CN117557434B - Dangerous rock collapse assessment method and system based on artificial intelligence - Google Patents
Dangerous rock collapse assessment method and system based on artificial intelligence Download PDFInfo
- Publication number
- CN117557434B CN117557434B CN202410046420.7A CN202410046420A CN117557434B CN 117557434 B CN117557434 B CN 117557434B CN 202410046420 A CN202410046420 A CN 202410046420A CN 117557434 B CN117557434 B CN 117557434B
- Authority
- CN
- China
- Prior art keywords
- target
- rock
- processed
- state information
- collapse
- 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
- 239000011435 rock Substances 0.000 title claims abstract description 540
- 238000000034 method Methods 0.000 title claims abstract description 44
- 238000013473 artificial intelligence Methods 0.000 title claims abstract description 19
- 238000011156 evaluation Methods 0.000 claims abstract description 53
- 238000012545 processing Methods 0.000 claims description 115
- 238000000611 regression analysis Methods 0.000 claims description 109
- 238000000605 extraction Methods 0.000 claims description 34
- 238000004140 cleaning Methods 0.000 claims description 19
- 230000008569 process Effects 0.000 claims description 14
- 230000006870 function Effects 0.000 claims description 13
- 230000008859 change Effects 0.000 claims description 10
- 238000004590 computer program Methods 0.000 claims description 5
- 238000001914 filtration Methods 0.000 claims description 5
- 238000004891 communication Methods 0.000 claims description 3
- 238000007499 fusion processing Methods 0.000 claims description 3
- 238000013507 mapping Methods 0.000 claims description 3
- 238000004880 explosion Methods 0.000 claims description 2
- 239000002360 explosive Substances 0.000 claims description 2
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 claims description 2
- 238000004422 calculation algorithm Methods 0.000 description 7
- 238000004364 calculation method Methods 0.000 description 4
- 238000011157 data evaluation Methods 0.000 description 3
- 238000004458 analytical method Methods 0.000 description 2
- 238000003491 array Methods 0.000 description 2
- 230000006835 compression Effects 0.000 description 2
- 238000007906 compression Methods 0.000 description 2
- 238000012854 evaluation process Methods 0.000 description 2
- 230000005484 gravity Effects 0.000 description 2
- 238000011835 investigation Methods 0.000 description 2
- 239000000203 mixture Substances 0.000 description 2
- 239000000178 monomer Substances 0.000 description 2
- 238000011176 pooling Methods 0.000 description 2
- 230000002265 prevention Effects 0.000 description 2
- 238000011160 research Methods 0.000 description 2
- 230000009471 action Effects 0.000 description 1
- 238000013459 approach Methods 0.000 description 1
- 238000007405 data analysis Methods 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000002474 experimental method Methods 0.000 description 1
- 239000010438 granite Substances 0.000 description 1
- 239000011159 matrix material Substances 0.000 description 1
- 238000003058 natural language processing Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000007781 pre-processing Methods 0.000 description 1
- 239000004065 semiconductor Substances 0.000 description 1
- 239000002689 soil Substances 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 230000036561 sun exposure Effects 0.000 description 1
- 230000002194 synthesizing effect Effects 0.000 description 1
- 238000012876 topography Methods 0.000 description 1
- 230000009466 transformation Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Systems or methods specially adapted for specific business sectors, e.g. utilities or tourism
- G06Q50/10—Services
- G06Q50/26—Government or public services
- G06Q50/265—Personal security, identity or safety
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/213—Feature extraction, e.g. by transforming the feature space; Summarisation; Mappings, e.g. subspace methods
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/243—Classification techniques relating to the number of classes
- G06F18/2431—Multiple classes
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/25—Fusion techniques
- G06F18/253—Fusion techniques of extracted features
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/27—Regression, e.g. linear or logistic regression
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Evolutionary Computation (AREA)
- Bioinformatics & Computational Biology (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Artificial Intelligence (AREA)
- Life Sciences & Earth Sciences (AREA)
- Evolutionary Biology (AREA)
- Business, Economics & Management (AREA)
- General Engineering & Computer Science (AREA)
- Tourism & Hospitality (AREA)
- Health & Medical Sciences (AREA)
- General Business, Economics & Management (AREA)
- Strategic Management (AREA)
- Primary Health Care (AREA)
- Marketing (AREA)
- Human Resources & Organizations (AREA)
- General Health & Medical Sciences (AREA)
- Economics (AREA)
- Educational Administration (AREA)
- Development Economics (AREA)
- Computer Security & Cryptography (AREA)
- Testing Or Calibration Of Command Recording Devices (AREA)
Abstract
According to the dangerous rock collapse assessment method and system based on artificial intelligence, the target rock state information of the target to be processed and the main characteristic information of the target to be processed are spliced to synthesize the potential characteristic information of the target to be processed and the main characteristic information of the target to be processed, more characteristic information of the target to be processed is extracted, and therefore stability of rock can be accurately determined, and accuracy and reliability of rock collapse assessment can be improved; in addition, through the target rock state information of the target to be processed, the target to be processed is evaluated to obtain a dangerous rock collapse evaluation result so as to ensure the accuracy of evaluation, thereby accurately performing advanced protection and reducing the loss caused by rock collapse as much as possible.
Description
Technical Field
The application relates to the technical field of collapse evaluation, in particular to a dangerous rock collapse evaluation method and system based on artificial intelligence.
Background
Collapse (sloughing, collapsing or collapse) is a geological phenomenon in which a rock-soil body on a steeper slope suddenly falls off the matrix under the action of gravity, rolls, and piles up on the toe (or valley) of the slope. In the situation that surge impacts the rock after the river channel in the three gorges reservoir region possibly causes rock loosening or is easy to collapse due to the influence of the situation such as rock loosening caused by earthquake, therefore, the stability evaluation of the rock is very important for the three gorges reservoir region, but in the actual operation process, the topography of the three gorges reservoir region is complex and dangerous rock collapse evaluation is difficult to perform, and therefore, a technical scheme is needed to improve the technical problems.
Disclosure of Invention
In order to improve the technical problems in the related art, the application provides a dangerous rock collapse assessment method and system based on artificial intelligence.
In a first aspect, there is provided an artificial intelligence based dangerous rock collapse assessment method, comprising: carrying out feature extraction processing on rock collapse grade feature of rock stability data to be processed through a rock collapse grade risk grade regression analysis thread to obtain feature information of a target to be processed corresponding to the rock collapse grade, so as to determine potential feature information of the target to be processed; carrying out regression analysis processing by combining the potential characteristic information of the target to be processed to obtain target rock state information of the target to be processed; performing main characteristic extraction processing on the rock stability data to be processed to obtain main characteristic information of the target to be processed; performing splicing processing on target rock state information of a target to be processed in the rock stability data to be processed and main characteristic information of the target to be processed to obtain a splicing result of the target to be processed; and carrying out evaluation treatment by combining the splicing result of the target to be treated to obtain a dangerous rock collapse evaluation result.
