CN114239379B - A method and system for analyzing geological hazards of power transmission lines based on deformation detection - Google Patents
A method and system for analyzing geological hazards of power transmission lines based on deformation detection Download PDFInfo
- Publication number
- CN114239379B CN114239379B CN202111340434.2A CN202111340434A CN114239379B CN 114239379 B CN114239379 B CN 114239379B CN 202111340434 A CN202111340434 A CN 202111340434A CN 114239379 B CN114239379 B CN 114239379B
- Authority
- CN
- China
- Prior art keywords
- geological
- damage
- deformation
- offset
- damage degree
- 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.)
- Active
Links
Classifications
-
- 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
- G01—MEASURING; TESTING
- G01S—RADIO DIRECTION-FINDING; RADIO NAVIGATION; DETERMINING DISTANCE OR VELOCITY BY USE OF RADIO WAVES; LOCATING OR PRESENCE-DETECTING BY USE OF THE REFLECTION OR RERADIATION OF RADIO WAVES; ANALOGOUS ARRANGEMENTS USING OTHER WAVES
- G01S13/00—Systems using the reflection or reradiation of radio waves, e.g. radar systems; Analogous systems using reflection or reradiation of waves whose nature or wavelength is irrelevant or unspecified
- G01S13/88—Radar or analogous systems specially adapted for specific applications
- G01S13/89—Radar or analogous systems specially adapted for specific applications for mapping or imaging
- G01S13/90—Radar or analogous systems specially adapted for specific applications for mapping or imaging using synthetic aperture techniques, e.g. synthetic aperture radar [SAR] techniques
- G01S13/9021—SAR image post-processing techniques
- G01S13/9023—SAR image post-processing techniques combined with interferometric techniques
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2119/00—Details relating to the type or aim of the analysis or the optimisation
- G06F2119/02—Reliability analysis or reliability optimisation; Failure analysis, e.g. worst case scenario performance, failure mode and effects analysis [FMEA]
Landscapes
- Engineering & Computer Science (AREA)
- Remote Sensing (AREA)
- Radar, Positioning & Navigation (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Evolutionary Computation (AREA)
- General Physics & Mathematics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Artificial Intelligence (AREA)
- Computer Networks & Wireless Communication (AREA)
- Medical Informatics (AREA)
- Software Systems (AREA)
- Computer Hardware Design (AREA)
- Geometry (AREA)
- General Engineering & Computer Science (AREA)
- Electromagnetism (AREA)
- Geophysics And Detection Of Objects (AREA)
Abstract
The invention relates to a deformation detection-based transmission line geological disaster analysis method and system, and belongs to the technical field of remote sensing application. The method comprises the steps of obtaining the geological damage degree distribution of a tower foundation based on the comparison of a plurality of groups of remote sensing images before and after an earthquake, obtaining a built earthquake deformation field diagram by adopting differential interference, marking the geological damage degree distribution of the tower foundation, dividing according to an offset value range and an offset direction to form a sample library, and training a plurality of artificial neural network models; and acquiring remote sensing images before and after the earthquake, establishing a deformation field by differential interference, dividing based on the offset value and the offset direction, and selecting a corresponding artificial neural network model to acquire the geological damage degree of the foundation of the broken tower so as to form the geological damage condition distribution of the foundation of the transmission line. According to the method, the differential interference is adopted to obtain and establish the seismic deformation field diagram to obtain the geological damage degree of the power transmission line tower foundation, and the rapid delineation or the accurate evaluation of the earthquake damage degree of the power transmission line tower foundation geological disaster-affected range is realized.
Description
Technical Field
The invention belongs to the technical field of remote sensing application, and particularly relates to a deformation detection-based transmission line geological disaster analysis method and system.
Background
Earthquake causes a great deal of tower collapse, resulting in huge life and property losses. The number and degree of post-earthquake pole foundation damage are information necessary for disaster area rescue and reconstruction before the start.
Currently, the number of tower losses is generally determined by manually reporting data and field survey data. However, this method, which relies only on human investigation, is inefficient and has a problem in that real data cannot be acquired at the first time.
The high-spatial-resolution remote sensing technology has the characteristics of reality, objectivity, small influence by ground communication conditions and the like, can acquire a large amount of effective data at the first time, and provides effective support for timely determining the pole tower inverted loss quantity. The method for determining the tower collapse based on the image recognition has great difficulty, particularly in mountain areas, the distribution of the power transmission line towers is more dispersed, the types are various, the damage degree is different, the foundation geology of the towers cannot be accurately recognized, and the damage degree cannot be accurately estimated. Therefore, how to overcome the defects of the prior art is a problem to be solved in the technical field of remote sensing application at present.
