CN115953691A - Method and system for dynamically identifying earthwork blasting - Google Patents
Method and system for dynamically identifying earthwork blasting Download PDFInfo
- Publication number
- CN115953691A CN115953691A CN202310220702.XA CN202310220702A CN115953691A CN 115953691 A CN115953691 A CN 115953691A CN 202310220702 A CN202310220702 A CN 202310220702A CN 115953691 A CN115953691 A CN 115953691A
- Authority
- CN
- China
- Prior art keywords
- blasting
- data
- earth
- hyperspectral
- matrix
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
- 238000005422 blasting Methods 0.000 title claims abstract description 174
- 238000000034 method Methods 0.000 title claims abstract description 52
- 230000008859 change Effects 0.000 claims abstract description 113
- 230000003595 spectral effect Effects 0.000 claims abstract description 90
- 239000004575 stone Substances 0.000 claims abstract description 83
- 238000001228 spectrum Methods 0.000 claims abstract description 29
- 230000000694 effects Effects 0.000 claims abstract description 27
- 239000011159 matrix material Substances 0.000 claims description 120
- 239000002245 particle Substances 0.000 claims description 76
- 238000012546 transfer Methods 0.000 claims description 26
- 238000013467 fragmentation Methods 0.000 claims description 24
- 238000006062 fragmentation reaction Methods 0.000 claims description 24
- 230000007547 defect Effects 0.000 claims description 14
- 239000011435 rock Substances 0.000 claims description 11
- 239000002689 soil Substances 0.000 claims description 10
- 238000012512 characterization method Methods 0.000 claims description 8
- 239000000463 material Substances 0.000 claims description 8
- 238000004590 computer program Methods 0.000 claims description 6
- 238000012216 screening Methods 0.000 claims description 6
- 239000000126 substance Substances 0.000 claims description 5
- 230000014509 gene expression Effects 0.000 claims description 4
- 230000008030 elimination Effects 0.000 claims description 3
- 238000003379 elimination reaction Methods 0.000 claims description 3
- 238000011156 evaluation Methods 0.000 claims description 3
- 238000005516 engineering process Methods 0.000 abstract description 7
- 238000012544 monitoring process Methods 0.000 abstract description 5
- 230000007812 deficiency Effects 0.000 abstract 1
- 230000008569 process Effects 0.000 description 12
- 230000004044 response Effects 0.000 description 10
- 238000002834 transmittance Methods 0.000 description 9
- 239000004973 liquid crystal related substance Substances 0.000 description 8
- 238000004880 explosion Methods 0.000 description 4
- 238000010276 construction Methods 0.000 description 3
- 238000010586 diagram Methods 0.000 description 3
- 230000000007 visual effect Effects 0.000 description 3
- 208000037656 Respiratory Sounds Diseases 0.000 description 2
- 238000009412 basement excavation Methods 0.000 description 2
- 238000004364 calculation method Methods 0.000 description 2
- 230000001737 promoting effect Effects 0.000 description 2
- 241000208340 Araliaceae Species 0.000 description 1
- 235000005035 Panax pseudoginseng ssp. pseudoginseng Nutrition 0.000 description 1
- 235000003140 Panax quinquefolius Nutrition 0.000 description 1
- 238000004458 analytical method Methods 0.000 description 1
- 238000012937 correction Methods 0.000 description 1
- 238000013135 deep learning Methods 0.000 description 1
- 239000000428 dust Substances 0.000 description 1
- 239000002360 explosive Substances 0.000 description 1
- 235000008434 ginseng Nutrition 0.000 description 1
- 239000008187 granular material Substances 0.000 description 1
- 238000003384 imaging method Methods 0.000 description 1
- 238000005065 mining Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
- 238000005316 response function Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 238000012800 visualization Methods 0.000 description 1
Images
Classifications
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
- Y02P90/00—Enabling technologies with a potential contribution to greenhouse gas [GHG] emissions mitigation
- Y02P90/30—Computing systems specially adapted for manufacturing
Landscapes
- Geophysics And Detection Of Objects (AREA)
- Image Processing (AREA)
Abstract
The invention relates to the field of earthwork blasting monitoring, in particular to a method and a system for dynamically identifying earthwork blasting, wherein the method for dynamically identifying earthwork blasting comprises the following steps: setting an observation angle and an observation position according to the spatial position of the earth and stone; adjusting the shooting positions of the hyperspectral camera and the high-speed camera according to the observation angle and the observation position; acquiring hyperspectral data and image data in the blasting area through a hyperspectral camera and a high-speed camera; acquiring dynamic spectrum change data in the blasting area according to the hyperspectral data; acquiring dynamic change data of a blasting block in a blasting area by using the image data; and dynamically identifying the earthwork blasting effect through the spectral dynamic change data and the blasting block dynamic change data. The method makes up the deficiency of image data in representing blasting effect capability by introducing hyperspectral data, and improves spectral resolution by a spectral reconstruction technology, so that the identified earthwork blasting effect is more accurate.
Description
Technical Field
The invention relates to the field of earthwork blasting monitoring, in particular to a method and a system for dynamically identifying earthwork blasting.
Background
The blasting technology is a key technology in capital construction projects such as railways, mines, reservoirs and the like, and specific implementation blasting modes and corresponding target blasting effects are different aiming at different blasting targets. The earth and rockfill blasting technology is a technical method for earth and rockfill mining, which is commonly used in blasting technology. The earthwork blasting refers to a construction method for blasting earthwork by using blasting materials such as explosive detonators and the like in engineering construction of roads, bridges, mines, tunnels, foundation pits, hole piles, pipe ditches and the like so as to achieve the aim of excavation. In the process of the earthwork blasting, due to the influence of various factors, some safety problems can occur in the process of the earthwork blasting, and therefore, the process of the earthwork blasting needs to be monitored safely in real time.
