Method for predicting development capacity of underground space of comprehensive transportation hub

Abstract

The application discloses a prediction method for comprehensive transportation hub underground space development capacity, and relates to the technical field of development capacity prediction, which comprises the following steps: performing discreteness analysis on a distributed transfer node, and positioning a transfer function space range; collecting passenger flow data to obtain distributed peak passenger flow data; performing extreme transfer scenario accommodation deduction to obtain peak hour passenger flow; performing function space scale deduction to output a transfer core area; mapping the transfer core area to a transfer core area space topology; constructing a transfer space envelope; and positioning an underground space development range. The application solves the technical problems that the existing technology cannot adapt to transfer demand, the development capacity is not clear, and the development planning lacks accuracy, and achieves the technical effects of realizing an underground space development range that can adapt to transfer demand and identify development capacity, and improving the accuracy and feasibility of underground space development planning.

Description

Technical Field

[0001] This invention relates to the field of development capacity prediction technology, and more specifically to a method for predicting the development capacity of underground space in integrated transportation hubs. Background Technology

[0002] With the acceleration of urbanization, integrated transportation hubs, as the core of passenger flow distribution, have an increasingly urgent need for underground space development. Current underground space development relies heavily on experience-based planning, failing to fully consider transfer needs and geological conditions: estimating space size based solely on single passenger flow data easily leads to a mismatch between the area of ​​the transfer core area and the actual peak hour passenger flow; the lack of standardized procedures for geological adaptability screening makes it difficult to accurately exclude unsafe areas; and the development capacity is not linked to the topology of the transfer space and energy consumption predictions, resulting in a disconnect between development scope and transfer efficiency, resource waste, and other problems, failing to meet the efficient, safe, and adaptable development needs of underground spaces in integrated transportation hubs.

[0003] Existing technologies suffer from technical problems such as the difficulty in adapting the development scope of underground space in integrated transportation hubs to the transfer demand, unclear development capacity, and a lack of precision in development planning. Summary of the Invention

[0004] This application provides a method for predicting the development capacity of underground space in integrated transportation hubs, which addresses the technical problems in the prior art where the development scope of underground space in integrated transportation hubs is difficult to adapt to transfer demand, the development capacity is unclear, and the development plan lacks precision.

[0005] In view of the above problems, this application provides a method for predicting the development capacity of underground space in integrated transportation hubs, the method comprising:

[0006] Using a preset transfer distance scale as a constraint, discrete analysis is performed on distributed transfer nodes to locate the transfer functional space range; passenger flow data is collected through interaction with the distributed transfer nodes to obtain distributed peak passenger flow data; extreme transfer scenario capacity simulation is performed on the distributed peak passenger flow data to obtain peak hour passenger flow; after retrieving the per capita dwell space benchmark value through network connection, the functional space scale is derived based on the per capita dwell space benchmark value and peak hour passenger flow, and the area of ​​the transfer core area is output; after obtaining the transfer building topology through interaction, the area of ​​the transfer core area is mapped to the transfer core area spatial topology according to the transfer building topology; the transfer auxiliary space is expanded on the transfer core area spatial topology to obtain the transfer space topology network, and then the transfer space envelope of the transfer space topology network is constructed; using the transfer space envelope as a constraint, geological adaptability space screening is performed within the transfer functional space range to locate the underground space development range, wherein the underground space development range is identified by the underground space development capacity.

[0007] One or more technical solutions provided in this application have at least the following technical effects or advantages:

[0008] Using a preset transfer distance scale as a constraint, discrete analysis is performed on distributed transfer nodes to locate the functional space range of transfers. Passenger flow data is collected through interaction with the distributed transfer nodes to obtain distributed peak passenger flow data. Extreme transfer scenario capacity simulations are performed on the distributed peak passenger flow data to obtain peak hourly passenger flow. Based on the per capita dwell space benchmark and peak hourly passenger flow, the functional space scale is derived, and the area of ​​the transfer core area is output. The area of ​​the transfer core area is mapped to the spatial topology of the transfer core area according to the transfer building topology. Transfer auxiliary space expansion is performed on the spatial topology of the transfer core area to obtain a transfer space topology network, and then the transfer space envelope of the transfer space topology network is constructed. Geological adaptability space screening is performed within the transfer functional space range to locate the underground space development scope. This achieves the technical effect of realizing an underground space development scope that adapts to transfer needs and identifies development capacity, improving the accuracy and feasibility of underground space development planning. Attached Figure Description

[0009] To more clearly illustrate the technical solutions in the embodiments of the present invention, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0010] Figure 1 A flowchart illustrating the method for predicting the development capacity of underground space in integrated transportation hubs, provided in an embodiment of this application.

[0011] Figure 2 This is a flowchart illustrating the process of obtaining the transfer space topology network in the prediction method for the development capacity of underground space in integrated transportation hubs provided in this application embodiment. Detailed Implementation

[0012] This application provides a method for predicting the development capacity of underground space in integrated transportation hubs, which addresses the technical problems in the prior art where the development scope of underground space in integrated transportation hubs is difficult to adapt to transfer demand, the development capacity is unclear, and the development plan lacks precision.

[0013] The technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only a part of the embodiments of this application, and not all of them. All other embodiments obtained by those skilled in the art based on the embodiments of this application without creative effort are within the scope of protection of this application.

[0014] Examples, such as Figure 1 As shown, this application provides a method for predicting the development capacity of underground space in integrated transportation hubs, the method comprising:

[0015] Step S100: Using a preset transfer distance scale as a constraint, perform discrete analysis on the distributed transfer nodes to locate the spatial range of the transfer function.

[0016] Specifically, using a walking distance of ≤300 meters as the preset transfer distance constraint, discrete analysis is conducted on distributed transfer nodes within the integrated transportation hub, such as subway transfer entrances, bus stops, and railway exit connection points, in order to locate the spatial range of transfer functions. The specific operation process is as follows: First, each distributed transfer node is used as the center of the spatial geometric analysis. With a fixed radius of 300 meters walking distance, a distributed transfer function space buffer zone covering the service radiation range of a single node is dynamically generated in the hub plane or three-dimensional space. This ensures that each buffer zone can completely cover the potential transfer activity area within the acceptable walking range of passengers around the node. Then, the planar intersection space of all generated distributed transfer function space buffer zones is solved using spatial geometric calculation tools. The core areas of multiple buffer zones that overlap and can serve multiple transfer nodes simultaneously are identified and extracted. At the same time, scattered edge areas in a single buffer zone that do not overlap, only serve a single node, and have weak support for the overall transfer function are eliminated. Finally, by integrating and defining the boundaries of the intersection areas, the transfer function space range that can centrally meet the passenger flow interaction needs between distributed transfer nodes and meets the 300-meter walking distance constraint is accurately located. This provides a clear spatial boundary basis for subsequent passenger flow data collection and screening of underground space development areas.

[0017] Step S200: Interact with the distributed transfer nodes to collect passenger flow data and obtain distributed peak passenger flow data.