Disclosure of Invention
The invention aims to solve the defects of the prior art, and provides a disaster analysis method and a disaster analysis system based on deformation detection, which are used for establishing a relation between a deformation field and the geological damage degree of a tower foundation, obtaining and establishing a deformation field diagram by adopting differential interference, further obtaining the geological damage degree of the tower foundation, and realizing rapid delineation of a disaster range or accurate evaluation of the earthquake damage degree.
In order to achieve the above purpose, the technical scheme adopted by the invention is as follows:
a deformation detection-based transmission line geological disaster analysis method comprises the following steps:
obtaining tower foundation geological damage degree distribution based on remote sensing image comparison before and after a plurality of groups of earthquakes, establishing a deformation field diagram by adopting differential interference, marking the tower foundation geological damage degree distribution, and dividing according to an offset value range and an offset direction to form a sample library;
Constructing a plurality of artificial neural network models, respectively adopting samples with different offset value ranges and offset directions to train and package;
remote sensing images before and after the earthquake to be analyzed are obtained, deformation fields are established through differential interference, segmentation is conducted based on offset values and offset directions, artificial neural network models corresponding to the offset value ranges and the offset directions are selected to identify the geological damage degree of the tower foundation, and the geological damage condition distribution of the tower foundation is formed.
Further, it is preferable that the method further comprises evaluating the seismic intensity based on the obtained damage condition and outputting the seismic intensity distribution.
Further, preferably, the distribution of the geological damage degree of the tower foundation comprises the duty ratio of each damage type, the change detection results of SAR remote sensing images before and after the earthquake and corresponding high-resolution optical remote sensing images are used for judging, and qualitative labeling confirmation is carried out through field visual investigation;
The damage types comprise damage collapse, damage non-collapse, serious damage, slight damage and basically perfect, wherein the area change rate of the corresponding front and rear images is more than or equal to 80%, the area change rate is more than or equal to 60% and less than 80%, the area change rate is more than or equal to 40% and less than 60%, the area change rate is more than or equal to 20% and less than 40%, and the area change rate is less than 20%; the region change rate is the root mean square error of the inclination displacement of the sequence images of two time phases in the same region.
Further, it is preferable that the differential interference set up the deformation field includes: and acquiring a deformation point map covering the seismic influence area for quantitative labeling, and calculating the inclination displacement information of the tower area so as to quantitatively reflect the influence degree of the geological disaster.
Further, it is preferable that the artificial neural network model includes a convolution layer, a pooling layer, an activation layer, and a full connection layer; the feature extraction of the convolution layer comprises the steps of extracting image features according to an interference pattern, extracting deformation value distribution according to deformation contour lines, and extracting whether the image features are located in a fault zone or not according to cross-fault section lines; the pooling layer reduces the dimension of the extracted features; the activation layer adopts Relu functions; and outputting the geological damage distribution result of the tower foundation by the full-connection layer.
Further, it is preferable that the dividing based on the offset value and the offset direction includes: the divided region has a certain range of offset values and offset directions.
The invention also provides a deformation detection-based transmission line geological disaster analysis system, which comprises an input module, a segmentation module, a selection module, a plurality of damage degree identification modules and an output module;
the input module is used for acquiring a deformation field;
the segmentation module is used for segmenting the deformation field based on the offset value and the offset direction;
The selection module is used for selecting the corresponding damage degree identification module to identify the geological damage degree of the foundation of the tower based on the offset value and the offset direction;
the output module is used for quantitatively outputting the geological damage degree of the tower foundation and forming a distribution result of geological damage of the tower foundation by combining corresponding geographic information.
Further, preferably, the damage degree identification module is constructed and obtained through training by an artificial neural network model; and obtaining the geological damage degree distribution of the tower foundation based on the comparison of a plurality of groups of remote sensing images before and after the earthquake, obtaining and establishing a deformation field diagram by adopting differential interference, marking the geological damage degree distribution of the tower foundation, dividing according to the range of the offset value and the offset direction to form a sample library, selecting a training sample by the sample library to train an artificial neural network model to meet the error grade, and packaging.
Further, it is preferable that the artificial neural network model includes a convolution layer, a pooling layer, an activation layer, and a full connection layer; the feature extraction of the convolution layer comprises the steps of extracting image features according to an interference pattern, extracting deformation value distribution according to deformation contour lines, and extracting whether the image features are located in a fault zone or not according to cross-fault section lines; the pooling layer reduces the dimension of the extracted features; the activation layer adopts Relu functions to perform nonlinear calculation; the full-connection layer outputs a tower foundation geological damage distribution result;
The distribution of the geological damage degree of the tower foundation comprises the duty ratio of each damage type, wherein the damage type comprises damage collapse, damage non-collapse, serious damage, slight damage and basically perfect;
The deformation field includes: and (5) covering the deformation point bitmap of the seismic influence area, and quantitatively marking based on the offset.
Preferably, the activation layer adopts Relu functions, and the Relu functions are utilized to perform nonlinear calculation on feature vectors such as geometry and texture provided by the high-resolution optical remote sensing image and polarization and inclination displacement provided by the SAR remote sensing image.
