A digital twin-based waterway dredging operation control system

Abstract

This invention provides a digital twin-based waterway dredging operation control system, belonging to the field of waterway traffic monitoring and construction technology. Based on the needs of waterway dredging control, the system utilizes artificial intelligence machine vision technology to perceive vessel and construction information in the dredging construction area. It integrates water level, weather, dredging vessel construction and engine room data, radar, AIS, and video data to achieve dynamic digital twin visualization of dredging vessel operations. Through dredging operation optimization algorithms, it monitors dredging vessel operations and the environment in real time, generating optimal construction operation plans. Using risk assessment calculation methods, it monitors vessel risks and the risks of the dredging vessels themselves within the construction area in real time, providing risk warning solutions. This invention enables efficient and precise operation of dredging vessels, improves real-time control and precise construction capabilities within the dredging construction area, and achieves all-weather, all-time, and full-coverage safety supervision of vessel navigation in the construction area, ensuring safe navigation.

Description

Technical Field

[0001] This invention relates to the field of waterway traffic monitoring and construction technology, and in particular to a digital twin-based waterway dredging operation control system. Background Technology

[0002] Water transport is the primary mode of modern trade and transportation. To ensure smooth waterways, dredging vessels are needed to dredge shallow water areas. However, waterway dredging carries numerous risks. Statistics show that accidents occur annually in dredging areas, causing significant property damage and personal injury, greatly impacting businesses and individuals. Analysis of dredging vessel accidents reveals that most are not accidental and possess a degree of predictability. Real-time monitoring, prediction, and early warning systems can help mitigate or avoid losses.

[0003] With the widespread application of new-generation technologies such as the Internet of Things, big data, and artificial intelligence, people have begun to adopt real-time and effective quantitative methods to monitor the real-time status and safety status of dredging vessels, conduct dynamic real-time assessments and predictions, anticipate risks in advance, and take intervention measures to ensure the safety of dredging vessels.

[0004] Currently, existing waterway dredging operation management and control systems mainly focus on monitoring construction areas. They primarily display the operational status of dredging operations based on CAD and GPS location data. However, they lack the ability to perform fine-grained monitoring and information prediction of real-time water levels and risks, as well as risk assessment and early warning capabilities. They cannot provide timely and accurate monitoring and early warning information and therefore cannot meet the needs of refined dredging operation management and control. Summary of the Invention

[0005] The purpose of this invention is to provide a digital twin-based waterway dredging operation control system. Unlike existing vessel safety management products or solutions, this system achieves refined and intelligent control of dredging operations through digital twins. Utilizing big data models and artificial intelligence technology, it optimizes the operations of dredging vessels and provides real-time risk warnings, thereby enabling efficient and precise operations and ensuring safe navigation and efficient construction in the dredging area. This invention enables real-time monitoring, early warning, and optimization of dredging vessels, reducing risks to dredging vessels, improving construction efficiency and quality, and ensuring safe waterway transportation.

[0006] To achieve the above objectives, the present invention provides a digital twin-based waterway dredging operation control system, comprising:

[0007] The basic data module is used to collect, store, and predict data on the dredging vessel itself and its surrounding environment.

[0008] The digital twin visualization module is used to create a digital twin environment model based on the acquired physical model data, and to dynamically and realistically recreate construction vessels, surrounding vessels, water levels, and weather elements in the digital twin scene.

[0009] The operation optimization and early warning module is used to automatically calculate the optimization data of dredging construction vessels based on the information obtained from the digital twin scenario through the dredging operation optimization algorithm model, and to evaluate the safety performance of dredging construction vessels through the risk assessment model, and provide risk early warning emergency plans and services.

[0010] The basic data module includes a real-time monitoring system, a historical database, and a channel water level and scale prediction model. The operation optimization and early warning module includes a dredging operation optimization model, a risk assessment model, and a dredging safety risk early warning model.

[0011] Preferably, a real-time monitoring system is used to acquire the dredging vessel's own construction data and engine room data, the surrounding environment's water level data, weather data, video data, and radar data and AIS data from surrounding vessels; a historical database is used to store the data collected by the real-time monitoring system; and a waterway water level and scale prediction model is used to predict the water level in the dredging vessel's construction area for the next 3-5 days using water level data, rainfall data, and flow data from the real-time monitoring system and the historical database.