At present, the real-time safety monitoring of earthwork blasting in-process mainly includes the dynamic image data of the earthwork blasting process of catching through the high-speed camera of high definition and combines the aspect of image recognition technique, the influence scope of dynamic recognition earthwork blasting, the distribution of blasting block, blasting effects such as the volume of blasting earthwork. However, the continuous image or video of the earth and stone blasting captured by the high-definition high-speed camera cannot accurately obtain the data information hidden under the flying dust and reflecting the blasting effect, such as the form and texture change of the earth and stone surface in the blasting area, the earth and stone composition change, the earth and stone crack and the defect change.
Disclosure of Invention
In order to quickly and accurately dynamically identify the influence and effect of earthwork blasting aiming at the defects of the prior art and the requirements of practical application, the invention provides a dynamic identification method of earthwork blasting on the first aspect, wherein the dynamic identification method of earthwork blasting comprises the following steps: setting an observation angle and an observation position according to the spatial position of the earth and stone; adjusting the shooting positions of the hyperspectral camera and the high-speed camera according to the observation angle and the observation position; respectively acquiring hyperspectral data and image data in a blasting area through the hyperspectral camera and the high-speed camera; acquiring dynamic spectrum change data in a blasting area according to the hyperspectral data; acquiring dynamic change data of the blasting blocks in the blasting area by using the image data; and dynamically identifying the earthwork blasting effect through the spectral dynamic change data and the blasting block dynamic change data. The hyperspectral image data are introduced, so that the defects of image data obtained by a high-speed camera on representing the influence and effect capability of earthwork blasting are overcome; and through introducing the hyperspectral reconstruction technology, when promoting the high spectral data's that the hyperspectral camera appearance acquireed resolution ratio, also obtained form and the texture change on the earth and stone side surface that can accurate sign blasting area, the earth and stone side composition changes, the spectrum dynamic change data of the change of earth and stone side crackle and defect, make the earth and stone side blasting effect of discernment more accurate, also satisfy the real time monitoring demand of earth and stone side blasting process, provide accurate and timely blasting effect feedback for the staff, help the staff in time according to feedback adjustment blasting scheme, the incidence of earth and stone side blasting accident has been reduced.
Optionally, the hyperspectral camera comprises a multi-stage tunable hyperspectral camera.
Optionally, the acquiring, according to the hyperspectral data, dynamic spectrum change data in the blasting area includes the following steps: respectively extracting hyperspectral data in blasting areas at different moments by taking the time sequence of earth-rock blasting as a reference; respectively carrying out high-dimensional reconstruction on the hyperspectral data at any moment to obtain high-resolution spectral data; and extracting spectral features in the high-resolution spectral data, and tracking the spectral feature change to obtain spectral dynamic change data in the blasting area. According to the invention, the spectrum reconstruction mode is utilized, the resolution of hyperspectral data is improved, and the dynamic identification capability of the earthwork blasting effect is improved.
Optionally, the performing high-dimensional reconstruction on the hyperspectral data at any time to obtain high-resolution spectral data respectively includes the following steps: setting a target hyperspectral matrix and acquiring an information transfer characteristic matrix of a hyperspectral camera; orthogonalizing the target hyperspectral matrix by using the information transfer characteristic matrix and obtaining an orthogonal basis matrix irrelevant to the information transfer characteristic matrix; combining the information transfer characteristic matrix and the hyperspectral data by using an orthogonal basis matrix to obtain a reconstruction condition; according to the reconstruction condition, a sparse coefficient matrix used for reconstructing a target hyperspectral matrix is reversely tracked; and reconstructing a target hyperspectral matrix by combining the sparse coefficient matrix with the information transfer characteristic matrix and obtaining corresponding high-resolution spectral data.
Optionally, the reconstruction condition satisfies the following relation:
wherein ,
representing a high spectral matrix of objects, -based on the spectral value of the object>
A spectrum matrix corresponding to the hyperspectral data is represented,
indicates the length of the matrix, is greater than or equal to>
Represents the width of the matrix, < > is>
and />
Are each representative of a matrix depth, ->
，/>
Represents a matrix of information transfer characteristics, and->
An orthogonal base matrix, representing a target hyperspectral matrix, based on the evaluation of the location of the target hyperspectral image>
Represents an initial sparse coefficient matrix, < > is selected>
Represents a sparse coefficient matrix, < > is selected>
Representing the minimum first order norm of the initial sparse coefficient matrix.
Optionally, the obtaining of the dynamic change data of the blasting block in the blasting area by using the image data includes the following steps: respectively extracting image data in blasting areas at different moments by taking the time sequence of the earthwork blasting as a reference; identifying particle characteristics in image data at any moment, and screening out particle characteristics of blasting blocks representing earthwork; and combining the screening results corresponding to different image data to obtain dynamic change data of the blasting blocks in the blasting area.
Optionally, the dynamically identifying the earthwork blasting effect through the spectral dynamic change data and the blasting block dynamic change data includes the following steps: identifying the change of material components in the blasting area, the change of the shape and texture of the earth and stone surface, and the change of earth and stone cracks and defects through the spectral dynamic change data; identifying the degree of the earth and stone square fragmentation by combining the spectral dynamic change data with the dynamic change data of the blasting block; and summarizing the change of the material composition in the blasting area, the change of the shape and the texture of the earth and stone surface, the change of the cracks and the defects of the earth and stone and the fragmentation degree of the earth and stone, and dynamically identifying the blasting effect of the earth and stone.