[0018] Specifically, the process begins by establishing a real-time communication link between the nodes and the data acquisition system, based on passenger flow monitoring equipment deployed at distributed transfer nodes, such as gate flow statistics devices, video image analysis terminals, and infrared sensor counters. This ensures that the equipment can continuously capture passenger flow dynamics around the nodes. Subsequently, passenger flow data is retrieved from the monitoring equipment at each distributed transfer node at preset time intervals, such as every 5 minutes. This data covers different transfer directions, such as the number of passengers transferring from subway to bus or from railway to subway, as well as information on travel time and dwell time. During the data acquisition process, the raw data is initially screened to remove abnormal values ​​and invalid records caused by equipment malfunctions. The data is then categorized and integrated according to transfer nodes. Finally, based on the operational patterns of the integrated transportation hub, peak periods with concentrated daily passenger flow are identified and extracted, such as morning commuting hours and evening return trips. The passenger flow information of each distributed transfer node during peak periods is then summarized and structured to form distributed peak passenger flow data that reflects the peak passenger flow characteristics of different nodes. This provides basic data support for subsequent simulations of extreme transfer scenarios.

[0019] Step S300: Perform extreme transfer scenario simulation on the distributed peak passenger flow data to obtain peak hour passenger flow.

[0020] Specifically, a connection is established with the data interaction system of distributed transfer nodes to obtain the geometric coordinates of the actual transfer paths between each node. Simultaneously, the flow organization relationships between different paths are analyzed. Based on this information, a visualized transfer and evacuation path topology is constructed, clearly presenting the passenger flow logic and spatial distribution between nodes. Next, considering the extreme passenger flow situations that integrated transportation hubs may face, a threshold for extreme traffic distribution scenarios is predefined. This threshold includes parameters such as passenger flow transfer rate, walking speed reduction rate, and instantaneous passenger flow increase, ensuring coverage of extreme scenarios such as sudden large passenger flows and passenger detours caused by equipment failures. Subsequently, based on distributed peak passenger flow data as input, combined with the already constructed transfer and evacuation paths... The topology employs a spatiotemporal coupling algorithm to build a multi-constraint evacuation capacity assessment model. This model can simultaneously consider multiple constraints such as passenger flow density, path capacity, and traffic speed. Then, predefined thresholds for extreme traffic distribution scenarios are loaded into the model, and a traffic distribution simulation process is initiated to simulate the passenger flow status on various transfer paths under extreme scenarios, outputting dynamic bottleneck safety capacity intervals for different time periods and paths. Finally, the dynamic bottleneck safety capacity intervals are processed, and the median of the interval is extracted as the final peak hour passenger flow. This value accurately reflects the passenger flow carrying capacity of the hub under extreme transfer scenarios, providing crucial data for subsequent derivation of functional space scale.

[0021] Step S400: After retrieving the average per capita dwell space benchmark value through the network, the functional space scale is derived based on the average per capita dwell space benchmark value and peak hour passenger flow, and the area of ​​the transfer core area is output.

[0022] Specifically, the system initiates a network data retrieval function, accessing a transportation space benchmark database covering various transportation hubs, such as subway hubs, railway hubs, and integrated bus hubs. Multiple traffic congestion space benchmark values ​​corresponding to different types of hubs are obtained, ensuring data coverage of the spatial usage characteristics of different hubs. Next, combined with current operational data of integrated transportation hubs, the system calculates the average daily passenger flow percentage of various transportation hubs within distributed transfer nodes, such as subway transfer areas, railway connection areas, and bus transfer areas. Distributed weight parameters are generated based on these percentages, used to adapt the impact of different hub types on overall congestion space demand. Subsequently, the retrieved multiple traffic congestion space benchmark values ​​are weighted and fused according to the distributed weight parameters. By balancing the differences in benchmark values ​​among different hub types through weight allocation, a per capita congestion space benchmark value that conforms to the current actual passenger flow structure of the hub is obtained. Finally, the obtained per capita congestion space benchmark value is multiplied by the determined peak hour passenger flow. This calculation derives the functional space scale, and the result is the area of ​​the transfer core area that can meet the passenger congestion demand during peak hours, providing a quantitative dimensional basis for the subsequent construction of the transfer core area spatial topology.

[0023] Step S500: After interactively obtaining the topology of the transfer building, the area of ​​the transfer core area is mapped to the spatial topology of the transfer core area based on the topology of the transfer building.

[0024] Specifically, the area of ​​the transfer core area is transformed into a concrete spatial topology of the transfer core area. The specific process is as follows: First, establish a data interaction link with the architectural design system or building information management platform of the integrated transportation hub. Through this link, obtain the transfer building topology, which includes the layout, size, and spatial relationship of key facilities such as transfer passages, platforms, stairs, elevators, and ticket gates within the hub. This ensures that the obtained topology information can fully reflect the existing or planned architectural spatial structure of the hub. Next, quantify and decompose the output transfer core area area. Combined with the spatial attributes of each functional area in the transfer building topology, such as passageway access requirements and platform dwelling requirements, determine the reasonable allocation ratio of the core area area in the topology. Subsequently, based on the spatial coordinate system and structural logic of the transfer building topology, map the decomposed area data one by one to the corresponding architectural spatial areas. Clarify the specific boundaries, coverage, and sub-areas of the transfer core area in the topology, such as the size of the main transfer passage area and temporary dwelling area. Finally, through spatial coordinate calibration and topology structure adaptation, form a transfer core area spatial topology that accurately corresponds to the actual architectural space and whose size meets the area requirements of the transfer core area. This realizes the transformation of area data into a concrete spatial form, providing a clear spatial foundation for subsequent expansion of transfer auxiliary spaces.

[0025] Step S600: Extend the transfer auxiliary space of the transfer core area spatial topology to obtain the transfer space topology network, and then construct the transfer space envelope of the transfer space topology network.

[0026] Specifically, based on the obtained spatial topology of the transfer core area, and combined with the actual operational needs of the integrated transportation hub, additional demand spaces, including commercial service areas, passenger rest and waiting areas, emergency refuge areas, and equipment management areas, are expanded. These auxiliary spaces are integrated with the spatial topology of the core area to form a transportation hub spatial topology that covers more comprehensive functions. Next, distributed peak passenger flow data aligned with the time sequence is retrieved to analyze the passenger flow distribution characteristics and flow patterns during different peak periods. Passenger flow facility matching analysis is conducted based on parameters such as passenger flow density and direction of travel to determine distributed transfer and evacuation facilities suitable for passenger flow needs, including evacuation signs, temporary diversion channels, and emergency evacuation exits. Subsequently, based on the spatial distribution of distributed transfer nodes... The initial transfer topology network is obtained by initially splicing the distributed transfer and evacuation facilities with the spatial topology of the transportation hub. Then, according to the distribution rules of fire evacuation routes, a fire evacuation route model is planned and constructed on the main passenger flow path of the initial transfer topology network. This model is coupled with the initial network to form a structurally complete transfer space topology network that meets the requirements for safe evacuation. Finally, referring to the preset building setback requirements of the integrated transportation hub building design, the boundary of the transfer space topology network is reasonably expanded to reserve the necessary structural safety space and future operation and maintenance space. Through boundary integration and scope definition, a transfer space envelope that can completely cover all transfer-related spaces is constructed, providing a clear spatial constraint range for subsequent geological adaptability space selection.

