A system and method for quantitative analysis of nested coupling planning of port water and land areas

Abstract

The present invention relates to the field of port planning technology, and specifically to a system and method for quantitative analysis of nested coupling planning of port water and land areas, including: a port water and land area planning scheme digitization module, which is used to digitally reconstruct the port water and port land area planning schemes to obtain physical models of the port water and port land areas; a nested coupling simulation module, which is used to perform information nesting interaction between physical models of port water and port land areas through a twin neural network based on the simulation scale and simulation results with ships as intelligent entities in the initialization simulation module, and construct simulation scales and simulation results with containers as intelligent entities. The present invention performs full-process, interactive, mixed-dimensional, spatiotemporal nested simulation of container ship inbound and outbound traffic flow, terminal production operation process, port gate logistics channel, etc. under the port water and land spatiotemporal planning scheme, to achieve quantitative evaluation of the water and land layout planning scheme under the coupling of multiple objectives and multiple environmental driving factors.

Description

Technical Field

[0001] The present invention relates to the technical field of port planning, and in particular to a system and method for quantitative analysis of nested coupling planning of port water and land areas. Background Art

[0002] The port system composed of water traffic and land traffic is a dynamic and random complex system. The resources of each link of water and land operations are mutually restricted, interrelated, mutually influenced, and work in coordination. At present, the existing research focuses on simulating port waters or land alone, and there is a lack of relevant research on joint simulation of waters and land. For example, "A Port Collection and Distribution Planning Simulation Analysis Method and System (CN113536499A)" uses the OD reverse push technology in the TransCAD platform to predict the traffic demand in the future year, and uses the output results of the traffic demand prediction model as the input initial data of the Trans Modeler platform for micro-simulation analysis, so as to use traffic simulation technology to analyze the micro-traffic flow at local key intersections, improve the comprehensiveness and accuracy of the analysis, and facilitate operation. For example, "A Port Water Planning Method and System Integrating AIS Data Mining (CN113435639A)" constructs a port water sample matrix for quantitative simulation analysis of port water planning, obtains a port water planning cluster that balances the planning accuracy and planning efficiency of quantitative simulation of port water planning and realizes unified analysis, and conducts quantitative simulation analysis of the passage planning of the port water based on the port water planning cluster.

[0003] In the existing technology, port planning simulation analysis mainly focuses on specific problem analysis of a single port, without fully considering the entire water and land operation system. Although the model is highly targeted, it has poor versatility, adaptability and scalability, and cannot be applied to the quantitative analysis of coordinated planning of most port water and land areas. Summary of the invention

[0004] The purpose of the present invention is to provide a system and method for quantitative analysis of nested coupling planning of port waters and land, so as to solve the technical problems that the prior art does not fully consider the entire water and land operation system, has poor versatility, adaptability and scalability, and cannot be applied to the quantitative analysis of the coordinated planning of most port waters and land areas.

[0005] In order to solve the above technical problems, the present invention specifically provides the following technical solutions:

[0006] A system for quantitative analysis of nested coupling planning of port waters and land areas, comprising:

[0007] The port water area-land area planning scheme digitalization module is used to digitally reconstruct the port water area and port land area planning schemes to obtain the physical models of the port water area and port land area;

[0008] The initialization simulation module is used to call the physical models of the port water area and the port land area to initialize the model, obtain the digital port, and make reservations for ships to arrive at the port, allocate berths and anchorages according to the feedback of ship movement at the digital port, and perform fine-grained simulation of the whole process of ships entering and leaving the port water area to the port terminal range in the physical model of the port water area, the physical model of the port land area and the digital port;

[0009] The nested coupling simulation module is used to construct the simulation scale and simulation results with the container as the intelligent agent by performing information nesting interaction between the entity models of the port water area and the port land area through the twin neural network based on the simulation scale and simulation results with the ship as the intelligent agent in the initialization simulation module;

[0010] The mixed-dimensional visualization statistical analysis module is used to output the visualization of the two-dimensional ship reaction trajectory in the simulation results with ships as intelligent entities, and to output the visualization of the three-dimensional container transportation operations in the simulation results with containers as intelligent entities. It automatically statistically analyzes ship records, port entry and exit delays, land loading and unloading, collection and distribution efficiency, cost, resource utilization, equipment energy consumption and carbon emissions, and port service level data.

[0011] As a preferred solution of the present invention, the port water area-land area planning scheme digitization module includes a water area planning scheme digitization submodule and a land area planning scheme digitization submodule;

[0012] The water area planning scheme digitization submodule is used to digitize and convert the coordinates of the port water area planning scheme's internal and external anchorages, channels, turning water areas, connecting water areas, crossing water areas, and shoreline berths to reconstruct them into a physical model of the port water area;

[0013] The land area planning scheme digitalization submodule is used to digitally analyze and coordinately transform the port scale, functional area layout, equipment parameters and configuration, road network structure generation, and loading and unloading process selection in the port land area planning scheme, and reconstruct it into a physical model of the port land area.

[0014] As a preferred solution of the present invention, the initialization simulation module includes a digital port initialization submodule, a ship operation behavior identification submodule, and a ship reaction behavior simulation submodule;

[0015] The digital port initialization submodule is used to initialize the physical models of the port water area and the port land area by presetting the port ship and container transportation rules to obtain the digital port;

[0016] The ship operation behavior identification submodule is used to perform physical simulation of ship arrival reservation, berth allocation and anchorage allocation at the digital port based on overall behavior identification and action feedback of all ships;

[0017] The ship reaction behavior simulation submodule is used to exchange information and call parameters with the digital port initialization submodule and the ship operation behavior identification submodule, and perform fine-grained entity simulation of the entire process of the ship entering and leaving the port waters and sailing to the port terminal range.

