A digital monitoring and analysis method and system for water transport engineering

Abstract

The present invention relates to the field of water transport engineering data processing, and in particular to a digital monitoring and analysis method and system for water transport engineering. The method comprises the following steps: acquiring multi-source monitoring data of the water transport engineering, performing multi-dimensional feature cross-fusion and channel focusing processing, generating channel operation data, deducing the ship's motion trajectory based on the channel operation data, and calculating the speed to obtain the ship's speed data, calculating the ship's immersion depth and load status, generating ship load data, performing overall simulation of the channel based on the speed and load data, deducing the ship's travel trajectory, generating simulated multi-ship travel data, constructing an analysis engine using the speed and load data, generating a channel analysis twin model, using the twin model to perform status analysis and scheduling processing on the water transport data, and completing intelligent monitoring and analysis of the water transport engineering. The present invention realizes a more comprehensive and efficient digital monitoring and analysis method for water transport engineering.

Description

Technical Field

[0001] The present invention relates to the field of water transport engineering data processing, and in particular to a digital monitoring and analysis method and system for water transport engineering. Background Art

[0002] With the continuous growth of global logistics and water transport demand, the importance of water transport engineering in the modern transportation system has become increasingly prominent. Traditional water transport monitoring methods mostly rely on manual observation and static data analysis, making it difficult to monitor and accurately predict ship operations and channel conditions in a dynamic environment in real time. Especially in the context of complex waterways and high-density ship traffic, how to effectively manage waterway resources and optimize ship scheduling has become a major challenge for water transport engineering. Modern water transport engineering urgently needs to leverage digital technology and intelligent analysis methods to improve the efficiency and safety of waterway operations. Existing water transport monitoring systems suffer from data isolation, lack of effective fusion, and difficulty in comprehensively utilizing multi-dimensional features. Due to the lack of intelligent cross-fusion and dynamic analysis capabilities for multi-source heterogeneous data, traditional systems are inefficient in ship trajectory prediction, speed estimation, and load status assessment, and struggle to make accurate judgments in complex water transport scenarios. In addition, existing water transport monitoring methods are mostly limited to real-time monitoring of a single vessel, making it difficult to intelligently analyze and simulate the interactions between multiple vessels and the overall operation status of the channel, increasing potential operational risks. Summary of the Invention

[0003] Based on this, it is necessary to provide a digital monitoring and analysis method and system for water transport projects to solve at least one of the above technical problems.

[0004] To achieve the above-mentioned purpose, a digital monitoring and analysis method for water transport engineering includes the following steps:

[0005] Step S1: Acquire water transport engineering monitoring data; perform multi-dimensional feature cross-fusion on multiple water transport engineering monitoring data, and perform waterway focusing processing to obtain waterway operation data;

[0006] Step S2: Evolving the ship's motion trajectory based on the channel operation data, and performing speed estimation to generate ship speed data;

[0007] Step S3: Calculate the ship immersion depth based on the channel operation data, and perform hull load situation deduction to generate ship load data;

[0008] Step S4: performing overall channel simulation processing on the channel operation data according to the ship speed data and the ship load data, and performing ship sailing evolution to obtain simulated multi-ship sailing data;

[0009] Step S5: constructing an analysis engine for the simulated multi-ship travel data based on the ship speed data and the ship load data to generate a channel analysis twin model;

[0010] Step S6: Use the waterway analysis twin model to analyze the water transport status of the water transport project monitoring data and perform response scheduling processing to perform digital monitoring and analysis of the water transport project.

[0011] The present invention generates comprehensive channel operation data by cross-integrating multi-dimensional features of multiple water transport project monitoring data and combining it with channel focusing processing, thereby ensuring the diversity of data sources and improving the accurate reflection of channel status. Through the evolution of ship motion trajectory, speed calculation, immersion depth calculation and load situation deduction, the dynamic motion and load conditions of the ship are tracked and evaluated in real time, which not only improves the monitoring capability of ship navigation safety, but also provides a scientific basis for ship scheduling. The constructed channel analysis twin model integrates speed data, load information and simulated multi-ship driving data, providing accurate channel simulation and prediction capabilities. Through comprehensive analysis of multiple factors, it makes reliable predictions on future channel operation status, assisting in the refined management of water transport projects. With the help of the channel analysis twin model, the water transport status is monitored in real time, and intelligent response scheduling is carried out according to the ship speed and load conditions, ensuring the efficient operation of the entire water transport project, especially realizing automated management and regulation under complex working conditions.

[0012] Preferably, step S1 includes the following steps:

[0013] Step S11: Acquire water transport engineering monitoring data;

[0014] Step S12: extracting features from a plurality of water transport engineering monitoring data to obtain multi-dimensional monitoring feature data;

[0015] Step S13: performing multi-dimensional feature cross-fusion on the multi-dimensional monitoring feature data to generate fused feature data;

[0016] Step S14: constructing a channel feature interactive network based on the fused feature data to generate a channel feature focus map;

[0017] Step S15: Perform spatial nesting processing on the channel feature focus map to obtain channel operation data.

[0018] The present invention can capture key monitoring data in different dimensions by acquiring water transport project monitoring data and extracting multi-dimensional features, thereby improving the accuracy of data processing, laying the foundation for subsequent analysis, and comprehensively reflecting the operating status of water transport projects. The cross-fusion of multi-dimensional monitoring feature data integrates key information of different dimensions. Through cross-processing of features, the phenomenon of data isolation and redundancy is reduced, and the global consistency of data is improved, so that the fused data can more comprehensively reflect the complex dynamic characteristics of the waterway. By constructing a waterway feature interaction network and generating a waterway feature focusing map, the accurate extraction and focusing of waterway features are achieved. Through the generation and focusing processing of feature maps, the accuracy of capturing and analyzing key features of the waterway is improved, and a deep insight into the waterway status is provided. After the waterway feature focusing map is spatially nested, the generated waterway operation data has higher accuracy in spatial and temporal dimensions, providing more detailed basic data for subsequent waterway monitoring and simulation, and enhancing the entire system's ability to accurately analyze the waterway operation status.

[0019] Preferably, step S2 includes the following steps:

[0020] Step S21: performing spatiotemporal feature analysis on the waterway operation data to obtain a ship spatiotemporal feature matrix;

[0021] Step S22: Evolving the ship's spatiotemporal feature matrix into a motion trajectory to generate a continuous trajectory curve of the ship;

[0022] Step S23: performing velocity field analysis on the continuous trajectory curve of the ship to obtain the ship velocity field;

[0023] Step S24: Calculate the ship's speed based on the ship's continuous trajectory curve to generate ship speed data.

[0024] The present invention performs spatiotemporal feature analysis on waterway operation data, and the generated spatiotemporal feature matrix of the ship can comprehensively reflect the dynamic changes of the ship in the time and space dimensions, thereby improving the accuracy of the monitoring data and making the subsequent trajectory evolution analysis more timely and spatially consistent. The motion trajectory evolution of the ship spatiotemporal feature matrix is performed, and the generated continuous trajectory curve of the ship can show the complete motion path of the ship, making the trajectory analysis more coherent, avoiding the breakpoint problem between data, and ensuring the overall analysis of the ship's motion. The ship velocity field analysis can accurately evaluate the real-time speed changes of the ship based on the continuous trajectory curve of the ship, and provide more dynamic ship motion status information, which can not only improve the accuracy of the speed, but also provide a solid basic data for speed calculation. The speed calculation of the continuous trajectory curve of the ship based on the velocity field is performed, and the generated ship speed data has high accuracy and strong real-time performance, which ensures the accurate measurement of the actual sailing speed of the ship and improves the monitoring and scheduling capabilities of the entire water transport system.

