railways and highways.
So far, most slope monitoring and early warning still stay in a single monitoring mode and a single-factor static analysis early warning model, a multi-level slope monitoring system and a dynamic multi-factor intelligent early warning model cannot be formed, and for a general slope engineering monitoring method, related data obtained by a single monitoring method is often insufficient in accuracy and referential performance, so that the early warning reliability of the whole slope monitoring system is greatly influenced, and the monitoring safety early warning work of the slope has great hidden danger.
Because the existing landslide monitoring and controlling technology focuses on single factor monitoring, and a high-efficiency advanced multi-level monitoring system is not provided aiming at the problems of wide landslide range, inconvenient traffic, high monitoring cost, high analysis difficulty and the like so as to realize batch monitoring of a large number of high slopes. Along with the emergence of low-cost and high-reliability flight equipment such as unmanned aerial vehicles and the like, the traditional monitoring mode is gradually replaced, and the rapid and efficient monitoring on a large range can be realized; in other words, the unmanned aerial vehicle equipment is utilized to carry out large-scale monitoring, and the monitoring information is reported and summarized through the wireless transmission equipment, so that the efficiency of slope landslide monitoring can be greatly improved, and landslide disasters are avoided.
Disclosure of Invention
The invention aims to solve the technical problem of providing a high slope monitoring and early warning system based on unmanned aerial vehicle data checking, which can combine with the multidimensional monitoring of the current construction requirement, adopts multi-level cooperative monitoring in the data collection process, effectively avoids the solid error and accidental error caused by a single monitoring mode, and rechecks each monitoring data through the linear regression relation of each level of monitoring data to ensure the reliability of the monitoring data.
In order to solve the technical problems, the technical scheme adopted by the invention is as follows: a high slope monitoring and early warning system based on unmanned aerial vehicle data checking comprises an unmanned aerial vehicle for acquiring slope images, a stay wire type displacement sensor array pre-embedded in a slope, a fixed inclinometer and seepage monitoring equipment;
the unmanned aerial vehicle is used for monitoring image data of the side slope from the air;
the stay wire type displacement sensor array is used for monitoring displacement data of the side slope surface;
the fixed inclinometer and the seepage monitoring equipment are used for monitoring the internal slip data of the side slope;
and carrying out real-time slope safety monitoring through data of the unmanned aerial vehicle, the stay wire type displacement sensor, the fixed inclinometer and the seepage monitoring equipment.
In the preferred scheme, still be equipped with rainwater collection device for it is data in order to assist carries out side slope safety monitoring to gather precipitation.
In the preferred scheme, the stay wire type displacement sensor array, the fixed inclinometer, the seepage monitoring equipment and the rainwater collection device are electrically connected with the data acquisition device so as to collect monitoring data;
the data acquisition device is connected with the monitoring cloud platform in a wireless mode, and the unmanned aerial vehicle is connected with the monitoring cloud platform in a wireless mode.
In the preferred scheme, the image data of the aerial photography of the unmanned aerial vehicle carries out one-dimensional wavelet transformation on the pixel data of the image line by line, and the image data is decomposed into two components of low-pass filtering L and high-pass filtering H for output;
then, one-dimensional wavelet transform is carried out on pixel data of the image column by column, and the pixel data are decomposed into LL, LH, HL and HH components for output so as to highlight sensitive data;
the sensitive data are image data related to the crack of the slope.
In the preferred scheme, ground monitoring data is obtained through kriging interpolation operation of the stay wire type displacement sensor array.
In the preferred scheme, the ground monitoring data and the image data of the unmanned aerial vehicle are subjected to F test method test, and if the test results are met, the optimal solution is output; if not, replacing the surface function in the spatial interpolation again by an AI learning method until the F test method is satisfied, and outputting an optimal solution;
the optimal solution is the optimized earth surface data.