In the application, the regression analysis thread for regression analysis of rock stability data comprises a plurality of dangerous grade regression analysis threads, and the plurality of dangerous grade regression analysis threads respectively correspond to different rock collapse grades; performing regression analysis processing by combining the potential characteristic information of the target to be processed to obtain target rock state information of the target to be processed, wherein the regression analysis processing comprises the following steps: performing potential regression analysis processing by combining characteristic information of the to-be-processed target corresponding to the rock collapse grade through a dangerous grade regression analysis thread of the rock collapse grade, so as to obtain target rock state information of the to-be-processed target corresponding to the rock collapse grade; and splicing the target rock state information of the target to be processed corresponding to a plurality of rock collapse grades to obtain the target rock state information of the target to be processed.
In this application, the performing a potential regression analysis process in combination with the feature information of the target to be processed corresponding to the rock collapse level to obtain target rock status information of the target to be processed corresponding to the rock collapse level includes: performing characteristic cleaning treatment on the characteristic information of the to-be-treated object corresponding to the rock collapse grade to obtain cleaned characteristic information; and performing function processing on the characteristic information after cleaning to obtain target rock state information of the target to be processed corresponding to the rock collapse grade.
In this application, the splicing the target rock state information of the target to be processed corresponding to a plurality of rock collapse levels to obtain the target rock state information of the target to be processed includes: when target rock state information corresponding to two different rock collapse grades exists, distinguishing the target rock state information of the two different rock collapse grades from each other, and determining the target rock state information of the target to be processed; and when target rock state information corresponding to not less than three different rock collapse grades exists, splicing the target rock state information of not less than three different rock collapse grades so as to obtain the target rock state information of the target to be processed.
In the application, each dangerous level regression analysis thread comprises a plurality of local regression analysis threads, and the local regression analysis threads correspond to different elements of the target to be processed; and performing feature extraction processing on the rock collapse grade on the rock stability data to be processed through the dangerous grade regression analysis thread of the rock collapse grade to obtain feature information of the target to be processed corresponding to the rock collapse grade, wherein the feature information comprises the following steps: for each element of the object to be processed, the following processing is performed: performing feature extraction processing on the rock stability data to be processed through a local regression analysis thread corresponding to the element to obtain feature information of the target to be processed corresponding to the element; and performing potential regression analysis processing by combining the dangerous grade regression analysis thread of the rock collapse grade and the characteristic information of the target to be processed corresponding to the rock collapse grade to obtain target rock state information of the target to be processed in the rock collapse grade, wherein the potential regression analysis processing comprises the following steps: for each element of the object to be processed, the following processing is performed: the target rock state information of the target to be processed corresponding to the element is obtained through a local regression analysis thread corresponding to the element and combining the characteristic information of the target to be processed corresponding to the element to perform potential regression analysis processing; and splicing the target rock state information of the target to be processed corresponding to a plurality of elements to obtain the target rock state information of the target to be processed corresponding to the rock collapse level.
In this application, the performing latent regression analysis processing in combination with the feature information of the element corresponding to the target to be processed to obtain target rock status information of the element corresponding to the target to be processed includes: performing characteristic cleaning treatment on the characteristic information of the target to be treated corresponding to the element to obtain cleaned characteristic information; and performing function processing on the characteristic information after cleaning to obtain target rock state information of the target to be processed corresponding to the element.
In this application, the performing a function process on the feature information after cleaning to obtain target rock status information of the target to be processed corresponding to the element includes: projecting the cleaned characteristic information into the target rock state information to obtain collapse possibility distribution; and determining the target rock state information corresponding to the maximum possibility in the collapse possibility distribution as the target rock state information corresponding to the element of the target to be processed.
In this application, before the potential feature extraction processing is performed on the rock stability data to be processed, the method further includes: dividing the rock stability data to be processed to obtain a plurality of rock stability range data of the rock stability data to be processed; the step of extracting the potential characteristics of the rock stability data to be processed to obtain the potential characteristic information of the target to be processed in the rock stability data to be processed comprises the following steps: performing potential feature extraction processing on each rock stability range data to obtain potential feature information of the target to be processed in the rock stability range data; performing regression analysis processing by combining the potential characteristic information of the target to be processed to obtain target rock state information of the target to be processed, wherein the regression analysis processing comprises the following steps: carrying out regression analysis processing by combining potential characteristic information of the target to be processed in each rock stability range data through a regression analysis thread to obtain target rock state information of the target to be processed corresponding to each rock stability range data; and integrating the target rock state information of the target to be processed corresponding to the plurality of ranges to obtain the target rock state information of the target to be processed.
In this application, the integrating the target rock state information of the target to be processed corresponding to a plurality of ranges to obtain the target rock state information of the target to be processed includes: carrying out fusion processing on the target rock state information of the target to be processed corresponding to a plurality of ranges to obtain fused target rock state information; and performing de-duplication treatment on the fused target rock state information to obtain the target rock state information of the target to be treated.
In this application, the integrating the target rock state information of the target to be processed corresponding to a plurality of ranges to obtain the target rock state information of the target to be processed includes: according to the change condition of the target to be processed, which is represented by the target rock state information, determining target rock state information with the largest change condition from target rock state information of the target to be processed, which corresponds to a plurality of rock stability range data, and determining the target rock state information with the largest change condition as the target rock state information of the target to be processed.
In this application, the performing evaluation processing in combination with the splicing result of the target to be processed to obtain a dangerous rock collapse evaluation result includes: mapping the splicing result of the target to be processed to collapse probability distribution of dangerous rock collapse evaluation results; and determining the rock collapse grade corresponding to the maximum possibility in the collapse possibility distribution as a dangerous rock collapse evaluation result.
In this application, before the potential feature extraction processing is performed on the rock stability data to be processed, the method further includes: responding to an evaluation instruction for rock stability data to be processed, and obtaining initial rock stability data; performing at least one of the following processes with respect to the initial rock stability data: carrying out dimensionless simplification processing on each data sub-bucket in the initial rock stability data, and determining the initial rock stability data subjected to dimensionless simplification as the rock stability data to be processed; filtering the interference information in the initial rock stability data, and determining the filtered initial rock stability data as the rock stability data to be processed; and analyzing and processing the target to be processed in the initial rock stability data, and determining the analyzed initial rock stability data as the rock stability data to be processed.
In a second aspect, an artificial intelligence based dangerous rock collapse assessment system is provided comprising a processor and a memory in communication with each other, the processor being adapted to read a computer program from the memory and execute the computer program to implement the method as described above.