[0025] Preferably, step S3 includes the following steps:

[0026] Step S31: extracting hydrological parameters from the waterway operation data to obtain waterway hydrological information;

[0027] Step S32: Analyze the ship's geometric characteristics on the channel operation data to generate ship geometric data;

[0028] Step S33: Calculating the ship immersion depth based on the channel hydrological information and the ship geometry data to obtain the ship immersion depth data;

[0029] Step S34: Deducing the ship load situation based on the ship geometry data according to the ship immersion depth data to generate ship load data.

[0030] The present invention extracts hydrological parameters from channel operation data to obtain channel hydrological information that can accurately reflect changes in the hydrological environment, such as water velocity and water depth. This provides important basic data for real-time monitoring and subsequent analysis of ship operations, improving the system's ability to perceive the hydrological environment. The step of analyzing ship geometric characteristics to generate ship geometric data effectively improves the structural understanding of different types of ships. It can not only handle complex ship shapes, but also provide key data support for subsequent immersion depth calculation and load analysis, enhancing the system's accurate portrayal of ship physical properties. By combining hydrological information with ship geometric data to calculate ship immersion depth, the resulting ship immersion depth data can accurately reflect the ship's draft under different hydrological environments, improve the assessment of the ship's adaptability in the channel, and ensure the safety and effectiveness of ship operations. Based on the ship immersion depth data, the ship geometric data is deduced to generate ship load data that can reflect the stress conditions of the ship under different load conditions. This provides an important basis for risk prediction and control in ship operations, improves the system's predictive ability, and ensures the stability and safety of ship operations.

[0031] Preferably, step S34 includes the following steps:

[0032] Analyze the ship's hull stress state based on the ship's immersion depth data and the ship's geometric data to obtain the hull stress state data;

[0033] Perform fluid pressure dynamics numerical simulation on the hull stress state data to generate the hull surface pressure distribution map;

[0034] The center of gravity of the ship is located by using the pressure distribution map on the hull surface to obtain the center of gravity of the ship;

[0035] Perform structural stress analysis on the hull stress state data to obtain the hull deformation stress field;

[0036] The load distribution at the center of gravity of the ship is deduced based on the hull deformation stress field to generate ship load data.

[0037] The present invention analyzes the stress state of the hull by performing a stress state analysis on the ship's geometric data based on the ship's immersion depth data, which can accurately reflect the stress distribution of the hull under different environmental and load conditions, improves the understanding of the stress state of the hull, and provides a solid technical foundation for subsequent pressure distribution simulation and center of gravity positioning. The fluid pressure dynamics numerical simulation of the hull stress state data and the generated hull surface pressure distribution map can accurately present the pressure changes on the hull surface. Through high-precision numerical simulation means, the force prediction ability of the ship in a complex water flow environment is optimized, and the system's assessment of the safety of ship operation is improved. By locating the center of gravity of the hull based on the hull surface pressure distribution map, the center of gravity position of the ship is calculated efficiently and accurately to ensure The stability of ship operation provides key data for subsequent load distribution deduction, enhances the management ability of ship balance and safety performance, performs structural stress analysis on the hull force status data, and the obtained hull deformation stress field can reflect the deformation of the hull under different load conditions, providing key support for ship structural health monitoring, discovering potential structural risks in advance, and improving the ship's stress resistance under extreme conditions. The load distribution deduction of the ship's center of gravity position based on the hull deformation stress field, the generated ship load data can dynamically reflect the hull status under different load conditions, providing intelligent technical support for ship load optimization, navigation stability and safety, and enhancing the real-time analysis capability of the overall monitoring system.

[0038] Preferably, step S4 includes the following steps:

[0039] Step S41: performing multi-source fusion processing on the ship speed data and the ship load data to obtain a comprehensive ship state vector;

[0040] Step S42: Performing hydrodynamic modeling on the ship's comprehensive state vector and channel operation data to generate channel flow field distribution data;

[0041] Step S43: performing global channel simulation processing on the channel flow field distribution data to obtain a simulated channel environment field;

[0042] Step S44: performing a multi-ship collaborative sailing simulation on the ship comprehensive state vector based on the simulated channel environment field to obtain simulated multi-ship sailing data;

[0043] Wherein, step S44 includes the following steps:

[0044] Perform multi-ship initial position simulation on the simulated channel environment field according to the ship comprehensive state vector to generate a simulated multi-ship channel environment;

[0045] Model the interaction between ships in the simulated multi-ship channel environment to obtain a multi-ship interaction model;

[0046] Perform time-series advancement simulation on the multi-ship interaction model to generate simulated multi-ship driving data.

[0047] The present invention generates a comprehensive ship state vector through multi-source fusion processing of ship speed data and ship load data, realizes the organic combination of different data dimensions, more comprehensively characterizes the overall operating status of the ship, enhances the response capability of the channel monitoring system to complex ship dynamics, and improves the system's adaptability to the actual navigation environment. The ship's comprehensive state vector and channel operation data are used for hydrodynamic modeling. The generated channel flow field distribution data can accurately depict the hydrodynamic conditions in the channel, provide high-resolution fluid mechanics basic data for channel simulation, improve the simulation authenticity of the channel environment, and provide high-quality input for simulation analysis. The global channel simulation processing can generate a simulated channel environment field, fully simulate the dynamic changes of the actual channel and the complex interactions between ships, and improve the system's adaptability to multi-ship navigation. The prediction and optimization effects can help solve the channel characteristics that are difficult to capture in actual operations, making channel monitoring more accurate and forward-looking. The multi-ship collaborative navigation simulation based on the simulated channel environment field can accurately predict the movement of multiple ships in the channel. Through multi-ship interaction modeling and time-series advancement simulation to generate multi-ship driving data, potential problems such as collisions and congestion of ships can be identified in advance, providing strong support for actual operations, thereby improving the safety and operation efficiency of the overall system. The interaction modeling between ships ensures that the interactive behavior of multiple ships in the simulation environment can be accurately simulated, laying a solid technical foundation for the construction of a simulated multi-ship channel environment, so that the mutual influence of ships under complex navigation conditions can be more efficiently evaluated and optimized, effectively enhancing the channel safety prediction capability.

[0048] Preferably, step S5 includes the following steps:

[0049] Step S51: performing deep learning model training on simulated multi-ship travel data based on ship speed data and ship load data to obtain a waterway state prediction model;

[0050] Step S52: Performing twin network architecture transformation on the waterway state prediction model to obtain a waterway twin prediction network;

[0051] Step S53: Perform channel situation fusion modeling on the channel twin prediction network and simulated multi-ship driving data to obtain a channel analysis twin model.

[0052] The present invention generates a channel state prediction model by training a deep learning model of simulated multi-ship driving data. It can effectively capture and learn the complex dynamic characteristics of multi-ship driving processes, improve the system's ability to predict the behavior of ships during navigation, and provide high-precision predictions for future navigation states, effectively reducing shipping risks. The channel state prediction model is transformed into a twin network architecture to form a channel twin prediction network, so that the model has real-time feedback and self-optimization capabilities, thereby more intelligently handling complex channel dynamic environments and enhancing the prediction system's response speed and accuracy to environmental changes. Based on the channel twin prediction network and simulated multi-ship driving data, channel situation fusion modeling is performed to generate a channel analysis twin model, which enables the channel monitoring system to have the ability to predict channel conditions. The comprehensive analysis capability of the overall situation of the channel, by integrating the driving data of multiple ships and environmental characteristics, can better predict and optimize the operation status of the channel, and achieve precise control of the channel situation. Through the combination of the twin network and the actual operation situation, the channel analysis twin model can simulate the complex dynamic changes of the channel, so that the system has stronger environmental adaptability, helps to predict potential safety issues, improves the real-time scheduling capability of the channel management system, and achieves efficient response to complex navigation environments. Through the continuous interaction and training of the channel twin prediction network and actual data, the system has the ability to dynamically adjust and optimize the channel status, and continuously predict and update according to the real-time channel situation, providing technical support for the safe driving of ships and the stable operation of the channel, and effectively improving the intelligence level of the water transport system.