The invention does not limit the specific division of the offset value and the offset direction, and can correspondingly divide according to the actual operational calculation amount, for example, the division can be performed in a thinner way if the load-bearing calculation amount is larger. For another example, the offset direction is equally divided into 8 ranges according to 360 ° representing 8 directions; the offset is divided into 8 ranges on average according to no offset to maximum offset.
Compared with the prior art, the invention has the beneficial effects that:
(1) The method utilizes the characteristics of wide coverage of the remote sensing image, no influence of ground conditions and capability of obtaining the remote sensing image at the first time, and realizes the first time delineating the disaster-affected range after the earthquake occurs and the evaluation of the earthquake damage degree.
(2) The InSAR technology is used as a novel geodetic technology, has the advantage of large-area coverage, and can image disaster areas and acquire deformation information of the disaster areas. The method establishes the relation between the deformation field and the geological damage degree of the tower foundation, utilizes the deformation field, combines corresponding high-resolution optical remote sensing images based on different fault directions, fault two-side deformation directions and deformation values, comprehensively forms standard and unified regional change rate, and is used for evaluating the corresponding geological damage degree of the tower foundation, so that the evaluation is more accurate.
(3) According to the invention, a plurality of groups of artificial neural network models are established aiming at different deformation directions and deformation values, and the corresponding artificial neural network models are selected according to the deformation directions and the deformation values, so that the identification accuracy is ensured.
Drawings
In order to more clearly illustrate the embodiments of the invention or the technical solutions of the prior art, the drawings which are used in the description of the embodiments or the prior art will be briefly described, it being obvious that the drawings in the description below are only some embodiments of the invention, and that other drawings can be obtained according to these drawings without inventive faculty for a person skilled in the art.
FIG. 1 is a flow chart of a method for analyzing geological disasters of a power transmission line based on deformation detection;
FIG. 2 is a schematic diagram of an artificial neural network model;
fig. 3 is a schematic diagram of a transmission line geological disaster analysis system based on deformation detection;
FIG. 4 is a diagram of the surface deformation field of the investigation region
FIG. 5 is a schematic diagram of image segmentation of a surface deformation field map according to different offset values; the external boundaries with different thicknesses correspond to different offset values;
FIG. 6 is a schematic diagram of training SAR and hyperspectral remote sensing images of a shaft tower area based on field verification for sample labeling;
FIG. 7 is a graph of results of tower foundation geological damage obtained by performing tower change monitoring and identification.
Detailed Description
The present invention will be described in further detail with reference to examples.
It will be appreciated by those skilled in the art that the following examples are illustrative of the present invention and should not be construed as limiting the scope of the invention. The specific techniques or conditions are not identified in the examples and are performed according to techniques or conditions described in the literature in this field or according to the product specifications. The materials or equipment used are conventional products available from commercial sources, not identified to the manufacturer. In addition, in the following description, descriptions of well-known structures and techniques are omitted so as not to unnecessarily obscure the present invention.
As shown in fig. 1, a method for analyzing geological disasters of a power transmission line based on deformation detection includes:
obtaining tower foundation geological damage degree distribution based on remote sensing image comparison before and after a plurality of groups of earthquakes, establishing a deformation field diagram by adopting differential interference, marking the tower foundation geological damage degree distribution, and dividing according to an offset value range and an offset direction to form a sample library;
Constructing a plurality of artificial neural network models, respectively adopting samples with different offset value ranges and offset directions to train and package;
remote sensing images before and after the earthquake to be analyzed are obtained, deformation fields are established through differential interference, segmentation is conducted based on offset values and offset directions, artificial neural network models corresponding to the offset value ranges and the offset directions are selected to identify the geological damage degree of the tower foundation, and the geological damage condition distribution of the tower foundation is formed.
Preferably, the method further comprises evaluating seismic intensity based on the obtained damage condition and outputting seismic intensity distribution.
Preferably, the geological damage degree distribution of the tower foundation comprises the duty ratio of each damage type, the change detection results of SAR remote sensing images before and after an earthquake and corresponding high-resolution optical remote sensing images are used for judging, and qualitative labeling confirmation is carried out through field visual investigation;
The damage types comprise damage collapse, damage non-collapse, serious damage, slight damage and basically perfect, wherein the area change rate of the corresponding front and rear images is more than or equal to 80%, the area change rate is more than or equal to 60% and less than 80%, the area change rate is more than or equal to 40% and less than 60%, the area change rate is more than or equal to 20% and less than 40%, and the area change rate is less than 20%; the region change rate is the root mean square error of the inclination displacement of the sequence images of two time phases in the same region.
Preferably, the differential interference establishing the deformation field comprises: and acquiring a deformation point map covering the seismic influence area for quantitative labeling, and calculating the inclination displacement information of the tower area.
