CN116843177A - State analysis method and system based on data set - Google Patents
State analysis method and system based on data set Download PDFInfo
- Publication number
- CN116843177A CN116843177A CN202310664125.3A CN202310664125A CN116843177A CN 116843177 A CN116843177 A CN 116843177A CN 202310664125 A CN202310664125 A CN 202310664125A CN 116843177 A CN116843177 A CN 116843177A
- Authority
- CN
- China
- Prior art keywords
- embankment
- dike
- data set
- data
- upstream
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000004458 analytical method Methods 0.000 title claims abstract description 104
- 238000011144 upstream manufacturing Methods 0.000 claims abstract description 96
- 238000001514 detection method Methods 0.000 claims abstract description 61
- 238000000034 method Methods 0.000 claims abstract description 58
- 238000012545 processing Methods 0.000 claims abstract description 45
- 238000004422 calculation algorithm Methods 0.000 claims abstract description 29
- 238000011835 investigation Methods 0.000 claims abstract description 19
- 238000012800 visualization Methods 0.000 claims abstract description 11
- 230000002776 aggregation Effects 0.000 claims abstract description 9
- 238000004220 aggregation Methods 0.000 claims abstract description 9
- 238000012544 monitoring process Methods 0.000 claims description 84
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 claims description 62
- 238000004364 calculation method Methods 0.000 claims description 49
- 239000002689 soil Substances 0.000 claims description 41
- 239000011435 rock Substances 0.000 claims description 16
- 239000000758 substrate Substances 0.000 claims description 16
- 230000000007 visual effect Effects 0.000 claims description 15
- 239000011159 matrix material Substances 0.000 claims description 14
- 238000013499 data model Methods 0.000 claims description 12
- 238000000491 multivariate analysis Methods 0.000 claims description 11
- 238000000611 regression analysis Methods 0.000 claims description 11
- 238000004140 cleaning Methods 0.000 claims description 9
- 238000000605 extraction Methods 0.000 claims description 9
- 230000004927 fusion Effects 0.000 claims description 9
- 230000009471 action Effects 0.000 claims description 8
- 238000004088 simulation Methods 0.000 claims description 8
- 238000013135 deep learning Methods 0.000 claims description 7
- 230000005484 gravity Effects 0.000 claims description 7
- 238000007619 statistical method Methods 0.000 claims description 7
- 238000013079 data visualisation Methods 0.000 claims description 6
- 238000013473 artificial intelligence Methods 0.000 claims description 4
- 238000004590 computer program Methods 0.000 claims description 4
- 238000012407 engineering method Methods 0.000 claims description 4
- 238000000556 factor analysis Methods 0.000 claims 1
- 230000015572 biosynthetic process Effects 0.000 description 26
- 238000005516 engineering process Methods 0.000 description 13
- 238000007726 management method Methods 0.000 description 10
- 238000012876 topography Methods 0.000 description 10
- 239000013598 vector Substances 0.000 description 8
- 238000013461 design Methods 0.000 description 7
- 230000009286 beneficial effect Effects 0.000 description 6
- 230000008569 process Effects 0.000 description 5
- 238000010586 diagram Methods 0.000 description 4
- 238000011156 evaluation Methods 0.000 description 4
- 239000004973 liquid crystal related substance Substances 0.000 description 4
- 238000007781 pre-processing Methods 0.000 description 4
- 230000008859 change Effects 0.000 description 3
- 238000007405 data analysis Methods 0.000 description 3
- 230000000694 effects Effects 0.000 description 3
- 238000001914 filtration Methods 0.000 description 3
- 238000007689 inspection Methods 0.000 description 3
- 230000005540 biological transmission Effects 0.000 description 2
- 238000010276 construction Methods 0.000 description 2
- 238000013075 data extraction Methods 0.000 description 2
- 230000007613 environmental effect Effects 0.000 description 2
- 230000006870 function Effects 0.000 description 2
- 238000012423 maintenance Methods 0.000 description 2
- 238000013439 planning Methods 0.000 description 2
- 230000002265 prevention Effects 0.000 description 2
- 230000001681 protective effect Effects 0.000 description 2
- 230000008439 repair process Effects 0.000 description 2
- 238000012549 training Methods 0.000 description 2
- 238000006243 chemical reaction Methods 0.000 description 1
- 239000003086 colorant Substances 0.000 description 1
- 238000012937 correction Methods 0.000 description 1
- 238000013523 data management Methods 0.000 description 1
- 238000007418 data mining Methods 0.000 description 1
- 238000000354 decomposition reaction Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000009434 installation Methods 0.000 description 1
- 238000010801 machine learning Methods 0.000 description 1
- 239000000463 material Substances 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000000513 principal component analysis Methods 0.000 description 1
- 230000001105 regulatory effect Effects 0.000 description 1
- 230000003014 reinforcing effect Effects 0.000 description 1
- 238000012216 screening Methods 0.000 description 1
- 239000013049 sediment Substances 0.000 description 1
- 238000005728 strengthening Methods 0.000 description 1
- 230000009466 transformation Effects 0.000 description 1
- 238000013024 troubleshooting Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01S—RADIO DIRECTION-FINDING; RADIO NAVIGATION; DETERMINING DISTANCE OR VELOCITY BY USE OF RADIO WAVES; LOCATING OR PRESENCE-DETECTING BY USE OF THE REFLECTION OR RERADIATION OF RADIO WAVES; ANALOGOUS ARRANGEMENTS USING OTHER WAVES
- G01S17/00—Systems using the reflection or reradiation of electromagnetic waves other than radio waves, e.g. lidar systems
- G01S17/88—Lidar systems specially adapted for specific applications
- G01S17/89—Lidar systems specially adapted for specific applications for mapping or imaging
- G01S17/894—3D imaging with simultaneous measurement of time-of-flight at a 2D array of receiver pixels, e.g. time-of-flight cameras or flash lidar
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01C—MEASURING DISTANCES, LEVELS OR BEARINGS; SURVEYING; NAVIGATION; GYROSCOPIC INSTRUMENTS; PHOTOGRAMMETRY OR VIDEOGRAMMETRY
- G01C13/00—Surveying specially adapted to open water, e.g. sea, lake, river or canal
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01D—MEASURING NOT SPECIALLY ADAPTED FOR A SPECIFIC VARIABLE; ARRANGEMENTS FOR MEASURING TWO OR MORE VARIABLES NOT COVERED IN A SINGLE OTHER SUBCLASS; TARIFF METERING APPARATUS; MEASURING OR TESTING NOT OTHERWISE PROVIDED FOR
- G01D21/00—Measuring or testing not otherwise provided for
- G01D21/02—Measuring two or more variables by means not covered by a single other subclass
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0635—Risk analysis of enterprise or organisation activities
-
- 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—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/08—Construction
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T17/00—Three dimensional [3D] modelling, e.g. data description of 3D objects
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Business, Economics & Management (AREA)
- General Physics & Mathematics (AREA)
- Human Resources & Organizations (AREA)
- Theoretical Computer Science (AREA)
- Strategic Management (AREA)
- Economics (AREA)
- General Business, Economics & Management (AREA)
- Entrepreneurship & Innovation (AREA)
- Tourism & Hospitality (AREA)
- Marketing (AREA)
- Remote Sensing (AREA)
- Radar, Positioning & Navigation (AREA)
- Quality & Reliability (AREA)
- Electromagnetism (AREA)
- Educational Administration (AREA)
- Development Economics (AREA)
- Operations Research (AREA)
- Hydrology & Water Resources (AREA)
- Life Sciences & Earth Sciences (AREA)
- Game Theory and Decision Science (AREA)
- Computer Networks & Wireless Communication (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Primary Health Care (AREA)
- Computer Graphics (AREA)
- Geometry (AREA)
- Software Systems (AREA)
- Testing Or Calibration Of Command Recording Devices (AREA)
Abstract
The invention relates to the technical field of detection of dyke hidden danger, in particular to a state analysis method and system based on a data set. The method comprises the following steps: performing stratum lithology detection on the embankment by using a laser radar, obtaining a multi-dimensional data set of the embankment, performing three-dimensional visualization processing on the basis of the multi-dimensional data set by using GIS software, and constructing a stratum analysis chart; based on the stratum analysis chart, the unmanned ship and the submersible are utilized to monitor and analyze the downstream hydrological data of the embankment, and a downstream high-definition remote sensing image of the embankment is generated; based on a dike downstream high-definition remote sensing image, acquiring a dike upstream real-time multi-mode data set by using a dike upstream sensor, and performing dike cloud aggregation operation by using the dike upstream real-time multi-mode data set; constructing a dike comprehensive decision support system by using a dike hydrologic artificial intelligent algorithm based on the upstream cloud data set and the downstream high-definition remote sensing image of the dike; according to the invention, the potential embankment hazard data set is processed, so that the potential embankment hazard investigation and analysis efficiency is improved.