[0053] Preferably, step S6 includes the following steps:

[0054] Step S61: using the waterway analysis twin model to perform water transport state analysis on the simulated multi-ship travel data to obtain a multi-ship collaborative navigation state tensor;

[0055] Step S62: performing abnormal conflict prediction on the multi-ship cooperative navigation state tensor to obtain navigation risk prediction data;

[0056] Step S63: performing a safety analysis on the water transport project based on the ship risk prediction data, the ship speed data, and the ship load data to generate water transport project safety data;

[0057] Step S64: Make safety response scheduling decisions for the water transport project based on the water transport project safety data, and build a water transport monitoring and scheduling strategy to perform digital monitoring and analysis of the water transport project.

[0058] The present invention uses the twin model of waterway analysis to analyze the water transport status of simulated multi-ship driving data, generates a multi-ship collaborative navigation state tensor, accurately captures the collaborative relationship between multiple ships, and provides accurate data support for multi-ship interaction in complex water transport environments, thereby improving navigation safety and efficiency. The multi-ship collaborative navigation state tensor is used to predict abnormal conflicts and generate navigation risk prediction data, thereby identifying potential conflicts and abnormal situations in advance and enhancing the predictability of shipping monitoring. Accidents can be effectively avoided through early risk identification and early warning. A comprehensive safety analysis of water transport projects is conducted based on navigation risk prediction data, ship speed data, and ship load data, and a water transport project is generated. It takes into account the dynamic operation status of ships and integrates real-time environmental factors to form a comprehensive safety assessment mechanism, providing a scientific basis for the safe operation of water transport projects. It makes safety response scheduling decisions based on the safety data of water transport projects, builds a water transport monitoring and scheduling strategy, and effectively responds to safety risks in the water transport process through real-time scheduling and decision optimization to ensure the continuity and stability of waterway operation. It uses the generated water transport monitoring and scheduling strategy to perform digital monitoring and analysis of water transport projects, so that the system has automated intelligent decision-making capabilities. It makes timely adjustments and optimizations based on real-time monitoring data and prediction results to ensure the safe and efficient operation of waterways and ships.

[0059] Preferably, step S63 includes the following steps:

[0060] The ship speed data is evaluated for safety based on a preset ship speed limit threshold. When the ship speed data exceeds the preset ship speed limit threshold, the ship speed data is judged to be dangerous speed data;

[0061] Performing a safety assessment on the ship load data based on a preset ship weight limit threshold; when the ship load data exceeds the preset ship weight limit threshold, the ship load data is judged to be overweight load data;

[0062] Conduct safety assessments on water transport projects based on dangerous speed data, overload data, and navigation risk prediction data to generate water transport project safety data.

[0063] The present invention can automatically evaluate the safety of ship speed data and load data based on the preset ship speed limit threshold and weight limit threshold. When the ship speed or load exceeds the set safety range, the system will automatically determine it as dangerous speed or overload, thereby improving the efficiency of safety management and reducing the complexity of manual monitoring. When the ship speed exceeds the speed limit threshold or the load exceeds the weight limit threshold, the system can immediately mark these data as abnormal, timely identify and respond to potential dangerous situations, avoid safety accidents caused by excessive speed or excessive load, and ensure the safe operation of the water transport system. By combining dangerous speed data , overweight load data and shipping risk prediction data, the system can conduct a comprehensive water transport engineering safety assessment, ensure the system's risk perception ability for complex shipping scenarios, provide more accurate and comprehensive safety assessment results, and improve the reliability of overall water transport management. It does not rely on a single data source for safety assessment, but dynamically adjusts the assessment results based on multiple data such as the ship's real-time speed, load and shipping risk prediction to adapt to different shipping conditions and changes, which helps to update the safety status in real time, ensure the safety of waterways and ships under different conditions, and provide real-time safety decision support by generating water transport engineering safety data.

[0064] The present invention further provides a digital monitoring and analysis system for water transport engineering, which is used to execute the digital monitoring and analysis method for water transport engineering described above. The digital monitoring and analysis system for water transport engineering comprises:

[0065] The data fusion module is used to obtain water transport project monitoring data; it performs multi-dimensional feature cross-fusion on multiple water transport project monitoring data and performs waterway focusing processing to obtain waterway operation data;

[0066] The trajectory deduction module is used to evolve the ship's motion trajectory based on the channel operation data, and to calculate the speed to generate the ship's speed data;

[0067] The load analysis module is used to calculate the ship immersion depth based on the channel operation data, perform hull load situation deduction, and generate ship load data;

[0068] The ship evolution module is used to simulate the channel operation data according to the ship speed data and ship load data, and to perform ship evolution to obtain simulated multi-ship travel data;

[0069] The model building module is used to build an analysis engine for simulating multi-ship travel data based on ship speed data and ship load data, and generate a twin model for channel analysis;

[0070] The response scheduling module is used to use the waterway analysis twin model to analyze the water transport status of water transport project monitoring data and perform response scheduling processing to execute digital monitoring and analysis of water transport projects.

[0071] The present invention can effectively integrate and optimize data resources by cross-fusion of multi-dimensional features and channel focusing processing of water transport engineering monitoring data from different sources, thereby improving the integrity and accuracy of data and providing high-quality channel operation data for subsequent analysis. By performing motion trajectory evolution and speed estimation on channel operation data, accurate ship speed data is generated, which supports detailed analysis of ship motion status, more accurately predicts ship behavior, optimizes shipping planning and operation, and provides detailed ship load data for ship immersion depth calculation and load situation deduction, ensuring the stability and safety of ships under various shipping conditions and preventing overloading or other safety hazards. Based on ship speed and load data, overall channel simulation processing is performed to generate simulated multi-ship operations. Based on navigation data, the complex waterway environment and ship behavior are fully simulated to evaluate and optimize the ship's navigation strategy under various conditions. By building an analysis engine based on speed and load data, a channel analysis twin model is generated, which provides accurate channel situation prediction, supports in-depth analysis and prediction, and improves the response capability to channel changes. The channel analysis twin model is used to analyze water transport status and perform response scheduling, realizing dynamic monitoring and management of the real-time status of water transport projects, improving the safety and operational efficiency of the water transport system, and enhancing the ability to respond to emergencies. It not only improves the efficiency of data processing and analysis, but also enhances the monitoring capability of the overall status of water transport projects, thereby significantly improving the operational safety and management level of water transport projects. BRIEF DESCRIPTION OF THE DRAWINGS

[0072] Figure 1 A schematic diagram of the steps of a digital monitoring and analysis method for water transport engineering;

[0073] Figure 2 Detailed implementation flow chart of step S2;

[0074] Figure 3 Detailed implementation flow chart of step S3;

[0075] The purpose, features and advantages of the present invention will be further described with reference to the accompanying drawings and in conjunction with the embodiments. DETAILED DESCRIPTION

[0076] The following is a clear and complete description of the technical method of the present invention in conjunction with the accompanying drawings. It is obvious that the embodiments described are part of the embodiments of the present invention, but not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without making any creative efforts are within the scope of protection of the present invention.

[0077] In addition, the accompanying drawings are merely schematic illustrations of the present invention and are not necessarily drawn to scale. Identical reference numerals in the figures denote identical or similar parts, and thus repetitive descriptions thereof will be omitted. Some of the blocks shown in the accompanying drawings are functional entities that do not necessarily correspond to physically or logically separate entities. These functional entities may be implemented in software, in a single hardware module or integrated circuit, or in different network and / or processor and / or microcontroller approaches.

[0078] It should be understood that although the terms "first," "second," and the like may be used herein to describe various elements, these elements should not be limited by these terms. These terms are used solely to distinguish one element from another. For example, a first element may be referred to as a second element, and similarly, a second element may be referred to as a first element, without departing from the scope of the exemplary embodiments. The term "and / or" as used herein includes any and all combinations of one or more of the listed associated items.