Optionally, the identifying the degree of cubic fragmentation of the earth and stone by using the spectral dynamic variation data in combination with the dynamic variation data of the blasting block includes the following steps: acquiring earth and stone spectral feature data; spectral characteristic data of other substances in the spectral dynamic change data are removed by utilizing the earthwork spectral characteristic data, and single earthwork spectral dynamic change data are obtained; removing the particle characteristics of non-earthwork in the dynamic change data of the blasting block by using the single earthwork spectrum dynamic change data; updating the corresponding dynamic change data of the blasting blocks in real time according to the elimination result; acquiring the particle diameter parameters of the blasting blocks at different moments and the quantity parameters of the earthwork particles with different particle diameters by using the updated dynamic change data of the blasting blocks; and identifying the degree of the earth and stone square fragmentation through the particle diameter parameter and the earth and stone square particle number parameter.
Optionally, the identifying the degree of earth and stone square fragmentation by the particle diameter parameter and the earth and stone square particle number parameter comprises the following steps: extracting the minimum value of the particle diameter parameter through the particle diameter parameter
And the maximum value of the particle diameter parameter->
(ii) a Expressing the minimum value of the particle diameter parameter->
And said particle diameter parameter maximum value>
To obtain the order of magnitude of the corresponding particle diameter parameter; with said order of magnitude, a particle diameter class range is divided>
(ii) a In combination with a range of different particle diameter classes>
And (3) building an earth and stone square fragmentation degree characterization model according to the quantity parameters of the interior earth and stone square particles, wherein the earth and stone square fragmentation degree characterization model meets the following formula:
wherein ,
represents the degree of fragmentation of the earth and stone>
Number of grade which signifies the diameter of the granule>
Is the maximum value of the particle diameter parameter
Magnitude of value obtained by scientific counting method>
Represents the minimum value of the particle diameter parameter->
Magnitude of value obtained by scientific counting method>
Represents a particle diameter class range->
The total number of the earth and stone particles in the soil and stone are combined>
Representing a particle diameter class range>
Fragmentation corresponding to the total number of interior earth and stone particlesAnd (4) degree correction coefficient. The spectral dynamic change data is combined with the dynamic change data of the blasting block body, so that the breaking degree of the earthwork under different moments is accurately represented.
In a second aspect, in order to efficiently perform the dynamic recognition method for earthwork blasting provided by the present invention, the present invention further provides a dynamic recognition system for earthwork blasting, where the dynamic recognition system for earthwork blasting includes a processor, an input device, an output device, and a memory, and the processor, the input device, the output device, and the memory are connected to each other, where the memory is used to store a computer program, and the computer program includes program instructions, and the processor is configured to call the program instructions to perform the dynamic recognition method for earthwork blasting according to the first aspect of the present invention. The dynamic identification system for the earthwork blasting has a compact structure and stable performance, and can efficiently execute the dynamic identification method for the earthwork blasting and improve the overall applicability and the practical application capability of the invention.
Drawings
FIG. 1 is a flow chart of a method for dynamic identification of earthwork blasting according to the present invention;
FIG. 2 is a flow chart of a method of spectral reconstruction in an embodiment of the present invention;
fig. 3 is a structural diagram of a dynamic recognition system for earthwork blasting according to the present invention.
Detailed Description
Specific embodiments of the present invention will be described in detail below, and it should be noted that the embodiments described herein are only for illustration and are not intended to limit the present invention. In the following description, numerous specific details are set forth in order to provide a thorough understanding of the present invention. However, it will be apparent to one of ordinary skill in the art that: it is not necessary to employ these specific details to practice the present invention. In other instances, well-known circuits, software, or methods have not been described in detail in order to avoid obscuring the present invention.
Throughout the specification, reference to "one embodiment," "an embodiment," "one example" or "an example" means: the particular features, structures, or characteristics described in connection with the embodiment or example are included in at least one embodiment of the invention. Thus, the appearances of the phrases "in one embodiment," "in an embodiment," "one example" or "an example" in various places throughout this specification are not necessarily all referring to the same embodiment or example. Furthermore, the particular features, structures, or characteristics may be combined in any suitable combination and/or sub-combination in one or more embodiments or examples. Further, those of ordinary skill in the art will appreciate that the illustrations provided herein are for illustrative purposes and are not necessarily drawn to scale.
Referring to fig. 1, in order to rapidly and accurately dynamically identify the influence and effect of earthwork blasting, the present invention provides a dynamic identification method of earthwork blasting, which includes the following steps:
and S01, setting an observation angle and an observation position according to the spatial position of the earth and stone.
And S01, setting an observation angle and an observation position according to the spatial position of the earthwork, so that the hyperspectral camera and the high-speed camera can capture complete and clear hyperspectral data and image data which can represent the whole process of the earthwork blasting at the observation position according to the observation angle. Further, the observation angle and the observation position point for the spatial position of the same earth and rock are set, and the observation position is not unique, but the observation angle is unique to the observation position. In an alternative embodiment, the fluctuation gradient of the earthwork to be blasted is small compared with that of the horizontal ground, so that a space position with a certain height vertical to the central position of the earthwork is selected as an observation position; in the observation position, a direction perpendicular to the center position of the earth and stone is set as an imaging direction.
And S02, adjusting the shooting positions of the hyperspectral camera and the high-speed camera according to the observation angle and the observation position.
Compared with the traditional image data, the hyperspectral data contains more information. It should be understood that the hyperspectral camera records hyperspectral data of the whole process of earth and rockfill blasting, and the hyperspectral data can be converted into hyperspectral images for visual representation and can also be used for relevant calculation analysis combined with the image data. The type of the hyperspectral camera and the corresponding performance parameters such as spectral range, spatial resolution, spectral resolution and the like in the step S02 can be selected according to actual engineering requirements. Meanwhile, the step S02 of adjusting the shooting positions of the hyperspectral camera and the high-speed camera can be realized by carrying the hyperspectral camera and the high-speed camera by the unmanned aerial vehicle and correspondingly adjusting the position of the unmanned aerial vehicle and the shooting angles of the hyperspectral camera and the high-speed camera on the unmanned aerial vehicle; the method can also be realized by arranging a fixed frame, selecting a proper slope surface and the like.
