CN117408536A - AI-based underwater mapping real-time analysis system - Google Patents
AI-based underwater mapping real-time analysis system Download PDFInfo
- Publication number
- CN117408536A CN117408536A CN202311723390.0A CN202311723390A CN117408536A CN 117408536 A CN117408536 A CN 117408536A CN 202311723390 A CN202311723390 A CN 202311723390A CN 117408536 A CN117408536 A CN 117408536A
- Authority
- CN
- China
- Prior art keywords
- module
- analysis
- data
- sub
- risk
- 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
- 238000013507 mapping Methods 0.000 title claims abstract description 44
- 238000010223 real-time analysis Methods 0.000 title claims abstract description 33
- 238000004458 analytical method Methods 0.000 claims abstract description 161
- 238000004422 calculation algorithm Methods 0.000 claims abstract description 93
- 238000005457 optimization Methods 0.000 claims abstract description 83
- 230000004927 fusion Effects 0.000 claims abstract description 65
- 238000012360 testing method Methods 0.000 claims abstract description 63
- 238000013439 planning Methods 0.000 claims abstract description 48
- 238000007726 management method Methods 0.000 claims abstract description 47
- 238000004088 simulation Methods 0.000 claims abstract description 39
- 238000012502 risk assessment Methods 0.000 claims abstract description 29
- 238000012795 verification Methods 0.000 claims abstract description 23
- 230000008859 change Effects 0.000 claims abstract description 19
- 238000013527 convolutional neural network Methods 0.000 claims abstract description 13
- 238000012706 support-vector machine Methods 0.000 claims abstract description 10
- 230000007787 long-term memory Effects 0.000 claims abstract description 8
- 230000006403 short-term memory Effects 0.000 claims abstract description 8
- 238000005516 engineering process Methods 0.000 claims description 88
- 238000011156 evaluation Methods 0.000 claims description 57
- 238000012545 processing Methods 0.000 claims description 54
- 238000000034 method Methods 0.000 claims description 52
- 230000002159 abnormal effect Effects 0.000 claims description 31
- 238000001514 detection method Methods 0.000 claims description 30
- 238000004364 calculation method Methods 0.000 claims description 21
- 238000000638 solvent extraction Methods 0.000 claims description 20
- 238000012300 Sequence Analysis Methods 0.000 claims description 19
- 238000012937 correction Methods 0.000 claims description 17
- 230000007613 environmental effect Effects 0.000 claims description 17
- 238000013210 evaluation model Methods 0.000 claims description 17
- 238000000605 extraction Methods 0.000 claims description 16
- 238000013461 design Methods 0.000 claims description 14
- 230000000694 effects Effects 0.000 claims description 14
- 238000003909 pattern recognition Methods 0.000 claims description 14
- 238000012876 topography Methods 0.000 claims description 14
- 238000000342 Monte Carlo simulation Methods 0.000 claims description 12
- 238000007418 data mining Methods 0.000 claims description 12
- 238000010276 construction Methods 0.000 claims description 11
- 230000008569 process Effects 0.000 claims description 11
- 238000013349 risk mitigation Methods 0.000 claims description 11
- 238000007619 statistical method Methods 0.000 claims description 11
- 238000010801 machine learning Methods 0.000 claims description 10
- 230000007246 mechanism Effects 0.000 claims description 10
- 238000010606 normalization Methods 0.000 claims description 10
- 238000009826 distribution Methods 0.000 claims description 8
- 238000012407 engineering method Methods 0.000 claims description 8
- 230000008713 feedback mechanism Effects 0.000 claims description 8
- 230000010354 integration Effects 0.000 claims description 8
- 230000008901 benefit Effects 0.000 claims description 7
- 238000003066 decision tree Methods 0.000 claims description 7
- 230000000116 mitigating effect Effects 0.000 claims description 7
- 238000013135 deep learning Methods 0.000 claims description 6
- 239000000284 extract Substances 0.000 claims description 6
- 238000005065 mining Methods 0.000 claims description 5
- 230000006399 behavior Effects 0.000 claims description 4
- 238000007727 cost benefit analysis Methods 0.000 claims description 4
- 238000013524 data verification Methods 0.000 claims description 4
- 238000013136 deep learning model Methods 0.000 claims description 4
- 238000000556 factor analysis Methods 0.000 claims description 4
- 230000002068 genetic effect Effects 0.000 claims description 4
- 239000011159 matrix material Substances 0.000 claims description 4
- 230000015654 memory Effects 0.000 claims description 4
- 230000001537 neural effect Effects 0.000 claims description 4
- 238000011056 performance test Methods 0.000 claims description 4
- 230000002265 prevention Effects 0.000 claims description 4
- 230000003449 preventive effect Effects 0.000 claims description 4
- 230000009467 reduction Effects 0.000 claims description 4
- 238000009877 rendering Methods 0.000 claims description 4
- 230000004044 response Effects 0.000 claims description 4
- 230000001932 seasonal effect Effects 0.000 claims description 4
- 238000010206 sensitivity analysis Methods 0.000 claims description 4
- 238000012351 Integrated analysis Methods 0.000 claims description 3
- 230000005856 abnormality Effects 0.000 claims description 3
- 238000007728 cost analysis Methods 0.000 claims description 3
- 238000009472 formulation Methods 0.000 claims description 3
- 238000007689 inspection Methods 0.000 claims description 3
- 239000000203 mixture Substances 0.000 claims description 3
- 238000002360 preparation method Methods 0.000 abstract description 2
- 238000005111 flow chemistry technique Methods 0.000 abstract 1
- 238000005259 measurement Methods 0.000 description 4
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 description 4
- 238000012544 monitoring process Methods 0.000 description 3
- 238000012731 temporal analysis Methods 0.000 description 3
- 238000000700 time series analysis Methods 0.000 description 3
- 230000003044 adaptive effect Effects 0.000 description 2
- 238000003745 diagnosis Methods 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000013473 artificial intelligence Methods 0.000 description 1
- 239000003653 coastal water Substances 0.000 description 1
- 238000010835 comparative analysis Methods 0.000 description 1
- 238000007405 data analysis Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000008676 import Effects 0.000 description 1
- 238000010921 in-depth analysis Methods 0.000 description 1
- 238000005192 partition Methods 0.000 description 1
- 230000008092 positive effect Effects 0.000 description 1
- 238000013468 resource allocation Methods 0.000 description 1
- 239000007787 solid Substances 0.000 description 1
- 230000001360 synchronised effect Effects 0.000 description 1
- 230000009897 systematic effect Effects 0.000 description 1
- 238000012549 training Methods 0.000 description 1
- 238000009827 uniform distribution Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01C—MEASURING DISTANCES, LEVELS OR BEARINGS; SURVEYING; NAVIGATION; GYROSCOPIC INSTRUMENTS; PHOTOGRAMMETRY OR VIDEOGRAMMETRY
- G01C15/00—Surveying instruments or accessories not provided for in groups G01C1/00 - G01C13/00
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01C—MEASURING DISTANCES, LEVELS OR BEARINGS; SURVEYING; NAVIGATION; GYROSCOPIC INSTRUMENTS; PHOTOGRAMMETRY OR VIDEOGRAMMETRY
- G01C21/00—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00
- G01C21/20—Instruments for performing navigational calculations
- G01C21/203—Specially adapted for sailing ships
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/24—Querying
- G06F16/245—Query processing
- G06F16/2458—Special types of queries, e.g. statistical queries, fuzzy queries or distributed queries
- G06F16/2462—Approximate or statistical queries
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/24—Querying
- G06F16/245—Query processing
- G06F16/2458—Special types of queries, e.g. statistical queries, fuzzy queries or distributed queries
- G06F16/2465—Query processing support for facilitating data mining operations in structured databases
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/29—Geographical information databases
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
- G06F18/2411—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches based on the proximity to a decision surface, e.g. support vector machines
-
- 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
- G06F18/24323—Tree-organised classifiers
-
- 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
- G06F18/2433—Single-class perspective, e.g. one-against-all classification; Novelty detection; Outlier detection
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/25—Fusion techniques
- G06F18/251—Fusion techniques of input or preprocessed data
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/26—Discovering frequent patterns
-
- 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
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N20/00—Machine learning
- G06N20/10—Machine learning using kernel methods, e.g. support vector machines [SVM]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/004—Artificial life, i.e. computing arrangements simulating life
- G06N3/006—Artificial life, i.e. computing arrangements simulating life based on simulated virtual individual or collective life forms, e.g. social simulations or particle swarm optimisation [PSO]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/044—Recurrent networks, e.g. Hopfield networks
- G06N3/0442—Recurrent networks, e.g. Hopfield networks characterised by memory or gating, e.g. long short-term memory [LSTM] or gated recurrent units [GRU]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/045—Combinations of networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/0464—Convolutional networks [CNN, ConvNet]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/12—Computing arrangements based on biological models using genetic models
- G06N3/126—Evolutionary algorithms, e.g. genetic algorithms or genetic programming
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N5/00—Computing arrangements using knowledge-based models
- G06N5/01—Dynamic search techniques; Heuristics; Dynamic trees; Branch-and-bound
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N7/00—Computing arrangements based on specific mathematical models
- G06N7/01—Probabilistic graphical models, e.g. probabilistic networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
- G06Q10/047—Optimisation of routes or paths, e.g. travelling salesman problem
-
- 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
- G06Q10/0631—Resource planning, allocation, distributing or scheduling for enterprises or organisations
- G06Q10/06313—Resource planning in a project environment
-
- 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
- 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
- G06Q10/0637—Strategic management or analysis, e.g. setting a goal or target of an organisation; Planning actions based on goals; Analysis or evaluation of effectiveness of goals
- G06Q10/06375—Prediction of business process outcome or impact based on a proposed change
-
- 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
- G06Q10/067—Enterprise or organisation modelling
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/40—Extraction of image or video features
- G06V10/44—Local feature extraction by analysis of parts of the pattern, e.g. by detecting edges, contours, loops, corners, strokes or intersections; Connectivity analysis, e.g. of connected components
