Subway station internal environment partition intelligent control system

Abstract

The utility model belongs to the technical field of rail transit, and particularly relates to an environment zoning intelligent control system in a subway station, which comprises a pedestrian flow data acquisition module, an environment sensing module, terminal equipment, a prediction-control integrated module and an energy supply module, and the energy supply module is electrically connected with the people flow data acquisition module, the environment sensing module, the prediction-control integrated module and the terminal equipment, and is used for supplying power to the whole system. A time sequence prediction unit in the prediction-control integrated module generates an environment prediction value according to detection data of the human traffic data acquisition module and the environment perception module, and a mixed integer nonlinear programming controller in the prediction-control integrated module generates overall parameters of the terminal equipment according to the environment prediction value. And the execution parameters of the terminal equipment in each region are configured according to the actual detection data of the environment sensing module, so that the environment in the subway station is controlled by regions, and the energy-saving effect of the system is greatly improved.

Description

Technical Field

[0001] This utility model belongs to the technical field of rail transit, specifically relating to an intelligent control system for environmental zoning in subway stations. Background Technology

[0002] my country's urban rail transit has developed rapidly, but energy consumption problems are becoming increasingly prominent. Taking Changsha Metro as an example, its six lines have an average daily passenger flow of over 2.5 million. In summer, air conditioning accounts for up to 50% of energy consumption, and ineffective cooling caused by heat exchange inside and outside stations accounts for over 30%, becoming the core pain point of energy waste under the "dual carbon" target.

[0003] Traditional subway station environmental control systems mostly operate in a fixed mode, set by subway staff. This type of system cannot automatically adjust based on temperature differences between the inside and outside of the station, or the temperature requirements of different areas within the station. This design not only wastes energy but also affects passenger comfort. Application CN202411762852.4 discloses a subway station environmental control and temperature control method and system. By introducing a dynamic thermal comfort model, which uses the Relative Thermal Indicator (RWI) as its core and comprehensively considers various influencing factors such as human metabolic rate, ambient temperature, and clothing thermal resistance, it can accurately assess passengers' thermal comfort under different environmental conditions. By monitoring outdoor temperature changes in real time and combining this with passengers' thermal comfort needs during their journey, the system can intelligently adjust the temperature of the station hall and platform to match passengers' physiological and psychological needs. While this solution can automatically adjust the temperature of the station hall and platform to a certain extent, it lacks advance prediction of environmental factors such as oxygen levels in different areas of the station hall and platform, and fails to adjust these factors in specific zones, resulting in a limited energy reduction effect for the subway station environmental control system.

[0004] It is evident that while the existing subway station environmental control system can reduce energy consumption to some extent, it still has shortcomings. Utility Model Content

[0005] This utility model provides an intelligent control system for environmental zoning in subway stations. The intelligent control system for environmental zoning in subway stations includes: a passenger flow data acquisition module, an environmental sensing module, terminal equipment, a prediction-control integrated module, and an energy supply module.

[0006] The passenger flow data collection module includes turnstile counters installed inside subway stations.

[0007] The environmental sensing module includes body temperature detectors, air quality detectors, and temperature sensors installed in various areas of the subway station.

[0008] The predictive-control integrated module includes a time-series prediction unit and a mixed-integer nonlinear programming controller. The time-series prediction unit generates environmental prediction values ​​based on the detection data from the passenger flow data acquisition module and the environmental perception module. The mixed-integer nonlinear programming controller generates the overall parameters of the terminal equipment based on the environmental prediction values ​​and configures the execution parameters of the terminal equipment in each area based on the actual detection data from the environmental perception module, so as to realize the regional control of the environment in the subway station.

[0009] The energy supply module is electrically connected to the pedestrian flow data acquisition module, environmental sensing module, prediction-control integrated module, and terminal equipment.