Preferably, the artificial neural network model comprises a convolution layer, a pooling layer, an activation layer and a full connection layer; the feature extraction of the convolution layer comprises the steps of extracting image features according to an interference pattern, extracting deformation value distribution according to deformation contour lines, and extracting whether the image features are located in a fault zone or not according to cross-fault section lines; the pooling layer reduces the dimension of the extracted features; the activation layer adopts Relu functions; and outputting the geological damage distribution result of the tower foundation by the full-connection layer.
Preferably, the dividing based on the offset value and the offset direction includes: the divided region has a certain range of offset values and offset directions.
As shown in fig. 3, the transmission line geological disaster analysis system based on deformation detection comprises an input module, a segmentation module, a selection module, a plurality of damage degree identification modules and an output module;
the input module is used for acquiring a deformation field;
the segmentation module is used for segmenting the deformation field based on the offset value and the offset direction;
The selection module is used for selecting the corresponding damage degree identification module to identify the geological damage degree of the foundation of the tower based on the offset value and the offset direction;
the output module is used for quantitatively outputting the geological damage degree of the tower foundation and forming a distribution result of geological damage of the tower foundation by combining corresponding geographic information.
Preferably, the damage degree recognition module is constructed and trained by an artificial neural network model; and obtaining the geological damage degree distribution of the tower foundation based on the comparison of a plurality of groups of remote sensing images before and after the earthquake, obtaining and establishing a deformation field diagram by adopting differential interference, marking the geological damage degree distribution of the tower foundation, dividing according to the range of the offset value and the offset direction to form a sample library, selecting a training sample by the sample library to train an artificial neural network model to meet the error grade, and packaging.
Preferably, the artificial neural network model comprises a convolution layer, a pooling layer, an activation layer and a full connection layer; the feature extraction of the convolution layer comprises the steps of extracting image features according to an interference pattern, extracting deformation value distribution according to deformation contour lines, and extracting whether the image features are located in a fault zone or not according to cross-fault section lines; the pooling layer reduces the dimension of the extracted features; the activation layer adopts Relu functions to perform nonlinear calculation; the full-connection layer outputs a tower foundation geological damage distribution result;
The distribution of the geological damage degree of the tower foundation comprises the duty ratio of each damage type, wherein the damage type comprises damage collapse, damage non-collapse, serious damage, slight damage and basically perfect;
The deformation field includes: and (5) covering the deformation point bitmap of the seismic influence area, and quantitatively marking based on the offset.
Specifically, the invention provides a deformation detection-based transmission line geological disaster analysis method, which comprises the following steps in combination with fig. 1:
(1) Obtaining the geological damage degree distribution of the tower foundation based on the comparison of a plurality of groups of remote sensing images before and after the earthquake, obtaining the terrain phase difference of the area by adopting differential interference, establishing a deformation field diagram, dividing according to the range of the offset value and the offset direction, combining the corresponding high-resolution optical remote sensing images to form a sample database, and marking the geological damage degree of the tower foundation.
The SAR interferometry technology is utilized to monitor the surface deformation and evaluate the earthquake damage index, the deformation field is obtained through image registration, noise filtering and phase unwrapping in the interferometry, and the spatial dynamic change characteristics of the deformation field are extracted through quantitative analysis of the offset information of each deformation point.
The differential interferometry utilizes two SAR complex images observed in the same area to carry out interference processing, and acquires the elevation information and deformation information of the ground surface through phase information. InSAR can be divided into a single-pass (single-pass) mode and a repeat-pass (repeat-pass) mode according to imaging time. The single track interference means that two antennae are loaded on the same airborne or spaceborne platform, one antenna transmits signals, the two antennae both receive ground echo signals, and the acquired data are used for interference processing. The repeated track interference refers to that the same sensor or similar sensors image the ground twice according to parallel tracks, and the obtained data is used for interference processing. The spatial distance between SAR systems at two imaging is called spatial baseline distance and the time interval is called temporal baseline. Under the condition of neglecting noise, assuming that the atmospheric conditions are basically consistent in the two imaging processes, deformation information of a ground target point can be obtained by removing the land phase and the terrain phase. The invention adopts the time sequence InSAR images before and after the earthquake, and the deformation monitoring points obtained by processing have three-dimensional position coordinates, deformation direction and speed information. The deformation refers to deformation of radar Sight Line (LOS), positive values represent movement towards the radar, negative values represent movement away from the radar, and are expressed as lifting and sinking respectively for convenience of expression. The green color indicates stability, the left side of the scale is subsidence and the right side of the scale is lifting, and the darker the color, the larger the deformation. As shown in fig. 4.