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
- G06V10/74—Image or video pattern matching; Proximity measures in feature spaces
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/05—Underwater scenes
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2123/00—Data types
- G06F2123/02—Data types in the time domain, e.g. time-series data
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2216/00—Indexing scheme relating to additional aspects of information retrieval not explicitly covered by G06F16/00 and subgroups
- G06F2216/03—Data mining
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02A—TECHNOLOGIES FOR ADAPTATION TO CLIMATE CHANGE
- Y02A90/00—Technologies having an indirect contribution to adaptation to climate change
- Y02A90/30—Assessment of water resources
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Business, Economics & Management (AREA)
- Data Mining & Analysis (AREA)
- Human Resources & Organizations (AREA)
- General Engineering & Computer Science (AREA)
- Evolutionary Computation (AREA)
- Artificial Intelligence (AREA)
- Life Sciences & Earth Sciences (AREA)
- Software Systems (AREA)
- Strategic Management (AREA)
- Mathematical Physics (AREA)
- Economics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Computing Systems (AREA)
- Entrepreneurship & Innovation (AREA)
- Health & Medical Sciences (AREA)
- Computational Linguistics (AREA)
- Evolutionary Biology (AREA)
- Biophysics (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- General Health & Medical Sciences (AREA)
- Databases & Information Systems (AREA)
- Molecular Biology (AREA)
- Biomedical Technology (AREA)
- Quality & Reliability (AREA)
- Remote Sensing (AREA)
- Tourism & Hospitality (AREA)
- General Business, Economics & Management (AREA)
- Operations Research (AREA)
- Marketing (AREA)
- Game Theory and Decision Science (AREA)
- Development Economics (AREA)
- Educational Administration (AREA)
- Probability & Statistics with Applications (AREA)
- Radar, Positioning & Navigation (AREA)
- Multimedia (AREA)
Abstract
The invention relates to the technical field of underwater surveying and mapping analysis, in particular to an AI-based underwater surveying and mapping real-time analysis system, which comprises a data flow processing module, a multi-source data fusion module, a real-time analysis and identification module, a path optimization and planning module, a risk assessment and management module, a dynamic learning and prediction module, a decision support and optimization module and an environment simulation and test module. In the invention, the convolutional neural network integrates multi-sensor data, so that the accuracy and the comprehensiveness of the data are improved, a support vector machine and incremental learning are adopted for real-time analysis, the terrain feature analysis and target recognition accuracy are improved, an ant colony optimization algorithm optimizes path planning, mapping efficiency and safety are improved, bayesian network risk assessment enhances operation safety, long-term and short-term memory network dynamic learning accurately predicts environment and terrain change, task preparation is optimized, decision support and environment simulation verification strategy reliability and practicality are adopted, and effective decision support is provided.
Description
Technical Field
The invention relates to the technical field of underwater surveying and mapping analysis, in particular to an AI-based underwater surveying and mapping real-time analysis system.
Background
Underwater mapping analysis techniques, commonly referred to as underwater topography or hydrologic measurements, are an application science aimed at accurately measuring and describing topography features, water depths and other important parameters under a body of water, and the field covers a wide geographical range from coastal waters to deep sea areas, including lakes, rivers, oceans, etc. The main applications include making ocean maps, determining channel water depths, ocean resource exploration, environmental monitoring, laying of seabed pipelines and cables, and the like. With the development of the technology, the underwater mapping analysis technology is not only limited to the traditional sonar and water depth measurement, but also comprises advanced remote sensing technology, laser ranging, satellite measurement and the like.
The AI-based underwater mapping real-time analysis system is an advanced underwater mapping tool integrated with artificial intelligence technology. The main purpose is to improve the accuracy and efficiency of underwater mapping, while analyzing the acquired data in real time, providing detailed and accurate underwater topography information at a faster rate. The design of such systems aims to quickly identify topographical features and potential obstructions by automating the processing of complex data sets, thereby improving the speed and quality of data processing. In the fields of marine exploration, submarine pipeline layout, environmental monitoring and the like, the system can greatly improve the decision-making efficiency and accuracy. The main means for realizing the system comprises utilizing various underwater measurement technologies such as sonar sounding, laser ranging, geological radar and the like, and combining with a satellite positioning system for accurate positioning. While the role of AI is mainly reflected in the real-time processing and analysis of data. Through machine learning and data mining techniques, the system can automatically identify patterns, predict trends, and make autonomous decisions even in complex marine environments.
Conventional underwater mapping systems exhibit limitations in many respects. The multi-source data fusion capability is insufficient, and the comprehensiveness and accuracy of data analysis are limited. Real-time analysis and recognition capabilities are limited depending on simple algorithms or manual analysis. The path planning adopts a simple algorithm, and an effective path optimizing scheme is lacked, so that mapping efficiency and safety are affected. Risk assessment and management capabilities are limited, and accurate prediction and control of risks are difficult. Lacking dynamic learning and prediction capabilities, it is difficult to adapt to environmental and terrain changes. The decision support is not scientific and comprehensive enough, and an effective simulation test verification means is lacking, so that the reliability and practicability of the strategy are limited.
Disclosure of Invention
The invention aims to solve the defects in the prior art, and provides an AI-based underwater mapping real-time analysis system.
In order to achieve the above purpose, the present invention adopts the following technical scheme: the AI-based underwater mapping real-time analysis system comprises a data stream processing module, a multi-source data fusion module, a real-time analysis and identification module, a path optimization and planning module, a risk assessment and management module, a dynamic learning and prediction module, a decision support and optimization module and an environment simulation and test module;
The data stream processing module is based on underwater sensor data, adopts Apache Flink or Spark Streaming data processing technology, and combines a time window algorithm to process and analyze real-time data streams to generate standardized data streams;
the multi-source data fusion module integrates data of multiple sensors through a convolutional neural network and generates a fusion data view by adopting a deep learning method and a statistical data fusion technology based on a standardized data stream;
the real-time analysis and recognition module is used for carrying out real-time topography characteristic analysis and target recognition by adopting a machine learning algorithm comprising a support vector machine and incremental learning based on the fusion data view to generate an analysis report;
the path optimization and planning module optimizes the underwater mapping path based on the analysis report by applying an ant colony optimization algorithm to generate an optimized path scheme;
the risk assessment and management module is used for carrying out risk prediction and management through a Bayesian network by applying a risk assessment algorithm based on an optimized path scheme and environment data, and generating a risk management report;
the dynamic learning and prediction module is used for predicting environmental and terrain changes through a long-term and short-term memory network by applying a self-adaptive learning model based on a risk management report to generate a prediction model;
The decision support and optimization module is used for providing a decision support and strategy optimization scheme based on the prediction model and the real-time data and combining an optimization algorithm and a decision tree to generate a decision optimization strategy;
the environment simulation and test module is used for performing policy test and verification in the virtual environment by using simulation software and a test algorithm based on a decision optimization policy and through Monte Carlo simulation, and generating a simulation test report.
As a further aspect of the present invention, the standardized data stream includes formatted, denoised and primarily analyzed data, the fused data view includes integrated analysis of sonar data, satellite imagery and lidar scan results, the analysis report includes topographic structure identification, object classification and abnormal pattern identification, the optimized path scheme includes optimized coverage routes, safe navigation paths and efficiency assessment, the risk management report includes potential risk point assessment, risk probability analysis and mitigation strategies, the prediction model includes environmental trend analysis and topographic dynamic prediction, the decision optimization strategy includes operation scheme, mission planning and execution scheme adjustment, the simulation test report includes scene reproduction effect, strategy execution performance and potential risk identification.
As a further scheme of the invention, the data stream processing module comprises a data partitioning sub-module, a time window sub-module, an error processing sub-module and a data standardization sub-module;
the data partitioning sub-module performs data distribution by adopting a Hash partitioning technology and a dynamic load balancing strategy based on underwater sensor data to generate a partitioned data stream;
the time window sub-module adopts a sliding window algorithm and a time trigger to conduct time sequence processing of the data stream based on the partitioned data stream, and generates a time window data stream;
the error processing submodule carries out error identification and correction by adopting an anomaly detection algorithm and an automatic error correction mechanism based on the time window data stream to generate an error correction data stream;
the data normalization submodule performs data stream normalization processing by adopting a format unification method and a data normalization technology based on the error correction data stream to generate a normalized data stream;
the hash partitioning technique includes hash mapping and partitioning based on data characteristics, the sliding window algorithm includes partitioning data windows and collecting data based on time intervals, and the anomaly detection algorithm includes error discovery and data verification based on pattern recognition.