In the preferred scheme, the data obtained by the rainwater collecting device, the seepage monitoring equipment and the fixed inclinometer are used as the internal data of the optimized side slope;
and establishing a monitoring and early warning model by the optimized surface data and the optimized internal data of the slope in a visual mode.
In the preferred scheme, the monitoring and early warning model comprises a prediction module and an evaluation module;
the prediction module is provided with the following steps:
s01, establishing factor monitoring influencing slope stability;
s02, preprocessing the monitored data;
s03, establishing a BP neural network prediction model;
s04, predicting future data;
the evaluation module is provided with the following steps:
s11, analyzing by a grey correlation method;
s12, establishing a fuzzy clustering iterative model;
s13, introducing predicted future data into a fuzzy clustering iterative model;
and S14, outputting and evaluating the slope state.
In a preferred scheme, the factors of the fuzzy clustering iterative model comprise volume weight, cohesion, internal friction angle, side slope height and pore pressure ratio.
In a preferred scheme, in step S14, the slope history monitoring data and the basic hydrology, geology and other data are used as sample data, corresponding eigenvalue matrix samples and relative membership degree matrices are constructed according to the eigenvalues of the factors in the samples, the weights of the influence factors are analyzed by adopting gray correlation, the optimal fuzzy cluster matrix and the optimal fuzzy cluster center matrix are solved by iterative operation, and the grade of stability evaluation can be obtained by multiplying the corresponding evaluation grade values by the relative membership degrees after sorting processing.
According to the high slope monitoring and early warning system based on unmanned aerial vehicle data checking, the scheme is adopted, firstly, cracks can be effectively identified, and sensitive information can be further strengthened; and secondly, the cracks of dangerous parts, the slight movement of dangerous rocks and the slight deformation on the monitoring section can be accurately identified and captured, future data is predicted by combining a prediction model based on neural network prediction through a visualization technology, and the real-time state of the side slope is simulated and displayed, so that the monitoring result of the side slope is visual and vivid. Thirdly, performing early warning report by using an intelligent monitoring early warning model based on multi-factor coupling; the system can effectively solve the problem of low data precision, can monitor the displacement change of the side slope in real time and report the displacement change of the side slope, effectively avoids landslide danger and greatly reduces economic loss and personnel safety risk.
Drawings
The invention is further illustrated by the following examples in conjunction with the accompanying drawings:
fig. 1 is a schematic diagram of the site arrangement of the slope of the present invention.
FIG. 2 is a schematic view of the flow structure of the present invention.
FIG. 3 is a graph of data collected in accordance with the present invention with intrinsic and extrinsic factors.
FIG. 4 is a flowchart of a BP neural network prediction model.
In the figure: unmanned aerial vehicle 1, stay-supported displacement sensor 2, rainwater collection device 3, seepage flow monitoring facilities 4, fixed inclinometer 5, data acquisition device 6, side slope 7.
Detailed Description
As shown in fig. 1, a high slope monitoring and early warning system based on unmanned aerial vehicle data checking comprises an unmanned aerial vehicle 1 for acquiring a slope 7 image, a guyed displacement sensor 2 array pre-embedded in a slope 7, a fixed inclinometer 5 and a seepage monitoring device 4;
according to engineering requirements, the stay wire type displacement meters and the fixed type inclinometers are sequentially and uniformly distributed in a slope area, and the remote monitoring platform is arranged in an area where a traffic convenience network is smooth. The layout mode of the stay wire type displacement meter is as follows: the vertical displacement installation method comprises the following steps: the stay wire type displacement sensor 2 is fixed above the slope surface of the side slope, the steel wire rope is pulled out from top to bottom, the pre-pulling length is controlled to be about 50% of the measuring range, the pulling end is fixed in an expansion bolt mode, if the stay wire distance is too long, the steel wire rope can seriously drop, 1 pulley can be added every 5 meters to play a role in pulling the steel wire rope, so that the steel wire rope is tensioned, and the measuring error is reduced. The horizontal displacement installation method comprises the following steps: the sensor is fixed at the slope surface of the side slope, the steel wire rope is horizontally pulled out, the pre-pulling length is controlled to be about 50% of the measuring range, the pulling end is fixed in an expansion bolt mode, if the wire pulling distance is too long, the steel wire rope can seriously fall down, 1 pulley can be added every 5 meters to play a role in pulling the steel wire rope, the steel wire rope is tensioned, and the measuring error is reduced.