In an optional embodiment, to obtain the hyperspectral data with high resolution, the hyperspectral camera used for obtaining the hyperspectral data in step S02 is a multi-level tunable hyperspectral camera. With the increase of the number of filter stages in the tunable hyperspectral camera, the resolution ratio of the obtained initial hyperspectral data is higher, so that the hyperspectral data with higher resolution ratio can be reconstructed through a deep learning network of spectrum reconstruction or spectrum reconstruction calculation by means of the hyperspectral data; meanwhile, the high spectral data with high spatial resolution and high spectral resolution is combined with the image data, so that the recognition capability of the blasting effect can be effectively improved.
And S03, respectively obtaining hyperspectral data and image data in the blasting area through the hyperspectral camera and the high-speed camera.
It can be understood that, because the hyperspectral camera and the high-speed camera are used for dynamically identifying the blasting process of the same earth and rocky area, on the premise of ignoring incident light difference caused by the relative position of the hyperspectral camera and the high-speed camera, the invention approximately considers that data captured by the hyperspectral camera and the high-speed camera are different expressions for the same incident light: the hyperspectral imager acquires continuous multi-frame hyperspectral images/a plurality of hyperspectral data, and the hyperspectral data not only comprises two-dimensional spatial position information, but also comprises one-dimensional spectral information; the high-speed camera obtains continuous multi-frame high-definition earthwork blasting process diagrams, and any one frame of high-definition earthwork blasting process diagram can correspond to two-dimensional spatial position information represented by hyperspectral data at the same time.
In an optional embodiment, in order to make it easier to combine the subsequent hyperspectral data with the image data, the hyperspectral camera and the high-speed camera in step S03 are used to obtain the hyperspectral data and the image data in the blast area, respectively, and the method includes the following steps: setting time resolution on the basis of the time sequence of the earthwork blasting; obtaining a plurality of continuous time nodes according to the time resolution; and capturing hyperspectral data and image data in the blasting area by utilizing a hyperspectral camera and a high-speed camera respectively according to the time nodes. In the embodiment, the discrete data at the corresponding time node is obtained through the time resolution, so that the overall data volume is reasonably reduced, and the speed of subsequent data processing is improved to a certain extent.
And S04, acquiring dynamic spectrum change data in the blasting area according to the hyperspectral data.
In the step S04, the dynamic spectrum change data in the blasting area is obtained according to the hyperspectral data, and the time-continuous or time-discrete hyperspectral data are combined to obtain the spectral data that can represent the time change in the blasting area, that is, the dynamic spectrum change data in the blasting area.
In an optional embodiment, to improve the resolution of the hyperspectral data and obtain a more accurate identification capability of the blasting effect, the step S04 of obtaining the dynamic spectrum change data in the blasting area according to the hyperspectral data includes the following steps: respectively extracting hyperspectral data in blasting areas at different moments by taking the time sequence of earthwork blasting as a reference; respectively carrying out high-dimensional reconstruction on the hyperspectral data at any moment to obtain high-resolution spectral data; and extracting spectral features in the high-resolution spectral data, and tracking the spectral feature change to obtain spectral dynamic change data in the blasting area. According to the invention, the spectrum reconstruction mode is utilized, the resolution of hyperspectral data is improved, and the dynamic identification capability of the earthwork blasting effect is improved.
Further, in an embodiment, referring to fig. 2, the performing high-dimensional reconstruction on the hyperspectral data at any time to obtain high-resolution spectral data includes the following steps:
s0411, setting a target hyperspectral matrix, and acquiring an information transfer characteristic matrix of the hyperspectral camera.
It should be appreciated that the spectral resolution of the target hyperspectral matrix is set to a resolution that corresponds much greater than the original hyperspectral data. In detail, the setting of the target high spectral matrix includes the following steps: setting the length of the target hyperspectral matrix according to the visible range of the hyperspectral camera
And width->
(ii) a Setting a target spectral range based on the spectral range detectable by the hyperspectral camera>
(ii) a Setting a target spectral resolution->
And using said target spectral resolution->
In combination with the spectral range->
Defining a target spectral depth->
Said target spectral depth->
The following formula is satisfied: />
(ii) a According to the length of the target high spectrum matrixDegree->
And has a width->
And a target spectral depth->
Setting a target hyperspectral matrix->
. It should be understood that>
Also characterizes the target hyperspectral matrix->
The matrix depth of (c).
In this embodiment, the hyperspectral imager is a multistage liquid crystal tunable spectrum imager, and the acquiring of the information transfer feature matrix of the hyperspectral imager includes the following steps: respectively building a transmittance characteristic matrix model and a response characteristic matrix model according to the tuning vector and the tuning times of the multistage liquid crystal tunable spectrum camera during shooting; combining the high spectral data by using the transmittance characteristic matrix model to obtain a transmittance characteristic matrix; combining the hyperspectral data by using a response characteristic matrix model to obtain a response characteristic matrix; and combining the transmittance characteristic matrix and the response characteristic matrix to obtain the information transfer characteristic matrix. Further, the constructed transmittance characteristic matrix model and the constructed response characteristic matrix model respectively satisfy the following relational expressions:
wherein ,
characteristic matrix model representing transmittance>
Indicates the fifth->
Segment band,. Or>
，/>
，/>
Represents the target spectral depth, is>
，/>
Indicates the number of tunings, further the number of tunings->
Spectral matrix ^ corresponding to hyperspectral data>
The medium matrix depth m is equal value->
Represents the target spectral range, is selected>
Represents a target spectral resolution, <' > in>
Represents a wave band->
The characteristic vector of the transmittance of the light ray is greater or less>
Represents a wave band->
Light is at the tuning vector->
The characteristic value of the transmittance below is->
Represents an ambient light intensity +>
Represents a wave band->
Light passing through to tune vector>
Modulates the original light intensity before the multi-stage liquid crystal tunable spectrum camera and then works>
Represents a wave band->
Light passes through to tune the vector->
Modulates the light intensity behind the multi-stage liquid crystal tunable spectrum camera and then picks up the light intensity>
Represents a response characteristic matrix model>
Representing wave band of multistage liquid crystal tunable spectrum camera
Response characteristic value for light>
Representing a gray scale response function, the independent variable of which is the light intensity,
represents a wave band->
The gray response value corresponding to the original light of the light ray is->
Represents the corresponding gray-scale response value of the ambient light, and->
Represents a wave band->
And (3) gray response values of the light after passing through the unmodulated multi-level liquid crystal tunable spectrum camera.