As a further scheme of the invention, the multi-source data fusion module comprises a multi-source data integration sub-module, a feature extraction sub-module, a depth fusion sub-module and a data integrity inspection sub-module;
the multi-source data integration sub-module integrates different source data by adopting a data fusion framework and a multi-source synchronization mechanism based on a standardized data stream to generate an aggregated data stream;
the feature extraction submodule extracts data features based on the aggregate data stream by adopting a feature engineering method and a statistical analysis technology to generate a feature extraction data stream;
the deep fusion submodule extracts a data stream based on the characteristics, performs data fusion by adopting a convolutional neural network and a deep learning model, and generates a deep fusion data stream;
the data integrity checking submodule verifies the accuracy of data fusion by adopting a data integrity checking algorithm based on the depth fusion data stream to generate a fusion data view;
the data fusion framework comprises data alignment, time synchronization and uniform format, the feature engineering method comprises feature selection, feature extraction and feature dimension reduction, the convolutional neural network specifically realizes analysis of data features through multi-level processing of a neural layer, and the data integrity checking algorithm comprises data integrity checking and consistency checking.
As a further scheme of the invention, the real-time analysis and recognition module comprises a topographic feature analysis sub-module, a target recognition sub-module, an abnormal mode detection sub-module and a real-time feedback sub-module;
the topographic feature analysis submodule carries out topographic feature analysis by adopting a topographic analysis algorithm and a geological modeling technology based on the fusion data view to generate a topographic feature analysis report;
the target recognition submodule carries out target recognition by using an image recognition algorithm and a machine learning model based on the topographic feature analysis report and a support vector machine to generate a target recognition report;
the abnormal pattern detection sub-module is used for carrying out abnormal detection by an isolated forest algorithm based on the target identification report by adopting an abnormal pattern identification technology to generate an abnormal detection report;
the real-time feedback sub-module carries out feedback processing by adopting a real-time data feedback mechanism and a decision support system based on the abnormality detection report to generate an analysis report;
the topographic analysis algorithm comprises digital elevation model analysis and topographic change detection, the image recognition algorithm comprises feature point matching and target contour analysis, the abnormal pattern recognition technology comprises data abnormal point analysis and behavior pattern recognition, and the real-time data feedback mechanism comprises dynamic data updating and a real-time alarm system.
As a further scheme of the invention, the path optimization and planning module comprises a path calculation sub-module, a dynamic adjustment sub-module, an efficiency evaluation sub-module and a safety planning sub-module;
the path calculation sub-module calculates an optimal mapping path by adopting a Dijkstra path optimization algorithm based on the analysis report, and generates a preliminary path plan;
the dynamic adjustment submodule adjusts the path based on the preliminary path planning by adopting a dynamic planning technology and an environment adaptability strategy to generate an adjusted path scheme;
the efficiency evaluation submodule adopts an efficiency evaluation model based on the adjusted path scheme, evaluates the path scheme through cost-benefit analysis and generates an efficiency evaluation report;
the safety planning submodule adopts safety risk analysis and preventive measure design to ensure the safety of the path based on the efficiency evaluation report, and generates an optimized path scheme;
the Dijkstra path optimization algorithm comprises cost minimization path calculation and multipath selection analysis, the dynamic planning technology comprises path updating and path efficiency optimization based on environmental change, the efficiency evaluation model comprises time and resource consumption evaluation and path optimization effect analysis, and the safety risk analysis comprises potential risk point identification and safety planning strategy design.
As a further scheme of the invention, the risk assessment and management module comprises a risk identification sub-module, a probability assessment sub-module, an influence analysis sub-module and a risk alleviation sub-module;
the risk identification submodule carries out risk point identification by adopting a data mining technology and a risk factor analysis method based on an optimized path scheme and environment data to generate a risk point identification report;
the probability evaluation sub-module quantitatively evaluates the probability of risk occurrence by adopting a statistical analysis method and a Bayesian network based on the risk point identification report to generate a risk probability evaluation report;
the influence analysis submodule analyzes potential influences of risks by adopting an influence evaluation model and a risk influence matrix based on the risk probability evaluation report to generate a risk influence analysis report;
the risk mitigation sub-module adopts a risk mitigation strategy and an emergency response plan to formulate a risk management scheme and generate a risk management report based on the risk influence analysis report;
the data mining technology comprises pattern recognition and association rule mining, the statistical analysis method comprises conditional probability calculation and probability distribution analysis, the influence evaluation model comprises risk influence scores and influence range prediction, and the risk mitigation strategy comprises the design of risk prevention and mitigation measures.
As a further scheme of the invention, the dynamic learning and prediction module comprises a time sequence analysis sub-module, an adaptive learning sub-module, a trend prediction sub-module and a model calibration sub-module;
the time sequence analysis submodule adopts a time sequence analysis method and historical data mining to deeply analyze the environment and the topography change based on the risk management report, and generates a time sequence analysis result;
the self-adaptive learning submodule applies a long-short-period memory network to deep learn and predict environmental changes based on time sequence analysis results to generate self-adaptive learning results;
the trend prediction submodule predicts future topography and environment change trend by using a prediction analysis technology based on the self-adaptive learning result to generate a trend prediction result;
the model calibration submodule is used for calibrating a model and verifying the prediction accuracy by adopting a model optimization and parameter adjustment technology based on a trend prediction result to generate a prediction model;
the time sequence analysis method comprises an autoregressive model and a seasonal variation analysis, the long-term and short-term memory network is specifically a network model for processing and predicting time sequence data, the prediction analysis technology comprises trend line analysis and prediction model construction, and the model optimization and parameter adjustment technology comprises model performance test and parameter fine adjustment.
As a further scheme of the invention, the decision support and optimization module comprises a policy generation sub-module, a decision analysis sub-module, a risk adjustment sub-module and an execution scheme evaluation sub-module;
the strategy generation submodule adopts a decision analysis technology and an optimization algorithm comprising a linear programming and genetic algorithm to formulate a strategy of a mapping task based on a prediction model and real-time data, and generates a strategy draft;
the decision analysis submodule analyzes feasibility and risks of multiple strategies through Monte Carlo simulation by adopting a decision tree analysis and risk assessment model based on a strategy draft, and generates a decision analysis report;
the risk adjustment sub-module adjusts and optimizes potential risks in the strategy based on the decision analysis report by adopting a risk management technology and sensitivity analysis, and generates a risk adjustment strategy;
the execution scheme evaluation sub-module adopts an execution evaluation model to perform efficiency analysis and cost benefit comparison based on a risk adjustment strategy, evaluates the efficiency and cost of the final execution scheme and generates a decision optimization strategy;
the decision analysis techniques include multi-criteria decision analysis, in particular decision path assessment based on predicted outcomes and probabilities, and risk-benefit assessment, the risk management techniques include risk identification, assessment and formulation of mitigation measures, and the performance assessment models include performance index calculation and implementation cost analysis.
As a further scheme of the invention, the environment simulation and test module comprises a scene construction sub-module, a strategy test sub-module, a performance evaluation sub-module and a result verification sub-module;
the scene construction submodule adopts a virtual reality technology and environment modeling to construct a virtual scene for testing based on a decision optimization strategy, and generates a virtual testing environment;
the strategy testing submodule is used for carrying out actual application testing of strategies by adopting a simulation testing algorithm through Monte Carlo simulation and system dynamics simulation based on a virtual testing environment to generate strategy testing results;
the performance evaluation sub-module adopts a performance evaluation tool to quantitatively analyze the implementation effect of the strategy based on the strategy test result to generate a performance evaluation report;
the result verification sub-module adopts a result verification technology to verify the validity and accuracy of the strategy based on the performance evaluation report and generates a simulation test report;
the virtual reality technology comprises three-dimensional scene rendering and simulated environment parameter setting, the simulated test algorithm is specifically result prediction based on random samples and system feedback, the performance evaluation tool comprises efficiency index calculation and performance comparison analysis, and the result verification technology is specifically comparison analysis and practical application simulation.
Compared with the prior art, the invention has the advantages and positive effects that:
in the invention, the data of the multiple sensors are integrated through the convolutional neural network, so that the accuracy and the comprehensiveness of the data are enhanced. And machine learning algorithms, such as a support vector machine and incremental learning, adopted by the real-time analysis and identification module improve the accuracy of the topographic feature analysis and the target identification. The ant colony optimization algorithm is applied to a path optimization and planning module, so that mapping efficiency and safety are improved. And the Bayesian network of the risk assessment and management module effectively predicts and manages risks and enhances the safety guarantee of operation. And a long-term and short-term memory network in the dynamic learning and prediction module accurately predicts the change of the environment and the terrain and optimizes the preparation of future tasks. The combination of the decision support and optimization module and the environment simulation and test module not only provides effective decision support, but also verifies the reliability and practicability of the strategy through the virtual environment test.