[0010] In one specific implementation, the body temperature detector is an infrared thermal imager, and the air quality detector includes a CO2 concentration detector, a PM2.5 detector, a hygrometer, and an oxygen content detector.

[0011] In one specific implementation, a data fusion processor is also included, which is connected to the pedestrian flow data acquisition module and the environmental perception module via a signal and is electrically connected to the energy supply module, for integrating multi-source detection data.

[0012] In one specific implementation, the terminal equipment includes an air curtain machine installed at the entrance of the subway station concourse, a central air conditioning system installed inside the subway station, and a fresh air system installed inside the subway station.

[0013] In one specific implementation, the timing prediction unit further includes:

[0014] The data preprocessing submodule, connected to the data fusion processor, is used to preprocess multi-source detection data.

[0015] The prediction module, connected to the data preprocessing submodule, has a built-in neural network-based artificial intelligence prediction model for generating environmental prediction values.

[0016] The output submodule, connected to the prediction module, is used to transmit environmental predictions to the mixed-integer nonlinear programming controller.

[0017] In one specific implementation, the mixed-integer nonlinear programming controller further includes:

[0018] The rolling optimization submodule, connected to the output submodule, is used to periodically generate the overall parameters of the terminal device.

[0019] The constraint management submodule, connected to the rolling optimization submodule, is used to limit the start-up and shutdown frequency of the air curtain machine, central air conditioning and fresh air system, and to set the temperature control range of the central air conditioning to 24±1.5℃.

[0020] The zone control module has its input end connected to the rolling optimization submodule and its output end connected to the control end of the central air conditioning and fresh air system.

[0021] In one specific implementation, the energy supply module is a power supply box connected to the power distribution network.

[0022] In one specific implementation, the fresh air system also includes a season selection control module for selecting its operating mode according to different seasons.

[0023] This invention has at least the following beneficial effects: the system accurately predicts environmental data in advance through a prediction-control integrated module constructed by a time-series prediction unit and a mixed integer nonlinear programming controller, and configures the execution parameters of the terminal equipment in each area according to the actual detection data of the environmental sensing module, so as to realize the regional control of the environment in the subway station, thereby greatly improving the energy-saving effect of the system. Attached Figure Description

[0024] Figure 1 This is a system structure diagram of an embodiment of the present utility model.

[0025] Figure 2 This is a simplified diagram of the longitudinal section structure of the subway station.

[0026] Figure 3 This is a 3D view of the subway station platform level.

[0027] Figure labels: 1. Pedestrian flow data acquisition module; 2. Environmental perception module; 21. Data fusion processor; 3. Terminal equipment; 31. Air curtain machine; 32. Central air conditioning; 33. Fresh air system; 4. Predictive-control integrated module; 41. Time series prediction unit; 411. Data preprocessing submodule; 412. Prediction module; 414. Output submodule; 42. Mixed integer nonlinear programming controller; 421. Rolling optimization submodule; 422. Constraint management submodule; 423. Zoning control module; 5. Energy supply module; 6. Turnstile a; 7. Security checkpoint b; Hall elevator c; Platform d. Detailed Implementation

[0028] Please see Figures 1-3 The present invention provides an intelligent control system for environmental zoning in a subway station, comprising: a passenger flow data acquisition module 1, an environmental sensing module 2, a terminal device 3, a prediction-control integrated module 4, and an energy supply module 5.

[0029] The passenger flow data acquisition module 1 includes turnstile counters installed inside the subway station, and the environmental sensing module 2 includes body temperature detectors, air quality detectors, and temperature sensors installed inside and outside the subway station in various areas of the subway station. These are used to collect real-time passenger flow data, environmental data, and temperature difference data between the inside and outside of the subway station. The body temperature detectors are infrared thermal imagers, and the air quality detectors include CO2 concentration detectors, PM2.5 detectors, hygrometers, and oxygen content detectors.