S0412, the target hyperspectral matrix is orthogonalized by utilizing the information transfer characteristic matrix, and an orthogonal basis matrix irrelevant to the information transfer characteristic matrix is obtained.
It should be understood that the information transfer feature matrix described in step S0412 is formed by combining the transmittance feature matrix and the response feature matrix obtained in the above embodiments, that is, the information transfer feature matrix satisfies the following relation:
, wherein ,/>
Representing the information transfer characteristic matrix, and obtaining a matrix which is based on the hyperspectral data and is based on the multi-level liquid crystal tunable spectrum camera>
The following equation should be satisfied: />
, wherein ,
representing a target hyperspectral matrix. Due to->
That is, the depth of the matrix corresponding to the hyperspectral data obtained by the multistage liquid crystal tunable spectral camera is far less than that of the target hyperspectral matrix, so that the following implementation conditions need to be satisfied to reconstruct the target hyperspectral matrix: />
, wherein ,/>
And/or>
Is a norm threshold coefficient>
，/>
. Step S0412, utilizing the information transfer characteristic matrix, orthogonalizing the target hyperspectral matrix and obtaining an orthogonal basis matrix and an initial sparse coefficient matrix unrelated to the information transfer characteristic matrix, i.e. the result of orthogonalizing the target hyperspectral matrix is &>
, wherein ,/>
An orthogonal base matrix, representing a target hyperspectral matrix, based on the evaluation of the location of the target hyperspectral image>
Sparse coefficient matrix, <' > or |, representing a target hyperspectral matrix>
And/or>
Matrices that are uncorrelated with each other.
And S0413, combining the information transfer characteristic matrix and the hyperspectral data by using the orthogonal basis matrix to obtain a reconstruction condition.
Based on the implementation conditions, obtaining reconstruction conditions by combining the information transfer characteristic matrix and the hyperspectral data by using an orthogonal basis matrix, wherein the reconstruction conditions satisfy the following relational expression:
wherein ,
represents a target hyperspectral matrix, < >>
A spectrum matrix corresponding to the hyperspectral data is represented,
indicates the length of the matrix, is greater than or equal to>
Represents the width of the matrix, < > is>
and />
Are each representative of a matrix depth, ->
，/>
Represents a matrix of information transfer characteristics, and->
Represents an orthogonal base matrix, <' > is selected>
Represents an initial sparse coefficient matrix, < > is selected>
Represents a sparse coefficient matrix, < > is selected>
Representing the smallest first order norm of the initial sparse coefficient matrix.
And S0414, reversely tracking the sparse coefficient matrix for reconstructing the target hyperspectral matrix according to the reconstruction condition.
In this embodiment, the sparse coefficient matrix for reconstructing the target hyperspectral matrix is the above-mentioned sparse coefficient matrix
。
And S0415, reconstructing a target hyperspectral matrix by combining the sparse coefficient matrix with the information transfer characteristic matrix and obtaining corresponding high-resolution spectral data.
In the present embodiment, the reconstructed target hyperspectral matrix satisfies the following equation:
, wherein ,/>
Representing a reconstructed object hyperspectral matrix>
Represents an orthogonal base matrix, <' > is selected>
A sparse coefficient matrix is represented.
And S05, acquiring dynamic change data of the blasting blocks in the blasting area by using the image data.
In an optional example, the step S05 of obtaining the dynamic change data of the blasting bulk in the blasting area by using the image data includes the following steps: respectively extracting image data in blasting areas at different moments by taking the timing sequence of the earth and rock blasting as a reference; identifying particle characteristics in image data at any moment, and screening out particle characteristics representing the blasting blocks of the earthwork; and combining the screening results corresponding to different image data to obtain dynamic change data of the blasting blocks in the blasting area. Wherein different types of particle features can be distinguished by color, and the same type of particle features can be distinguished by image edge recognition technology. In other words, in step S05, images corresponding to obvious non-earthwork substances in the image data captured by the high-speed camera are preliminarily filtered, and the filtered image data at different times are connected in series through the sequence of earthwork blasting, so as to obtain dynamic change data of a blasting block generated by earthwork blasting in a blasting area.
And S06, dynamically identifying the earthwork blasting effect through the spectral dynamic change data and the blasting block dynamic change data.
In an optional embodiment, the dynamically identifying the earthwork blasting effect through the spectral dynamic change data and the blasting block dynamic change data comprises the following steps: identifying the change of material components in the blasting area, the change of the shape and texture of the earth and stone surface, and the change of earth and stone cracks and defects through the spectral dynamic change data; identifying the degree of earthwork fragmentation by combining the spectral dynamic change data with the dynamic change data of the blasting block; and summarizing the change of the material composition in the blasting area, the change of the shape and the texture of the earth and stone surface, the change of the cracks and the defects of the earth and stone and the fragmentation degree of the earth and stone, and dynamically identifying the blasting effect of the earth and stone.
