Intelligent channel management method and system based on digital twinning

Abstract

The invention discloses an intelligent channel management method and system based on digital twinning. The method comprises the following steps: acquiring GIS data and historical monitoring data of a target channel, and constructing an intelligent channel digital twin model; importing channel monitoring data in a preset time period, performing dynamic simulation, and determining and updating a data updating strategy of the model in real time; monitoring the ship in the target channel in real time through the model, and identifying the behavior state of the ship; in combination with ship behaviors and meteorological and hydrological data, the navigation risk is assessed, and a risk assessment result is generated; and optimizing a data updating strategy according to an evaluation result. According to the method, the intelligence of channel management and the safety of ship navigation are improved.

Description

Technical Field

[0001] The present invention relates to the field of digital twin technology, and in particular to an intelligent waterway management method and system based on digital twin. Background Art

[0002] With the development of the global shipping industry, the safety and efficiency of ocean waterways have received more and more attention. In particular, the measurement and management of deep-water waterways have become a key task to ensure navigation safety and improve the efficiency of waterway passage. To this end, the International Maritime Organization (IMO) and the International Hydrographic Organization (IHO) have proposed the S-100 series of standards to support the modernization and standardization of digital charts and related services. Among them, the S-102 standard is a three-dimensional water depth data product standard under the S-100 framework, which aims to provide more accurate water depth information to meet the navigation needs of complex waterways.

[0003] However, the existing S-102 standard still faces several challenges and technical bottlenecks. First, the amount of bathymetric data for deep-water channels is huge. Especially in the processing of high-resolution, wide-coverage underwater terrain data, the amount of data actually used is less than 1% of the total measurement data, resulting in a huge amount of redundant data produced. Therefore, how to efficiently use this data has become an urgent problem to be solved. Secondly, the existing standards lack intelligent identification methods for ship behavior status, making it difficult to promptly detect and deal with potential navigation risks; finally, the data update strategy is relatively simple, and it is impossible to flexibly adjust the data update frequency according to the dynamic changes of the waterway and risk assessment results, resulting in low management efficiency and failure to meet the needs of the modern shipping industry for efficient and safe management. Based on this background, it is urgent to propose an intelligent waterway management method and system based on digital twin technology. By optimizing the water depth three-dimensional data products and information service system, an integrated and dynamic waterway management model can be established to update waterway data in real time, monitor ship status, and conduct navigation risk assessment and management. This will greatly improve the level of intelligent waterway management, ensure shipping safety, and improve waterway traffic efficiency. Summary of the invention

[0004] In order to solve at least one of the above technical problems, the present invention proposes an intelligent waterway management method and system based on digital twins.

[0005] The first aspect of the present invention provides an intelligent waterway management method based on digital twins, comprising: Acquire GIS data and historical waterway monitoring data of the target waterway, and build a digital twin model of the intelligent waterway based on the GIS data and historical waterway monitoring data; Acquire waterway monitoring data for a preset time period and import it into the smart waterway digital twin model to perform waterway dynamic simulation, determine a data update strategy for the smart waterway digital twin model based on the waterway dynamic simulation, and perform real-time data update on the smart waterway digital twin model based on the data update strategy; According to the smart waterway digital twin model, real-time monitoring of ships in the target waterway is performed to identify the behavior status of ships in the target waterway; Assess the navigation risk of the ship according to the behavior state and the meteorological data and hydrological data of the location where the ship is sailing, and obtain a navigation risk assessment result; The data updating strategy is optimized according to the navigation risk assessment result to obtain a data updating strategy optimization scheme.

[0006] In this solution, the GIS data and historical waterway monitoring data of the target waterway are obtained, and a digital twin model of the intelligent waterway is constructed based on the GIS data and historical waterway monitoring data, specifically: Acquire GIS data of the target waterway, wherein the GIS data includes topographic data, geomorphic data, location information of waterway facilities, spatial coordinates, length, width, and depth data of the target waterway; Extracting the boundary, shoreline and centerline of the channel according to the GIS data of the target channel, and extracting the transverse and longitudinal section information of the channel according to the terrain data of the target channel and the boundary, shoreline and centerline of the channel; Based on the linear interpolation method, spatial interpolation operation is performed on the transverse and longitudinal section information, and continuous curve changes of the transverse and longitudinal sections of the target waterway are fitted, and a three-dimensional geometric model of the target waterway is constructed according to the fitted transverse and longitudinal section information, and the three-dimensional geometric model is subjected to landform texture mapping according to the landform data, and a waterway facility geometric model is constructed and mapped in the three-dimensional geometric model; Acquire historical waterway monitoring data of the target waterway, wherein the historical waterway monitoring data includes meteorological data, ship AIS data, and hydrological data of the target waterway; Performing time synchronization analysis on the meteorological data and the hydrological data to determine the hydrological impact of different meteorological conditions on the target waterway and obtain meteorological-hydrological impact data; Constructing a weather environment simulation model and a hydrodynamic model of the target waterway according to the meteorological data and the hydrological data, and determining a synchronous change relationship between the weather environment simulation model and the hydrodynamic model according to the meteorological-hydrological impact data; Constructing a digital twin model of an intelligent waterway based on digital twin technology according to the three-dimensional geometric model, the weather environment simulation model and the hydrodynamic model, and the synchronous change relationship between the weather environment simulation model and the hydrodynamic model; The ship AIS data is imported into the smart waterway digital twin model for data fitting, and the ship dynamics of the target waterway are updated in real time to obtain a complete smart waterway digital twin model.