[0030] The system also includes a data fusion processor 21, which is connected to the pedestrian flow data acquisition module 1 and the environmental perception module 2 via a signal to integrate the aforementioned multi-source detection data. The data fusion processor 21 is implemented using existing technology.

[0031] Terminal equipment 3 includes an air curtain machine 31 installed at the entrance of the subway station concourse, a central air conditioning system 32 installed inside the subway station, and a fresh air system 33 installed inside the subway station. The air curtain machine 31 discharges air downwards, forming an invisible air curtain to block the airflow between the inside and outside of the subway station, which can effectively reduce the heat exchange between the inside and outside of the subway station. The central air conditioning system 32 and the fresh air system 33 are equipped with terminal fans in various areas of the subway station, which can realize the individual control of the environment in each area of ​​the subway station.

[0032] The predictive-control integrated module 4 includes a timing prediction unit 41 and a mixed-integer nonlinear programming controller 42.

[0033] The time-series prediction unit 41 further includes a data preprocessing submodule 411, a prediction module 412, and an output submodule 414. The data preprocessing submodule 411 is connected to the data fusion processor 21 and is used to preprocess the integrated multi-source detection data. The prediction module 412 is connected to the data preprocessing submodule 411 and has a built-in artificial intelligence prediction model based on neural networks in the prior art, which is used to generate environmental prediction values. The output submodule 414 is connected to the prediction module 412 and is used to transmit the environmental prediction values ​​to the mixed integer nonlinear programming controller 42.

[0034] The mixed-integer nonlinear programming controller 42 further includes a rolling optimization submodule 421, a constraint management submodule 422, and a zone control module 423. The rolling optimization submodule 421 is connected to the output submodule 414. The rolling optimization submodule 421 is implemented using existing technology and is used to periodically generate the overall parameters of the terminal equipment. The constraint management submodule 422 is connected to the rolling optimization submodule 421. The constraint management submodule 422 is implemented using existing technology and is used to limit the start-up and shutdown frequency of the air curtain machine 31, the central air conditioning 32, and the fresh air system 33, and to set the temperature control range of the central air conditioning 32 to 24±1.5℃. The input end of the zone control module 423 is connected to the rolling optimization submodule 421, and the output end is connected to the control end of the central air conditioning 32 and the fresh air system 33. The working principle of the zone control module 423 is based on existing known technology. It is used to generate the overall parameters of the terminal equipment 3 according to the environmental prediction value, and to configure the execution parameters of the terminal equipment 3 in each area according to the actual detection data of the environmental sensing module 2, thereby realizing zoned control of the environment in the subway station.

[0035] The energy supply module 5 is a power supply box connected to the power distribution network. The power supply box is electrically connected to the pedestrian flow data acquisition module 1, the environmental perception module 2, the data fusion processor 21, the prediction-control integrated module 4, and the terminal equipment 3, and is used to supply power to the entire system.