It should be understood that the spectral dynamic change data in step S06 has high spatial resolution and high spectral resolution, and therefore, in such continuously dynamically changing spectral data, clear spectral information that can represent the continuous change of the whole process of the earth and rockburst can be easily captured. Therefore, the change of the material composition in the blasting area, the change of the shape and texture of the earth and stone surface, and the change of earth and stone cracks and defects can be visually captured in a visual interface after the dynamic spectrum change data are visualized. The visualization operation of the spectral dynamic change data can be realized by using a drawing library of Matplotlib in Python and combining the spectral dynamic change data, namely, a visual image of characteristic dynamic changes such as substance component change, earth and stone surface form and texture change, earth and stone crack and defect change and the like in the blasting area is obtained.
Further, the aboveIn the embodiment, the identifying the degree of cubic fragmentation of earth and stone by using the spectral dynamic change data in combination with the dynamic change data of the blasting blocks includes the following steps: acquiring earth and stone spectral characteristic data; spectral characterization data of other substances in the spectral dynamic change data are removed by using the earth and stone spectral feature data, and single earth and stone spectral dynamic change data are obtained; removing the particle characteristics of non-earthwork in the dynamic change data of the blasting block by using the single earthwork spectrum dynamic change data; updating the corresponding dynamic change data of the blasting blocks in real time according to the elimination result; acquiring the particle diameter parameters of the blasting blocks at different moments and the quantity parameters of the earthwork particles with different particle diameters by using the updated dynamic change data of the blasting blocks; and identifying the degree of the earth and stone square fragmentation through the particle diameter parameter and the earth and stone square particle number parameter. Wherein, the step of identifying the fragmentation degree of the earthwork through the particle diameter parameter and the quantity parameter of the earthwork particles comprises the following steps: extracting the minimum value of the particle diameter parameter through the particle diameter parameter
And the maximum value of the particle diameter parameter->
(ii) a Respectively expressing the minimum value of the particle diameter parameter by scientific notation
And the maximum value of the particle diameter parameter->
To obtain the order of magnitude of the corresponding particle diameter parameter; with said order of magnitude, a particle diameter class range is divided>
(ii) a In combination with a range of different particle diameter classes>
Ginseng with earth and stone particlesAnd (3) building an earth and stone square fragmentation degree characterization model, wherein the earth and stone square fragmentation degree characterization model meets the following formula:
wherein ,
representing the degree of the soil and stone disintegration, the larger the E value is, the higher the corresponding soil and stone disintegration degree is, and the more the soil and stone disintegration degree is, the more the corresponding soil and stone are>
Indicates the grade number of the diameter of the particle, and>
is the maximum value of the particle diameter parameter->
Magnitude of value obtained by scientific counting method>
Represents the minimum value of the particle diameter parameter->
Magnitude of value obtained by scientific counting method>
Represents a particle diameter class range->
The total number of the earth and stone particles in the soil and stone are combined>
Represents a particle diameter class range->
And (4) correcting the coefficient of the fracture degree corresponding to the total number of the inner earth-rock particles. The invention utilizes the spectrum dynamic change data to combine with the dynamic change data of the blasting block body, and accurately represents the soil excavation at different momentsDegree of stone chipping.
The hyperspectral image data are introduced, so that the defects of image data obtained by a high-speed camera on representing the influence and effect capability of earthwork blasting are overcome; and through introducing the hyperspectral reconstruction technique, when promoting the high spectral data's that hyperspectral camera appearance acquireed resolution ratio, also obtained can accurate sign blasting regional cubic metre form and texture change on earth and stone surface, cubic metre of earth and stone composition change, the spectrum dynamic change data of the change of cubic metre crackle and defect, make the cubic metre blasting effect of discernment more accurate, also satisfy the real time monitoring demand of cubic metre blasting process, provide accurate and timely blasting effect feedback for the staff, help the staff in time according to feedback adjustment blasting scheme, the incidence of cubic metre blasting accident has been reduced.
Referring to fig. 3, in an alternative embodiment, in order to efficiently perform the dynamic identification method of an earth and rock explosion provided by the present invention, the present invention further provides a dynamic identification system of an earth and rock explosion, where the dynamic identification system of an earth and rock explosion includes a processor, an input device, an output device, and a memory, and the processor, the input device, the output device, and the memory are connected with each other, where the memory is used to store a computer program, and the computer program includes program instructions, and the processor is configured to call the program instructions to perform the dynamic identification method of an earth and rock explosion provided by the first aspect of the present invention. The dynamic identification system for the earthwork blasting has a compact structure and stable performance, and can efficiently execute the dynamic identification method for the earthwork blasting and improve the overall applicability and the practical application capability of the invention.
Finally, it should be noted that: the above embodiments are only used to illustrate the technical solution of the present invention, and not to limit the same; while the invention has been described in detail and with reference to the foregoing embodiments, it will be understood by those skilled in the art that: the technical solutions described in the foregoing embodiments may still be modified, or some or all of the technical features may be equivalently replaced; such modifications and substitutions do not depart from the spirit and scope of the present invention, and they should be construed as being included in the following claims and description.
Claims (10)
1. A dynamic identification method for earthwork blasting is characterized by comprising the following steps:
setting an observation angle and an observation position according to the spatial position of the earth and stone;
adjusting the shooting positions of the hyperspectral camera and the high-speed camera according to the observation angle and the observation position;
respectively acquiring hyperspectral data and image data in a blasting area through the hyperspectral camera and the high-speed camera;
acquiring dynamic spectrum change data in a blasting area according to the hyperspectral data;
acquiring dynamic change data of the blasting blocks in the blasting area by using the image data;
and dynamically identifying the earthwork blasting effect through the spectral dynamic change data and the blasting block dynamic change data.
2. The dynamic identification method of an earthwork blast according to claim 1, wherein the hyperspectral camera comprises a multistage tunable hyperspectral camera.