[0018] As a preferred solution of the present invention, the nested coupling simulation module includes a front loading and unloading operation simulation submodule, a horizontal transportation operation simulation submodule, a yard operation simulation submodule and an external logistics transportation operation submodule;

[0019] The frontier loading and unloading operation simulation submodule is an interactive undertaking module of the initialization simulation module and the nested coupling simulation module. It uses the twin neural network to nest and interact with the information between the physical models of the port water area and the port land area, performs the physical simulation of the loading and unloading transportation operations after the ship arrives at the port, and interacts with the horizontal transportation operation simulation submodule to perform the physical simulation of the container import and export process;

[0020] The horizontal transportation operation simulation submodule is a connection module between the frontier loading and unloading operation simulation submodule and the yard operation simulation submodule, and is used to perform a physical simulation of the container storage and transportation process from the ship to the yard area after loading and unloading based on the service rules, charging and swapping strategies, loading and unloading operation rules of the horizontal transportation equipment;

[0021] The yard operation simulation submodule is a connection system between the horizontal transportation operation simulation submodule and the external logistics transportation operation submodule, and is used to interact with the horizontal transportation operation simulation submodule to perform physical simulation of unloading and loading operations of containers during the loading and unloading process between the yard area and the horizontal transportation equipment; and interact with the external logistics transportation operation submodule to perform physical simulation of the process of containers leaving the port for external transportation;

[0022] The external logistics and transportation operation submodule is used to interact with the yard operation simulation submodule to perform physical simulation of the port collection and pickup operation process and the port delivery operation process at the gate, buffer zone and landside handover area;

[0023] The frontier loading and unloading operation simulation submodule uses twin neural networks to nest and interact information between the physical models of the port water area and the port land area, including:

[0024] The entity model of the port waters is input into the first neural network structure in the twin neural network, and the first neural network structure in the twin neural network outputs the two-dimensional spatiotemporal characteristics of the port waters;

[0025] The physical model of the port land area is input into the second neural network structure in the twin neural network, and the second neural network structure in the twin neural network outputs the three-dimensional spatiotemporal characteristics of the port land area;

[0026] The L1 norm error between the two-dimensional spatiotemporal characteristics of the port water area and the three-dimensional spatiotemporal characteristics of the port land area and are used as the loss function of the twin neural network;

[0027] Based on minimizing the loss function, the twin neural network is trained to obtain the interactive information extraction network;

[0028] The interactive information extraction network outputs the interactive information between the entity models of the port water area and the port land area;

[0029] The interactive information in the physical model of the port water area and the interactive information in the physical model of the port land area are nested to achieve scale coordination between the two-dimensional simulation of the port water area and the three-dimensional simulation of the port land area;

[0030] Among them, the expression of the interactive information extraction network is:

[0031]

[0032] Loss=L1[neural_net1(G1), neural_net2(G2)];

[0033] Where K is the interaction information, neural_net1 is the first neural network, neural_net2 is the second neural network, G1 is the entity model of the port water area, G2 is the entity model of the port land area, L1 is the L1 norm error operator, Loss is the loss function, and L1[neural_net1(G1), neural_net2(G2)] is the L1 norm error between neural_net1(G1) and neural_net2(G2).

[0034] As a preferred solution of the present invention, the mixed-dimensional visualization statistical analysis module outputs a two-dimensional ship reaction trajectory in the simulation results with the ship as the intelligent body, including the ship trajectory constituted by the entity simulation in the ship operation behavior identification submodule and the ship trajectory constituted by the entity simulation in the ship reaction behavior simulation submodule; and outputs a three-dimensional container transportation operation in the simulation results with the container as the intelligent body, including the entity simulation in the frontier loading and unloading operation simulation submodule, the entity simulation in the horizontal transportation operation simulation submodule, the entity simulation in the yard operation simulation submodule and the entity simulation in the external logistics transportation operation submodule.

[0035] As a preferred embodiment of the present invention, the present invention provides a method for quantitative analysis of nested coupling planning of port water area and land area, comprising the following steps:

[0036] Step S1, using the port water area-land area planning scheme digitization module to digitally reconstruct the port water area and port land area planning schemes to obtain the physical models of the port water area and port land area;

[0037] Step S2, using the initialization simulation module to call the physical models of the port water area and the port land area to initialize the model, obtain the digital port, and make an appointment for the ship to arrive at the port, allocate berths and anchorages according to the ship movement feedback at the digital port, and perform fine-grained simulation of the entire process of the ship entering and leaving the port water area to the port terminal range in the physical model of the port water area, the physical model of the port land area and the digital port;

[0038] Step S3, using the nested coupling simulation module based on the simulation scale and simulation results with the ship as the intelligent agent in the initialization simulation module, and performing information nesting interaction between the entity models of the port water area and the port land area through the twin neural network to construct the simulation scale and simulation results with the container as the intelligent agent;

[0039] Step S4, using the mixed-dimensional visualization statistical analysis module to output the visualization of the two-dimensional ship reaction trajectory in the simulation results with the ship as the intelligent body, and to output the visualization of the three-dimensional container transportation operation in the simulation results with the container as the intelligent body, and automatically statistically analyze the ship records, port entry and exit delays, land loading and unloading and collection and distribution operation efficiency, cost, resource utilization, equipment energy consumption and carbon emissions and port service level data.

[0040] As a preferred solution of the present invention, the construction of the physical model of the port water area and the port land area includes:

[0041] Through the water area planning scheme digitization submodule in the port water area-land area planning scheme digitization module, the port's internal and external anchorages, channels, turning waters, connecting waters, crossing waters, and shoreline berths in the port water area planning scheme are digitally analyzed and coordinate converted to reconstruct the physical model of the port water area;

[0042] Through the land area planning scheme digitization sub-module in the port water area-land area planning scheme digitization module, the port scale, functional area layout, equipment parameters and configuration, road network structure generation, and loading and unloading process selection in the port land area planning scheme are digitally analyzed and coordinate converted, and reconstructed into a physical model of the port land area.

[0043] As a preferred solution of the present invention, the digital port makes reservations for ships to arrive at the port, allocates berths and anchorages according to the feedback of ship movement, and performs fine-grained simulation of the entire process of ships entering and leaving the port waters and sailing to the port terminal in the physical model of the port waters, the physical model of the port land area and the digital port, including:

[0044] By initializing the digital port initialization submodule in the simulation module, the physical models of the port water area and the port land area are initialized based on the preset port ship and container transportation rules to obtain a digital port;

[0045] By initializing the ship operation behavior recognition submodule in the simulation module, based on the overall behavior recognition and action feedback of all ships, the physical simulation of the ship's scheduled arrival at the digital port, the allocation of berths and the allocation of anchorages is performed;

[0046] By initializing the ship reaction behavior simulation submodule in the simulation module, information interaction and parameter calls are carried out with the digital port initialization submodule and the ship operation behavior identification submodule to perform a fine-grained physical simulation of the entire process of the ship entering and leaving the port waters to the port terminal.