[0036] The working principle of this utility model is as follows: the gate counter detects the number of people entering the subway station in real time; the body temperature detector detects the average human body temperature in each area of ​​the station hall and platform in real time; the air quality detector detects the CO2 concentration, PM2.5 value, humidity value and oxygen content value in each area of ​​the station hall and platform in real time; the temperature sensor 14 installed in the subway station detects the temperature value in each area of ​​the station hall and platform in real time; the temperature sensor 14 installed outside the subway station detects the temperature value outside the subway station in real time. The above detection data are integrated by the data fusion processor 21 and input into the prediction-control integrated module 4. The data preprocessing submodule 411 of the time-series prediction unit 41 preprocesses the fused data. The prediction module 412 generates the environmental prediction value of the subway station in the next 2 hours through the built-in neural network-based artificial intelligence prediction model. The output submodule 414 transmits the generated environmental prediction value to the mixed integer nonlinear programming controller 42. The mixed-integer nonlinear programming controller 42 generates the overall parameters of all air curtain machines 31, the central air conditioning system 32, and the fresh air system 33 every 15 minutes, ensuring that the start-up and shutdown frequencies of the air curtain machines 31, the central air conditioning system 32, and the fresh air system 33 are within a preset range, while ensuring that the temperature control range of the central air conditioning system 32 is within 24±1.5℃. The zone control module 423 receives the overall parameters adjusted by the mixed-integer nonlinear programming controller 42, and configures the execution parameters of the terminal fans of the central air conditioning system 32 and the fresh air system 33 in these areas based on the actual detection data of the body temperature detector, air quality detector, and temperature sensors installed in the subway station in the environmental perception module 2 at the turnstile a, security checkpoint b, elevator c in the station hall, and platform d areas respectively. Based on the actual detection data of the temperature sensors installed inside and outside the subway station in the environmental perception module 2, it configures the execution parameters of the air curtain machines 31 at each entrance of the station hall. For example, the overall parameters of the central air conditioning 32 optimized by the mixed integer nonlinear programming controller 42 are a cooling power of 18kW. The zone control module 423 receives this overall parameter and, based on the actual detection data from the body temperature detector, air quality detector, and temperature sensors installed in the environmental sensing module 2 at the turnstile a, security checkpoint b, station hall elevator c, and platform d areas respectively, configures the cooling power of the terminal fan of the central air conditioning 32 to 6kW in the turnstile a area, 4kW in the security checkpoint b area, 4kW in the station hall elevator c area, and 4kW in the platform d area, thereby achieving zoned temperature control.For example, the overall parameters of the air curtain machine 31 optimized by the mixed integer nonlinear programming controller 42 are an output power of 10kW. The zone control module 423 receives this overall parameter and, based on the actual detection data of the temperature sensors installed inside and outside the station hall of the subway station in the environmental perception module 2, configures the output power of the air curtain machine 31 at entrance A to be 3kW, the output power of the air curtain machine 31 at entrance B to be 2.5kW, the output power of the air curtain machine 31 at entrance C to be 2.5kW, and the output power of the air curtain machine 31 at entrance D to be 2kW.

[0037] The fresh air system 33 also includes a seasonal selection control module, which is used to select its working mode according to different seasons. For example, due to the large temperature fluctuations and significant day-night temperature differences in spring and autumn, as well as the abundance of pollen and dust and the complex external environment in spring, it is necessary to enhance air filtration and ventilation while meeting comfort requirements. Natural cold sources can be fully utilized, so the proportion of fresh air volume is relatively high. In the spring working mode, the proportion of fresh air volume in the fresh air system 33 is 55%-70%. At the same time, during the "return to spring" weather in spring, the fresh air / air conditioning system can maintain comfortable indoor humidity through intelligent control: when the humidity sensor detects that the indoor humidity exceeds the set target range, such as 50%-60%RH, the system automatically switches to dehumidification mode, using a heat exchanger to condense water molecules in the humid air into water droplets and discharge them, thereby ensuring that the indoor humidity is always maintained within a comfortable range. In autumn, the air is relatively stable. While ensuring air quality and comfort, the fresh air volume can be slightly lower than in spring. In autumn operating mode, the fresh air volume of the fresh air system 33 accounts for 50%-65%. During spring and autumn operating modes, the filters of the fresh air system 33 are also activated. Additionally, due to the dry autumn air, the humidifier of the fresh air system 33 can be activated in autumn operating mode to maintain the humidity inside the station at 40%-50%. In summer, due to the higher oxygen demand of passengers, the minimum fresh air requirement must be met while also controlling the cooling load. The fresh air volume of the fresh air system 33 accounts for 20%-30%, and the air intake function of the underground air inlet is activated. In winter, due to the low temperature and relatively low metabolic rate of passengers, the fresh air volume of the fresh air system 33 accounts for 50%-60%, strengthening ventilation and humidity control to prevent excessive cold air from entering the station. The fresh air system is linked to the heating system, preheating the fresh air through a heat exchanger. The heat exchanger's thermal efficiency can reach 70%-80%, effectively increasing the fresh air temperature and reducing the energy consumption of the heating system.