Drawings
FIG. 1 is a system flow diagram of the present invention;
FIG. 2 is a schematic diagram of a system framework of the present invention;
FIG. 3 is a flow chart of a data stream processing module according to the present invention;
FIG. 4 is a flow chart of a multi-source data fusion module according to the present invention;
FIG. 5 is a flow chart of the real-time analysis and recognition module of the present invention;
FIG. 6 is a flow chart of a path optimization and planning module according to the present invention;
FIG. 7 is a flowchart of a risk assessment and management module according to the present invention;
FIG. 8 is a flow chart of a dynamic learning and prediction module according to the present invention;
FIG. 9 is a flow chart of the decision support and optimization module of the present invention;
FIG. 10 is a flow chart of an environmental simulation and test module according to the present invention.
Detailed Description
The present invention will be described in further detail with reference to the drawings and examples, in order to make the objects, technical solutions and advantages of the present invention more apparent. 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 invention.
In the description of the present invention, it should be understood that the terms "length," "width," "upper," "lower," "front," "rear," "left," "right," "vertical," "horizontal," "top," "bottom," "inner," "outer," and the like indicate orientations or positional relationships based on the orientation or positional relationships shown in the drawings, merely to facilitate describing the present invention and simplify the description, and do not indicate or imply that the devices or elements referred to must have a specific orientation, be configured and operated in a specific orientation, and therefore should not be construed as limiting the present invention. Furthermore, in the description of the present invention, the meaning of "a plurality" is two or more, unless explicitly defined otherwise.
Embodiment one:
referring to fig. 1 to 2, the AI-based underwater mapping real-time analysis system includes a data stream processing module, a multi-source data fusion module, a real-time analysis and identification module, a path optimization and planning module, a risk assessment and management module, a dynamic learning and prediction module, a decision support and optimization module, and an environment simulation and test module;
the data stream processing module is based on underwater sensor data, adopts an Apache Flink or Spark Streaming data processing technology, and combines a time window algorithm to process and analyze a real-time data stream so as to generate a standardized data stream;
the multi-source data fusion module is based on a standardized data stream, adopts a deep learning method and a statistical data fusion technology, integrates data of multiple sensors through a convolutional neural network, and generates a fusion data view;
the real-time analysis and recognition module is used for carrying out real-time topography characteristic analysis and target recognition by adopting a machine learning algorithm comprising a support vector machine and incremental learning based on the fusion data view to generate an analysis report;
the path optimization and planning module optimizes the underwater mapping path based on the analysis report by applying an ant colony optimization algorithm to generate an optimized path scheme;
The risk assessment and management module is used for carrying out risk prediction and management through a Bayesian network by applying a risk assessment algorithm based on an optimized path scheme and environment data, and generating a risk management report;
the dynamic learning and prediction module is used for predicting environmental and terrain changes through a long-term and short-term memory network by applying a self-adaptive learning model based on the risk management report to generate a prediction model;
the decision support and optimization module is used for providing a decision support and strategy optimization scheme based on the prediction model and the real-time data and combining an optimization algorithm and a decision tree to generate a decision optimization strategy;
the environment simulation and test module is used for performing policy test and verification in the virtual environment by using simulation software and a test algorithm through Monte Carlo simulation based on the decision optimization policy, and generating a simulation test report.
The standardized data flow comprises data subjected to formatting, denoising and preliminary analysis, the fusion data view comprises sonar data, satellite images and integrated analysis of laser radar scanning results, the analysis report comprises terrain structure identification, object classification and abnormal pattern identification, the optimized path scheme comprises an optimized coverage route, a safe navigation path and efficiency evaluation, the risk management report comprises potential risk point evaluation, risk probability analysis and relief strategies, the prediction model comprises environment change trend analysis and terrain dynamic prediction, the decision optimization strategy comprises operation scheme, task planning and execution scheme adjustment, and the simulation test report comprises scene reproduction effect, strategy execution performance and potential risk identification.
The data stream processing module adopts stream data processing technologies such as Apache Flink or Spark Streaming, and the like, so that high-efficiency and real-time data processing capacity is realized, and an accurate and rapid data basis is provided for subsequent analysis. The multi-source data fusion module integrates various sensor data through deep learning and statistical data fusion technology, so that the comprehensive utilization efficiency and dimension of the data are greatly improved, and the recognition accuracy of submarine topography and targets is enhanced. The application of the real-time analysis and recognition module improves the speed and accuracy of the topographic feature analysis and the target recognition by utilizing a machine learning algorithm such as a support vector machine and incremental learning, and particularly has obvious application effect in a complex submarine environment. The path optimization and planning module generates an optimized mapping path by using an ant colony optimization algorithm, so that the coverage area and efficiency of mapping are improved, and the potential risk is reduced. The risk assessment and management module predicts and manages risks through the Bayesian network, effectively assesses potential risk points, provides a risk relief strategy, and enhances the safety of task execution. The combination of the dynamic learning and prediction module and the decision support and optimization module provides strong self-adaption and decision optimization capability, provides scientific basis for decision making based on current and future trend prediction, and improves the prospective and accuracy of the decision making. The environment simulation and test module tests and verifies the strategy in the virtual environment by using technologies such as Monte Carlo simulation and the like, and ensures the stability and reliability of the system.
Referring to fig. 3, the data stream processing module includes a data partitioning sub-module, a time window sub-module, an error processing sub-module, and a data standardization sub-module;
the data partitioning sub-module performs data distribution by adopting a hash partitioning technology and a dynamic load balancing strategy based on underwater sensor data to generate a partitioned data stream;
the time window submodule adopts a sliding window algorithm and a time trigger to conduct time sequence processing of the data stream based on the partitioned data stream, and generates a time window data stream;
the error processing sub-module performs error identification and correction by adopting an anomaly detection algorithm and an automatic error correction mechanism based on the time window data stream to generate an error correction data stream;
the data standardization submodule performs standardization processing of the data stream by adopting a format unification method and a data normalization technology based on the error correction data stream to generate a standardized data stream;
the hash partitioning technique includes hash mapping and partitioning based on data characteristics, the sliding window algorithm includes partitioning data windows based on time intervals and collecting data, and the anomaly detection algorithm includes error discovery and data verification based on pattern recognition.
In the data partitioning sub-module, the system firstly distributes and processes a large amount of data of the underwater sensor through a hash partitioning technology and a dynamic load balancing strategy. Based on data characteristics, hash mapping is adopted to carry out data partition distribution, so that uniform distribution of data among processing nodes is ensured. The dynamic load balancing strategy further ensures the efficiency of distributed processing, and the data flow direction is dynamically adjusted by monitoring the loads of all nodes in real time, so that efficient data processing is realized, and partitioned data flows are generated.
In the time window sub-module, a sliding window algorithm and a time trigger are adopted to conduct time sequence processing on the partitioned data stream. Based on the time interval, the sliding window algorithm divides the data window and collects data, the data in the window is updated periodically through the time trigger, and the time sequence and the continuity of the data stream are guaranteed, so that the time window data stream is generated.
In the error processing sub-module, the system adopts an anomaly detection algorithm and an automatic error correction mechanism to perform error identification and correction based on the time window data stream. And finding out abnormal modes and errors in the data by using a mode identification technology, and carrying out error diagnosis by combining a data verification method. And the automatic error correction mechanism automatically corrects and cleans the data according to the diagnosis result to generate more accurate and reliable error correction data flow.
In the data normalization sub-module, the system performs normalization processing based on the error correction data stream. The data is converted into a unified format by a format unification method, so that the subsequent processing is convenient. The data normalization technology performs standardized processing on the data, so that the data with different sources and different types are analyzed and processed under the same standard, and finally standardized data streams are generated.
Referring to fig. 4, the multi-source data fusion module includes a multi-source data integration sub-module, a feature extraction sub-module, a depth fusion sub-module, and a data integrity inspection sub-module;
the multi-source data integration sub-module integrates different source data by adopting a data fusion framework and a multi-source synchronization mechanism based on the standardized data stream to generate an aggregate data stream;
the feature extraction submodule extracts data features based on the aggregate data stream by adopting a feature engineering method and a statistical analysis technology to generate a feature extraction data stream;
the deep fusion submodule extracts a data stream based on the characteristics, performs data fusion by adopting a convolutional neural network and a deep learning model, and generates a deep fusion data stream;
the data integrity checking submodule verifies the accuracy of data fusion by adopting a data integrity checking algorithm based on the depth fusion data flow to generate a fusion data view;
the data fusion framework comprises data alignment, time synchronization and uniform format, the feature engineering method comprises feature selection, feature extraction and feature dimension reduction, the convolutional neural network specifically realizes analysis of data features through multi-level processing of a neural layer, and the data integrity checking algorithm comprises data integrity checking and consistency checking.
In the multi-source data integration sub-module, the system firstly performs integrated processing on standardized data streams from different sources through a data fusion framework and a multi-source synchronization mechanism. The data fusion framework comprises data alignment, time synchronization and format unification processing, and ensures the consistency of data from different sources in time and format. The multi-source synchronization mechanism ensures the synchronous update and integration of different data sources, thereby generating an aggregate data stream.