[0047] As a preferred solution of the present invention, the construction of the simulation scale and simulation results using the container as the intelligent body includes:

[0048] By nesting the frontier loading and unloading operation simulation submodule in the coupled simulation module, the twin neural network is used to nest and interact the information between the physical models of the port water area and the port land area, and the physical simulation of the loading and unloading transportation operations after the ship arrives at the port is performed. It also interacts with the horizontal transportation operation simulation submodule to perform the physical simulation of the container import and export process;

[0049] The submodule of horizontal transportation operation simulation in the nested coupling simulation module is to perform the physical simulation of the process of container storage and transportation from the ship to the yard area after loading and unloading based on the service rules, charging and swapping strategies, loading and unloading operation rules of the horizontal transportation equipment;

[0050] Through the nested coupled simulation module, the yard operation simulation submodule interacts with the horizontal transportation operation simulation submodule to perform the physical simulation of the unloading and loading operations of containers during the loading and unloading process between the yard area and the horizontal transportation equipment; and interacts with the external logistics transportation operation submodule to perform the physical simulation of the process of containers leaving the port for external transportation;

[0051] By nesting the external logistics and transportation operation submodule in the coupled simulation module and interacting with the yard operation simulation submodule, physical simulation of the port collection and pickup operation process and the port delivery operation process at the gate, buffer zone and landside handover area is performed.

[0052] As a preferred solution of the present invention, the information nesting interaction between the entity models of the port water area and the port land area includes:

[0053] The entity model of the port waters is input into the first neural network structure in the twin neural network, and the first neural network structure in the twin neural network outputs the two-dimensional spatiotemporal characteristics of the port waters;

[0054] The physical model of the port land area is input into the second neural network structure in the twin neural network, and the second neural network structure in the twin neural network outputs the three-dimensional spatiotemporal characteristics of the port land area;

[0055] The L1 norm error between the two-dimensional spatiotemporal characteristics of the port water area and the three-dimensional spatiotemporal characteristics of the port land area and are used as the loss function of the twin neural network;

[0056] Based on minimizing the loss function, the twin neural network is trained to obtain the interactive information extraction network;

[0057] The interactive information extraction network outputs the interactive information between the entity models of the port water area and the port land area;

[0058] The interactive information in the physical model of the port water area and the interactive information in the physical model of the port land area are nested to achieve scale coordination between the two-dimensional simulation of the port water area and the three-dimensional simulation of the port land area;

[0059] Among them, the expression of the interactive information extraction network is:

[0060]

[0061] Loss=L1[neural_net1(G1), neural_net2(G2)];

[0062] Where K is the interaction information, neural_net1 is the first neural network, neural_net2 is the second neural network, G1 is the entity model of the port water area, G2 is the entity model of the port land area, L1 is the L1 norm error operator, Loss is the loss function, and L1[neural_net1(G1), neural_net2(G2)] is the L1 norm error between neural_net1(G1) and neural_net2(G2).

[0063] Compared with the prior art, the present invention has the following beneficial effects:

[0064] The present invention takes the container transportation process as the research object. On the basis of analyzing the general layout of the container port and the loading and unloading process, the data such as the port scale, layout form, road network structure and loading and unloading process designed by the land planners and the port water area, berth layout planning scheme, navigation rules and predicted number of ships arriving at the port, ship reaction behavior logic and other data designed by the water area planners are used as modeling input data. The whole process, interactive, mixed-dimensional, and spatiotemporal nested simulation is performed on the container ship inbound and outbound traffic flow-terminal production operation process-port gate logistics channel under the port's land and water spatiotemporal planning scheme, and the statistical values ​​of important indicators of concern are output, so as to realize the quantitative evaluation of the land and water layout planning scheme under the coupling of multiple objectives and multiple environmental driving factors. BRIEF DESCRIPTION OF THE DRAWINGS

[0065] In order to more clearly illustrate the implementation methods of the present invention or the technical solutions in the prior art, the following briefly introduces the drawings required for the implementation methods or the description of the prior art. Obviously, the drawings in the following description are only exemplary, and for ordinary technicians in this field, other implementation drawings can be derived from the provided drawings without creative work.

[0066] Figure 1 A system structure diagram of the quantitative analysis of the nested coupling planning of port water and land areas provided by an embodiment of the present invention;

[0067] Figure 2 A logic flow chart of a ship operation behavior identification submodule provided in an embodiment of the present invention;

[0068] Figure 3 A logic flow chart of a front-end loading and unloading operation simulation submodule provided by an embodiment of the present invention;

[0069] Figure 4 A logic flow chart of a submodule for simulating horizontal transport operations provided by an embodiment of the present invention;

[0070] Figure 5 A logic flow chart of a yard operation simulation submodule provided by an embodiment of the present invention;

[0071] Figure 6 A logic flow chart of the external logistics transportation operation submodule provided by an embodiment of the present invention;

[0072] Figure 7 A flow chart of a quantitative analysis method for nested coupling planning of port water and land areas provided in an embodiment of the present invention;

[0073] Figure 8A logic block diagram of a quantitative analysis method for nested coupling planning of port water areas and land areas provided in an embodiment of the present invention. DETAILED DESCRIPTION

[0074] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0075] like Figure 1 As shown, the present invention provides a system for quantitative analysis of nested coupling planning of port water and land areas, including:

[0076] The port water area-land area planning scheme digitalization module is used to digitally reconstruct the port water area and port land area planning schemes to obtain the physical models of the port water area and port land area;

[0077] The initialization simulation module is used to call the physical models of the port water area and the port land area to initialize the model, obtain the digital port, and make reservations for ships to arrive at the port, allocate berths and anchorages according to the feedback of ship movement at the digital port, and perform fine-grained simulation of the whole process of ships entering and leaving the port water area to the port terminal range in the physical model of the port water area, the physical model of the port land area and the digital port;

[0078] The nested coupling simulation module is used to construct the simulation scale and simulation results with the container as the intelligent agent by performing information nesting interaction between the entity models of the port water area and the port land area through the twin neural network based on the simulation scale and simulation results with the ship as the intelligent agent in the initialization simulation module;

[0079] The mixed-dimensional visualization statistical analysis module is used to output the visualization of the two-dimensional ship reaction trajectory in the simulation results with ships as intelligent entities, and to output the visualization of the three-dimensional container transportation operations in the simulation results with containers as intelligent entities. It automatically statistically analyzes ship records, port entry and exit delays, land loading and unloading, collection and distribution efficiency, cost, resource utilization, equipment energy consumption and carbon emissions, and port service level data.