[0038] The above description, in conjunction with specific preferred embodiments, provides a further detailed explanation of the present invention. It should not be construed that the specific implementation of the present invention is limited to these descriptions. For those skilled in the art, various simple deductions and substitutions can be made without departing from the concept of the present invention, and all such modifications and substitutions should be considered within the protection scope of the present invention.

Claims

1. A subway station environment partitioning intelligent control system, characterized in that, The utility model relates to a subway station environment control system, including: Passenger flow data acquisition module (1), environmental perception module (2), terminal equipment (3), forecast-control integrated module (4) and energy supply module (5); The passenger flow data acquisition module (1) includes the gate counter that sets up in the subway station; The environmental perception module (2) includes the temperature detector that sets up in each area in the subway station, air quality detector and temperature sensor that sets up in the inside and outside of subway station; The forecast-control integrated module (4) includes time series prediction unit (41) and mixed integer nonlinear programming controller (42), time series prediction unit (41) generates environment predicted value according to the detection data of passenger flow data acquisition module (1) and environmental perception module (2), mixed integer nonlinear programming controller (42) generates the overall parameter of terminal equipment (3) according to the environment predicted value, and the actual detection data of environmental perception module (2) is configured to execute parameter in each area of terminal equipment (3), to realize the control of the environment in subway station in regional control; The energy supply module (5) is electrically connected with the passenger flow data acquisition module (1), environmental perception module (2), forecast-control integrated module (4) and terminal equipment (3).

2. The metro station environment partitioning intelligent control system according to claim 1, characterized in that, The temperature detector is infrared thermal imager, and the air quality detector includes CO2 concentration detector, PM2.5 detector, hygrometer and oxygen content detector.

3. The underground station environment partitioning intelligent control system of claim 1, wherein, Further including data fusion processor (21), which is signal connected with the passenger flow data acquisition module (1) and the environmental perception module (2), and is electrically connected with the energy supply module (5), for integrating multi-source detection data.

4. The underground station environment partitioning intelligent control system of claim 1, wherein, The terminal equipment (3) includes the air curtain machine (31) that sets up at the entrance of the station hall of subway station, the central air conditioning (32) that sets up in subway station and fresh air system (33) that sets up in subway station.

5. The underground station environment partitioning intelligent control system according to claim 3, characterized in that, The time series prediction unit (41) further includes: Data preprocessing submodule (411) is connected with the data fusion processor (21), and is used for pre-processing the multi-source detection data; Prediction module (412) is connected with the data preprocessing submodule (411), and the prediction module (412) is built-in artificial intelligence prediction model based on neural network, and is used for generating environment predicted value; Output submodule (414) is connected with the prediction module (412), and is used for transmitting environment predicted value to mixed integer nonlinear programming controller (42).

6. The underground station environment partitioning intelligent control system of claim 4, wherein, The mixed integer nonlinear programming controller (42) further includes: Rolling optimization submodule (421) is connected with output submodule (414), and is used for periodically generating the overall parameter of terminal equipment; Constraint management submodule (422) is connected with the rolling optimization submodule (421), and is used for limiting the start-stop frequency of air curtain machine (31), central air conditioning (32) and fresh air system (33), and setting the temperature control interval of central air conditioning (32) to 24±1.5 DEG C; A partition control module (423) is connected with the rolling optimization sub-module (421) at the input end and connected with the control end of the central air conditioner (32) and the fresh air system (33) at the output end.

7. The underground station environment partitioning intelligent control system of claim 1, wherein, The energy supply module (5) is a power supply box connected with a power distribution network.

8. The underground station environment partitioning intelligent control system of claim 4, wherein, The fresh air system (33) further comprises a seasonal selection control module for selecting a working mode according to different seasons.

Images