[0079] To achieve the above purpose, see Figures 1 to 3 A digital monitoring and analysis method for water transport engineering includes the following steps:

[0080] Step S1: Acquire water transport engineering monitoring data; perform multi-dimensional feature cross-fusion on multiple water transport engineering monitoring data, and perform waterway focusing processing to obtain waterway operation data;

[0081] Step S2: Evolving the ship's motion trajectory based on the channel operation data, and performing speed estimation to generate ship speed data;

[0082] Step S3: Calculate the ship immersion depth based on the channel operation data, and perform hull load situation deduction to generate ship load data;

[0083] Step S4: performing overall channel simulation processing on the channel operation data according to the ship speed data and the ship load data, and performing ship sailing evolution to obtain simulated multi-ship sailing data;

[0084] Step S5: constructing an analysis engine for the simulated multi-ship travel data based on the ship speed data and the ship load data to generate a channel analysis twin model;

[0085] Step S6: Use the waterway analysis twin model to analyze the water transport status of the water transport project monitoring data and perform response scheduling processing to perform digital monitoring and analysis of the water transport project.

[0086] In the embodiment of the present invention, see Figure 1, which is a schematic flow chart of the steps of a digital monitoring and analysis method for a water transport project according to the present invention. In this example, the digital monitoring and analysis method for a water transport project includes the following steps:

[0087] Step S1: Acquire water transport engineering monitoring data; perform multi-dimensional feature cross-fusion on multiple water transport engineering monitoring data, and perform waterway focusing processing to obtain waterway operation data;

[0088] In this embodiment, data is collected from sensors, satellite monitoring systems, and on-site cameras from various sources. This data typically includes hydrological data (e.g., water level, flow velocity), environmental data (e.g., weather conditions, wind speed), vessel data (e.g., location, speed, load), and waterway data (e.g., waterway depth, obstacle location). After data acquisition, multi-dimensional feature cross-fusion is performed on multiple waterway engineering monitoring data. Specifically, different data sources are normalized, and core features are extracted using dimensionality reduction techniques such as principal component analysis (PCA). Data fusion algorithms (e.g., weighted averaging and Kalman filtering) are used to synthesize the features of each data source to generate fused feature data. This fused feature data is then subjected to channel focusing processing, and spatial interpolation techniques (e.g., Kriging interpolation) are used to map the data to a specific waterway model. Ultimately, waterway operation data is obtained.

[0089] Step S2: Evolving the ship's motion trajectory based on the channel operation data, and performing speed estimation to generate ship speed data;

[0090] In this embodiment, a time series analysis method is used to model the historical motion data of the ship, which is preprocessed using a moving average method or an exponential smoothing method. Then, the trajectory data of different time steps are aligned using a dynamic time warping (DTW) algorithm. Based on the processed data, a trajectory prediction model (such as a long short-term memory network (LSTM)) is applied to predict the future motion trajectory of the ship. The speed is estimated by calculating the displacement changes of the ship in different time periods. The speed is estimated using a linear regression model or a support vector regression (SVR) algorithm to generate ship speed data.

[0091] Step S3: Calculate the ship immersion depth based on the channel operation data, and perform hull load situation deduction to generate ship load data;

[0092] In this embodiment, the ship immersion depth is calculated based on the channel operation data. This is accomplished by obtaining the geometric characteristics of the ship and the hydrological parameters of the channel. The hull model and hydrological data are used for calculation to determine the ship immersion depth. Based on the ship immersion depth data, the hull load situation is deduced. The hull structure is analyzed using finite element analysis (FEA) tools. Combined with the ship load and environmental conditions, the stress and deformation of the hull under different operating conditions are calculated to generate ship load data.

[0093] Step S4: performing overall channel simulation processing on the channel operation data according to the ship speed data and the ship load data, and performing ship sailing evolution to obtain simulated multi-ship sailing data;

[0094] In this embodiment, a flow field model of the waterway is established using a CFD tool. The ship's speed and load data are input into the model to perform a fluid dynamics simulation of the ship. Numerical simulation techniques (such as the finite volume method) are used to simulate the flow of ships in the waterway, generating simulated multi-ship travel data, including dynamic information on the coordinated travel of multiple ships in the waterway. The simulation results can be used to analyze the interactions between ships and their impact on the waterway environment.

[0095] Step S5: constructing an analysis engine for the simulated multi-ship travel data based on the ship speed data and the ship load data to generate a channel analysis twin model;

[0096] In this embodiment, an analysis engine is constructed for simulated multi-ship driving data based on ship speed data and ship load data, and machine learning technology (such as deep neural networks) is used to train the simulated data to construct a channel analysis twin model. The training data is divided into a training set and a validation set. The model is optimized through the back propagation algorithm. The generated channel analysis twin model can predict future channel conditions and provide real-time analysis capabilities of ship behavior and channel status.

[0097] Step S6: Use the waterway analysis twin model to analyze the water transport status of the water transport project monitoring data and perform response scheduling processing to perform digital monitoring and analysis of the water transport project.

[0098] In this embodiment, real-time monitoring data is input into the waterway analysis twin model for status prediction. The model analysis results include the operating status of the ship, the usage of the waterway, and safety hazards. Based on the analysis results, response scheduling processing is implemented to generate a scheduling strategy, including suggestions for adjusting the ship's route, alarm triggering, and emergency response measures. The generated scheduling strategy is applied to actual operations to optimize the operating efficiency and safety of water transport projects.

[0099] Preferably, step S1 includes the following steps:

[0100] Step S11: Acquire water transport engineering monitoring data;

[0101] Step S12: extracting features from a plurality of water transport engineering monitoring data to obtain multi-dimensional monitoring feature data;

[0102] Step S13: performing multi-dimensional feature cross-fusion on the multi-dimensional monitoring feature data to generate fused feature data;

[0103] Step S14: constructing a channel feature interactive network based on the fused feature data to generate a channel feature focus map;

[0104] Step S15: Perform spatial nesting processing on the channel feature focus map to obtain channel operation data.

[0105] In this embodiment, obtaining water transport engineering monitoring data includes collecting raw data from a variety of data sources (such as sensors, satellite monitoring systems, weather stations, cameras, etc.). The information collected by these data sources includes water level, flow rate, weather conditions, ship position, speed, load and channel status. The data collection process uses high-precision sensors to monitor various environmental and ship indicators in real time. Data transmission sends real-time monitoring data to the central data processing system through a wireless communication network. During the processing, the raw data will undergo pre-processing steps such as denoising, interpolation and data cleaning to ensure the accuracy and consistency of the data. The collected data is marked with timestamps and spatial coordinates and stored in a database. Feature extraction is performed on multiple water transport engineering monitoring data, which involves extracting meaningful indicators from the raw monitoring data. Feature extraction algorithms (such as statistical analysis, Fourier transform, wavelet transform) are used to extract key features from raw data such as water level, flow rate, and ship position. These features include but are not limited to water flow velocity, Traffic flow changes, ship position changes, speed fluctuations, etc., use data processing tools to standardize and normalize the extracted features so that data from different sources can be unified on a comparable scale. The data after feature extraction and standardization form multi-dimensional monitoring feature data, and multi-dimensional feature cross-fusion is performed on the multi-dimensional monitoring feature data. The fusion algorithm is used to synthesize multiple feature data into a comprehensive data set. The cross-fusion method is selected, such as principal component analysis (PCA) or feature selection algorithm, to reduce the data dimension and retain the main features. The data from different sources are fused using data fusion technology (such as weighted fusion, Kalman filtering). The fusion process eliminates data redundancy and noise and enhances data representativeness. By calculating the weight of each feature and applying these weights to the fusion process, fused feature data is generated. This fused feature data integrates various types of information from multidimensional monitoring data. Graph neural networks (GNNs) or convolutional neural networks (CNNs) are used to process the fused feature data and construct a waterway feature interaction network. During the construction process, the fused feature data is mapped to the waterway network model through graph convolution operations, and the relationship between feature nodes and edges is established to capture the complex interactions between features. The spatial structure of the waterway is represented by the adjacency matrix and the feature matrix. The model parameters are optimized through network training to obtain a waterway feature focus map. The waterway feature focus map shows the relationship and interaction between features. Spatial interpolation techniques (such as Kriging interpolation) are used to expand the data in the waterway feature focus map to a finer spatial grid. Through spatial interpolation, higher-resolution data can be generated based on the waterway feature map to capture local changes in the waterway. Then, spatial data analysis tools are used for spatial nesting processing, and the processed data is mapped to the actual waterway environment model. Through further processing of the spatially nested data, the generated waterway operation data contains detailed waterway status information.