Description
Technical Field
The invention relates to the technical field of detection of dyke hidden danger, in particular to a state analysis method and system based on a data set.
Background
The state analysis method and the system based on the data set introduce various physical detection technologies, such as a laser radar, unmanned sensing equipment and the like, and perform data processing and analysis by reading and recording the physical characteristics of the embankment, and finally realize the rapid and accurate detection and evaluation of the embankment hidden danger, so that the safety and stability of the embankment are improved, and meanwhile, the application range of the state analysis method and the system based on the data set is continuously expanded and improved along with the rapid development of the computer technology and the image processing technology, so that the method becomes an important means for the embankment detection, greatly improves the detection efficiency of the embankment hidden danger and improves the working safety.
Disclosure of Invention
The invention provides a state analysis method and a state analysis system based on a data set to solve at least one technical problem.
In order to achieve the above object, the present invention provides a state analysis method based on a data set, including the steps of:
Step S1: performing stratum lithology detection on the embankment by using a laser radar to obtain an embankment multidimensional data set, wherein the embankment multidimensional data set comprises a stratum lithology data set, an embankment contour data set and a terrain height data set, and performing three-dimensional visualization processing on the multidimensional data set by using GIS software to construct a stratum analysis chart;
step S2: according to the stratum analysis chart, monitoring and analyzing the downstream hydrological data of the embankment by using the unmanned ship and the submersible to obtain a downstream high-definition remote sensing image of the embankment;
step S3: acquiring a dike upstream real-time multi-mode data set by using a dike upstream sensor according to a dike downstream high-definition remote sensing image, and performing dike cloud aggregation operation on the dike upstream real-time multi-mode data set to generate a dike cloud data set;
step S4: based on the upstream cloud data set and the downstream high-definition remote sensing image of the dike, the dike comprehensive decision support system is constructed by utilizing the dike hydrologic artificial intelligent algorithm, so that the omnibearing and multilayer monitoring and investigation of the hidden danger state of the dike are realized.
The invention provides a state analysis method based on a data set, which utilizes a stratum lithology data set, a dike profile data set, a terrain height data set and GIS software to carry out three-dimensional visualization processing on the multi-dimensional data set, constructs a stratum analysis chart, thereby improving the accuracy and the range of dike monitoring, utilizes an unmanned ship and a submersible to carry out dike downstream hydrological data monitoring analysis through the stratum analysis chart, generates a dike downstream high-definition remote sensing image, integrates data to carry out comprehensive analysis, provides decision support, and can carry out dike gathering operation based on the stratum analysis chart and the dike downstream high-definition remote sensing image to generate a dike cloud data set, and utilizes a dike hydrological artificial intelligent algorithm to construct a dike comprehensive decision support system through the dike cloud data set, so that the full-dimensional and multi-level monitoring and investigation of the dike hidden danger state is realized.
Preferably, step S1 comprises the steps of:
step S11: performing stratum lithology multidimensional detection on the embankment by using a laser radar to obtain a stratum multidimensional data set of the embankment;
step S12: carrying out data-driven modeling on the multi-dimensional data set of the embankment stratum based on a geostatistical method to generate a three-dimensional embankment physical model;
step S13: performing three-dimensional visualization processing by using GIS software based on the three-dimensional dike physical model, and constructing a dike data visualization view;
step S14: and performing machine vision recognition analysis on the visual view of the embankment data by using a machine vision recognition algorithm to construct a stratum analysis chart.
According to the method, the formation lithology of the embankment is detected in a multi-dimension mode through the laser radar, a multi-dimension data set of the embankment formation is generated, the multi-dimension data set of the embankment formation is subjected to data driving modeling through a geostatistical method, a physical model of the embankment is generated, three-dimensional visual processing is conducted through GIS software on the basis of the data driving modeling, a visual view of the embankment data is constructed, visual expression is provided for the formation analysis of the embankment, meanwhile, machine visual recognition is conducted through a machine visual recognition algorithm, and a formation analysis graph is generated through analysis of the visual view of the embankment data.
Preferably, step S12 comprises the steps of:
step S121: carrying out data cleaning on the stratum multidimensional data set to generate a dyke standardized data set;
step S122: analyzing and calculating variation coefficients of the dike normalized data set by using a multivariate statistical analysis method to generate a dike multivariate analysis data set;
step S123: performing geological difference calculation by using a geostatistical spatial interpolation method based on the dike multivariate analysis data set to generate a stratum data warehouse;
step S124: performing simulation analysis by utilizing numerical simulation based on the stratum data warehouse to generate a embankment three-dimensional physical model;
according to the invention, the problems of nonstandard and incomplete formation data in the prior art are effectively solved by carrying out data cleaning and dyke standardized data set generation on the formation multidimensional data set, the variation coefficient analysis calculation is carried out on the dyke standardized data set by utilizing a multivariate statistical analysis method, the accuracy and the efficiency of data analysis are improved on the premise of ensuring the data quality, the geological difference calculation is carried out on the dyke multivariate analysis data set by utilizing a geostatistical spatial interpolation method, and the generated formation data warehouse has higher geological precision and reliability; and the numerical simulation analysis is carried out based on the stratum data warehouse, so that the generated embankment three-dimensional physical model can more accurately simulate the embankment structure, and the flood control and disaster prevention capabilities and safety are improved.
Preferably, step S2 comprises the steps of:
step S21: dividing monitoring areas according to the stratum analysis chart to generate a monitoring module table;
step S22: according to the monitoring module list, extracting monitoring point parameter data by using unmanned ships and submersible carrying detection equipment, and generating a downstream water detection data list of the embankment;
step S23: carrying out regression calculation on the downstream hydrological detection data table of the dike by using a downstream regression analysis calculation formula of the dike to generate a primary downstream remote sensing data set of the dike;
step S24: and performing pixel classification calculation by using a pixel-level iterative classifier method based on the primary dike downstream remote sensing data set to obtain a dike downstream high-definition remote sensing image.
According to the method, the monitoring area is divided based on the stratum analysis graph, the monitoring area is definitely divided, the monitoring precision and the monitoring efficiency are improved, meanwhile, the generation of the monitoring module table is convenient for the extraction and management of follow-up monitoring point parameter data, the unmanned ship and the submersible carrier detection equipment are utilized for carrying out the monitoring point parameter data extraction operation, the hydrological data table can be obtained, the information can be used for analyzing the hydrological environment of the downstream of the embankment, the accuracy of monitoring is improved, the prediction and the evaluation of key parameters such as the water level and the flow of the downstream of the embankment are facilitated, the regression calculation is carried out through the regression analysis calculation formula of the downstream of the embankment, the primary embankment downstream remote sensing data set can be obtained, the inversion of surface coverage characteristic information is facilitated based on the primary embankment downstream remote sensing data set, the important data basis is provided for the follow-up pixel level iterative classifier, the method can be used for carrying out the pixel classification calculation of the primary embankment downstream remote sensing data set, the downstream of the embankment high-definition remote sensing image can be obtained, the downstream area of the embankment is predicted, the downstream area is well-land and the land quality of the downstream of the embankment is well-down, the monitoring quality is improved, the accurate monitoring condition is improved, the risk is well-down, the monitoring method is improved, and the risk is well-down is improved, and the monitoring is well-down, and the risk is well-down.
Preferably, the downstream dike regression analysis calculation formula in step S23 is specifically:
NDVI＝(NIR-RED)/(NIR+RED)；
NDBI＝(SWIR-NIR)/(SWIR+NIR)；
wherein SF is the safety coefficient of the embankment, T n For the embankment terrain adjustment coefficient, n is the size of a fragmented terrain model data set, H is the water level height, HC is the elevation of the embankment roof, DC is the vertical distance from the downstream side of the embankment roof to the river bed, NDVI is the normalized vegetation index, x i Abscissa data of embankment terrain detection points from unmanned ships and submarines, y i For the ordinate data of the embankment terrain detection points from the unmanned ship and the submersible, NDBI is a normalized building index, NIR is a reflection value of a near infrared band, RED is a reflection value of a RED band, and SWIR is a reflection value of a short wave infrared band.