[0080] In order to improve the versatility of quantitative analysis of port planning, the present invention conducts collaborative quantitative analysis of the entire water area and land operation system in the port, and uses the data such as port scale, layout form, road network structure and loading and unloading process designed by land planners and the data such as port water area, berth layout planning scheme, navigation rules and predicted number of ships arriving at the port, ship reaction behavior logic designed by water area planners as modeling input data, and conducts full-process, interactive, and spatiotemporal nested simulation of container ship inbound and outbound traffic flow-terminal production operation process-port gate logistics channel under the port's water and land spatiotemporal planning scheme.

[0081] Specifically, the present invention digitally models the water area planning scheme and land area planning scheme designed by planners, and performs full-process physical simulation of container ship inbound and outbound traffic flow-terminal production operation process-port gate logistics channel under the port water and land area spatiotemporal planning scheme, and visualizes the physical simulation process of container ship inbound and outbound traffic flow-terminal production operation process-port gate logistics channel under the port water and land area spatiotemporal planning scheme through a mixed-dimensional visualization statistical analysis module. In the visualization process, it also automatically statistically analyzes ship records, port inbound and outbound delays, land loading and unloading and collection and distribution operation efficiency, cost, resource utilization, equipment energy consumption and carbon emissions and port service level data, so as to help planners understand the actual application of the planning scheme and realize the visualized quantitative evaluation of the port planning scheme.

[0082] Furthermore, due to the differences in spatial and temporal scales between water and land, there are technical barriers to collaborative quantitative analysis. The scale of land is smaller than that of water, and it is more inclined to three-dimensional simulation; the water area is vast, including information elements such as waterways and anchorages, and the spatial scale is larger, so it is more inclined to two-dimensional simulation. Therefore, during collaborative quantification, the scale coordination between three-dimensional land and two-dimensional water is achieved through information nesting and interaction between the physical models of port water and port land, so that the inaccurate physical simulation caused by dimensional differences in the physical simulation of the entire port container transportation process is reduced, and the accuracy of physical simulation is improved from the construction of digital models, avoiding the misassessment of water planning and land planning caused by inaccurate physical simulation, thereby ensuring the accuracy of quantitative evaluation of water planning and land planning.

[0083] The digital module of port water area-land area planning scheme includes the digital submodule of water area planning scheme and the digital submodule of land area planning scheme;

[0084] The water area planning scheme digitalization submodule is used to digitize and convert the coordinates of the port water area planning scheme's internal and external anchorages, channels, turning water areas, connecting water areas, crossing water areas, and shoreline berths to reconstruct them into a physical model of the port water area;

[0085] The land area planning scheme digitalization submodule is used to digitally analyze and coordinately transform the port scale, functional area layout, equipment parameters and configuration, road network structure generation, and loading and unloading process selection in the port land area planning scheme, and reconstruct it into a physical model of the port land area.

[0086] The initialization simulation module includes a digital port initialization submodule, a ship operation behavior identification submodule, and a ship reaction behavior simulation submodule;

[0087] The digital port initialization submodule is used to initialize the physical models of the port water area and the port land area by presetting the port ship and container transportation rules to obtain the digital port;

[0088] like Figure 2 As shown, the ship operation behavior identification submodule is used to perform physical simulation of ship arrival reservation, berth allocation and anchorage allocation at the digital port based on the overall behavior identification and action feedback of all ships;

[0089] The ship reaction behavior simulation submodule is used to exchange information and call parameters with the digital port initialization submodule and the ship operation behavior identification submodule, and perform fine-grained physical simulation of the entire process of ships entering and leaving the port waters and sailing to the port terminal.

[0090] The nested coupling simulation module includes the frontier loading and unloading operation simulation submodule, the horizontal transportation operation simulation submodule, the yard operation simulation submodule and the external logistics transportation operation submodule;

[0091] like Figure 3 As shown, the frontier loading and unloading operation simulation submodule is an interactive undertaking module of the initialization simulation module and the nested coupling simulation module. It uses the twin neural network to nest and interact with the information between the physical models of the port water area and the port land area, and performs the physical simulation of the loading and unloading transportation operations after the ship arrives at the port and berths. It also interacts with the horizontal transportation operation simulation submodule to perform the physical simulation of the container import and export process.

[0092] like Figure 4 As shown, the horizontal transportation operation simulation submodule is a connection module between the front loading and unloading operation simulation submodule and the yard operation simulation submodule, and is used to perform a physical simulation of the container storage and transportation process from the ship to the yard area after loading and unloading based on the service rules, charging and swapping strategies, loading and unloading operation rules of the horizontal transportation equipment;

[0093] like Figure 5As shown, the yard operation simulation submodule is a connection system between the horizontal transportation operation simulation submodule and the external logistics transportation operation submodule, and is used to interact with the horizontal transportation operation simulation submodule to perform the physical simulation of the unloading and loading transportation operations of containers in the loading and unloading process between the yard area and the horizontal transportation equipment; and interact with the external logistics transportation operation submodule to perform the physical simulation of the process of containers leaving the port for external transportation;

[0094] like Figure 6 As shown, the external logistics and transportation operation submodule is used to interact with the yard operation simulation submodule to perform physical simulation of the port collection and pickup operation process and the port delivery operation process at the gate, buffer zone and landside handover area;

[0095] The frontier loading and unloading operation simulation submodule uses twin neural networks to nest and interact information between the physical models of the port water area and the port land area, including:

[0096] The entity model of the port waters is input into the first neural network structure in the twin neural network, and the first neural network structure in the twin neural network outputs the two-dimensional spatiotemporal characteristics of the port waters;

[0097] The physical model of the port land area is input into the second neural network structure in the twin neural network, and the second neural network structure in the twin neural network outputs the three-dimensional spatiotemporal characteristics of the port land area;

[0098] The L1 norm error between the two-dimensional spatiotemporal characteristics of the port water area and the three-dimensional spatiotemporal characteristics of the port land area and are used as the loss function of the twin neural network;

[0099] Based on minimizing the loss function, the twin neural network is trained to obtain the interactive information extraction network;

[0100] The interactive information extraction network outputs the interactive information between the entity models of the port water area and the port land area;

[0101] The interactive information in the physical model of the port water area and the interactive information in the physical model of the port land area are nested to achieve scale coordination between the two-dimensional simulation of the port water area and the three-dimensional simulation of the port land area;

[0102] Among them, the expression of the interactive information extraction network is:

[0103]

[0104] Loss=L1[neural_net1(G1), neural_net2(G2)];

[0105] Where K is the interaction information, neural_net1 is the first neural network, neural_net2 is the second neural network, G1 is the entity model of the port water area, G2 is the entity model of the port land area, L1 is the L1 norm error operator, Loss is the loss function, and L1[neural_net1(G1), neural_net2(G2)] is the L1 norm error between neural_net1(G1) and neural_net2(G2).