According to the dangerous rock collapse evaluation method and system based on artificial intelligence, the target rock state information of the target to be processed and the main characteristic information of the target to be processed are spliced to synthesize the potential characteristic information of the target to be processed and the main characteristic information of the target to be processed, so that more characteristic information of the target to be processed is extracted, the stability of rock can be accurately determined, and the accuracy and reliability of rock collapse evaluation can be improved; in addition, through the target rock state information of the target to be processed, the target to be processed is evaluated to obtain a dangerous rock collapse evaluation result so as to ensure the accuracy of evaluation, thereby accurately performing advanced protection and reducing the loss caused by rock collapse as much as possible.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings that are needed in the embodiments will be briefly described below, it being understood that the following drawings only illustrate some embodiments of the present application and therefore should not be considered limiting the scope, and that other related drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.
Fig. 1 is a flowchart of a dangerous rock collapse assessment method based on artificial intelligence according to an embodiment of the present application.
Description of the embodiments
In order to better understand the technical solutions described above, the following detailed description of the technical solutions of the present application is provided through the accompanying drawings and specific embodiments, and it should be understood that the specific features of the embodiments and embodiments of the present application are detailed descriptions of the technical solutions of the present application, and not limit the technical solutions of the present application, and the technical features of the embodiments and embodiments of the present application may be combined with each other without conflict.
Referring to fig. 1, an artificial intelligence based dangerous rock collapse assessment method is shown, which may include the following steps 101-105.
In step 101, feature extraction processing of the rock collapse grade is performed on the rock stability data to be processed through a dangerous grade regression analysis thread of the rock collapse grade, so that feature information of a target to be processed corresponding to the rock collapse grade is obtained, and potential feature information of the target to be processed is determined.
Wherein the rock collapse level may be classified according to 1-10 levels, with the risk level being higher as the value is larger.
By way of example, rock stability data may be understood as the stability of rock embedded in the ground (whether or not it can be fixed), the stability of the rock internal structure (whether or not the rock will crack or break), etc., such as: and (3) applying an extreme-jet barefoot projection graph according to the relation between the fissures and the occurrence of the free surfaces in the mountain gorge project, and carrying out macroscopic analysis on the stability of the dangerous rock monomer and the secondary dangerous rock body in the investigation region by combining deformation damage characteristics.
For example, the risk level regression analysis thread is one of artificial intelligence threads, and can analyze the possibility of rock collapse; wherein, artificial intelligence (Artificial Intelligence) is a new technical Science based on Computer Science (Computer Science), which is a cross-discipline, emerging discipline, in which multiple disciplines such as Computer, psychology, philosophy are cross-fused, to research, develop theories, methods, techniques and application systems for simulating, extending and expanding human intelligence, in an effort to understand the nature of the intelligence, and to produce a new intelligent machine that can react in a similar manner to human intelligence, and research in this field includes robotics, language recognition, image recognition, natural language processing, expert systems, and the like.
Further, the collapse instability of the dangerous rock main body and the secondary monomer in the investigation mainly comprises 3 conventional collapse modes of dumping type, falling type and sliding type, namely a compression shearing-sliding type, a collapse bending-dumping type and an unconventional collapse mode. Since the three gorges reservoir geological disaster prevention engineering geological survey technical requirement (2012 edition) and the geological disaster prevention engineering survey norm (DB 50/T143-2018) only have 3 conventional calculation modes of falling, dumping and sliding, for the convenience of quantitative calculation, the compression shearing-sliding mode refers to sliding dangerous rock with steep-slope cracks at the rear edge for calculation, and the collapse-dumping mode refers to dumping dangerous rock (rear stretch-break dumping) with the center of gravity of the dangerous rock body at the inner side of the front edge of the top surface of the base (the karst cave is regarded as a concave cavity).
The potential characteristic information may include information that rock loosens after the earthquake, explosive explosion, water impact and other operations are performed, and the rock is not unstable due to the potential characteristic information.
The method comprises the steps that an example of obtaining rock stability data to be processed is determined, rock stability data can be obtained after rock is analyzed through ultrasonic equipment, the collected rock stability data to be processed is sent to a terminal, the terminal forwards the rock stability data to be processed to a server, so that the server can conduct potential feature extraction on the rock stability data to be processed, potential feature information of a target to be processed in the rock stability data to be processed is obtained, and subsequent analysis processing can be conducted according to the potential feature information of the target to be processed.
In some possible embodiments, before the potential feature extraction processing is performed on the rock stability data to be processed, the method further includes: responding to an evaluation instruction for rock stability data to be processed, and obtaining initial rock stability data; at least one of the following processes is performed for the initial rock stability data: carrying out dimensionless simplification processing on each data sub-bucket in the initial rock stability data, and determining the initial rock stability data subjected to dimensionless simplification as rock stability data to be processed; filtering the interference information in the initial rock stability data, and determining the filtered initial rock stability data as rock stability data to be processed; and analyzing and processing the target to be processed in the initial rock stability data, and determining the analyzed initial rock stability data as the rock stability data to be processed. The non-dimensional simplification process is understood to mean that, by substitution of a suitable variable, some or all of the units of an equation relating to a physical quantity are removed for the purpose of simplifying experiments or calculations.
For example, initial rock stability data is collected, the terminal forwards the initial rock stability data to the server, the server receives the initial rock stability data and then preprocesses the initial rock stability data, the preprocessed rock stability data is more suitable for subsequent rock stability data analysis, wherein preprocessing can be understood as debugging the initial rock stability data through potential characteristics, such as dimensionless simplification processing is carried out on each data sub-bin in the initial rock stability data, the dimensionless simplified initial rock stability data is determined as rock stability data to be processed, and certain characteristics of the rock stability data have unchanged properties under given transformation; filtering the interference information in the initial rock stability data, determining the filtered initial rock stability data as rock stability data to be processed, and filtering to remove random interference information in the rock stability data; and analyzing the target to be processed in the initial rock stability data, determining the analyzed initial rock stability data as the rock stability data to be processed, and analyzing the information in the rock stability data can be performed in a targeted manner so as to solve the problem of inaccuracy of the rock stability data.
In step 102, regression analysis is performed in combination with the potential feature information of the target to be processed, so as to obtain target rock status information of the target to be processed.
For example, after the server obtains the potential feature information of the target to be processed, regression analysis processing can be performed based on the potential feature information of the target to be processed to obtain target rock state information of the target to be processed, so that subsequent rock stability data evaluation operations can be performed according to the target rock state information of the target to be processed.
The dangerous rock collapse assessment method based on artificial intelligence provided by the embodiment of the invention comprises the following steps of: in step 1011A, the following processing is performed for any one of a number of rock collapse levels: carrying out feature extraction processing of rock collapse grades on rock stability data to be processed through a dangerous grade regression analysis thread of the rock collapse grades to obtain feature information of the rock collapse grades corresponding to the targets to be processed so as to determine potential feature information of the targets to be processed;
further to, step 102 includes steps 1021A-1022A: in step 1021A, performing potential regression analysis processing by combining the characteristic information of the rock collapse level corresponding to the target to be processed through a dangerous level regression analysis thread of the rock collapse level to obtain target rock state information of the rock collapse level corresponding to the target to be processed; in step 1022A, the target rock status information of the target to be processed corresponding to the plurality of rock collapse levels is spliced, so as to obtain the target rock status information of the target to be processed.