[0012] Preferably, the workflow of the channel water level and scale prediction model includes:

[0013] Acquire water level data, rainfall data, and flow rate data, and perform standardization processing;

[0014] Construct the input feature matrix of the multidimensional time series and the output of the input gate;

[0015] The output of constructing the forget gate;

[0016] Generate new candidate memory cell states;

[0017] The current memory unit state is calculated based on the forget gate, the previous memory unit state, and the candidate memory unit states.

[0018] Generate predicted water level data;

[0019] Get the hidden state at the current moment.

[0020] Preferably, the workflow of the digital twin visualization module includes:

[0021] Physical model data of the dredging construction area is obtained by using drone oblique photography or laser point cloud, and then digitally converted to achieve a static digital twin of the construction area.

[0022] Acquire vessel type, name, and real-time heading, speed, and position information, and integrate the data;

[0023] Based on the integrated information data, a model of the dredging construction vessel and a model of the surrounding navigation vessels are built in the digital twin system, and the relevant status information is mapped into the digital twin system to realize a dynamic digital twin of the dredging construction area.

[0024] Connect the digital twin system to the monitoring center for visualization;

[0025] The relevant status information includes the construction status, mechanical status, course, speed, and position information of the dredging vessel, as well as the course, speed, and position information of surrounding vessels.

[0026] Preferably, the dredging operation optimization model is used to automatically calculate the optimization data of dredging construction vessels based on information obtained from the digital twin scenario through the dredging operation optimization algorithm model; the risk assessment model is used to obtain the risks of collision, grounding, and severe weather of dredging vessels and assess the safety performance of dredging construction vessels; and the dredging safety risk early warning module is used to provide early warning information of dredging construction vessels to management personnel.

[0027] Preferably, the workflow of the dredging operation optimization model includes:

[0028] The system uses a digital twin to obtain real-time data on the construction status of dredging vessels and surrounding water levels, weather conditions, and risks.

[0029] Construct a multidimensional time series matrix of construction vessels based on the acquired data;

[0030] Generate the query matrix, key matrix, and value matrix using matrix multiplication, and calculate the attention head;

[0031] Calculate multi-head attention based on the number of attention heads;

[0032] Based on multi-head attention and combined with a multi-dimensional time series matrix, the LayerNorm normalization technique is used to calculate the first layer normalization of the encoder.

[0033] Based on the first layer normalized data of the encoder, combined with the feedforward neural network model FFN, the second layer normalization of the encoder is calculated using the LayerNorm normalization technique.

[0034] Based on the normalized data from the second layer of the encoder, and combined with the feedforward neural network model FFN, the optimized cost and timeframe are calculated.

[0035] Preferred risk assessment models include:

[0036] Ship collision risk assessment consists of the nearest encounter distance and the nearest encounter time.

[0037] Ship grounding risk assessment is used to determine the impact of low water levels on the suspension of dredging operations.

[0038] Severe weather risk assessment consists of strong wind risk and high water level risk.

[0039] Preferably, the workflow for ship collision risk assessment includes:

[0040] The location, speed, course, and current speed and direction of the dredging vessel and its surrounding vessels are obtained in real time through a digital twin system.

[0041] Calculate the nearest encounter distance between the dredging vessel and surrounding vessels based on location information, and obtain the minimum nearest encounter distance;

[0042] Calculate the relative speed and relative encounter time between the dredging vessel and surrounding vessels based on speed, heading information, current speed, and current direction information, and obtain the minimum relative encounter time.

[0043] Based on the minimum nearest encounter distance and relative encounter time, the collision risk is assessed, and high-risk information is sent to the dredging safety risk early warning module.

[0044] Preferably, the workflow for ship grounding risk assessment includes:

[0045] The digital twin system can be used to obtain the predicted water level near the dredging vessel's work area for the next 5 days in real time, and also to obtain the minimum predicted water level for the next 5 days.

[0046] The risk of grounding is assessed by comparing the minimum predicted water level with the minimum draft of the dredging vessel, and high-risk information is sent to the dredging safety risk early warning module.

[0047] The preferred workflow for severe weather risk assessment includes:

[0048] The digital twin system obtains the predicted wind speed and water level of the dredging construction vessel's work area for the next 5 days in real time, and also obtains the maximum predicted wind speed and maximum predicted water level for the next 5 days.

[0049] Assess the risk of strong winds by comparing the maximum predicted wind speed with the maximum wind resistance speed of the dredging vessel.

[0050] Assess the risk of high water levels by comparing the maximum predicted water level with the maximum operating water level of the dredging vessel.

[0051] High-risk information is sent to the dredging safety risk early warning module.