The quantitative evaluation of the distribution of the degree of geological damage of the foundation of the tower comprises the duty ratio of each damaged type. And judging by using the change detection results of the remote sensing images before and after geology, and taking the area change rate as an index, namely, the root mean square error of the inclination displacement of the two images in the same area and the like. The tilt direction is a direction away from the satellite radar or a direction close to the satellite radar. By counting the root mean square error (in cm,) Dividing by the threshold value of the ground (e.g., 10 cm) to obtain the ratio of the area change rate. (X, Y) is the coordinates after displacement, and (X ', Y') is the coordinates before displacement, wherein the damage type comprises collapse damage, non-collapse damage, serious damage, slight damage and basically perfect damage, and the area change rate of the images before and after damage is more than or equal to 80%, the area change rate is more than or equal to 60% and less than or equal to 80%, the area change rate is more than or equal to 40% and less than or equal to 60%, the area change rate is more than or equal to 20% and less than or equal to 40%, and the area change rate is less than or equal to 20%.
Artificial neural networks require a large number of training samples. According to the method, a geological deformation field map is segmented according to the range of the offset value and the offset direction (the offset direction is the direction far from the satellite radar or the direction close to the satellite radar, the offset value is usually in the level of 1 mm), and a sample library is formed by combining the corresponding high-resolution optical remote sensing image. The images corresponding to the geological deformation field map are interpreted by adopting manual visual observation and combined with the issued information, so that the damage degree of the single body of the pole tower is determined, and the correction is carried out by combining with the issued information, as shown in fig. 5 and 6.
Further, in order to ensure the richness of the sample and the comprehensiveness of coverage, deformation field diagrams of geology of different areas can be established for multiple times and marked to form a sample library.
(2) And constructing a plurality of artificial neural network models, respectively adopting samples with different offset value ranges and offset directions to train and package.
In order to obtain a more accurate evaluation result, the offset value is divided into a plurality of ranges, and different sample training is adopted for different offset value ranges and offset directions respectively for identifying the different offset value ranges and offset directions in use.
An artificial neural network model, in combination with fig. 2, includes a convolution layer, a pooling layer, an activation layer, and a full connection layer; the input of the convolution layer is a geological deformation field map divided into single offset and direction. The feature extraction comprises the geometric and texture of a high-spectroscope remote sensing image, the polarization and inclined displacement features of an SAR remote sensing image, the deformation value distribution is extracted according to deformation contour lines, whether the cross-fault section line extraction is located in a fault zone or not is judged, and the features 1 to M are obtained after the extraction; the pooling layer performs dimension reduction on the extracted features, as shown in fig. 2, dimension-reduces the features 1 to M to the nodes a21 to a2n through the weight W1n, dimension-reduces the nodes a21 to a2n to the nodes a31 to a3n through the weight W2n, and dimension-reduces the nodes to the output node through the weight W3 n; the activation layer adopts Relu functions to carry out nonlinear calculation on the required feature vectors; and outputting the geological damage distribution result of the tower foundation by the full-connection layer. And continuously updating W1n, W2n and W3n in the training process to finish classification.
Each artificial neural network model is obtained through training, which includes:
Selecting training samples and verification samples from the corresponding sub-sample libraries; training the set rounds by adopting training samples; and adopting a verification sample to verify, judging whether the error level is accepted, if so, completing training, otherwise, performing training of set rounds. The set number of rounds is, for example, 50.
And packaging the trained artificial neural network for on-site recognition.
(3) The method comprises the steps of obtaining remote sensing images before and after an earthquake, obtaining differential interference to establish a deformation field, dividing based on offset values and offset directions, combining high-resolution optical remote sensing images, and selecting a corresponding artificial neural network model to obtain the geological damage degree of a broken tower foundation so as to form the geological damage condition distribution of the tower foundation.
Dividing based on the offset value and the offset direction includes dividing the region into a single offset value and offset direction, further dividing the region into a recognizable size if the size exceeds the size recognized by the artificial neural network model, and amplifying the region to satisfy the recognized size if the image is too small. And the corresponding artificial neural network model is input to be identified by a single offset value and an offset direction, so that the damage degree is marked, and the marking accuracy is ensured. And marking all parts to form the geological damage condition distribution of the foundation of the tower.
By adopting a plurality of artificial neural networks for recognition, on one hand, the accuracy is higher, and on the other hand, the recognition efficiency can be higher in parallel.
In another aspect, the invention provides a deformation detection-based power transmission line geological disaster analysis system, which is combined with fig. 3, and comprises an input module, a segmentation module, a selection module, a plurality of damage degree identification modules and an output module;
The input module acquires a geological deformation field;
the segmentation module segments the geological deformation field based on the offset value and the offset direction;
The selection module selects a corresponding damage degree identification module to identify the geological damage degree of the foundation of the tower based on the offset value and the offset direction;
The damage degree identification module is constructed and trained by an artificial neural network model; and obtaining the geological damage degree distribution of the tower foundation based on the comparison of a plurality of groups of remote sensing images before and after the earthquake, obtaining and establishing a deformation field diagram by adopting differential interference, marking the geological damage degree distribution of the tower foundation, dividing according to the range of the offset value and the offset direction to form a sample library, selecting a training sample by the sample library to train an artificial neural network model to meet the error grade, and packaging. The method divides the image based on two indexes of the offset value and the offset direction, and correspondingly inputs the SAR remote sensing image with different damage degree marks and the high-resolution optical remote sensing image as training samples into a neural network, and outputs the training samples through the network to obtain a tower foundation geological damage distribution map, as shown in figure 7.