It can be understood that the regression analysis thread for regression analysis of rock stability data comprises a plurality of dangerous grade regression analysis threads, and the plurality of dangerous grade regression analysis threads respectively correspond to different rock collapse grades; when the regression analysis processing is carried out by combining the potential characteristic information of the target to be processed, the problem of inaccurate regression analysis is solved, so that the accuracy of the target rock state information of the target to be processed can be ensured.
The regression analysis threads for regression analysis of the rock stability data comprise a plurality of dangerous grade regression analysis threads, and the plurality of dangerous grade regression analysis threads respectively correspond to different rock collapse grades. For any one of a plurality of rock collapse grades, extracting characteristic information of the rock collapse grade in the to-be-processed rock stability data through a decision unit in a dangerous grade regression analysis thread corresponding to the rock collapse grade, combining the characteristic information of the to-be-processed target corresponding to the rock collapse grade, performing potential regression analysis on the to-be-processed target through the dangerous grade regression analysis thread corresponding to the rock collapse grade to obtain target rock state information of the to-be-processed target corresponding to the rock collapse grade, namely obtaining targeted target rock state information, splicing the targeted target rock state information to obtain target rock state information of all the rock collapse grades, and performing accurate target evaluation according to the target rock state information of all the rock collapse grades.
In some possible embodiments, the potential regression analysis processing is performed in combination with the characteristic information of the rock collapse level corresponding to the target to be processed, to obtain the target rock status information of the rock collapse level corresponding to the target to be processed, including: performing characteristic cleaning treatment on characteristic information of the target to be treated corresponding to the rock collapse grade to obtain cleaned characteristic information; and performing function processing on the characteristic information after cleaning to obtain target rock state information of the target to be processed corresponding to the rock collapse grade. Wherein the function processing may include a hierarchical computing approach.
It can be understood that when the potential regression analysis processing is performed in combination with the characteristic information of the rock collapse level corresponding to the target to be processed, the problem of interference is solved, so that the target rock state information of the rock collapse level corresponding to the target to be processed can be accurately obtained.
Further, feature cleaning is carried out on feature information of the rock collapse grade corresponding to the target to be processed through a pooling layer in the dangerous grade regression analysis thread corresponding to the rock collapse grade, feature information after cleaning is obtained, unimportant feature information is deleted, function processing is carried out on the feature information after cleaning through a prediction unit in the dangerous grade regression analysis thread corresponding to the rock collapse grade, and therefore target rock state information of the rock collapse grade corresponding to the target to be processed is obtained.
In some possible embodiments, performing a stitching process on target rock status information of a target to be processed corresponding to a plurality of rock collapse levels to obtain target rock status information of the target to be processed, including: when target rock state information corresponding to two different rock collapse grades exists, distinguishing the target rock state information of the two different rock collapse grades, and determining the target rock state information as target rock state information of a target to be processed; and when the target rock state information corresponding to not less than three different rock collapse grades exists, splicing the target rock state information of not less than three different rock collapse grades so as to obtain the target rock state information of the target to be processed.
It can be understood that when the target rock state information of the target to be processed corresponding to a plurality of rock collapse grades is spliced, the problem of splicing errors is solved, so that the target rock state information of the target to be processed can be accurately obtained.
Further, when two different rock collapse grades exist, target rock state information corresponding to the two different rock collapse grades is generated, the distinction between the target rock state information of the two different rock collapse grades is determined as the target rock state information of the target to be processed, so that feature extraction and learning are performed through contrast learning, and the intra-extraction domain commonality and inter-domain distinction are better; when no less than three different rock collapse grades exist, generating target rock state information corresponding to the no less than three different rock collapse grades, splicing the target rock state information of the no less than three different rock collapse grades, determining a splicing result as target rock state information of a target to be processed, enabling the target rock state information of the target to be processed to comprise the target rock state information aiming at all the rock collapse grades, and performing accurate rock stability data evaluation according to the target rock state information of the target to be processed.
In some possible embodiments, the rock collapse level is further subdivided, and feature extraction processing of the rock collapse level is performed on the rock stability data to be processed through a risk level regression analysis thread of the rock collapse level, so as to obtain feature information of the rock collapse level corresponding to the target to be processed, including: for each element of the target to be processed, the following processing is performed: carrying out feature extraction processing on the rock stability data to be processed through a local regression analysis thread of the corresponding element to obtain feature information of the corresponding element of the target to be processed;
further, through a dangerous grade regression analysis thread of the rock collapse grade, and combining characteristic information of the rock collapse grade corresponding to the target to be processed, potential regression analysis processing is performed, so as to obtain target rock state information of the target to be processed in the rock collapse grade, including: for each element of the target to be processed, the following processing is performed: performing potential regression analysis processing by combining the characteristic information of the corresponding element of the target to be processed through the local regression analysis thread of the corresponding element to obtain the target rock state information of the corresponding element of the target to be processed; and splicing the target rock state information of the target to be processed corresponding to the plurality of elements to obtain the target rock state information of the target to be processed corresponding to the rock collapse level.
Illustratively, an element may be understood as a rock condition attribute, such as: the internal structure of the rock, composition information, etc.
It can be understood that each dangerous level regression analysis thread comprises a plurality of local regression analysis threads, and the local regression analysis threads correspond to different elements of the target to be processed; and when the feature extraction processing of the rock collapse grade is carried out on the rock stability data to be processed through the dangerous grade regression analysis thread of the rock collapse grade, the problem of inaccurate extraction is solved, so that the feature information of the target to be processed corresponding to the rock collapse grade can be accurately obtained.
Further, each dangerous level regression analysis thread comprises a plurality of local regression analysis threads, and the plurality of local regression analysis threads correspond to different elements of the target to be processed; for any element of a plurality of elements under a certain rock collapse level, extracting characteristic information of the element in the rock stability data to be processed through a decision unit in a local regression analysis thread corresponding to the element, combining the characteristic information of the element corresponding to the target to be processed, performing potential regression analysis on the target to be processed through a dangerous level regression analysis thread corresponding to the element to obtain target rock state information of the element corresponding to the target to be processed, namely, obtaining targeted target rock state information, splicing the targeted target rock state information to obtain target rock state information of all elements, splicing the target rock state information of the target to be processed corresponding to the plurality of elements to obtain target rock state information of the rock collapse level corresponding to the target to be processed, and performing accurate target evaluation according to the target rock state information of all elements.
In some possible embodiments, performing potential regression analysis processing in combination with feature information of a target corresponding element to be processed to obtain target rock state information of the target corresponding element to be processed, including: performing characteristic cleaning treatment on the characteristic information of the corresponding element of the target to be treated to obtain cleaned characteristic information; and performing function processing on the cleaned characteristic information to obtain target rock state information of the corresponding element of the target to be processed.