In the feature extraction sub-module, the system adopts a feature engineering method and a statistical analysis technology to extract key data features based on the aggregate data flow. The feature engineering method comprises feature selection, feature extraction and feature dimension reduction, and through the technologies, the most valuable features in the data can be effectively identified and extracted, and a feature extraction data stream is generated.
In the deep fusion sub-module, the system adopts a convolutional neural network and a deep learning model to perform data fusion based on the feature extraction data stream. The convolutional neural network can deeply mine and integrate the characteristics of different data sources through multi-layer neural layer processing, so that deep fusion of data is realized, and a deep fusion data stream is generated.
In the data integrity checking sub-module, the system adopts a data integrity checking algorithm based on the depth fusion data flow to verify the accuracy and integrity of data fusion, and the steps are key links for ensuring the accuracy and reliability of a data fusion result, and a final fusion data view is generated through the processing of the module.
Referring to fig. 5, the real-time analysis and recognition module includes a topographic feature analysis sub-module, a target recognition sub-module, an abnormal pattern detection sub-module, and a real-time feedback sub-module;
the topographic feature analysis submodule carries out topographic feature analysis by adopting a topographic analysis algorithm and a geological modeling technology based on the fusion data view to generate a topographic feature analysis report;
the target recognition submodule carries out target recognition by using an image recognition algorithm and a machine learning model based on the topographic feature analysis report and a support vector machine to generate a target recognition report;
the abnormal pattern detection sub-module is used for carrying out abnormal detection by an isolated forest algorithm based on the target identification report by adopting an abnormal pattern identification technology, so as to generate an abnormal detection report;
the real-time feedback sub-module carries out feedback processing by adopting a real-time data feedback mechanism and a decision support system based on the abnormality detection report to generate an analysis report;
the topographic analysis algorithm comprises digital elevation model analysis and topographic change detection, the image recognition algorithm comprises feature point matching and target contour analysis, the abnormal pattern recognition technology comprises data abnormal point analysis and behavior pattern recognition, and the real-time data feedback mechanism comprises dynamic data updating and a real-time alarm system.
In the topographic feature analysis sub-module, the system performs in-depth analysis on topographic features in the fused data view through topographic analysis algorithms and geologic modeling techniques. The topographic analysis algorithm comprises digital elevation model analysis and topographic change detection, and the technologies can accurately analyze topographic structures and identify topographic changes so as to generate detailed topographic feature analysis reports.
In the target recognition sub-module, the system adopts an image recognition algorithm and a machine learning model based on the topographic feature analysis report, and particularly carries out target recognition through a support vector machine. The image recognition algorithm comprises characteristic point matching and target contour analysis, and the technology can accurately recognize and classify submarine targets and generate a target recognition report.
In the abnormal pattern detection sub-module, the system performs abnormal detection by using an abnormal pattern recognition technology based on the target recognition report. Through an isolated forest algorithm, the module can effectively identify abnormal points and behavior patterns in data, rapidly detect abnormal conditions and generate an abnormal detection report.
In the real-time feedback sub-module, the system adopts a real-time data feedback mechanism and a decision support system to carry out feedback processing based on the anomaly detection report. The real-time data feedback mechanism comprises a dynamic data updating and real-time alarm system, can respond to analysis results in time, provides immediate decision support for operators, and generates comprehensive analysis reports.
Referring to fig. 6, the path optimizing and planning module includes a path calculating sub-module, a dynamic adjusting sub-module, an efficiency evaluating sub-module, and a safety planning sub-module;
the path calculation sub-module calculates an optimal mapping path by adopting a Dijkstra path optimization algorithm based on the analysis report, and generates a preliminary path plan;
the dynamic adjustment submodule adjusts the path based on the preliminary path planning by adopting a dynamic planning technology and an environment adaptability strategy to generate an adjusted path scheme;
the efficiency evaluation submodule adopts an efficiency evaluation model based on the adjusted path scheme, evaluates the path scheme through cost-benefit analysis and generates an efficiency evaluation report;
the safety planning sub-module adopts safety risk analysis and preventive measure design to ensure the safety of the path based on the efficiency evaluation report, and generates an optimized path scheme;
dijkstra path optimization algorithm comprises cost minimization path calculation and multipath selection analysis, dynamic planning technology comprises path updating and path efficiency optimization based on environmental change, efficiency evaluation model comprises time and resource consumption evaluation and path optimization effect analysis, and security risk analysis comprises potential risk point identification and security planning strategy design.
In the path calculation sub-module, based on the analysis report, the optimal path is calculated by using Dijkstra path optimization algorithm. The Dijkstra algorithm is mainly used for calculating a path with minimized cost, and is suitable for determining a shortest path from point to point. The following is an example implementation of the Dijkstra algorithm in Python:
import heapq
def dijkstra(graph, start):
distances = {vertex: float('infinity') for vertex in graph}
distances[start] = 0
priority_queue = [(0, start)]
while priority_queue:
current_distance, current_vertex = heapq.heappop(priority_queue)
for neighbor, weight in graph[current_vertex].items():
distance = current_distance + weight
if distance < distances[neighbor]:
distances[neighbor] = distance
heapq.heappush(priority_queue, (distance, neighbor))
return distances
# example graph Structure
graph = {
'A': {'B': 1, 'C': 4},
'B': {'A': 1, 'C': 2, 'D': 5},
'C': {'A': 4, 'B': 2, 'D': 1},
'D': {'B': 5, 'C': 1}
}
Calculation of shortest Path from point A to other points
shortest_paths = dijkstra(graph, 'A')
In the dynamic adjustment sub-module, based on the preliminary path planning, the module adopts a dynamic planning technology and an environment adaptability strategy to adjust the path. Dynamic planning is applicable where environmental changes and path efficiency optimization are considered. The following is a simplified example of dynamic programming:
def dynamic_path_planning(paths, environmental_factors):
# adding Environment change based Path update logic here
Return adjusted path scheme
return adjusted_path_plan
adjusted_path_plan = dynamic_path_planning(shortest_paths, environmental_data)
In the efficiency evaluation sub-module, a cost-benefit analysis is performed using an efficiency evaluation model based on the adjusted path plan. This includes time and resource consumption assessment and path optimization effect analysis. The following is a framework for efficiency assessment:
def evaluate_path_efficiency(path_plan):
# time and resource consumption assessment
Return efficiency assessment report
return efficiency_report
efficiency_report = evaluate_path_efficiency(adjusted_path_plan)
In the safety planning sub-module, safety risk analysis and preventive measure design are used to ensure path safety based on the efficiency evaluation report. This includes identification of potential risk points and design of safety planning strategies. The following is a simplified framework for security planning:
def safety_planning(efficiency_report):
# potential risk Point identification from efficiency assessment report
Design safety planning strategy
return optimized_path_plan
optimized_path_plan = safety_planning(efficiency_report)
Referring to fig. 7, the risk assessment and management module includes a risk identification sub-module, a probability assessment sub-module, an impact analysis sub-module, and a risk mitigation sub-module;
the risk identification sub-module is used for identifying risk points by adopting a data mining technology and a risk factor analysis method based on an optimized path scheme and environment data, and generating a risk point identification report;
the probability evaluation sub-module quantitatively evaluates the risk occurrence probability based on the risk point identification report by adopting a statistical analysis method and a Bayesian network to generate a risk probability evaluation report;
the influence analysis submodule analyzes potential influences of risks by adopting an influence evaluation model and a risk influence matrix based on the risk probability evaluation report to generate a risk influence analysis report;
the risk mitigation sub-module adopts a risk mitigation strategy and an emergency response plan to formulate a risk management scheme and generate a risk management report based on the risk influence analysis report;
the data mining technology comprises pattern recognition and association rule mining, the statistical analysis method comprises conditional probability calculation and probability distribution analysis, the influence evaluation model comprises risk influence scores and influence range prediction, and the risk relief strategy comprises the design of risk prevention and relief measures.
In the risk identification sub-module, the risk points are deeply analyzed by optimizing the path scheme and the environment data, applying data mining technologies such as pattern recognition and association rule mining, and a risk factor analysis method. The operation steps comprise collecting and processing related data, identifying potential risk factors by using a data mining algorithm, and generating an exhaustive risk point identification report, wherein in the process, the key information is screened out from a large amount of data, so that accurate identification of risk points is ensured.
In the probability evaluation sub-module, based on the risk point identification report, a statistical analysis method and a Bayesian network are adopted to quantify the probability of risk occurrence. And (5) quantitatively analyzing the risk by using a conditional probability calculation and probability distribution analysis method. Further probability inference is carried out on the risks through a Bayesian network, a risk probability evaluation report is generated, and the key of the steps is to accurately evaluate the occurrence probability of each risk point, so that a scientific basis is provided for subsequent risk management.
In the impact analysis sub-module, an impact assessment model and a risk impact matrix are applied to analyze potential impact of the risk based on the risk probability assessment report. This includes using a risk impact score and an impact range prediction model to integrate the consequences of risk. The influence degree and range of each risk point need to be deeply analyzed in the operation process, and a detailed risk influence analysis report is compiled according to the influence degree and range. The key point of the link is to comprehensively evaluate the influence caused by risks, and lay a foundation for making effective countermeasures.