[0052] Therefore, the present invention employs the above-mentioned digital twin-based waterway dredging operation control system, and the beneficial technical effects are as follows:

[0053] (1) By leveraging the Internet of Things and new-generation information technology, we have fully integrated the full-element perception information of dredging construction vessels and their surrounding working conditions, and realized real-time dynamic monitoring of dredging construction vessels and their surrounding working conditions. This has provided construction management personnel with comprehensive, accurate and real-time on-site data support, and effectively improved their ability to control the construction process.

[0054] (2) Using big data analysis and artificial intelligence prediction models, we can accurately predict the future situation of dredging construction vessels and their surrounding conditions, so that construction management personnel can understand the water level changes, weather conditions and vessel operation trends in the construction area in advance, thereby making construction plans and resource allocation in advance, optimizing construction processes and improving construction efficiency.

[0055] (3) Through big data analysis and artificial intelligence prediction models, various risks faced by dredging construction vessels are scientifically assessed, and corresponding risk response measures are taken in advance. It can monitor and warn of risks such as vessel collisions, grounding, and severe weather in real time, providing comprehensive safety protection for construction vessels, reducing the probability of accidents, and ensuring the safe operation of dredging construction vessels.

[0056] (4) Based on multi-dimensional data in the digital twin scenario, the optimization data of dredging construction vessels is automatically calculated through the dredging operation optimization algorithm model, providing scientific decision-making basis for construction management personnel. This helps management personnel to rationally arrange construction tasks, optimize construction paths, and adjust construction parameters, thereby improving construction quality, reducing construction costs, and achieving efficient and refined management of dredging operations. Attached Figure Description

[0057] Figure 1 This is a schematic diagram illustrating the working principle of a digital twin-based waterway dredging operation control system according to the present invention.

[0058] Figure 2 Flowchart for predicting channel water level and dimensions;

[0059] Figure 3 Flowchart for the digital twin visualization module;

[0060] Figure 4 Optimize the flowchart for dredging operations;

[0061] Figure 5 The flowchart shows the nearest encounter distance.

[0062] Figure 6 A timeline of the most recent meetings;

[0063] Figure 7 A flowchart illustrating the risks of ship grounding;

[0064] Figure 8 A flowchart for ship high wind risk;

[0065] Figure 9 A flowchart illustrating the risks of high water levels for ships;

[0066] Figure 10 Flowchart for the dredging safety risk early warning module. Detailed Implementation

[0067] The technical solution of the present invention will be further described below with reference to the accompanying drawings and embodiments.

[0068] Unless otherwise defined, the technical or scientific terms used in this invention shall have the ordinary meaning as understood by one of ordinary skill in the art to which this invention pertains.

[0069] Example 1

[0070] like Figure 1 As shown, a digital twin-based waterway dredging operation control system includes a basic data module, a digital twin visualization module, and an operation optimization and early warning module.

[0071] The basic data module consists of a real-time monitoring system, a historical database, and a channel water level and scale prediction model. It is used to collect, store, and predict data on the dredging vessel itself and its surrounding environment, and to provide business data support for the digital twin visualization module and the operation optimization and early warning module.

[0072] The real-time monitoring system uses equipment such as flow sensors, PLC sensors, water level sensors, weather stations, cameras, marine radar, and AIS terminals to acquire the dredging vessel's own construction data and engine room data, the surrounding environment's water level data, weather data, video data, and the radar data and AIS data of surrounding vessels.

[0073] Historical database is used to store data collected by the real-time monitoring system.

[0074] The waterway water level and scale prediction model uses real-time monitoring systems and historical databases of water level, rainfall, and flow data to predict the water level in the dredging vessel's work area for the next 3-5 days. The specific workflow is as follows: Figure 2 As shown, it includes the following steps:

[0075] Step S11: Obtain water level data Rainfall data and traffic data and use the data Model standardization processing.

[0076] in, For standardized data, This is the original data. This is the average value of the water level data. This represents the standard deviation of the water level data.

[0077] Step S12 involves constructing a multidimensional time series input feature matrix from the standardized water level data, rainfall data, and flow rate data, and then constructing the output of the input gate to obtain the degree of influence of the water level data, rainfall data, and flow rate data on the input information. The calculation method is as follows:

[0078] ;

[0079] ;

[0080] in, For the input feature matrix, For standardized water level data, For standardized rainfall data, Standardized traffic data; The output of the input gate, Here is the weight matrix of the input gate. The hidden state of the previous moment and the input feature matrix at the current time The concatenated vector, This is the correction vector for the input gate. This is the Sigmoid activation function.