It can be understood that when the potential regression analysis processing is performed in combination with the feature information of the target corresponding element to be processed, the problem of influence of the interference information is improved, so that the target rock state information of the target corresponding element to be processed can be accurately obtained.
Further, feature cleaning is carried out on feature information of the corresponding element of the target to be processed through a pooling layer in the local regression analysis thread corresponding to the element, so that feature information after cleaning is obtained, unimportant feature information is deleted, and function processing is carried out on the feature information after cleaning through a prediction unit in the local regression analysis thread corresponding to the element, so that target rock state information of the corresponding element of the target to be processed is obtained.
In some possible embodiments, performing a function process on the cleaned feature information to obtain target rock status information of a corresponding element of the target to be processed, where the method includes: projecting the cleaned characteristic information into target rock state information to obtain collapse possibility distribution; and determining the target rock state information corresponding to the maximum possibility in the collapse possibility distribution as the target rock state information of the corresponding element of the target to be processed.
It can be understood that when the function processing is performed on the characteristic information after the cleaning, the problem of inaccurate collapse probability distribution is solved, so that the target rock state information of the target to be processed corresponding to the element can be accurately obtained.
Further, the cleaned characteristic information is projected into the target rock state information to obtain a collapse possibility distribution, and a plurality of different target rock state information possibilities exist in the collapse possibility distribution corresponding to the element.
The dangerous rock collapse assessment method based on artificial intelligence provided by the embodiment of the invention further comprises the following step 106: in step 106, the rock stability data to be processed is divided to obtain a plurality of rock stability range data of the rock stability data to be processed, where the dividing process may be understood as dividing the stability data according to a preset numerical interval, for example: the range of poor stability is 7-9, then data with stability between 7-9 are considered poor stability, and so on; step 101 includes step 1011B: in step 1011B, performing a potential feature extraction process on each rock stability range data to obtain potential feature information of the target to be processed in the rock stability range data; where the potential feature extraction process may be understood as key content extraction or identification.
It can be understood that when the target rock state information of the target to be processed corresponding to a plurality of the ranges is integrated, the repeated problem is improved, and thus the target rock state information of the target to be processed can be accurately obtained.
Further, step 102 includes steps 1021B-1022B: in step 1021B, performing regression analysis processing by combining potential characteristic information of the target to be processed in each rock stability range data through a regression analysis thread to obtain target rock state information of the target to be processed corresponding to each rock stability range data; in step 1022B, the target rock status information of the target to be processed corresponding to the plurality of ranges is integrated, so as to obtain the target rock status information of the target to be processed. Regression analysis, among other things, can be understood as prediction.
It can be understood that when regression analysis processing is performed in combination with potential characteristic information of the target to be processed, the problem of inaccurate regression analysis processing is solved, so that target rock state information of the target to be processed can be accurately obtained.
For example, firstly dividing rock stability data to be processed to obtain a plurality of rock stability range data of the rock stability data to be processed, then carrying out regression analysis by combining potential characteristic information of a target to be processed in each rock stability range data through a regression analysis thread for regression analysis of the rock stability data to obtain target rock state information of the target to be processed corresponding to each rock stability range data, and finally synthesizing the target rock state information of the target to be processed corresponding to a plurality of ranges to obtain target rock state information of the target to be processed. The local target rock state information corresponding to each rock stability range data is obtained, so that the target rock state information of all the targets to be processed in the rock stability data to be processed is accurately obtained, and the missing of the local target rock state information in the rock stability data to be processed is avoided.
In some possible embodiments, the integrating processing is performed on the target rock status information of the target to be processed corresponding to a plurality of ranges to obtain the target rock status information of the target to be processed, including: carrying out fusion processing on target rock state information of a target to be processed, which corresponds to a plurality of ranges, to obtain fused target rock state information; and performing de-duplication treatment on the fused target rock state information to obtain target rock state information of the target to be treated.
Further, after the server obtains the target rock state information corresponding to each range of the target to be processed, the target rock state information corresponding to a plurality of ranges (the plurality of ranges may be partial ranges in all ranges or all ranges) of the target to be processed may be fused, and as the target rock state information of the plurality of ranges may have repetition, the fused target rock state information is deduplicated to remove the repeated target rock state information, so as to obtain the target rock state information of the target to be processed without repetition.
In some possible embodiments, the integrating processing is performed on the target rock status information of the target to be processed corresponding to a plurality of ranges to obtain the target rock status information of the target to be processed, including: according to the change condition of the to-be-processed item represented by the target rock state information, determining target rock state information with the largest change condition from target rock state information of the to-be-processed object corresponding to a plurality of rock stability range data, and determining the target rock state information with the largest change condition as the target rock state information of the to-be-processed object.
It can be understood that when the target rock state information of the target to be processed corresponding to a plurality of ranges is integrated, the problem that the change condition in the rock state information is not measurable is solved, so that the target rock state information of the target to be processed can be accurately obtained.
In step 103, main feature extraction processing is performed on the rock stability data to be processed, so as to obtain main feature information of the target to be processed.
By way of example, the main features may include information of instability of the internal result of the rock caused by wind and sun exposure or information of instability of the internal structure of the rock caused by different rock compositions (for example, the structure of sandstone is unstable and fragile, and the structure of granite is stable and firm, which is determined by the rock itself).
And extracting main characteristics of the rock stability data to be processed to obtain comprehensive characteristic information of the target to be processed.
In step 104, the target rock state information of the target to be processed in the rock stability data to be processed and the main characteristic information of the target to be processed are spliced to obtain the splicing result of the target to be processed.
For example, after the server obtains the target rock state information of the target to be processed and the main feature information of the target to be processed, the target rock state information of the target to be processed and the main feature information of the target to be processed are spliced to obtain a splicing result of the target to be processed, so that rock stability data evaluation processing can be performed based on the splicing result of the target to be processed.
In step 105, an evaluation process is performed in combination with the splicing result of the target to be processed, so as to obtain a dangerous rock collapse evaluation result.
For example, after the server obtains the splicing result of the target to be processed, the target to be processed is evaluated based on the splicing result of the target to be processed, so as to obtain the dangerous rock collapse evaluation result.
In some possible embodiments, performing an evaluation process based on a splice result of the target to be processed to obtain a dangerous rock collapse evaluation result includes: mapping the splicing result of the target to be processed to the collapse possibility distribution of the dangerous rock collapse evaluation result; and determining the rock collapse grade corresponding to the maximum possibility in the collapse possibility distribution as a dangerous rock collapse evaluation result.
It can be understood that when the evaluation processing is performed in combination with the splicing result of the target to be processed, the problem that the collapse possibility is unreliable is solved, so that the dangerous rock collapse evaluation result can be accurately obtained.