3. The method for dynamically identifying an earthwork according to claim 1, wherein the step of obtaining the spectral dynamic change data in the blasting area according to the hyperspectral data comprises the steps of:
respectively extracting hyperspectral data in blasting areas at different moments by taking the time sequence of earth-rock blasting as a reference;
respectively carrying out high-dimensional reconstruction on the hyperspectral data at any moment to obtain high-resolution spectral data;
and extracting spectral features in the high-resolution spectral data, and tracking the spectral feature change to obtain spectral dynamic change data in the blasting area.
4. The dynamic identification method of earthwork blasting according to claim 3, wherein the high-dimensional reconstruction of the hyperspectral data at any moment to obtain high-resolution spectral data comprises the following steps:
setting a target hyperspectral matrix and acquiring an information transfer characteristic matrix of the hyperspectral camera;
orthogonalizing the target hyperspectral matrix by using the information transfer characteristic matrix and obtaining an orthogonal basis matrix irrelevant to the information transfer characteristic matrix;
combining the information transfer characteristic matrix and the hyperspectral data by using an orthogonal basis matrix to obtain a reconstruction condition;
according to the reconstruction condition, a sparse coefficient matrix used for reconstructing a target hyperspectral matrix is reversely tracked;
and reconstructing a target hyperspectral matrix by combining the sparse coefficient matrix with the information transfer characteristic matrix and obtaining corresponding high-resolution spectral data.
5. The dynamic identification method of an earthwork blast according to claim 4, wherein the reconstruction condition satisfies the following relational expression:
wherein ,
represents a target hyperspectral matrix, < >>
Represents the spectral matrix corresponding to the hyperspectral data, and->
Indicates the length of the matrix, is greater than or equal to>
Represents the width of the matrix, < > is>
and />
Are each representative of a matrix depth, ->
，/>
Represents a matrix of information transfer characteristics, and->
An orthogonal base matrix, representing a target hyperspectral matrix, based on the evaluation of the location of the target hyperspectral image>
Represents an initial sparse coefficient matrix, < > is selected>
Represents a sparse coefficient matrix, < > is selected>
Representing the smallest first order norm of the initial sparse coefficient matrix.
6. The method for dynamically identifying an earthwork according to claim 3, wherein the step of obtaining the data of the dynamic change of the blasting bulk in the blasting area by using the image data comprises the steps of:
respectively extracting image data in blasting areas at different moments by taking the timing sequence of the earth and rock blasting as a reference;
identifying particle characteristics in image data at any moment, and screening out particle characteristics of blasting blocks representing earthwork;
and combining the screening results corresponding to different image data to obtain dynamic change data of the blasting blocks in the blasting area.
7. The method for dynamically identifying earthwork according to claim 6, wherein the dynamically identifying earthwork effect through the spectral dynamic change data and the blasting block dynamic change data comprises the following steps:
identifying the change of material components in the blasting area, the change of the shape and texture of the earth and stone surface, and the change of earth and stone cracks and defects through the spectral dynamic change data;
identifying the degree of the earth and stone square fragmentation by combining the spectral dynamic change data with the dynamic change data of the blasting block;
and summarizing the change of the material composition in the blasting area, the change of the shape and the texture of the earth and stone surface, the change of the cracks and the defects of the earth and stone and the fragmentation degree of the earth and stone, and dynamically identifying the blasting effect of the earth and stone.
8. The method of claim 7, wherein said identifying the fragmentation degree of earthwork by using said spectral dynamic variation data in combination with said blasting block dynamic variation data comprises the steps of:
acquiring earth and stone spectral characteristic data;
spectral characterization data of other substances in the spectral dynamic change data are removed by using the earth and stone spectral feature data, and single earth and stone spectral dynamic change data are obtained;
removing the particle characteristics of non-earthwork in the dynamic change data of the blasting block by using the single earthwork spectrum dynamic change data;
updating the corresponding dynamic change data of the blasting blocks in real time according to the elimination result;
acquiring the particle diameter parameters of the blasting blocks at different moments and the quantity parameters of the earthwork particles with different particle diameters by using the updated dynamic change data of the blasting blocks;
and identifying the degree of the earth and stone square fragmentation through the particle diameter parameter and the earth and stone square particle number parameter.
9. The method of claim 8, wherein said identifying the degree of cubic fragmentation of said earth and rocky earth through said particle diameter parameter and said number of cubic particles parameter comprises the steps of:
extracting a particle diameter parameter minimum value from the particle diameter parameter
And the maximum value of the particle diameter parameter->
；
Respectively expressing the minimum value of the particle diameter parameter by scientific notation
With maximum value of said particle diameter parameter
To obtain the order of magnitude of the corresponding particle diameter parameter;
using said order of magnitude, dividing the range of particle diameter classes
；
Combining different particle diameter grade ranges
And (3) building an earth and stone square fragmentation degree characterization model according to the quantity parameters of the interior earth and stone square particles, wherein the earth and stone square fragmentation degree characterization model meets the following formula:
wherein ,
represents the degree of fragmentation of soil and stone>
Indicates the grade number of the diameter of the particle, and>
is the maximum value of the particle diameter parameter
Magnitude of value obtained by scientific counting method>
Represents the minimum value of the particle diameter parameter->
Magnitude of value obtained by scientific counting method>
Representing a particle diameter class range>
The total number of the soil and stone grains inside the soil and stone chamber>
Represents a particle diameter class range->
And (4) correcting the coefficient of the fracture degree corresponding to the total number of the inner earth-rock particles.