[0027] Step S700: Using the transfer space envelope as a constraint, perform geological adaptability space screening within the transfer function space range to locate the underground space development range, wherein the underground space development range is marked with the underground space development capacity.

[0028] Specifically, the 1 / K spatial cube encompassing the transfer space is set as a uniform grid scale. Through spatial gridding, the entire transfer functional space is divided into a regular and continuous array of transfer functional spaces, ensuring that the spatial attributes of each grid unit can be individually identified and analyzed. Next, the geotechnical exploration database within the transfer functional space is accessed online to obtain geotechnical mechanical parameters, groundwater level depth, and stratum stability data corresponding to each grid unit, integrating them to form a geotechnical exploration data array that corresponds one-to-one with the transfer functional space array. Subsequently, based on a preset geological safety threshold, the geotechnical exploration data array is rigidly culled grid by grid, removing grid units with insufficient soil bearing capacity, excessively high groundwater levels, or stratum stability that do not meet development requirements, resulting in a geologically safe spatial array that retains only those with acceptable geological conditions. Then, morphological closing operations are performed on the geologically safe spatial array using 7×7 grid-scale structural elements, first targeting isolated voids in the array. The region undergoes an expansion operation to extend its boundaries, followed by an erosion operation to eliminate temporary redundant boundaries, fill spatial voids, and generate a smooth spatial array with uniform boundaries. Simultaneously, the accessibility of each grid unit is verified using a preset transfer distance scale, eliminating restricted grids that cannot meet transfer requirements, thus forming a connected and practical developable space. Finally, using the transfer space envelope as a spatial boundary constraint, the connected developable space is divided into multiple independent three-dimensional spatial units. A layered development potential assessment is conducted for each three-dimensional spatial unit, predicting energy consumption in building material production, transportation, construction machinery operation, and subsequent maintenance and ventilation. Development priorities are determined based on energy consumption levels, and three-dimensional spatial units with high development potential and meeting spatial envelope constraints are selected. These units are integrated, and the developable volume of each region is labeled, ultimately defining the underground space development area with clearly defined underground space development capacity.

[0029] In one possible implementation, step S600 further includes:

[0030] Step S610: Starting from the spatial topology of the transfer core area, expand the additional demand space to obtain the spatial topology of the transportation hub.

[0031] Step S620: Based on the time-aligned distributed peak passenger flow data, perform passenger flow facility matching analysis and output distributed transfer and evacuation facilities.

[0032] Step S630: Based on the spatial distribution of the distributed transfer nodes, the spatial topology of the distributed transfer and evacuation facilities and the transportation hub is spliced ​​together to obtain the transfer spatial topology network.

[0033] Step S640: Based on the preset building setback requirements, expand the transfer space topology network to construct the transfer space envelope.

[0034] Specifically, starting with the established spatial topology of the core transfer area, additional demand spaces are expanded in conjunction with the multi-functional operational needs of the integrated transportation hub. First, essential functions in hub operation, besides core transfers, are identified, including passenger rest and waiting spaces, commercial service spaces such as convenience stores, service stations, emergency shelters, and equipment management and maintenance spaces. Then, based on the spatial layout of the core transfer area and passenger flow direction, the location and scale of these additional spaces are rationally planned around the core topology to ensure that they do not interfere with the core transfer flow while conveniently serving passengers. Finally, the additional demand spaces are spatially integrated with the spatial topology of the core transfer area to form a transportation hub spatial topology encompassing both core transfers and auxiliary functions.

[0035] Based on time-aligned distributed peak passenger flow data, passenger flow facility matching analysis is conducted. First, the distributed peak passenger flow data is subdivided by time period and transfer direction to clarify the passenger flow density, passage speed, and flow characteristics of each transfer node during different peak periods. Then, based on these passenger flow characteristics, suitable types of transfer and evacuation facilities are selected, such as adding temporary diversion channels for high passenger flow directions, configuring evacuation signs in areas where passenger flow is concentrated, and setting up emergency evacuation exits at the connection points of transfer nodes. Subsequently, the number, size, and layout of each type of evacuation facility are determined in combination with passenger flow carrying capacity requirements, and finally, distributed transfer and evacuation facilities that are accurately matched with passenger flow characteristics are output.

[0036] Based on the spatial distribution of distributed transfer nodes, the distributed transfer and evacuation facilities are spliced ​​with the spatial topology of the transportation hub. First, using the coordinates of the distributed transfer nodes as spatial references, the relative positions of each evacuation facility with the nodes, core transfer areas, and additional spaces are clarified. Then, following the principles of providing services nearby and not obstructing passenger flow, the distributed transfer and evacuation facilities are connected one by one to the corresponding areas of the transportation hub spatial topology. For example, evacuation signs are placed along transfer passages, and temporary diversion passages are connected to transfer nodes with high passenger flow. At the same time, the rationality of the spliced ​​spatial structure is verified to ensure that the evacuation facilities form a coherent passage network with the original topology, ultimately resulting in a functionally complete and smoothly flowing transfer spatial topology network.

[0037] Based on pre-set building setback requirements, the boundary of the transfer space topology network is expanded to construct a transfer space envelope. First, the pre-set setback standards in the integrated transportation hub building design are retrieved. These standards cover structural safety setbacks, such as reserving construction space for walls and beams; fire safety code setbacks, such as safe distances from fire sources; and post-operation and maintenance setbacks, such as reserving space for equipment maintenance access. Then, according to the setback standards, the outer boundary of the transfer space topology network is uniformly expanded to ensure that each area meets the setback requirements. Finally, the expanded spatial range is integrated to form a closed and continuous spatial outline, i.e., the transfer space envelope, providing clear spatial constraints for subsequent geological adaptability screening.

[0038] In one possible implementation, such as Figure 2 As shown, step S630 further includes:

[0039] Step S631: Based on the spatial distribution of the distributed transfer nodes, initialize and splice the spatial topology of the distributed transfer and evacuation facilities and transportation hubs to obtain the initial transfer topology network.

[0040] Step S632: Based on the distribution rules of fire evacuation routes, construct a fire evacuation route model on the main passenger flow path of the initial transfer topology network.

[0041] Step S633: Couple the fire evacuation route model and splice the distributed transfer evacuation facilities and transportation hub spatial topology into the transfer space topology network.

[0042] Specifically, the precise spatial coordinate data of distributed transfer nodes is retrieved to clarify the specific location of each node in the overall spatial coordinate system of the integrated transportation hub and the distance relationship between them, which serves as the spatial reference for the splicing operation. Next, the spatial model data of the output distributed transfer and evacuation facilities and the obtained transportation hub spatial topology are obtained. The distributed transfer and evacuation facilities include temporary diversion channels, evacuation signs, emergency evacuation exits, etc., while the transportation hub spatial topology covers the core transfer area, additional demand space, and connecting channels of various functional areas. Subsequently, in accordance with the principle of "evacuation facilities serving the corresponding transfer nodes nearby without blocking the core transfer flow", the spatial model of the distributed transfer and evacuation facilities is aligned with the functionally matching areas in the transportation hub spatial topology. For example, emergency evacuation exits are connected to the entrances and exits of channels near transfer nodes, and temporary diversion channels are connected to the edge of transfer areas with large passenger flow. Through spatial geometric calculations, the initial integration of each facility and the topology is completed to ensure that the evacuation facilities and the transportation hub spatial topology are spatially connected and conflict-free, ultimately forming an initial transfer topology network that includes core transfer functions, additional demand space, and basic evacuation facilities.