The fixed inclinometer 5 is installed in the following manner:
installation of the inclinometer: the inclinometer pipe is firstly arranged on the upper pipe bottom cover and fixed by screws or glue. The inclinometer pipe and the inclinometer pipe are connected by a pipe joint, and the inclinometer pipe and the pipe joint are fixed by screws and then are sealed by gluing and filling joints. The direction of the guide groove should be noticed during installation of the inclinometer pipe, and the direction of the guide groove must be consistent with the direction required by the design. When the inclinometer is determined to be installed well, the inclinometer can be backfilled, and the backfilling is generally carried out by using bentonite balls or original soil sand. And during backfilling, water is injected once when the depth is 3-5 m, wherein the water injection is used for firmly combining the bentonite balls or the original soil sand with the hole wall after the bentonite balls or the original soil sand meet water, and the hole is formed by the method. The inclinometer pipe exposed on the ground surface needs to be protected by attention, and a pipe cover is covered to prevent objects from falling. Concrete should be poured into the pipe orifice section of the inclinometer pipe, and the pipe orifice section and the corner section of the inclinometer pipe are made into concrete abutments to protect the stability of the pipe orifice and the corner thereof. The pier should be set with surveying and mapping points.
Mounting of instruments
Firstly, whether the guide wheel of the inclinometer rotates flexibly and whether the torsion spring is powerful or not should be checked. And checking whether the sensor component works normally, intercepting the connecting rod according to the designed elevation, connecting the fixed inclinometer end to end by using a steel wire rope, and determining that the fixed inclinometer is intact for mounting. When the fixed inclinometer is assembled, the fixed inclinometer is assembled into measuring units according to the quantity required by construction drawings, and the fixed inclinometer is checked and confirmed to be intact for hoisting. During hoisting, the measuring units are placed into the inclinometer in sequence, the measuring units are firmly connected through the connecting rods, and all guide wheels of the measuring units are consistent in direction. Each set of fixed inclinometer needs to be numbered and recorded in sequence, cables need to be straightened one by one when being loaded one by one, all the cables need to be loosened and can not be tensioned, and the last connecting rod is tied on a transverse shaft of the orifice device and locked by a lock catch. Finally, a protective facility is arranged at the hole opening. The observation cable is fixedly buried according to the specified direction.
The seepage monitoring device 4 is arranged inside the slope 7.
In order to ensure the effectiveness of data communication between the unmanned aerial vehicle and the remote monitoring cloud platform and consider the conditions of complex environment in a construction area and weak network card signals, the unmanned aerial vehicle is provided with a USB wireless network card of a high-power wifi module. The unmanned aerial vehicle lithium battery is a high-performance lithium battery with the capacity not lower than 40000 mAh.
The daily collection frequency of the whole monitoring system is 1 time/day, the encrypted collection can be carried out under the severe conditions of rainfall and the like, the frequency is 1 time/hour, and the mobile network adopts more than 4G so as to ensure the smoothness of real-time data; the frequency of automatic monitoring by the drone was 2 times per week.
The unmanned aerial vehicle 1 is used for monitoring image data of the side slope 7 from the air;
the stay wire type displacement sensor 2 array is used for monitoring displacement data of the surface of the side slope 7;
the fixed inclinometer 5 and the seepage monitoring equipment 4 are used for monitoring the internal slip data of the slope 7;
the real-time slope safety monitoring is carried out through the data of the unmanned aerial vehicle 1, the stay wire type displacement sensor 2, the fixed inclinometer 5 and the seepage monitoring equipment 4.
