A method and system for intelligent layout of underground spaces

Abstract

The application discloses a kind of underground space intelligent layout method and system, and layout method includes the following steps S1, based on the preset underground space layout knowledge and user input constraint condition, initial layout is generated using graph theory method;S2, using multi-objective optimization algorithm, the initial layout is optimized by comprehensive evaluation index;S3, layout result and evaluation data are directly shown.Layout system includes layout module, optimization module and visualization module, and optimization module uses multi-objective optimization algorithm, and the initial layout generated is optimized by comprehensive evaluation index.The application greatly improves the efficiency of underground space layout design, comprehensively considers multiple key indicators such as function compatibility, human flow organization efficiency, average accessibility and space utilization, to ensure that the layout scheme generated realizes optimal balance in each dimension.

Description

TECHNICAL FIELD

[0001] The present application relates to the field of architectural design and urban planning, and particularly relates to a method and system for intelligent layout of underground space. BACKGROUND

[0002] With the accelerating process of global urbanization, the increasing population density and the increasing tension of land space, the development and utilization of underground space becomes increasingly important. Underground space not only can alleviate the pressure of ground space, but also can provide new public facilities, transportation hubs, commercial and residential space, providing new possibilities for urban development. However, as a key link of underground space development, the layout design of underground space faces many unique and complex challenges. These challenges include the limitation of space, such as the shape and area of underground space are usually limited by geological conditions, surrounding building foundation structure and other factors; the requirement of safety, such as the strict requirements of fire prevention, flood control, earthquake prevention and other safety issues in underground environment; and the complexity of environmental factors, such as the influence of underground water level, soil properties, geological structure and other factors on design and construction.

[0003] However, the traditional design method is difficult to effectively cope with these complex factors, often leading to low design efficiency, and the design scheme is difficult to fully consider all related factors. In recent years, although some computer-aided design tools have been applied in the field of architectural design, most of these tools mainly focus on the design of above-ground buildings, and do not fully consider the special needs of underground space. The special nature of underground space determines that its design process is more complex than above-ground buildings, and the design needs to fully consider the various limitations of underground environment, in addition, the functional diversity and complexity of underground space require the design system to consider multiple objectives such as space utilization rate, people flow organization efficiency, safety and economy, etc. These objectives are usually contradictory, so seeking the optimal balance between multiple design objectives becomes a major challenge, and this situation leads to the fact that the effect and efficiency of underground space layout design cannot meet the rapid growth of urban underground space development needs. SUMMARY

[0004] In view of the deficiencies of the prior art, the present application proposes a method and system for intelligent layout of underground space, aiming to overcome the limitations of traditional design methods in dealing with the complexity of underground space, and to solve the multi-dimensional challenges faced in the layout design of underground space by constructing an intelligent layout system that can comprehensively consider the particularity of underground space.

[0005] To achieve the above-mentioned purpose, the technical scheme of the present application is as follows:

[0006] A method for intelligent layout of underground space, comprising the following steps:

[0007] S1, based on the preset underground space layout knowledge and the constraint conditions input by the user, an initial layout is generated using a graph theory method;

[0008] S2, using a multi-objective optimization algorithm, the initial layout is optimized through comprehensive evaluation indexes;

[0009] S3, the layout result and evaluation data are intuitively displayed.

[0010] Preferably, the step S1 comprises:

[0011] S11, a functional relationship graph is constructed, and a connection relationship graph between functional units is established using an adjacency matrix or a visualization graph tool according to the functional requirements and spatial relationships input by the user;

[0012] S12, a maximum plane subgraph is solved, and the functional relationship graph is converted into a plane graph using a graph theory algorithm for subsequent processing;

[0013] S13, rectangular layout design, the plane graph is converted into a rectangular layout, and a heuristic algorithm is used to optimize the rectangular arrangement to maximize space utilization;

[0014] S14, non-rectangular layout adaptation, the rectangular layout is adjusted according to the actual underground space shape to adapt to the non-rectangular space requirements.