The invention utilizes a downstream regression analysis calculation formula of the embankment, can effectively evaluate the flood fighting capacity of the embankment through setting up the safety coefficient SF, and reduces the safety risk caused by the influence of factors such as water level height, embankment elevation, relative height and the like, thereby improving the safety performance of the embankment and adjusting the coefficient T of the embankment topography n The introduction of the method can be used for detection and evaluation under different embankment topography conditions, so that the safety condition of the embankment can be accurately judged, related parameters are regulated, the safety of the embankment is improved, and normalized vegetation means The application of the number NDVI can evaluate the vegetation coverage condition of the embankment along the line, and timely master the ecological environment condition around the embankment by monitoring the change of the vegetation index, so that the effect of vegetation on the stability of the embankment is judged, a scientific basis is provided for the management and maintenance of the embankment, the application of the normalized building index NDBI can evaluate the building density and the height of the embankment to the river, and further judge which safety risks of the buildings around the embankment to the embankment are increased or reduced, a beneficial reference is provided for the management and the planning of the embankment, and the topography condition of the embankment can be better reflected by combining the multi-wavelength reflection values.
Preferably, step S3 comprises the steps of:
step S31: performing deployment operation of a dike upstream sensor according to a dike downstream high-definition remote sensing image, and building a dike upstream monitoring area;
step S32: monitoring the upstream real-time multi-modal data of the dike according to the upstream monitoring area of the dike, and generating a real-time multi-modal data set of the upstream of the dike;
step S33: performing sequence calculation on the upstream real-time multi-mode data set of the dike by using a dike upstream sequence weight analysis and calculation formula to generate an upstream real-time multi-mode model of the dike;
step S34: performing model homomorphic encryption based on the upstream real-time multi-mode model of the embankment to generate homomorphic ciphertext data sets;
Step S35: and carrying out cloud data aggregation processing based on the homomorphic ciphertext data set to generate a dike cloud data set.
The invention uses high-definition remote sensing images to perform sensor deployment operation and builds a monitoring area at the upstream of the embankment to improve the coverage area and monitoring efficiency of upstream monitoring data of the embankment, thereby effectively improving the safety of the embankment, utilizing the upstream monitoring area of the embankment to monitor a plurality of signals and generating a real-time multi-mode data set, the monitoring of the multi-mode data set can improve the problem of single data variable in the traditional monitoring mode, more comprehensively and accurately reflect the change of the state of the embankment, thereby improving the reliability and accuracy of the safety monitoring of the embankment, using an upstream sequence weight analysis and calculation formula to perform sequence calculation according to the real-time multi-mode data set, thereby obtaining an upstream real-time multi-mode model of the embankment, better reflecting the relation among multi-dimensional data, therefore, the method has higher prediction accuracy and robustness, so that accuracy and timeliness of dike safety monitoring are improved, a homomorphic encryption technology is used for encrypting a real-time multimodal model of upstream dike, a homomorphic ciphertext data set is generated, confidentiality and safety of data further improve privacy protection and data safety of dike data, possible data leakage and abuse are avoided, cloud data gathering processing is carried out by utilizing the homomorphic ciphertext data set, a dike cloud data set is generated, and multimode data from different sensors are better integrated, analyzed and processed by a cloud, so that stability and safety of the dike are better monitored, fed back, early warned and predicted in time, the safety of dike engineering is improved, and pressure brought by manpower and material resource investment in a flood period is relieved.
Preferably, the calculation formula of the upstream sequence weight analysis of the dike in step S33 is specifically:
wherein Q is a time series weight analysis coefficient of the upstream of the embankment, P is rainfall, K1 is a regression weight coefficient of a first observation point, T is time, T1 is a hysteresis error coefficient of the first observation point, K2 is a regression weight coefficient of a 2 nd observation point, T2 is a hysteresis error coefficient of a second observation point, K3 is a fixed water capacity coefficient of the upstream land, K4 is the area of an upstream basin of the embankment, and A is the area of a downstream basin of the embankment.
The invention utilizes a dyke upstream sequence weight analysis calculation formula, the formula fully considers P as rainfall, K1 as regression weight coefficient of a first observation point, T as time, T1 as hysteresis error coefficient of the first observation point, K2 as regression weight coefficient of a 2 nd observation point, T2 as hysteresis error coefficient of a second observation point, K3 as fixed water capacity coefficient of upstream land, K4 as area of upstream river basin of the dyke, A as area of upstream river basin of the dyke, the formula comprises various influences on the dykeThe stability factor relates to acting force and resultant force of a plurality of factors such as water, soil, rock substrate and the like, and the acting force and resultant force of the water and the soil can be calculated through K3 x exp (-K4A), so that the stability of the embankment can be more comprehensively and accurately estimated, the method is beneficial to guiding engineering design and inspection, improving the design quality of the embankment, The contribution of the second observation point to the weight coefficient is represented, wherein the sine function with the regression weight coefficient K2 and the hysteresis error coefficient T2 is multiplied by the factors related to the fixed water capacity K3 of the upstream land and the upstream drainage basin area K4A of the dykes, the influence of the slope of the dykes and the soil type of the dykes on the stability of the dykes is considered by analyzing the effect aspect of the slope of the dykes and the soil type of the dykes, the influence degree of the factors on the stability of the dykes can be more comprehensively analyzed, and a beneficial reference is provided for optimizing engineering design and strengthening protective measures.
Preferably, step S4 comprises the steps of:
step S41: performing stratum feature extraction by using an image processing algorithm based on the upstream cloud data set and the downstream high-definition remote sensing image of the dike to generate a stratum feature matrix;
step S42: performing dyke deep learning by utilizing a dyke hydrological artificial intelligence algorithm based on the stratum feature matrix, and generating a dyke hydrological data model flow chart;
step S43: based on a dyke hydrological data model flow chart, constructing a physical sequence flow by utilizing a dyke danger coefficient analysis formula, and generating a dyke hidden danger detection model;
step S44: performing triple data fusion by utilizing a characteristic engineering method based on a dyke hidden danger detection model to generate a dyke comprehensive decision support frame;
Step S45: and carrying out dyke data fusion based on the dyke comprehensive decision support frame to construct the dyke comprehensive decision support system.
According to the invention, the stratum characteristic matrix is extracted by an image processing algorithm to generate stratum characteristic matrix, so that information of stratum around the embankment can be accurately and efficiently obtained, a foundation is established for subsequent detection of the hidden danger of the embankment, the accuracy and the efficiency of detection are improved, model training can be carried out by combining a data-driven thought through embankment deep learning, the detection accuracy is greatly improved, an upstream cloud data set and a downstream high-definition remote sensing image of the embankment are fully utilized, so that detection data are more accurate and reliable, the hidden danger of the embankment can be more comprehensively grasped by processing and analyzing the acquired data according to an analysis formula of the danger coefficient of the embankment, thereby providing more reliable data support for subsequent detection, the reliability and the accuracy of the data can be improved by utilizing data in different fields through triad data fusion, the safety of the embankment can be more comprehensively evaluated, meanwhile, the accuracy of the model can be improved, more meaningful data characteristics can be mined, the comprehensive decision support system of the embankment can be utilized to fuse data and parameterize, the detection result can be more easily understood and supported, and the safety management of the embankment can be more accurately and comprehensively evaluated.
Preferably, the embankment risk coefficient analysis formula in step S43 is specifically:
wherein FS is the safety factor of the embankment, W is the weight of water content of unit soil in a embankment hydrological data model, beta is the slope of the embankment, C is the unit weight of soil, gamma is the unit weight of water, D is the depth of water, ks is the slope of a rock substrate, s is the sub-surface pressure coefficient, i is the extension coefficient of the embankment top, tz is the wave period, do is the soil type and intensity coefficient of the embankment, sin beta represents the acting force of water on the embankment surface, ccos beta represents the gravity action of soil in the vertical direction, (1-sin beta) represents the resultant force of water and soil above the embankment body, kssin beta represents the downward acting force of the rock substrate.
The invention provides a calculation formula for analyzing a dike danger coefficient, which fully considers the weight of water in soil with W as a unit, beta as the slope gradient of a dike, C as the unit weight of soil, gamma as the unit weight of water, D as the depth of water, ks as the slope of a rock substrate, s as a sub-surface pressure coefficient, C as the coefficient of the extension of the dike, tz as the wave period, do as the soil type and intensity coefficient of the dike, sin beta as the acting force of water on the dike surface, ccos beta as the gravity action of soil in the vertical direction, (1-sin beta) gamma D as the resultant force of water and soil above the dike body, kssin beta as the acting force of rock substrate downwards, and by W (sin beta+Ccos beta) calculating the acting force of water and soil on the dike surface, including the weight of water and the gravity action of soil in the vertical direction, (1-sin beta) gamma D as the resultant force of water and soil above the dike surface, including the pressure of water and the soil resistance of the dike surface, kssin beta as the acting force of rock substrate downwards, kssin beta as the acting force of rock substrate can be more accurately calculated and the stability of the dike surface and the wave coefficient and the stability of the dike surface can be evaluated, and the stability factor of the dike can be more comprehensively considered.