In the preferred scheme, still be equipped with rainwater collection device 3 for it is data in order to assist carries out side slope safety monitoring to gather precipitation. From this structure, improved monitoring data's full coverage nature, through laying unmanned aerial vehicle above the high slope, stay-supported displacement meter and rainwater collector are laid to the high slope surface, and fixed inclinometer is laid to inside, monitors in coordination from three dimension to this comprehensive of guaranteeing data can effectively avoid solid error and accidental error brought by single monitoring mode.
In the preferred scheme, the array of the stay wire type displacement sensor 2, the fixed inclinometer 5, the seepage monitoring equipment 4 and the rainwater collection device 3 are electrically connected with the data acquisition device 6 to collect monitoring data;
data acquisition device 6 is connected with control cloud platform through wireless mode, and unmanned aerial vehicle 1 is connected with control cloud platform through wireless mode.
In the preferred scheme, the image data of the aerial photography of the unmanned aerial vehicle 1 is subjected to one-dimensional wavelet transform on pixel data of the image line by line, and is decomposed into two components of low-pass filtering L and high-pass filtering H for output;
then, one-dimensional wavelet transform is carried out on pixel data of the image column by column, and the pixel data are decomposed into LL, LH, HL and HH components for output so as to highlight sensitive data;
the sensitive data are image data related to the crack of the slope 7.
In the preferred scheme, the stay wire type displacement sensor 2 array converts the earth surface displacement data into surface displacement data through kriging interpolation operation, and obtains ground monitoring data.
In the preferred scheme, the ground monitoring data and the image data of the unmanned aerial vehicle 1 are subjected to F test method test, and if the test results are met, the optimal solution is output; if not, replacing the surface function in the spatial interpolation again by an AI learning method until the F test method is satisfied, and outputting an optimal solution; in order to ensure the accuracy of the space interpolation data and unmanned aerial vehicle data accounting, the random surface function in the kriging interpolation method needs to be continuously optimized and reconstructed by means of an AI deep learning algorithm. Furthermore, in order to ensure the accuracy of the data, earth surface monitoring data of a fixed time period and monitoring data of the unmanned aerial vehicle are used as samples, historical side slope monitoring data are used as statistical samples, a regression model for collaborative monitoring rechecking is established through correlation analysis and an F test method, and rechecking correction is carried out on each monitoring data according to the model.
The optimal solution is the optimized earth surface data.
In the preferred scheme, the rainwater collecting device 3, the seepage monitoring equipment 4 and the fixed inclinometer 5 obtain data as the internal data of the optimized side slope 7;
and establishing a monitoring and early warning model by the optimized surface data and the optimized internal data of the slope 7 in a visual mode. In order to ensure the visual and visual monitoring result, the processed data is expressed in a three-dimensional visual modeling mode, and the method has the advantages that: firstly, can effectively discern the crack, secondly can carry out accurate discernment and catch to the crack of dangerous position, the slight motion of dangerous rock and the slight deformation on the monitoring section to through the real-time state of visual technical analog display side slope, make the monitoring result of side slope more clear. In order to improve the accuracy of image visualization, an effective mode of combining a convolutional neural network model with a Faster-R-CNN algorithm is adopted to improve the speed and the accuracy of image identification.