The output module corresponds the geological damage degree of the tower foundation with the geographical position, and the geological damage condition distribution of the tower foundation is formed.
1) The geological deformation field map is a surface deformation field distribution map obtained by a D-InSAR technology, preprocessing is carried out on two-scene complex SAR images before and after geology through track parameter correction and pre-filtering, then the generation processing of image fine registration, interferogram and coherent image generation, post-filtering and phase unwrapping is carried out, and then the calculation from the interference phase to the geographic information is carried out, wherein the calculation mainly comprises phase to elevation conversion, geocoding and DEM construction, and finally the surface deformation information can be obtained.
2) The tower pole foundation geological damage degree distribution diagram is obtained by analyzing related geological data in a geological region collected in the earlier stage, or can be obtained by manually drawing a ground surface deformation diagram obtained in the earlier stage according to geographic coordinates, and the geological deformation field diagram and the tower pole foundation geological damage degree distribution diagram are input into a network according to geographic position relations for feature extraction.
3) The fault surface position and trend change data can be obtained from local geological departments to obtain related vectors or grid data, and can be obtained by carrying out vectorization on a local geological atlas according to actual needs, wherein a geographic coordinate system used in vectorizing a layer is the same as a geological deformation field distribution diagram in the earlier stage so as to ensure that superposition analysis processing can be carried out.
4) The offset value needs to be calculated according to the surface deformation graph acquired in the earlier stage. The surface deformation value obtained by D-InSAR direct settlement is deformation observed in a distance direction, the deformation quantity in a certain direction of vertical deformation and plane, namely an offset value, can be calculated according to the relation with the incident angle of the satellite, and the offset direction obtained at the moment is vertical to the flight direction of the satellite; and the three-dimensional deformation calculation can be performed by using different orbit data and utilizing two observation angles, so that the offset in the north-south and east-west directions can be obtained. As the monitoring precision can reach millimeter level, the offset value range can be divided into intervals according to the offset caused by the vibration level, and the offset value range is related to the vibration level so as to quantitatively evaluate the damage degree of the tower pole.
5) The model structure comprises a convolution layer, a pooling layer, an activation layer and a full connection layer, and is specifically described in the specification. The offset, the offset direction, the geological damage degree of the foundation of the tower pole and the fault trend can be respectively endowed with different initial weight values when training is started, and the initial weight values can be set to 0.4,0.1,0.4,0.1, and the specific values are set according to the geological condition of the vibration range.
In summary, the invention provides a deformation detection-based transmission line geological disaster analysis method and system, which are used for obtaining tower foundation geological damage degree distribution based on remote sensing image comparison before and after a plurality of groups of earthquakes, obtaining a deformation field diagram by adopting differential interference, marking the tower foundation geological damage degree distribution, dividing according to an offset value range and an offset direction to form a sample library, and training a plurality of artificial neural network models; and acquiring remote sensing images before and after the earthquake, establishing a deformation field by differential interference, dividing based on the offset value and the offset direction, and selecting a corresponding artificial neural network model to acquire the geological damage degree of the foundation of the tower, thereby forming the geological damage condition distribution of the foundation of the tower. According to the method, the deformation field diagram is built by adopting differential interference to obtain the geological damage degree of the tower foundation, and the rapid delineation of the disaster range or the accurate evaluation of the earthquake damage degree are realized.
The foregoing has shown and described the basic principles, principal features and advantages of the invention. It will be understood by those skilled in the art that the present invention is not limited to the embodiments described above, and that the above embodiments and descriptions are merely illustrative of the principles of the present invention, and various changes and modifications may be made without departing from the spirit and scope of the invention, which is defined in the appended claims. The scope of the invention is defined by the appended claims and equivalents thereof.