[0081] Step S13: Construct the output of the forget gate to obtain the degree of influence of the water level status information of the memory unit at the previous time step on the current time step. The calculation method is as follows:

[0082] ;

[0083] in, For the output of the forget gate, Here is the weight matrix for the forget gate. This is the correction vector for the forget gate.

[0084] Step S14: Generate new candidate memory cell states, calculated as follows:

[0085] ;

[0086] in, This represents a new candidate memory cell state. This is the weight matrix for the candidate memory cell states. This is the correction vector for the candidate memory cell state. It is the hyperbolic tangent activation function.

[0087] Step S15: Calculate the current memory unit state based on the forget gate, the previous memory unit state, and the candidate memory unit states. The calculation method is as follows:

[0088] ;

[0089] in, To remember the state of the memory unit at the current moment, This represents the state of the memory unit from the previous moment.

[0090] Step S16: Generate predicted water level data, the calculation method of which is as follows:

[0091] ;

[0092] in, The output of the output gate is the predicted data such as water level, rainfall, and flow rate. Here is the weight matrix of the output gate. This is the correction vector for the output gate.

[0093] Step S17: Obtain the hidden state at the current moment. The calculation method is as follows:

[0094] .

[0095] The digital twin visualization module is used to create a digital twin environment model corresponding to the actual construction area based on the static targets of the dredging vessel construction area obtained by UAV oblique photography or laser point cloud. It dynamically and realistically restores the construction vessel, surrounding vessels, water level, and weather elements in the digital twin scene, and provides the vessel with a driving perspective and a following perspective, supporting three-dimensional digital twin rotation visualization.

[0096] The digital twin visualization module is used to build static digital twin scenes and dynamically map data in dredging construction areas. The specific implementation process is as follows: Figure 3 As shown, it includes the following steps:

[0097] Step S21: Obtain physical model data of the dredging construction area through UAV oblique photography or laser point cloud, including static targets such as construction area boundaries, anchorages, construction markers, construction vessels, and transport vessels, and perform digital conversion to realize a static digital twin of the construction area.

[0098] Step S22: Obtain the ship type, name, and real-time heading, speed, and location information through multiple devices such as AIS, Beidou, marine radar, and cameras, and integrate the dynamic information into data.

[0099] Data integration refers to the complementary use of four sensing technologies—AIS, BeiDou, marine radar, and cameras—to improve sensing accuracy and obtain precise speed, heading, and positioning information of dredging vessels and surrounding vessels within the construction area. The data integration process involves: using camera video analysis to acquire vessel position and name information; using marine radar to acquire vessel position, speed, and heading information; and using AIS and BeiDou data for error correction. For vessels without AIS terminals, cameras and marine radar are used to collect vessel sensing data; for vessels with interrupted or excessively delayed AIS data transmission, existing AIS and BeiDou data are used to fill in the gaps.

[0100] Step S23: Based on the integrated information data and prior knowledge, build a model of the dredging construction vessel and the surrounding navigation vessels in the digital twin system, and map the construction status, mechanical status, course, speed and position information of the dredging construction vessel into the digital twin system, and map the course, speed and position information of the surrounding vessels into the digital twin system, so as to realize a dynamic digital twin of the dredging construction area.

[0101] Step S24: Connect the digital twin system to the monitoring center for visualization and provide multiple visualization methods for the vessels of interest, including follow view, top view, and driving view. At the same time, the system calculates the distance and risk between the dredging vessel and surrounding vessels based on the dredging vessel's construction status, mechanical status, course, speed, position, and weather information, as well as the course, speed, and position information of surrounding vessels, and pushes this data to the operation optimization and early warning module to provide it with business data support.

[0102] The operation optimization and early warning module consists of a dredging operation optimization model, a risk assessment model, and a dredging safety risk early warning module. Based on information obtained from the digital twin scenario, such as vessel spacing, heading, speed, status, construction conditions, environment, and water level, the dredging operation optimization algorithm model automatically calculates optimized data for dredging vessels, providing decision-making support for construction management personnel. The risk assessment model identifies the risks of collisions, groundings, and severe weather for dredging vessels, assesses their safety performance, and provides corresponding risk warnings, emergency plans, and services based on various types of vessel risks.

