1626 results about "Subway station" patented technology

The invention provides a public transportation network toughness evaluation method considering subway passenger evacuation and station failure propagation, and the evaluation method is used for an urban public transportation composite network, and comprises the steps: firstly obtaining urban public transportation network station map data, passenger flow OD data and vehicle operation related information; then, an urban bus composite network considering the one-to-many coupling relation between subway stations and conventional bus stations is constructed through a Space L method, and meanwhile, composite network performance indexes considering the structure and operation performance are defined in the propagation process of station cascade failure by considering the re-decision of the travel mode of blocked passengers in the urban bus composite network under sudden interruption; based on the network performance curve, the urban bus composite network toughness evaluation model is constructed to measure the toughness level of the urban bus composite network under sudden interruption; according to the method, the toughness of the urban bus composite network can be accurately evaluated, and the operation stability and safety of a bus system are improved.

The invention discloses a subway ventilation demand dynamic decision-making method and system fused with people flow prediction, and belongs to the technical field of intelligent traffic and environment control, and the method comprises the steps: collecting real-time people flow data, historical passenger flow records, station layout information and external environment parameters of each region in a subway station; constructing a deep learning prediction model through multi-source data fusion, and generating short-term and medium-term people flow distribution prediction results; based on the prediction result, combining the ventilation equipment operation parameters, the air quality index and the energy consumption cost to construct a multi-objective optimization model; dynamic decision making is carried out on a ventilation system by utilizing the model, and an optimal ventilation strategy in different regions and different time periods is output; through a real-time feedback mechanism, prediction and control parameters are continuously corrected according to actual people flow changes, closed-loop regulation and control are formed, the response precision and the energy efficiency level of a subway ventilation system can be remarkably improved, and passenger comfort and environment safety are guaranteed.

The invention relates to the technical field of data processing, and discloses a soil pressure analysis method and system for a subway double-side extension foundation pit enclosure structure, and the method comprises the steps: carrying out the multi-point soil pressure monitoring of the periphery of extension deep foundation pits at two sides of a subway station, and obtaining the original soil stress data; performing process defect influence elimination and geological condition correction on the original soil stress data to obtain corrected soil pressure distribution data, and performing space-time coupling analysis to obtain soil pressure evolution characteristics; performing characteristic analysis and support parameter optimization on the soil pressure evolution characteristics to obtain a soil pressure prediction result in the dynamic construction process; performing normal use and limit working condition simulation on the soil pressure prediction result to obtain a soil pressure change rule under different excavation conditions; and carrying out retaining structure stress analysis and settlement influence evaluation on the soil pressure change rule to obtain safety evaluation data of the retaining structure. According to the method, the efficiency and accuracy of analyzing the soil pressure of the subway double-side extension foundation pit support structure are improved.

The invention provides a switching station control method and system of a subway station. The system comprises a subsystem control unit, a main control unit, a communication module and a data caching module, the subsystem control unit transmits an equipment on-off state, a fault signal and an environment parameter to the main control unit in a hybrid networking mode, and a first cooperative control instruction set is generated in combination with a linkage rule base; a target priority is distributed for the operation instruction to obtain a second cooperative control instruction set, and the communication module adopts a multi-channel parallel distribution mechanism for pushing; in the process of executing the switching station operation, the data caching module stores running state data, identifies a time sequence mode by using a machine learning model, pre-judges a switching station linkage scene and loads a control strategy; and the main control unit detects the response delay of the subsystem control unit and generates a third cooperative control instruction set according to the control strategy so as to optimize the switching station control time sequence. According to the invention, intelligent cooperative control of multiple electromechanical devices can be realized.

The invention discloses a metro station non-commuting passenger proportion calculation method based on a random forest model, and the method specifically comprises the steps: selecting a research region, and collecting metro-related built environment data and transportation data; important built-up environment variables are determined through preliminary analysis, and variables influencing non-commuter are added; establishing a prediction model by adopting a random forest algorithm, and dividing a training set and a test set; analyzing the output of the random forest model by applying an SHAP technology, and determining the importance sequence of the influence of each built-up environment factor on the proportion of non-commuting passengers and the action mechanism of the influence of each built-up environment factor; according to the size of the SHAP value and in combination with an actual scene, a numerical matrix of all built-up environment factors around the subway station in the scene is determined; and substituting a model coefficient result into the established environment factor matrix, and calculating the subway station non-commuting travel proportion. According to the method, the prediction precision of the non-commuting passenger quantity of the subway station is remarkably improved, the understanding of non-commuting travel behaviors is deepened, and powerful support is provided for urban traffic management and planning.