[0106] Preferably, step S2 includes the following steps:

[0107] Step S21: performing spatiotemporal feature analysis on the waterway operation data to obtain a ship spatiotemporal feature matrix;

[0108] Step S22: Evolving the ship's spatiotemporal feature matrix into a motion trajectory to generate a continuous trajectory curve of the ship;

[0109] Step S23: performing velocity field analysis on the continuous trajectory curve of the ship to obtain the ship velocity field;

[0110] Step S24: Calculate the ship's speed based on the ship's continuous trajectory curve to generate ship speed data.

[0111] As an example of the present invention, see Figure 2 In this example, step S2 includes:

[0112] Step S21: performing spatiotemporal feature analysis on the waterway operation data to obtain a ship spatiotemporal feature matrix;

[0113] In this example, the waterway operation data is divided into time series and spatial series data. Spatiotemporal data analysis tools are used to decompose the time series data, grouping the data by time intervals to extract time-related features, such as trend components, cyclical components, and residual components. Spatial series analysis is then performed, and spatial analysis tools are used to extract spatial features, such as spatial distribution density and hotspots. The time series and spatial features are integrated to construct a spatiotemporal feature matrix to represent the state of a ship at different time points and spatial locations. This matrix contains information such as the ship's speed, position, and current velocity.

[0114] Step S22: Evolving the ship's spatiotemporal feature matrix into a motion trajectory to generate a continuous trajectory curve of the ship;

[0115] In this embodiment, a trajectory smoothing algorithm (such as a Kalman filter) is applied to filter the original trajectory data to remove noise and outliers, and a time series modeling tool (such as an ARIMA model (autoregressive integrated moving average model)) is used to model the motion trajectory of the ship to predict the future motion position of the ship. Combined with a trajectory evolution algorithm (such as a Bayesian filter or a particle filter), continuous trajectory curves of the ship are generated. These curves represent the continuous motion path of the ship in time. The trajectory curves are smoothed by interpolation technology (such as spline interpolation) to accurately represent the motion trajectory of the ship.

[0116] Step S23: performing velocity field analysis on the continuous trajectory curve of the ship to obtain the ship velocity field;

[0117] In this embodiment, position and time data points are extracted from the continuous trajectory curve. Velocity field analysis methods (such as numerical differentiation) are used to calculate the velocity variation between each position point. Fluid dynamics simulation tools (such as OpenFOAM) are then used to model the velocity field and generate ship velocity field data. This velocity field data represents the velocity distribution of the ship along the channel. Velocity vectors at each position point are calculated to determine the spatial distribution of the velocity field. During the analysis process, the velocity field data is combined with other channel characteristics (such as water velocity and vessel load) to ensure the accuracy and completeness of the velocity field.

[0118] Step S24: Calculate the ship's speed based on the ship's continuous trajectory curve to generate ship speed data.

[0119] In this embodiment, the ship's velocity vector information is extracted from the ship's velocity field data. This velocity information is aligned with the continuous trajectory curve. The velocity field data is then mapped to the ship's trajectory curve using a velocity-position relationship model (e.g., a velocity field interpolation model). Numerical analysis tools (e.g., the PDE toolbox in MATLAB) are then used to interpolate and extrapolate the velocity field data to generate the ship's speed data at each time point. This speed data represents the ship's actual speed at a specific location. The accuracy of the extrapolated speed is verified by comparing it with actual observation data.

[0120] Preferably, step S3 includes the following steps:

[0121] Step S31: extracting hydrological parameters from the waterway operation data to obtain waterway hydrological information;

[0122] Step S32: Analyze the ship's geometric characteristics on the channel operation data to generate ship geometric data;

[0123] Step S33: Calculating the ship immersion depth based on the channel hydrological information and the ship geometry data to obtain the ship immersion depth data;

[0124] Step S34: Deducing the ship load situation based on the ship geometry data according to the ship immersion depth data to generate ship load data.

[0125] As an example of the present invention, see Figure 3 In this example, step S3 includes:

[0126] Step S31: extracting hydrological parameters from the waterway operation data to obtain waterway hydrological information;

[0127] In this embodiment, raw data related to hydrology, including water depth, water temperature, flow rate and other information, is extracted from the waterway operation data. Hydrological analysis tools (such as the HydroML library in Python) are used to extract hydrological parameters. The specific operations include applying data from water depth sensors and using statistical analysis methods (such as mean and standard deviation) to calculate the distribution of water depth changes. For water temperature and flow rate data, data cleaning techniques (such as denoising algorithms) are used to process outliers to ensure data accuracy. The extracted hydrological data are mapped to a spatial grid through an interpolation algorithm (such as bilinear interpolation) to generate a complete waterway hydrological information map, which includes spatial distribution data of water depth, flow rate and water temperature.

[0128] Step S32: Analyze the ship's geometric characteristics on the channel operation data to generate ship geometric data;

[0129] In this embodiment, geometric feature data, including hull length, width, draft, etc., are extracted from ship-related data. Image processing tools (such as the OpenCV library) are used to process the ship's image data to extract the hull outline and geometric dimensions. Computer vision techniques (such as edge detection and contour extraction) are used to obtain the ship's geometric parameters. CAD software (such as AutoCAD) is used for geometric modeling to accurately describe the ship's structural features. The parsed geometric data is then organized into a structured data format (such as a CSV file).

[0130] Step S33: Calculating the ship immersion depth based on the channel hydrological information and the ship geometry data to obtain the ship immersion depth data;

[0131] In this embodiment, the immersion depth is calculated using fluid dynamics formulas in combination with a waterway hydrographic diagram and ship geometry data. By applying a fluid dynamics tool (such as ANSYS Fluent), the buoyancy of the ship at different water depths is simulated to calculate the actual immersion depth of the ship. The specific steps include inputting the ship's geometry parameters, waterway depth data, and flow conditions, running a fluid dynamics simulation, obtaining the immersion depth of the ship, comparing the simulation results with actual observation data, calibrating the model to improve calculation accuracy, and generating a ship immersion depth data table.

[0132] Step S34: Deducing the ship load situation based on the ship geometry data according to the ship immersion depth data to generate ship load data.

[0133] In this embodiment, the ship's immersion depth data is combined with the ship's geometric data, and load calculations are performed using a structural mechanics model. A finite element analysis tool (such as ANSYS Workbench) is used to perform structural analysis on the hull, simulating the hull stress distribution under different load conditions. Specific operations include inputting the ship's geometric data, immersion depth data, and load conditions, running a structural analysis simulation, calculating the hull's load situation, generating a hull force distribution diagram, describing the stress distribution at various locations on the hull, and using a load deduction model (such as a load distribution model) to predict changes in the ship's load under different conditions, thereby generating a ship load data table.

[0134] Preferably, step S34 includes the following steps:

[0135] Analyze the ship's hull stress state based on the ship's immersion depth data and the ship's geometric data to obtain the hull stress state data;

[0136] Perform fluid pressure dynamics numerical simulation on the hull stress state data to generate the hull surface pressure distribution map;

[0137] The center of gravity of the ship is located by using the pressure distribution map on the hull surface to obtain the center of gravity of the ship;

[0138] Perform structural stress analysis on the hull stress state data to obtain the hull deformation stress field;

[0139] The load distribution at the center of gravity of the ship is deduced based on the hull deformation stress field to generate ship load data.