[0103] The dredging operation optimization model, based on information obtained from a digital twin scenario including construction status, vessel spacing, course, speed, vessel status, construction conditions, environment, water level, weather, and risks, automatically calculates optimized data for dredging operations using a dredging operation optimization algorithm model. This data is then provided to construction management personnel for decision-making. The specific implementation process is as follows: Figure 4 As shown, it includes the following steps:

[0104] Step S31: Real-time data on the construction status of the dredging vessel and its surrounding water level, weather, and risk data are obtained through a digital twin system.

[0105] Step S32: Based on the construction status data of the dredging vessel and the surrounding water level, weather, and risk data, construct a multi-dimensional time series matrix of the dredging vessel. ;

[0106] in, The time series length is set to 15, meaning data from the past 15 days. The data consists of feature dimensions, including data on water level, weather, and risk.

[0107] Step S33, based on the multidimensional time series matrix Generate the query matrix through matrix multiplication. Key matrix Value matrix The calculation method is as follows:

[0108] ;

[0109] ;

[0110] ;

[0111] in, , , The weights are learnable matrix weights, obtained through supervised learning training. For the attention dimension, the value is... , For the number of attention heads, This refers to feature dimension data.

[0112] Step S34, calculate the attention head, the calculation method is as follows:

[0113] ;

[0114] in, For the first Each attention point can be calculated using the softmax activation function. , , For the first Weight matrix of each attention head.

[0115] Step S35: Calculate multi-head attention based on the number of attention heads. The calculation method is as follows:

[0116] ;

[0117] in, For dimension concatenation function, This is the weight matrix.

[0118] Step S36: Based on multi-head attention and combined with the multi-dimensional time series matrix, use LayerNorm normalization technique to calculate the first layer normalization of the encoder. The calculation method is as follows:

[0119] .

[0120] Step S37: Based on the normalized data of the first layer of the encoder, and combined with the feedforward neural network model FFN, calculate the normalized data of the second layer of the encoder using LayerNorm normalization technology. The calculation method is as follows:

[0121] .

[0122] Step S38: Based on the normalized data from the second layer of the encoder, and combined with the feedforward neural network model FFN, calculate the optimized cost and duration. The calculation method is as follows:

[0123] ;

[0124] in, , The predicted construction cost after model optimization. The predicted construction period is the result of model optimization.

[0125] The risk assessment model identifies the risks of collisions, groundings, and severe weather for dredging vessels, and evaluates the safety performance of dredging operations. The risk assessment model includes collision risk assessment, grounding risk assessment, and severe weather risk assessment.

[0126] Ship collision risk assessment includes the nearest encounter distance and the nearest encounter time.

[0127] The closest encounter distance is used to assess the collision risk between dredging vessels and surrounding vessels in the spatial domain. The specific implementation process is as follows: Figure 5 As shown, it includes the following steps:

[0128] Step S41: Obtain the location information of the dredging construction vessel and its surrounding vessels in real time through the digital twin system.

[0129] Step S42: Based on the position information of the dredging vessel and surrounding vessels, calculate the relative positions of the dredging vessel and surrounding vessels. The closest encounter distance of the ships The calculation method is as follows:

[0130] ;

[0131] in, The radius of the Earth is taken as 637,100 m; The geodetic coordinate system of the dredging construction vessel is its latitude and longitude coordinates. For the dredging of the area around the construction vessel The geodetic coordinates of the ship are its latitude and longitude.

[0132] Step S43: Obtain the minimum nearest encounter distance based on the nearest encounter distance between the dredging vessel and surrounding vessels. The calculation method is as follows:

[0133] ;

[0134] in, The closest approach distance between the dredging vessel and the first vessel in the vicinity. The closest approach distance between the dredging vessel and the second vessel in the vicinity. The closest approach distance between the dredging vessel and the third vessel in the vicinity. To dredge construction vessels and surrounding areas The closest encounter distance of a ship.

[0135] Step S44, the minimum safe distance set in the system in advance ,like The risk assessment module classifies the collision risk as high and sends this risk information to the dredging safety risk early warning module; if The risk assessment module will assess the collision risk as low and will not send information to the dredging safety risk warning module.

[0136] The closest encounter time is used to assess the collision risk between dredging vessels and surrounding vessels in the time domain. The specific implementation process is as follows: Figure 6 As shown, it includes the following steps:

[0137] Step S51: Obtain in real time the speed, heading, flow velocity, and flow direction information of the dredging vessel and surrounding vessels through the digital twin system.