[0106] The present invention utilizes a twin neural network to extract interactive information based on a loss function, so that the three-dimensional land features and the two-dimensional water features extracted from the twin neural network have the highest similarity, that is, the interactive information extracted by the twin neural network has both three-dimensional land features and two-dimensional water features. The interactive information is nested, and the physical model dimensions of the port water area and the port land area can be linked from the feature point of view, so that the two-dimensional scale of the port water area is unified with the three-dimensional scale of the port land area, and the trajectory of the ship in the water area and the container transportation operation on land are on the same dimensional scale. The three-dimensional and two-dimensional mixed-dimensional collaborative simulation is completed in the physical simulation, and the collaborative quantitative analysis of the spatial and temporal scales of the water and land areas in the port planning and evaluation is realized.

[0107] The mixed-dimensional visualization statistical analysis module outputs the two-dimensional ship reaction trajectory in the simulation results with the ship as the intelligent agent, including the ship trajectory constituted by the entity simulation in the ship operation behavior identification submodule and the ship trajectory constituted by the entity simulation in the ship reaction behavior simulation submodule; and outputs the three-dimensional container transportation operation in the simulation results with the container as the intelligent agent, including the entity simulation in the frontier loading and unloading operation simulation submodule, the entity simulation in the horizontal transportation operation simulation submodule, the entity simulation in the yard operation simulation submodule and the entity simulation in the external logistics transportation operation submodule.

[0108] like Figure 7 and Figure 8 As shown, the present invention provides a method for quantitative analysis of nested coupling planning of port water area and land area, comprising the following steps:

[0109] Step S1, using the port water area-land area planning scheme digitization module to digitally reconstruct the port water area and port land area planning schemes to obtain the physical models of the port water area and port land area;

[0110] Step S2, using the initialization simulation module to call the physical models of the port water area and the port land area to initialize the model, obtain the digital port, and make an appointment for the ship to arrive at the port, allocate berths and anchorages according to the ship movement feedback at the digital port, and perform fine-grained simulation of the entire process of the ship entering and leaving the port water area to the port terminal range in the physical model of the port water area, the physical model of the port land area and the digital port;

[0111] Step S3, using the nested coupling simulation module based on the simulation scale and simulation results with the ship as the intelligent agent in the initialization simulation module, and performing information nesting interaction between the entity models of the port water area and the port land area through the twin neural network to construct the simulation scale and simulation results with the container as the intelligent agent;

[0112] Step S4, using the mixed-dimensional visualization statistical analysis module to output the visualization of the two-dimensional ship reaction trajectory in the simulation results with the ship as the intelligent body, and to output the visualization of the three-dimensional container transportation operation in the simulation results with the container as the intelligent body, and automatically statistically analyze the ship records, port entry and exit delays, land loading and unloading and collection and distribution operation efficiency, cost, resource utilization, equipment energy consumption and carbon emissions and port service level data.

[0113] In order to improve the versatility of quantitative analysis of port planning, the present invention conducts collaborative quantitative analysis of the entire water area and land operation system in the port, and uses the data such as port scale, layout form, road network structure and loading and unloading process designed by land planners and the data such as port water area, berth layout planning scheme, navigation rules and predicted number of ships arriving at the port, ship reaction behavior logic designed by water area planners as modeling input data, and conducts full-process, interactive, and spatiotemporal nested simulation of container ship inbound and outbound traffic flow-terminal production operation process-port gate logistics channel under the port's water and land spatiotemporal planning scheme.

[0114] Specifically, the present invention digitally models the water area planning scheme and land area planning scheme designed by planners, and performs full-process physical simulation of container ship inbound and outbound traffic flow-terminal production operation process-port gate logistics channel under the port water and land area spatiotemporal planning scheme, and visualizes the physical simulation process of container ship inbound and outbound traffic flow-terminal production operation process-port gate logistics channel under the port water and land area spatiotemporal planning scheme through a mixed-dimensional visualization statistical analysis module. In the visualization process, it also automatically statistically analyzes ship records, port inbound and outbound delays, land loading and unloading and collection and distribution operation efficiency, cost, resource utilization, equipment energy consumption and carbon emissions and port service level data, so as to help planners understand the actual application of the planning scheme and realize the visualized quantitative evaluation of the port planning scheme.

[0115] Furthermore, due to the differences in spatial and temporal scales between water and land, there are technical barriers to collaborative quantitative analysis. The scale of land is smaller than that of water, and it is more inclined to three-dimensional simulation; the water area is vast, including information elements such as waterways and anchorages, and the spatial scale is larger, so it is more inclined to two-dimensional simulation. Therefore, during collaborative quantification, the scale coordination between three-dimensional land and two-dimensional water is achieved through information nesting and interaction between the physical models of port water and port land, so that the inaccurate physical simulation caused by dimensional differences in the physical simulation of the entire port container transportation process is reduced, and the accuracy of physical simulation is improved from the construction of digital models, avoiding the misassessment of water planning and land planning caused by inaccurate physical simulation, thereby ensuring the accuracy of quantitative evaluation of water planning and land planning.

[0116] Construction of physical models of port waters and port land areas, including:

[0117] Through the water area planning scheme digitization submodule in the port water area-land area planning scheme digitization module, the port's internal and external anchorages, channels, turning waters, connecting waters, crossing waters, and shoreline berths in the port water area planning scheme are digitally analyzed and coordinate converted to reconstruct the physical model of the port water area;

[0118] Through the land area planning scheme digitization sub-module in the port water area-land area planning scheme digitization module, the port scale, functional area layout, equipment parameters and configuration, road network structure generation, and loading and unloading process selection in the port land area planning scheme are digitally analyzed and coordinate converted, and reconstructed into a physical model of the port land area.