In the preferred scheme, the monitoring and early warning model comprises a prediction module and an evaluation module;
the prediction module is provided with the following steps:
s01, establishing factor monitoring influencing slope stability;
the slope is a complex system, the analysis of the slope stability is also a complex problem, the slope stability is researched at the present stage, the slope stability is generally researched by researching factors influencing the slope stability, and due to the fact that the factors influencing the slope stability are numerous, the factors influencing the slope stability should be determined at first. Due to the complexity of landslide, the development to occurrence process of landslide is influenced by various factors, generally, the landslide is mainly divided into internal factors and external factors, wherein the internal factors are characterized by slow change; the external factors are characterized by remarkable change, the internal factors are also called geological and landform background factors, the external factors are also called non-geological factors, and the influence of the change of the mountain external environment on the stability of the side slope is brought. Internal factors including formation lithology, geological structure, etc., are inherent geological features of the slope, which constitute the main body of the entire slope. The internal factors are the conditions of the foundation wood for forming and developing the landslide, have the characteristics of slow change and little change, the external factors are catalysts for forming the landslide, the external factors can accelerate the formation of the landslide, the external factors can inhibit the formation of the side slope, and the external factors have the characteristics of quick change and more mutation. As shown in fig. 3.
In the current stage of research, internal factors and external factors influencing the side slope are generally converted into the research of volume weight, cohesive force, internal friction angle, side slope height and pore pressure ratio, so that the main factors in the fuzzy clustering iterative model are determined as the volume weight, the cohesive force, the internal friction angle, the side slope height and the pore pressure ratio to research the stability of the side slope, and the stability of the side slope can be predicted essentially.
S02, preprocessing the monitored data;
from the composite model, the main factors influencing the slope stability are determined as volume weight, cohesive force, internal friction angle, slope height and pore pressure ratio. The monitored data of the A-section stay wire type displacement meter is selected as a research object of which the displacement is a monitoring result, so that a soil sampling point of the soil sample is also near the A-section stay wire type displacement meter, the soil sampling depth is 25 meters, the soil at the positions of 4 meters, 10 meters, 16 meters and 22 meters is respectively selected as sample soil samples, four groups of monitoring values of volume weight, cohesive force, internal friction angle, side slope angle and pore pressure ratio are obtained, and the average value of the four monitoring values is taken as a final monitoring value. And collecting data of six influencing factors of the slope, and performing noise reduction on the initial data by using an MATLAB wavelet analysis toolbox.
S03, establishing a BP neural network prediction model;
the BP neural network is roughly divided into 3 steps, which are input to neurons, training of neurons, and output of neurons, respectively. By inputting initial data of factors which originally affect slope stability as input of neurons and training by using a model, the change trend of each factor in the future can be predicted, and each prediction result is output as the neurons.
The MATLAB software is programmed according to the steps, so that data prediction of various factors influencing slope stability can be realized, as shown in figure 4.
S04, predicting future data;
after the noise reduction data of six factors influencing the slope stability are obtained, the future change conditions of all the factors are predicted, programming is carried out according to the BP neural network programming principle, and the volume weight, the cohesion, the internal friction angle, the slope height and the hole pressure ratio are predicted backwards for seven times.
And calculating the weight of the main factors influencing the slope stability, and calculating the weight of the main factors influencing the slope by taking the arc slippage data of the A-section soil slope as a sample. The main influencing parameters include volume weight, cohesion, internal friction angle, side slope height and pore pressure ratio.
The evaluation module is provided with the following steps:
s11, analyzing by a grey correlation method;
the grey correlation analysis theory is used for researching the degree of relation between two or more factors in the system, which changes with time or different objects, and is a measure for describing the magnitude of the correlation, which is called the degree of correlation. A new weight determination method needs to be introduced for slope evaluation errors caused by subjectivity. The grey correlation analysis theory is to study the degree of correlation of each influence factor to the subject, and it is obvious that if the degree of correlation of the factor to the subject is higher, the influence of the factor to the subject is higher, so the grey correlation theory can be introduced to determine the weight of each factor.
S12, establishing a fuzzy clustering iterative model;
the fuzzy clustering is used for constructing a corresponding eigenvalue matrix by using eigenvalues of various factors given in a sample according to the eigenvalues of the various factors given in the sample on the premise of solving the problem of a large amount of known historical sample wood data, solving the eigenvalue of the corresponding level of each factor according to the given relative membership degree, and carrying out classification according to the eigenvalues of the various factors.