The invention discloses a large-section long-footage mechanical blasting mixed excavation method suitable for a subway station, and relates to the technical field of underground rail transit engineering, and the method comprises the following steps: obtaining a tunnel section contour, a geologic structure and blasting parameters, building a three-dimensional blasting wave propagation inversion model, and combining geology and material heterogeneity to obtain a three-dimensional blasting wave propagation inversion model; and identifying a closed space region forming reflection interference, and predicting a space point location where blasting wave energy is abnormally accumulated. Based on the three-dimensional blasting wave propagation inversion model, the abnormal wave energy accumulation area is predicted in combination with geological heterogeneity, the high-risk blasting section is recognized, parameters are reconstructed, vibration real-time monitoring and model feedback correction are assisted, a closed-loop control system is constructed, local wave crest abnormity is effectively restrained, and the safety and controllability of large-section tunnel blasting construction are improved.

The invention discloses a subway station ventilation alarm method and system, and relates to the technical field of subway station ventilation equipment intelligent monitoring and alarm devices, and the method comprises the steps: monitoring equipment state data in real time, constructing a dependency relationship between different ventilation equipment in a subway station by using a Petri network model based on FMECA analysis, and dynamically updating a fault propagation path; dynamically evaluating the priority of the fault according to the position, the influence range and the propagation speed of the equipment fault in combination with the importance and the working state of the equipment; and according to the evaluated priority, automatically triggering a fault alarm through an alarm device, and sending a repair instruction to a maintainer through an instruction sending device. According to the method, the intelligent level of the system is improved through the design of the alarm device combining dynamic evaluation and priority driving, the processing time of high-priority faults is shortened through the design of a multi-factor comprehensive evaluation method and a linkage repair instruction, and the safety and the operation efficiency of the subway ventilation system are effectively improved.

The invention relates to the technical field of civil engineering, and discloses a metro room position design method and system based on a mechanical simulation system, and the method comprises the steps: obtaining the connection relation between metro station rooms, and determining the topological relation between the metro station rooms according to the connection relation; determining an agent point of each subway station room, setting a constraint condition of each agent point according to the topological relation, and constructing a mechanical simulation system; wherein the room agent point is a central point of each subway station room; and operating the mechanical simulation system to obtain the final position coordinates of each agent point. According to the method, a plurality of layout schemes can be automatically and quickly generated, so that the optimal solution is quickly found, and the design period is greatly shortened.

The invention relates to a subway station large passenger flow emergency command linkage method and device and a storage medium. The method comprises the steps that station passenger flow information is received in real time; the station passenger flow information is preprocessed and analyzed, and real-time passenger flow data are extracted; the historical passenger flow data and the real-time passenger flow data are utilized, the future passenger flow condition and the number of passengers getting off a train about to arrive are predicted through a machine learning algorithm, if it is predicted that the future passenger flow exceeds a station bearing capacity threshold value, the abnormal passenger flow condition is judged, and if it is judged that the abnormal passenger flow is generated, a large passenger flow alarm is generated; alarm information is automatically generated according to large passenger flow alarm, and is pushed to an operation control center for confirmation; and after the alarm information is confirmed, an emergency plan is started for station management and control. Compared with the prior art, real-time monitoring, early warning, evaluation and emergency command of the large passenger flow of the subway station are realized, and the emergency response speed and the disposal efficiency are improved.

The invention discloses a subway service robot real-time path planning method based on a graph neural network, and the method comprises the following steps: scanning the environment in a subway station, completing the map construction, and obtaining basic environment data; performing target detection and personnel statistics to form an environment and passenger flow fusion map; taking the fused map as input, setting a starting point and a target position, and outputting a global path search initial state; calling an improved A * algorithm to carry out node expansion, calculating a cost estimation function, and generating candidate paths; performing redundant node deletion and arc smoothing processing on the candidate path, performing step length dynamic adjustment, and outputting an optimized global path; performing local path planning by adopting an improved dynamic window method, and outputting an update path in real time; a passenger evacuation scheme is generated and is output through a display screen and voice broadcast, evacuation is guided, and passing is guaranteed. According to the invention, real-time path planning of the subway service robot is realized.