In the risk mitigation sub-module, a targeted risk management scheme is formulated using a risk mitigation strategy and an emergency response plan based on the risk impact analysis report. This involves design risk prevention and mitigation measures such as emergency planning, optimization procedures, resource allocation, etc. Finally, all of these measures are integrated into one comprehensive risk management report.
Referring to fig. 8, the dynamic learning and prediction module includes a time sequence analysis sub-module, an adaptive learning sub-module, a trend prediction sub-module, and a model calibration sub-module;
the time sequence analysis submodule adopts a time sequence analysis method and historical data mining to deeply analyze the environment and the topography change based on the risk management report, and generates a time sequence analysis result;
the self-adaptive learning submodule applies a long-period memory network to deep learning and prediction of environmental changes based on the time sequence analysis result to generate a self-adaptive learning result;
the trend prediction sub-module predicts future topography and environment change trend by using a prediction analysis technology based on the self-adaptive learning result, and generates a trend prediction result;
the model calibration sub-module is used for calibrating the model and verifying the prediction accuracy by adopting a model optimization and parameter adjustment technology based on the trend prediction result, so as to generate a prediction model;
The time sequence analysis method comprises an autoregressive model and seasonal variation analysis, the long-term and short-term memory network is specifically a network model for processing and predicting time sequence data, the prediction analysis technology comprises trend line analysis and prediction model construction, and the model optimization and parameter adjustment technology comprises model performance test and parameter fine adjustment.
In the time series analysis sub-module, through the risk management report and the historical data, deep analysis is performed by adopting a time series analysis method. Operations include systematic mining of environmental and terrain changes using autoregressive models and seasonal variation analysis. The key point of the step is to understand and interpret past data patterns, provide a basis for future prediction and finally generate a time series analysis result.
And in the self-adaptive learning sub-module, based on a time sequence analysis result, a long-period and short-period memory network is applied to deep learning and prediction of environmental changes. In the operation process, the emphasis is on training a network to identify and adapt to complex patterns in time series data, so that a more accurate self-adaptive learning result is generated, and the importance of the steps is that the model can be self-adjusted and optimized according to new data, so that the prediction accuracy is improved.
And in the trend prediction sub-module, based on the self-adaptive learning result, predicting the future topography and environment change trend by using a prediction analysis technology. This includes trend line analysis and predictive model construction in order to accurately predict future changes, generating trend prediction results. The key of the link is to apply the learned mode and trend to the prediction of future scenes, thereby providing scientific basis for decision making.
In the model calibration submodule, based on a trend prediction result, a model optimization and parameter adjustment technology is adopted to carry out fine adjustment and verification on a prediction model, and the steps relate to model performance test and parameter fine adjustment, so that the accuracy and reliability of the model are improved. Through continuous calibration and verification, the prediction model is ensured to achieve the optimal performance in practical application, and more accurate support is provided for decision making.
Referring to fig. 9, the decision support and optimization module includes a policy generation sub-module, a decision analysis sub-module, a risk adjustment sub-module, and an execution scheme evaluation sub-module;
the strategy generation submodule adopts a decision analysis technology and an optimization algorithm comprising a linear programming and genetic algorithm to formulate a strategy of a mapping task based on the prediction model and the real-time data, and generates a strategy draft;
The decision analysis sub-module analyzes feasibility and risk of multiple strategies by Monte Carlo simulation by adopting a decision tree analysis and risk assessment model based on a strategy draft, and generates a decision analysis report;
the risk adjustment sub-module adjusts and optimizes potential risks in the strategy based on the decision analysis report by adopting a risk management technology and sensitivity analysis, and generates a risk adjustment strategy;
the execution scheme evaluation sub-module adopts an execution evaluation model to perform efficiency analysis and cost benefit comparison based on the risk adjustment strategy, evaluates the efficiency and cost of the final execution scheme and generates a decision optimization strategy;
decision analysis techniques include multi-criteria decision analysis, specifically decision path assessment based on predicted outcomes and probabilities, and risk management techniques include risk identification, assessment, and formulation of mitigation measures, performance assessment models including performance index calculations, and implementation cost analysis.
In the strategy generation sub-module, strategy of mapping task is formulated by prediction model and real-time data and adopting decision analysis technology and optimization algorithm such as linear programming and genetic algorithm. The operation steps include analyzing the current environment and the predicted result, applying an optimization algorithm to formulate the most effective strategy, and generating a strategy draft. The key to this step is to combine the prediction with the current data to develop a strategy that is both practical and efficient.
In the decision analysis sub-module, based on the policy draft, the feasibility and risk of multiple policies are analyzed through Monte Carlo simulation using decision tree analysis and risk assessment models. Operations include evaluating the advantages and disadvantages of different strategies, as well as the risks faced, and generating decision analysis reports based thereon. The key point of the link is to comprehensively evaluate potential results and risks of all strategies and provide scientific basis for final strategy selection.
In the risk adjustment sub-module, based on the decision analysis report, a risk management technique and a sensitivity analysis are applied to adjust and optimize the potential risks in the policy. The operation process involves identifying potential risks, evaluating the influence of the risks, formulating corresponding relieving measures, and generating a risk adjustment strategy, wherein the key of the steps is to ensure the reliability and the robustness of the strategy through careful risk management.
In the execution scheme evaluation sub-module, an execution evaluation model is employed for efficiency analysis and cost benefit comparison based on the risk adjustment strategy. This includes calculating performance metrics and implementation costs to evaluate the efficiency and cost effectiveness of the final execution scheme, ultimately generating a decision-optimization strategy. The focus at this stage is to ensure that the selected scheme is not only effective, but also efficient and economical in terms of resource utilization.
Referring to fig. 10, the environment simulation and test module includes a scene construction sub-module, a policy test sub-module, a performance evaluation sub-module, and a result verification sub-module;
the scene construction submodule adopts a virtual reality technology and environment modeling to construct a virtual scene for testing based on a decision optimization strategy, and generates a virtual testing environment;
the strategy testing sub-module is used for carrying out actual application testing of the strategy by adopting a simulation testing algorithm through Monte Carlo simulation and system dynamics simulation based on the virtual testing environment to generate a strategy testing result;
the performance evaluation sub-module adopts a performance evaluation tool to quantitatively analyze the implementation effect of the strategy based on the strategy test result to generate a performance evaluation report;
the result verification sub-module verifies the validity and accuracy of the strategy based on the performance evaluation report by adopting a result verification technology, and generates a simulation test report;
the virtual reality technology comprises three-dimensional scene rendering and simulated environment parameter setting, a simulation test algorithm is specifically result prediction based on random samples and system feedback, the performance evaluation tool comprises efficiency index calculation and performance comparison analysis, and a result verification technology is specifically comparison analysis and practical application simulation.
In the scene construction sub-module, virtual scenes required for testing are constructed by adopting a decision optimization strategy and adopting a virtual reality technology and environment modeling, and the process involves three-dimensional scene rendering and simulated environment parameter setting so as to ensure the authenticity and fidelity of the virtual environment. Through the steps, a virtual test environment similar to the actual operation environment is generated, and an accurate simulation platform is provided for testing the strategy.
In the strategy testing sub-module, based on the virtual testing environment, a simulation testing algorithm is adopted to conduct actual application testing of the strategy. This includes Monte Carlo simulations and system dynamics simulations for evaluating the performance and effect of strategies in various contexts. In the operation process, the emphasis is on verifying the adaptability and the effectiveness of the strategy under different conditions in a simulation mode, so that a strategy test result is generated.
In the performance evaluation sub-module, based on the policy test result, the implementation effect of the policy is quantitatively analyzed by using a performance evaluation tool. This includes efficiency index calculations and performance comparison analysis to accurately evaluate the actual performance of the strategy. Through these steps, performance assessment reports can be generated, providing detailed quantitative data about the effects of the policies.
In the result verification sub-module, based on the performance evaluation report, a result verification technique is applied to verify the validity and accuracy of the policy. This includes comparative analysis and practical application simulation to ensure the feasibility of the strategy in a real environment. Through these verification processes, simulated test reports are generated, providing a solid verification basis for the final implementation of policies.
The present invention is not limited to the above embodiments, and any equivalent embodiments which can be changed or modified by the technical disclosure described above can be applied to other fields, but any simple modification, equivalent changes and modification made to the above embodiments according to the technical matter of the present invention will still fall within the scope of the technical disclosure.