[0007] In this solution, the waterway monitoring data acquired in a preset time period is imported into the smart waterway digital twin model for waterway dynamic simulation, and the data update strategy of the smart waterway digital twin model is determined according to the waterway dynamic simulation, specifically: Preset a data monitoring cycle of the smart waterway digital twin model, obtain waterway monitoring data of the current data monitoring cycle, import the waterway monitoring data into the smart waterway digital twin model to perform waterway dynamic simulation, and divide the target waterway into N sub-areas based on geographical location; Acquire the waterway monitoring simulation change data of each sub-area during the waterway dynamic simulation process, and determine the value range of each data feature of the waterway monitoring simulation change data according to the waterway monitoring simulation change data; Preset a data segmentation width for each data feature value range, and perform an equal-width discretization operation on the region range of each data feature according to the data segmentation width to obtain a data distribution interval for each data feature; Calculate the data occurrence frequency of each data distribution interval of each data feature according to the waterway monitoring simulation change data, and calculate the probability distribution of each data distribution interval according to the data occurrence frequency; Analyzing the probability distribution based on an information entropy evaluation method, calculating the information entropy of each data feature of each sub-region, and evaluating the data redundancy of each data feature of each sub-region according to the information entropy; Constructing a data feature-redundancy distribution map of each data feature in each sub-area of ​​the target waterway according to the data redundancy of each data feature in each sub-area; Performing a comprehensive redundancy evaluation on the waterway simulation monitoring change data of each sub-area according to the data feature-redundancy distribution map, and obtaining a comprehensive redundancy evaluation result of each sub-area in the current data monitoring cycle; Obtaining the data update frequency of each sub-area in the current data monitoring cycle, and presetting a first comprehensive redundancy threshold and a second comprehensive redundancy threshold; According to the comprehensive redundancy evaluation result, if the comprehensive redundancy of the sub-area in the current data monitoring cycle is less than the first comprehensive redundancy threshold, the data update frequency of the next data monitoring cycle is increased; if the comprehensive redundancy is greater than or equal to the first comprehensive redundancy threshold and less than the second comprehensive redundancy threshold, the existing data update frequency is maintained in the next data monitoring cycle; if the comprehensive redundancy is greater than or equal to the second comprehensive redundancy threshold, the data update frequency of the next data monitoring cycle is reduced, and the data update strategy of the smart waterway digital twin model is obtained.

[0008] In this solution, the ships in the target waterway are monitored in real time according to the smart waterway digital twin model to identify the behavior status of the ships in the target waterway, specifically: Acquire historical behavior state data of the ship, extract navigation characteristics of different behavior states according to the historical behavior state data of the ship, and construct a navigation characteristic database with the navigation characteristics of different behavior states; A ship behavior state recognition model is constructed based on a decision tree algorithm, an information gain feature selection criterion is used as a data division criterion for the ship behavior state recognition model, navigation features in a navigation feature database are used as model inputs, and behavior states are used as model outputs to construct a decision tree for the ship behavior state recognition model, and a training operation is performed on the model according to the constructed decision tree; Acquire real-time ship navigation data in the target waterway according to the smart waterway digital twin model, wherein the real-time ship navigation data includes the navigation speed, direction, and position of the ship in the target waterway at each data update frequency; The real-time ship navigation data is imported into the ship behavior state recognition model, and the behavior state of the ship in the target channel is recognized in real time to obtain a recognition result.

[0009] In this solution, the navigation risk of the ship is assessed according to the behavior state and the meteorological data and hydrological data of the location where the ship is sailing, and the navigation risk assessment result is obtained, which is specifically: Obtaining basic information of ships in the target waterway, meteorological data and hydrological data of the location where the ships are sailing according to the smart waterway digital twin model, evaluating the navigation suitability of the location where the ships are sailing according to the basic information of the ships, the meteorological data and hydrological data of the location where the ships are sailing, and obtaining a navigation suitability evaluation result; Identify whether the sailing ship has abnormal sailing behavior according to the behavior state, wherein the abnormal sailing behavior includes speeding, dangerous approach between ships, deviation from the waterway, and anchoring; If there is no abnormal navigation behavior, a risk assessment is performed on the target channel ship according to the navigation suitability assessment result. If there is an abnormal navigation behavior, a risk assessment is performed on the target channel ship according to the abnormal navigation behavior and the navigation suitability assessment result to obtain a navigation risk assessment result.

[0010] In this solution, the data update strategy is optimized according to the navigation risk assessment result to obtain a data update strategy optimization solution, which is specifically: Preset a navigation risk threshold, and mark ships with a risk greater than the navigation risk threshold according to the navigation risk assessment result to obtain marked ships; Determine the position information of the marked ship according to the real-time ship navigation data, determine the sub-area where the marked ship is located in the target channel according to the position information of the marked ship, and mark it as the area to be optimized for the data update strategy; Performing a secondary adjustment on the data update frequency of the area to be optimized for the data update strategy; Acquiring information on the number of ships in the area to be optimized for the data update strategy, and determining a network transmission competition state of the ships in the area to be optimized for the data update strategy according to the information on the number of ships; According to the network transmission competition state, the data transmission delay of the ships in the area to be optimized for the data update strategy is evaluated, the network transmission speed requirement required for the adjusted data update frequency in the area to be optimized for the data update strategy is obtained, and the data transmission delay acceptance threshold is determined according to the network transmission speed requirement; A data transmission buffer is constructed for each sub-area. If the data transmission delay in the area to be optimized for the data update strategy is greater than the data transmission delay acceptance threshold, the AIS data, meteorological data, and hydrological data of the unmarked ships in the area to be optimized for the data update strategy are imported into the data transmission buffer. After the AIS data transmission of the marked ships is completed, the data in the data transmission buffer is transmitted to obtain the data update strategy optimization plan for each sub-area of ​​the target waterway.

[0011] The second aspect of the present invention further provides an intelligent waterway management system based on digital twins, the system comprising: a memory, a processor, the memory comprising an intelligent waterway management method program based on digital twins, and when the intelligent waterway management method program based on digital twins is executed by the processor, the following steps are implemented: Acquire GIS data and historical waterway monitoring data of the target waterway, and build a digital twin model of the intelligent waterway based on the GIS data and historical waterway monitoring data; Acquire waterway monitoring data for a preset time period and import it into the smart waterway digital twin model to perform waterway dynamic simulation, determine a data update strategy for the smart waterway digital twin model based on the waterway dynamic simulation, and perform real-time data update on the smart waterway digital twin model based on the data update strategy; According to the smart waterway digital twin model, real-time monitoring of ships in the target waterway is performed to identify the behavior status of ships in the target waterway; Assess the navigation risk of the ship according to the behavior state and the meteorological data and hydrological data of the location where the ship is sailing, and obtain a navigation risk assessment result; The data updating strategy is optimized according to the navigation risk assessment result to obtain a data updating strategy optimization scheme.