[0015] Preferably, the step S2 comprises:

[0016] S21, parameter initialization;

[0017] S22, initial scheme generation, an initial scheme is generated based on the output of the layout module;

[0018] S23, score calculation, each layout scheme is scored using a comprehensive evaluation index;

[0019] S24, scheme iteration and optimization, a genetic algorithm or a particle swarm optimization algorithm is used for iterative optimization;

[0020] S25, optimal scheme selection, the scheme with the highest score is selected as the final optimization result.

[0021] Preferably, the parameters in the step S21 include space unit functions, expected traffic volume, and space utilization.

[0022] Preferably, the calculation formula of the comprehensive evaluation index CEI in the step S23 is as follows:

[0023]

[0024] In the above formula, w1, w2, w3, w4: weight coefficients of each index;

[0025] FCI: Functional Compatibility Index, ;

[0026] FOEI: Flow Organization Efficiency Index, ;

[0027] AAI: Average Accessibility Index, ;

[0028] SUR: Space Utilization Ratio, ;

[0029] N: Total number of functional units;

[0030] M: Total number of main flow paths;

[0031] : Relationship strength between functional units i and j;

[0032] : Spatial distance between functional units i and j;

[0033] : Flow of the kth main flow path;

[0034] : Length of the kth main flow path;

[0035] : Shortest path time from functional unit i to j;

[0036] : Area of functional unit i;

[0037] A_total: Total available area.

[0038] Preferably, step S3 further comprises:

[0039] S31, hierarchical display, displaying the layout of each functional area in the form of a two-dimensional plan;

[0040] S32, three-dimensional display, providing a three-dimensional view of the underground space layout, supporting rotation, scaling and other interactive operations;

[0041] S33, real-time data visualization chart, dynamically displaying the changes of evaluation indicators during the optimization process, including trend charts of comprehensive evaluation indicators and their constituent indicators.

[0042] Preferably, it further comprises step S34, through interactive adjustment function, allowing users to adjust the generated layout scheme according to actual needs, and real-time view the impact of adjustment on the layout scheme.

[0043] The present application also discloses an underground space intelligent layout system, comprising:

[0044] a layout module that generates an initial layout based on preset underground space layout knowledge and user-inputted constraint conditions using a graph theory method;

[0045] an optimization module that optimizes the initial layout using a multi-objective optimization algorithm through comprehensive evaluation indicators;

[0046] a visualization module that visually displays the layout results and evaluation data.

[0047] Preferably, the optimization module includes a multi-objective evaluation module and an optimization algorithm module, the multi-objective evaluation module calculates the functional compatibility index, the human flow organization efficiency index, the average accessibility index, and the space utilization rate, and performs overall evaluation through comprehensive evaluation indicators; the optimization algorithm module uses a genetic algorithm or a particle swarm optimization method to customize the design according to the characteristics of underground space.

[0048] Preferably, the visualization module includes an interactive optimization module and a result output module, the interactive optimization module allows designers to manually adjust the layout and instantly view the impact, and the result output module generates standardized output including floor plans, 3D models, and evaluation reports, and provides a data interface with mainstream CAD software.

[0049] The present application has the following advantages: first, by introducing intelligent algorithms and multi-objective optimization techniques, the present application greatly improves the efficiency of underground space layout design and significantly shortens the design cycle. The system comprehensively considers multiple key indicators such as functional compatibility, human flow organization efficiency, average accessibility, and space utilization rate, ensuring that the generated layout scheme achieves optimal balance in various dimensions. In addition, the system has high adaptability and can adapt to different types and sizes of underground space projects through flexible parameter settings, meeting a wide range of application needs. The present application also provides intuitive 2D and 3D visualization interfaces, greatly improving the readability and understandability of the layout scheme, facilitating designers and other relevant personnel to evaluate and make decisions on the scheme. Through iterative optimization algorithms, the system can continuously improve the layout scheme to achieve the best balance of design indicators. At the same time, the system supports multi-person collaboration, promoting the joint participation and optimization of designers with different professional backgrounds, and improving the work efficiency of the design team. Finally, by optimizing space utilization and functional configuration, the layout scheme generated by the present application can effectively reduce construction and operation costs and improve the overall economic efficiency of the project, providing strong technical support for the successful implementation of underground space development projects. BRIEF DESCRIPTION OF DRAWINGS