[0140] In this embodiment, the ship's immersion depth data is combined with the ship's geometry data, and a structural mechanics model is used to perform a stress analysis on the hull. Specifically, using a finite element analysis tool (such as ANSYS Mechanical), the hull's geometry data is imported into the model, boundary conditions and loading conditions are set for the hull, and then the ship's immersion depth data is input. By setting fluid pressure, gravity, and other forces, an analysis is run to calculate the stress state of the hull under these conditions. Based on the hull's geometric characteristics, material properties, and applied external forces, the hull's stress state data is generated, including the stress and deformation of each component. This hull stress state data is then input into a fluid dynamics simulation tool (such as ANSYS Fluent). The simulation tool predicts the pressure distribution on the hull surface by solving fluid dynamics equations. The specific operation steps include setting the boundary conditions of the fluid domain, meshing the hull surface, and taking the hull force state data as the initial conditions, running the fluid pressure simulation, and calculating the pressure distribution of the hull in the fluid environment by numerical methods to obtain the hull surface pressure distribution map, wherein the hull surface pressure distribution map shows the fluid pressure intensity at different positions of the hull, reflecting the force situation of the hull in actual operation, using image processing technology to analyze the hull surface pressure distribution map, applying image processing tools (such as the image analysis toolbox in MATLAB), converting the pressure distribution map into a pressure matrix, and determining the center of gravity of the hull by calculating the center of mass of the pressure matrix. The specific method includes using the pressure value of each point in the image and its coordinates to calculate Calculate the weighted center of mass position, that is, the pressure values of all points in the pressure distribution diagram are multiplied by their coordinates and then averaged to obtain the position coordinates of the hull's center of gravity. Input the hull stress state data into the structural analysis software (such as ABAQUS). By establishing a three-dimensional finite element model, setting parameters such as the elastic modulus and yield strength of the hull material, and using the hull stress state data as the load condition, perform structural stress analysis. Specific operations include defining the geometry, meshing, boundary conditions, and load conditions of the analysis model, running stress analysis simulation, calculating the stress distribution at various parts of the hull, and obtaining hull deformation stress field data. The hull deformation stress field data is combined with the ship's center of gravity position and analyzed using a load distribution deduction model. Structural analysis tools (such as ANSYS Workbench) are used to process the hull deformation stress field data. The load distribution deduction model is set, and the hull's center of gravity position is used as the key input. Run simulations to calculate the distribution under different load conditions. Specific operations include inputting the hull's deformation stress field data, defining the load distribution calculation method (such as using the finite element method), calculating the hull's stress distribution under different loads, and generating ship load data.

[0141] Preferably, step S4 includes the following steps:

[0142] Step S41: performing multi-source fusion processing on the ship speed data and the ship load data to obtain a comprehensive ship state vector;

[0143] Step S42: Performing hydrodynamic modeling on the ship's comprehensive state vector and channel operation data to generate channel flow field distribution data;

[0144] Step S43: performing global channel simulation processing on the channel flow field distribution data to obtain a simulated channel environment field;

[0145] Step S44: performing a multi-ship collaborative sailing simulation on the ship comprehensive state vector based on the simulated channel environment field to obtain simulated multi-ship sailing data;

[0146] Wherein, step S44 includes the following steps:

[0147] Perform multi-ship initial position simulation on the simulated channel environment field according to the ship comprehensive state vector to generate a simulated multi-ship channel environment;

[0148] Model the interaction between ships in the simulated multi-ship channel environment to obtain a multi-ship interaction model;

[0149] Perform time-series advancement simulation on the multi-ship interaction model to generate simulated multi-ship driving data.

[0150] In this embodiment, the speed and load data from different sources are integrated into a unified format, including the use of data fusion tools for data cleaning and standardization. The first step of data fusion is to align the speed data and load data to ensure the consistency of time stamps. The speed and load data are merged into a comprehensive state vector using a data fusion algorithm (such as weighted average or principal component analysis). The vector contains the comprehensive state information of the ship at a given point in time, including the actual speed, load condition and other relevant dynamic parameters of the ship. A hydrodynamic model including the ship and the channel environment is established using computational fluid dynamics (CFD) tools (such as OpenFOAM). Input the channel operation data into the CFD model, define the boundary conditions and fluid properties of the water area, use the ship parameters (such as speed, load, etc.) in the ship's comprehensive state vector as the model's initial conditions, run the CFD simulation, calculate the forces acting on the ship, and generate channel flow field distribution data, including information such as flow velocity, flow direction, and fluid pressure. Import the channel flow field distribution data into a channel simulation platform (such as COMSOL Multiphysics), establish a global channel environment model within the simulation platform, and configure the flow field distribution data as input conditions. Set the spatial range and time step of the simulation model to ensure that the fluid dynamic characteristics of the entire channel are covered. By running the global channel simulation, calculate and generate the simulated channel environment field, showing the channel's fluid environment under different temporal and spatial conditions, including the flow velocity field, pressure field, and their changes.

[0151] The specific steps of step S44 include:

[0152] Based on the ship parameters in the integrated state vector, the initial positions of multiple ships are set in the simulated channel environment. By inputting the integrated state vector into the simulation platform, the initial position, speed, and heading of each ship are defined, generating a simulated multi-ship channel environment. The initial state of each ship is configured based on the information in the integrated state vector to ensure that the ship position at the beginning of the simulation is consistent with the actual situation. The simulated multi-ship channel environment is then modeled for ship interaction. Multibody dynamics simulation tools (such as MSC Adams) are used to construct the ship interaction model. Collision and avoidance rules and interaction forces between ships are defined, and model parameters are set, including the relative motion, thrust, drag, and hydrodynamic effects of the ships, to form a multi-ship interaction model. A time-series advancement simulation is then performed on the multi-ship interaction model. By running a time-stepping simulation, the dynamic behavior of the ships in the simulation environment is simulated. The numerical solver in the simulation platform is used to calculate the motion trajectories of the ships at different time steps, generating simulated multi-ship movement data. The resulting data includes the ship motion paths, speed changes, and interaction effects.

[0153] Preferably, step S5 includes the following steps:

[0154] Step S51: performing deep learning model training on simulated multi-ship travel data based on ship speed data and ship load data to obtain a waterway state prediction model;

[0155] Step S52: Performing twin network architecture transformation on the waterway state prediction model to obtain a waterway twin prediction network;

[0156] Step S53: Perform channel situation fusion modeling on the channel twin prediction network and simulated multi-ship driving data to obtain a channel analysis twin model.

[0157] In this embodiment, the ship speed data and the ship load data are integrated to form a training sample. The data preprocessing includes standardization, feature selection and data segmentation. The data is divided into a training set, a validation set and a test set. An appropriate deep learning framework (such as TensorFlow (symbolic mathematical system)) is selected to establish a neural network model. The model structure includes a convolutional neural network (CNN) or a long short-term memory network (LSTM), etc., which is used to capture the spatial and temporal features in the data. The training set data is input into the model for training, and the model parameters are optimized to minimize the prediction error. After the training is completed, the hyperparameters are tuned through the validation set, and the performance of the model is evaluated on the test set to ensure that the model can accurately predict the channel status. The basic architecture of the twin network is defined, including two sub-networks with shared weights, each sub-network The model consists of several convolutional, pooling, and fully connected layers to capture the characteristics of the input data. A trained channel state prediction model is used as a baseline model and modified using transfer learning methods. Specific layers of the twin network are added, such as distance and similarity metrics, to compare the similarities and differences between different channel state data. The twin network architecture is then used to train new data, and network parameters are optimized to improve the network's ability to identify and predict channel states. This results in a channel twin prediction network. The twin network model is then applied to simulated multi-ship navigation data to extract characteristic information about channel status. By defining a fusion model architecture, the output of the twin network is fused with the simulated data. This information is then integrated using data fusion methods (such as weighted averaging or a data fusion network) to form a comprehensive channel status model. During the fusion process, the correlation and influence between different data sources are calculated, and the fusion strategy is adjusted to ensure model accuracy. The fusion model is then trained using optimization algorithms (such as gradient descent) to optimize model parameters and ensure that it accurately reflects the comprehensive channel status, resulting in a channel analysis twin model.