[0012] The present invention discloses a method and system for intelligent waterway management based on digital twins. The method comprises: obtaining GIS data and historical monitoring data of the target waterway, constructing a digital twin model of the intelligent waterway; importing waterway monitoring data of a preset time period, performing dynamic simulation, determining and updating the data update strategy of the model in real time; monitoring ships in the target waterway in real time through the model, identifying the behavior status of the ships; combining ship behavior, meteorological and hydrological data, assessing navigation risks, and generating risk assessment results; optimizing data update strategies according to the assessment results. The method improves the intelligence of waterway management and the safety of ship navigation. BRIEF DESCRIPTION OF THE DRAWINGS

[0013] Figure 1 A flow chart of an intelligent waterway management method based on digital twins of the present invention is shown; Figure 2 A flow chart showing the behavior status of a ship in a target channel according to the present invention is shown; Figure 3 A flow chart showing the navigation risk assessment result obtained by the present invention is shown; Figure 4 A block diagram of an intelligent waterway management system based on digital twins of the present invention is shown. DETAILED DESCRIPTION

[0014] In order to more clearly understand the above-mentioned purpose, features and advantages of the present invention, the present invention is further described in detail below in conjunction with the accompanying drawings and specific embodiments. It should be noted that the embodiments of the present application and the features in the embodiments can be combined with each other without conflict.

[0015] In the following description, many specific details are set forth to facilitate a full understanding of the present invention. However, the present invention may also be implemented in other ways different from those described herein. Therefore, the protection scope of the present invention is not limited to the specific embodiments disclosed below.

[0016] Figure 1 A flow chart of an intelligent waterway management method based on digital twins of the present invention is shown.

[0017] like Figure 1 As shown, the first aspect of the present invention provides an intelligent waterway management method based on digital twins, comprising: S102, acquiring GIS data and historical waterway monitoring data of the target waterway, and constructing a digital twin model of the intelligent waterway according to the GIS data and the historical waterway monitoring data; S104, obtaining waterway monitoring data for a preset time period and importing the data into the smart waterway digital twin model to perform waterway dynamic simulation, determining a data update strategy for the smart waterway digital twin model according to the waterway dynamic simulation, and performing real-time data update on the smart waterway digital twin model according to the data update strategy; S106, monitoring the ships in the target waterway in real time according to the smart waterway digital twin model, and identifying the behavior status of the ships in the target waterway; S108, assessing the navigation risk of the ship according to the behavior state and the meteorological data and hydrological data of the location where the ship is sailing, and obtaining a navigation risk assessment result; S110, optimizing the data updating strategy according to the navigation risk assessment result to obtain a data updating strategy optimization solution.

[0018] It should be noted that by obtaining the geographic information system (GIS) data and historical monitoring data of the target waterway, a highly simulated digital twin model can be built for the waterway. The model includes the geographical location, physical characteristics of the waterway, and hydrological and meteorological factors reflected in historical data, which can fully and accurately reflect the actual waterway conditions; by real-time importing waterway monitoring data (such as hydrological, meteorological and waterway use information, etc.) within a specific time period and combining it with the digital twin model for dynamic simulation, an optimized data update strategy can be formulated based on the results of the dynamic simulation of the waterway, which can avoid unnecessary frequent updates and reduce the system's computing load and resource waste. For example, when the waterway conditions are relatively stable, the update frequency can be reduced, thereby reducing the resource consumption of computing, storage and communication. This can not only optimize the operating efficiency of the system, but also reduce the operation and maintenance costs, reduce the data redundancy of the system, and avoid the system from generating a large amount of low-value data; through the constructed intelligent waterway digital twin model, the behavior of ships in the target waterway is monitored and the navigation risk is assessed. Based on the risk assessment results, the original data update strategy can be optimized to improve the efficiency and flexibility of waterway monitoring, so that the waterway management system can make rapid adjustments when the risk changes.

[0019] According to an embodiment of the present invention, the GIS data and historical waterway monitoring data of the target waterway are obtained, and a digital twin model of the intelligent waterway is constructed according to the GIS data and the historical waterway monitoring data, specifically: Acquire GIS data of the target waterway, wherein the GIS data includes topographic data, geomorphic data, location information of waterway facilities, spatial coordinates, length, width, and depth data of the target waterway; Extracting the boundary, shoreline and centerline of the channel according to the GIS data of the target channel, and extracting the transverse and longitudinal section information of the channel according to the terrain data of the target channel and the boundary, shoreline and centerline of the channel; Based on the linear interpolation method, spatial interpolation operation is performed on the transverse and longitudinal section information, and continuous curve changes of the transverse and longitudinal sections of the target waterway are fitted, and a three-dimensional geometric model of the target waterway is constructed according to the fitted transverse and longitudinal section information, and the three-dimensional geometric model is subjected to landform texture mapping according to the landform data, and a waterway facility geometric model is constructed and mapped in the three-dimensional geometric model; Acquire historical waterway monitoring data of the target waterway, wherein the historical waterway monitoring data includes meteorological data, ship AIS data, and hydrological data of the target waterway; Performing time synchronization analysis on the meteorological data and the hydrological data to determine the hydrological impact of different meteorological conditions on the target waterway and obtain meteorological-hydrological impact data; Constructing a weather environment simulation model and a hydrodynamic model of the target waterway according to the meteorological data and the hydrological data, and determining a synchronous change relationship between the weather environment simulation model and the hydrodynamic model according to the meteorological-hydrological impact data; Constructing a digital twin model of an intelligent waterway based on digital twin technology according to the three-dimensional geometric model, the weather environment simulation model and the hydrodynamic model, and the synchronous change relationship between the weather environment simulation model and the hydrodynamic model; The ship AIS data is imported into the smart waterway digital twin model for data fitting, and the ship dynamics of the target waterway are updated in real time to obtain a complete smart waterway digital twin model.