[0050] Figure 1 is a flowchart of the underground space intelligent layout method according to an embodiment of the present application;

[0051] Figure 2is a layout flowchart of an embodiment of the present application;

[0052] Figure 3 is an optimization flowchart of an embodiment of the present application;

[0053] Figure 4 is a system structure and workflow diagram for an underground space intelligent layout system of an embodiment of the present application;

[0054] Figure 5 is a whole architecture diagram for an underground space intelligent layout system of an embodiment of the present application;

[0055] Figure 6 is a user interaction interface schematic diagram of an embodiment of the present application. DETAILED DESCRIPTION

[0056] The technical solutions in the embodiments of the present application will be described clearly and completely below with reference to the accompanying drawings in the embodiments of the present application. Obviously, the described embodiments are only some of the embodiments of the present application, but not all the embodiments of the present application. Based on the embodiments of the present application, all other embodiments obtained by those of ordinary skill in the art belong to the present application.

[0057] In addition, the described features, structures or characteristics can be combined in any suitable way in one or more embodiments. In the following description, many specific details are provided to give a full understanding of the embodiments of the present application. However, one of ordinary skill in the art will realize that the technical solutions of the present application can be practiced without one or more of the specific details, or other methods, components, devices, steps, etc. can be used. In other cases, well-known methods, devices, implementations or operations are not shown or described in detail to avoid obscuring the aspects of the present application.

[0058] Referring to Figures 1-3 The present embodiment provides an underground space intelligent layout method, comprising the following steps:

[0059] S1, based on the preset underground space layout knowledge and the user input constraint condition, an initial layout is generated by using a graph theory method;

[0060] S2, using a multi-objective optimization algorithm, the initial layout is optimized by comprehensive evaluation indexes;

[0061] S3, the layout result and the evaluation data are intuitively displayed. In this step, the system provides a variety of visualization functions.

[0062] Through the above series of intelligent steps, the automatic design and optimization of underground space layout are realized, from the generation of initial layout to the execution of multi-objective optimization and the final visualization display. The system provides a high-efficiency and intuitive tool for designers, which can quickly generate and optimize layout schemes in complex underground environments.

[0063] Further, step S1 includes:

[0064] S11, construct a functional relationship graph, according to the functional requirements and spatial relationships input by the user, use an adjacency matrix or a visualization graph tool to establish a connection relationship graph between functional units. This relationship graph reflects the mutual dependency and spatial correlation between various functional units. In this way, the system can clearly define the positional relationship of each functional unit at an early stage, laying a foundation for subsequent layout generation.

[0065] S12, solve the maximum plane subgraph, use graph theory algorithm to convert the functional relationship graph into a plane graph for subsequent processing. This conversion process involves simplifying and optimizing the functional relationship graph so that it can represent the connection relationship between functional units without intersection on a two-dimensional plane. This step ensures the rationality of the layout design in two-dimensional space and lays the foundation for subsequent rectangular layout design. In this process, Kuratowski's theorem can be applied to detect and identify K5 or K 3,3 subgraphs in the functional relationship graph, i.e., complete five-node graphs or complete three-node graphs of bipartite graphs. These subgraphs are the main causes of the non-planar graph, and by deleting or restructuring these subgraphs, the functional relationship graph can be effectively simplified to retain the maximum plane subgraph.