In some possible embodiments, in order to analyze the rock collapse level of a target by a rock stability data processing thread, the rock stability data processing thread needs to be configured, the configuration process of which includes: regression analysis processing is carried out on the rock stability data example through a rock stability data processing thread, so that target rock state information of a target to be processed is obtained; splicing target rock state information of the target to be processed in the rock stability data example and main characteristic information of the target to be processed to obtain a splicing result of the target to be processed; performing evaluation processing based on the splicing result of the target to be processed to obtain a dangerous rock collapse evaluation result; constructing an evaluation index algorithm of a rock stability data processing thread according to the dangerous rock collapse evaluation result and the rock collapse grade identification; and updating the coefficient of the rock stability data processing thread until the evaluation index algorithm converges, and determining the updated coefficient of the rock stability data processing thread when the evaluation index algorithm converges as the coefficient of the configured rock stability data processing thread.
For example, potential feature extraction processing is performed on the rock stability data example through the rock stability data processing thread to obtain potential feature information of a target to be processed in the rock stability data example, regression analysis processing is performed on the basis of the potential feature information of the target to be processed to obtain target rock state information of the target to be processed, main feature extraction processing is performed on the rock stability data example to obtain main feature information of the target to be processed, splicing processing is performed on the target rock state information of the target to be processed and the main feature information of the target to be processed in the rock stability data example to obtain a splicing result of the target to be processed, evaluation processing is performed on the basis of the splicing result of the target to be processed to obtain a dangerous rock collapse evaluation result, after the value of the evaluation index algorithm of the rock stability data processing thread is determined according to the dangerous rock collapse evaluation result and the rock collapse grade identification, whether the value of the evaluation index algorithm of the rock stability data processing thread exceeds the specified target value or not can be judged, when the value of the evaluation index algorithm of the rock stability data processing thread exceeds the specified target value, error information of the rock stability data processing thread is determined on the basis of the evaluation index algorithm of the rock stability data processing thread, error information is input into the rock stability data processing thread, and each thread is optimized in the debugging process.
On the basis of the above, there is provided an artificial intelligence-based dangerous rock collapse assessment device, the device comprising:
the information determining module is used for carrying out feature extraction processing on rock collapse grade of rock stability data to be processed through a dangerous grade regression analysis thread of the rock collapse grade to obtain feature information of a target to be processed corresponding to the rock collapse grade so as to determine potential feature information of the target to be processed;
the information regression analysis module is used for carrying out regression analysis processing by combining the potential characteristic information of the target to be processed to obtain target rock state information of the target to be processed;
the feature extraction module is used for carrying out main feature extraction processing on the rock stability data to be processed to obtain main feature information of the target to be processed;
the result splicing module is used for splicing the target rock state information of the target to be processed in the rock stability data to be processed with the main characteristic information of the target to be processed to obtain a splicing result of the target to be processed;
and the result evaluation module is used for performing evaluation processing by combining the splicing result of the target to be processed to obtain a dangerous rock collapse evaluation result.
On the above basis, an artificial intelligence based dangerous rock collapse assessment system is shown comprising a processor and a memory in communication with each other, the processor being adapted to read a computer program from the memory and execute it to implement the method described above.
On the basis of the above, there is also provided a computer readable storage medium on which a computer program stored which, when run, implements the above method.
In summary, based on the above scheme, by splicing the target rock state information of the target to be processed and the main feature information of the target to be processed, so as to synthesize the potential feature information of the target to be processed and the main feature information of the target to be processed, extract more feature information of the target to be processed, the stability of the rock can be accurately determined, and thus the accuracy and reliability of rock collapse evaluation can be improved; in addition, through the target rock state information of the target to be processed, the target to be processed is evaluated to obtain a dangerous rock collapse evaluation result so as to ensure the accuracy of evaluation, thereby accurately performing advanced protection and reducing the loss caused by rock collapse as much as possible.
It should be appreciated that the systems and modules thereof shown above may be implemented in a variety of ways. For example, in some embodiments, the system and its modules may be implemented in hardware, software, or a combination of software and hardware. Wherein the hardware portion may be implemented using dedicated logic; the software portions may then be stored in a memory and executed by a suitable instruction execution system, such as a microprocessor or special purpose design hardware. Those skilled in the art will appreciate that the methods and systems described above may be implemented using computer executable instructions and/or embodied in processor control code, such as provided on a carrier medium such as a magnetic disk, CD or DVD-ROM, a programmable memory such as read only memory (firmware), or a data carrier such as an optical or electronic signal carrier. The system and its modules of the present application may be implemented not only with hardware circuitry, such as very large scale integrated circuits or gate arrays, semiconductors such as logic chips, transistors, etc., or programmable hardware devices such as field programmable gate arrays, programmable logic devices, etc., but also with software, such as executed by various types of processors, and with a combination of the above hardware circuitry and software (e.g., firmware).
It should be noted that, the advantages that may be generated by different embodiments may be different, and in different embodiments, the advantages that may be generated may be any one or a combination of several of the above, or any other possible advantages that may be obtained.
Claims (10)
1. An artificial intelligence-based dangerous rock collapse assessment method, which is characterized by comprising the following steps:
carrying out feature extraction processing on rock collapse grade feature of rock stability data to be processed through a rock collapse grade risk grade regression analysis thread to obtain feature information of a target to be processed corresponding to the rock collapse grade, so as to determine potential feature information of the target to be processed;
carrying out regression analysis processing by combining the potential characteristic information of the target to be processed to obtain target rock state information of the target to be processed;
performing main characteristic extraction processing on the rock stability data to be processed to obtain main characteristic information of the target to be processed;
performing splicing processing on target rock state information of a target to be processed in the rock stability data to be processed and main characteristic information of the target to be processed to obtain a splicing result of the target to be processed;
Performing evaluation treatment by combining the splicing result of the target to be treated to obtain a dangerous rock collapse evaluation result;
the potential characteristic information can comprise information that rock loosens after earthquake, explosive explosion and water impact rock operation are carried out, and the rock is not unstable due to the potential characteristic information;
the main characteristics can include information of unstable internal results caused by the fact that the rock is exposed to the wind and the sun or information of unstable internal structure of the rock caused by different rock components.
2. The method of claim 1, wherein the regression analysis thread for regression analysis of rock stability data comprises a number of risk level regression analysis threads, and the number of risk level regression analysis threads each correspond to a different rock collapse level; performing regression analysis processing by combining the potential characteristic information of the target to be processed to obtain target rock state information of the target to be processed, wherein the regression analysis processing comprises the following steps:
performing potential regression analysis processing by combining characteristic information of the to-be-processed target corresponding to the rock collapse grade through a dangerous grade regression analysis thread of the rock collapse grade, so as to obtain target rock state information of the to-be-processed target corresponding to the rock collapse grade;
And splicing the target rock state information of the target to be processed corresponding to a plurality of rock collapse grades to obtain the target rock state information of the target to be processed.