[0020] It should be noted that the transverse and longitudinal section information of the channel is extracted by acquiring the GIS data of the target channel. The transverse section information describes the shape of the channel on a certain cross section, and the longitudinal section information reflects the ups and downs of the channel in the downstream direction. Since the GIS data is discrete, the discrete transverse and longitudinal section data can be converted into continuous curves through linear interpolation to fill the blank areas of the data, thereby providing more comprehensive and detailed channel geometry information, and then constructing a complete three-dimensional geometric model of the channel; by performing time synchronization analysis on meteorological data and hydrological data, the influence of different meteorological conditions on hydrological characteristics can be revealed, and by determining the synchronous change relationship between the weather environment simulation model and the hydrodynamic model, more accurate dynamic monitoring of the channel status can be achieved. Combining the three-dimensional geometric model, the weather environment simulation model and the hydrodynamic model, the constructed intelligent channel digital twin model can display the real-time status of the channel; the ship AIS data includes ship type, position, speed, heading, and draft depth information; the hydrological data includes water flow velocity, water level depth, and water flow direction data. If the target channel is a sea channel, it also includes wave height data.

[0021] According to an embodiment of the present invention, the waterway monitoring data acquired in a preset time period is imported into the smart waterway digital twin model for waterway dynamic simulation, and the data update strategy of the smart waterway digital twin model is determined according to the waterway dynamic simulation, specifically: Preset a data monitoring cycle of the smart waterway digital twin model, obtain waterway monitoring data of the current data monitoring cycle, import the waterway monitoring data into the smart waterway digital twin model to perform waterway dynamic simulation, and divide the target waterway into N sub-areas based on geographical location; Acquire the waterway monitoring simulation change data of each sub-area during the waterway dynamic simulation process, and determine the value range of each data feature of the waterway monitoring simulation change data according to the waterway monitoring simulation change data; Preset a data segmentation width for the value range of each data feature, and perform an equal-width discretization operation on the region range of each data feature according to the data segmentation width to obtain a data distribution interval for each data feature; Calculate the data occurrence frequency of each data distribution interval of each data feature according to the waterway monitoring simulation change data, and calculate the probability distribution of each data distribution interval according to the data occurrence frequency; It should be noted that the waterway monitoring simulation change data is the waterway meteorological change data, ship AIS change data, and hydrological change data during the dynamic simulation of the waterway, and only when there are ships sailing in the sub-area, the sub-area will have ship AIS change data; the data features are the data items contained in the waterway monitoring simulation change data; the equal-width discretization operation is to divide the value range of the time series data of the waterway monitoring simulation change data into several intervals. For example, assuming that the water level change range is 0 to 10 meters, it can be divided into 5 intervals: 0-2, 2-4, 4-6, 6-8, 8-10; the probability distribution is the number of times the interval appears divided by the total number of data points. For example, in the process of dynamic simulation of the waterway, 100 dynamically changing water level change data points are collected, and there are 10 data points in the interval of 0-2, then the probability distribution in the interval of 0-2 is 0.1.

[0022] Analyzing the probability distribution based on an information entropy evaluation method, calculating the information entropy of each data feature of each sub-region, and evaluating the data redundancy of each data feature of each sub-region according to the information entropy; Constructing a data feature-redundancy distribution map of each data feature in each sub-area of ​​the target waterway according to the data redundancy of each data feature in each sub-area; It should be noted that high information entropy means that the data distribution in this area is relatively uniform, the amount of information is large, and the changes are more complex, which means that the data redundancy in this area is low and a higher update frequency and sampling accuracy are required; low information entropy means that the data in this area is concentrated in a few intervals, the amount of information is small, and the changes are small, which means that the data redundancy in this area is high and the data update frequency can be reduced; the data feature-redundancy distribution diagram is the distribution of the data redundancy of each data feature in the target channel.

[0023] Performing a comprehensive redundancy evaluation on the waterway simulation monitoring change data of each sub-area according to the data feature-redundancy distribution map, and obtaining a comprehensive redundancy evaluation result of each sub-area in the current data monitoring cycle; Obtaining the data update frequency of each sub-area in the current data monitoring cycle, and presetting a first comprehensive redundancy threshold and a second comprehensive redundancy threshold; According to the comprehensive redundancy evaluation result, if the comprehensive redundancy of the sub-area in the current data monitoring cycle is less than the first comprehensive redundancy threshold, the data update frequency of the next data monitoring cycle is increased; if the comprehensive redundancy is greater than or equal to the first comprehensive redundancy threshold and less than the second comprehensive redundancy threshold, the existing data update frequency is maintained in the next data monitoring cycle; if the comprehensive redundancy is greater than or equal to the second comprehensive redundancy threshold, the data update frequency of the next data monitoring cycle is reduced, and the data update strategy of the smart waterway digital twin model is obtained.