[0066] S13, rectangular layout design, convert the plane graph into a rectangular layout and use heuristic algorithms to optimize the rectangular arrangement to maximize space utilization. In this stage, the system converts the previously generated plane graph into a rectangular layout. In order to maximize space utilization, the system introduces heuristic algorithms to optimize the arrangement of rectangles. This optimization process aims to ensure that each functional unit occupies the best position in the layout while minimizing space waste, making the entire layout more compact and efficient.

[0067] Specifically, the following heuristic algorithms can be used to optimize the arrangement of rectangles:

[0068] Simulated Annealing Algorithm: The system first generates an initial arrangement of rectangular layouts. In each iteration, it generates a new layout by randomly perturbing the current layout. By calculating the space utilization of the new layout, if the utilization is higher, the system accepts the new layout; if the utilization is lower, the system accepts the new layout with a certain probability to avoid getting stuck in a local optimal solution. As the iterations proceed, the system gradually reduces the magnitude of perturbation and eventually converges to a globally optimal or near-optimal rectangular arrangement that maximizes space utilization.

[0069] Genetic Algorithm: In the genetic algorithm, the system first generates multiple initial rectangular layouts (i.e., "individuals"). Then, it generates new layouts through crossover and mutation operations. The fitness (i.e., space utilization) of each generation of layouts is calculated and evaluated. The system selects the layouts with the highest fitness as the "parents" for the next generation, and through repeated genetic operations, it gradually optimizes the arrangement of rectangular layouts to ultimately obtain a layout scheme with the highest space utilization.

[0070] S14, Non-Rectangular Layout Adaptation, adjusts the rectangular layout to adapt to the actual underground space shape. This adjustment process involves fine-tuning the edges and internal structure of the rectangular layout to ensure that the final layout not only meets the actual space conditions but also maintains the high space utilization achieved in the previous optimization process. Through the above steps, the system ultimately generates a reasonable and applicable underground space layout scheme, providing a solid foundation for subsequent optimization and visualization.

[0071] Specifically, the following methods and algorithms can be used for adjustment:

[0072] Fractal Geometry Algorithm: By analyzing the complex geometric shapes of underground spaces, the fractal geometry algorithm can gradually approach the boundaries of non-rectangular areas layer by layer. This algorithm uses a recursive method to gradually adjust the edges of the layout, enabling the rectangular layout to better adapt to irregular underground space shapes while maximizing space utilization.

[0073] Affine Transformation Model: Through the affine transformation model, the system can perform linear transformations on the boundaries of the rectangular layout, including scaling, rotation, translation, and other operations, to make the rectangular layout highly compatible with the non-rectangular space shape. In this process, the system dynamically adjusts the geometric parameters of the layout to achieve optimal space adaptability.

[0074] Perspective Transformation Model: In some more complex underground spaces, perspective transformation can be used to make non-linear adjustments to the rectangular layout. By adjusting the perspective parameters of the layout, the system can better simulate the actual shape of the underground space in three-dimensional space and perform corresponding distortion and stretching on the rectangular layout to adapt to the non-rectangular space requirements.

[0075] Further, step S2 includes:

[0076] S21, parameter initialization. In this step, the system first performs parameter initialization, setting key parameters required in the design process, such as space unit functions, expected traffic volume, and space utilization, etc. By reasonably setting these parameters, the system can accurately reflect the design goals and provide effective basic data for subsequent layout generation and optimization. This step ensures that the system can fully consider actual needs and design constraints in the subsequent optimization process.

[0077] S22, initial scheme generation, generates an initial scheme based on the output of the layout module. This preliminary generated scheme has considered the basic functional distribution and space utilization, although it is still in the initial version, but it provides a good starting point for the subsequent optimization process. The generation of the initial scheme is based on the parameters set in advance and the layout knowledge base, and will serve as the basis for subsequent optimization.