In one embodiment of the present specification, there is provided a data set-based state analysis system comprising
At least one processor;
a memory communicatively coupled to the at least one processor; wherein, the liquid crystal display device comprises a liquid crystal display device,
the memory stores a computer program executable by the at least one processor to enable the at least one processor to perform the data set based state analysis method as described above.
The invention provides a physical detection-based hidden danger investigation and analysis system, which utilizes a physical detection technology to carry out investigation and analysis on hidden danger of a embankment, can improve the safety and stability of the embankment, avoid disaster accidents such as flood and the like, protect life and property safety of people, can carry out investigation on the embankment with large area in a shorter time, greatly improve investigation efficiency, can automatically carry out investigation and analysis process, reduces the cost of manual operation and the risk of personnel, improves the resource utilization efficiency, and can monitor and early warn the situation of the hidden danger of the embankment in real time, timely take measures to repair and strengthen the disaster accident caused by the hidden danger of the embankment, thereby effectively preventing the occurrence of the disaster accident caused by the hidden danger of the embankment.
Drawings
FIG. 1 is a flow chart illustrating steps of a state analysis method based on a data set according to the present application;
FIG. 2 is a detailed implementation step flow diagram of step S1;
fig. 3 is a detailed implementation step flow diagram of step S2.
Detailed Description
It should be understood that the specific embodiments described herein are for purposes of illustration only and are not intended to limit the scope of the application.
The embodiment of the application provides a state analysis method and a state analysis system based on a data set. The execution main body of the embankment hidden danger investigation and analysis method and system comprises but is not limited to a system carrying the system: mechanical devices, data processing platforms, cloud server nodes, network transmission devices, etc. may be considered general purpose computing nodes of the present application, including but not limited to: at least one of an audio image management system, an information management system and a cloud data management system.
Referring to fig. 1 to 3, the present application provides a state analysis method based on a data set, the method comprising the following steps:
step S1: the method comprises the steps of detecting formation lithology of a dike by using a laser radar to obtain a multi-dimensional data set of the dike, wherein the multi-dimensional data set comprises a formation lithology data set, a dike profile data set and a terrain height data set, and performing three-dimensional visualization processing on the multi-dimensional data set by using GIS software to construct a formation analysis chart;
Step S2: according to the stratum analysis chart, monitoring and analyzing the downstream hydrological data of the embankment by using the unmanned ship and the submersible to obtain a downstream high-definition remote sensing image of the embankment;
step S3: acquiring a dike upstream real-time multi-mode data set by using a dike upstream sensor according to a dike downstream high-definition remote sensing image, and performing dike cloud aggregation operation on the dike upstream real-time multi-mode data set to generate a dike cloud data set;
step S4: based on the upstream cloud data set and the downstream high-definition remote sensing image of the dike, the dike comprehensive decision support system is constructed by utilizing the dike hydrologic artificial intelligent algorithm, so that the omnibearing and multilayer monitoring and investigation of the hidden danger state of the dike are realized.
The invention provides a state analysis method based on a data set, which utilizes a stratum lithology data set, a dike profile data set, a terrain height data set and GIS software to carry out three-dimensional visualization processing on the multi-dimensional data set, constructs a stratum analysis chart, thereby improving the accuracy and the range of dike monitoring, utilizes an unmanned ship and a submersible to carry out dike downstream hydrological data monitoring analysis through the stratum analysis chart, generates a dike downstream high-definition remote sensing image, integrates data to carry out comprehensive analysis, provides decision support, and can carry out dike gathering operation based on the stratum analysis chart and the dike downstream high-definition remote sensing image to generate a dike cloud data set, and utilizes a dike hydrological artificial intelligent algorithm to construct a dike comprehensive decision support system through the dike cloud data set, so that the full-dimensional and multi-level monitoring and investigation of the dike hidden danger state is realized.
In the embodiment of the present invention, as described with reference to fig. 1, a flow chart of steps of a state analysis method based on a data set of the present invention is shown, where in this example, the steps of the state analysis method based on a data set include:
step S1: the method comprises the steps of detecting formation lithology of a dike by using a laser radar to obtain a multi-dimensional data set of the dike, wherein the multi-dimensional data set comprises a formation lithology data set, a dike profile data set and a terrain height data set, and performing three-dimensional visualization processing on the multi-dimensional data set by using GIS software to construct a formation analysis chart;
in the embodiment of the invention, for example, laser radar equipment is used for emitting laser beams for scanning, the formation lithology detection is carried out on the embankment to obtain an embankment multidimensional data set, the embankment multidimensional data set comprises the formation lithology data set, the embankment contour data and the topography height data, the original data obtained from the laser radar equipment is preprocessed, the data denoising, the data filtering and the data registering are carried out, the accurate original data are obtained through the processes, on the basis of the original data, the formation lithology information is extracted by combining the results of field investigation, the literature data such as geological maps and formation columns and the like and by using a computer algorithm and a manual interpretation method to form a formation data set, the formation lithology data set, the embankment contour data set, the topography height data set and other multidimensional data sets are integrated, data format conversion and data correction are carried out, GIS software is used for carrying out three-dimensional visualization processing on the embankment multidimensional data set, and the multidimensional data sets such as the formation lithology data set, the embankment contour data set, the topography height data set and the topography height data set are spatially superimposed to form formation analysis maps with different colors, different heights and different thicknesses, so that the formation analysis maps of the embankment map is generated.
Step S2: according to the stratum analysis chart, monitoring and analyzing the downstream hydrological data of the embankment by using the unmanned ship and the submersible to obtain a downstream high-definition remote sensing image of the embankment;
in the embodiment of the invention, for example, equipment such as a surveying instrument is utilized to carry out stratum analysis in a region needing to be monitored, various data related to geological structures of the region are obtained, a monitoring module table is generated, unmanned ships and submarines are utilized to provide remote control for ferrying by calling a control system of a remote sensing cloud platform based on the monitoring module table, a control system of the remote sensing cloud platform is utilized to provide carrying detection equipment to extract monitoring point parameter data, a downstream water detection data table of the embankment is generated, a computer is utilized to carry out image processing on the data according to the downstream water detection data table of the embankment, a primary downstream remote sensing data set is generated, and a pixel classification calculation is carried out by utilizing a pixel-level iteration classifier method based on the primary downstream remote sensing data set of the embankment, so that a downstream high-definition remote sensing image of the embankment is generated.
Step S3: acquiring a dike upstream real-time multi-mode data set by using a dike upstream sensor according to a dike downstream high-definition remote sensing image, and performing dike cloud aggregation operation on the dike upstream real-time multi-mode data set to generate a dike cloud data set;
In the embodiment of the invention, for example, a sensor is deployed at the upstream of the embankment, the sensor can comprise but is not limited to a meteorological sensor, a hydrological sensor, a geological sensor and other various types, an upstream monitoring area of the embankment is built, real-time multi-modal data at the upstream of the embankment is obtained through the sensor of the embankment, a real-time multi-modal data set at the upstream of the embankment is generated, a high-definition remote sensing image at the downstream of the embankment is obtained through the sensor at the upstream of the embankment, a real-time multi-modal model at the upstream of the embankment is generated through deep learning and other technologies, homomorphic encryption is carried out on the built real-time multi-modal model, the original data set is converted into a homomorphic ciphertext data set, confidentiality and security of data are guaranteed, cloud data gathering processing is carried out on the homomorphic ciphertext data sets, the cloud data processing technology and the cloud data processing and data analysis are carried out on data from different sources to generate the embankment data set.
Step S4: based on the upstream cloud data set and the downstream high-definition remote sensing image of the dike, the dike comprehensive decision support system is constructed by utilizing the dike hydrologic artificial intelligent algorithm, so that the omnibearing and multilayer monitoring and investigation of the hidden danger state of the dike are realized.