[0024] It should be noted that in the process of monitoring the target waterway by the digital twin model of the smart waterway, a large amount of data is often required to realize the real-time data update of the model to reflect the latest waterway conditions. However, since the data in most areas of the target waterway are in a state of unchanged data within a certain period of time, continuous updating of such data will greatly cause redundant data updates; therefore, by determining the data monitoring cycle and dividing the target waterway into N sub-areas, the waterway monitoring data of the current data monitoring cycle is obtained and imported into the digital twin model of the smart waterway for dynamic simulation of the waterway. The information entropy analysis method is used to evaluate the data information entropy in each sub-area according to the simulated change data of the waterway monitoring in each sub-area, and then the data redundancy of each sub-area is determined. Finally, the data update strategy of the digital twin model of the smart waterway is constructed according to the data redundancy; the focus and frequency of data monitoring are automatically adjusted for different waterway environments and dynamic conditions. This means that there will be higher frequency data monitoring in sub-areas with large data changes, while the monitoring frequency can be reduced in relatively stable areas, thereby achieving optimal allocation of resources; in some sub-areas that are greatly affected by the environment (such as areas with frequent tidal effects, rapid water flow or dense ships), the waterway conditions may change rapidly over time. If the original data update frequency is maintained, it may not be possible to capture subtle changes in the environment in time, resulting in a delayed response of the waterway management system. In this case, through the comprehensive redundancy assessment, it is found that the redundancy is low, and the system can automatically increase the data update frequency to ensure the real-time and accuracy of waterway monitoring; some sub-areas may be in a relatively stable waterway environment, such as areas with wide waterways, few ships or gentle water flow. In such scenarios, the waterway conditions change little and the redundancy of the monitoring data is high. If the data is updated continuously at a high frequency, it may waste system resources and increase unnecessary data processing pressure. Through the evaluation, it is found that the redundancy is large, and the system can reduce the data update frequency to reduce resource consumption; in some sub-areas, the waterway changes are between drastic and stable, and the data redundancy is neither low nor high, but in an intermediate state. In this case, frequent adjustment of the data update frequency may lead to system instability. If the redundancy is found to be between the first threshold and the second threshold through evaluation, the system can choose to maintain the existing data update frequency to maintain the balance and stability of monitoring without causing unnecessary resource fluctuations; the comprehensive redundancy is the sum of the redundancy of each data feature multiplied by the corresponding weight.

[0025] Figure 2 A flow chart of the present invention for identifying the behavior status of a ship in a target channel is shown.

[0026] According to an embodiment of the present invention, real-time monitoring of ships in the target waterway according to the smart waterway digital twin model and identification of the behavior status of ships in the target waterway are specifically as follows: S202, acquiring historical behavior state data of the ship, extracting navigation characteristics of different behavior states according to the historical behavior state data of the ship, and constructing a navigation characteristic database with the navigation characteristics of different behavior states; S204, constructing a ship behavior state recognition model based on a decision tree algorithm, using an information gain feature selection criterion as a data division criterion for the ship behavior state recognition model, importing navigation features in a navigation feature database as model inputs and behavior states as model outputs into the ship behavior state recognition model to construct a decision tree, and performing a training operation on the model according to the constructed decision tree; S206, acquiring real-time ship navigation data in the target waterway according to the smart waterway digital twin model, wherein the real-time ship navigation data includes the navigation speed, direction, and position of the ship in the target waterway at each data update frequency; S208, importing the real-time ship navigation data into the ship behavior state recognition model, performing real-time recognition on the behavior state of the ship in the target channel, and obtaining a recognition result.

[0027] It should be noted that the decision tree algorithm is a classification algorithm based on feature selection, which can quickly divide the behavior status of ships according to navigation characteristics. By using information gain as the feature selection criterion, different behavior states of ships (such as normal navigation, deceleration, turning, berthing, etc.) can be effectively identified, which improves the accuracy and efficiency of identification. This allows waterway managers to grasp the dynamic behavior of ships in a timely manner and carry out targeted management and intervention based on the identification results; based on the real-time ship navigation data obtained by the smart waterway digital twin model, combined with the ship behavior state identification model constructed by the decision tree algorithm, the navigation status of ships can be dynamically updated and identified at different monitoring frequencies. By inputting the real-time speed, direction, position and other data of the ship into the model, the operation status of the ship in the waterway can be tracked in real time; the historical behavior state data includes berthing, acceleration and deceleration, steering, emergency braking, avoidance operation, and dangerous approach between ships; the navigation characteristics include the change characteristics of navigation speed and navigation direction, position change characteristics, and relative position characteristics between ships.

[0028] Figure 3 A flow chart of obtaining navigation risk assessment results according to the present invention is shown.

[0029] According to an embodiment of the present invention, the navigation risk of the ship is assessed according to the behavior state and the meteorological data and hydrological data of the location where the ship is sailing, and the navigation risk assessment result is obtained, specifically: S302, obtaining basic information of ships in the target waterway, meteorological data and hydrological data of the location where the ships are sailing according to the smart waterway digital twin model, evaluating the navigation suitability of the location where the ships are sailing according to the basic information of the ships, the meteorological data and hydrological data of the location where the ships are sailing, and obtaining a navigation suitability evaluation result; S304, identifying whether the sailing ship has abnormal sailing behavior according to the behavior state, wherein the abnormal sailing behavior includes speeding, dangerous approach between ships, deviation from the waterway, and anchoring; S306, if there is no abnormal navigation behavior, perform risk assessment on the target channel ship according to the navigation suitability assessment result; if there is abnormal navigation behavior, perform risk assessment on the target channel ship according to the abnormal navigation behavior and the navigation suitability assessment result to obtain a navigation risk assessment result.

[0030] It should be noted that by integrating the basic information of the ship, meteorological data and hydrological data, this method can comprehensively evaluate the navigation environment of the ship. The navigation suitability of the ship reflects the safety of the ship's current location and the goodness of the navigation conditions. This comprehensive assessment can identify potential risk factors (such as bad weather, turbulent water, etc.) in advance. The method can identify whether there are abnormal navigation behaviors based on the behavior status of the ship, such as speeding, dangerous approaches between ships, deviation from the channel or improper mooring. Once abnormal behavior is identified, the system will conduct a more detailed risk assessment in combination with the navigation suitability; the basic information of the ship includes the type of ship and the draft of the ship.