The invention relates to the technical field of real-time early warning of risks in the construction process of a subway station, and particularly discloses a real-time visual early warning method for the risks in the construction process of the subway station. The hydrological monitoring data is transmitted to a ground control center through a wireless communication network; processing the hydrological monitoring data of the current subway tunnel construction stage, comprehensively analyzing a possible coefficient of occurrence of a water burst event of the current subway tunnel construction stage, and sending a water burst analysis early warning signal; after the water gushing analysis early warning signal is received, the water gushing early warning risk level of the current subway tunnel construction stage is evaluated, and corresponding processing is carried out; the predicted tunnel water inflow of the subway tunnel in the future period is synchronously predicted, and timely early warning processing operation is carried out; the risk control in the construction process is ensured to be within an acceptable range, and scientific risk assessment and prevention measures are provided for tunnel construction.

The invention discloses an assembly type subway station main body structure construction method based on a cover-excavation top-down construction method. Comprising the steps of underground diaphragm wall construction, upper covering soil excavation and pile position drilling, prefabricated pile construction, prefabricated top beam lifting and placing, prefabricated top plate lifting and placing, top beam plate-column joint post-pouring, top plate-side wall joint post-pouring, upper covering soil backfilling, negative first layer earthwork excavation, prefabricated middle beam lifting and placing, prefabricated middle plate lifting and placing, middle beam plate-column joint post-pouring and middle plate-side wall joint post-pouring. Excavating a negative second layer earthwork, pouring a bottom plate cushion layer, prefabricating a bottom beam in place and suspending, binding bottom plate steel bars, post-pouring a bottom plate, and post-pouring a bottom beam column node. A bottom plate is cast in place, a top beam, a top plate, a longitudinal beam and a floor slab are fully prefabricated, and an underground continuous wall and a prefabricated pile serve as temporary enclosure components and also serve as permanent vertical supporting components; and only a simple template needs to be erected, and after the top plate is mounted, the covering soil is backfilled to restore the road surface, so that the construction period is greatly shortened, and the influence of construction on urban traffic and environment is reduced to the minimum.

The invention relates to a subway station pedestrian emergency evacuation system and method based on identification guidance, in particular to a dynamic identification guidance system optimized in combination with Legon simulation software. According to the system, a dynamic identification device is deployed in a subway station, Legon simulation software is combined to simulate and analyze people flow in the station in real time, and an optimal evacuation path is provided. In an emergency, the system dynamically adjusts the guiding direction of the evacuation identification by using simulation data and environment monitoring information. Legion simulation software can accurately simulate driving behaviors of passengers in different environments and under different congestion conditions, so that the accuracy of an evacuation scheme is improved. Through a simulation test, the system can significantly reduce the evacuation time, improve the evacuation speed, optimize the distribution of personnel in the station, reduce the residence time in a high-density area, and ensure the safe evacuation of passengers in an emergency.

The invention relates to the technical field of subway station safety management and disaster emergency, and provides a subway station flood life-saving facility arrangement optimization method and device and electronic equipment, and the subway station flood life-saving facility arrangement optimization method comprises the steps: obtaining passenger position distribution data of a target subway station and disaster data during flood; modeling the passenger density information by using a density-based noise application space clustering algorithm, and identifying a passenger high-density area; according to the passenger position distribution data and the disaster data, dividing the area in the subway station into different danger levels by using a Bayesian network; constructing a robustness optimization problem based on the passenger high-density area and the danger level; and solving a robustness optimization problem, and determining the setting position and number of the lifesaving equipment. According to the method, the arrangement position and the number of the optimized lifesaving equipment are determined by constructing and solving the robustness optimization problem, and the rescue capacity of the subway station on passengers under the flood condition can be improved by arranging the lifesaving equipment based on the arrangement position and the number of the optimized lifesaving equipment.

The invention provides a passenger flow regulation and control method based on simulation prediction and a feedback closed loop, and the method comprises the steps: obtaining monitored real-time monitoring data through a camera, and fusing the real-time monitoring data with historical passenger flow data on an edge computing device; constructing a simulation environment according to the fused data, and performing simulation prediction on passenger flow distribution of the subway station in a future time period; inputting the simulation prediction result into a strategy generation module to generate a passenger flow control strategy; executing a passenger flow control strategy, and controlling the passenger flow by adjusting hardware facilities of the station; in the passenger flow control strategy execution process, feedback data are collected in real time through a camera, the control strategy is adjusted according to the feedback data, and closed-loop regulation and control are achieved. According to the method, the passenger flow distribution of the station in the future time period is simulated and predicted, the possible congestion trend can be predicted before the actual passenger flow growth arrives, and a strategy suitable for the actual conditions of different stations is finally made through continuous verification and adjustment, so that the station operation safety and the passenger passing efficiency are improved.