[0043] The existing fire evacuation route distribution rules in the industry were retrieved to clarify core technical parameters such as route width, turning radius, safety distance, and traffic capacity, which served as the standard basis for model construction. Next, distributed peak passenger flow data after time-alignment was loaded onto the initial transfer topology network, and a passenger flow simulation analysis program was launched. By simulating the flow trajectory and traffic volume of passenger flow within the network during different peak hours, the main passenger flow routes with the highest passenger volume and carrying the main transfer demand were identified. Subsequently, combining the fire evacuation route distribution rules and the spatial characteristics of the main passenger flow routes, the orientation of the fire evacuation routes was planned, prioritizing routes along the main routes. The passageways are laid out alongside or parallel to the main routes to ensure convenient access to the main routes. The width of the passageways and the radius of curvature at turns are determined according to the rules, and a safe distance is reserved from potential fire sources within the network (such as equipment rooms and commercial service areas). Finally, a three-dimensional spatial modeling technology is used to construct a fire evacuation passageway model that is consistent with the spatial proportion of the initial transfer topology network according to the planning parameters. The model clearly marks the start and end points of the passageways, the coordinates of key nodes, and functional attributes to ensure that the model not only meets the requirements of fire protection codes but also forms a coordinated evacuation system with the main passenger flow routes of the initial transfer topology network.

[0044] The constructed fire evacuation route model is imported into the spatial coordinate system of the initial transfer topology network. Spatial coordinate calibration technology is used to ensure accurate matching of the positional relationships between the fire evacuation route model and the facilities in the initial network, avoiding spatial overlaps or gaps. Next, the connection areas between the fire evacuation route model and the distributed transfer evacuation facilities and the spatial topology of the transportation hub are verified one by one. If spatial conflicts are found between the route and existing facilities, such as overlap between route entrances / exits and congestion points in transfer routes, the route positions or facility layouts are adjusted according to passenger flow lines and fire safety regulations to ensure overall spatial functional coordination. Subsequently, a fire evacuation... The functional connection between passageways and distributed transfer and evacuation facilities, and the spatial topology of transportation hubs, such as setting up interconnected entrances and exits between fire evacuation passageways and temporary diversion passageways, and reserving emergency evacuation interfaces at the locations where passageways pass through the core transfer area and additional demand spaces, ensures that various facilities form a coherent evacuation and transfer network; finally, the integrity and rationality of the overall spatial structure after splicing and integration are verified to confirm that the network covers core transfer functions, additional demand spaces, basic evacuation facilities and fire passageways, and that the flow of each part is smooth and complies with safety regulations, ultimately forming a functionally complete and collaboratively efficient transfer space topology network.

[0045] In one possible implementation, step S300 further includes:

[0046] Step S310: Interact to obtain the real-time transfer path geometric coordinates and streamline organization relationship between the distributed transfer nodes.

[0047] Step S320: Based on the real-time transfer path geometric coordinates and streamline organization relationship, construct the transfer evacuation path topology.

[0048] Step S330: Predefine extreme traffic gathering and dispersal scenario thresholds, wherein the extreme traffic gathering and dispersal scenario thresholds include passenger flow transfer rate, walking speed reduction rate, and instantaneous passenger flow increase parameters.

[0049] Step S340: Based on the distributed peak passenger flow data and transfer evacuation path topology, a multi-constraint evacuation capacity evaluation model is constructed using a spatiotemporal coupling algorithm.

[0050] Step S350: Load the extreme traffic gathering and dispersal scenario threshold into the multi-constraint evacuation capacity assessment model, and output the dynamic bottleneck safety capacity range through traffic gathering and dispersal simulation.

[0051] Step S360: Extract the median of the dynamic bottleneck safety capacity range as the peak hour passenger flow output.

[0052] Specifically, by establishing interactive connections with the spatial information system or route planning platform of integrated transportation hubs, real-time geometric coordinates and flow organization relationships of transfer paths between distributed transfer nodes are obtained. During the interaction, precise coordinate data of the actual travel paths between each transfer node, such as subway transfer entrances and bus connection points, are retrieved, including the three-dimensional coordinates of the starting point, ending point, and key points along the path. At the same time, the flow organization relationships of these paths are analyzed, clarifying the primary and secondary levels of different paths, the priority of transfer directions, and the connection logic between them, providing basic spatial data for subsequent topology construction.

[0053] The geometric coordinates of each transfer path are transformed into nodes and edges in a spatial network. Transfer nodes and key points along the path are used as network nodes, and path segments are used as connecting edges. Then, the connection rules between nodes are determined according to the flow organization relationship. For example, the edge weights corresponding to the main direction of passenger flow are marked first, and the transfer connection nodes between different paths are clarified. Finally, these nodes and edges are integrated through network modeling tools to form a transfer and evacuation path topology that can intuitively reflect the path distribution, connection relationship and passenger flow direction.

[0054] Predefined thresholds for extreme traffic distribution scenarios are set around key parameters of passenger flow operation. Among them, the passenger flow transfer rate is used to characterize the proportion of passenger flow to transfer to other routes under sudden circumstances, such as the failure of a certain route. The walking speed reduction rate is used to reflect the extent to which the walking speed of passengers is reduced from the normal state under extreme passenger flow density. The instantaneous passenger flow increase parameter is used to define the sudden increase multiple of passenger flow in a short period of time, such as the departure of a large event. By setting specific numerical ranges for these parameters, the characteristics of passenger flow changes under extreme scenarios are covered.

[0055] Based on distributed peak passenger flow data as input, and combined with the established transfer and evacuation path topology, a multi-constraint evacuation capacity assessment model is built using a spatiotemporal coupling algorithm. This algorithm considers both the time dimension (e.g., peak passenger flow distribution and passenger travel time) and the spatial dimension (e.g., path width and node capacity). Distributed peak passenger flow data is allocated to corresponding nodes and edges in the transfer and evacuation path topology according to time slices. Constraints such as path capacity, passenger walking speed, and node transfer efficiency are then incorporated. Through algorithmic computation, a multi-constraint assessment model capable of simulating evacuation capacity under different scenarios is constructed.

[0056] The predefined extreme traffic distribution scenario thresholds are loaded into the multi-constraint evacuation capacity assessment model to initiate the traffic distribution simulation process. During the simulation, the model simulates the flow of passenger flow in the transfer and evacuation path topology under extreme thresholds. For example, it simulates passenger flow path switching based on passenger flow transfer rate, adjusts passenger passage speed based on walking speed reduction rate, and simulates sudden passenger flow growth based on instantaneous passenger flow increase parameters. It monitors the passenger flow carrying capacity of each path and node in real time, identifies bottleneck areas of passenger flow congestion, and then outputs the dynamic bottleneck safety capacity range corresponding to different time periods and different bottleneck areas. This range reflects the safe passenger flow carrying capacity range of each area under extreme scenarios.