In the embodiment of the invention, for example, the data acquired by various sensors are uploaded to a cloud in real time by using a sensing data acquisition technology, the characteristics of the surrounding environment of the embankment are extracted by using an image processing technology aiming at the high-definition remote sensing image at the downstream of the embankment, including various vegetation, roads, buildings and the like, meanwhile, the condition inside the embankment is scanned by using the remote sensing technology, the condition inside the embankment is known, then, the data at the upstream and downstream of the embankment are analyzed and processed by using an embankment hydrologic artificial intelligence algorithm, the characteristic information related to the embankment is extracted, the security assessment of the embankment is carried out according to the characteristic information of the embankment, the early warning and the investigation of the hidden danger of the embankment are realized, finally, the comprehensive decision support system of the embankment is constructed, the hidden danger problems of the embankment are all-round and multi-layer monitored and the hidden danger state of the embankment are timely found and early-warned, and effective decision support is provided for an embankment manager.
In the embodiment of the present invention, as described with reference to fig. 2, a detailed implementation step flow diagram of the step S1 is shown, and in one embodiment of the present specification, the detailed implementation step of the step S1 includes:
step S11: performing stratum lithology multidimensional detection on the embankment by using a laser radar to obtain a stratum multidimensional data set of the embankment;
Step S12: carrying out data-driven modeling on the multi-dimensional data set of the embankment stratum based on a geostatistical method to generate a three-dimensional embankment physical model;
step S13: performing three-dimensional visualization processing by using GIS software based on the three-dimensional dike physical model, and constructing a dike data visualization view;
step S14: and carrying out machine vision recognition analysis on the visual view of the embankment data by using a machine vision recognition algorithm to construct a stratum analysis chart.
The invention provides a method for analyzing a dike stratum, which is characterized in that the multi-dimensional detection of the stratum lithology of the dike is carried out by a laser radar, a multi-dimensional data set of the dike stratum is generated, the multi-dimensional data set of the dike stratum is subjected to data driving modeling by a geostatistical method, a three-dimensional physical model of the dike is generated, on the basis, three-dimensional visual processing is carried out by GIS software, a dike data visual view is constructed, visual expression is provided for the dike stratum analysis, and meanwhile, the machine visual recognition algorithm is utilized for machine visual recognition, and a stratum analysis graph is generated by analyzing the dike data visual view.
In the embodiment of the invention, the laser radar is used for transmitting laser beams to scan the embankment to obtain embankment stratum data, the data acquisition module is used for acquiring the embankment stratum data, the acquired data are uploaded to the data processing module, the data processing module is used for screening, processing and arranging the acquired data based on an algorithm to form an embankment stratum multi-dimensional dataset, the data importing module is used for receiving the embankment stratum multi-dimensional dataset, the data are transmitted to the geological data modeling module, the geological data modeling module is used for carrying out data mining and modeling based on a geostatistical method to generate a three-dimensional embankment physical model, the model output module is used for outputting the generated three-dimensional embankment physical model, the data processing module is used for carrying out secondary processing and processing on the three-dimensional embankment physical model based on GIS software to form an embankment data visualization view, the data are transmitted to the image decomposing module, the image decomposing module is used for carrying out image decomposition on the embankment data visualization view based on an image processing technology to form a plurality of sub-images, the feature extraction module is used for carrying out feature extraction on each sub-image based on a machine vision recognition algorithm to obtain feature vectors, and all the feature vectors of the sub-image are analyzed by using the feature vector analysis module to obtain the feature vector of the stratum analysis.
In one embodiment of the present specification, the specific steps of step S12 are as follows:
step S121: carrying out data cleaning on the stratum multidimensional data set to generate a dyke standardized data set;
step S122: analyzing and calculating variation coefficients of the dike normalized data set by using a multivariate statistical analysis method to generate a dike multivariate analysis data set;
step S123: performing geological difference calculation by using a geostatistical spatial interpolation method based on the dike multivariate analysis data set to generate a stratum data warehouse;
step S124: performing simulation analysis by utilizing numerical simulation based on the stratum data warehouse to generate a embankment three-dimensional physical model;
according to the invention, the problems of nonstandard and incomplete formation data in the prior art are effectively solved by carrying out data cleaning and dyke standardized data set generation on the formation multidimensional data set, the variation coefficient analysis calculation is carried out on the dyke standardized data set by utilizing a multivariate statistical analysis method, the accuracy and the efficiency of data analysis are improved on the premise of ensuring the data quality, the geological difference calculation is carried out on the dyke multivariate analysis data set by utilizing a geostatistical spatial interpolation method, and the generated formation data warehouse has higher geological precision and reliability; and the numerical simulation analysis is carried out based on the stratum data warehouse, so that the generated embankment three-dimensional physical model can more accurately simulate the embankment structure, and the flood control and disaster prevention capabilities and safety are improved.
In the embodiment of the invention, for example, a data acquisition module is used for acquiring multi-dimensional data of a dike stratum, the acquired data are transmitted to a data cleaning module, a normalized dike data set is obtained through data preprocessing and cleaning operation by the data cleaning module, the normalized dike data set is received by a data importing module, the data are transmitted to a multivariate statistical analysis module, the dike normalized data set is analyzed by the multivariate statistical analysis module based on a variation coefficient analysis calculation method to generate a dike multivariate analysis data set, an analysis output module outputs the generated dike multivariate analysis data set, the data are transmitted to a geostatistical spatial interpolation module, the generated dike multivariate analysis data set is subjected to interpolation processing by the geostatistical spatial interpolation module based on a spatial interpolation method to obtain a stratum data warehouse, the generated stratum data warehouse is stored in a database by a warehouse generating module, and a dike three-dimensional physical model is constructed by a model constructing module based on the stratum data warehouse and a modeling principle.
In the embodiment of the present invention, as described with reference to fig. 3, a detailed implementation step flow diagram of step S2 is shown, and in one embodiment of the present specification, the detailed implementation step of step S2 includes:
Step S21: dividing monitoring areas according to the stratum analysis chart to generate a monitoring module table;
step S22: according to the monitoring module list, extracting monitoring point parameter data by using unmanned ships and submersible carrying detection equipment, and generating a downstream water detection data list of the embankment;
step S23: carrying out regression calculation on the downstream hydrological detection data table of the dike by using a downstream regression analysis calculation formula of the dike to generate a primary downstream remote sensing data set of the dike;
step S24: and performing pixel classification calculation by using a pixel-level iterative classifier method based on the primary dike downstream remote sensing data set to obtain a dike downstream high-definition remote sensing image.
According to the method, the monitoring area is divided based on the stratum analysis graph, the monitoring area is definitely divided, the monitoring precision and the monitoring efficiency are improved, meanwhile, the generation of the monitoring module table is convenient for the extraction and management of follow-up monitoring point parameter data, the unmanned ship and the submersible carrier detection equipment are utilized for carrying out the monitoring point parameter data extraction operation, the hydrological data table can be obtained, the information can be used for analyzing the hydrological environment of the downstream of the embankment, the accuracy of monitoring is improved, the prediction and the evaluation of key parameters such as the water level and the flow of the downstream of the embankment are facilitated, the regression calculation is carried out through the regression analysis calculation formula of the downstream of the embankment, the primary embankment downstream remote sensing data set can be obtained, the inversion of surface coverage characteristic information is facilitated based on the primary embankment downstream remote sensing data set, the important data basis is provided for the follow-up pixel level iterative classifier, the method can be used for carrying out the pixel classification calculation of the primary embankment downstream remote sensing data set, the downstream of the embankment high-definition remote sensing image can be obtained, the downstream area of the embankment is predicted, the downstream area is well-land and the land quality of the downstream of the embankment is well-down, the monitoring quality is improved, the accurate monitoring condition is improved, the risk is well-down, the monitoring method is improved, and the risk is well-down is improved, and the monitoring is well-down, and the risk is well-down.
In the embodiment of the invention, a monitoring area is divided into a plurality of monitoring modules by using a dike downstream stratum analysis chart, a monitoring module table is generated, monitoring points are periodically acquired by using unmanned ships and submersible carrying detection equipment according to the monitoring module table, parameters such as water level, flow speed, water temperature and the like of the monitoring points are acquired through an image processing technology, data are stored in the dike downstream hydrological detection data table, regression calculation is carried out on the basis of a dike downstream regression analysis calculation formula and the dike downstream hydrological detection data table to obtain a primary dike downstream remote sensing data set, wherein the primary dike downstream remote sensing data set comprises parameter data such as water depth, sediment concentration, water transparency, water temperature, color and the like, image preprocessing is carried out by using a pixel-level iterative classifier method according to the primary dike downstream remote sensing data set, such as edge extraction, average filtering and the like, a downstream dike high-definition remote sensing image is finally obtained, and characteristic information of the image is obtained by using a characteristic extraction algorithm such as principal component analysis, wavelet transformation and the like, and further such as a downstream quality image is classified by a support vector, such as a K-nearest neighbor, and the like.