[0078] S23, score calculation, scores each layout scheme using comprehensive evaluation indicators. In this step, the system uses comprehensive evaluation indicators to score each generated layout scheme. These comprehensive evaluation indicators cover multiple factors, including functional compatibility, traffic organization efficiency, average accessibility, and space utilization, etc. These scores provide a quantitative evaluation standard for each scheme, allowing the system to objectively compare the pros and cons of different layout schemes, providing a reliable basis for subsequent optimization.

[0079] S24, scheme iteration and optimization, uses genetic algorithm or particle swarm optimization algorithm for iterative optimization. Then, the system enters the iteration and optimization stage, and iteratively optimizes the layout scheme through genetic algorithm or particle swarm optimization algorithm. In each iteration, the system gradually adjusts the parameters in the layout based on the results of score calculation, to continuously approach the optimal solution. This process allows the system to repeatedly optimize the layout scheme, solve complex design requirements, and find the best balance among multiple objectives.

[0080] S25, optimal scheme selection, selects the scheme with the highest score as the final optimization result. After multiple rounds of iteration and optimization, the system finally selects the layout scheme with the highest score as the final optimization result. This scheme has been repeatedly adjusted and evaluated, not only achieving the expected design goals, but also achieving the best configuration in terms of functionality, efficiency, and space utilization, ensuring the feasibility and practicality of the scheme in actual application.

[0081] In this embodiment, the comprehensive evaluation index CEI in step S23 is obtained by weighted combination of multiple indexes, including a functional compatibility index (FCI), a people flow organization efficiency index (FOEI), an average accessibility index (AAI), and a space utilization rate (SUR). Each index has a corresponding weight coefficient w1, w2, w3, and w4, and the influence of different indexes on the overall score is adjusted through these weight coefficients. The calculation formula of the comprehensive evaluation index is as follows:

[0082]

[0083] In the above formula: w1, w2, w3, w4: weight coefficients of each index;

[0084] FCI: functional compatibility index, ;

[0085] FOEI: people flow organization efficiency index, ;

[0086] AAI: average accessibility index, ;

[0087] SUR: space utilization rate, ;

[0088] N: total number of functional units;

[0089] M: total number of main people flow paths;

[0090] : relationship strength of functional units i and j;

[0091] : spatial distance between functional units i and j;

[0092] : flow of the kth main people flow path;

[0093] : length of the kth main people flow path;

[0094] : shortest path time from functional unit i to j;

[0095] : area of functional unit i;

[0096] A_total: total available area.

[0097] In the embodiment of the present application, step S3 further comprises:

[0098] S31, hierarchical display, displaying the layout of each functional area in a two-dimensional plan view. In this step, the system displays the layout results in a two-dimensional plan view through the hierarchical display function. In this way, users can clearly view the distribution and mutual relationship of different functional areas, which helps to preliminarily understand the overall structure of the layout scheme. The two-dimensional plan view is simple and intuitive, which can help users quickly grasp the layout of each functional area, providing a basis for subsequent evaluation and adjustment.

[0099] S32, three-dimensional display, providing a three-dimensional view of the underground space layout, supporting rotation, scaling and other interactive operations. The system then generates a three-dimensional display to present a three-dimensional view of the underground space layout. Users can view the spatial relationship and specific details of the layout through rotation, scaling and other interactive operations. The three-dimensional view provides a comprehensive perspective, allowing users to understand the three-dimensional structure of the layout from multiple angles, which helps to more accurately evaluate and adjust the layout scheme.

[0100] S33, real-time data visualization chart, dynamically displaying the changes of evaluation indicators in the optimization process, including trend charts of comprehensive evaluation indicators and their constituent indicators. In this step, the system dynamically displays the changes of evaluation indicators in the optimization process through real-time data visualization charts. Users can view the trend charts of comprehensive evaluation indicators and their constituent indicators to understand the impact of each adjustment in the optimization process on the layout scheme. This dynamic display method allows users to track the optimization progress in real time and make more informed design decisions.