S13, introducing predicted future data into a fuzzy clustering iterative model;
and training the historical data of the 6 factors which are determined to influence the slope stability through a BP neural network model, predicting the historical data, inputting a prediction result into an evaluation module, and introducing a fuzzy clustering iterative model.
And S14, outputting and evaluating the slope state.
And evaluating the stability of the slope according to the constructed fuzzy clustering iterative model, and performing self-programming by using MATLAB to realize a calculation process. The optimal fuzzy clustering matrix can be obtained by improving the fuzzy clustering iterative model calculation program, and after the optimal fuzzy clustering matrix is obtained, the slope stability state needs to be divided. In general, the slope stability state can be divided into three levels, one level is stable, the second level is general, and the third level is damaged, so that the relative level feature vector of each cluster sample can determine an optimal fuzzy cluster matrix, and according to the corresponding division region, after an evaluation value corresponding to the sample slope is obtained, the slope stability can be judged.
In order to fully consider the monitored displacement and crack development as well as the influence of original geological factors and natural conditions of the side slope in stability evaluation, a fuzzy clustering iterative model is adopted as a basic model for stability evaluation, and a composite model of a BP neural network model and the fuzzy clustering iterative model is constructed as an early warning module.
In a preferred scheme, in step S14, the slope history monitoring data and the basic hydrology, geology and other data are used as sample data, corresponding eigenvalue matrix samples and relative membership degree matrices are constructed according to the eigenvalues of the factors in the samples, the weights of the influence factors are analyzed by adopting gray correlation, the optimal fuzzy cluster matrix and the optimal fuzzy cluster center matrix are solved by iterative operation, and the grade of stability evaluation can be obtained by multiplying the corresponding evaluation grade values by the relative membership degrees after sorting processing.
Landslide and rainfall are related, and historical data shows that when the accumulated rainfall is larger than 100mm, the number of landslides is obviously increased. Therefore, when the daily accumulated rainfall is greater than 100mm, the monitoring cloud platform should enter a warning state, the monitoring frequency of the side slope is increased, and when road traffic and communication on the next day or a later day have unmanned aerial vehicle monitoring conditions, corresponding inspection needs to be carried out on all monitoring instruments according to the set early warning threshold value, and unmanned aerial vehicle cooperative monitoring is carried out on the day when the unmanned aerial vehicle monitoring conditions are met.
The above-described embodiments are merely preferred embodiments of the present invention, and should not be construed as limiting the present invention, and the technical features described in the present invention can be used in combination with each other without conflict, and the scope of the present invention should be defined by the technical means described in the claims, and equivalents thereof including the technical features described in the claims. I.e., equivalent alterations and modifications within the scope hereof, are also intended to be within the scope of the invention.
Claims (10)
1. The utility model provides a high slope monitoring and early warning system based on unmanned aerial vehicle data is checked, characterized by: the system comprises an unmanned aerial vehicle (1) for collecting images of a side slope (7), a stay wire type displacement sensor (2) array embedded in the side slope (7), a fixed inclinometer (5) and seepage monitoring equipment (4);
the unmanned aerial vehicle (1) is used for monitoring image data of the side slope (7) from the air;
the stay wire type displacement sensor (2) array is used for monitoring displacement data of the surface of the side slope (7);
the fixed inclinometer (5) and the seepage monitoring equipment (4) are used for monitoring the internal slip data of the side slope (7);
the real-time slope safety monitoring is carried out through data of the unmanned aerial vehicle (1), the stay wire type displacement sensor (2), the fixed inclinometer (5) and the seepage monitoring equipment (4).
2. The high slope monitoring and early warning system based on unmanned aerial vehicle data check of claim 1, characterized by: still be equipped with rainwater collection device (3) for it is data in order to assist carries out side slope safety monitoring to gather the precipitation.