[0057] This study collects all dynamic bottleneck safety capacity intervals output from traffic distribution simulations. These intervals correspond to different bottleneck areas in the transfer and evacuation path topology, such as the safe passenger flow carrying capacity of key transfer nodes and core passage sections under extreme scenarios. Next, numerical analysis is performed on each dynamic bottleneck safety capacity interval to calculate the median of each interval. This eliminates the impact of interval boundary fluctuations on data representativeness, ensuring that the data for a single interval accurately reflects the safety carrying capacity level of the corresponding bottleneck area. Subsequently, the medians of each interval are weighted and balanced based on the functional weight of each bottleneck area in the overall transfer and evacuation network, such as the passenger flow distribution ratio of core transfer nodes and the passenger flow proportion of main passages. This avoids distortion of the overall results due to data bias from a single high-weight bottleneck area. Finally, the weighted average value is determined as the final peak hour passenger flow and output. This value encompasses the safety constraints of each bottleneck area and comprehensively reflects the overall passenger flow carrying capacity of the integrated transportation hub under extreme transfer scenarios, providing a precise quantitative basis for subsequent functional space scale derivation.

[0058] In one possible implementation, step S100 further includes:

[0059] Step S110: Dynamically generate a distributed transfer function space buffer with the distributed transfer node as the center and the transfer distance scale as the radius.

[0060] Step S120: Solve the planar intersection space of the distributed transfer function space buffer to locate the range of the transfer function space.

[0061] Specifically, the precise 3D coordinate data of all distributed transfer nodes are retrieved. These nodes cover key transfer locations within the hub, such as subway transfer entrances, bus connection points, and railway exit transfer points. Simultaneously, the coordinates of each node are calibrated against the overall spatial coordinate system of the hub to ensure accurate spatial positioning. Next, a spatial buffer zone generation program is initiated. Centered on the coordinates of each distributed transfer node, and with a radius parameter of ≤300 meters walking distance, a coverage area is dynamically drawn in planar or 3D space, forming a transfer function spatial buffer zone corresponding to each node. During the generation process, the buffer zone boundaries are adaptively adjusted based on the actual spatial characteristics of the hub, such as existing building structures and passageway layouts, to avoid overlap between buffer zones and impassable areas (such as walls and equipment rooms). This ensures that each buffer zone accurately covers the potential transfer activity area centered on the node and reachable by passengers within a 300-meter walking distance. Finally, each distributed transfer node generates an independent transfer function spatial buffer zone, and each buffer zone is associated with and labeled with the functional attributes and spatial extent data of the corresponding node, providing a clear basic spatial unit for subsequent planar intersection space solutions.

[0062] All distributed transfer function spatial buffers are imported into a unified planar coordinate system to ensure that the spatial coordinates of each buffer are consistent with the overall spatial positioning of the hub, avoiding the impact of coordinate system deviation on the accuracy of intersection calculation. Next, spatial geometry calculation tools are launched to compare and analyze the boundary contours and internal coverage areas of each buffer one by one, identifying spatial regions where multiple buffers overlap. These overlapping regions can simultaneously cover the service range of multiple distributed transfer nodes and are core areas with concentrated passenger transfer activities and frequent passenger flow interaction between multiple nodes. Subsequently, scattered edge areas in a single buffer that do not overlap with other buffers are removed. These areas can only serve a single transfer node, have weak support for the overall transfer function, and their inclusion would increase the redundancy of subsequent development and analysis. Finally, the extracted overlapping intersection areas are integrated and their contours optimized. The precise spatial range of the regions is clarified through coordinate calibration, forming a complete and continuous transfer function spatial range.

[0063] In one possible implementation, step S400 further includes:

[0064] Step S410: Retrieve multiple traffic congestion space benchmark values ​​from various transportation hubs via the network.

[0065] Step S420: Calculate the average daily passenger flow ratio of the various transportation hubs in the distributed transfer nodes, and output the distributed weight parameters.

[0066] Step S430: Based on the distributed weight parameters, the multiple traffic congestion space benchmark values ​​are weighted and fused to obtain the per capita congestion space benchmark value.

[0067] Step S440: Based on the benchmark value of per capita dwell space and peak hour passenger flow, deduce the functional space scale and output the area of ​​the transfer core area.

[0068] Specifically, the network data interaction function is activated to access a traffic space benchmark database covering various types of transportation hubs. This database stores multiple traffic congestion space benchmark values ​​for different types of hubs, such as subway hubs, railway hubs, public transport hubs, and intercity rail hubs. These benchmark values ​​are derived from long-term operational data of various hubs and reflect industry standards and practical data on the average passenger congestion space required in different scenarios. By accessing the network, these traffic congestion space benchmark values ​​covering multiple hub types can be obtained, providing a data foundation for subsequent benchmark value adaptation.

[0069] For the distributed transfer nodes of current integrated transportation hubs, the daily average passenger flow data of various types of transportation hubs, such as areas for subway transfers, areas for railway connections, and areas for bus transfers, is statistically analyzed. The proportion of each type of transportation hub in the total daily average passenger flow of all distributed transfer nodes is calculated. This proportion directly reflects the degree of influence of different types of hubs on the overall transfer space demand. These proportion data are converted into corresponding distributed weight parameters. The value of the weight parameter is positively correlated with the daily average passenger flow proportion of the corresponding transportation hub, thereby quantifying the contribution of different hub types in the space demand calculation.

[0070] Based on the output distributed weight parameters, a weighted fusion calculation is performed on multiple retrieved traffic congestion space benchmark values. During the calculation, the traffic congestion space benchmark value corresponding to each type of transportation hub is multiplied by the distributed weight parameters of that type of hub to obtain the weighted term of each benchmark value. Then, all weighted terms are summed to finally obtain the per capita congestion space benchmark value that adapts to the current passenger flow structure of the integrated transportation hub. This benchmark value takes into account the spatial demand characteristics of different types of hubs to ensure a high degree of matching with the actual transfer scenario.

[0071] Data verification was performed on the two core parameters to confirm that the baseline value of per capita dwell space conforms to the current passenger flow structure characteristics of the hub and that the peak hour passenger flow can reflect the passenger flow carrying capacity demand under extreme scenarios, thus avoiding parameter deviations from affecting the derivation results. Next, preliminary calculations were performed based on the formula: functional space scale = baseline value of per capita dwell space × peak hour passenger flow, to obtain the theoretical space scale required to meet the simultaneous dwelling of all passengers during peak hours. Subsequently, the theoretical space scale was fine-tuned in combination with the actual operational needs of the integrated transportation hub. For example, the space occupied by transfer passage redundancy requirements, facility layout (such as ticket gates and directional signs), and temporary buffering needs for sudden passenger flow were considered, and a certain proportion of space margin was appropriately increased. Finally, through space size calibration, the fine-tuned space scale was converted into a specific area value. This value is the area of ​​the transfer core area that can adapt to transfer needs and ensure traffic efficiency, serving as the quantitative basis for the subsequent spatial topology construction of the transfer core area.