[0101] In addition, step S34 is also included, which allows users to adjust the generated layout scheme according to actual needs through interactive adjustment functions and view the impact of adjustments on the layout scheme in real time. The system also provides interactive adjustment functions, allowing users to adjust the generated layout scheme according to actual needs and immediately view the specific impact of these adjustments on the layout scheme. This function makes the design process more flexible, allowing users to actively optimize the layout scheme during the design process to ensure that the final layout better meets actual needs and application scenarios.

[0102] Please refer to Figure 4Another embodiment of the present application describes an underground space intelligent layout system, including a layout module, an optimization module, and a visualization module. The layout module generates an initial layout based on preset underground space layout knowledge and user-input constraints using graph theory methods. The optimization module uses multi-objective optimization algorithms to optimize the generated initial layout through comprehensive evaluation indicators. The optimization module includes a multi-objective evaluation module and an optimization algorithm module. In operation, the multi-objective evaluation module first performs multi-objective evaluation, calculating the functional compatibility index, the human flow organization efficiency index, the average accessibility index, and the space utilization rate, and conducting overall evaluation through comprehensive evaluation indicators. The comprehensive evaluation indicators evaluate the initial layout as a whole by weighting these indicators, thereby identifying the strengths and weaknesses of the layout. Subsequently, the optimization algorithm module customizes the design for underground space characteristics through genetic algorithms or particle swarm optimization methods, i.e., iteratively adjusting the layout scheme to meet the special needs of underground space. Through these modules, the system can continuously optimize the layout to ensure that the design scheme achieves the best balance among multiple objectives.

[0103] The visualization module is used to visually display the layout results and evaluation data. The visualization module includes an interactive optimization module and a result output module. The interactive optimization module allows designers to manually adjust the layout while viewing it and instantly view the impact of these adjustments on the layout scheme. This interactive operation makes the design process more flexible, allowing users to make fine adjustments during the design process. The result output module generates standardized outputs, including floor plans, 3D models, and evaluation reports, and can provide data interfaces with mainstream CAD software to ensure the operability and portability of the design scheme. In this way, the system not only realizes intelligent design of the layout, but also provides comprehensive tool support for designers to ensure that the final scheme meets actual needs and is efficiently implemented.

[0104] Please refer to Figures 5-6 , the input data is passed to the layout module, which generates an initial layout based on preset underground space layout knowledge and user-input constraints. After generating the initial layout, the system passes the layout results to the optimization module. The optimization module uses multi-objective optimization algorithms to optimize the initial layout through comprehensive evaluation indicators, further refining the layout scheme. After optimization, the layout results enter the visualization module, through which the system visually displays the layout results and evaluation data. The results generated by the visualization module are presented to the user through user interaction, and the user can view the two-dimensional floor plan, three-dimensional perspective view, and real-time data visualization charts of the layout scheme through the interactive interface.

[0105] In the embodiment of the present application, in the specific implementation process of the underground space intelligent layout system, the system is developed based on the.Net platform using C# language, and the UI interface uses the WPF framework. The system architecture follows the MVVM (Model-View-ViewModel) mode, which effectively separates the user interaction part from the simulation model part, ensuring the scalability of the system and the low coupling between modules. This architecture design enables the system to maintain high efficiency while facilitating the expansion and maintenance of subsequent functions. The system also has powerful data processing capabilities, capable of handling large amounts of spatial information and user demand data. Through intelligent algorithms, the system can quickly generate multiple alternative solutions, helping designers find the best solution in a short time.