3. The high slope monitoring and early warning system based on unmanned aerial vehicle data check of claim 2, characterized by: the stay wire type displacement sensor (2) array, the fixed inclinometer (5), the seepage monitoring equipment (4) and the rainwater collection device (3) are electrically connected with the data acquisition device (6) to collect monitoring data;
data acquisition device (6) are connected with control cloud platform through wireless mode, and unmanned aerial vehicle (1) is connected with control cloud platform through wireless mode.
4. The high slope monitoring and early warning system based on unmanned aerial vehicle data check of claim 3, characterized by: the method comprises the steps that one-dimensional wavelet transformation is carried out on pixel data of an image line by line on image data of aerial photography of an unmanned aerial vehicle (1), and the image data are decomposed into two components of low-pass filtering L and high-pass filtering H for output;
then, one-dimensional wavelet transform is carried out on pixel data of the image column by column, and the pixel data are decomposed into LL, LH, HL and HH components for output so as to highlight sensitive data;
the sensitive data are image data related to a crack of the slope (7).
5. The high slope monitoring and early warning system based on unmanned aerial vehicle data check of claim 4, characterized by: and the ground monitoring data is obtained through the kriging interpolation operation of the array of the stay wire type displacement sensor (2).
6. The high slope monitoring and early warning system based on unmanned aerial vehicle data check of claim 5, characterized by: carrying out F-test method test on the ground monitoring data and the image data of the unmanned aerial vehicle (1), and outputting an optimal solution if the test result is met; if not, replacing the surface function in the spatial interpolation again by an AI learning method until the F test method is satisfied, and outputting an optimal solution;
the optimal solution is the optimized earth surface data.
7. The high slope monitoring and early warning system based on unmanned aerial vehicle data check of claim 6, characterized by: the rainwater collection device (3), the seepage monitoring equipment (4) and the fixed inclinometer (5) obtain data which are used as internal data of the optimized side slope (7);
and establishing a monitoring and early warning model by the optimized surface data and the optimized internal data of the slope (7) in a visual mode.
8. The high slope monitoring and early warning system based on unmanned aerial vehicle data check of claim 7, characterized by: the monitoring and early warning model comprises a prediction module and an evaluation module;
the prediction module is provided with the following steps:
s01, establishing factor monitoring influencing slope stability;
s02, preprocessing the monitored data;
s03, establishing a BP neural network prediction model;
s04, predicting future data;
the evaluation module is provided with the following steps:
s11, analyzing by a grey correlation method;
s12, establishing a fuzzy clustering iterative model;
s13, introducing predicted future data into a fuzzy clustering iterative model;
and S14, outputting and evaluating the slope state.
9. The high slope monitoring and early warning system based on unmanned aerial vehicle data check of claim 8, characterized by: factors of the fuzzy clustering iterative model comprise volume weight, cohesion, internal friction angle, slope height and pore pressure ratio.