3. The method according to claim 2, wherein the performing a latent regression analysis process in combination with the characteristic information of the target to be processed corresponding to the rock collapse level to obtain target rock status information of the target to be processed corresponding to the rock collapse level includes:
performing characteristic cleaning treatment on the characteristic information of the to-be-treated object corresponding to the rock collapse grade to obtain cleaned characteristic information;
and performing function processing on the characteristic information after cleaning to obtain target rock state information of the target to be processed corresponding to the rock collapse grade.
4. The method according to claim 2, wherein the performing the splicing processing on the target rock status information of the target to be processed corresponding to the plurality of rock collapse levels to obtain the target rock status information of the target to be processed includes:
when target rock state information corresponding to two different rock collapse grades exists, distinguishing the target rock state information of the two different rock collapse grades from each other, and determining the target rock state information of the target to be processed;
And when target rock state information corresponding to not less than three different rock collapse grades exists, splicing the target rock state information of not less than three different rock collapse grades so as to obtain the target rock state information of the target to be processed.
5. The method of claim 2, wherein each of the threat level regression analysis threads comprises a number of partial regression analysis threads, and the number of partial regression analysis threads correspond to different elements of the object to be processed; and performing feature extraction processing on the rock collapse grade on the rock stability data to be processed through the dangerous grade regression analysis thread of the rock collapse grade to obtain feature information of the target to be processed corresponding to the rock collapse grade, wherein the feature information comprises the following steps:
for each element of the object to be processed, the following processing is performed: performing feature extraction processing on the rock stability data to be processed through a local regression analysis thread corresponding to the element to obtain feature information of the target to be processed corresponding to the element;
and performing potential regression analysis processing by combining the dangerous grade regression analysis thread of the rock collapse grade and the characteristic information of the target to be processed corresponding to the rock collapse grade to obtain target rock state information of the target to be processed in the rock collapse grade, wherein the potential regression analysis processing comprises the following steps:
For each element of the object to be processed, the following processing is performed: the target rock state information of the target to be processed corresponding to the element is obtained through a local regression analysis thread corresponding to the element and combining the characteristic information of the target to be processed corresponding to the element to perform potential regression analysis processing;
and splicing the target rock state information of the target to be processed corresponding to a plurality of elements to obtain the target rock state information of the target to be processed corresponding to the rock collapse level.
6. The method according to claim 5, wherein the performing a latent regression analysis process in combination with the feature information of the element corresponding to the target to be processed to obtain target rock status information of the element corresponding to the target to be processed includes:
performing characteristic cleaning treatment on the characteristic information of the target to be treated corresponding to the element to obtain cleaned characteristic information;
performing function processing on the characteristic information after cleaning to obtain target rock state information of the target to be processed corresponding to the element;
the step of performing function processing on the cleaned characteristic information to obtain target rock state information of the target to be processed corresponding to the element comprises the following steps:
Projecting the cleaned characteristic information into the target rock state information to obtain collapse possibility distribution;
and determining the target rock state information corresponding to the maximum possibility in the collapse possibility distribution as the target rock state information corresponding to the element of the target to be processed.
7. The method of claim 1, further comprising, prior to potential feature extraction processing of the rock stability data to be processed: dividing the rock stability data to be processed to obtain a plurality of rock stability range data of the rock stability data to be processed;
performing potential feature extraction processing on the rock stability data to be processed to obtain potential feature information of a target to be processed in the rock stability data to be processed, wherein the potential feature information comprises: performing potential feature extraction processing on each rock stability range data to obtain potential feature information of the target to be processed in the rock stability range data;
performing regression analysis processing by combining the potential characteristic information of the target to be processed to obtain target rock state information of the target to be processed, wherein the regression analysis processing comprises the following steps: carrying out regression analysis processing by combining potential characteristic information of the target to be processed in each rock stability range data through a regression analysis thread to obtain target rock state information of the target to be processed corresponding to each rock stability range data; integrating the target rock state information of the target to be processed corresponding to a plurality of ranges to obtain target rock state information of the target to be processed;
The integrating the target rock state information of the target to be processed corresponding to a plurality of ranges to obtain the target rock state information of the target to be processed includes:
carrying out fusion processing on the target rock state information of the target to be processed corresponding to a plurality of ranges to obtain fused target rock state information;
performing de-duplication treatment on the fused target rock state information to obtain target rock state information of the target to be treated;
the integrating the target rock state information of the target to be processed corresponding to a plurality of ranges to obtain the target rock state information of the target to be processed includes: according to the change condition of the target to be processed, which is represented by the target rock state information, determining target rock state information with the largest change condition from target rock state information of the target to be processed, which corresponds to a plurality of rock stability range data, and determining the target rock state information with the largest change condition as the target rock state information of the target to be processed.
8. The method according to claim 1, wherein the performing evaluation processing in combination with the splicing result of the target to be processed to obtain a dangerous rock collapse evaluation result includes:
Mapping the splicing result of the target to be processed to collapse probability distribution of dangerous rock collapse evaluation results;
and determining the rock collapse grade corresponding to the maximum possibility in the collapse possibility distribution as a dangerous rock collapse evaluation result.
9. The method of claim 1, further comprising, prior to potential feature extraction processing of the rock stability data to be processed:
responding to an evaluation instruction for rock stability data to be processed, and obtaining initial rock stability data; performing at least one of the following processes with respect to the initial rock stability data: carrying out dimensionless simplification processing on each data sub-bucket in the initial rock stability data, and determining the initial rock stability data subjected to dimensionless simplification as the rock stability data to be processed;
filtering the interference information in the initial rock stability data, and determining the filtered initial rock stability data as the rock stability data to be processed;
and analyzing and processing the target to be processed in the initial rock stability data, and determining the analyzed initial rock stability data as the rock stability data to be processed.