[0106] Taking a subway station as an example, as a complex public building, the subway station contains multiple functional areas such as station hall, platform, commercial area, equipment room and evacuation passage, which need to be efficiently laid out in limited underground space. First, the system generates an initial layout by inputting the functional requirements and design constraints of the subway station, constructs a functional relationship graph, and applies the Kuratowski theorem to simplify and optimize the functional relationship graph, generating a reasonable planar layout. Then, the system converts the planar graph to a rectangular layout, optimizes the arrangement of rectangular regions using simulated annealing algorithm and genetic algorithm, ensures that each functional unit occupies the best position, and maximizes space utilization. At the same time, the system adjusts the rectangular layout to adapt to the non-rectangular space requirements using fractal geometry algorithm and affine transformation model, and ensures the reasonable layout of each functional unit in three-dimensional space through perspective transformation model. The system evaluates and optimizes the layout scheme through multi-objective optimization algorithm, and finally generates an optimal layout scheme that meets the actual requirements of the subway station. Through the display of two-dimensional planar graph, three-dimensional solid view and real-time data visualization chart, designers can view the layout in detail and make adjustments as needed to ensure that the final scheme is optimal in functionality, safety and economy.

[0107] In summary, the present application proposes an underground space intelligent layout method and system, aiming to solve the complexity and diversity problems in underground space design. By using advanced multi-objective optimization algorithm, the present application can find the best balance between multiple design objectives, ensuring that the layout scheme is optimal in terms of functionality, people flow line, safety standards, etc. Not only can it effectively integrate multi-dimensional data in underground space design, but also provide designers with a scientific and efficient decision support tool, significantly improving design efficiency and scheme quality. This method and system are particularly suitable for the design process of complex underground space, especially in the context of accelerating urbanization, the development and utilization of underground space is becoming increasingly important, and the demand for such efficient design tools is also increasing. The present application has broad market application prospects in the field of underground space design, and provides strong support for future underground space development and utilization.

[0108] The above examples are only used to illustrate the technical solutions of the present application, and are not limited thereto; under the idea of the present application, the technical features in the above examples or different examples can also be combined, the steps can be implemented in any order, and there are many other changes of different aspects of the present application as described above, which are not provided in details for simplicity; although the present application has been described in detail with reference to the foregoing examples, those skilled in the art should understand that the technical solutions recorded in the foregoing examples can still be modified, or some technical features can be replaced by equivalents; and these modifications or replacements do not make the essence of the corresponding technical solutions deviate from the scope of the technical solutions of the embodiments of the present application.

Claims

1. A method for intelligent layout of underground space, characterized in that, Includes the following steps: S1, based on the preset knowledge of underground space layout and the constraints input by the user, uses graph theory to generate the initial layout; S2, using a multi-objective optimization algorithm, the initial layout is optimized through comprehensive evaluation indicators; S3 provides an intuitive display of layout results and evaluation data; Step S1 includes: S11, Construct a functional relationship diagram. Based on the user's input functional requirements and spatial relationships, use adjacency matrix or visualization tools to establish a connection relationship diagram between functional units. S12, Solve for the largest planar subgraph, and use graph theory algorithms to transform the functional relationship graph into a planar graph for subsequent processing; S13, Rectangular Layout Design: Convert the floor plan into a rectangular layout and use a heuristic algorithm to optimize the arrangement of rectangles to maximize space utilization; S14, Non-rectangular layout adaptation: Adjust the rectangular layout according to the actual shape of the underground space to adapt to the needs of non-rectangular space. Step S2 includes: S21, parameter initialization; S22, Initial scheme generation: An initial scheme is generated based on the output of the layout module; S23, Scoring calculation: Each layout scheme is scored using comprehensive evaluation indicators; S24, Scheme iteration and optimization, using genetic algorithm or particle swarm optimization algorithm for iterative optimization; S25, Optimal solution selection: Select the solution with the highest score as the final optimization result; The formula for calculating the comprehensive evaluation index CEI in step S23 is as follows: ； In the above formula: w1, w2, w3, w4: weight coefficients of each indicator; FCI: Functional Compatibility Index ; FOEI: Crowd Flow Efficiency Index ; AAI: Average Accessibility Index ; SUR: Space Utilization Rate ; N: Total number of functional units; M: Total number of main pedestrian routes; R ij The strength of the relationship between functional units i and j; D ij Spatial distance between functional units i and j; F k Traffic flow along the kth main pedestrian path; L k : The length of the kth main pedestrian path; T ij : The shortest path time from functional unit i to j; Aᵢ: Area of ​​functional unit i; A_total: Total available area.