[0119] At the digital port, the ship is scheduled to arrive at the port, berths are allocated, and anchorages are allocated according to the ship movement feedback. In addition, in the physical model of the port water area, the physical model of the port land area, and the digital port, the whole process of the ship entering and leaving the port water area to the port terminal range is simulated in fine-grained manner, including:

[0120] By initializing the digital port initialization submodule in the simulation module, the physical models of the port water area and the port land area are initialized based on the preset port ship and container transportation rules to obtain a digital port;

[0121] By initializing the ship operation behavior recognition submodule in the simulation module, based on the overall behavior recognition and action feedback of all ships, the physical simulation of the ship's scheduled arrival at the digital port, the allocation of berths and the allocation of anchorages is performed;

[0122] By initializing the ship reaction behavior simulation submodule in the simulation module, information interaction and parameter calls are carried out with the digital port initialization submodule and the ship operation behavior identification submodule to perform a fine-grained physical simulation of the entire process of the ship entering and leaving the port waters to the port terminal.

[0123] The simulation scale and simulation results based on containers are constructed, including:

[0124] By nesting the frontier loading and unloading operation simulation submodule in the coupled simulation module, the twin neural network is used to nest and interact the information between the physical models of the port water area and the port land area, and the physical simulation of the loading and unloading transportation operations after the ship arrives at the port is performed. It also interacts with the horizontal transportation operation simulation submodule to perform the physical simulation of the container import and export process;

[0125] The submodule of horizontal transportation operation simulation in the nested coupling simulation module is to perform the physical simulation of the process of container storage and transportation from the ship to the yard area after loading and unloading based on the service rules, charging and swapping strategies, loading and unloading operation rules of the horizontal transportation equipment;

[0126] Through the nested coupled simulation module, the yard operation simulation submodule interacts with the horizontal transportation operation simulation submodule to perform the physical simulation of the unloading and loading operations of containers during the loading and unloading process between the yard area and the horizontal transportation equipment; and interacts with the external logistics transportation operation submodule to perform the physical simulation of the process of containers leaving the port for external transportation;

[0127] By nesting the external logistics and transportation operation submodule in the coupled simulation module and interacting with the yard operation simulation submodule, physical simulation of the port collection and pickup operation process and the port delivery operation process at the gate, buffer zone and landside handover area is performed.

[0128] The information nesting interaction between the entity models of the port water area and the port land area includes:

[0129] The entity model of the port waters is input into the first neural network structure in the twin neural network, and the first neural network structure in the twin neural network outputs the two-dimensional spatiotemporal characteristics of the port waters;

[0130] The physical model of the port land area is input into the second neural network structure in the twin neural network, and the second neural network structure in the twin neural network outputs the three-dimensional spatiotemporal characteristics of the port land area;

[0131] The L1 norm error between the two-dimensional spatiotemporal characteristics of the port water area and the three-dimensional spatiotemporal characteristics of the port land area and are used as the loss function of the twin neural network;

[0132] Based on minimizing the loss function, the twin neural network is trained to obtain the interactive information extraction network;

[0133] The interactive information extraction network outputs the interactive information between the entity models of the port water area and the port land area;

[0134] The interactive information in the physical model of the port water area and the interactive information in the physical model of the port land area are nested to achieve scale coordination between the two-dimensional simulation of the port water area and the three-dimensional simulation of the port land area;

[0135] Among them, the expression of the interactive information extraction network is:

[0136]

[0137] Loss=L1[neural_net1(G1), neural_net2(G2)];

[0138] Where K is the interaction information, neural_net1 is the first neural network, neural_net2 is the second neural network, G1 is the entity model of the port water area, G2 is the entity model of the port land area, L1 is the L1 norm error operator, Loss is the loss function, and L1[neural_net1(G1), neural_net2(G2)] is the L1 norm error between neural_net1(G1) and neural_net2(G2).

[0139] The present invention utilizes a twin neural network to extract interactive information based on a loss function, so that the three-dimensional land features and the two-dimensional water features extracted from the twin neural network have the highest similarity, that is, the interactive information extracted by the twin neural network has both three-dimensional land features and two-dimensional water features. The interactive information is nested, and the physical model dimensions of the port water area and the port land area can be linked from the feature point of view, so that the two-dimensional scale of the port water area is unified with the three-dimensional scale of the port land area, and the trajectory of the ship in the water area and the container transportation operation on land are on the same dimensional scale. The three-dimensional and two-dimensional mixed-dimensional collaborative simulation is completed in the physical simulation, and the collaborative quantitative analysis of the spatial and temporal scales of the water and land areas in the port planning and evaluation is realized.

[0140] The present invention takes the container transportation process as the research object. On the basis of analyzing the general layout of the container port and the loading and unloading process, the data such as the port scale, layout form, road network structure and loading and unloading process designed by the land planners and the port water area, berth layout planning scheme, navigation rules and predicted number of ships arriving at the port, ship reaction behavior logic and other data designed by the water area planners are used as modeling input data. The whole process, interactive, mixed-dimensional, and spatiotemporal nested simulation is performed on the container ship inbound and outbound traffic flow-terminal production operation process-port gate logistics channel under the port's land and water spatiotemporal planning scheme, and the statistical values ​​of important indicators of concern are output, so as to realize the quantitative evaluation of the land and water layout planning scheme under the coupling of multiple objectives and multiple environmental driving factors.

[0141] The above embodiments are only exemplary embodiments of the present application and are not intended to limit the present application. The protection scope of the present application is defined by the claims. Those skilled in the art may make various modifications or equivalent substitutions to the present application within the essence and protection scope of the present application, and such modifications or equivalent substitutions shall also be deemed to fall within the protection scope of the present application.