[0072] In one possible implementation, step S700 further includes:

[0073] Step S710: Using the 1 / K space cube of the transfer space envelope as a grid scale, divide the transfer function space range into a transfer function space array.

[0074] Step S720: Retrieve soil and rock exploration data from the transfer function spatial array to obtain a soil and rock exploration data array.

[0075] Step S730: Based on the preset geological safety threshold, traverse the rock and soil exploration data array and perform grid-by-grid rigid removal to obtain a geological safety spatial array.

[0076] Step S740: Perform morphological closure operation on the geological safety space array to fill the voids and generate a connected exploitable space range.

[0077] Step S750: Using the transfer space envelope as a constraint, the development potential of the connected developable space is assessed by layering, and the development scope of the underground space is selected and located.

[0078] Specifically, based on the constructed transfer space envelope, the 1 / K spatial cube of this envelope is set as a uniform grid scale, and the K value is determined according to the accuracy requirements of the hub space. The spatial division process is then initiated to regularly divide the located transfer function space range. During the division process, the transfer function space range is decomposed into multiple three-dimensional grid units of uniform size and clearly defined coordinates according to the grid scale. Each unit corresponds to a unique spatial location identifier, ultimately forming a structurally regular and individually analyzable transfer function space array, providing standardized spatial units for subsequent geotechnical data retrieval and geological screening.

[0079] For the completed transfer function spatial array, the geotechnical exploration data exchange retrieval function is activated, connecting to the geotechnical engineering database of the area where the integrated transportation hub is located. Based on the spatial coordinates of each grid cell, the corresponding geotechnical exploration data is precisely matched and retrieved, including key geological parameters such as soil type, bearing capacity, groundwater level depth, stratum lithology, and void ratio. This data is then integrated according to the grid cells to form a geotechnical exploration data array that perfectly matches the spatial location of the transfer function spatial array, ensuring that the geological conditions of each grid cell can be quantitatively assessed.

[0080] Based on preset geological safety thresholds, such as minimum soil bearing capacity limits, maximum groundwater level control values, and critical parameters for stratum stability, a grid-by-grid rigid elimination operation is performed on the geotechnical exploration data array. The geotechnical parameters corresponding to each grid cell are iterated. If the parameters of a cell exceed the safety threshold (e.g., bearing capacity below the limit or groundwater level above the control value), the geological conditions of that cell are deemed unsuitable for development and it is eliminated. Only grid cells whose parameters meet the safety thresholds are retained, ultimately forming a geologically safe spatial array containing only geologically safe areas, thus initially identifying spatial ranges with development potential.

[0081] Morphological closure operations are performed on the geological safety spatial array to fill spatial voids. During the operation, a 7×7 grid-scale structural element is used to traverse the geological safety spatial array. First, isolated void regions in the array are identified, which are non-safe blank units surrounded by safety grid units. Then, using the structural element as a constraint, an expansion operation is performed on the void regions to expand the boundaries, so that the edge of the void merges with the surrounding safety units to form an expansion zone. Next, an erosion operation is performed on the expansion zone to eliminate the temporary redundant boundaries generated during the expansion process, resulting in a smooth spatial array with closed voids and smooth boundaries. Finally, the accessibility of each grid unit is verified by combining a preset transfer distance scale, and restricted grids that cannot meet the transfer passage requirements are eliminated, ultimately generating a continuous and complete connected exploitable spatial range.

[0082] According to a preset depth interval, such as 5 meters per layer, the connected developable space is slidably divided to obtain multiple independent three-dimensional spatial units, each corresponding to a specific development depth level. Next, the energy consumption of each three-dimensional spatial unit is predicted for layered development, focusing on calculating carbon emissions from building material production, carbon emissions during transportation, energy consumption of construction machinery, and energy consumption for operation and maintenance ventilation. The layered energy consumption coefficient of each unit is determined based on the energy consumption level. Then, the units are sorted in descending order of layered energy consumption coefficient, with lower energy consumption indicating higher development potential. Combined with the boundary constraints of the transfer space envelope, three-dimensional spatial units with lower energy consumption coefficients and within the envelope are selected. Finally, these units are integrated and the developable volume of each area is marked, ultimately locating the underground space development area marked with underground space development capacity.

[0083] In one possible implementation, step S740 further includes:

[0084] Step S741: Using 7×7 grid cells as the structural elements for morphological closure operations, traverse the geological safety space array to identify the distribution of isolated pore areas.

[0085] Step S742: Using the grid cells as constraints, perform an expansion operation on the isolated hole region distribution to generate an expansion zone.

[0086] Step S743: Perform an erosion operation on the expansion region to eliminate temporary redundant boundaries and obtain a smooth spatial array with closed pores.

[0087] Step S744: Verify the transfer accessibility of the smooth space array based on the transfer distance scale to eliminate restricted grids and output the connected exploitable space range.

[0088] Specifically, a 7×7 grid cell is selected as the structural element for morphological closure operations. The size and accuracy of this structural element have been calibrated to meet the needs of underground space development, enabling precise identification of tiny isolated cavities in the geological safety space array. Traversal is initiated, scanning the geological safety space array row by row and column by column according to a preset path. By comparing the attributes (safe / unsafe) of adjacent grid cells, isolated cavity regions that are completely surrounded by safe grid cells and are themselves unsafe are marked. At the same time, the spatial coordinates and extent of these regions are recorded, forming isolated cavity region distribution data.

[0089] Using 7×7 grid cells as constraints, an expansion operation is performed on the identified isolated hole regions to extend their boundaries. During the operation, starting from the boundary grid of the isolated hole region, the expansion proceeds uniformly outwards to the safe area outside the hole, according to the size of the 7×7 grid cells. This gradually merges the hole boundary with the surrounding safe grid cells, filling the unsafe blank areas inside the hole, and ultimately generating an expanded area that covers the hole and part of the surrounding safe area, thus initially eliminating spatial discontinuity issues.

[0090] Corrosion operations were performed on the expansion zone to eliminate temporary redundant boundaries generated during the expansion process. Using the 7×7 grid cell as a reference, the edges of the expansion zone were shrunken grid by grid, preserving the core area that was closely connected to the original geological safety spatial array, and removing redundant boundaries that exceeded reasonable limits due to excessive expansion. This restored the boundaries of the processed spatial array to a smooth and continuous state, ultimately resulting in a uniform spatial array with completely closed pores and a regular spatial shape.

[0091] The precise three-dimensional coordinates of all grid cells in the smooth spatial array are retrieved, and the coordinate data of each distributed transfer node within the integrated transportation hub are also obtained to establish a unified spatial distance calculation coordinate system. Next, the straight-line walking distance from each grid cell to the nearest distributed transfer node is calculated one by one. If the walking distance of a certain grid cell exceeds 300 meters, it is determined to be a restricted grid cell that cannot meet the passenger transfer access needs and is marked and included in the elimination range. Subsequently, the smooth spatial array is checked grid by grid, and all grid cells marked as restricted are removed, leaving only grid cells with a walking distance within 300 meters and meeting the geological conditions. Finally, the spatial continuity of the remaining grid cells is checked, and adjacent grid cells with the same attributes are integrated to form a complete and coherent spatial region. The final output is a connected and developable spatial range that can simultaneously meet the requirements of geological safety and transfer accessibility.