In the embodiment of the invention, in the step S23, the downstream regression analysis calculation formula of the embankment is specifically:
NDVI＝(NIR-RED)/(NIR+RED)；
NDBI＝(SWIR-NIR)/(SWIR+NIR)；
wherein SF is the safety coefficient of the embankment, T n For the embankment terrain adjustment coefficient, n is the size of a fragmented terrain model data set, H is the water level height, HC is the elevation of the embankment roof, DC is the vertical distance from the downstream side of the embankment roof to the river bed, NDVI is the normalized vegetation index, x i Abscissa data of embankment terrain detection points from unmanned ships and submarines, y i For the ordinate data of the embankment terrain detection points from the unmanned ship and the submersible, NDBI is a normalized building index, NIR is a reflection value of a near infrared band, RED is a reflection value of a RED band, and SWIR is a reflection value of a short wave infrared band.
The invention provides a downstream regression analysis calculation formula of a embankment, which can effectively evaluate the flood fighting capacity of the embankment through setting up a safety coefficient SF, reduce the safety risk caused by the influence of factors such as water level height, embankment elevation, relative height and the like, thereby improving the safety performance of the embankment and adjusting the coefficient T of the embankment topography n The introduction of the method can detect and evaluate under different embankment topography conditions, so as to accurately judge the security of the embankment, adjust related parameters, improve the security of the embankment, normalize the application of vegetation index NDVI and evaluate the embankment The vegetation coverage condition along the line is monitored, the ecological environment condition around the embankment is mastered in time by monitoring the change of the vegetation index, so that the effect of vegetation on the stability play of the embankment is judged, a scientific basis is provided for embankment management and maintenance, the building density and the height of the embankment to a river can be estimated by normalizing the application of the building index NDBI, and further, the safety risks of the surrounding buildings of the embankment on the embankment are judged, a beneficial reference is provided for embankment management and planning, and the topography condition of the embankment can be better reflected by using the multi-wavelength reflection value in a combined way.
In one embodiment of the present specification, step S3 includes the steps of:
step S31: performing deployment operation of a dike upstream sensor according to a dike downstream high-definition remote sensing image, and building a dike upstream monitoring area;
step S32: monitoring the upstream real-time multi-modal data of the dike according to the upstream monitoring area of the dike, and generating a real-time multi-modal data set of the upstream of the dike;
step S33: performing sequence calculation on the upstream real-time multi-mode data set of the dike by using a dike upstream sequence weight analysis and calculation formula to generate an upstream real-time multi-mode model of the dike;
step S34: performing model homomorphic encryption based on the upstream real-time multi-mode model of the embankment to generate homomorphic ciphertext data sets;
Step S35: and carrying out cloud data aggregation processing based on the homomorphic ciphertext data set to generate a dike cloud data set.
The invention determines the position and the range of the upstream monitoring area of the embankment according to the downstream high-definition remote sensing image of the embankment, designs a sensor deployment scheme of the upstream monitoring area of the embankment, comprises sensor types, quantity, positions and the like, performs wiring, installation and debugging of the sensor according to the sensor deployment scheme, ensures that the sensor can work normally, builds a data acquisition, transmission and processing system of the upstream monitoring area of the embankment, processes and stores the data acquired by the sensor, performs real-time data acquisition on each sensor in the upstream monitoring area of the embankment, integrates and processes the data acquired by a plurality of sensors, generates a real-time multi-mode data set of the upstream of the embankment, performs preprocessing such as data cleaning, denoising, filtering and the like, improves the data quality and accuracy, and according to the real-time data set and preprocessing result, the method comprises the steps of extracting characteristics of data to obtain characteristic vectors, carrying out sequence calculation on the characteristic vectors by utilizing a sequence weight analysis calculation formula to generate sequence weights, modeling by utilizing methods such as machine learning and the like according to the sequence weights and the characteristic vectors to generate a real-time multi-mode model at the upstream of a dike, encrypting the model according to the existing real-time multi-mode model at the upstream of the dike by adopting a homomorphic encryption algorithm, applying the encrypted model to a real-time data set to generate a homomorphic ciphertext data set, uploading the homomorphic ciphertext data set to a cloud server, carrying out decryption and aggregation processing on the homomorphic ciphertext data set on the cloud server to obtain the cloud data set, analyzing and processing the cloud data set to extract useful information such as indexes of water level, flow rate, rainfall and the like at the upstream of the dike, and carrying out data visualization and display.
In one example of the present specification, the upstream-dike sequence weight analysis calculation formula in step S33 is specifically:
wherein Q is a time series weight analysis coefficient of the upstream of the embankment, P is rainfall, K1 is a regression weight coefficient of a first observation point, T is time, T1 is a hysteresis error coefficient of the first observation point, K2 is a regression weight coefficient of a 2 nd observation point, T2 is a hysteresis error coefficient of a second observation point, K3 is a fixed water capacity coefficient of the upstream land, K4 is the area of an upstream basin of the embankment, and A is the area of a downstream basin of the embankment.
The invention provides a calculation formula for analyzing the upstream sequence weight of a dike, which fully considers that P is rainfall, K1 is a regression weight coefficient of a first observation point, T is time, T1 is a hysteresis error coefficient of the first observation point, K2 is a regression weight coefficient of a 2 nd observation point, T2 is a hysteresis error coefficient of a second observation point, and K3 is upstream landThe water capacity coefficient is fixed, the area of the upstream flow field of the K4 embankment is the area of the upstream flow field of the embankment, the formula contains various factors influencing the stability of the embankment, the acting force and resultant force of the factors such as water, soil, rock substrate and the like are involved, the acting force and resultant force of the water and the soil are calculated through K3 x exp (-K4 x A), the stability of the embankment can be estimated more comprehensively and accurately, the method is beneficial to guiding engineering design and inspection, the design quality of the embankment is improved, The contribution of the second observation point to the weight coefficient is represented, wherein the sine function with the regression weight coefficient K2 and the hysteresis error coefficient T2 is multiplied by the factors related to the fixed water capacity K3 of the upstream land and the upstream flow field area K4 of the dykes and dams, and the influence of the slope of the dykes and the soil type of the dykes on the stability of the dykes is considered by analyzing the action aspects of the slope of the dykes and the soil type of the dykes, so that the influence degree of the factors on the stability of the dykes can be analyzed more comprehensively, and a beneficial reference is provided for optimizing engineering design and reinforcing protective measures.
In one embodiment of the present specification, step S4 includes the steps of:
step S41: performing stratum feature extraction by using an image processing algorithm based on the upstream cloud data set and the downstream high-definition remote sensing image of the dike to generate a stratum feature matrix;
step S42: performing dyke deep learning by utilizing a dyke hydrological artificial intelligence algorithm based on the stratum feature matrix, and generating a dyke hydrological data model flow chart;
step S43: based on a dyke hydrological data model flow chart, constructing a physical sequence flow by utilizing a dyke danger coefficient analysis formula, and generating a dyke hidden danger detection model;
step S44: performing triple data fusion by utilizing a characteristic engineering method based on a dyke hidden danger detection model to generate a dyke comprehensive decision support frame;
Step S45: and carrying out dyke data fusion based on the dyke comprehensive decision support frame to construct the dyke comprehensive decision support system.
According to the invention, the stratum characteristic matrix is extracted by an image processing algorithm to generate stratum characteristic matrix, so that information of stratum around the embankment can be accurately and efficiently obtained, a foundation is established for subsequent detection of the hidden danger of the embankment, the accuracy and the efficiency of detection are improved, model training can be carried out by combining a data-driven thought through embankment deep learning, the detection accuracy is greatly improved, an upstream cloud data set and a downstream high-definition remote sensing image of the embankment are fully utilized, so that detection data are more accurate and reliable, the hidden danger of the embankment can be more comprehensively grasped by processing and analyzing the acquired data according to an analysis formula of the danger coefficient of the embankment, thereby providing more reliable data support for subsequent detection, the reliability and the accuracy of the data can be improved by utilizing data in different fields through triad data fusion, the safety of the embankment can be more comprehensively evaluated, meanwhile, the accuracy of the model can be improved, more meaningful data characteristics can be mined, the comprehensive decision support system of the embankment can be utilized to fuse data and parameterize, the detection result can be more easily understood and supported, and the safety management of the embankment can be more accurately and comprehensively evaluated.