Claims (7)
1. The deformation detection-based transmission line geological disaster analysis method is characterized by comprising the following steps of:
obtaining tower foundation geological damage degree distribution based on remote sensing image comparison before and after a plurality of groups of earthquakes, establishing a deformation field diagram by adopting differential interference, marking the tower foundation geological damage degree distribution, and dividing according to an offset value range and an offset direction to form a sample library;
Constructing a plurality of artificial neural network models, respectively adopting samples with different offset value ranges and offset directions to train and package;
acquiring remote sensing images before and after an earthquake to be analyzed, establishing a deformation field by adopting differential interference, dividing based on offset values and offset directions, and selecting an artificial neural network model corresponding to the offset value range and the offset directions to identify the geological damage degree of the tower foundation so as to form the geological damage condition distribution of the tower foundation;
the differential interference establishes a deformation field comprising: acquiring a deformation point map covering an earthquake influence area for quantitative labeling, and calculating inclination displacement information of a tower area;
The artificial neural network model comprises a convolution layer, a pooling layer, an activation layer and a full connection layer; the feature extraction of the convolution layer comprises the steps of extracting image features according to an interference pattern, extracting deformation value distribution according to deformation contour lines, and extracting whether the image features are located in a fault zone or not according to cross-fault section lines; the pooling layer reduces the dimension of the extracted features; the activation layer adopts Relu functions; and outputting the geological damage distribution result of the tower foundation by the full-connection layer.
2. The deformation detection-based transmission line geological disaster analysis method according to claim 1, further comprising evaluating seismic intensity based on the obtained damage condition and outputting seismic intensity distribution.
3. The deformation detection-based transmission line geological disaster analysis method according to claim 1 or 2, wherein the tower foundation geological damage degree distribution comprises the duty ratio of each damage type, is judged according to the change detection results of SAR remote sensing images before and after an earthquake and corresponding high-resolution optical remote sensing images, and is subjected to qualitative labeling confirmation through field visual investigation;
The damage types comprise damage collapse, damage non-collapse, serious damage, slight damage and basically perfect, wherein the area change rate of the corresponding front and rear images is more than or equal to 80%, the area change rate is more than or equal to 60% and less than 80%, the area change rate is more than or equal to 40% and less than 60%, the area change rate is more than or equal to 20% and less than 40%, and the area change rate is less than 20%; the region change rate is the root mean square error of the inclination displacement of the sequence images of two time phases in the same region.
4. The deformation detection-based transmission line geological disaster analysis method according to claim 1, wherein the dividing based on the offset value and the offset direction comprises: the division into the regions has a single offset value and offset direction.
5. A deformation detection-based transmission line geological disaster analysis system, which adopts the deformation detection-based transmission line geological disaster analysis method according to any one of claims 1-4, and is characterized by comprising an input module, a segmentation module, a selection module, a plurality of damage degree identification modules and an output module;
the input module is used for acquiring a deformation field;
the segmentation module is used for segmenting the deformation field based on the offset value and the offset direction;
The selection module is used for selecting the corresponding damage degree identification module to identify the geological damage degree of the foundation of the tower based on the offset value and the offset direction;
the output module is used for quantitatively outputting the geological damage degree of the tower foundation and forming a distribution result of geological damage of the tower foundation by combining corresponding geographic information.
6. The deformation detection-based transmission line geological disaster analysis system according to claim 5, wherein the damage degree identification module is constructed and trained by an artificial neural network model; and obtaining the geological damage degree distribution of the tower foundation based on the comparison of a plurality of groups of remote sensing images before and after the earthquake, obtaining and establishing a deformation field diagram by adopting differential interference, marking the geological damage degree distribution of the tower foundation, dividing according to the range of the offset value and the offset direction to form a sample library, selecting a training sample by the sample library to train an artificial neural network model to meet the error grade, and packaging.
7. The deformation detection-based transmission line geological disaster analysis system according to claim 6, wherein the artificial neural network model comprises a convolution layer, a pooling layer, an activation layer and a full connection layer; the feature extraction of the convolution layer comprises the steps of extracting image features according to an interference pattern, extracting deformation value distribution according to deformation contour lines, and extracting whether the image features are located in a fault zone or not according to cross-fault section lines; the pooling layer reduces the dimension of the extracted features; the activation layer adopts Relu functions to perform nonlinear calculation; the full-connection layer outputs a tower foundation geological damage distribution result;