[0092] In one possible implementation, step S750 further includes:

[0093] Step S751: Using the transfer space envelope as a constraint, slide to divide the connected exploitable space range to obtain multiple three-dimensional spatial units.

[0094] Step S752: Perform layered development energy consumption prediction on the multiple three-dimensional spatial units to obtain multiple layered energy consumption coefficients.

[0095] Step S753: Arrange the multiple layered energy consumption coefficients in descending order, and locate the underground space development area in the multiple three-dimensional spatial units according to the sorting results.

[0096] Specifically, the three-dimensional boundary coordinates of the transfer space envelope are clearly defined, including the horizontal planar range and the vertical depth range, ensuring that the segmented spatial units are completely within the envelope boundary and do not exceed the development area defined by the envelope. Next, uniform sliding segmentation parameters are set: horizontally, planar areas are divided according to a preset grid span, such as a 20m x 20m square grid; vertically, cutting layers are determined at fixed depth intervals, such as every 5 meters, forming a standardized segmentation grid system. Then, sliding segmentation is initiated, using the horizontal cutting plane parallel to the ground as a reference, and proceeding vertically from the connected openable... The system slides and cuts the space layer by layer from top to bottom, while simultaneously dividing it into horizontal grids. This process decomposes the overall space into multiple regularly sized, clearly defined cubic or cuboid three-dimensional spatial units. During the segmentation process, the system verifies in real time whether the boundary of each unit conforms to the envelope constraint of the transfer space. If a part of a unit exceeds the envelope, the excess part is automatically trimmed, retaining only the space within the envelope. This ensures that all the three-dimensional spatial units obtained are completely within the transfer space envelope, and each unit is marked with a unique spatial location identifier and size parameters, providing a standardized analysis unit for subsequent layered development energy consumption prediction.

[0097] The Gradient Boosting Regression Tree (GBRT) algorithm is used to predict the energy consumption of multiple three-dimensional spatial units in a hierarchical manner, in order to accurately obtain the hierarchical energy consumption coefficient. The specific implementation process is as follows: First, a multi-dimensional feature dataset is constructed. Geological parameters of each three-dimensional spatial unit, such as soil and rock type coding and groundwater level depth; spatial parameters, such as volume, depth, and horizontal coordinates; surrounding resource parameters, such as distance to building material bases and accessibility scores for construction machinery; and historical energy consumption data from similar projects are used as input features. Simultaneously, the actual full-cycle energy consumption of the corresponding unit, covering building material production, transportation, construction machinery, and operation and maintenance ventilation, is used as label values ​​to form a training sample set. Next, the feature data undergoes standardized preprocessing, such as Min-Max normalization, to eliminate the dimensional differences between parameters of different dimensions. Then, K-fold cross-validation is used to divide the sample set into a training set and a validation set for model training and hyperparameter optimization. During the model training phase, the GBRT algorithm... Multiple regression decision trees are constructed iteratively, with each tree trained based on the prediction residuals of the preceding model to gradually reduce prediction errors. A learning rate is introduced to control the contribution weight of each tree, preventing overfitting. After training, the feature data of the three-dimensional spatial unit to be predicted is input into the optimized GBRT model. The model automatically learns the nonlinear mapping relationship between each feature and energy consumption, outputting predictions for carbon emissions from building material production, transportation, construction machinery, and operation and maintenance ventilation for each unit. Finally, the predicted values ​​for each stage are weighted and summed, with weights determined based on the energy consumption proportion of each stage in historical projects, resulting in a comprehensive energy consumption quantification index for each three-dimensional spatial unit, i.e., a hierarchical energy consumption coefficient. This enables accurate prediction of development energy consumption for different three-dimensional spatial units.

[0098] The energy consumption coefficients of all three-dimensional spatial units are sorted in descending order, with the unit with the lowest energy consumption coefficient and the highest development potential placed first, and units with higher energy consumption coefficients and lower development potential placed later. Then, in combination with the constraints of the transfer space envelope, the selection process starts from the front of the sorted results, prioritizing three-dimensional spatial units with low energy consumption coefficients that fully meet the envelope boundary constraints, while removing units that are ranked later, have higher energy consumption, or are close to the envelope boundary and pose development risks. Finally, the selected high-quality three-dimensional spatial units are spatially integrated to clarify the connection relationship and overall scope of each unit, mark the developable volume of each unit, and finally locate the underground space development area marked with underground space development capacity.

[0099] In one possible implementation, step S752 further includes:

[0100] The energy consumption forecast for the tiered development includes forecasts of carbon emissions from building material production, carbon emissions from transportation, energy consumption from construction machinery, and energy consumption from operation and maintenance ventilation.

[0101] Specifically, the energy consumption forecast for tiered development covers four core dimensions: Carbon emission forecasting for building material production refers to calculating the total carbon emissions of the production process based on the types and quantities of building materials required for underground space development, such as concrete, steel, and waterproofing materials, combined with the unit carbon emission coefficients of various building materials during production; Carbon emission forecasting for transportation is based on the transportation distance and mode of transportation from the production base to the construction site, such as road transport, rail transport, waterway transport, and the corresponding unit mileage carbon emission intensity of the transport vehicles, combined with the volume of building materials transported, to calculate the total carbon emissions of the entire transportation process; Energy consumption forecasting for construction machinery considers the type, power, and estimated operating time of machinery used in underground space construction, such as excavators, tunnel boring machines, cranes, and concrete pump trucks, combined with the energy consumption standards per unit operating time of the machinery, to arrive at the total energy consumption of the construction phase; Energy consumption forecasting for operation and maintenance ventilation is based on the depth and volume of the underground space, and the design parameters of the ventilation system, such as the power of ventilation equipment, ventilation frequency, and average daily operation and maintenance time, to estimate the total energy consumption of the ventilation system required to ensure air circulation and meet the requirements of personnel breathing and environmental quality during long-term operation.

[0102] It should be noted that the order of the embodiments described above is merely for descriptive purposes and does not represent the superiority or inferiority of the embodiments. Furthermore, the above description focuses on specific embodiments of this specification. Additionally, the processes depicted in the accompanying drawings do not necessarily require a specific or sequential order to achieve the desired results. In some implementations, multitasking and parallel processing are possible or may be advantageous.

[0103] The above description is only a preferred embodiment of this application and is not intended to limit this application. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of this application should be included within the protection scope of this application.

[0104] This specification and accompanying drawings are merely illustrative examples of this application and are intended to cover any and all modifications, variations, combinations, or equivalents within the scope of this application. Clearly, those skilled in the art can make various alterations and modifications to this application without departing from its scope. Therefore, if such modifications and variations fall within the scope of this application and its equivalents, this application intends to include such modifications and variations.