10. A dangerous rock collapse assessment system based on artificial intelligence, comprising a processor and a memory in communication with each other, the processor being adapted to read a computer program from the memory and execute it to implement the method of any of claims 1-9.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410046420.7A CN117557434B (en) | 2024-01-12 | 2024-01-12 | Dangerous rock collapse assessment method and system based on artificial intelligence |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410046420.7A CN117557434B (en) | 2024-01-12 | 2024-01-12 | Dangerous rock collapse assessment method and system based on artificial intelligence |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN117557434A CN117557434A (en) | 2024-02-13 |
| CN117557434B true CN117557434B (en) | 2024-03-19 |
Family
ID=89817123
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202410046420.7A Active CN117557434B (en) | 2024-01-12 | 2024-01-12 | Dangerous rock collapse assessment method and system based on artificial intelligence |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117557434B (en) |
Citations (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2012198886A (en) * | 2011-03-10 | 2012-10-18 | Yamaguchi Univ | Sediment disaster occurring risk evaluation system according to volcanic activity level and program thereof |
| CN102809332A (en) * | 2012-08-17 | 2012-12-05 | 重庆市爆破工程建设有限责任公司 | Safety and protection method for blasting of high-slope unstable rock |
| CN106198924A (en) * | 2016-06-27 | 2016-12-07 | 重庆大学 | Precarious rock mass monitoring system based on self adaptation frequency acquisition and methods of risk assessment thereof |
| CN107067333A (en) * | 2017-01-16 | 2017-08-18 | 长沙矿山研究院有限责任公司 | A kind of high altitudes and cold stability of the high and steep slope monitoring method |
| CN107194049A (en) * | 2017-05-09 | 2017-09-22 | 山东大学 | A kind of multi objective Grade system of tunnels and underground engineering rockfall risk |
| CN108596518A (en) * | 2018-05-14 | 2018-09-28 | 中国路桥工程有限责任公司 | A kind of Highway Geological Disaster risk assessment method |
| CN113821977A (en) * | 2021-09-28 | 2021-12-21 | 成都理工大学 | Rock burst risk assessment system and method for TBM tunnel construction |
| CN114021487A (en) * | 2022-01-10 | 2022-02-08 | 西南交通大学 | Early warning method, device and equipment for landslide collapse and readable storage medium |
| CN114134877A (en) * | 2021-11-15 | 2022-03-04 | 山东科技大学 | Treatment method for mining ground cracks of shallow coal seam in hilly area of hilly landform |
| CN116757335A (en) * | 2023-08-17 | 2023-09-15 | 四川省华地建设工程有限责任公司 | Collapse prediction method and system based on Beidou satellite |
| CN117116010A (en) * | 2023-08-25 | 2023-11-24 | 沈阳工业大学 | Intelligent rock mass collapse early warning method and system |
-
2024
- 2024-01-12 CN CN202410046420.7A patent/CN117557434B/en active Active
Patent Citations (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2012198886A (en) * | 2011-03-10 | 2012-10-18 | Yamaguchi Univ | Sediment disaster occurring risk evaluation system according to volcanic activity level and program thereof |
| CN102809332A (en) * | 2012-08-17 | 2012-12-05 | 重庆市爆破工程建设有限责任公司 | Safety and protection method for blasting of high-slope unstable rock |
| CN106198924A (en) * | 2016-06-27 | 2016-12-07 | 重庆大学 | Precarious rock mass monitoring system based on self adaptation frequency acquisition and methods of risk assessment thereof |
| CN107067333A (en) * | 2017-01-16 | 2017-08-18 | 长沙矿山研究院有限责任公司 | A kind of high altitudes and cold stability of the high and steep slope monitoring method |
| CN107194049A (en) * | 2017-05-09 | 2017-09-22 | 山东大学 | A kind of multi objective Grade system of tunnels and underground engineering rockfall risk |
| CN108596518A (en) * | 2018-05-14 | 2018-09-28 | 中国路桥工程有限责任公司 | A kind of Highway Geological Disaster risk assessment method |
| CN113821977A (en) * | 2021-09-28 | 2021-12-21 | 成都理工大学 | Rock burst risk assessment system and method for TBM tunnel construction |
| CN114134877A (en) * | 2021-11-15 | 2022-03-04 | 山东科技大学 | Treatment method for mining ground cracks of shallow coal seam in hilly area of hilly landform |
| CN114021487A (en) * | 2022-01-10 | 2022-02-08 | 西南交通大学 | Early warning method, device and equipment for landslide collapse and readable storage medium |
| CN116757335A (en) * | 2023-08-17 | 2023-09-15 | 四川省华地建设工程有限责任公司 | Collapse prediction method and system based on Beidou satellite |
| CN117116010A (en) * | 2023-08-25 | 2023-11-24 | 沈阳工业大学 | Intelligent rock mass collapse early warning method and system |
Non-Patent Citations (5)
| Title |
|---|
| A new approach for prediction of collapse settlement of sandy gravel soils;Soleimani, Sepehr 等;《ENGINEERING WITH COMPUTERS》;20180131;第34卷(第1期);第15-24页 * |
| Influence of rock property correlation on reliability analysis of rock slope stability: From property characterization to reliability analysis;Adeyemi Emman Aladejare 等;《Geoscience Frontiers》;20181130;第9卷(第6期);第1639-1648页 * |
| 基于坐标投影法岩质边坡块体稳定性分析及其可视化研究;高丙丽 等;《岩土力学》;20220131;第43卷(第1期);第181-194页 * |
| 岩质高边坡坡体结构特征分析与稳定性研究——以焦作市龙寺矿山岩质高边坡为例;陈鹏宇;《中国博士学位论文全文数据库 基础科学辑》;20160115(第1期);第A011-2页 * |
| 祁连山滑坡灾害初步研究;吴玮江 等;《甘肃地质》;20211231;第30卷(第4期);第16-29页 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN117557434A (en) | 2024-02-13 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US10785241B2 (en) | URL attack detection method and apparatus, and electronic device | |
| Wu et al. | Defiranger: Detecting price manipulation attacks on defi applications | |
| CN110457428B (en) | Sensitive word detection and filtering method and device and electronic equipment | |
| CN111092894A (en) | Webshell detection method based on incremental learning, terminal device and storage medium | |
| CN111931179A (en) | Cloud malicious program detection system and method based on deep learning | |
| CN112926399A (en) | Target object detection method and device, electronic equipment and storage medium | |
| CN111881300A (en) | Third-party library dependency-oriented knowledge graph construction method and system | |
| CN117557434B (en) | Dangerous rock collapse assessment method and system based on artificial intelligence | |
| CN110719278A (en) | Method, device, equipment and medium for detecting network intrusion data | |
| CN112783508B (en) | File compiling method, device, equipment and storage medium | |
| KR102344496B1 (en) | Method and apparatus for analysing function of malicious code | |
| JP6789844B2 (en) | Similar function extractor and similar function extractor | |
| CN113963197A (en) | Image recognition method and device, electronic equipment and readable storage medium | |
| JP2014206382A (en) | Target type identification device | |
| CN108664900B (en) | Method and equipment for identifying similarities and differences of written works | |
| JP7003435B2 (en) | Information processing equipment, programs, information processing methods and data structures | |
| CN111104963A (en) | Target user determination method and device, storage medium and electronic equipment | |
| CN116305171B (en) | Component vulnerability analysis method, device, equipment and storage medium | |
| US20210373866A1 (en) | Bottleneck detection device and computer readable medium | |
| CN117312833B (en) | Data identification method and system applied to digital asset environment | |
| CN117671508B (en) | SAR image-based high-steep side slope landslide detection method and system | |
| CN115501610B (en) | Abnormal data processing method and system of game system | |
| JP7075011B2 (en) | Information processing device, patch application confirmation system, patch application confirmation method, and patch application confirmation program | |
| KR102382017B1 (en) | Apparatus and method for malware lineage inference system with generating phylogeny | |
| CN112329931B (en) | Countermeasure sample generation method and device based on proxy model |
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 |