According to the embodiment of the invention, various environmental data acquired by various sensors at different positions are utilized, the data are preprocessed through an image processing algorithm, the image data are converted into a digital matrix, stratum characteristic information is extracted, the stratum characteristic information is integrated with the environmental data to generate a stratum characteristic matrix, the stratum characteristic matrix is input into an artificial intelligent algorithm, the stratum characteristic matrix is processed and a hydrologic data model is established, the levee hydrologic artificial intelligent algorithm is utilized for carrying out levee deep learning, a levee hydrologic data model flow chart is generated, a levee hazard detection model is generated based on the levee hydrologic data model flow chart, a physical sequence flow construction is carried out through a levee hazard coefficient analysis formula, a characteristic engineering method is adopted for carrying out triple data fusion based on the result output by the levee hazard detection model and other related data, a levee comprehensive decision support frame is generated, the result output by the levee comprehensive decision support frame is fused with other data sources, such as manual inspection data, internet of things data, historical monitoring data and the like, the data are stored in a database, and the data is visually presented through an application program, so that the construction of the levee comprehensive decision support system is realized.
In one example of the present specification, the embankment risk coefficient analysis calculation formula in step S43 is specifically:
wherein FS is the safety factor of the embankment, W is the weight of water content of unit soil in a embankment hydrological data model, beta is the slope of the embankment, C is the unit weight of soil, gamma is the unit weight of water, D is the depth of water, ks is the slope of a rock substrate, s is the sub-surface pressure coefficient, i is the extension coefficient of the embankment top, tz is the wave period, do is the soil type and intensity coefficient of the embankment, sin beta represents the acting force of water on the embankment surface, ccos beta represents the gravity action of soil in the vertical direction, (1-sin beta) represents the resultant force of water and soil above the embankment body, kssin beta represents the downward acting force of the rock substrate.
The invention provides a calculation formula for analyzing a dike danger coefficient, which fully considers the weight of water in soil with W as a unit, beta as the slope gradient of a dike, C as the unit weight of soil, gamma as the unit weight of water, D as the depth of water, ks as the slope of a rock substrate, s as a sub-surface pressure coefficient, C as the coefficient of the extension of the dike, tz as the wave period, do as the soil type and intensity coefficient of the dike, sin beta as the acting force of water on the dike surface, ccos beta as the gravity action of soil in the vertical direction, (1-sin beta) gamma D as the resultant force of water and soil above the dike body, kssin beta as the acting force of rock substrate downwards, and by W (sin beta+Ccos beta) calculating the acting force of water and soil on the dike surface, including the weight of water and the gravity action of soil in the vertical direction, (1-sin beta) gamma D as the resultant force of water and soil above the dike surface, including the pressure of water and the soil resistance of the dike surface, kssin beta as the acting force of rock substrate downwards, kssin beta as the acting force of rock substrate can be more accurately calculated and the stability of the dike surface and the wave coefficient and the stability of the dike surface can be evaluated, and the stability factor of the dike can be more comprehensively considered.
In one embodiment of the present specification, there is provided a data set-based state analysis system comprising
A processor;
a memory communicatively coupled to the at least one processor; wherein, the liquid crystal display device comprises a liquid crystal display device,
the memory stores a computer program executable by the at least one processor, the computer program being executable by the at least one processor
At least one processor executing such that the at least one processor is capable of performing a method of bank potential troubleshooting analysis as described above.
The invention provides a state analysis system based on a data set, which utilizes a physical detection technology to carry out investigation and analysis on the hidden danger of a embankment, can improve the safety and stability of the embankment, avoid disaster accidents such as flood and the like, can carry out investigation on the embankment with a large area in a shorter time, greatly improves the investigation efficiency, can automatically carry out the investigation and analysis process, reduces the cost of manual operation and the risk of personnel, improves the resource utilization efficiency, and can monitor and early warn the situation of the hidden danger of the embankment in real time, timely take measures to repair and strengthen the situation of the hidden danger of the embankment, thereby effectively preventing the disaster accidents caused by the hidden danger of the embankment.
The present embodiments are, therefore, to be considered in all respects as illustrative and not restrictive, the scope of the invention being indicated by the appended claims rather than by the foregoing description, and all changes which come within the meaning and range of equivalency of the claims are therefore intended to be embraced therein.
It will be understood that, although the terms "first," "second," etc. may be used herein to describe various elements, these elements should not be limited by these terms. These terms are only used to distinguish one element from another element. For example, a first element could be termed a second element, and, similarly, a second element could be termed a first element, without departing from the scope of example embodiments. The term "and/or" as used herein includes any and all combinations of one or more of the associated listed items.
The foregoing is only a specific embodiment of the invention to enable those skilled in the art to understand or practice the invention. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the generic principles defined herein may be applied to other embodiments without departing from the spirit or scope of the invention. Thus, the present invention is not intended to be limited to the embodiments shown herein but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.
Claims (10)
1. A method of state analysis based on a data set, comprising the steps of:
step S1: performing stratum lithology detection on the embankment by using a laser radar to obtain an embankment multidimensional data set, wherein the embankment multidimensional data set comprises a stratum lithology data set, an embankment contour data set and a terrain height data set, and performing three-dimensional visualization processing on the multidimensional data set by using GIS software to construct a stratum analysis chart;
step S2: according to the stratum analysis chart, monitoring and analyzing the downstream hydrological data of the embankment by using the unmanned ship and the submersible to obtain a downstream high-definition remote sensing image of the embankment;
step S3: acquiring a dike upstream real-time multi-mode data set by using a dike upstream sensor according to a dike downstream high-definition remote sensing image, and performing dike cloud aggregation operation on the dike upstream real-time multi-mode data set to generate a dike cloud data set;
step S4: based on the upstream cloud data set and the downstream high-definition remote sensing image of the dike, the dike comprehensive decision support system is constructed by utilizing the dike hydrologic artificial intelligent algorithm, so that the omnibearing and multilayer monitoring and investigation of the hidden danger state of the dike are realized.
2. The method according to claim 1, wherein the specific steps of step S1 are:
Step S11: performing stratum lithology multidimensional detection on the embankment by using a laser radar to obtain a stratum multidimensional data set of the embankment;
step S12: carrying out data-driven modeling on the multi-dimensional data set of the embankment stratum based on a geostatistical method to generate a three-dimensional embankment physical model;
step S13: performing three-dimensional visualization processing by using GIS software based on the three-dimensional dike physical model, and constructing a dike data visualization view;
step S14: and performing machine vision recognition analysis on the visual view of the embankment data by using a machine vision recognition algorithm to construct a stratum analysis chart.
3. The method according to claim 2, wherein the specific steps of step S12 are:
step S121: carrying out data cleaning on the stratum multidimensional data set to generate a dyke standardized data set;
step S122: analyzing and calculating variation coefficients of the dike normalized data set by using a multivariate statistical analysis method to generate a dike multivariate analysis data set;
step S123: performing geological difference calculation by using a geostatistical spatial interpolation method based on the dike multivariate analysis data set to generate a stratum data warehouse;
step S124: and performing simulation analysis by utilizing numerical simulation based on the stratum data warehouse to generate the embankment three-dimensional physical model.
4. The method according to claim 2, wherein the specific steps of step S2 are:
step S21: dividing monitoring areas according to the stratum analysis chart to generate a monitoring module table;
step S22: according to the monitoring module list, extracting monitoring point parameter data by using unmanned ships and submersible carrying detection equipment, and generating a downstream water detection data list of the embankment;
step S23: carrying out regression calculation on the downstream hydrological detection data table of the dike by using a downstream regression analysis calculation formula of the dike to generate a primary downstream remote sensing data set of the dike;
step S24: and performing pixel classification calculation by using a pixel-level iterative classifier method based on the primary dike downstream remote sensing data set to obtain a dike downstream high-definition remote sensing image.
5. The method of claim 4, wherein the downstream dike regression analysis calculation formula in step S23 is specifically:
NDVI＝(NIR-RED)/(NIR+RED)；
NDBI＝(SWIR-NIR)/(SWIR+NIR)；
wherein SF is the safety coefficient of the embankment, T n For the embankment terrain adjustment coefficient, n is the size of a fragmented terrain model data set, H is the water level height, HC is the elevation of the embankment roof, DC is the vertical distance from the downstream side of the embankment roof to the river bed, NDVI is the normalized vegetation index, x i Abscissa data of embankment terrain detection points from unmanned ships and submarines, y i For the ordinate data of the embankment terrain detection points from the unmanned ship and the submersible, NDBI is a normalized building index, NIR is a reflection value of a near infrared band, RED is a reflection value of a RED band, and SWIR is a reflection value of a short wave infrared band.