[0158] Preferably, step S6 includes the following steps:

[0159] Step S61: using the waterway analysis twin model to perform water transport state analysis on the simulated multi-ship travel data to obtain a multi-ship collaborative navigation state tensor;

[0160] Step S62: performing abnormal conflict prediction on the multi-ship cooperative navigation state tensor to obtain navigation risk prediction data;

[0161] Step S63: performing a safety analysis on the water transport project based on the ship risk prediction data, the ship speed data, and the ship load data to generate water transport project safety data;

[0162] Step S64: Make safety response scheduling decisions for the water transport project based on the water transport project safety data, and build a water transport monitoring and scheduling strategy to perform digital monitoring and analysis of the water transport project.

[0163] In this embodiment, the simulated multi-ship driving data is input into the channel analysis twin model. The multi-layer neural network in the model processes this data to identify and analyze the motion state and interaction of each ship. A deep learning framework (such as TensorFlow) is used to implement the model's reasoning process, including forward propagation of data and feature extraction. The channel analysis twin model simulates the interaction between ships and their performance in different channel environments to generate a multi-dimensional tensor containing information such as ship position, speed, and load to represent the collaborative navigation state of the ships. These tensors provide detailed navigation state information, including the distance between ships, speed changes, and collision risks, forming a multi-ship collaborative navigation state tensor. The motion trajectory data, velocity field data, and mutual distance data of each ship are extracted from the multi-ship collaborative navigation state tensor. Anomaly detection algorithms (such as statistical anomaly detection or deep learning anomaly detection methods) are used to analyze these data. Data-driven models (such as isolation forests, variational autoencoders, or LSTM autoregressive models) are used to identify abnormal patterns in the data, compare them with normal navigation patterns, and predict Detect potential conflicts and abnormal behaviors between ships, generate navigation risk prediction data based on the prediction results, mark the conflict points and their severity, integrate the navigation risk prediction data with the ship speed data and ship load data to form a comprehensive data set, use safety analysis models (such as rule-based decision systems or risk assessment algorithms) to analyze these data, extract features and standardize the data, apply weighted risk models or risk matrix methods, calculate the safety score of each ship, generate water transport project safety data, including risk points, overall risk level and safety assessment of each ship, input the water transport project safety data into the scheduling decision system, and the decision algorithm within the system (such as optimization algorithm or rule engine) processes the data, analyzes the risk level and priority, and generates safety response strategies through multi-objective optimization models or intelligent scheduling algorithms, including adjusting the waterway, optimizing the navigation route, setting warning areas or rescheduling the ship operation time. The generated scheduling strategies are applied to actual water transport projects, and the monitoring system adjusts the waterway and ship operation in real time to ensure the implementation of safety response measures.

[0164] Preferably, step S63 includes the following steps:

[0165] The ship speed data is evaluated for safety based on a preset ship speed limit threshold. When the ship speed data exceeds the preset ship speed limit threshold, the ship speed data is judged to be dangerous speed data;

[0166] Performing a safety assessment on the ship load data based on a preset ship weight limit threshold; when the ship load data exceeds the preset ship weight limit threshold, the ship load data is judged to be overweight load data;

[0167] Conduct safety assessments on water transport projects based on dangerous speed data, overload data, and navigation risk prediction data to generate water transport project safety data.

[0168] In this embodiment, when ship speed data is input into the assessment system, the system compares the speed data with a preset speed limit threshold. The preset ship speed limit threshold can be set according to specific waterway regulations or safety requirements, for example, a safe speed value determined through historical data analysis. A threshold comparison algorithm is used to check each speed data point one by one. If the speed data exceeds the speed limit threshold, it is marked as dangerous speed data. The tools used in this process include data processing software or scripts, using the pandas library in Python for data manipulation and comparison. The generated dangerous speed data will be recorded as a safety issue and trigger an alarm in the system, prompting relevant management personnel to take further safety measures or intervention. When the ship load data is input into the assessment system, the system compares the load data with the preset weight limit threshold. The preset ship weight limit threshold is determined according to the ship design parameters or safety regulations. For example, the threshold is set by calculating the maximum design load of the ship. Using the threshold comparison algorithm, each load data point is checked one by one. If the load data exceeds the weight limit threshold, it is marked as overweight load data. This process uses data processing tools such as the conditional formatting function in Excel or the numpy library in Python for processing and comparison. The generated overweight load data will be recorded as a safety hazard and an alarm will be generated in the system to notify management personnel to take corresponding measures, such as adjusting the load or rescheduling the passage plan. The above data is collected into the safety assessment system. The system uses a weighted comprehensive model or a multi-level risk assessment algorithm to process data. Through weighted average or risk matrix methods, a comprehensive safety score is calculated according to the risk level of each data type. For example, dangerous speed data and overweight load data can be given higher weights because these factors directly affect the safety of the ship. Combined with the ship risk prediction data, the overall safety risk of each ship is evaluated to generate water transport engineering safety data. These safety data include comprehensive risk scores and specific safety recommendations, including speed adjustments, load limits or adjustments to navigation paths. The data analysis and modeling tools used in this process can include statistical analysis software, machine learning models or custom programming implementations. The safety data ultimately generated provides managers with a comprehensive view of the safety status and helps to formulate targeted safety improvement measures.

[0169] The present invention further provides a digital monitoring and analysis system for water transport engineering, which is used to execute the digital monitoring and analysis method for water transport engineering described above. The digital monitoring and analysis system for water transport engineering comprises:

[0170] The data fusion module is used to obtain water transport project monitoring data; it performs multi-dimensional feature cross-fusion on multiple water transport project monitoring data and performs waterway focusing processing to obtain waterway operation data;

[0171] The trajectory deduction module is used to evolve the ship's motion trajectory based on the channel operation data, and to calculate the speed to generate the ship's speed data;

[0172] The load analysis module is used to calculate the ship immersion depth based on the channel operation data, perform hull load situation deduction, and generate ship load data;

[0173] The ship evolution module is used to simulate the channel operation data according to the ship speed data and ship load data, and to perform ship evolution to obtain simulated multi-ship travel data;

[0174] The model building module is used to build an analysis engine for simulating multi-ship travel data based on ship speed data and ship load data, and generate a twin model for channel analysis;

[0175] The response scheduling module is used to use the waterway analysis twin model to analyze the water transport status of water transport project monitoring data and perform response scheduling processing to execute digital monitoring and analysis of water transport projects.

[0176] The present invention can effectively integrate and optimize data resources by cross-fusion of multi-dimensional features and channel focusing processing of water transport engineering monitoring data from different sources, thereby improving the integrity and accuracy of data and providing high-quality channel operation data for subsequent analysis. By performing motion trajectory evolution and speed estimation on channel operation data, accurate ship speed data is generated, which supports detailed analysis of ship motion status, more accurately predicts ship behavior, optimizes shipping planning and operation, and provides detailed ship load data for ship immersion depth calculation and load situation deduction, ensuring the stability and safety of ships under various shipping conditions and preventing overloading or other safety hazards. Based on ship speed and load data, overall channel simulation processing is performed to generate simulated multi-ship operations. Based on navigation data, the complex waterway environment and ship behavior are fully simulated to evaluate and optimize the ship's navigation strategy under various conditions. By building an analysis engine based on speed and load data, a channel analysis twin model is generated, which provides accurate channel situation prediction, supports in-depth analysis and prediction, and improves the response capability to channel changes. The channel analysis twin model is used to analyze water transport status and perform response scheduling, realizing dynamic monitoring and management of the real-time status of water transport projects, improving the safety and operational efficiency of the water transport system, and enhancing the ability to respond to emergencies. It not only improves the efficiency of data processing and analysis, but also enhances the monitoring capability of the overall status of water transport projects, thereby significantly improving the operational safety and management level of water transport projects.