[0031] According to an embodiment of the present invention, the data update strategy is optimized according to the navigation risk assessment result to obtain a data update strategy optimization scheme, which is specifically: Preset a navigation risk threshold, and mark ships with a risk greater than the navigation risk threshold according to the navigation risk assessment result to obtain marked ships; Determine the position information of the marked ship according to the real-time ship navigation data, determine the sub-area where the marked ship is located in the target channel according to the position information of the marked ship, and mark it as the area to be optimized for the data update strategy; Performing a secondary adjustment on the data update frequency of the area to be optimized for the data update strategy; Acquiring information on the number of ships in the area to be optimized for the data update strategy, and determining a network transmission competition state of the ships in the area to be optimized for the data update strategy according to the information on the number of ships; According to the network transmission competition state, the data transmission delay of the ships in the area to be optimized for the data update strategy is evaluated, the network transmission speed requirement required for the adjusted data update frequency in the area to be optimized for the data update strategy is obtained, and the data transmission delay acceptance threshold is determined according to the network transmission speed requirement; A data transmission buffer is constructed for each sub-area. If the data transmission delay in the area to be optimized for the data update strategy is greater than the data transmission delay acceptance threshold, the AIS data, meteorological data, and hydrological data of the unmarked ships in the area to be optimized for the data update strategy are imported into the data transmission buffer. After the AIS data transmission of the marked ships is completed, the data in the data transmission buffer is transmitted to obtain the data update strategy optimization plan for each sub-area of ​​the target waterway.

[0032] It should be noted that by marking ships with risks exceeding the threshold and optimizing the data update frequency of their sub-areas, this method can focus on monitoring high-risk areas. For these high-risk areas, the system can adjust the data update frequency twice to increase the frequency of data updates, so that managers can timely grasp the dynamic changes of ships in these areas and reduce the risk of accidents; by calibrating the area to be optimized, only the data update frequency of the sub-area where high-risk ships are located is optimized, while other sub-areas maintain the regular update frequency, so as to achieve targeted allocation of resources and improve the efficiency of the overall system; when there are multiple ships in the target channel for data transmission, data transmission may cause competition, resulting in increased delay. By evaluating the network transmission competition status, this method can dynamically adjust the priority of data transmission, ensure that the data transmission of the marked ship is not interfered with, and reduce the monitoring lag caused by transmission delay. This mechanism effectively optimizes the utilization rate of the network transmission channel and ensures more timely risk monitoring of key ships; according to the number of ships in the area and the network competition situation, the data transmission strategy is adjusted according to the data transmission delay acceptance threshold. In areas with dense ships and fierce network competition, this method can intelligently adjust the data transmission order while ensuring the update frequency, thereby ensuring that the transmission speed requirement matches the delay threshold, and ultimately optimizing the data update strategy for each sub-area. The network transmission competition state refers to the competition phenomenon generated when multiple devices or nodes (such as ships) try to transmit data at the same time when network resources are limited. This competition will affect the speed and delay of data transmission of each device.

[0033] According to an embodiment of the present invention, before importing the AIS data, meteorological data, and hydrological data of the non-marked ships in the area to be optimized for the data update strategy into the data transmission buffer, the method further includes: Estimate the amount of data to be imported into the data transmission buffer based on the ship quantity information, meteorological data, and hydrological data in the area to be optimized by the data update strategy; Acquire capacity information of the data transmission buffer, and if the amount of data to be imported into the data transmission buffer is greater than the capacity of the data transmission buffer, convert the data to be imported into a character representation format to obtain character format data; Performing character appearance frequency statistics on the character format data, constructing a priority queue, and importing each character in the character format data into the priority queue according to the character appearance frequency; Constructing a Huffman tree according to the priority queue, constructing a Huffman code for each character according to the Huffman tree, performing a character encoding operation on the character format data according to the Huffman code, and obtaining compressed data of the data to be imported; The compressed data is imported into a data transmission buffer to wait for transmission, and when the data transmission in the data transmission buffer is completed, the compressed data is decoded and restored according to the Huffman tree.

[0034] It should be noted that, since the data capacity of the constructed data transmission buffer is limited, when the amount of data to be imported into the data transmission buffer is greater than the data capacity of the data transmission buffer, if the data is still imported, data loss will occur; therefore, when the amount of data to be imported into the data transmission buffer is greater than the capacity of the data transmission buffer, by introducing the Huffman coding data compression algorithm to compress the imported data, the limited storage space can be more effectively utilized, data loss caused by insufficient space can be avoided, and the data transmission speed can be improved. After the data transmission is completed, the Huffman tree can be used to decode the compressed data, and the original data can be quickly restored to ensure the integrity and availability of the data; the data to be imported is the AIS data, meteorological data, and hydrological data of non-marked ships in the data update strategy optimization area that need to be imported into the data transmission buffer.

[0035] Figure 4 A block diagram of an intelligent waterway management system based on digital twins of the present invention is shown.

[0036] The second aspect of the present invention further provides an intelligent waterway management system 4 based on digital twins, the system comprising: a memory 41, a processor 42, the memory comprising an intelligent waterway management method program based on digital twins, and when the intelligent waterway management method program based on digital twins is executed by the processor, the following steps are implemented: Acquire GIS data and historical waterway monitoring data of the target waterway, and build a digital twin model of the intelligent waterway based on the GIS data and historical waterway monitoring data; Acquire waterway monitoring data for a preset time period and import it into the smart waterway digital twin model to perform waterway dynamic simulation, determine a data update strategy for the smart waterway digital twin model based on the waterway dynamic simulation, and perform real-time data update on the smart waterway digital twin model based on the data update strategy; According to the smart waterway digital twin model, real-time monitoring of ships in the target waterway is performed to identify the behavior status of ships in the target waterway; Assess the navigation risk of the ship according to the behavior state and the meteorological data and hydrological data of the location where the ship is sailing, and obtain a navigation risk assessment result; The data updating strategy is optimized according to the navigation risk assessment result to obtain the data updating strategy optimization scheme The present invention discloses a method and system for intelligent waterway management based on digital twins. The method comprises: obtaining GIS data and historical monitoring data of the target waterway, constructing a digital twin model of the intelligent waterway; importing waterway monitoring data of a preset time period, performing dynamic simulation, determining and updating the data update strategy of the model in real time; monitoring ships in the target waterway in real time through the model, identifying the behavior status of the ships; combining ship behavior, meteorological and hydrological data, assessing navigation risks, and generating risk assessment results; optimizing data update strategies according to the assessment results. The method improves the intelligence of waterway management and the safety of ship navigation.