10. A dynamic identification system of earth and stone blasting, characterized in that the system comprises a processor, an input device, an output device and a memory, the processor, the input device, the output device and the memory being interconnected, wherein the memory is configured to store a computer program, the computer program comprising program instructions, the processor being configured to invoke the program instructions to perform the method of dynamic identification of earth and stone blasting according to any of claims 1-9.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310220702.XA CN115953691B (en) | 2023-03-09 | 2023-03-09 | Dynamic identification method and system for earth and stone blasting |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310220702.XA CN115953691B (en) | 2023-03-09 | 2023-03-09 | Dynamic identification method and system for earth and stone blasting |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN115953691A true CN115953691A (en) | 2023-04-11 |
| CN115953691B CN115953691B (en) | 2023-05-16 |
Family
ID=85896222
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310220702.XA Active CN115953691B (en) | 2023-03-09 | 2023-03-09 | Dynamic identification method and system for earth and stone blasting |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115953691B (en) |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| PL429095A1 (en) * | 2019-02-28 | 2020-09-07 | Wyroby Granitowe Wołczyk Spółka Jawna | Method of creating a map of cracks and scratches in stone slabs or stones |
| EP3835833A1 (en) * | 2019-12-10 | 2021-06-16 | Wise Robotics Societa' a Responsabilita' Limitata Semplificata | Improved monitoring and early warning system |
| CN113446998A (en) * | 2021-06-29 | 2021-09-28 | 哈尔滨工业大学 | Hyperspectral target detection data-based dynamic unmixing method |
| CN113537142A (en) * | 2021-08-03 | 2021-10-22 | 广东电网有限责任公司 | Monitoring method, device and system for construction progress of capital construction project and storage medium |
| CN115456960A (en) * | 2022-08-23 | 2022-12-09 | 广东工业大学 | Citrus huanglongbing disease and pest monitoring and early warning system and method |
-
2023
- 2023-03-09 CN CN202310220702.XA patent/CN115953691B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| PL429095A1 (en) * | 2019-02-28 | 2020-09-07 | Wyroby Granitowe Wołczyk Spółka Jawna | Method of creating a map of cracks and scratches in stone slabs or stones |
| EP3835833A1 (en) * | 2019-12-10 | 2021-06-16 | Wise Robotics Societa' a Responsabilita' Limitata Semplificata | Improved monitoring and early warning system |
| CN113446998A (en) * | 2021-06-29 | 2021-09-28 | 哈尔滨工业大学 | Hyperspectral target detection data-based dynamic unmixing method |
| CN113537142A (en) * | 2021-08-03 | 2021-10-22 | 广东电网有限责任公司 | Monitoring method, device and system for construction progress of capital construction project and storage medium |
| CN115456960A (en) * | 2022-08-23 | 2022-12-09 | 广东工业大学 | Citrus huanglongbing disease and pest monitoring and early warning system and method |
Non-Patent Citations (2)
| Title |
|---|
| S.A. ARGYROUDIS等: "Data-driven resilience assessment for transport infrastructure exposed to multiple hazards", 《10TH INTERNATIONAL CONFERENCE ON BRIDGE MAINTENANCE, SAFETY AND MANAGEMENT》 * |
| 陈然: "基于双门限阈值的爆堆岩块图像分割技术及图像识别系统开发", 《中国优秀硕士学位论文全文数据库 (工程科技Ⅰ辑)》 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN115953691B (en) | 2023-05-16 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Liu et al. | The effect of LiDAR data density on DEM accuracy | |
| Bagde et al. | Rock mass characterization by fractal dimension | |
| Tavus et al. | Considerations on the use of Sentinel-1 data in flood mapping in urban areas: Ankara (Turkey) 2018 floods | |
| Liu et al. | High-resolution remote sensing image-based extensive deformation-induced landslide displacement field monitoring method | |
| Engin et al. | Practical measurement of size distribution of blasted rocks using LiDAR scan data | |
| CN110889834A (en) | Road tunnel surrounding rock grading method based on cloud computing | |
| CN115953691A (en) | Method and system for dynamically identifying earthwork blasting | |
| Medinac et al. | Pre-and post-blast rock block size analysis using uav-lidar based data and discrete fracture network | |
| CN105096334B (en) | A kind of mining area monitoring method and system | |
| CN111144005A (en) | Method for constructing particle size calculation model of collapsed falling stones | |
| Bagheri Shendi et al. | A case study for utilization of image processing in jointed network detection in open-pit mining | |
| Chirico et al. | Mapping informal small-scale mining features in a data-sparse tropical environment with a small UAS | |
| CN113177949B (en) | Large-size rock particle feature recognition method and device | |
| Karakas et al. | On the effect of DEM quality for landslide susceptibility mapping | |
| Brzovic et al. | Integrated photogrammetry and discrete fracture network modelling to determine rock structure around excavations at the El Teniente Mine | |
| Lv et al. | A Framework for Fracture Extraction Under Glaciological Property‐Based Constraints: Scientific Application on the Filchner–Ronne Ice Shelf of Antarctica | |
| CN113592032B (en) | Infrared imaging false alarm source classification method based on physical model constraint | |
| Barone et al. | A remote sensing approach to understanding the archaeological potential: the case study of some Roman evidence in Umbria (Italy) | |
| Jeddi et al. | Application of Image Processing Techniques for Geometrical Simulation in Rock Slopes | |
| Yang et al. | Enhanced detection of freeze‒thaw induced landslides in Zhidoi county (Tibetan Plateau, China) with Google Earth Engine and image fusion | |
| Yaacob et al. | Investigation of Rock Slope Stability Using Drone-Based Thermal Sensor | |
| CN111724380B (en) | Rock-soil structure quality evaluation method based on ELO algorithm | |
| CN115131295A (en) | Construction method, system and device of engineering rock mass fracture network | |
| Tarnavsky et al. | Modeling of radar land clutter map for small grazing angles | |
| Pavelka Jr et al. | USING SATELLITE IMAGES FOR DOCUMENTATION OF DAMAGES IN ALEPPO HISTORICAL CENTRE DURING CIVIL WAR |
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 |