2. The method for intelligent layout of underground space according to claim 1, characterized in that, The parameters in step S21 include spatial unit function, expected pedestrian flow, and space utilization rate.

3. The method for intelligent layout of underground space according to claim 1, characterized in that, Step S3 further includes: S31, layered display, showing the layout of each functional area in the form of a two-dimensional plan view; S32, a 3D display, provides a 3D stereoscopic view of the underground space layout and supports interactive operations such as rotation and zoom. S33 provides real-time data visualization charts that dynamically display changes in evaluation metrics during the optimization process, including trend charts of comprehensive evaluation metrics and their component metrics.

4. The method for intelligent layout of underground space according to claim 3, characterized in that, It also includes step S34, which allows users to adjust the generated layout scheme according to actual needs through an interactive adjustment function, and view the impact of the adjustment on the layout scheme in real time.

5. An intelligent layout system for underground space, characterized in that, include: The layout module generates an initial layout using graph theory methods, based on pre-defined knowledge of underground space layout and user-input constraints. The optimization module uses a multi-objective optimization algorithm to optimize the initial layout through comprehensive evaluation indicators; The visualization module provides an intuitive display of the layout results and evaluation data. The optimization module includes a multi-objective evaluation module and an optimization algorithm module. The multi-objective evaluation module calculates the functional compatibility index, the pedestrian flow organization efficiency index, the average accessibility index, and the space utilization rate, and performs an overall evaluation through comprehensive evaluation indicators. The optimization algorithm module uses a genetic algorithm or particle swarm optimization method to perform customized design for the characteristics of underground space. The layout module can be used to perform the following steps: S11, Construct a functional relationship diagram. Based on the user's input functional requirements and spatial relationships, use adjacency matrix or visualization tools to establish a connection relationship diagram between functional units. S12, Solve for the largest planar subgraph, and use graph theory algorithms to transform the functional relationship graph into a planar graph for subsequent processing; S13, Rectangular Layout Design: Convert the floor plan into a rectangular layout and use a heuristic algorithm to optimize the arrangement of rectangles to maximize space utilization; S14, Non-rectangular layout adaptation: Adjust the rectangular layout according to the actual shape of the underground space to adapt to the needs of non-rectangular space. The optimization module can be used to perform the following steps: S21, parameter initialization; S22, Initial scheme generation: An initial scheme is generated based on the output of the layout module; S23, Scoring calculation: Each layout scheme is scored using comprehensive evaluation indicators; S24, Scheme iteration and optimization, using genetic algorithm or particle swarm optimization algorithm for iterative optimization; S25, Optimal solution selection: Select the solution with the highest score as the final optimization result; The formula for calculating the comprehensive evaluation index CEI in step S23 is as follows: ; In the above formula: w1, w2, w3, w4: weight coefficients of each indicator; FCI: Functional Compatibility Index ; FOEI: Crowd Flow Efficiency Index ; AAI: Average Accessibility Index ; SUR: Space Utilization Rate ; N: Total number of functional units; M: Total number of main pedestrian routes; R ij The strength of the relationship between functional units i and j; D ij Spatial distance between functional units i and j; F k Traffic flow along the kth main pedestrian path; L k : The length of the kth main pedestrian path; T ij : The shortest path time from functional unit i to j; Aᵢ: Area of ​​functional unit i; A_total: Total available area.

6. The intelligent layout system for underground space according to claim 5, characterized in that, The visualization module includes an interaction optimization module and a result output module. The interaction optimization module allows designers to manually adjust the layout and view the impact in real time. The result output module generates standardized outputs, including floor plans, 3D models, and evaluation reports, and provides data interfaces with mainstream CAD software.

Images