[0037] In the several embodiments provided in the present application, it should be understood that the disclosed devices and methods can be implemented in other ways. The device embodiments described above are only schematic. For example, the division of the units is only a logical function division. There may be other division methods in actual implementation, such as: multiple units or components can be combined, or can be integrated into another system, or some features can be ignored or not executed. In addition, the coupling, direct coupling, or communication connection between the components shown or discussed can be through some interfaces, and the indirect coupling or communication connection of the devices or units can be electrical, mechanical or other forms.

[0038] The units described above as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units; they may be located in one place or distributed on multiple network units; some or all of the units may be selected according to actual needs to achieve the purpose of the present embodiment.

[0039] In addition, all functional units in the embodiments of the present invention may be integrated into one processing unit, or each unit may be separately used as a unit, or two or more units may be integrated into one unit; the above-mentioned integrated units may be implemented in the form of hardware or in the form of hardware plus software functional units.

[0040] A person of ordinary skill in the art can understand that: all or part of the steps of implementing the above method embodiment can be completed by hardware related to program instructions, and the aforementioned program can be stored in a computer-readable storage medium. When the program is executed, it executes the steps of the above method embodiment; and the aforementioned storage medium includes: a mobile storage device, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk, and other media that can store program codes.

[0041] Alternatively, if the above-mentioned integrated unit of the present invention is implemented in the form of a software function module and sold or used as an independent product, it can also be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the embodiment of the present invention can be essentially or partly reflected in the form of a software product that contributes to the prior art. The computer software product is stored in a storage medium and includes several instructions for a computer device (which can be a personal computer, server, or network device, etc.) to execute all or part of the methods described in each embodiment of the present invention. The aforementioned storage medium includes: various media that can store program codes, such as mobile storage devices, ROM, RAM, magnetic disks or optical disks.

[0042] The above is only a specific embodiment of the present invention, but the protection scope of the present invention is not limited thereto. Any person skilled in the art can easily think of changes or substitutions within the technical scope disclosed by the present invention, which should be included in the protection scope of the present invention. Therefore, the protection scope of the present invention should be based on the protection scope of the claims.

Claims

1. An intelligent waterway management method based on digital twins, characterized in that: The following steps are involved: Acquire GIS data and historical waterway monitoring data of the target waterway, and build a digital twin model of the intelligent waterway based on the GIS data and historical waterway monitoring data; Acquire waterway monitoring data for a preset time period and import it into the smart waterway digital twin model to perform waterway dynamic simulation, determine a data update strategy for the smart waterway digital twin model based on the waterway dynamic simulation, and perform real-time data update on the smart waterway digital twin model based on the data update strategy; According to the smart waterway digital twin model, real-time monitoring of ships in the target waterway is performed to identify the behavior status of ships in the target waterway; Assess the navigation risk of the ship according to the behavior state and the meteorological data and hydrological data of the location where the ship is sailing, and obtain a navigation risk assessment result; The data updating strategy is optimized according to the navigation risk assessment result to obtain a data updating strategy optimization scheme.

2. According to claim 1, a digital twin-based intelligent waterway management method is characterized in that: The step of acquiring the GIS data and historical waterway monitoring data of the target waterway and constructing the intelligent waterway digital twin model according to the GIS data and historical waterway monitoring data is as follows: Acquire GIS data of the target waterway, wherein the GIS data includes topographic data, geomorphic data, location information of waterway facilities, spatial coordinates, length, width, and depth data of the target waterway; Extracting the boundary, shoreline and centerline of the channel according to the GIS data of the target channel, and extracting the transverse and longitudinal section information of the channel according to the terrain data of the target channel and the boundary, shoreline and centerline of the channel; Based on the linear interpolation method, spatial interpolation operation is performed on the transverse and longitudinal section information, and continuous curve changes of the transverse and longitudinal sections of the target waterway are fitted, and a three-dimensional geometric model of the target waterway is constructed according to the fitted transverse and longitudinal section information, and the three-dimensional geometric model is subjected to landform texture mapping according to the landform data, and a waterway facility geometric model is constructed and mapped in the three-dimensional geometric model; Acquire historical waterway monitoring data of the target waterway, wherein the historical waterway monitoring data includes meteorological data, ship AIS data, and hydrological data of the target waterway; Performing time synchronization analysis on the meteorological data and the hydrological data to determine the hydrological impact of different meteorological conditions on the target waterway and obtain meteorological-hydrological impact data; Constructing a weather environment simulation model and a hydrodynamic model of the target waterway according to the meteorological data and the hydrological data, and determining a synchronous change relationship between the weather environment simulation model and the hydrodynamic model according to the meteorological-hydrological impact data; Constructing a digital twin model of an intelligent waterway based on digital twin technology according to the three-dimensional geometric model, the weather environment simulation model and the hydrodynamic model, and the synchronous change relationship between the weather environment simulation model and the hydrodynamic model; The ship AIS data is imported into the smart waterway digital twin model for data fitting, and the ship dynamics of the target waterway are updated in real time to obtain a complete smart waterway digital twin model.