Claims (10)
1. AI-based underwater mapping real-time analysis system, its characterized in that: the system comprises a data stream processing module, a multi-source data fusion module, a real-time analysis and identification module, a path optimization and planning module, a risk assessment and management module, a dynamic learning and prediction module, a decision support and optimization module and an environment simulation and test module;
The data stream processing module is based on underwater sensor data, adopts Apache Flink or Spark Streaming data processing technology, and combines a time window algorithm to process and analyze real-time data streams to generate standardized data streams;
the multi-source data fusion module integrates data of multiple sensors through a convolutional neural network and generates a fusion data view by adopting a deep learning method and a statistical data fusion technology based on a standardized data stream;
the real-time analysis and recognition module is used for carrying out real-time topography characteristic analysis and target recognition by adopting a machine learning algorithm comprising a support vector machine and incremental learning based on the fusion data view to generate an analysis report;
the path optimization and planning module optimizes the underwater mapping path based on the analysis report by applying an ant colony optimization algorithm to generate an optimized path scheme;
the risk assessment and management module is used for carrying out risk prediction and management through a Bayesian network by applying a risk assessment algorithm based on an optimized path scheme and environment data, and generating a risk management report;
the dynamic learning and prediction module is used for predicting environmental and terrain changes through a long-term and short-term memory network by applying a self-adaptive learning model based on a risk management report to generate a prediction model;
The decision support and optimization module is used for providing a decision support and strategy optimization scheme based on the prediction model and the real-time data and combining an optimization algorithm and a decision tree to generate a decision optimization strategy;
the environment simulation and test module is used for performing policy test and verification in the virtual environment by using simulation software and a test algorithm based on a decision optimization policy and through Monte Carlo simulation, and generating a simulation test report.
2. The AI-based underwater mapping real-time analysis system of claim 1, wherein: the standardized data flow comprises data subjected to formatting, denoising and preliminary analysis, the fusion data view comprises integrated analysis of sonar data, satellite images and laser radar scanning results, the analysis report comprises terrain structure identification, object classification and abnormal pattern identification, the optimized path scheme comprises an optimized coverage route, a safe navigation path and efficiency assessment, the risk management report comprises potential risk point assessment, risk probability analysis and relief strategies, the prediction model comprises environment change trend analysis and terrain dynamic prediction, the decision optimization strategy comprises operation scheme, task planning and execution scheme adjustment, and the simulation test report comprises scene reproduction effect, strategy execution performance and potential risk identification.
3. The AI-based underwater mapping real-time analysis system of claim 1, wherein: the data stream processing module comprises a data partitioning sub-module, a time window sub-module, an error processing sub-module and a data standardization sub-module;
the data partitioning sub-module performs data distribution by adopting a Hash partitioning technology and a dynamic load balancing strategy based on underwater sensor data to generate a partitioned data stream;
the time window sub-module adopts a sliding window algorithm and a time trigger to conduct time sequence processing of the data stream based on the partitioned data stream, and generates a time window data stream;
the error processing submodule carries out error identification and correction by adopting an anomaly detection algorithm and an automatic error correction mechanism based on the time window data stream to generate an error correction data stream;
the data normalization submodule performs data stream normalization processing by adopting a format unification method and a data normalization technology based on the error correction data stream to generate a normalized data stream;
the hash partitioning technique includes hash mapping and partitioning based on data characteristics, the sliding window algorithm includes partitioning data windows and collecting data based on time intervals, and the anomaly detection algorithm includes error discovery and data verification based on pattern recognition.
4. The AI-based underwater mapping real-time analysis system of claim 1, wherein: the multi-source data fusion module comprises a multi-source data integration sub-module, a feature extraction sub-module, a depth fusion sub-module and a data integrity inspection sub-module;
the multi-source data integration sub-module integrates different source data by adopting a data fusion framework and a multi-source synchronization mechanism based on a standardized data stream to generate an aggregated data stream;
the feature extraction submodule extracts data features based on the aggregate data stream by adopting a feature engineering method and a statistical analysis technology to generate a feature extraction data stream;
the deep fusion submodule extracts a data stream based on the characteristics, performs data fusion by adopting a convolutional neural network and a deep learning model, and generates a deep fusion data stream;
the data integrity checking submodule verifies the accuracy of data fusion by adopting a data integrity checking algorithm based on the depth fusion data stream to generate a fusion data view;
the data fusion framework comprises data alignment, time synchronization and uniform format, the feature engineering method comprises feature selection, feature extraction and feature dimension reduction, the convolutional neural network specifically realizes analysis of data features through multi-level processing of a neural layer, and the data integrity checking algorithm comprises data integrity checking and consistency checking.
5. The AI-based underwater mapping real-time analysis system of claim 1, wherein: the real-time analysis and recognition module comprises a topographic feature analysis sub-module, a target recognition sub-module, an abnormal mode detection sub-module and a real-time feedback sub-module;
the topographic feature analysis submodule carries out topographic feature analysis by adopting a topographic analysis algorithm and a geological modeling technology based on the fusion data view to generate a topographic feature analysis report;
the target recognition submodule carries out target recognition by using an image recognition algorithm and a machine learning model based on the topographic feature analysis report and a support vector machine to generate a target recognition report;
the abnormal pattern detection sub-module is used for carrying out abnormal detection by an isolated forest algorithm based on the target identification report by adopting an abnormal pattern identification technology to generate an abnormal detection report;
the real-time feedback sub-module carries out feedback processing by adopting a real-time data feedback mechanism and a decision support system based on the abnormality detection report to generate an analysis report;
the topographic analysis algorithm comprises digital elevation model analysis and topographic change detection, the image recognition algorithm comprises feature point matching and target contour analysis, the abnormal pattern recognition technology comprises data abnormal point analysis and behavior pattern recognition, and the real-time data feedback mechanism comprises dynamic data updating and a real-time alarm system.
6. The AI-based underwater mapping real-time analysis system of claim 1, wherein: the path optimization and planning module comprises a path calculation sub-module, a dynamic adjustment sub-module, an efficiency evaluation sub-module and a safety planning sub-module;
the path calculation sub-module calculates an optimal mapping path by adopting a Dijkstra path optimization algorithm based on the analysis report, and generates a preliminary path plan;
the dynamic adjustment submodule adjusts the path based on the preliminary path planning by adopting a dynamic planning technology and an environment adaptability strategy to generate an adjusted path scheme;
the efficiency evaluation submodule adopts an efficiency evaluation model based on the adjusted path scheme, evaluates the path scheme through cost-benefit analysis and generates an efficiency evaluation report;
the safety planning submodule adopts safety risk analysis and preventive measure design to ensure the safety of the path based on the efficiency evaluation report, and generates an optimized path scheme;
the Dijkstra path optimization algorithm comprises cost minimization path calculation and multipath selection analysis, the dynamic planning technology comprises path updating and path efficiency optimization based on environmental change, the efficiency evaluation model comprises time and resource consumption evaluation and path optimization effect analysis, and the safety risk analysis comprises potential risk point identification and safety planning strategy design.
7. The AI-based underwater mapping real-time analysis system of claim 1, wherein: the risk assessment and management module comprises a risk identification sub-module, a probability assessment sub-module, an influence analysis sub-module and a risk alleviation sub-module;
the risk identification submodule carries out risk point identification by adopting a data mining technology and a risk factor analysis method based on an optimized path scheme and environment data to generate a risk point identification report;
the probability evaluation sub-module quantitatively evaluates the probability of risk occurrence by adopting a statistical analysis method and a Bayesian network based on the risk point identification report to generate a risk probability evaluation report;
the influence analysis submodule analyzes potential influences of risks by adopting an influence evaluation model and a risk influence matrix based on the risk probability evaluation report to generate a risk influence analysis report;
the risk mitigation sub-module adopts a risk mitigation strategy and an emergency response plan to formulate a risk management scheme and generate a risk management report based on the risk influence analysis report;
the data mining technology comprises pattern recognition and association rule mining, the statistical analysis method comprises conditional probability calculation and probability distribution analysis, the influence evaluation model comprises risk influence scores and influence range prediction, and the risk mitigation strategy comprises the design of risk prevention and mitigation measures.
8. The AI-based underwater mapping real-time analysis system of claim 1, wherein: the dynamic learning and prediction module comprises a time sequence analysis sub-module, a self-adaptive learning sub-module, a trend prediction sub-module and a model calibration sub-module;
the time sequence analysis submodule adopts a time sequence analysis method and historical data mining to deeply analyze the environment and the topography change based on the risk management report, and generates a time sequence analysis result;
the self-adaptive learning submodule applies a long-short-period memory network to deep learn and predict environmental changes based on time sequence analysis results to generate self-adaptive learning results;
the trend prediction submodule predicts future topography and environment change trend by using a prediction analysis technology based on the self-adaptive learning result to generate a trend prediction result;
the model calibration submodule is used for calibrating a model and verifying the prediction accuracy by adopting a model optimization and parameter adjustment technology based on a trend prediction result to generate a prediction model;
the time sequence analysis method comprises an autoregressive model and a seasonal variation analysis, the long-term and short-term memory network is specifically a network model for processing and predicting time sequence data, the prediction analysis technology comprises trend line analysis and prediction model construction, and the model optimization and parameter adjustment technology comprises model performance test and parameter fine adjustment.