6. The method according to claim 1, wherein the specific step of step S3 is:
step S31: performing deployment operation of a dike upstream sensor according to a dike downstream high-definition remote sensing image, and building a dike upstream monitoring area;
step S32: monitoring the upstream real-time multi-modal data of the dike according to the upstream monitoring area of the dike, and generating a real-time multi-modal data set of the upstream of the dike;
step S33: performing sequence calculation on the upstream real-time multi-mode data set of the dike by using a dike upstream sequence weight analysis and calculation formula to generate an upstream real-time multi-mode model of the dike;
step S34: performing model homomorphic encryption based on the upstream real-time multi-mode model of the embankment to generate homomorphic ciphertext data sets;
step S35: and carrying out cloud data aggregation processing based on the homomorphic ciphertext data set to generate a dike cloud data set.
7. The method according to claim 6, wherein the upstream time series weight analysis calculation formula of the dike in step S33 is specifically:
Wherein Q is a time series weight analysis coefficient of the upstream of the embankment, P is rainfall, K1 is a regression weight coefficient of a first observation point, T is time, T1 is a hysteresis error coefficient of the first observation point, K2 is a regression weight coefficient of a 2 nd observation point, T2 is a hysteresis error coefficient of a second observation point, K3 is a fixed water capacity coefficient of the upstream land, K4 is the area of an upstream basin of the embankment, and A is the area of a downstream basin of the embankment.
8. The method according to claim 1, wherein the specific step of step S4 is:
step S41: performing stratum feature extraction by using an image processing algorithm based on the upstream cloud data set and the downstream high-definition remote sensing image of the dike to generate a stratum feature matrix;
step S42: performing dyke deep learning by utilizing a dyke hydrological artificial intelligence algorithm based on the stratum feature matrix to generate a dyke hydrological data model;
step S43: according to the embankment hydrological data model, constructing a physical sequence flow by utilizing an embankment danger coefficient analysis formula, and generating an embankment hidden danger detection model;
step S44: performing triple data fusion by utilizing a characteristic engineering method based on a dyke hidden danger detection model to generate a dyke comprehensive decision support frame;
Step S45: and carrying out dyke data fusion based on the dyke comprehensive decision support frame to construct the dyke comprehensive decision support system.
9. The method of claim 8, wherein the bank risk factor analysis formula in step S43 is specifically:
wherein FS is the safety factor of the embankment, W is the weight of water content of unit soil in a embankment hydrological data model, beta is the slope of the embankment, C is the unit weight of soil, gamma is the unit weight of water, D is the depth of water, ks is the slope of rock substrate, s is the sub-surface pressure coefficient, i is the extension coefficient of the embankment top, tz is the wave period, do is the soil type and intensity coefficient of the embankment, sin beta represents the acting force of water on the embankment surface, ccos beta represents the gravity action of soil in the vertical direction, (1-sin beta) gamma D represents the resultant force of water and soil above the embankment body, kssin beta represents the downward acting force of rock substrate.
10. A data set-based state analysis system, comprising:
at least one processor;
a memory communicatively coupled to the at least one processor;
the memory stores a computer program executable by the at least one processor to enable the at least one processor to perform the data set based state analysis method of any one of claims 1 to 9.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310664125.3A CN116843177A (en) | 2023-06-05 | 2023-06-05 | State analysis method and system based on data set |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310664125.3A CN116843177A (en) | 2023-06-05 | 2023-06-05 | State analysis method and system based on data set |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN116843177A true CN116843177A (en) | 2023-10-03 |
Family
ID=88166146
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310664125.3A Pending CN116843177A (en) | 2023-06-05 | 2023-06-05 | State analysis method and system based on data set |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116843177A (en) |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| KR20050037017A (en) * | 2003-10-17 | 2005-04-21 | 주식회사 도래정보시스템 | Combination system for prevention of disasters |
| CN111008941A (en) * | 2019-11-29 | 2020-04-14 | 中国农业科学院农业资源与农业区划研究所 | Agricultural flood disaster range monitoring system and method based on high-resolution satellite remote sensing image |
| CN111866452A (en) * | 2020-06-30 | 2020-10-30 | 河海大学 | Video real-time monitoring system and method for emergency disposal of landslide and barrage dam |
| CN113505546A (en) * | 2021-07-14 | 2021-10-15 | 浙江大禹信息技术有限公司 | Flood risk prediction system |
| CN113886922A (en) * | 2021-10-08 | 2022-01-04 | 河北省水利水电勘测设计研究院集团有限公司 | Spur dike group design method based on big data and field test |
| CN114118677A (en) * | 2021-10-13 | 2022-03-01 | 中通服和信科技有限公司 | Tailing pond risk monitoring and early warning system based on Internet of things |
| CN115854912A (en) * | 2022-11-30 | 2023-03-28 | 国网福建省电力有限公司 | Dam water seepage area recognition device and method based on three-dimensional laser scanning technology |
-
2023
- 2023-06-05 CN CN202310664125.3A patent/CN116843177A/en active Pending
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| KR20050037017A (en) * | 2003-10-17 | 2005-04-21 | 주식회사 도래정보시스템 | Combination system for prevention of disasters |
| CN111008941A (en) * | 2019-11-29 | 2020-04-14 | 中国农业科学院农业资源与农业区划研究所 | Agricultural flood disaster range monitoring system and method based on high-resolution satellite remote sensing image |
| CN111866452A (en) * | 2020-06-30 | 2020-10-30 | 河海大学 | Video real-time monitoring system and method for emergency disposal of landslide and barrage dam |
| CN113505546A (en) * | 2021-07-14 | 2021-10-15 | 浙江大禹信息技术有限公司 | Flood risk prediction system |
| CN113886922A (en) * | 2021-10-08 | 2022-01-04 | 河北省水利水电勘测设计研究院集团有限公司 | Spur dike group design method based on big data and field test |
| CN114118677A (en) * | 2021-10-13 | 2022-03-01 | 中通服和信科技有限公司 | Tailing pond risk monitoring and early warning system based on Internet of things |
| CN115854912A (en) * | 2022-11-30 | 2023-03-28 | 国网福建省电力有限公司 | Dam water seepage area recognition device and method based on three-dimensional laser scanning technology |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108460231A (en) | A kind of bridge builds foster overall process intellectual monitoring assessment early warning decision system and method | |
| Abuodha et al. | Assessing vulnerability of coasts to climate change: A review of approaches and their application to the Australian coast | |
| Xu et al. | BrIM and UAS for bridge inspections and management | |
| Peng et al. | Urban flood mapping with bitemporal multispectral imagery via a self-supervised learning framework | |
| Pradhan | An assessment of the use of an advanced neural network model with five different training strategies for the preparation of landslide susceptibility maps | |
| CN117576581B (en) | Geological exploration remote sensing monitoring method based on image processing | |
| Teodoro et al. | Retrieving TSM concentration from multispectral satellite data by multiple regression and artificial neural networks | |
| Sarp et al. | An approach for detection of buildings and changes in buildings using orthophotos and point clouds: A case study of Van Erriş earthquake | |
| CN116452765A (en) | Strip mine geological modeling system | |
| Yasir et al. | ShipGeoNet: SAR image-based geometric feature extraction of ships using convolutional neural networks | |
| CN116403093B (en) | Multi-source remote sensing interpretation method and device for potential landslide along railway | |
| CN106529600A (en) | SVM-based recognition method of building angular points in high-resolution optical image | |
| Wang et al. | A dynamic marine oil spill prediction model based on deep learning | |
| Kim et al. | A review of UAV integration in forensic civil engineering: From sensor technologies to geotechnical, structural and water infrastructure applications | |
| CN116843177A (en) | State analysis method and system based on data set | |
| Tochamnanvita et al. | Investigation of coastline changes in three provinces of Thailand using remote sensing | |
| Gilvear et al. | Remote sensing: mapping natural and managed river corridors from the micro to the network scale | |
| Collins et al. | Automated Extraction of a Depth-Defined Wave Runup Time Series From Lidar Data Using Deep Learning | |
| Donne et al. | Wave height quantification using land based seismic data with grammatical evolution | |
| Nuyts et al. | A methodology to assess the morphological change of a multilevel beach cusp system and their hydrodynamics: case study of Long Strand, Ireland | |
| Firoozi et al. | Application of Machine Learning in Geotechnical Engineering for Risk Assessment | |
| Lynda | Systematic survey of convolutional neural network in satellite image classification for geological mapping | |
| Kavzoglu et al. | Assessment of environmental change and land degradation using time series of remote sensing images | |
| Huque et al. | Application of remote sensing to study the behavior and dynamics of riverine and coastal chars | |
| Letshwiti | Improving Highwall Monitoring Through Fracture Identification in Open-Pit Mines Using Image Segmentation |
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 |