3. According to the digital twin-based intelligent waterway management method of claim 1, it is characterized in that: The channel monitoring data acquired in the preset time period is imported into the smart waterway digital twin model to perform dynamic simulation of the channel, and the data update strategy of the smart waterway digital twin model is determined according to the dynamic simulation of the channel, specifically: Preset a data monitoring cycle of the smart waterway digital twin model, obtain waterway monitoring data of the current data monitoring cycle, import the waterway monitoring data into the smart waterway digital twin model to perform waterway dynamic simulation, and divide the target waterway into N sub-areas based on geographical location; Acquire the waterway monitoring simulation change data of each sub-area during the waterway dynamic simulation process, and determine the value range of each data feature of the waterway monitoring simulation change data according to the waterway monitoring simulation change data; Preset a data segmentation width for each data feature value range, and perform an equal-width discretization operation on the region range of each data feature according to the data segmentation width to obtain a data distribution interval for each data feature; Calculate the data occurrence frequency of each data distribution interval of each data feature according to the waterway monitoring simulation change data, and calculate the probability distribution of each data distribution interval according to the data occurrence frequency; Analyzing the probability distribution based on an information entropy evaluation method, calculating the information entropy of each data feature of each sub-region, and evaluating the data redundancy of each data feature of each sub-region according to the information entropy; Constructing a data feature-redundancy distribution map of each data feature in each sub-area of ​​the target waterway according to the data redundancy of each data feature in each sub-area; Performing a comprehensive redundancy evaluation on the waterway simulation monitoring change data of each sub-area according to the data feature-redundancy distribution map, and obtaining a comprehensive redundancy evaluation result of each sub-area in the current data monitoring cycle; Obtaining the data update frequency of each sub-area in the current data monitoring cycle, and presetting a first comprehensive redundancy threshold and a second comprehensive redundancy threshold; According to the comprehensive redundancy evaluation result, if the comprehensive redundancy of the sub-area in the current data monitoring cycle is less than the first comprehensive redundancy threshold, the data update frequency of the next data monitoring cycle is increased; if the comprehensive redundancy is greater than or equal to the first comprehensive redundancy threshold and less than the second comprehensive redundancy threshold, the existing data update frequency is maintained in the next data monitoring cycle; if the comprehensive redundancy is greater than or equal to the second comprehensive redundancy threshold, the data update frequency of the next data monitoring cycle is reduced, so as to obtain the data update strategy of the smart waterway digital twin model.

4. According to claim 1, a digital twin-based intelligent waterway management method is characterized in that: The real-time monitoring of the ships in the target waterway according to the smart waterway digital twin model and the identification of the behavior status of the ships in the target waterway are specifically as follows: Acquire historical behavior state data of the ship, extract navigation characteristics of different behavior states according to the historical behavior state data of the ship, and construct a navigation characteristic database with the navigation characteristics of different behavior states; A ship behavior state recognition model is constructed based on a decision tree algorithm, an information gain feature selection criterion is used as a data division criterion for the ship behavior state recognition model, navigation features in a navigation feature database are used as model inputs, and behavior states are used as model outputs to construct a decision tree for the ship behavior state recognition model, and a training operation is performed on the model according to the constructed decision tree; Acquire real-time ship navigation data in the target waterway according to the smart waterway digital twin model, wherein the real-time ship navigation data includes the navigation speed, direction, and position of the ship in the target waterway at each data update frequency; The real-time ship navigation data is imported into the ship behavior state recognition model, and the behavior state of the ship in the target channel is recognized in real time to obtain a recognition result.

5. The intelligent waterway management method based on digital twin according to claim 1 is characterized in that: The navigation risk of the ship is assessed according to the behavior state and the meteorological data and hydrological data of the location where the ship is sailing, and the navigation risk assessment result is obtained, which is specifically: Obtaining basic information of ships in the target waterway, meteorological data and hydrological data of the location where the ships are sailing according to the smart waterway digital twin model, evaluating the navigation suitability of the location where the ships are sailing according to the basic information of the ships, the meteorological data and hydrological data of the location where the ships are sailing, and obtaining a navigation suitability evaluation result; Identify whether the sailing ship has abnormal sailing behavior according to the behavior state, wherein the abnormal sailing behavior includes speeding, dangerous approach between ships, deviation from the waterway, and anchoring; If there is no abnormal navigation behavior, a risk assessment is performed on the target channel ship according to the navigation suitability assessment result. If there is an abnormal navigation behavior, a risk assessment is performed on the target channel ship according to the abnormal navigation behavior and the navigation suitability assessment result to obtain a navigation risk assessment result.

6. The intelligent waterway management method based on digital twin according to claim 1 is characterized in that: The data updating strategy is optimized according to the navigation risk assessment result to obtain a data updating strategy optimization scheme, which is specifically: Preset a navigation risk threshold, and mark ships with a risk greater than the navigation risk threshold according to the navigation risk assessment result to obtain marked ships; Determine the position information of the marked ship according to the real-time ship navigation data, determine the sub-area where the marked ship is located in the target channel according to the position information of the marked ship, and mark it as the area to be optimized for the data update strategy; Performing a secondary adjustment on the data update frequency of the area to be optimized for the data update strategy; Acquiring information on the number of ships in the area to be optimized for the data update strategy, and determining a network transmission competition state of the ships in the area to be optimized for the data update strategy according to the information on the number of ships; According to the network transmission competition state, the data transmission delay of the ships in the area to be optimized for the data update strategy is evaluated, the network transmission speed requirement required for the adjusted data update frequency in the area to be optimized for the data update strategy is obtained, and the data transmission delay acceptance threshold is determined according to the network transmission speed requirement; A data transmission buffer is constructed for each sub-area. If the data transmission delay in the area to be optimized for the data update strategy is greater than the data transmission delay acceptance threshold, the AIS data, meteorological data, and hydrological data of the unmarked ships in the area to be optimized for the data update strategy are imported into the data transmission buffer. After the AIS data transmission of the marked ships is completed, the data in the data transmission buffer is transmitted to obtain the data update strategy optimization plan for each sub-area of ​​the target waterway.

7. An intelligent waterway management system based on digital twins, characterized in that: The intelligent waterway management system based on digital twins includes a storage device and a processor. The storage device includes an intelligent waterway management method program based on digital twins. When the intelligent waterway management method program based on digital twins is executed by the processor, the following steps are implemented: Acquire GIS data and historical waterway monitoring data of the target waterway, and build a digital twin model of the intelligent waterway based on the GIS data and historical waterway monitoring data; Acquire waterway monitoring data for a preset time period and import it into the smart waterway digital twin model to perform waterway dynamic simulation, determine a data update strategy for the smart waterway digital twin model based on the waterway dynamic simulation, and perform real-time data update on the smart waterway digital twin model based on the data update strategy; According to the smart waterway digital twin model, real-time monitoring of ships in the target waterway is performed to identify the behavior status of ships in the target waterway; Assess the navigation risk of the ship according to the behavior state and the meteorological data and hydrological data of the location where the ship is sailing, and obtain a navigation risk assessment result; The data updating strategy is optimized according to the navigation risk assessment result to obtain a data updating strategy optimization scheme.

Images