9. The AI-based underwater mapping real-time analysis system of claim 1, wherein: the decision support and optimization module comprises a policy generation sub-module, a decision analysis sub-module, a risk adjustment sub-module and an execution scheme evaluation sub-module;
the strategy generation submodule adopts a decision analysis technology and an optimization algorithm comprising a linear programming and genetic algorithm to formulate a strategy of a mapping task based on a prediction model and real-time data, and generates a strategy draft;
the decision analysis submodule analyzes feasibility and risks of multiple strategies through Monte Carlo simulation by adopting a decision tree analysis and risk assessment model based on a strategy draft, and generates a decision analysis report;
the risk adjustment sub-module adjusts and optimizes potential risks in the strategy based on the decision analysis report by adopting a risk management technology and sensitivity analysis, and generates a risk adjustment strategy;
the execution scheme evaluation sub-module adopts an execution evaluation model to perform efficiency analysis and cost benefit comparison based on a risk adjustment strategy, evaluates the efficiency and cost of the final execution scheme and generates a decision optimization strategy;
the decision analysis techniques include multi-criteria decision analysis, in particular decision path assessment based on predicted outcomes and probabilities, and risk-benefit assessment, the risk management techniques include risk identification, assessment and formulation of mitigation measures, and the performance assessment models include performance index calculation and implementation cost analysis.
10. The AI-based underwater mapping real-time analysis system of claim 1, wherein: the environment simulation and test module comprises a scene construction sub-module, a strategy test sub-module, a performance evaluation sub-module and a result verification sub-module;
the scene construction submodule adopts a virtual reality technology and environment modeling to construct a virtual scene for testing based on a decision optimization strategy, and generates a virtual testing environment;
the strategy testing submodule is used for carrying out actual application testing of strategies by adopting a simulation testing algorithm through Monte Carlo simulation and system dynamics simulation based on a virtual testing environment to generate strategy testing results;
the performance evaluation sub-module adopts a performance evaluation tool to quantitatively analyze the implementation effect of the strategy based on the strategy test result to generate a performance evaluation report;
the result verification sub-module adopts a result verification technology to verify the validity and accuracy of the strategy based on the performance evaluation report and generates a simulation test report;
the virtual reality technology comprises three-dimensional scene rendering and simulated environment parameter setting, the simulated test algorithm is specifically result prediction based on random samples and system feedback, the performance evaluation tool comprises efficiency index calculation and performance comparison analysis, and the result verification technology is specifically comparison analysis and practical application simulation.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311723390.0A CN117408536A (en) | 2023-12-15 | 2023-12-15 | AI-based underwater mapping real-time analysis system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311723390.0A CN117408536A (en) | 2023-12-15 | 2023-12-15 | AI-based underwater mapping real-time analysis system |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN117408536A true CN117408536A (en) | 2024-01-16 |
Family
ID=89489423
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311723390.0A Pending CN117408536A (en) | 2023-12-15 | 2023-12-15 | AI-based underwater mapping real-time analysis system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117408536A (en) |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117608865A (en) * | 2024-01-23 | 2024-02-27 | 江西科技学院 | Mathematical model service method and system of take-away meal delivery platform based on cloud computing |
| CN117611015A (en) * | 2024-01-22 | 2024-02-27 | 衡水烨通建设工程有限公司 | Real-time monitoring system for quality of building engineering |
| CN117633722A (en) * | 2024-01-25 | 2024-03-01 | 江西省交通工程集团有限公司 | Detection control method and system based on intelligent detection robot |
| CN117726053A (en) * | 2024-02-09 | 2024-03-19 | 广州市威士丹利智能科技有限公司 | Carbon emission monitoring method and system applied to digital platform system |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101620275A (en) * | 2009-08-12 | 2010-01-06 | 中国煤炭地质总局水文地质局 | Hydrogeololgic comprehensive prospecting method for coal deposit |
| CN103175513A (en) * | 2013-03-01 | 2013-06-26 | 戴会超 | System and method for monitoring hydrology and water quality of river basin under influence of water projects based on Internet of Things |
| CN103942941A (en) * | 2014-04-11 | 2014-07-23 | 中国人民解放军61139部队 | Mobile monitoring fusion platform based on geographic information system (GIS) |
| CN114707227A (en) * | 2022-04-28 | 2022-07-05 | 水利部南京水利水文自动化研究所 | Dam safety early warning and warning method and system based on digital twins |
| CN116975576A (en) * | 2023-09-19 | 2023-10-31 | 四川省公路规划勘察设计研究院有限公司 | Mountain road geological disaster risk evaluation method based on key information statistics |
-
2023
- 2023-12-15 CN CN202311723390.0A patent/CN117408536A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101620275A (en) * | 2009-08-12 | 2010-01-06 | 中国煤炭地质总局水文地质局 | Hydrogeololgic comprehensive prospecting method for coal deposit |
| CN103175513A (en) * | 2013-03-01 | 2013-06-26 | 戴会超 | System and method for monitoring hydrology and water quality of river basin under influence of water projects based on Internet of Things |
| CN103942941A (en) * | 2014-04-11 | 2014-07-23 | 中国人民解放军61139部队 | Mobile monitoring fusion platform based on geographic information system (GIS) |
| CN114707227A (en) * | 2022-04-28 | 2022-07-05 | 水利部南京水利水文自动化研究所 | Dam safety early warning and warning method and system based on digital twins |
| CN116975576A (en) * | 2023-09-19 | 2023-10-31 | 四川省公路规划勘察设计研究院有限公司 | Mountain road geological disaster risk evaluation method based on key information statistics |
Cited By (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117611015A (en) * | 2024-01-22 | 2024-02-27 | 衡水烨通建设工程有限公司 | Real-time monitoring system for quality of building engineering |
| CN117611015B (en) * | 2024-01-22 | 2024-03-29 | 衡水烨通建设工程有限公司 | Real-time monitoring system for quality of building engineering |
| CN117608865A (en) * | 2024-01-23 | 2024-02-27 | 江西科技学院 | Mathematical model service method and system of take-away meal delivery platform based on cloud computing |
| CN117608865B (en) * | 2024-01-23 | 2024-04-05 | 江西科技学院 | Mathematical model service method and system of take-away meal delivery platform based on cloud computing |
| CN117633722A (en) * | 2024-01-25 | 2024-03-01 | 江西省交通工程集团有限公司 | Detection control method and system based on intelligent detection robot |
| CN117633722B (en) * | 2024-01-25 | 2024-04-23 | 江西省交通工程集团有限公司 | Detection control method and system based on intelligent detection robot |
| CN117726053A (en) * | 2024-02-09 | 2024-03-19 | 广州市威士丹利智能科技有限公司 | Carbon emission monitoring method and system applied to digital platform system |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN117408536A (en) | AI-based underwater mapping real-time analysis system | |
| CN113298110A (en) | Submarine cable fault diagnosis method, device and equipment | |
| Gholami et al. | Comparison of self-organizing map, artificial neural network, and co-active neuro-fuzzy inference system methods in simulating groundwater quality: geospatial artificial intelligence | |
| Chebbi et al. | Optimal extension of rain gauge monitoring network for rainfall intensity and erosivity index interpolation | |
| KR101588232B1 (en) | Landslide Prediction System using Geographic Information System and NeuroFuzzy techniques and Landslide Prediction Method using Thereof | |
| Vega et al. | A novel framework for integration of abstracted inspection data and structural health monitoring for damage prognosis of miter gates | |
| CN117687416B (en) | Path planning method and system for river network water safety detection device | |
| Dawood et al. | Soft computing for modeling pipeline risk index under uncertainty | |
| Jalagam et al. | Water Quality Predictions for Urban Streams Using Machine Learning | |
| Mehrabi et al. | Forecasting air quality in kiev during 2022 military conflict using sentinel 5P and optimized machine learning | |
| Foss et al. | Using an autonomous underwater vehicle with onboard stochastic advection‐diffusion models to map excursion sets of environmental variables | |
| US20230401651A1 (en) | Airborne and/or spaceborne optical flood and flood damage sensory system and method thereof | |
| CN116403093B (en) | Multi-source remote sensing interpretation method and device for potential landslide along railway | |
| CN116738192A (en) | Digital twinning-based security data evaluation method and system | |
| Mirakhorlo et al. | Integration of SimWeight and Markov Chain to Predict Land Use of Lavasanat Basin | |
| WO2022093036A1 (en) | Method of estimating polymetallic nodule abundance | |
| Rong et al. | Collision probability assessment based on uncertainty prediction of ship trajectories | |
| KR20220071038A (en) | Devices and Methods for Detection and Prediction of Cold Water Mass Using Artificial Intelligence and Satellite Imaging | |
| Cui et al. | Pipeline corrosion prediction and uncertainty analysis with an ensemble Bayesian neural network approach | |
| Zhou et al. | A Modelling Tool for Rainfall-triggered Landslide Susceptibility Mapping and Hazard Warning based on GIS and Machine Learning | |
| Pereira et al. | A 3-D Lightweight Convolutional Neural Network for Detecting Docking Structures in Cluttered Environments | |
| Du et al. | Neural network models for seabed stability: a deep learning approach to wave-induced pore pressure prediction | |
| KR102485924B1 (en) | Apparatus and method for calculating optical thickness of aerosol based on deep learning using remote sensing data of optical sensor | |
| Percival et al. | PATHA: A planning aid for tasking heterogeneous assets for route survey or mine countermeasures operations | |
| CN117520718B (en) | Tidal river hydrologic data processing method and system |
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 |