Claims

1. A system for quantitative analysis of nested coupling planning of port waters and land areas, characterized in that: include: The port water area-land area planning scheme digitalization module is used to digitally reconstruct the port water area and port land area planning schemes to obtain the physical models of the port water area and port land area; The initialization simulation module is used to call the physical models of the port waters and port land to initialize the model and obtain the digital port. At the digital port, the ship is scheduled to arrive at the port, the berth is allocated, and the anchorage is allocated according to the ship movement feedback. In the physical model of the port waters, the physical model of the port land, and the digital port, the whole process of the ship entering and leaving the port waters to the port terminal is simulated in fine-grained manner; The nested coupling simulation module is used to construct the simulation scale and simulation results with the container as the intelligent body based on the simulation scale and simulation results with the ship as the intelligent body in the initialization simulation module, including: the nested coupling simulation module includes a front loading and unloading operation simulation submodule, a horizontal transportation operation simulation submodule, a yard operation simulation submodule and an external logistics transportation operation submodule; The frontier loading and unloading operation simulation submodule is an interactive module for the initialization simulation module and the nested coupling simulation module. It uses the twin neural network to nest and interact with the information between the physical models of the port water area and the port land area, and performs the physical simulation of the loading and unloading transportation operations after the ship arrives at the port. It interacts with the horizontal transportation operation simulation submodule to perform the physical simulation of the container import and export process. The nested interactions include: Inputting the physical model of the port waters into the first neural network structure in the twin neural network, and the first neural network structure outputs the two-dimensional spatiotemporal characteristics of the port waters; Inputting the physical model of the port land area into the second neural network structure in the twin neural network, and the second neural network structure outputs the three-dimensional spatiotemporal characteristics of the port land area; Using the L1 norm error between the two-dimensional spatiotemporal feature and the three-dimensional spatiotemporal feature as the loss function of the twin neural network; Based on minimizing the loss function, the twin neural network is trained to obtain the interactive information extraction network; The interactive information extraction network outputs the interactive information between the entity models of the port water area and the port land area; The interactive information in the port water area entity model and the interactive information in the port land area entity model are nested to achieve scale coordination between the two-dimensional simulation of the port water area and the three-dimensional simulation of the port land area; The mixed-dimensional visualization statistical analysis module is used to output the visualization of the two-dimensional ship reaction trajectory in the simulation results with ships as intelligent entities, and to output the visualization of the three-dimensional container transportation operations in the simulation results with containers as intelligent entities. It automatically statistically analyzes ship records, port entry and exit delays, land loading and unloading, collection and distribution efficiency, cost, resource utilization, equipment energy consumption and carbon emissions, and port service level data.

2. The system for quantitative analysis of nested coupling planning of port water and land areas according to claim 1 is characterized by: The port water area-land area planning scheme digitization module includes a water area planning scheme digitization submodule and a land area planning scheme digitization submodule; The water area planning scheme digitization submodule is used to digitize and convert the coordinates of the port water area planning scheme's internal and external anchorages, channels, turning water areas, connecting water areas, crossing water areas, and shoreline berths to reconstruct them into a physical model of the port water area; The land area planning scheme digitalization submodule is used to digitally analyze and coordinately transform the port scale, functional area layout, equipment parameters and configuration, road network structure generation, and loading and unloading process selection in the port land area planning scheme, and reconstruct it into a physical model of the port land area.

3. The system for quantitative analysis of nested coupling planning of port water area and land area according to claim 2 is characterized by: The initialization simulation module includes a digital port initialization submodule, a ship operation behavior identification submodule, and a ship reaction behavior simulation submodule; The digital port initialization submodule is used to initialize the physical models of the port water area and the port land area by presetting the port ship and container transportation rules to obtain the digital port; The ship operation behavior identification submodule is used to perform physical simulation of ship arrival reservation, berth allocation and anchorage allocation at the digital port based on overall behavior identification and action feedback of all ships; The ship reaction behavior simulation submodule is used to exchange information and call parameters with the digital port initialization submodule and the ship operation behavior identification submodule, and perform fine-grained entity simulation of the entire process of the ship entering and leaving the port waters and sailing to the port terminal range.

4. The system for quantitative analysis of nested coupling planning of port water area and land area according to claim 3 is characterized by: The horizontal transportation operation simulation submodule is a connection module between the frontier loading and unloading operation simulation submodule and the yard operation simulation submodule, and is used to perform a physical simulation of the container storage and transportation process from the ship to the yard area after loading and unloading based on the service rules, charging and swapping strategies, loading and unloading operation rules of the horizontal transportation equipment; The yard operation simulation submodule is a connection system between the horizontal transportation operation simulation submodule and the external logistics transportation operation submodule, and is used to interact with the horizontal transportation operation simulation submodule to perform physical simulation of unloading and loading operations of containers during the loading and unloading process between the yard area and the horizontal transportation equipment; and interact with the external logistics transportation operation submodule to perform physical simulation of the process of containers leaving the port for external transportation; The external logistics and transportation operation submodule is used to interact with the yard operation simulation submodule to perform physical simulation of the port collection and pickup operation process and the port delivery operation process at the gate, buffer zone and landside handover area; The expression of the interactive information extraction network is: ； Loss=L1[neural_net1(G1), neural_net2(G2)]; Where K is the interaction information, neural_net1 is the first neural network, neural_net2 is the second neural network, G1 is the entity model of the port water area, G2 is the entity model of the port land area, L1 is the L1 norm error operator, Loss is the loss function, and L1[neural_net1(G1), neural_net2(G2)] is the L1 norm error between neural_net1(G1) and neural_net2(G2).

5. The system for quantitative analysis of nested coupling planning of port water area and land area according to claim 4 is characterized by: The mixed-dimensional visualization statistical analysis module outputs the two-dimensional ship reaction trajectory in the simulation results with the ship as the intelligent body, including the ship trajectory constituted by the entity simulation in the ship operation behavior identification submodule and the ship trajectory constituted by the entity simulation in the ship reaction behavior simulation submodule; and outputs the three-dimensional container transportation operation in the simulation results with the container as the intelligent body, including the entity simulation in the frontier loading and unloading operation simulation submodule, the entity simulation in the horizontal transportation operation simulation submodule, the entity simulation in the yard operation simulation submodule and the entity simulation in the external logistics transportation operation submodule.