The invention discloses a design and construction scheme optimization method and system for subway double-side extension heaving and sinking control, and the method comprises the steps: collecting design parameters, monitoring data and construction management data in the extension construction process of a subway station, and forming a standardized data set; and performing multi-dimensional fusion analysis on the standardized data set, evaluating the effects of earth excavation, a supporting system and deformation control, and generating target evaluation data. And based on the evaluation results, optimizing the subway double-side extension construction scheme by using an optimization algorithm to generate an optimized sub-scheme. The system analyzes the construction progress through a critical path algorithm, forms an adjustable progress plan, monitors the construction state in real time, dynamically updates the progress plan and control measures, and ensures the safety and high efficiency of construction. The system can effectively control the deformation problem in the construction process, the construction precision and the management level are improved, and the system is suitable for improving the quality and safety of subway double-side extension construction.

The invention relates to an underground engineering construction design technology, discloses a method for analyzing the influence of underground excavation under-crossing on an existing subway station, and improves the efficiency and precision of analyzing the influence of underground excavation under-crossing construction on the existing subway station. The method comprises the steps that by defining a structure and geometrical shapes and material attributes of a stratum, boundary conditions and external loads are set, grid division is carried out, and a finite element three-dimensional basic calculation model is constructed; according to theories of porous media and the like, a multi-physical field coupling model of a seepage-deformation-temperature full coupling effect is constructed; the rigidity of the underground excavation vertical pile foundation is calculated, and the rigidity of the underground excavation vertical pile foundation is corrected based on the influence factors of the soil squeezing effect and the negative friction resistance; subsurface excavation construction is subdivided into a plurality of stages, structural stress, deformation and stratum displacement are calculated through an incremental method, and the timeliness of a supporting structure and the influence of different excavation modes on stratum disturbance are analyzed; and obtaining a structural response through finite element iteration solution, and judging the influence of underground excavation under-crossing on the existing subway station.

The invention relates to the technical field of subway passenger flow prediction, and discloses a space-time perception subway passenger flow prediction method based on large model and multi-source information fusion, which comprises the following steps: constructing a data agent based on a large language model and a model context protocol; generating text description of each subway station and a corresponding spatial context embedding vector based on the peripheral interest point data of each subway station by utilizing a data agent; constructing an enhanced graph neural network according to the spatial context embedded vector, and performing spatio-temporal joint prediction based on the historical passenger flow data and the spatial context embedded vector by using the enhanced graph neural network to obtain a preliminary passenger flow prediction result; and constructing a cue word template, and performing domain knowledge calibration based on the cue word template by using the pre-trained large language model to obtain a final passenger flow prediction result. According to the method, external multi-source information is deeply fused, so that the urban rail transit passenger flow prediction task performance, robustness and interpretability are remarkably improved.

The invention provides a dynamic planning method for a fire evacuation path of a deep subway station based on a cellular automaton, and the method comprises the steps: building a subway space topology through employing the cellular automaton, simulating a fire environment through employing an FDS tool, and obtaining environment data; constructing a multi-field model based on subway space topology and environment data; based on the multi-field model, the pedestrian transition probability is calculated, then the pedestrian transition probability is corrected in combination with the deep subway facility characteristics and the pedestrian consensus behaviors, and finally the corrected pedestrian transition probability is output; and optimizing a cost function of an A star algorithm based on the corrected pedestrian transition probability to obtain a dynamic cost function, further obtaining an improved A star algorithm, planning an initial path based on the improved A star algorithm, formulating a path updating rule, and implementing a smooth transition strategy to realize dynamic path planning. According to the invention, the evacuation safety and the scheduling efficiency under the fire situation can be improved.

The invention provides a metro platform screen door safety monitoring method and monitoring system based on multi-source data analysis, and the method comprises the steps: obtaining a multi-source data set of a target metro platform, carrying out the time-space alignment processing of the multi-source data set, generating a multi-modal monitoring data set fusing the time-space characteristics, and carrying out the monitoring of the metro platform screen door safety. And performing foreign matter identification processing based on the multi-modal monitoring data set, generating a foreign matter monitoring result and foreign matter position distribution information of the shielding door area, performing density prediction processing according to the foreign matter monitoring result and a passenger flow data sequence in the multi-source data set, generating a passenger linear density prediction result and density change trend information, and performing density prediction processing according to the passenger linear density prediction result and the density change trend information. And generating a safety early warning strategy based on the foreign matter position distribution information and the density change trend information, and transmitting the safety early warning strategy to a subway platform control system to trigger emergency response operation. According to the invention, the emergency processing efficiency and passenger guidance accuracy of the subway platform in a sudden foreign matter blocking scene are effectively improved.