The distribution of the geological damage degree of the tower foundation comprises the duty ratio of each damage type, wherein the damage type comprises damage collapse, damage non-collapse, serious damage, slight damage and basically perfect;
The deformation field includes: and (5) covering the deformation point bitmap of the seismic influence area, and quantitatively marking based on the offset.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111340434.2A CN114239379B (en) | 2021-11-12 | 2021-11-12 | A method and system for analyzing geological hazards of power transmission lines based on deformation detection |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111340434.2A CN114239379B (en) | 2021-11-12 | 2021-11-12 | A method and system for analyzing geological hazards of power transmission lines based on deformation detection |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN114239379A CN114239379A (en) | 2022-03-25 |
| CN114239379B true CN114239379B (en) | 2024-11-15 |
Family
ID=80749424
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111340434.2A Active CN114239379B (en) | 2021-11-12 | 2021-11-12 | A method and system for analyzing geological hazards of power transmission lines based on deformation detection |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114239379B (en) |
Families Citing this family (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115019145A (en) * | 2022-06-15 | 2022-09-06 | 交通运输部公路科学研究所 | A monitoring method for road surface settlement and deformation of Qinghai-Tibet Plateau highway |
| CN115071974B (en) * | 2022-06-24 | 2025-02-14 | 广西电网有限责任公司电力科学研究院 | Autonomous post-disaster survey method of unmanned aerial vehicle based on geological hazard monitoring system |
| CN116091926B (en) * | 2023-01-06 | 2025-06-03 | 广西电网有限责任公司电力科学研究院 | A method for determining geological hazards based on geological settlement data of power facilities |
| CN117612339B (en) * | 2023-11-09 | 2024-06-04 | 应急管理部大数据中心 | Geological disaster monitoring method and system based on iron tower big data |
| CN119693578A (en) * | 2025-02-20 | 2025-03-25 | 中国地震局地质研究所 | Fault shape variation zone drawing method, device, electronic equipment and storage medium |
Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111880210A (en) * | 2020-08-05 | 2020-11-03 | 中国南方电网有限责任公司 | Ground disaster monitoring and processing method and device for power transmission line, early warning system and equipment |
Family Cites Families (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110456346B (en) * | 2019-06-28 | 2020-10-23 | 深圳市水务规划设计院股份有限公司 | Power transmission tower inclination monitoring method based on InSAR technology |
| CN111090954A (en) * | 2019-12-17 | 2020-05-01 | 国家电网有限公司 | Geological disaster hidden danger identification and analysis, evaluation and treatment method |
| CN111929683B (en) * | 2020-07-28 | 2021-06-25 | 中国自然资源航空物探遥感中心 | Landslide Deformation Agglomeration Prediction Model Generation Method and Landslide Deformation Aggregate Prediction Method |
-
2021
- 2021-11-12 CN CN202111340434.2A patent/CN114239379B/en active Active
Patent Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111880210A (en) * | 2020-08-05 | 2020-11-03 | 中国南方电网有限责任公司 | Ground disaster monitoring and processing method and device for power transmission line, early warning system and equipment |
Non-Patent Citations (1)
| Title |
|---|
| 冻土区输电线塔监测预警系统设计;付兵彬等;《农村电气化》;20201110(第11期);正文第42-45页 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN114239379A (en) | 2022-03-25 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN114239379B (en) | A method and system for analyzing geological hazards of power transmission lines based on deformation detection | |
| CN111142119B (en) | A method for dynamic identification and monitoring of mine geological hazards based on multi-source remote sensing data | |
| CN114353876A (en) | A method for health monitoring of loess highway slopes | |
| CN111090954A (en) | Geological disaster hidden danger identification and analysis, evaluation and treatment method | |
| Lehtomäki et al. | Power line mapping technique using all-terrain mobile laser scanning | |
| CN105678085A (en) | PM2.5 concentration estimation method and system | |
| CN118196637B (en) | A potential landslide identification method based on coupling of InSAR deformation and influencing factors | |
| CN117968631A (en) | Pavement subsidence detection method based on unmanned aerial vehicle DOM and satellite-borne SAR image | |
| Hao et al. | Extraction and analysis of tree canopy height information in high-voltage transmission-line corridors by using integrated optical remote sensing and LiDAR | |
| Shan et al. | Feasibility of Accurate Point Cloud Model Reconstruction for Earthquake‐Damaged Structures Using UAV‐Based Photogrammetry | |
| CN119085616B (en) | Three-dimensional topography mapping system based on remote sensing technology | |
| Liu et al. | Architecture planning and geo-disasters assessment mapping of landslide by using airborne LiDAR data and UAV images | |
| Comert et al. | Object based building extraction and building period estimation from unmanned aerial vehicle data | |
| CN114998395A (en) | Effective embankment three-dimensional data change detection method and system | |
| Ajayi et al. | Modelling 3D Topography by comparing airborne LiDAR data with Unmanned Aerial System (UAS) photogrammetry under multiple imaging conditions | |
| CN110470275A (en) | A method of withered riverbed bed ripples morphological parameters are measured based on UAV aerial survey terrain data | |
| Sui et al. | Processing of multitemporal data and change detection | |
| CN112902823B (en) | Bridge space-to-ground multi-source observation collaborative dynamic monitoring and safety early warning technology | |
| CN112166688B (en) | Method for monitoring desert and desertification land based on minisatellite | |
| CN111414867A (en) | Method for measuring and calculating aboveground biomass of plants | |
| CN117437559A (en) | Unmanned aerial vehicle-based method and device for detecting ground surface rock movement deformation of coal mining area | |
| CN117452402A (en) | An interferometric SAR measurement method and system | |
| Cuartero et al. | Positional accuracy analysis of satellite imagery by circular statistics | |
| Li et al. | Detecting, Monitoring, and Analyzing the Surface Subsidence in the Yellow River Delta (China) Combined with CenterNet Network and SBAS‐InSAR | |
| Asghar | Landslide mapping from analysis of UAV-SFM point clouds |
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 |