Claims

1. A method for predicting the development capacity of underground space in integrated transportation hubs, characterized in that, The method includes: Using a preset transfer distance scale as a constraint, a discrete analysis is performed on distributed transfer nodes to locate the spatial range of transfer functions; The distributed transfer nodes are used to collect passenger flow data to obtain distributed peak passenger flow data. The peak hour passenger flow is obtained by performing extreme transfer scenario simulations on the distributed peak passenger flow data. After retrieving the average per capita dwell space benchmark value from the network, the functional space scale is derived based on the average per capita dwell space benchmark value and peak hour passenger flow, and the area of ​​the transfer core area is output. After obtaining the topology of the transfer buildings interactively, the area of ​​the transfer core area is mapped to the spatial topology of the transfer core area based on the topology of the transfer buildings. After performing transfer auxiliary space expansion on the spatial topology of the transfer core area to obtain the transfer space topology network, the transfer space envelope of the transfer space topology network is constructed. Using the transfer space envelope as a constraint, geological adaptability space screening is carried out within the transfer function space to locate the underground space development range, wherein the underground space development range is marked with the underground space development capacity. The method includes: extending the spatial topology of the transfer core area through transfer auxiliary space expansion to obtain a transfer spatial topology network, and then constructing the transfer spatial envelope of the transfer spatial topology network. Starting from the spatial topology of the transfer core area, additional demand space expansion is carried out to obtain the spatial topology of the transportation hub; Based on the time-aligned distributed peak passenger flow data, passenger flow facility matching analysis is performed, and distributed transfer and evacuation facilities are output. Based on the spatial distribution of the distributed transfer nodes, the spatial topology of the distributed transfer and evacuation facilities and the transportation hub is spliced ​​together to obtain the transfer spatial topology network; Based on the preset building setback requirements, the transfer space topology network is expanded to construct the transfer space envelope; Based on the spatial distribution of the distributed transfer nodes, the spatial topology of the distributed transfer and evacuation facilities and the transportation hub is pieced together to obtain the transfer spatial topology network. The method includes: Based on the spatial distribution of the distributed transfer nodes, the spatial topology of the distributed transfer and evacuation facilities and transportation hubs is initialized and spliced ​​to obtain an initial transfer topology network; Based on the distribution rules of fire evacuation routes, a fire evacuation route model is constructed on the main passenger flow path of the initial transfer topology network. Couple the fire evacuation route model and stitch the distributed transfer evacuation facilities and transportation hub spatial topology together to form the transfer space topology network.

2. The method for predicting the development capacity of underground space in integrated transportation hubs as described in claim 1, characterized in that, The method involves performing extreme transfer scenario simulations on the distributed peak passenger flow data to obtain peak hour passenger flow. The real-time geometric coordinates of transfer paths and streamline organization relationships between the distributed transfer nodes are obtained interactively. Based on the real-time transfer path geometric coordinates and streamline organization relationship, a transfer evacuation path topology is constructed; Predefined thresholds for extreme traffic gathering and dispersal scenarios, wherein the thresholds for extreme traffic gathering and dispersal scenarios include passenger flow transfer rate, walking speed reduction rate, and instantaneous passenger flow increase parameters; Based on the distributed peak passenger flow data and transfer evacuation path topology, a multi-constraint evacuation capacity evaluation model is constructed using a spatiotemporal coupling algorithm. The extreme traffic gathering and dispersal scenario threshold is loaded into the multi-constraint evacuation capacity assessment model, and the dynamic bottleneck safety capacity range is output through traffic gathering and dispersal simulation. The median of the dynamic bottleneck safety capacity range is extracted and used as the peak hour passenger flow output.

3. The method for predicting the development capacity of underground space in integrated transportation hubs as described in claim 1, characterized in that, Using a preset transfer distance scale as a constraint, a discrete analysis is performed on distributed transfer nodes to locate the spatial range of transfer functions. The method includes: Using the distributed transfer node as the center and the transfer distance scale as the radius, a distributed transfer function space buffer is dynamically generated; The planar intersection space of the distributed transfer function space buffer is solved to locate the range of the transfer function space.

4. The method for predicting the development capacity of underground space in integrated transportation hubs as described in claim 1, characterized in that, After retrieving the baseline value of average dwell time per person from the network, the functional space scale is derived based on the baseline value of average dwell time per person and peak hour passenger flow, and the area of ​​the transfer core area is output. The method includes: The system retrieves multiple traffic congestion space benchmark values ​​from various transportation hubs via a network. The daily average passenger flow percentage of the various transportation hubs in the distributed transfer nodes is statistically analyzed, and the distributed weight parameters are output. The average traffic congestion space benchmark value is obtained by weighting and fusing the multiple traffic congestion space benchmark values ​​based on the distributed weight parameters. Based on the baseline value of per capita dwell space and peak hour passenger flow, the functional space scale is derived, and the area of ​​the transfer core area is output.

5. The method for predicting the development capacity of underground space in integrated transportation hubs as described in claim 1, characterized in that, Using the aforementioned transfer space envelope as a constraint, geological adaptability space screening is performed within the transfer functional space to locate the underground space development area, wherein the underground space development area is identified by its development capacity. The method includes: Using the 1 / K space cube of the transfer space envelope as a grid scale, the transfer function space range is divided into a transfer function space array; Geotechnical exploration data is retrieved from the transfer function spatial array to obtain a geotechnical exploration data array; Based on a preset geological safety threshold, the geotechnical exploration data array is traversed and rigidly removed grid by grid to obtain a geological safety spatial array. Morphological closure operations are performed on the geological safety space array to fill the voids and generate a connected exploitable space range; Using the transfer space envelope as a constraint, the development potential of the connected developable space is assessed in layers to identify and locate the development scope of the underground space.

6. The method for predicting the development capacity of underground space in integrated transportation hubs as described in claim 5, characterized in that, Using the transfer space envelope as a constraint, morphological closure operations are performed on the geological safety space array to fill voids and generate a connected exploitable space range. The method includes: Using 7×7 grid cells as structural elements for morphological closure operations, the geological safety spatial array is traversed to identify the distribution of isolated cavity areas. Using the grid cells as constraints, an expansion operation is performed on the isolated hole region distribution to generate an expansion zone. Erosion is performed on the expansion region to eliminate temporary redundant boundaries, resulting in a smooth spatial array with closed pores. Based on the transfer distance scale, the transfer accessibility of the smooth spatial array is verified to eliminate restricted grids and output the connected and exploitable spatial range.

7. The method for predicting the development capacity of underground space in integrated transportation hubs as described in claim 5, characterized in that, Using the transfer space envelope as a constraint, the method involves assessing the development potential of the connected developable space in layers to identify and locate the development area of ​​the underground space. Using the transfer space envelope as a constraint, the connected exploitable space range is slidably divided to obtain multiple three-dimensional spatial units; Layered development energy consumption prediction is performed on the multiple three-dimensional spatial units to obtain multiple layered energy consumption coefficients; The multiple layered energy consumption coefficients are arranged in descending order, and the underground space development area is located in the multiple three-dimensional spatial units according to the sorting results.

8. The method for predicting the development capacity of underground space in integrated transportation hubs as described in claim 7, characterized in that, The energy consumption forecast for the tiered development includes forecasts of carbon emissions from building material production, carbon emissions from transportation, energy consumption from construction machinery, and energy consumption from operation and maintenance ventilation.

Images