The invention provides a subway station room layout drawing wall line extraction method based on an improved Canny algorithm and Hough transform. According to the method, through image multi-channel CLAHE processing enhancement and Laplacian sharpening, an improved Canny edge detection algorithm and Hough transform are applied to detect wall lines, then wall line merging is carried out, wall line geometric data of a standardized subway station room layout drawing are extracted, an output file can be directly imported into CAD software, good practical engineering application adaptability is achieved, and the method is suitable for popularization and application. The problems that a traditional method is low in efficiency, poor in precision and unstructured in output are solved.

The invention discloses a rail transit engineering simulation practical training system based on virtual reality and artificial intelligence, and relates to the field of rail transit engineering, and the system comprises a virtual reality scene module which constructs a whole-process virtual scene of a subway station from planning to completion; the task simulation module is used for designing a station construction task, and the task simulation module further comprises an operation guidance unit and a tool use training unit; the data acquisition and analysis module is used for acquiring student operation data and analyzing the student operation data to obtain an analysis report; and the feedback and evaluation module is used for providing real-time feedback according to the analysis report and generating an operation progress report.

A subway station environment control wind and water linkage energy-saving optimization control method based on deep learning comprises the steps that the train operation state, the station environment data and the environment control equipment data are preprocessed, and a time sequence data matrix is obtained; and decomposing the time sequence data matrix through non-negative matrix decomposition, extracting disturbance characteristics in the time sequence data matrix, and outputting a blind source separation result matrix. And performing convolution operation on the blind source separation result matrix through a convolutional neural network, extracting a spatial pattern of disturbance characteristics, and generating a spatial feature vector through pooling dimension reduction. And capturing a time change rule of dynamic disturbance through a bidirectional GRU structure in the recurrent neural network, and generating an implicit state sequence. And an attention mechanism is introduced into an output layer of the recurrent neural network, an implicit state when the train enters the station is concerned, and optimized disturbance feature representation is generated through weight weighting. And taking the optimized disturbance characteristic representation as the input of a full connection layer, and generating and outputting a corresponding energy-saving strategy category.

The invention relates to the field of metro platform smoke control, in particular to a metro platform screen door type smoke exhaust system based on a one-way closed smoke exhaust ventilation valve, which realizes communication between a metro platform space and a station tunnel space under a smoke exhaust working condition by arranging the one-way closed smoke exhaust ventilation valve above a platform screen door type top beam. A shielding door system mode is converted into an opening and closing type system mode for smoke exhaust scheme design, arrangement of a rail top air duct on a subway platform is avoided, and arrangement of a subway platform smoke exhaust system is simplified. The one-way closed smoke exhaust ventilation valve can meet the requirement that the train in the upstream section crosses the fire subway platform, smoke backflow is avoided, the control technology of the one-way closed smoke exhaust ventilation valve is simple, and manual or automatic control intervention can be avoided.

The invention relates to the technical field of twin models, in particular to a subway station flood prevention simulation method and system based on a three-dimensional model. According to the method, local important evaluation indexes are obtained through placename approximate analysis and concavity-convexity analysis of structures of point cloud data in a neighborhood space, and structural important evaluation indexes of single point cloud data are determined by combining and analyzing density distribution complexity in the neighborhood space; clustering the point cloud data and dividing the point cloud data into different regions; analyzing depth distribution of all the point cloud data in the regions; combining structural importance evaluation, determining an attention rate of each region, performing differential modeling and semantic processing to obtain a semantic three-dimensional model; and combining a hydrodynamic model to obtain a digital twinborn model. According to the method, differentiated three-dimensional modeling is carried out by evaluating the importance of each point cloud data in subway station flood prevention simulation, and flood prevention analysis is carried out more comprehensively and accurately by combining a digital twin model with a hydrodynamic model, so that the protection capability of subway flood prevention is improved.