10. The high slope monitoring and early warning system based on unmanned aerial vehicle data check of claim 8, characterized by: in step S14, the slope historical monitoring data and the data of basic hydrology, geology and the like are used as sample data, corresponding eigenvalue matrix samples and relative membership degree matrixes are constructed according to the eigenvalues of all factors in the samples, the weights of all influence factors are analyzed by adopting gray correlation, the optimal fuzzy clustering matrix and the optimal fuzzy clustering center matrix are solved by iterative operation, and after sorting processing, the corresponding evaluation level value is multiplied by each relative membership degree to obtain the stability evaluation level.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111027783.9A CN113936228A (en) | 2021-09-02 | 2021-09-02 | High slope monitoring and early warning system based on unmanned aerial vehicle data check |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111027783.9A CN113936228A (en) | 2021-09-02 | 2021-09-02 | High slope monitoring and early warning system based on unmanned aerial vehicle data check |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN113936228A true CN113936228A (en) | 2022-01-14 |
Family
ID=79275048
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111027783.9A Pending CN113936228A (en) | 2021-09-02 | 2021-09-02 | High slope monitoring and early warning system based on unmanned aerial vehicle data check |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113936228A (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114582095A (en) * | 2022-03-16 | 2022-06-03 | 浙江电力建设工程咨询有限公司 | Remote slope safety monitoring data acquisition device and data analysis method |
| CN115492175A (en) * | 2022-09-19 | 2022-12-20 | 中交第一公路勘察设计研究院有限公司 | Automatic monitoring system and method for highway side slope |
| CN116222670A (en) * | 2023-05-08 | 2023-06-06 | 山东交通学院 | Ecological landscape slope monitoring method for urban green land planning |
-
2021
- 2021-09-02 CN CN202111027783.9A patent/CN113936228A/en active Pending
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114582095A (en) * | 2022-03-16 | 2022-06-03 | 浙江电力建设工程咨询有限公司 | Remote slope safety monitoring data acquisition device and data analysis method |
| CN115492175A (en) * | 2022-09-19 | 2022-12-20 | 中交第一公路勘察设计研究院有限公司 | Automatic monitoring system and method for highway side slope |
| CN116222670A (en) * | 2023-05-08 | 2023-06-06 | 山东交通学院 | Ecological landscape slope monitoring method for urban green land planning |
| CN116222670B (en) * | 2023-05-08 | 2023-07-21 | 山东交通学院 | Ecological landscape slope monitoring method for urban green land planning |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN215909901U (en) | Multi-data mixed high slope monitoring and early warning device | |
| CN113936228A (en) | High slope monitoring and early warning system based on unmanned aerial vehicle data check | |
| Smethurst et al. | Current and future role of instrumentation and monitoring in the performance of transport infrastructure slopes | |
| KR101642951B1 (en) | GIS-based real time earthquake prediction method | |
| CN113779835A (en) | AI and intelligent monitoring system based deep and large foundation pit safety early warning method | |
| CN114353876A (en) | Loess highway slope health monitoring method | |
| CN111105600B (en) | Cutting slope stability dynamic monitoring and early warning system and method based on rainfall condition | |
| CN1587923A (en) | Device and its method for monitoring river bed sedimentation in tunnel pass through river construction | |
| CN112487545A (en) | Slope safety real-time monitoring and early warning system based on big data axial force monitoring | |
| CN107764192A (en) | One kind landslide multi-point displacement intelligent monitoring device and monitoring method | |
| CN108280969A (en) | A kind of high slope surface deformation monitoring and warning system and its method for early warning | |
| CN108195346B (en) | Method for monitoring underground multi-level space surface settlement deformation in real time | |
| CN113554849A (en) | Air-ground monitoring slope system and instability risk assessment method thereof | |
| CN115263432A (en) | Stability and safety monitoring and analyzing system for deeply-buried tunnel | |
| CN114399889B (en) | Rock-soil slope geological disaster early warning system | |
| CN117037428A (en) | Big data-based open pit coal mine slope safety early warning prediction system and method | |
| CN114638035A (en) | Control method and application of whole process of large open caisson construction | |
| CN207423114U (en) | A kind of landslide multi-point displacement intelligent monitoring device | |
| Xiao et al. | Safety monitoring of expressway construction based on multisource data fusion | |
| CN103196599B (en) | System and method for monitoring soil body inner stress variation of loess field under soaking condition | |
| CN115014272B (en) | Dyke intelligent monitoring device based on Internet of things and installation and monitoring method | |
| CN116233191A (en) | Intelligent foundation pit monitoring system | |
| CN112946240B (en) | Landslide geological disaster gene identification and prediction system | |
| CN203132748U (en) | Soil internal stress change monitoring system in loess place immersing condition | |
| CN203049632U (en) | Remote monitoring and recording system for construction of plastic drainage plate spile machine |
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 |