[0138] Step S52, based on the speed of the dredging vessel and the surrounding area of ​​the dredging vessel... The speed and heading information of each ship, combined with the current speed and direction information, are used to calculate the fused relative speed and heading information. The calculation method is as follows:

[0139] ;

[0140] ;

[0141] ;

[0142] ;

[0143] in, To determine the relative speed between the dredging vessels and the water flow, For water flow velocity, To improve the speed of dredging vessels, The angle between the water flow velocity and the due east direction. The angle between the speed of the dredging vessel and due east direction, The relative speed between the dredging vessel and the water flow and the eastward angle; For the dredging of the area around the construction vessel The relative speed of the ship to the water current, For the first The speed of the ships For the first The angle between the ship's speed and due east, For the first The relative speed of the ship to the water flow and the angle between the ship and due east.

[0144] Step S53, based on the relative speed of the dredging vessel and the water flow and the surrounding... The relative speed of the vessel to the water flow is calculated, and the dredging vessel's speed relative to the first vessel is determined. Relative speed of the ships The calculation method is as follows:

[0145] .

[0146] Step S54: Based on the position information of the dredging vessel and surrounding vessels, calculate the relative positions of the dredging vessel and surrounding vessels. The closest encounter distance of the ships The calculation method is as follows:

[0147] .

[0148] Step S55, based on the dredging construction vessel and the surrounding area... The location information of the vessel was used to calculate the relationship between the dredging vessel and the surrounding area. The azimuth of the ship relative to due east The calculation method is as follows:

[0149] , , ;

[0150] ;

[0151] in, Convert the latitude coordinates of the construction vessel to radians. For the first Convert the latitude coordinates of a ship to radians. For the first The difference in longitude coordinates between the ship and the construction vessel is converted into radians.

[0152] Step S56, based on the dredging construction vessel and the surrounding area... The relative distance and relative speed of the vessels were used to calculate the relationship between the dredging vessel and the surrounding vessels. Relative meeting time of the ships The calculation method is as follows:

[0153] .

[0154] Step S57: Obtain the minimum relative encounter time based on the relative encounter time between the dredging vessel and surrounding vessels. The calculation method is as follows:

[0155] ;

[0156] in, The relative encounter time between the dredging vessel and the first vessel in the vicinity. The relative encounter time between the dredging vessel and the second vessel in the vicinity. The relative encounter time between the dredging vessel and the third surrounding vessel. To dredge construction vessels and surrounding areas The relative meeting time of the two ships.

[0157] Step S58, the minimum safe time set in the system in advance ,like The risk assessment module classifies the collision risk as high and sends this risk information to the dredging safety risk early warning module; if The risk assessment module will assess the collision risk as low and will not send information to the dredging safety risk warning module.

[0158] Ship grounding risk assessment is used to determine the impact of low water levels on dredging vessel work stoppages. This is achieved by predicting the water level every minute for the next five days. The specific implementation process is as follows: Figure 7 As shown, it includes the following steps:

[0159] Step S61: Use a digital twin system to obtain real-time data on the area near the dredging vessel's work site for the next 5 days. Predicted water level in minutes The minimum predicted water level for the next 5 days is The calculation method is as follows;

[0160] ;

[0161] in, The forecast water level near the dredging vessel's work area for the first minute of the next 5 days. The forecast water level near the dredging construction area for the 2nd minute of the next 5 days. The predicted water level near the dredging vessel's work area for the 3rd minute of the next 5 days. The predicted water level near the construction area of ​​the dredging vessel at the 7200th minute of the next 5 days.

[0162] Step S62, the minimum draft of the dredging vessel is preset in the system as follows: ,like The risk assessment module will classify the grounding risk as high and send this risk information to the dredging safety risk early warning module; if The risk assessment module will assess the grounding risk as low and will not send information to the dredging safety risk early warning module.

[0163] Severe weather risk assessment consists of strong wind risk and high water level risk.

[0164] High wind risk is used to assess the impact of strong winds on dredging vessels. This is achieved by predicting wind speeds every 15 minutes for the next 5 days. The specific implementation process is as follows: Figure 8 As shown, it includes the following steps:

[0165] Step S71: Obtain the data in real time for the next 5 days from the construction area of ​​the dredging vessel using a digital twin system. Predicted wind speed The maximum predicted wind speed for the next 5 days is The calculation method is as follows:

[0166] ;

[0167] in, The predicted wind speed at the first quarter of the next five days near the dredging construction area. The predicted wind speed near the dredging vessel's work area at the second quarter of the next five days. Forecast wind speeds for the third quarter of the next five days near the dredging site. Forecast wind speed near the construction area of ​​dredging vessels at the 480th moment of the next 5 days.