The invention discloses an extension method for adding a layer downwards to an existing subway station by using a non-closed bundled pipe curtain. The extension method comprises the following steps: arranging a starting well and a receiving well on two sides of the existing subway station; arranging a non-closed bunching pipe curtain below the existing subway station; pre-supporting reinforcing bodies are constructed in the pipe roofing; a freezing cushion layer is formed by freezing a soil body between the pipe curtain and the bottom of the existing subway station; constructing a water stop reinforcing member on the outer side of the top of the pipe roof; a soil body between the pre-supporting reinforcing body and the bottom of the existing subway station is excavated; the bottom of the existing subway station is poured to form a reverse top beam which is also used as a top pipe roof force transfer bracket; a soil body between the pre-supporting reinforcing body and the bottom of the pipe curtain is excavated, and the pre-supporting reinforcing body is dismantled; and the transfer channel structure is constructed in the construction space. The problems that platform transfer is difficult to achieve or the reinforcement amount is large, the construction disturbance is large and the construction speed is low due to the fact that existing shield method or mining method crossing construction is adopted for downward storey adding extension and transformation of the old station are solved.

The invention provides a subarea illumination control method and system for a subway station, and relates to the technical field of subway illumination, and the method comprises the steps: carrying out the calculation according to three-dimensional building model data, functional area division data and passenger flow data, and obtaining illumination demand data; simulating the original lamp arrangement scheme, the three-dimensional building model data and the illumination demand data to obtain initial illumination intensity distribution data; processing the initial illumination intensity distribution data to obtain an illumination intensity superposition matrix; adjusting according to the optical characteristic data and the passenger flow data to obtain illumination adjustment data of the reflection area; processing according to the illumination adjustment data, the illumination intensity superposition matrix and the illumination demand data to obtain a regional optical interaction matrix; and obtaining a real-time control strategy according to the regional optical interaction matrix. According to the method, the illumination requirements and actual illumination distribution of all the areas are dynamically analyzed, and the problems that due to a complex building structure, light is not uniform, and the local part is too bright or too dark are solved.

The invention discloses a subway peripheral non-commuter destination selection prediction method based on a built environment, and the method specifically comprises the steps: data collection: selecting a research region in a target city, and collecting the related built environment data in a subway station water collection region; feature selection: adding variables influencing non-commuter according to the built environment variables in combination with local special conditions; model construction: adopting a random forest algorithm to establish a prediction model; sHAP analysis: analyzing the output of the random forest model by applying an SHAP technology, and determining the importance sequence and the action mechanism of each built-up environment factor for the destination selection of the non-commuter; and result interpretation and prediction: determining each built environment factor numerical matrix of the new scene, and calculating to obtain a final destination selection result of each non-commuting trip individual in the new scene. The method can accurately understand and predict the destination selection behavior of the non-commuter around the subway station, thereby providing powerful support for urban planning and traffic management.

The utility model relates to a capillary tube energy wall ground source heat pump air-conditioning system for a subway station. A traditional underground station air-conditioning system water chilling unit usually adopts a ground cooling tower to eliminate unit condensation heat, and the problems that the cooling tower is difficult to expropriate land and arrange, influences urban landscapes and the like exist. The system comprises a capillary energy wall close to the soil side and used for eliminating condensation heat, and the capillary energy wall sequentially comprises a structural wall, a capillary mesh buried pipe layer, a heat preservation layer, an aluminum tin film, an air interlayer, an aluminum tin film and a wall separation wall from the soil side to the station side; the capillary mesh buried pipe layer comprises a capillary mesh laid on the inner side of the structural wall. According to the utility model, station waste heat is transferred to surrounding soil through the capillary tube mesh grid laid on the inner surface of the structural wall, underground renewable energy sources are extracted for cooling, and a traditional cooling tower is reduced or replaced. The underground heat exchanger is combined with an underground station supporting structure, cold energy in soil can be extracted, heat can also be extracted, and the occupied space of the underground heat exchanger is effectively reduced.

The invention provides a subway platform edge behavior abnormity real-time identification and early warning method based on deep learning, and relates to the technical field of deep learning, which comprises the steps of obtaining real-time video data, performing pedestrian detection and track extraction, calculating behavior characteristic parameters and a dynamic distance threshold value, performing danger grade division on pedestrians, and performing early warning and early warning. According to the method, time sequence feature extraction is carried out on potential dangerous targets, a behavior abnormity scoring mechanism is established, timely early warning of abnormal behaviors is realized, the accuracy and real-time performance of safety monitoring of the subway platform can be effectively improved, and the occurrence rate of safety accidents can be reduced.