6. A method for quantitative analysis of nested coupling planning of port waters and land areas, characterized in that: The following steps are involved: Step S1, using the port water area-land area planning scheme digitization module to digitally reconstruct the port water area and port land area planning schemes to obtain the physical models of the port water area and port land area; Step S2, using the initialization simulation module to call the physical models of the port water area and the port land area to initialize the model, and obtain the digital port. At the digital port, the ship is scheduled to arrive at the port, the berth is allocated, and the anchorage is allocated according to the ship movement feedback. In the physical model of the port water area, the physical model of the port land area, and the digital port, a fine-grained simulation is performed on the whole process of the ship entering and leaving the port water area to the port terminal range; Step S3, using the nested coupling simulation module to construct the simulation scale and simulation results with the container as the intelligent body based on the simulation scale and simulation results with the ship as the intelligent body in the initialization simulation module, including: the nested coupling simulation module includes a frontier loading and unloading operation simulation submodule, a horizontal transportation operation simulation submodule, a yard operation simulation submodule and an external logistics transportation operation submodule; The frontier loading and unloading operation simulation submodule is an interactive module for the initialization simulation module and the nested coupling simulation module. It uses the twin neural network to nest and interact with the information between the physical models of the port water area and the port land area, and performs the physical simulation of the loading and unloading transportation operations after the ship arrives at the port. It interacts with the horizontal transportation operation simulation submodule to perform the physical simulation of the container import and export process. The nested interactions include: Inputting the physical model of the port waters into the first neural network structure in the twin neural network, and the first neural network structure outputs the two-dimensional spatiotemporal characteristics of the port waters; Inputting the physical model of the port land area into the second neural network structure in the twin neural network, and the second neural network structure outputs the three-dimensional spatiotemporal characteristics of the port land area; Using the L1 norm error between the two-dimensional spatiotemporal feature and the three-dimensional spatiotemporal feature as the loss function of the twin neural network; Based on minimizing the loss function, the twin neural network is trained to obtain the interactive information extraction network; The interactive information extraction network outputs the interactive information between the entity models of the port water area and the port land area; The interactive information in the port water area entity model and the interactive information in the port land area entity model are nested to achieve scale coordination between the two-dimensional simulation of the port water area and the three-dimensional simulation of the port land area; Step S4, using the mixed-dimensional visualization statistical analysis module to output the visualization of the two-dimensional ship reaction trajectory in the simulation results with the ship as the intelligent body, and to output the visualization of the three-dimensional container transportation operation in the simulation results with the container as the intelligent body, and automatically statistically analyze the ship records, port entry and exit delays, land loading and unloading and collection and distribution operation efficiency, cost, resource utilization, equipment energy consumption and carbon emissions and port service level data.

7. The method for quantitative analysis of nested coupling planning of port water area and land area according to claim 6 is characterized by: The construction of the physical model of the port water area and the port land area includes: Through the water area planning scheme digitization submodule in the port water area-land area planning scheme digitization module, the port's internal and external anchorages, channels, turning waters, connecting waters, crossing waters, and shoreline berths in the port water area planning scheme are digitally analyzed and coordinate converted to reconstruct the physical model of the port water area; Through the land area planning scheme digitization sub-module in the port water area-land area planning scheme digitization module, the port scale, functional area layout, equipment parameters and configuration, road network structure generation, and loading and unloading process selection in the port land area planning scheme are digitally analyzed and coordinate converted, and reconstructed into a physical model of the port land area.

8. The method for quantitative analysis of nested coupling planning of port water area and land area according to claim 7 is characterized by: At the digital port, the ship is scheduled to arrive at the port, berths are allocated, and anchorages are allocated according to the feedback of ship movement. In the physical model of the port water area, the physical model of the port land area, and the digital port, the whole process of the ship entering and leaving the port water area to the port terminal is simulated in fine-grained manner, including: By initializing the digital port initialization submodule in the simulation module, the physical models of the port water area and the port land area are initialized based on the preset port ship and container transportation rules to obtain a digital port; By initializing the ship operation behavior recognition submodule in the simulation module, based on the overall behavior recognition and action feedback of all ships, the physical simulation of the ship's scheduled arrival at the digital port, the allocation of berths and the allocation of anchorages is performed; By initializing the ship reaction behavior simulation submodule in the simulation module, information interaction and parameter calls are carried out with the digital port initialization submodule and the ship operation behavior identification submodule to perform a fine-grained physical simulation of the entire process of the ship entering and leaving the port waters to the port terminal.

9. The method for quantitative analysis of nested coupling planning of port water area and land area according to claim 8 is characterized by: The simulation scale and simulation results based on containers are constructed, including: Through the horizontal transportation operation simulation submodule in the nested coupling simulation module, based on the service rules, charging and swapping strategies, loading and unloading operation rules of the horizontal transportation equipment, the physical simulation of the container storage and transportation process from the ship to the yard area is performed; Through the nested coupled simulation module, the yard operation simulation submodule interacts with the horizontal transportation operation simulation submodule to perform the physical simulation of the unloading and loading operations of containers during the loading and unloading process between the yard area and the horizontal transportation equipment; and interacts with the external logistics transportation operation submodule to perform the physical simulation of the process of containers leaving the port for external transportation; Through the nested coupling simulation module, the external logistics transportation operation submodule interacts with the yard operation simulation submodule to perform physical simulation of the port collection and delivery operation process at the gate, buffer zone and landside handover area; The expression of the interactive information extraction network is: ； Loss=L1[neural_net1(G1), neural_net2(G2)]; Where K is the interaction information, neural_net1 is the first neural network, neural_net2 is the second neural network, G1 is the entity model of the port water area, G2 is the entity model of the port land area, L1 is the L1 norm error operator, Loss is the loss function, and L1[neural_net1(G1), neural_net2(G2)] is the L1 norm error between neural_net1(G1) and neural_net2(G2).

10. The method for quantitative analysis of nested coupling planning of port water area and land area according to claim 9 is characterized by: The mixed-dimensional visualization statistical analysis module outputs the two-dimensional ship reaction trajectory in the simulation results with the ship as the intelligent body, including the ship trajectory constituted by the entity simulation in the ship operation behavior identification submodule and the ship trajectory constituted by the entity simulation in the ship reaction behavior simulation submodule; and outputs the three-dimensional container transportation operation in the simulation results with the container as the intelligent body, including the entity simulation in the frontier loading and unloading operation simulation submodule, the entity simulation in the horizontal transportation operation simulation submodule, the entity simulation in the yard operation simulation submodule and the entity simulation in the external logistics transportation operation submodule.

Images