[0168] Step S72, the maximum wind resistance speed of the dredging vessel is set in advance in the system. ,like The risk assessment module classifies severe weather risk as high risk and sends this risk information to the dredging safety risk early warning module; if The risk assessment module assesses severe weather risk as low risk and does not send information to the dredging safety risk early warning module.

[0169] High water level risk is used to assess the risk of dredging vessels being forced to halt operations. The specific implementation process is as follows: Figure 9 As shown, it includes the following steps:

[0170] Step S81: Use a digital twin system to obtain real-time data on the area surrounding the dredging vessel's work site for the next 5 days. Predicted water level in minutes The maximum predicted water level for the next 5 days is The calculation method is as follows;

[0171] ;

[0172] Step S82, the maximum construction water level for dredging vessels is preset in the system as follows: ,like The risk assessment module classifies severe weather as high-risk and sends this risk information to the dredging safety risk early warning module; if The risk assessment module will assess the grounding risk as low and will not send information to the dredging safety risk early warning module.

[0173] The dredging safety risk early warning module is used to provide management personnel with early warning information about dredging construction vessels, enabling them to make informed decisions. The specific implementation process is as follows: Figure 10 As shown, it includes the following steps:

[0174] Step S91: Connect to the risk assessment module to obtain risk warning information.

[0175] Step S92: Based on the type of risk warning information, automatically generate different risk emergency plans. For example, if the risk warning information is a collision risk, immediately anchor and set sail, while simultaneously driving away vessels sailing near the construction area; if the risk warning information is a grounding risk, based on the predicted grounding time, anchor and set sail at an appropriate time to proceed to other deep-water areas for construction; if the risk warning information is a strong wind risk in severe weather, based on the predicted arrival time of the strong wind, anchor and set sail at an appropriate time to proceed to the designated maritime anchorage for shelter; if the risk warning information is a high water level risk in severe weather, based on the predicted arrival time of the high water level, suspend work and operations on-site.

[0176] Step S93: According to the risk emergency plan, reminders are given through voice broadcasts, flashing alarm lights, text messages, etc., and risk warning information and risk emergency plan are pushed to the three-dimensional digital twin system.

[0177] It is worth noting that the contents not described in detail in this invention are all prior art and are well known to those skilled in the art.

[0178] Therefore, the present invention adopts the above-mentioned digital twin waterway dredging operation control system, which integrates Internet of Things, big data and artificial intelligence technologies to realize real-time monitoring, risk assessment and early warning of dredging construction vessels and their surrounding environment, so as to improve construction efficiency and safety.

[0179] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and not to limit them. Although the present invention has been described in detail with reference to preferred embodiments, those skilled in the art should understand that modifications or equivalent substitutions can still be made to the technical solutions of the present invention, and these modifications or equivalent substitutions cannot cause the modified technical solutions to deviate from the spirit and scope of the technical solutions of the present invention.

Claims

1. A digital-twin-based fairway dredging operation management and control system, characterized by, The application relates to a digital twin system for dredging construction ship safety management, which comprises the following: a basic data module for collecting, storing and predicting data of a dredging construction ship and surrounding environment; a digital twin visualization module for making a digital twin environment model according to obtained physical model data, and dynamically and truly restoring the construction ship, surrounding ships, water level and weather elements in the digital twin scene; an operation optimization and early warning module for automatically calculating optimization data of the dredging construction ship through a dredging operation optimization algorithm model according to information obtained from the digital twin scene, and evaluating the safety performance of the dredging construction ship through a risk assessment model, and providing a risk early warning emergency plan and service; the basic data module comprises a real-time monitoring system, a historical database and a channel water level and scale prediction model, and the operation optimization and early warning module comprises a dredging operation optimization model, a risk assessment model and a dredging safety risk early warning model; the dredging operation optimization model is used for automatically calculating optimization data of the dredging construction ship through a dredging operation optimization algorithm model according to information obtained from the digital twin scene; the risk assessment model is used for obtaining the risks of collision, grounding and severe weather of the dredging ship, and evaluating the safety performance of the dredging construction ship; and the dredging safety risk early warning module is used for providing early warning information of the dredging construction ship to managers; the working process of the dredging operation optimization model comprises the following steps: real-time acquisition of construction state data of the dredging construction ship and water level, weather and risk data around the dredging construction ship through a digital twin system; construction of a multi-dimensional time sequence matrix according to the obtained data; generation of a query matrix, a key matrix and a value matrix through matrix multiplication, and calculation of an attention head; calculation of multi-head attention according to the attention head; calculation of encoder first layer normalization by combining the multi-dimensional time sequence matrix and using a LayerNorm normalization technology according to the multi-head attention; calculation of encoder second layer normalization by combining a feedforward neural network model FFN and using a LayerNorm normalization technology according to the encoder first layer normalization data; calculation of optimized cost and construction period according to the encoder second layer normalization data and the feedforward neural network model FFN.