[0177] The present invention is therefore intended to be illustrative and non-restrictive in all respects, with the scope of the invention being defined by the appended claims rather than the foregoing description, and all changes that come within the meaning and range of equivalents of the application documents are intended to be embraced therein.

[0178] The foregoing description is intended only to provide specific embodiments of the present invention, which will enable those skilled in the art to understand and implement the present invention. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present invention. Therefore, the present invention is not intended to be limited to the embodiments shown herein, but is to be construed in the widest possible manner consistent with the principles and novel features disclosed herein.

Claims

1. A digital monitoring and analysis method for water transport engineering, characterized in that: The following steps are involved: Step S1: Acquire water transport engineering monitoring data; perform multi-dimensional feature cross-fusion on multiple water transport engineering monitoring data, and perform waterway focusing processing to obtain waterway operation data; Step S2: Evolving the ship's motion trajectory based on the channel operation data, and performing speed estimation to generate ship speed data; Step S3: Calculate the ship immersion depth based on the channel operation data, and perform hull load situation deduction to generate ship load data; Step S4: performing overall channel simulation processing on the channel operation data according to the ship speed data and the ship load data, and performing ship sailing evolution to obtain simulated multi-ship sailing data; Step S5: constructing an analysis engine for the simulated multi-ship travel data based on the ship speed data and the ship load data to generate a channel analysis twin model; Step S6: Use the waterway analysis twin model to analyze the water transport status of the water transport project monitoring data and perform response scheduling processing to perform digital monitoring and analysis of the water transport project.

2. The digital monitoring and analysis method for water transport engineering according to claim 1 is characterized in that: Step S1 includes the following steps: Step S11: Acquire water transport engineering monitoring data; Step S12: extracting features from a plurality of water transport engineering monitoring data to obtain multi-dimensional monitoring feature data; Step S13: performing multi-dimensional feature cross-fusion on the multi-dimensional monitoring feature data to generate fused feature data; Step S14: constructing a channel feature interactive network based on the fused feature data to generate a channel feature focus map; Step S15: Perform spatial nesting processing on the channel feature focus map to obtain channel operation data.

3. The digital monitoring and analysis method for water transport engineering according to claim 1 is characterized in that: Step S2 includes the following steps: Step S21: performing spatiotemporal feature analysis on the waterway operation data to obtain a ship spatiotemporal feature matrix; Step S22: Evolving the ship's spatiotemporal feature matrix into a motion trajectory to generate a continuous trajectory curve of the ship; Step S23: performing velocity field analysis on the continuous trajectory curve of the ship to obtain the ship velocity field; Step S24: Calculate the ship's speed based on the ship's continuous trajectory curve to generate ship speed data.

4. The digital monitoring and analysis method for water transport engineering according to claim 1 is characterized in that: Step S3 includes the following steps: Step S31: extracting hydrological parameters from the waterway operation data to obtain waterway hydrological information; Step S32: Analyze the ship's geometric characteristics on the channel operation data to generate ship geometric data; Step S33: Calculating the ship immersion depth based on the channel hydrological information and the ship geometry data to obtain the ship immersion depth data; Step S34: Deducing the ship load situation based on the ship geometry data according to the ship immersion depth data to generate ship load data.

5. The digital monitoring and analysis method for water transport engineering according to claim 1 is characterized in that: Step S34 includes the following steps: Analyze the ship's hull stress state based on the ship's immersion depth data and the ship's geometric data to obtain the hull stress state data; Perform fluid pressure dynamics numerical simulation on the hull stress state data to generate the hull surface pressure distribution map; The center of gravity of the ship is located by using the pressure distribution map on the hull surface to obtain the center of gravity of the ship; Perform structural stress analysis on the hull stress state data to obtain the hull deformation stress field; The load distribution at the center of gravity of the ship is deduced based on the hull deformation stress field to generate ship load data.

6. The digital monitoring and analysis method for water transport engineering according to claim 1 is characterized in that: Step S4 includes the following steps: Step S41: performing multi-source fusion processing on the ship speed data and the ship load data to obtain a comprehensive ship state vector; Step S42: Performing hydrodynamic modeling on the ship's comprehensive state vector and channel operation data to generate channel flow field distribution data; Step S43: performing global channel simulation processing on the channel flow field distribution data to obtain a simulated channel environment field; Step S44: performing a multi-ship collaborative sailing simulation on the ship comprehensive state vector based on the simulated channel environment field to obtain simulated multi-ship sailing data; Wherein, step S44 includes the following steps: Perform multi-ship initial position simulation on the simulated channel environment field according to the ship comprehensive state vector to generate a simulated multi-ship channel environment; Model the interaction between ships in the simulated multi-ship channel environment to obtain a multi-ship interaction model; Perform time-series advancement simulation on the multi-ship interaction model to generate simulated multi-ship driving data.

7. The digital monitoring and analysis method for water transport engineering according to claim 1 is characterized in that: Step S5 includes the following steps: Step S51: performing deep learning model training on simulated multi-ship travel data based on ship speed data and ship load data to obtain a waterway state prediction model; Step S52: Performing twin network architecture transformation on the waterway state prediction model to obtain a waterway twin prediction network; Step S53: Perform channel situation fusion modeling on the channel twin prediction network and simulated multi-ship driving data to obtain a channel analysis twin model.

8. The digital monitoring and analysis method for water transport engineering according to claim 1 is characterized in that: Step S6 includes the following steps: Step S61: using the waterway analysis twin model to perform water transport state analysis on the simulated multi-ship travel data to obtain a multi-ship collaborative navigation state tensor; Step S62: performing abnormal conflict prediction on the multi-ship cooperative navigation state tensor to obtain navigation risk prediction data; Step S63: performing a safety analysis on the water transport project based on the ship risk prediction data, the ship speed data, and the ship load data to generate water transport project safety data; Step S64: Make safety response scheduling decisions for the water transport project based on the water transport project safety data, and build a water transport monitoring and scheduling strategy to perform digital monitoring and analysis of the water transport project.

9. The digital monitoring and analysis method for water transport engineering according to claim 8, characterized in that: Step S63 includes the following steps: The ship speed data is evaluated for safety based on a preset ship speed limit threshold. When the ship speed data exceeds the preset ship speed limit threshold, the ship speed data is judged to be dangerous speed data; Performing a safety assessment on the ship load data based on a preset ship weight limit threshold; when the ship load data exceeds the preset ship weight limit threshold, the ship load data is judged to be overweight load data; Conduct safety assessments on water transport projects based on dangerous speed data, overload data, and navigation risk prediction data to generate water transport project safety data.

10. A digital monitoring and analysis system for water transport engineering, characterized in that: The digital monitoring and analysis system for water transport engineering according to claim 1 is used to perform the digital monitoring and analysis method for water transport engineering, and the digital monitoring and analysis system for water transport engineering comprises: The data fusion module is used to obtain water transport project monitoring data; it performs multi-dimensional feature cross-fusion on multiple water transport project monitoring data and performs waterway focusing processing to obtain waterway operation data; The trajectory deduction module is used to evolve the ship's motion trajectory based on the channel operation data, and to calculate the speed to generate the ship's speed data; The load analysis module is used to calculate the ship immersion depth based on the channel operation data, perform hull load situation deduction, and generate ship load data; The ship evolution module is used to simulate the channel operation data according to the ship speed data and ship load data, and to perform ship evolution to obtain simulated multi-ship travel data; The model building module is used to build an analysis engine for simulating multi-ship travel data based on ship speed data and ship load data, and generate a twin model for channel analysis; The response scheduling module is used to use the waterway analysis twin model to analyze the water transport status of water transport project monitoring data and perform response scheduling processing to execute digital monitoring and analysis of water transport projects.

Images