2. The digital-twin-based fairway dredging operation management and control system according to claim 1, characterized in that, The real-time monitoring system obtains construction data and cabin data of the dredging ship, water level data, weather data and video data of the surrounding environment, and radar data and AIS data of surrounding ships; the historical database is used for storing data collected by the real-time monitoring system; and the channel water level and scale prediction model is used for predicting the water level of a dredging ship construction area in the future 3-5 days by using water level data, rainfall data and flow data in the real-time monitoring system and the historical database.

3. The digital-twin-based fairway dredging operation management and control system according to claim 2, characterized in that, The working process of the channel water level and scale prediction model comprises the following steps: acquisition of water level data, rainfall data and flow data, and standardization processing; construction of an input feature matrix of a multi-dimensional time sequence, and construction of an output of an input gate; construction of an output of a forgetting gate; generation of a new candidate memory cell state; calculation of a memory cell state at a current moment according to the forgetting gate, a memory cell state at a previous moment and the candidate memory cell state; generation of predicted water level data; acquisition of a hidden state at the current moment.

4. The digital-twin-based fairway dredging operation management and control system according to claim 1, characterized in that, The working process of the digital twin visualization module comprises the following steps: The physical model data of the dredging construction area is obtained by unmanned aerial vehicle oblique photography or laser point cloud, and is digitally converted to realize the static digital twinning of the construction area; The type, name, and real-time heading, speed, and position information of the ship are obtained and integrated; According to the integrated information data, the dredging construction ship model and the surrounding navigation ship model in the digital twinning system are built, and the relevant state information is mapped into the digital twinning system to realize the dynamic digital twinning of the dredging construction area; The digital twinning system is connected to the monitoring center for visual display; The relevant state information includes the construction state, mechanical state, heading, speed, and position information of the dredging construction ship, and the heading, speed, and position information of the surrounding ship.

5. The digital-twin-based fairway dredging operation management and control system according to claim 1, characterized in that, The risk assessment model includes: Ship collision risk assessment, composed of the closest point of approach distance and the closest point of approach time of the ship; Ship grounding risk assessment, used to judge the influence of low water level on the construction stoppage of the dredging ship; Adverse weather risk assessment, composed of strong wind risk and high water level risk.

6. The digital-twin-based fairway dredging operation management and control system according to claim 5, characterized in that, The workflow of ship collision risk assessment includes: The position information, speed, heading information, and flow rate and direction information of the dredging construction ship and its surrounding ships are obtained in real time through the digital twinning system; The closest point of approach distance between the dredging construction ship and the surrounding ships is calculated according to the position information, and the minimum closest point of approach distance is obtained; The relative speed and relative approach time between the dredging construction ship and the surrounding ships are calculated according to the speed, heading information, and flow rate and direction information, and the minimum relative approach time is obtained; According to the minimum closest point of approach distance and the relative approach time, the collision risk is assessed, and high-risk information is sent to the dredging safety risk warning module.

7. The digital-twin-based fairway dredging operation management and control system according to claim 5, characterized in that, The workflow of ship grounding risk assessment includes: The predicted water level near the dredging construction ship construction area in the next 5 days is obtained in real time through the digital twinning system, and the minimum predicted water level in the next 5 days is obtained; According to the comparison of the minimum predicted water level and the minimum draft of the dredging construction ship, the grounding risk is assessed, and high-risk information is sent to the dredging safety risk warning module.

8. The digital-twin-based fairway dredging operation management and control system according to claim 7, characterized in that, The workflow of adverse weather risk assessment includes: The predicted wind speed and predicted water level of the dredging construction ship construction area in the next 5 days are obtained in real time through the digital twinning system, and the maximum predicted wind speed and maximum predicted water level in the next 5 days are obtained respectively; According to the comparison of the maximum predicted wind speed and the maximum wind resistance speed of the dredging construction ship, the strong wind risk is assessed; According to the comparison of the maximum predicted water level and the maximum construction water level of the dredging construction ship, the high water level risk is assessed; High-risk information is sent to the dredging safety risk warning module.

Images